#!/bin/sh -x
set -e
-test -L xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
-rm xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
+test -L old/xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
+rm old/xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
(find -depth -type d -print | xargs -r rmdir 2>/dev/null) || true
exit 0
#!/bin/sh -x
set -e
-mkdir -p xenolinux-2.4.16-sparse
-mkdir -p xenolinux-2.4.16-sparse/include
-mkdir -p xenolinux-2.4.16-sparse/include/asm-xeno
-ln -s ../../../xen-2.4.16/include/hypervisor-ifs xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
+mkdir -p old
+mkdir -p old/xenolinux-2.4.16-sparse
+mkdir -p old/xenolinux-2.4.16-sparse/include
+mkdir -p old/xenolinux-2.4.16-sparse/include/asm-xeno
+ln -s ../../../xen-2.4.16/include/hypervisor-ifs old/xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
(find -depth -type d -print | xargs -r rmdir 2>/dev/null) || true
exit 0
3ddb6b0bKlMz_dz-M59a1mkUa1lASw BitKeeper/etc/config
3ddb6b0buTaC5zg1_a8FoAR9FWi_mw BitKeeper/etc/ignore
3ddb79c9_hgSp-gsQm8HqWM_9W3B_A BitKeeper/etc/logging_ok
+3ddb79bbYMXGmQTsr5BeGS_RuZ5f_w old/xenolinux-2.4.16-sparse/Makefile
+3ddb79b7e0ssyz3Q1GoqjDds-x1PLQ old/xenolinux-2.4.16-sparse/arch/xeno/Makefile
+3ddb79b7_rLvYZU3tOY6Wwuw_Sg3_w old/xenolinux-2.4.16-sparse/arch/xeno/boot/Makefile
+3ddb79b8L4xnwrcvWk6nAbgKVbNkSA old/xenolinux-2.4.16-sparse/arch/xeno/config.in
+3ddb79b7v_Be34as7_mlzFlw65hOjQ old/xenolinux-2.4.16-sparse/arch/xeno/defconfig
+3ddb79b7KUvtx0knQJoRaBDZQeNidg old/xenolinux-2.4.16-sparse/arch/xeno/drivers/block/Makefile
+3e4a8cb7JECr--r1ipnrkd7NKdbUqQ old/xenolinux-2.4.16-sparse/arch/xeno/drivers/block/xl_block.c
+3e4a8cb7SLWsLTXQjv7ng6-3hL4pCA old/xenolinux-2.4.16-sparse/arch/xeno/drivers/block/xl_block_test.c
+3ddb79b7LLVJBGynxHSOh9A9l97sug old/xenolinux-2.4.16-sparse/arch/xeno/drivers/console/Makefile
+3ddb79b7UG2QiRAU-Wvc1Y_BLigu1Q old/xenolinux-2.4.16-sparse/arch/xeno/drivers/console/console.c
+3ddb79b75eo4PRXkT6Th9popt_SJhg old/xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/Makefile
+3e4a8cb79dT0F4q5T4GEqMj4CtAquQ old/xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_block.c
+3ddb79b7Xyaoep6U0kLvx6Kx7OauDw old/xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_core.c
+3df9ce13K7qSLBtHV-01QHPW62649Q old/xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_memory.c
+3ddb79b7PulSkF9m3c7K5MkxHRf4hA old/xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_ops.h
+3ddba759XOjcl_OF-52dOYq7sgMykQ old/xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/vfr.c
+3ddb79b7s7yYBioHidSkIoHtQxYmOw old/xenolinux-2.4.16-sparse/arch/xeno/drivers/network/Makefile
+3ddb79b7CpLL98ScdpbKkVBktlbCtQ old/xenolinux-2.4.16-sparse/arch/xeno/drivers/network/network.c
+3ddb79b7hqi9krq6h98lnpONHGzvEA old/xenolinux-2.4.16-sparse/arch/xeno/kernel/Makefile
+3ddb79b7eyEv5bsN8EQkjIG0y11Q1A old/xenolinux-2.4.16-sparse/arch/xeno/kernel/entry.S
+3ddb79b70XAg9bJwp0-DWHe0LtzlBw old/xenolinux-2.4.16-sparse/arch/xeno/kernel/head.S
+3ddb79b7dDsKjU22VxQ-C5BMFaMUmw old/xenolinux-2.4.16-sparse/arch/xeno/kernel/hypervisor.c
+3ddb79b7xzwEc8-lo1vu3BxB-gBURQ old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i386_ksyms.c
+3ddb79b7i7pfPEcy_zjDfW9JHD305g old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i387.c
+3ddb79b7Ti2i5ztQzM-w67zN-cJD8A old/xenolinux-2.4.16-sparse/arch/xeno/kernel/init_task.c
+3ddb79b7MEQGMZrsF94atNJZ4-OGzA old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ioport.c
+3ddb79b7DOz-Mz5jsjRd5W8jN0XbPw old/xenolinux-2.4.16-sparse/arch/xeno/kernel/irq.c
+3ddb79b7bOAPk_YAUUsruhVGO2GOOg old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ldt.c
+3ddb79b7qf2WK6vMKcmOLIeKN5GSjg old/xenolinux-2.4.16-sparse/arch/xeno/kernel/process.c
+3ddb79b7HdaBR7yk_u51auihbr31aQ old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ptrace.c
+3ddb79b7yJunvnrgWD2VTy6yot0PMg old/xenolinux-2.4.16-sparse/arch/xeno/kernel/semaphore.c
+3ddb79b7BIitpVygiksiMBQYvh5Z2A old/xenolinux-2.4.16-sparse/arch/xeno/kernel/setup.c
+3ddb79b7DTevmwhNla67jZxjBSIKFg old/xenolinux-2.4.16-sparse/arch/xeno/kernel/signal.c
+3ddb79b76mCf-gZPR4KLjL8ktZ37GA old/xenolinux-2.4.16-sparse/arch/xeno/kernel/sys_i386.c
+3ddb79b7xDsEKErRFeqcSm6eRrTEIg old/xenolinux-2.4.16-sparse/arch/xeno/kernel/time.c
+3ddb79b7V4dv_KAQu4Msa2Ebhd0aKw old/xenolinux-2.4.16-sparse/arch/xeno/kernel/traps.c
+3ddb79b8oUnwncDaZuRWF3-n3jPsIA old/xenolinux-2.4.16-sparse/arch/xeno/lib/Makefile
+3ddb79b8BMxi8qW3_NT44SSd1uMD3Q old/xenolinux-2.4.16-sparse/arch/xeno/lib/checksum.S
+3ddb79b8WcWel2g9zU9pBJb-yA8jBw old/xenolinux-2.4.16-sparse/arch/xeno/lib/dec_and_lock.c
+3ddb79b8oxeiaIW6Au95OM0GlsMrMw old/xenolinux-2.4.16-sparse/arch/xeno/lib/delay.c
+3ddb79b8XPasnRhvK-_6xYksf3S6qA old/xenolinux-2.4.16-sparse/arch/xeno/lib/getuser.S
+3ddb79b8HFLUh8mwcl4X44ta-ny1KA old/xenolinux-2.4.16-sparse/arch/xeno/lib/iodebug.c
+3ddb79b879qeoLlarHXvNIDEva6ssA old/xenolinux-2.4.16-sparse/arch/xeno/lib/memcpy.c
+3ddb79b869CY_yr4HymV6k98pfpMgg old/xenolinux-2.4.16-sparse/arch/xeno/lib/mmx.c
+3ddb79b8S77yf1--Qa4C0ZYmqKXCww old/xenolinux-2.4.16-sparse/arch/xeno/lib/old-checksum.c
+3ddb79b8ffZ79cU2ZzfA2ekeo6pqeg old/xenolinux-2.4.16-sparse/arch/xeno/lib/strstr.c
+3ddb79b82kQ5oIXpxq3TUmlgxsLzLg old/xenolinux-2.4.16-sparse/arch/xeno/lib/usercopy.c
+3ddb79b8qdD_svLCCAja_oP2w4Tn8Q old/xenolinux-2.4.16-sparse/arch/xeno/mm/Makefile
+3ddb79b8ukY8dsPYmR8eNk-aCzFPsQ old/xenolinux-2.4.16-sparse/arch/xeno/mm/extable.c
+3ddb79b856Zta9b3s0bgUCGbG1blvQ old/xenolinux-2.4.16-sparse/arch/xeno/mm/fault.c
+3df9ce13dZ6UGDjZbUeZfyH4Hy6aCA old/xenolinux-2.4.16-sparse/arch/xeno/mm/get_unmapped_area.c
+3ddb79b85fpsKT8A9WYnuJg03b715g old/xenolinux-2.4.16-sparse/arch/xeno/mm/hypervisor.c
+3ddb79b83Zj7Xn2QVhU4HeMuAC9FjA old/xenolinux-2.4.16-sparse/arch/xeno/mm/init.c
+3df9ce13TRWIv0Mawm15zESP7jcT7A old/xenolinux-2.4.16-sparse/arch/xeno/mm/mmu_context.c
+3ddb79b7aKdTkbr3u6aze8tVwGh_TQ old/xenolinux-2.4.16-sparse/arch/xeno/vmlinux.lds
+3e4a8cb7lpFFwT1Iu9zXWc8Ew4klFA old/xenolinux-2.4.16-sparse/drivers/block/Config.in
+3ddb79bbx682YH6vR2zbVOXwg73ULg old/xenolinux-2.4.16-sparse/drivers/block/ll_rw_blk.c
+3ddb79bcJfHdwrPsjqgI33_OsGdVCg old/xenolinux-2.4.16-sparse/drivers/block/rd.c
+3ddb79bcpVu-IbnqwQqpRqsEbLpsuw old/xenolinux-2.4.16-sparse/drivers/char/tty_io.c
+3e15d5273gfR2fbcYe05kqBSAvCX_w old/xenolinux-2.4.16-sparse/fs/exec.c
+3ddb79b8VFtfWSCrXKPN2K21zd_vtw old/xenolinux-2.4.16-sparse/include/asm-xeno/a.out.h
+3ddb79b8Zzi13p3OAPV25QgiC3THAQ old/xenolinux-2.4.16-sparse/include/asm-xeno/apic.h
+3ddb79baZDlsdV_m6C5CXnWMl15p1g old/xenolinux-2.4.16-sparse/include/asm-xeno/apicdef.h
+3ddb79baZM88u4CnriVA8ZXBdnMNvg old/xenolinux-2.4.16-sparse/include/asm-xeno/atomic.h
+3ddb79baYHyZsDCiXiq8Y8_XxHE-jQ old/xenolinux-2.4.16-sparse/include/asm-xeno/bitops.h
+3ddb79b8vFGtGb6pg3GZFXSiwOZfcg old/xenolinux-2.4.16-sparse/include/asm-xeno/boot.h
+3ddb79baW8tf6PiBQUF50QQM5nY9sw old/xenolinux-2.4.16-sparse/include/asm-xeno/bugs.h
+3ddb79b80msOlzTZRoVudYdemzgOlA old/xenolinux-2.4.16-sparse/include/asm-xeno/byteorder.h
+3ddb79b8brNSUEujnq8f_zr8kA-cUg old/xenolinux-2.4.16-sparse/include/asm-xeno/cache.h
+3ddb79bayhr6C6prVhAYlFRChhf3wg old/xenolinux-2.4.16-sparse/include/asm-xeno/checksum.h
+3ddb79b8RNUaDbpPjdVVwKAsbiTBKQ old/xenolinux-2.4.16-sparse/include/asm-xeno/cpufeature.h
+3ddb79b8pJe4aNsUKkfHEoBT9Y-UMA old/xenolinux-2.4.16-sparse/include/asm-xeno/current.h
+3ddb79b8KL7icUfxKRoWDIkHkLQ1kQ old/xenolinux-2.4.16-sparse/include/asm-xeno/debugreg.h
+3ddb79baDUP_cRdFgqaH0rXUvMxx4A old/xenolinux-2.4.16-sparse/include/asm-xeno/delay.h
+3ddb79b89CgBTFsS3joEJ1ZniSHEgA old/xenolinux-2.4.16-sparse/include/asm-xeno/desc.h
+3ddb79ba6xyT4mJOYSp1Fg2l0ta93A old/xenolinux-2.4.16-sparse/include/asm-xeno/div64.h
+3ddb79b80Z4ZUIqbD1Xu_t4OCuEHeQ old/xenolinux-2.4.16-sparse/include/asm-xeno/dma.h
+3ddb79bac26NkKcPIEsfxETc5Snyag old/xenolinux-2.4.16-sparse/include/asm-xeno/elf.h
+3ddb79ba722pCJ_g_xI8ebsE31IK-Q old/xenolinux-2.4.16-sparse/include/asm-xeno/errno.h
+3ddb79b8vIpUpgaSNEneFkg5hYSvNg old/xenolinux-2.4.16-sparse/include/asm-xeno/fcntl.h
+3e53dbfb9mmyM-y5NuBBTDJvQkDzjA old/xenolinux-2.4.16-sparse/include/asm-xeno/fixmap.h
+3ddb79b8780YvqvK1g5KPIWzQ6P15w old/xenolinux-2.4.16-sparse/include/asm-xeno/floppy.h
+3ddb79bas-nFywnmilbUeT34PEAA0g old/xenolinux-2.4.16-sparse/include/asm-xeno/hardirq.h
+3ddb79batzR40ZFY9dvgs5f1aM9I6g old/xenolinux-2.4.16-sparse/include/asm-xeno/hdreg.h
+3ddb79b90xBgbeYgCcImS2ZxJakxBA old/xenolinux-2.4.16-sparse/include/asm-xeno/highmem.h
+3ddb79baXLZV3dUKQI2gIYpAy67RuA old/xenolinux-2.4.16-sparse/include/asm-xeno/hw_irq.h
+3e00b957iYsdTI1x6THRwMoWSPIW2Q old/xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
+3ddb79bapQ9Z9ewa5O1pqAVaNBTazg old/xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor.h
+3ddb79baL-pjPI8hg5xjPgd4__SlOA old/xenolinux-2.4.16-sparse/include/asm-xeno/i387.h
+3ddb79ba66TwvG7HpbBo04fRhmj3KQ old/xenolinux-2.4.16-sparse/include/asm-xeno/ide.h
+3ddb79bahFfCuRcmd9kBYA-CuGtCSg old/xenolinux-2.4.16-sparse/include/asm-xeno/init.h
+3ddb79ba3wnwflaNW6QheYvxoj5S8Q old/xenolinux-2.4.16-sparse/include/asm-xeno/io.h
+3ddb79ba1MhHpElCXFlijej2zWVk4g old/xenolinux-2.4.16-sparse/include/asm-xeno/io_apic.h
+3ddb79baiyfcZN9rJwhq0UeFjI6GkQ old/xenolinux-2.4.16-sparse/include/asm-xeno/ioctl.h
+3ddb79badReKYSok3yHShb4jg0vA-A old/xenolinux-2.4.16-sparse/include/asm-xeno/ioctls.h
+3ddb79b9iuIxteTXg8_myIsrWF5uxg old/xenolinux-2.4.16-sparse/include/asm-xeno/ipc.h
+3ddb79baw5Dxo78880UMSanDV70WdA old/xenolinux-2.4.16-sparse/include/asm-xeno/ipcbuf.h
+3ddb79ban9FUBuEaznRZvPfry3xnHQ old/xenolinux-2.4.16-sparse/include/asm-xeno/irq.h
+3ddb79banJ5r-mqE7LZ8nPGTADaGBA old/xenolinux-2.4.16-sparse/include/asm-xeno/kdb.h
+3ddb79baoaoHGTW0oiBXFPUg4KWydw old/xenolinux-2.4.16-sparse/include/asm-xeno/kdbprivate.h
+3ddb79bam2K6c7tS2HX6jis2Bqx71w old/xenolinux-2.4.16-sparse/include/asm-xeno/keyboard.h
+3ddb79baQ8gGrZm2Jlo3I1ntD0H5HA old/xenolinux-2.4.16-sparse/include/asm-xeno/kmap_types.h
+3ddb79b9MeQEYrafy-Mx9OoeVFM_uw old/xenolinux-2.4.16-sparse/include/asm-xeno/ldt.h
+3ddb79baAsy5W-cJ9ML_w9chqqUh4A old/xenolinux-2.4.16-sparse/include/asm-xeno/linux_logo.h
+3ddb79b9uhsumPVE0wGgarfIkYDSFA old/xenolinux-2.4.16-sparse/include/asm-xeno/locks.h
+3ddb79b954ISbF9e68hB0WTulCJRgg old/xenolinux-2.4.16-sparse/include/asm-xeno/math_emu.h
+3ddb79b9EZDlC6RGn_y0OYr0nyQWlw old/xenolinux-2.4.16-sparse/include/asm-xeno/mc146818rtc.h
+3ddb79b9M6pTF4maDgh8TYbg_HHUbw old/xenolinux-2.4.16-sparse/include/asm-xeno/mca_dma.h
+3ddb79baA7dlps8FkicOUEXKEQuQsA old/xenolinux-2.4.16-sparse/include/asm-xeno/mman.h
+3ddb79baKfF36-eRvkxnEvMRQRai-w old/xenolinux-2.4.16-sparse/include/asm-xeno/mmu.h
+3ddb79baQyKbT5U4EmZNePY9Txp-tA old/xenolinux-2.4.16-sparse/include/asm-xeno/mmu_context.h
+3ddb79bberC3Ghs4vy-06Pu-LSiWtw old/xenolinux-2.4.16-sparse/include/asm-xeno/mmx.h
+3ddb79bbsJLF10xQcKDoV8f_7gcOXg old/xenolinux-2.4.16-sparse/include/asm-xeno/module.h
+3ddb79bbY5RffJ8_F1oC4VI7q3Eejg old/xenolinux-2.4.16-sparse/include/asm-xeno/mpspec.h
+3ddb79b90vB4Vzzy_wL6SYXQMy9N9Q old/xenolinux-2.4.16-sparse/include/asm-xeno/msgbuf.h
+3ddb79bbZ5a_vTk0xcgOHuPokaqwMw old/xenolinux-2.4.16-sparse/include/asm-xeno/msr.h
+3ddb79b9y1xAKaPiBd79MBcCopNNYw old/xenolinux-2.4.16-sparse/include/asm-xeno/mtrr.h
+3ddb79b90hX0QBJlWQN_VsHtX5Ijkw old/xenolinux-2.4.16-sparse/include/asm-xeno/namei.h
+3ddb79bbG2p9MNq7tuISz8md1Oj2lg old/xenolinux-2.4.16-sparse/include/asm-xeno/page.h
+3ddb79bb_iUa2piFSwaB8YPw-rB5SQ old/xenolinux-2.4.16-sparse/include/asm-xeno/param.h
+3ddb79b9Y8UU0S9AoDznoqqcYxg9-A old/xenolinux-2.4.16-sparse/include/asm-xeno/parport.h
+3ddb79b9K9_edWxBHS7TdCpyDmfp6g old/xenolinux-2.4.16-sparse/include/asm-xeno/pgalloc.h
+3ddb79bahaS_P3UYp9VEU6kHxXbajA old/xenolinux-2.4.16-sparse/include/asm-xeno/pgtable-2level.h
+3ddb79b9MjXUB_rk29GJgaNY24feCw old/xenolinux-2.4.16-sparse/include/asm-xeno/pgtable-3level.h
+3ddb79bbPF2ENpNHBru8K3hyYVPmkQ old/xenolinux-2.4.16-sparse/include/asm-xeno/pgtable.h
+3ddb79b9t9xKrOf8aP3X5jEit9tj-w old/xenolinux-2.4.16-sparse/include/asm-xeno/poll.h
+3ddb79b9xHtTDWFaI9ncAtxyUth0Yg old/xenolinux-2.4.16-sparse/include/asm-xeno/posix_types.h
+3ddb79b9VwZ9YsSpA7CkJmYXVadrCA old/xenolinux-2.4.16-sparse/include/asm-xeno/processor.h
+3ddb79bbKaOkHrGG9j05AGlii-voaQ old/xenolinux-2.4.16-sparse/include/asm-xeno/ptrace.h
+3ddb79bbVpJCVTXmc2yNf1rsC00YEg old/xenolinux-2.4.16-sparse/include/asm-xeno/resource.h
+3ddb79bbtU0Kh27NbNpqKAIhshJvXQ old/xenolinux-2.4.16-sparse/include/asm-xeno/rwlock.h
+3ddb79b97LhdmW6hYmybQOPDkK6plg old/xenolinux-2.4.16-sparse/include/asm-xeno/rwsem.h
+3ddb79bbgRzM1NoXYbLoOCbZt8s5NA old/xenolinux-2.4.16-sparse/include/asm-xeno/scatterlist.h
+3ddb79b9xCi3F80Z6xxx6nzkCAo8vQ old/xenolinux-2.4.16-sparse/include/asm-xeno/segment.h
+3ddb79b9WxySbCKDoMgTgPtn1G3BFw old/xenolinux-2.4.16-sparse/include/asm-xeno/semaphore.h
+3ddb79b9gNK3dtgXONloSBaNgZPjAg old/xenolinux-2.4.16-sparse/include/asm-xeno/sembuf.h
+3ddb79bb2UTDgfwju2J3weDXemw3LA old/xenolinux-2.4.16-sparse/include/asm-xeno/serial.h
+3ddb79bbAPFyA_n4dNVCRoee8obOKA old/xenolinux-2.4.16-sparse/include/asm-xeno/setup.h
+3ddb79b9XTOB5DwWBGzPLLR4rNEkDQ old/xenolinux-2.4.16-sparse/include/asm-xeno/shmbuf.h
+3ddb79b9-_jDlAj3qVZe4opi3zectQ old/xenolinux-2.4.16-sparse/include/asm-xeno/shmparam.h
+3ddb79b9AW75ErwlTRX4McxO15sEaQ old/xenolinux-2.4.16-sparse/include/asm-xeno/sigcontext.h
+3ddb79b9NBJW-KAI3mgveUCr7sIOwA old/xenolinux-2.4.16-sparse/include/asm-xeno/siginfo.h
+3ddb79bbj0i8tUVNMKtZVrLJqv3Nsw old/xenolinux-2.4.16-sparse/include/asm-xeno/signal.h
+3ddb79bbfAmpotdy-No2dwGez2fnIg old/xenolinux-2.4.16-sparse/include/asm-xeno/smp.h
+3ddb79b9pDERXiqSumFWMTFJ1X9xIw old/xenolinux-2.4.16-sparse/include/asm-xeno/smplock.h
+3ddb79bbuCOIWTlWEHgOTexEBbdDow old/xenolinux-2.4.16-sparse/include/asm-xeno/socket.h
+3ddb79b9ExeUznVBlSn1e2nvOCrJ4A old/xenolinux-2.4.16-sparse/include/asm-xeno/sockios.h
+3ddb79b9kL3xvucBb-Gmg4_vo-99vw old/xenolinux-2.4.16-sparse/include/asm-xeno/softirq.h
+3ddb79b9rJ8AfSzGzA0arI8mazYLlQ old/xenolinux-2.4.16-sparse/include/asm-xeno/spinlock.h
+3ddb79bbXaA_zUHNPkAKRNz1h0gIJw old/xenolinux-2.4.16-sparse/include/asm-xeno/stat.h
+3ddb79b9G004IlCplrjWgF1aXbp8dA old/xenolinux-2.4.16-sparse/include/asm-xeno/statfs.h
+3ddb79bbRsy3GlCFrQEbVMVp--xlwQ old/xenolinux-2.4.16-sparse/include/asm-xeno/string-486.h
+3ddb79bb4xug4cDph6ODLQFQIan_sg old/xenolinux-2.4.16-sparse/include/asm-xeno/string.h
+3ddb79b9JhjJtJUO3g5LmrHPkdxgKg old/xenolinux-2.4.16-sparse/include/asm-xeno/system.h
+3ddb79b9tbjCU9zSbqKbbv4m8tijlg old/xenolinux-2.4.16-sparse/include/asm-xeno/termbits.h
+3ddb79bbi0mW10tH4xX1_KHXKM_xPg old/xenolinux-2.4.16-sparse/include/asm-xeno/termios.h
+3ddb79b9JuR1VvNzlkyMlA-Dnlmy9Q old/xenolinux-2.4.16-sparse/include/asm-xeno/timex.h
+3ddb79b9Bofq-p3sCTF0ELVuf_iBYA old/xenolinux-2.4.16-sparse/include/asm-xeno/tlb.h
+3ddb79b9tpBUqS8-S6euSqyk2hFkKg old/xenolinux-2.4.16-sparse/include/asm-xeno/types.h
+3ddb79bb5bkAaEzD7pdqQZdWyA_0eQ old/xenolinux-2.4.16-sparse/include/asm-xeno/uaccess.h
+3ddb79bbiDIz1dxgFixHKyGuqRqfDQ old/xenolinux-2.4.16-sparse/include/asm-xeno/ucontext.h
+3ddb79ba_Smn-GiYtr5ZTMaZXn-AHg old/xenolinux-2.4.16-sparse/include/asm-xeno/unaligned.h
+3ddb79bb3cMSs_k2X5Oq2hOIBvmPYA old/xenolinux-2.4.16-sparse/include/asm-xeno/unistd.h
+3ddb79ba2qYtIQAT_-vCFkkZUXu_UQ old/xenolinux-2.4.16-sparse/include/asm-xeno/user.h
+3ddb79bbqhb9X9qWOz5Bv4wOzrkITg old/xenolinux-2.4.16-sparse/include/asm-xeno/vga.h
+3ddb79bbA52x94o6uwDYsbzrH2hjzA old/xenolinux-2.4.16-sparse/include/asm-xeno/xor.h
+3e4a8cb7ON8EclY3NN3YPXyMT941hA old/xenolinux-2.4.16-sparse/include/linux/blk.h
+3e4a8cb7GJrKD0z7EF0VZOhdEa01Mw old/xenolinux-2.4.16-sparse/include/linux/major.h
+3ddb79bb_7YG4U75ZmEic9YXWTW7Vw old/xenolinux-2.4.16-sparse/include/linux/sunrpc/debug.h
+3e4a8cb7j05wwb1uPZgY16s68o7qAw old/xenolinux-2.4.16-sparse/init/main.c
+3ddb79bcxkVPfWlZ1PQKvDrfArzOVw old/xenolinux-2.4.16-sparse/kernel/panic.c
+3ddb79bbP31im-mx2NbfthSeqty1Dg old/xenolinux-2.4.16-sparse/mk
+3e15d52e0_j129JPvo7xfYGndVFpwQ old/xenolinux-2.4.16-sparse/mm/memory.c
+3e15d535DLvpzTrLRUIerB69LpJD1g old/xenolinux-2.4.16-sparse/mm/mremap.c
+3e15d531m1Y1_W8ki64AFOU_ua4C4w old/xenolinux-2.4.16-sparse/mm/swapfile.c
3e4d00468-FN2VDeEHo96zxrMHK_mA tools/domain_builder/Makefile
3e4d0046SPau_y0sw2WLJz8QkqNoRA tools/domain_builder/README
3e4d0046bbdH0GsI9J_1Eb4ZQHfIiQ tools/domain_builder/dom0_defs.h
3ddb79c4TZj1wXPKQt36O72SddtBNQ xen-2.4.16/net/skbuff.c
3ddb79c4x8dvwPtzclghWAKFWpEBFA xen-2.4.16/tools/Makefile
3ddb79c4yGZ7_22QAFFwPzqP4NSHwA xen-2.4.16/tools/elf-reloc.c
-3ddb79bbYMXGmQTsr5BeGS_RuZ5f_w xenolinux-2.4.16-sparse/Makefile
-3ddb79b7e0ssyz3Q1GoqjDds-x1PLQ xenolinux-2.4.16-sparse/arch/xeno/Makefile
-3ddb79b7_rLvYZU3tOY6Wwuw_Sg3_w xenolinux-2.4.16-sparse/arch/xeno/boot/Makefile
-3ddb79b8L4xnwrcvWk6nAbgKVbNkSA xenolinux-2.4.16-sparse/arch/xeno/config.in
-3ddb79b7v_Be34as7_mlzFlw65hOjQ xenolinux-2.4.16-sparse/arch/xeno/defconfig
-3ddb79b7KUvtx0knQJoRaBDZQeNidg xenolinux-2.4.16-sparse/arch/xeno/drivers/block/Makefile
-3e4a8cb7JECr--r1ipnrkd7NKdbUqQ xenolinux-2.4.16-sparse/arch/xeno/drivers/block/xl_block.c
-3e4a8cb7SLWsLTXQjv7ng6-3hL4pCA xenolinux-2.4.16-sparse/arch/xeno/drivers/block/xl_block_test.c
-3ddb79b7LLVJBGynxHSOh9A9l97sug xenolinux-2.4.16-sparse/arch/xeno/drivers/console/Makefile
-3ddb79b7UG2QiRAU-Wvc1Y_BLigu1Q xenolinux-2.4.16-sparse/arch/xeno/drivers/console/console.c
-3ddb79b75eo4PRXkT6Th9popt_SJhg xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/Makefile
-3e4a8cb79dT0F4q5T4GEqMj4CtAquQ xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_block.c
-3ddb79b7Xyaoep6U0kLvx6Kx7OauDw xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_core.c
-3df9ce13K7qSLBtHV-01QHPW62649Q xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_memory.c
-3ddb79b7PulSkF9m3c7K5MkxHRf4hA xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/dom0_ops.h
-3ddba759XOjcl_OF-52dOYq7sgMykQ xenolinux-2.4.16-sparse/arch/xeno/drivers/dom0/vfr.c
-3ddb79b7s7yYBioHidSkIoHtQxYmOw xenolinux-2.4.16-sparse/arch/xeno/drivers/network/Makefile
-3ddb79b7CpLL98ScdpbKkVBktlbCtQ xenolinux-2.4.16-sparse/arch/xeno/drivers/network/network.c
-3ddb79b7hqi9krq6h98lnpONHGzvEA xenolinux-2.4.16-sparse/arch/xeno/kernel/Makefile
-3ddb79b7eyEv5bsN8EQkjIG0y11Q1A xenolinux-2.4.16-sparse/arch/xeno/kernel/entry.S
-3ddb79b70XAg9bJwp0-DWHe0LtzlBw xenolinux-2.4.16-sparse/arch/xeno/kernel/head.S
-3ddb79b7dDsKjU22VxQ-C5BMFaMUmw xenolinux-2.4.16-sparse/arch/xeno/kernel/hypervisor.c
-3ddb79b7xzwEc8-lo1vu3BxB-gBURQ xenolinux-2.4.16-sparse/arch/xeno/kernel/i386_ksyms.c
-3ddb79b7i7pfPEcy_zjDfW9JHD305g xenolinux-2.4.16-sparse/arch/xeno/kernel/i387.c
-3ddb79b7Ti2i5ztQzM-w67zN-cJD8A xenolinux-2.4.16-sparse/arch/xeno/kernel/init_task.c
-3ddb79b7MEQGMZrsF94atNJZ4-OGzA xenolinux-2.4.16-sparse/arch/xeno/kernel/ioport.c
-3ddb79b7DOz-Mz5jsjRd5W8jN0XbPw xenolinux-2.4.16-sparse/arch/xeno/kernel/irq.c
-3ddb79b7bOAPk_YAUUsruhVGO2GOOg xenolinux-2.4.16-sparse/arch/xeno/kernel/ldt.c
-3ddb79b7qf2WK6vMKcmOLIeKN5GSjg xenolinux-2.4.16-sparse/arch/xeno/kernel/process.c
-3ddb79b7HdaBR7yk_u51auihbr31aQ xenolinux-2.4.16-sparse/arch/xeno/kernel/ptrace.c
-3ddb79b7yJunvnrgWD2VTy6yot0PMg xenolinux-2.4.16-sparse/arch/xeno/kernel/semaphore.c
-3ddb79b7BIitpVygiksiMBQYvh5Z2A xenolinux-2.4.16-sparse/arch/xeno/kernel/setup.c
-3ddb79b7DTevmwhNla67jZxjBSIKFg xenolinux-2.4.16-sparse/arch/xeno/kernel/signal.c
-3ddb79b76mCf-gZPR4KLjL8ktZ37GA xenolinux-2.4.16-sparse/arch/xeno/kernel/sys_i386.c
-3ddb79b7xDsEKErRFeqcSm6eRrTEIg xenolinux-2.4.16-sparse/arch/xeno/kernel/time.c
-3ddb79b7V4dv_KAQu4Msa2Ebhd0aKw xenolinux-2.4.16-sparse/arch/xeno/kernel/traps.c
-3ddb79b8oUnwncDaZuRWF3-n3jPsIA xenolinux-2.4.16-sparse/arch/xeno/lib/Makefile
-3ddb79b8BMxi8qW3_NT44SSd1uMD3Q xenolinux-2.4.16-sparse/arch/xeno/lib/checksum.S
-3ddb79b8WcWel2g9zU9pBJb-yA8jBw xenolinux-2.4.16-sparse/arch/xeno/lib/dec_and_lock.c
-3ddb79b8oxeiaIW6Au95OM0GlsMrMw xenolinux-2.4.16-sparse/arch/xeno/lib/delay.c
-3ddb79b8XPasnRhvK-_6xYksf3S6qA xenolinux-2.4.16-sparse/arch/xeno/lib/getuser.S
-3ddb79b8HFLUh8mwcl4X44ta-ny1KA xenolinux-2.4.16-sparse/arch/xeno/lib/iodebug.c
-3ddb79b879qeoLlarHXvNIDEva6ssA xenolinux-2.4.16-sparse/arch/xeno/lib/memcpy.c
-3ddb79b869CY_yr4HymV6k98pfpMgg xenolinux-2.4.16-sparse/arch/xeno/lib/mmx.c
-3ddb79b8S77yf1--Qa4C0ZYmqKXCww xenolinux-2.4.16-sparse/arch/xeno/lib/old-checksum.c
-3ddb79b8ffZ79cU2ZzfA2ekeo6pqeg xenolinux-2.4.16-sparse/arch/xeno/lib/strstr.c
-3ddb79b82kQ5oIXpxq3TUmlgxsLzLg xenolinux-2.4.16-sparse/arch/xeno/lib/usercopy.c
-3ddb79b8qdD_svLCCAja_oP2w4Tn8Q xenolinux-2.4.16-sparse/arch/xeno/mm/Makefile
-3ddb79b8ukY8dsPYmR8eNk-aCzFPsQ xenolinux-2.4.16-sparse/arch/xeno/mm/extable.c
-3ddb79b856Zta9b3s0bgUCGbG1blvQ xenolinux-2.4.16-sparse/arch/xeno/mm/fault.c
-3df9ce13dZ6UGDjZbUeZfyH4Hy6aCA xenolinux-2.4.16-sparse/arch/xeno/mm/get_unmapped_area.c
-3ddb79b85fpsKT8A9WYnuJg03b715g xenolinux-2.4.16-sparse/arch/xeno/mm/hypervisor.c
-3ddb79b83Zj7Xn2QVhU4HeMuAC9FjA xenolinux-2.4.16-sparse/arch/xeno/mm/init.c
-3df9ce13TRWIv0Mawm15zESP7jcT7A xenolinux-2.4.16-sparse/arch/xeno/mm/mmu_context.c
-3ddb79b7aKdTkbr3u6aze8tVwGh_TQ xenolinux-2.4.16-sparse/arch/xeno/vmlinux.lds
-3e4a8cb7lpFFwT1Iu9zXWc8Ew4klFA xenolinux-2.4.16-sparse/drivers/block/Config.in
-3ddb79bbx682YH6vR2zbVOXwg73ULg xenolinux-2.4.16-sparse/drivers/block/ll_rw_blk.c
-3ddb79bcJfHdwrPsjqgI33_OsGdVCg xenolinux-2.4.16-sparse/drivers/block/rd.c
-3ddb79bcpVu-IbnqwQqpRqsEbLpsuw xenolinux-2.4.16-sparse/drivers/char/tty_io.c
-3e15d5273gfR2fbcYe05kqBSAvCX_w xenolinux-2.4.16-sparse/fs/exec.c
-3ddb79b8VFtfWSCrXKPN2K21zd_vtw xenolinux-2.4.16-sparse/include/asm-xeno/a.out.h
-3ddb79b8Zzi13p3OAPV25QgiC3THAQ xenolinux-2.4.16-sparse/include/asm-xeno/apic.h
-3ddb79baZDlsdV_m6C5CXnWMl15p1g xenolinux-2.4.16-sparse/include/asm-xeno/apicdef.h
-3ddb79baZM88u4CnriVA8ZXBdnMNvg xenolinux-2.4.16-sparse/include/asm-xeno/atomic.h
-3ddb79baYHyZsDCiXiq8Y8_XxHE-jQ xenolinux-2.4.16-sparse/include/asm-xeno/bitops.h
-3ddb79b8vFGtGb6pg3GZFXSiwOZfcg xenolinux-2.4.16-sparse/include/asm-xeno/boot.h
-3ddb79baW8tf6PiBQUF50QQM5nY9sw xenolinux-2.4.16-sparse/include/asm-xeno/bugs.h
-3ddb79b80msOlzTZRoVudYdemzgOlA xenolinux-2.4.16-sparse/include/asm-xeno/byteorder.h
-3ddb79b8brNSUEujnq8f_zr8kA-cUg xenolinux-2.4.16-sparse/include/asm-xeno/cache.h
-3ddb79bayhr6C6prVhAYlFRChhf3wg xenolinux-2.4.16-sparse/include/asm-xeno/checksum.h
-3ddb79b8RNUaDbpPjdVVwKAsbiTBKQ xenolinux-2.4.16-sparse/include/asm-xeno/cpufeature.h
-3ddb79b8pJe4aNsUKkfHEoBT9Y-UMA xenolinux-2.4.16-sparse/include/asm-xeno/current.h
-3ddb79b8KL7icUfxKRoWDIkHkLQ1kQ xenolinux-2.4.16-sparse/include/asm-xeno/debugreg.h
-3ddb79baDUP_cRdFgqaH0rXUvMxx4A xenolinux-2.4.16-sparse/include/asm-xeno/delay.h
-3ddb79b89CgBTFsS3joEJ1ZniSHEgA xenolinux-2.4.16-sparse/include/asm-xeno/desc.h
-3ddb79ba6xyT4mJOYSp1Fg2l0ta93A xenolinux-2.4.16-sparse/include/asm-xeno/div64.h
-3ddb79b80Z4ZUIqbD1Xu_t4OCuEHeQ xenolinux-2.4.16-sparse/include/asm-xeno/dma.h
-3ddb79bac26NkKcPIEsfxETc5Snyag xenolinux-2.4.16-sparse/include/asm-xeno/elf.h
-3ddb79ba722pCJ_g_xI8ebsE31IK-Q xenolinux-2.4.16-sparse/include/asm-xeno/errno.h
-3ddb79b8vIpUpgaSNEneFkg5hYSvNg xenolinux-2.4.16-sparse/include/asm-xeno/fcntl.h
-3e53dbfb9mmyM-y5NuBBTDJvQkDzjA xenolinux-2.4.16-sparse/include/asm-xeno/fixmap.h
-3ddb79b8780YvqvK1g5KPIWzQ6P15w xenolinux-2.4.16-sparse/include/asm-xeno/floppy.h
-3ddb79bas-nFywnmilbUeT34PEAA0g xenolinux-2.4.16-sparse/include/asm-xeno/hardirq.h
-3ddb79batzR40ZFY9dvgs5f1aM9I6g xenolinux-2.4.16-sparse/include/asm-xeno/hdreg.h
-3ddb79b90xBgbeYgCcImS2ZxJakxBA xenolinux-2.4.16-sparse/include/asm-xeno/highmem.h
-3ddb79baXLZV3dUKQI2gIYpAy67RuA xenolinux-2.4.16-sparse/include/asm-xeno/hw_irq.h
-3e00b957iYsdTI1x6THRwMoWSPIW2Q xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor-ifs
-3ddb79bapQ9Z9ewa5O1pqAVaNBTazg xenolinux-2.4.16-sparse/include/asm-xeno/hypervisor.h
-3ddb79baL-pjPI8hg5xjPgd4__SlOA xenolinux-2.4.16-sparse/include/asm-xeno/i387.h
-3ddb79ba66TwvG7HpbBo04fRhmj3KQ xenolinux-2.4.16-sparse/include/asm-xeno/ide.h
-3ddb79bahFfCuRcmd9kBYA-CuGtCSg xenolinux-2.4.16-sparse/include/asm-xeno/init.h
-3ddb79ba3wnwflaNW6QheYvxoj5S8Q xenolinux-2.4.16-sparse/include/asm-xeno/io.h
-3ddb79ba1MhHpElCXFlijej2zWVk4g xenolinux-2.4.16-sparse/include/asm-xeno/io_apic.h
-3ddb79baiyfcZN9rJwhq0UeFjI6GkQ xenolinux-2.4.16-sparse/include/asm-xeno/ioctl.h
-3ddb79badReKYSok3yHShb4jg0vA-A xenolinux-2.4.16-sparse/include/asm-xeno/ioctls.h
-3ddb79b9iuIxteTXg8_myIsrWF5uxg xenolinux-2.4.16-sparse/include/asm-xeno/ipc.h
-3ddb79baw5Dxo78880UMSanDV70WdA xenolinux-2.4.16-sparse/include/asm-xeno/ipcbuf.h
-3ddb79ban9FUBuEaznRZvPfry3xnHQ xenolinux-2.4.16-sparse/include/asm-xeno/irq.h
-3ddb79banJ5r-mqE7LZ8nPGTADaGBA xenolinux-2.4.16-sparse/include/asm-xeno/kdb.h
-3ddb79baoaoHGTW0oiBXFPUg4KWydw xenolinux-2.4.16-sparse/include/asm-xeno/kdbprivate.h
-3ddb79bam2K6c7tS2HX6jis2Bqx71w xenolinux-2.4.16-sparse/include/asm-xeno/keyboard.h
-3ddb79baQ8gGrZm2Jlo3I1ntD0H5HA xenolinux-2.4.16-sparse/include/asm-xeno/kmap_types.h
-3ddb79b9MeQEYrafy-Mx9OoeVFM_uw xenolinux-2.4.16-sparse/include/asm-xeno/ldt.h
-3ddb79baAsy5W-cJ9ML_w9chqqUh4A xenolinux-2.4.16-sparse/include/asm-xeno/linux_logo.h
-3ddb79b9uhsumPVE0wGgarfIkYDSFA xenolinux-2.4.16-sparse/include/asm-xeno/locks.h
-3ddb79b954ISbF9e68hB0WTulCJRgg xenolinux-2.4.16-sparse/include/asm-xeno/math_emu.h
-3ddb79b9EZDlC6RGn_y0OYr0nyQWlw xenolinux-2.4.16-sparse/include/asm-xeno/mc146818rtc.h
-3ddb79b9M6pTF4maDgh8TYbg_HHUbw xenolinux-2.4.16-sparse/include/asm-xeno/mca_dma.h
-3ddb79baA7dlps8FkicOUEXKEQuQsA xenolinux-2.4.16-sparse/include/asm-xeno/mman.h
-3ddb79baKfF36-eRvkxnEvMRQRai-w xenolinux-2.4.16-sparse/include/asm-xeno/mmu.h
-3ddb79baQyKbT5U4EmZNePY9Txp-tA xenolinux-2.4.16-sparse/include/asm-xeno/mmu_context.h
-3ddb79bberC3Ghs4vy-06Pu-LSiWtw xenolinux-2.4.16-sparse/include/asm-xeno/mmx.h
-3ddb79bbsJLF10xQcKDoV8f_7gcOXg xenolinux-2.4.16-sparse/include/asm-xeno/module.h
-3ddb79bbY5RffJ8_F1oC4VI7q3Eejg xenolinux-2.4.16-sparse/include/asm-xeno/mpspec.h
-3ddb79b90vB4Vzzy_wL6SYXQMy9N9Q xenolinux-2.4.16-sparse/include/asm-xeno/msgbuf.h
-3ddb79bbZ5a_vTk0xcgOHuPokaqwMw xenolinux-2.4.16-sparse/include/asm-xeno/msr.h
-3ddb79b9y1xAKaPiBd79MBcCopNNYw xenolinux-2.4.16-sparse/include/asm-xeno/mtrr.h
-3ddb79b90hX0QBJlWQN_VsHtX5Ijkw xenolinux-2.4.16-sparse/include/asm-xeno/namei.h
-3ddb79bbG2p9MNq7tuISz8md1Oj2lg xenolinux-2.4.16-sparse/include/asm-xeno/page.h
-3ddb79bb_iUa2piFSwaB8YPw-rB5SQ xenolinux-2.4.16-sparse/include/asm-xeno/param.h
-3ddb79b9Y8UU0S9AoDznoqqcYxg9-A xenolinux-2.4.16-sparse/include/asm-xeno/parport.h
-3ddb79b9K9_edWxBHS7TdCpyDmfp6g xenolinux-2.4.16-sparse/include/asm-xeno/pgalloc.h
-3ddb79bahaS_P3UYp9VEU6kHxXbajA xenolinux-2.4.16-sparse/include/asm-xeno/pgtable-2level.h
-3ddb79b9MjXUB_rk29GJgaNY24feCw xenolinux-2.4.16-sparse/include/asm-xeno/pgtable-3level.h
-3ddb79bbPF2ENpNHBru8K3hyYVPmkQ xenolinux-2.4.16-sparse/include/asm-xeno/pgtable.h
-3ddb79b9t9xKrOf8aP3X5jEit9tj-w xenolinux-2.4.16-sparse/include/asm-xeno/poll.h
-3ddb79b9xHtTDWFaI9ncAtxyUth0Yg xenolinux-2.4.16-sparse/include/asm-xeno/posix_types.h
-3ddb79b9VwZ9YsSpA7CkJmYXVadrCA xenolinux-2.4.16-sparse/include/asm-xeno/processor.h
-3ddb79bbKaOkHrGG9j05AGlii-voaQ xenolinux-2.4.16-sparse/include/asm-xeno/ptrace.h
-3ddb79bbVpJCVTXmc2yNf1rsC00YEg xenolinux-2.4.16-sparse/include/asm-xeno/resource.h
-3ddb79bbtU0Kh27NbNpqKAIhshJvXQ xenolinux-2.4.16-sparse/include/asm-xeno/rwlock.h
-3ddb79b97LhdmW6hYmybQOPDkK6plg xenolinux-2.4.16-sparse/include/asm-xeno/rwsem.h
-3ddb79bbgRzM1NoXYbLoOCbZt8s5NA xenolinux-2.4.16-sparse/include/asm-xeno/scatterlist.h
-3ddb79b9xCi3F80Z6xxx6nzkCAo8vQ xenolinux-2.4.16-sparse/include/asm-xeno/segment.h
-3ddb79b9WxySbCKDoMgTgPtn1G3BFw xenolinux-2.4.16-sparse/include/asm-xeno/semaphore.h
-3ddb79b9gNK3dtgXONloSBaNgZPjAg xenolinux-2.4.16-sparse/include/asm-xeno/sembuf.h
-3ddb79bb2UTDgfwju2J3weDXemw3LA xenolinux-2.4.16-sparse/include/asm-xeno/serial.h
-3ddb79bbAPFyA_n4dNVCRoee8obOKA xenolinux-2.4.16-sparse/include/asm-xeno/setup.h
-3ddb79b9XTOB5DwWBGzPLLR4rNEkDQ xenolinux-2.4.16-sparse/include/asm-xeno/shmbuf.h
-3ddb79b9-_jDlAj3qVZe4opi3zectQ xenolinux-2.4.16-sparse/include/asm-xeno/shmparam.h
-3ddb79b9AW75ErwlTRX4McxO15sEaQ xenolinux-2.4.16-sparse/include/asm-xeno/sigcontext.h
-3ddb79b9NBJW-KAI3mgveUCr7sIOwA xenolinux-2.4.16-sparse/include/asm-xeno/siginfo.h
-3ddb79bbj0i8tUVNMKtZVrLJqv3Nsw xenolinux-2.4.16-sparse/include/asm-xeno/signal.h
-3ddb79bbfAmpotdy-No2dwGez2fnIg xenolinux-2.4.16-sparse/include/asm-xeno/smp.h
-3ddb79b9pDERXiqSumFWMTFJ1X9xIw xenolinux-2.4.16-sparse/include/asm-xeno/smplock.h
-3ddb79bbuCOIWTlWEHgOTexEBbdDow xenolinux-2.4.16-sparse/include/asm-xeno/socket.h
-3ddb79b9ExeUznVBlSn1e2nvOCrJ4A xenolinux-2.4.16-sparse/include/asm-xeno/sockios.h
-3ddb79b9kL3xvucBb-Gmg4_vo-99vw xenolinux-2.4.16-sparse/include/asm-xeno/softirq.h
-3ddb79b9rJ8AfSzGzA0arI8mazYLlQ xenolinux-2.4.16-sparse/include/asm-xeno/spinlock.h
-3ddb79bbXaA_zUHNPkAKRNz1h0gIJw xenolinux-2.4.16-sparse/include/asm-xeno/stat.h
-3ddb79b9G004IlCplrjWgF1aXbp8dA xenolinux-2.4.16-sparse/include/asm-xeno/statfs.h
-3ddb79bbRsy3GlCFrQEbVMVp--xlwQ xenolinux-2.4.16-sparse/include/asm-xeno/string-486.h
-3ddb79bb4xug4cDph6ODLQFQIan_sg xenolinux-2.4.16-sparse/include/asm-xeno/string.h
-3ddb79b9JhjJtJUO3g5LmrHPkdxgKg xenolinux-2.4.16-sparse/include/asm-xeno/system.h
-3ddb79b9tbjCU9zSbqKbbv4m8tijlg xenolinux-2.4.16-sparse/include/asm-xeno/termbits.h
-3ddb79bbi0mW10tH4xX1_KHXKM_xPg xenolinux-2.4.16-sparse/include/asm-xeno/termios.h
-3ddb79b9JuR1VvNzlkyMlA-Dnlmy9Q xenolinux-2.4.16-sparse/include/asm-xeno/timex.h
-3ddb79b9Bofq-p3sCTF0ELVuf_iBYA xenolinux-2.4.16-sparse/include/asm-xeno/tlb.h
-3ddb79b9tpBUqS8-S6euSqyk2hFkKg xenolinux-2.4.16-sparse/include/asm-xeno/types.h
-3ddb79bb5bkAaEzD7pdqQZdWyA_0eQ xenolinux-2.4.16-sparse/include/asm-xeno/uaccess.h
-3ddb79bbiDIz1dxgFixHKyGuqRqfDQ xenolinux-2.4.16-sparse/include/asm-xeno/ucontext.h
-3ddb79ba_Smn-GiYtr5ZTMaZXn-AHg xenolinux-2.4.16-sparse/include/asm-xeno/unaligned.h
-3ddb79bb3cMSs_k2X5Oq2hOIBvmPYA xenolinux-2.4.16-sparse/include/asm-xeno/unistd.h
-3ddb79ba2qYtIQAT_-vCFkkZUXu_UQ xenolinux-2.4.16-sparse/include/asm-xeno/user.h
-3ddb79bbqhb9X9qWOz5Bv4wOzrkITg xenolinux-2.4.16-sparse/include/asm-xeno/vga.h
-3ddb79bbA52x94o6uwDYsbzrH2hjzA xenolinux-2.4.16-sparse/include/asm-xeno/xor.h
-3e4a8cb7ON8EclY3NN3YPXyMT941hA xenolinux-2.4.16-sparse/include/linux/blk.h
-3e4a8cb7GJrKD0z7EF0VZOhdEa01Mw xenolinux-2.4.16-sparse/include/linux/major.h
-3ddb79bb_7YG4U75ZmEic9YXWTW7Vw xenolinux-2.4.16-sparse/include/linux/sunrpc/debug.h
-3e4a8cb7j05wwb1uPZgY16s68o7qAw xenolinux-2.4.16-sparse/init/main.c
-3ddb79bcxkVPfWlZ1PQKvDrfArzOVw xenolinux-2.4.16-sparse/kernel/panic.c
-3ddb79bbP31im-mx2NbfthSeqty1Dg xenolinux-2.4.16-sparse/mk
-3e15d52e0_j129JPvo7xfYGndVFpwQ xenolinux-2.4.16-sparse/mm/memory.c
-3e15d535DLvpzTrLRUIerB69LpJD1g xenolinux-2.4.16-sparse/mm/mremap.c
-3e15d531m1Y1_W8ki64AFOU_ua4C4w xenolinux-2.4.16-sparse/mm/swapfile.c
+3e5a4e6589G-U42lFKs43plskXoFxQ xenolinux-2.4.21-pre4-sparse/Makefile
+3e5a4e65IEPjnWPZ5w3TxS5scV8Ewg xenolinux-2.4.21-pre4-sparse/arch/xeno/Makefile
+3e5a4e65n-KhsEAs-A4ULiStBp-r6w xenolinux-2.4.21-pre4-sparse/arch/xeno/boot/Makefile
+3e5a4e65OV_j_DBtjzt5vej771AJsA xenolinux-2.4.21-pre4-sparse/arch/xeno/config.in
+3e5a4e65TNEycLeXqPSXQJQm_xGecA xenolinux-2.4.21-pre4-sparse/arch/xeno/defconfig
+3e5a4e65iHEuC5sjFhj42XALYbLVRw xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/block/Makefile
+3e5a4e65pP5spJErBW69pJxSSdK9RA xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/block/xl_block.c
+3e5a4e65GtI9JZRAjuRdXaxt_4ohyQ xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/block/xl_block_test.c
+3e5a4e65G3e2s0ghPMgiJ-gBTUJ0uQ xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/console/Makefile
+3e5a4e651TH-SXHoufurnWjgl5bfOA xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/console/console.c
+3e5a4e656nfFISThfbyXQOA6HN6YHw xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/dom0/Makefile
+3e5a4e65Cc7io-vynYob10SlqXTjAQ xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/dom0/dom0_block.c
+3e5a4e65BXtftInNHUC2PjDfPhdZZA xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/dom0/dom0_core.c
+3e5a4e65uXAx05p6B1-HU2tijuw8qA xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/dom0/dom0_memory.c
+3e5a4e65EOOLlPwXnhSuX-iVdWLmnA xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/dom0/dom0_ops.h
+3e5a4e65gfn_ltB8ujHMVFApnTTNRQ xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/dom0/vfr.c
+3e5a4e65gZBRBB6RsSVg1c9iahigAw xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/network/Makefile
+3e5a4e65ZxKrbFetVB84JhrTyZ1YuQ xenolinux-2.4.21-pre4-sparse/arch/xeno/drivers/network/network.c
+3e5a4e65lWzkiPXsZdzPt2RNnJGG1g xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/Makefile
+3e5a4e65_hqfuxtGG8IUy6wRM86Ecg xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/entry.S
+3e5a4e65Hy_1iUvMTPsNqGNXd9uFpg xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/head.S
+3e5a4e65ibVQmwlOn0j3sVH_j_6hAg xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/hypervisor.c
+3e5a4e65RMGcuA-HCn3-wNx3fFQwdg xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/i386_ksyms.c
+3e5a4e65JfSHwduNJO6j-upYnjoWLA xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/i387.c
+3e5a4e65tzCYKTX26zdI8rk2m48BDA xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/init_task.c
+3e5a4e65MEvZhlr070sK5JsfAQlv7Q xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/ioport.c
+3e5a4e653U6cELGv528IxOLHvCq8iA xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/irq.c
+3e5a4e65muT6SU3ck47IP87Q7Ti5hA xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/ldt.c
+3e5a4e65IGt3WwQDNiL4h-gYWgNTWQ xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/process.c
+3e5a4e65vXUggUHe9b_D9q0CNcZmQg xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/ptrace.c
+3e5a4e66StFP0OPSNngVwPJ4cJDy4g xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/semaphore.c
+3e5a4e66tR-qJMLj3MppcKqmvuI2XQ xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/setup.c
+3e5a4e66fWSTagLGU2P8BGFGRjhDiw xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/signal.c
+3e5a4e66Id8AWFANwLRFP4mKJgIFQw xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/sys_i386.c
+3e5a4e66N__lUXNwzQ-eADRzK9LXuQ xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/time.c
+3e5a4e66aHCbQ_F5QZ8VeyikLmuRZQ xenolinux-2.4.21-pre4-sparse/arch/xeno/kernel/traps.c
+3e5a4e66-9_NczrVMbuQkoSLyXckIw xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/Makefile
+3e5a4e66pZtp3RawntDpdofnJEvHIg xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/checksum.S
+3e5a4e660Zju423CmC6q_-ZdObYhuA xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/dec_and_lock.c
+3e5a4e6637ZDk0BvFEC-aFQs599-ng xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/delay.c
+3e5a4e66Cf-sjHkzP95oIJ6hBC1pOA xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/getuser.S
+3e5a4e66s_LxC8VI5vqmr-TPOdJYsw xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/iodebug.c
+3e5a4e667pxnNndXVcVxVNBvZezxhw xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/memcpy.c
+3e5a4e66MHYcXyO9DndD8k0DDBovYw xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/mmx.c
+3e5a4e669xZJQRPtO8oiRIqMwChrLg xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/old-checksum.c
+3e5a4e66RzO4JzKOAraCe2dnQ5m-yw xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/strstr.c
+3e5a4e66us6VmRaduHUnWiKcAONyLA xenolinux-2.4.21-pre4-sparse/arch/xeno/lib/usercopy.c
+3e5a4e66croVgpcJyJuF2ycQw0HuJw xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/Makefile
+3e5a4e661LP_6AdxThMuysfcYtOexA xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/extable.c
+3e5a4e66l8Q5Tv-6B3lQIRmaVbFPzg xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/fault.c
+3e5a4e66TyNNUEXkr5RxqvQhXK1MQA xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/get_unmapped_area.c
+3e5a4e668SE9rixq4ahho9rNhLUUFQ xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/hypervisor.c
+3e5a4e661gLzzff25pJooKIIWe7IWg xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/init.c
+3e5a4e66U45cAIoHmxg0y1e1XhzVCA xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/mmu_context.c
+3e5a4e66_jLCqAOBvqAy5N4mP7hmBA xenolinux-2.4.21-pre4-sparse/arch/xeno/mm/pageattr.c
+3e5a4e66qRlSTcjafidMB6ulECADvg xenolinux-2.4.21-pre4-sparse/arch/xeno/vmlinux.lds
+3e5a4e668yELUdtr3HiJZBIqxqUyuA xenolinux-2.4.21-pre4-sparse/drivers/block/Config.in
+3e5a4e66mrtlmV75L1tjKDg8RaM5gA xenolinux-2.4.21-pre4-sparse/drivers/block/ll_rw_blk.c
+3e5a4e66rw65CxyolW9PKz4GG42RcA xenolinux-2.4.21-pre4-sparse/drivers/char/tty_io.c
+3e5a4e669uzIE54VwucPYtGwXLAbzA xenolinux-2.4.21-pre4-sparse/fs/exec.c
+3e5a4e66HUJwJfJBBOilIN7LeL0twg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/a.out.h
+3e5a4e66nv3Esm5N8FS5r0qs-l7A0w xenolinux-2.4.21-pre4-sparse/include/asm-xeno/apic.h
+3e5a4e66BHReK8U7xl4qqZMXvFXihQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/apicdef.h
+3e5a4e668V7Eo08_6qmVoevzFrlxGQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/atomic.h
+3e5a4e66FNm4qKYGsIMdX6DGJ1pI1g xenolinux-2.4.21-pre4-sparse/include/asm-xeno/bitops.h
+3e5a4e66zkP-aEQkEtznyyp-e7tUGA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/boot.h
+3e5a4e66wbeCpsJgVf_U8Jde-CNcsA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/bugs.h
+3e5a4e66wTE9HEEjsnOHrijDB8iXrQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/byteorder.h
+3e5a4e66VqboK-qHV-HxmSflMh4VqQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/cache.h
+3e5a4e66bTVzeqJUJQiu67FWoHM5iw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/checksum.h
+3e5a4e66JVArkZ-0_pav3AsvKbftdw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/cpufeature.h
+3e5a4e66cCx28DaXo1U_nKvVX-5Y5w xenolinux-2.4.21-pre4-sparse/include/asm-xeno/current.h
+3e5a4e66o7NZjoJZjzJa-Z7XcGmGqg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/debugreg.h
+3e5a4e66rpzD2c7pNKF0XLbHzxb24A xenolinux-2.4.21-pre4-sparse/include/asm-xeno/delay.h
+3e5a4e66HdSkvIV6SJ1evG_xmTmXHA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/desc.h
+3e5a4e66GP6AL7wpHyxcsHOH4cJ4BQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/div64.h
+3e5a4e66wJ9hmUtY2rLWliznHdjWaw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/dma.h
+3e5a4e667P_1mO6v1YFRZ-ocfpiyVQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/elf.h
+3e5a4e66qeYk1odm2esnGypmiMcxqw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/errno.h
+3e5a4e663pDK4oQnfbuT38CR04cXDQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/fcntl.h
+3e5a4e66SYp_UpAVcF8Lc1wa3Qtgzw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/fixmap.h
+3e5a4e67fsayUJFE3A24CKZoUDI88A xenolinux-2.4.21-pre4-sparse/include/asm-xeno/floppy.h
+3e5a4e67uPmwPbjvF7YGsG2hX-3oBQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hardirq.h
+3e5a4e67P_6RRoCzUiQt_gyx6lmyWw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hdreg.h
+3e5a4e67w_DWgjIJ17Tlossu1LGujQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/highmem.h
+3e5a4e67YtcyDLQsShhCfQwPSELfvA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hw_irq.h
+3e5a4e67ASLV411RBbSd1tsCc1Dobg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hypervisor-ifs/block.h
+3e5a4e675NGZazUEJ9DDEbTzK3PuDQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hypervisor-ifs/hypervisor-if.h
+3e5a4e67poqyxiAz_921VNzba90kmw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hypervisor-ifs/network.h
+3e5a4e677VBavzM1UZIEcH1B-RlXMA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/hypervisor.h
+3e5a4e679TYbXAUiURvTeX4cFb1RlQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/i387.h
+3e5a4e672eNAzAKUZsefsPdmsH19hA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ide.h
+3e5a4e67XHl6b9C1Oqv79FiE1T3ybg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/init.h
+3e5a4e67Ulv-Ll8Zp4j2GwMwQ8aAXQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/io.h
+3e5a4e67cWGE9V1O6DSwvj5KtkY04g xenolinux-2.4.21-pre4-sparse/include/asm-xeno/io_apic.h
+3e5a4e67-vXNELtSK-qDSYyK55febg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ioctl.h
+3e5a4e67iqnkteX3g1IFQ-0Hf-vyuA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ioctls.h
+3e5a4e674l2NZF3klG30JX_auXUBgA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ipc.h
+3e5a4e678dxUg9lvKOXvH1s5a9GNsA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ipcbuf.h
+3e5a4e673p7PEOyHFm3nHkYX6HQYBg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/irq.h
+3e5a4e67nfnw10Wsugp5ZeMYFO_Eeg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/keyboard.h
+3e5a4e67FbgZ92JO9Vp2CKlW6z7wjA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/kmap_types.h
+3e5a4e674VIvXJxlOtz7LjtNAJttAA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ldt.h
+3e5a4e67X2GwDXstxQeuIyr65hdOig xenolinux-2.4.21-pre4-sparse/include/asm-xeno/linux_logo.h
+3e5a4e67mLXkDcU-aaeMByYb1-3v7Q xenolinux-2.4.21-pre4-sparse/include/asm-xeno/locks.h
+3e5a4e67g8B4DjzsIajoy1_mlxlvLg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/math_emu.h
+3e5a4e67J6JsiPWb0AwWZzQcOLbKKw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mc146818rtc.h
+3e5a4e67otTxTEz6CA4vVHE-CFLGkQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mca_dma.h
+3e5a4e67hSfhasW1McVONBMITBY28g xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mman.h
+3e5a4e67zoNch27qYhEBpr2k6SABOg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mmu.h
+3e5a4e678ddsQOpbSiRdy1GRcDc9WA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mmu_context.h
+3e5a4e67YQ_cLDcJjIsd8XTCk3w4rg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mmx.h
+3e5a4e67Zv1yObwNLd_9AYbyGTTvSw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/module.h
+3e5a4e67C-czbgW6YxgEbJG1e9aPGg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mpspec.h
+3e5a4e67swa8teSCnQDQvpV90xYiZQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/msgbuf.h
+3e5a4e67U1TsB9azleujfFZm3E5i3w xenolinux-2.4.21-pre4-sparse/include/asm-xeno/msr.h
+3e5a4e67f6dvHFEisaZ4wCR2t3a0yw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/mtrr.h
+3e5a4e67Kd-KWcgJON9dfcJEQD9hdg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/namei.h
+3e5a4e67mnQfh-R8KcQCaVo2Oho6yg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/page.h
+3e5a4e67IYaS0RnLo3SntreGd59gMA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/param.h
+3e5a4e67nvdHRk38knQeDl-0Z2j6_Q xenolinux-2.4.21-pre4-sparse/include/asm-xeno/parport.h
+3e5a4e67uTYU5oEnIDjxuaez8njjqg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/pgalloc.h
+3e5a4e67X7JyupgdYkgDX19Huj2sAw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/pgtable-2level.h
+3e5a4e67w3ckNdrTEgqiSiYYAYMwOQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/pgtable-3level.h
+3e5a4e67gr4NLGtQ5CvSLimMYZlkOA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/pgtable.h
+3e5a4e671OnIMxuFE59yynI-qvwKCA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/poll.h
+3e5a4e67o7FLcNPHjwyw5vb01EQTCg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/posix_types.h
+3e5a4e676uK4xErTBDH6XJREn9LSyg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/processor.h
+3e5a4e67AJPjW-zL7p-xWuA6IVeH1g xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ptrace.h
+3e5a4e67tIfXJYRQFxfRbcpZ25vqfw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/resource.h
+3e5a4e68E-U7HbKdTBaYoo3ZISdxuQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/rwlock.h
+3e5a4e68unR4ktSClycraOPanwxvTg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/rwsem.h
+3e5a4e68DATgqBYbF9W2Pkw5fGZBRg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/scatterlist.h
+3e5a4e68uJz-xI0IBVMD7xRLQKJDFg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/segment.h
+3e5a4e68Ug8hqChUpD2m_IDQSiu8jw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/semaphore.h
+3e5a4e68uFNNH3YQvZS1EnL0v_E6ew xenolinux-2.4.21-pre4-sparse/include/asm-xeno/sembuf.h
+3e5a4e689R_c0pr8Ycb-w6zveleWEw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/serial.h
+3e5a4e682D6yseOVKoJIx6HafkEKJw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/setup.h
+3e5a4e680_gLjMSi1Ql0nUnqCoQSyQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/shmbuf.h
+3e5a4e68PFVCbzUszQ4anRN8iZ1DUg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/shmparam.h
+3e5a4e689rAyWPwrwdvtJEkrtVw1rA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/sigcontext.h
+3e5a4e68D7dXWzciOKbyG1G3l3yt0w xenolinux-2.4.21-pre4-sparse/include/asm-xeno/siginfo.h
+3e5a4e68soo0VsYXn1HYv2XeUnlxgw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/signal.h
+3e5a4e68Nfdh6QcOKUTGCaYkf2LmYA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/smp.h
+3e5a4e688pv8zI1Z3wciLUik3c2iEw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/smplock.h
+3e5a4e68jaQZMOApQVZiq7T_gGPZhw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/socket.h
+3e5a4e68wlnX8Huhsl0gd7VgmiA8uA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/sockios.h
+3e5a4e68tuqUkZ3kyZGk6BZ1hrkXyw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/softirq.h
+3e5a4e68viR5sAz1SvKnPNrpKmlAZA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/spinlock.h
+3e5a4e68nUxBYfOOLm0_cZN7XM-3LQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/stat.h
+3e5a4e68my8BhpsHYBD63VUrxLXRCg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/statfs.h
+3e5a4e68W6piFzx4c4kiqwNB-h8PbQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/string-486.h
+3e5a4e68gFzDdQZEy91vkcdKWubf2g xenolinux-2.4.21-pre4-sparse/include/asm-xeno/string.h
+3e5a4e68mTr0zcp9SXDbnd-XLrrfxw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/system.h
+3e5a4e686Tful7frKeVbjeeWZ4S0nA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/termbits.h
+3e5a4e68fZcskF52zTGHdiF_yoVBiw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/termios.h
+3e5a4e68t8oGxTdC3i40nPjFwW00_g xenolinux-2.4.21-pre4-sparse/include/asm-xeno/timex.h
+3e5a4e685uCbimBjS_2iGxUqptPYiQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/tlb.h
+3e5a4e68Elybq23T6RnEt6vopg3mxg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/types.h
+3e5a4e68NeADbbaqoo4emjpU5xcaqA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/uaccess.h
+3e5a4e68HMMGyb6iBvG-qVbd9hODaQ xenolinux-2.4.21-pre4-sparse/include/asm-xeno/ucontext.h
+3e5a4e68m2MrAb54gFw8n-ZGNEu-Fw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/unaligned.h
+3e5a4e68vggReonfTJ1gdzYjFaOSKw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/unistd.h
+3e5a4e68QPC4T0aOA61QgK2SGDPVVA xenolinux-2.4.21-pre4-sparse/include/asm-xeno/user.h
+3e5a4e68g2boOp0d45bjtwugxQ8zNw xenolinux-2.4.21-pre4-sparse/include/asm-xeno/vga.h
+3e5a4e68AB-TTHj1oXtqVJvUo9jzIg xenolinux-2.4.21-pre4-sparse/include/asm-xeno/xor.h
+3e5a4e68-X9_qn9HYcRvUFNc8htBSw xenolinux-2.4.21-pre4-sparse/include/linux/blk.h
+3e5a4e68WLX3B8owTvktP3HHOtznPQ xenolinux-2.4.21-pre4-sparse/include/linux/major.h
+3e5a4e686V0nioX2ZpFf056sgvdiQw xenolinux-2.4.21-pre4-sparse/include/linux/sunrpc/debug.h
+3e5a4e68W_hpMlM3u_-QOKMp3gzcwQ xenolinux-2.4.21-pre4-sparse/init/do_mounts.c
+3e5a4e68TJJavrunYwTAnLRSBxSYqQ xenolinux-2.4.21-pre4-sparse/kernel/panic.c
+3e5a4e68GxCIaFH4sy01v1wjapetaA xenolinux-2.4.21-pre4-sparse/mm/memory.c
+3e5a4e681xMPdF9xCMwpyfuYMySU5g xenolinux-2.4.21-pre4-sparse/mm/mremap.c
+3e5a4e683HKVU-sxtagrDasRB8eBVw xenolinux-2.4.21-pre4-sparse/mm/swapfile.c
--- /dev/null
+VERSION = 2
+PATCHLEVEL = 4
+SUBLEVEL = 16
+EXTRAVERSION = -kdb-xeno
+
+KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
+
+HW_ARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ -e s/arm.*/arm/ -e s/sa110/arm/)
+ifndef ARCH
+ARCH := $(HW_ARCH)
+endif
+
+ARCH=xeno
+
+KERNELPATH=kernel-$(shell echo $(KERNELRELEASE) | sed -e "s/-//")
+
+CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
+ else if [ -x /bin/bash ]; then echo /bin/bash; \
+ else echo sh; fi ; fi)
+TOPDIR := $(shell /bin/pwd)
+
+HPATH = $(TOPDIR)/include
+FINDHPATH = $(HPATH)/asm $(HPATH)/linux $(HPATH)/scsi $(HPATH)/net
+
+HOSTCC = gcc
+HOSTCFLAGS = -Wall -Wstrict-prototypes -O2 -fomit-frame-pointer
+
+CROSS_COMPILE =
+
+#
+# Include the make variables (CC, etc...)
+#
+
+AS = $(CROSS_COMPILE)as
+LD = $(CROSS_COMPILE)ld
+CC = $(CROSS_COMPILE)gcc
+CPP = $(CC) -E
+AR = $(CROSS_COMPILE)ar
+NM = $(CROSS_COMPILE)nm
+STRIP = $(CROSS_COMPILE)strip
+OBJCOPY = $(CROSS_COMPILE)objcopy
+OBJDUMP = $(CROSS_COMPILE)objdump
+MAKEFILES = $(TOPDIR)/.config
+GENKSYMS = /sbin/genksyms
+DEPMOD = /sbin/depmod
+KALLSYMS = /sbin/kallsyms
+MODFLAGS = -DMODULE
+CFLAGS_KERNEL =
+PERL = perl
+AWK = awk
+TMPPREFIX =
+
+export VERSION PATCHLEVEL SUBLEVEL EXTRAVERSION KERNELRELEASE ARCH \
+ CONFIG_SHELL TOPDIR HPATH HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC \
+ CPP AR NM STRIP OBJCOPY OBJDUMP MAKE MAKEFILES GENKSYMS MODFLAGS PERL AWK
+
+all: do-it-all
+
+#
+# Make "config" the default target if there is no configuration file or
+# "depend" the target if there is no top-level dependency information.
+#
+
+ifeq (.config,$(wildcard .config))
+include .config
+ifeq (.depend,$(wildcard .depend))
+include .depend
+do-it-all: Version vmlinux
+else
+CONFIGURATION = depend
+do-it-all: depend
+endif
+else
+CONFIGURATION = config
+do-it-all: config
+endif
+
+#
+# INSTALL_PATH specifies where to place the updated kernel and system map
+# images. Uncomment if you want to place them anywhere other than root.
+#
+
+#export INSTALL_PATH=/boot
+
+#
+# INSTALL_MOD_PATH specifies a prefix to MODLIB for module directory
+# relocations required by build roots. This is not defined in the
+# makefile but the arguement can be passed to make if needed.
+#
+
+MODLIB := $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
+export MODLIB
+
+#
+# standard CFLAGS
+#
+
+CPPFLAGS := -D__KERNEL__ -I$(HPATH)
+CPPFLAGS += $(patsubst %,-I%,$(CROSS_COMPILE_INC))
+
+CFLAGS := $(CPPFLAGS) -Wall -Wstrict-prototypes -Wno-trigraphs -O2 \
+ -fno-strict-aliasing -fno-common
+ifndef CONFIG_FRAME_POINTER
+CFLAGS += -fomit-frame-pointer
+endif
+AFLAGS := -D__ASSEMBLY__ $(CPPFLAGS)
+
+#
+# ROOT_DEV specifies the default root-device when making the image.
+# This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case
+# the default of FLOPPY is used by 'build'.
+# This is i386 specific.
+#
+
+export ROOT_DEV = CURRENT
+
+#
+# If you want to preset the SVGA mode, uncomment the next line and
+# set SVGA_MODE to whatever number you want.
+# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
+# The number is the same as you would ordinarily press at bootup.
+# This is i386 specific.
+#
+
+export SVGA_MODE = -DSVGA_MODE=NORMAL_VGA
+
+#
+# If you want the RAM disk device, define this to be the size in blocks.
+# This is i386 specific.
+#
+
+#export RAMDISK = -DRAMDISK=512
+
+CORE_FILES =kernel/kernel.o mm/mm.o fs/fs.o ipc/ipc.o
+NETWORKS =net/network.o
+
+LIBS =$(TOPDIR)/lib/lib.a
+SUBDIRS =kernel drivers mm fs net ipc lib
+
+ifeq ($(CONFIG_KDB),y)
+CORE_FILES += kdb/kdb.o
+SUBDIRS += kdb
+endif
+
+DRIVERS-n :=
+DRIVERS-y :=
+DRIVERS-m :=
+DRIVERS- :=
+
+DRIVERS-$(CONFIG_ACPI) += drivers/acpi/acpi.o
+DRIVERS-$(CONFIG_PARPORT) += drivers/parport/driver.o
+DRIVERS-y += drivers/char/char.o \
+ drivers/block/block.o \
+ drivers/misc/misc.o \
+ drivers/net/net.o \
+ drivers/media/media.o
+DRIVERS-$(CONFIG_AGP) += drivers/char/agp/agp.o
+DRIVERS-$(CONFIG_DRM) += drivers/char/drm/drm.o
+DRIVERS-$(CONFIG_NUBUS) += drivers/nubus/nubus.a
+DRIVERS-$(CONFIG_ISDN) += drivers/isdn/isdn.a
+DRIVERS-$(CONFIG_NET_FC) += drivers/net/fc/fc.o
+DRIVERS-$(CONFIG_APPLETALK) += drivers/net/appletalk/appletalk.o
+DRIVERS-$(CONFIG_TR) += drivers/net/tokenring/tr.o
+DRIVERS-$(CONFIG_WAN) += drivers/net/wan/wan.o
+DRIVERS-$(CONFIG_ARCNET) += drivers/net/arcnet/arcnetdrv.o
+DRIVERS-$(CONFIG_ATM) += drivers/atm/atm.o
+DRIVERS-$(CONFIG_IDE) += drivers/ide/idedriver.o
+DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
+DRIVERS-$(CONFIG_SCSI) += drivers/scsi/scsidrv.o
+DRIVERS-$(CONFIG_FUSION_BOOT) += drivers/message/fusion/fusion.o
+DRIVERS-$(CONFIG_IEEE1394) += drivers/ieee1394/ieee1394drv.o
+
+ifneq ($(CONFIG_CD_NO_IDESCSI)$(CONFIG_BLK_DEV_IDECD)$(CONFIG_BLK_DEV_SR)$(CONFIG_PARIDE_PCD),)
+DRIVERS-y += drivers/cdrom/driver.o
+endif
+
+DRIVERS-$(CONFIG_SOUND) += drivers/sound/sounddrivers.o
+DRIVERS-$(CONFIG_PCI) += drivers/pci/driver.o
+DRIVERS-$(CONFIG_MTD) += drivers/mtd/mtdlink.o
+DRIVERS-$(CONFIG_PCMCIA) += drivers/pcmcia/pcmcia.o
+DRIVERS-$(CONFIG_NET_PCMCIA) += drivers/net/pcmcia/pcmcia_net.o
+DRIVERS-$(CONFIG_NET_WIRELESS) += drivers/net/wireless/wireless_net.o
+DRIVERS-$(CONFIG_PCMCIA_CHRDEV) += drivers/char/pcmcia/pcmcia_char.o
+DRIVERS-$(CONFIG_DIO) += drivers/dio/dio.a
+DRIVERS-$(CONFIG_SBUS) += drivers/sbus/sbus_all.o
+DRIVERS-$(CONFIG_ZORRO) += drivers/zorro/driver.o
+DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
+DRIVERS-$(CONFIG_ALL_PPC) += drivers/macintosh/macintosh.o
+DRIVERS-$(CONFIG_MAC) += drivers/macintosh/macintosh.o
+DRIVERS-$(CONFIG_ISAPNP) += drivers/pnp/pnp.o
+DRIVERS-$(CONFIG_SGI_IP22) += drivers/sgi/sgi.a
+DRIVERS-$(CONFIG_VT) += drivers/video/video.o
+DRIVERS-$(CONFIG_PARIDE) += drivers/block/paride/paride.a
+DRIVERS-$(CONFIG_HAMRADIO) += drivers/net/hamradio/hamradio.o
+DRIVERS-$(CONFIG_TC) += drivers/tc/tc.a
+DRIVERS-$(CONFIG_USB) += drivers/usb/usbdrv.o
+DRIVERS-$(CONFIG_INPUT) += drivers/input/inputdrv.o
+DRIVERS-$(CONFIG_I2O) += drivers/message/i2o/i2o.o
+DRIVERS-$(CONFIG_IRDA) += drivers/net/irda/irda.o
+DRIVERS-$(CONFIG_I2C) += drivers/i2c/i2c.o
+DRIVERS-$(CONFIG_PHONE) += drivers/telephony/telephony.o
+DRIVERS-$(CONFIG_MD) += drivers/md/mddev.o
+DRIVERS-$(CONFIG_BLUEZ) += drivers/bluetooth/bluetooth.o
+DRIVERS-$(CONFIG_HOTPLUG_PCI) += drivers/hotplug/vmlinux-obj.o
+
+DRIVERS := $(DRIVERS-y)
+
+
+# files removed with 'make clean'
+CLEAN_FILES = \
+ kernel/ksyms.lst include/linux/compile.h \
+ vmlinux System.map \
+ $(TMPPREFIX).tmp* \
+ drivers/char/consolemap_deftbl.c drivers/video/promcon_tbl.c \
+ drivers/char/conmakehash \
+ drivers/char/drm/*-mod.c \
+ drivers/pci/devlist.h drivers/pci/classlist.h drivers/pci/gen-devlist \
+ drivers/zorro/devlist.h drivers/zorro/gen-devlist \
+ drivers/sound/bin2hex drivers/sound/hex2hex \
+ drivers/atm/fore200e_mkfirm drivers/atm/{pca,sba}*{.bin,.bin1,.bin2} \
+ drivers/scsi/aic7xxx/aicasm/aicasm_gram.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_scan.c \
+ drivers/scsi/aic7xxx/aicasm/y.tab.h \
+ drivers/scsi/aic7xxx/aicasm/aicasm \
+ drivers/scsi/53c700-mem.c \
+ net/khttpd/make_times_h \
+ net/khttpd/times.h \
+ submenu*
+# directories removed with 'make clean'
+CLEAN_DIRS = \
+ modules
+
+# files removed with 'make mrproper'
+MRPROPER_FILES = \
+ include/linux/autoconf.h include/linux/version.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{afsk1200,afsk2666,fsk9600}.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{hapn4800,psk4800}.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{afsk2400_7,afsk2400_8}.h \
+ drivers/net/hamradio/soundmodem/gentbl \
+ drivers/sound/*_boot.h drivers/sound/.*.boot \
+ drivers/sound/msndinit.c \
+ drivers/sound/msndperm.c \
+ drivers/sound/pndsperm.c \
+ drivers/sound/pndspini.c \
+ drivers/atm/fore200e_*_fw.c drivers/atm/.fore200e_*.fw \
+ .version .config* config.in config.old \
+ scripts/tkparse scripts/kconfig.tk scripts/kconfig.tmp \
+ scripts/lxdialog/*.o scripts/lxdialog/lxdialog \
+ .menuconfig.log \
+ include/asm \
+ kdb/gen-kdb_cmds.c \
+ .hdepend scripts/mkdep scripts/split-include scripts/docproc \
+ $(TOPDIR)/include/linux/modversions.h \
+ kernel.spec
+
+# directories removed with 'make mrproper'
+MRPROPER_DIRS = \
+ include/config \
+ $(TOPDIR)/include/linux/modules
+
+
+include arch/$(ARCH)/Makefile
+
+export CPPFLAGS CFLAGS CFLAGS_KERNEL AFLAGS AFLAGS_KERNEL
+
+export NETWORKS DRIVERS LIBS HEAD LDFLAGS LINKFLAGS MAKEBOOT ASFLAGS
+
+.S.s:
+ $(CPP) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -o $*.s $<
+.S.o:
+ $(CC) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -c -o $*.o $<
+
+Version: dummy
+ @rm -f include/linux/compile.h
+
+boot: vmlinux
+ @$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C arch/$(ARCH)/boot
+
+LD_VMLINUX := $(LD) $(LINKFLAGS) $(HEAD) init/main.o init/version.o \
+ --start-group \
+ $(CORE_FILES) \
+ $(DRIVERS) \
+ $(NETWORKS) \
+ $(LIBS) \
+ --end-group
+ifeq ($(CONFIG_KALLSYMS),y)
+LD_VMLINUX_KALLSYMS := $(TMPPREFIX).tmp_kallsyms3.o
+else
+LD_VMLINUX_KALLSYMS :=
+endif
+
+vmlinux: include/linux/version.h $(CONFIGURATION) init/main.o init/version.o linuxsubdirs
+ @$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" kallsyms
+
+.PHONY: kallsyms
+
+kallsyms:
+ifeq ($(CONFIG_KALLSYMS),y)
+ @echo kallsyms pass 1
+ $(LD_VMLINUX) -o $(TMPPREFIX).tmp_vmlinux1
+ @$(KALLSYMS) $(TMPPREFIX).tmp_vmlinux1 > $(TMPPREFIX).tmp_kallsyms1.o
+ @echo kallsyms pass 2
+ @$(LD_VMLINUX) $(TMPPREFIX).tmp_kallsyms1.o -o $(TMPPREFIX).tmp_vmlinux2
+ @$(KALLSYMS) $(TMPPREFIX).tmp_vmlinux2 > $(TMPPREFIX).tmp_kallsyms2.o
+ @echo kallsyms pass 3
+ @$(LD_VMLINUX) $(TMPPREFIX).tmp_kallsyms2.o -o $(TMPPREFIX).tmp_vmlinux3
+ @$(KALLSYMS) $(TMPPREFIX).tmp_vmlinux3 > $(TMPPREFIX).tmp_kallsyms3.o
+endif
+ $(LD_VMLINUX) $(LD_VMLINUX_KALLSYMS) -o $(TMPPREFIX)vmlinux
+ifneq ($(TMPPREFIX),)
+ mv $(TMPPREFIX)vmlinux vmlinux
+endif
+ $(NM) vmlinux | grep -v '\(compiled\)\|\(\.o$$\)\|\( [aUw] \)\|\(\.\.ng$$\)\|\(LASH[RL]DI\)' | sort > System.map
+ @rm -f $(TMPPREFIX).tmp_vmlinux* $(TMPPREFIX).tmp_kallsyms*
+
+symlinks:
+ rm -f include/asm
+ ( cd include ; ln -sf asm-$(ARCH) asm)
+ @if [ ! -d include/linux/modules ]; then \
+ mkdir include/linux/modules; \
+ fi
+
+oldconfig: symlinks
+ $(CONFIG_SHELL) scripts/Configure -d arch/$(ARCH)/config.in
+
+xconfig: symlinks
+ $(MAKE) -C scripts kconfig.tk
+ wish -f scripts/kconfig.tk
+
+menuconfig: include/linux/version.h symlinks
+ $(MAKE) -C scripts/lxdialog all
+ $(CONFIG_SHELL) scripts/Menuconfig arch/$(ARCH)/config.in
+
+config: symlinks
+ $(CONFIG_SHELL) scripts/Configure arch/$(ARCH)/config.in
+
+include/config/MARKER: scripts/split-include include/linux/autoconf.h
+ scripts/split-include include/linux/autoconf.h include/config
+ @ touch include/config/MARKER
+
+linuxsubdirs: $(patsubst %, _dir_%, $(SUBDIRS))
+
+$(patsubst %, _dir_%, $(SUBDIRS)) : dummy include/linux/version.h include/config/MARKER
+ $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C $(patsubst _dir_%, %, $@)
+
+$(TOPDIR)/include/linux/version.h: include/linux/version.h
+$(TOPDIR)/include/linux/compile.h: include/linux/compile.h
+
+newversion:
+ . scripts/mkversion > .tmpversion
+ @mv -f .tmpversion .version
+
+include/linux/compile.h: $(CONFIGURATION) include/linux/version.h newversion
+ @echo -n \#define UTS_VERSION \"\#`cat .version` > .ver
+ @if [ -n "$(CONFIG_SMP)" ] ; then echo -n " SMP" >> .ver; fi
+ @if [ -f .name ]; then echo -n \-`cat .name` >> .ver; fi
+ @echo ' '`date`'"' >> .ver
+ @echo \#define LINUX_COMPILE_TIME \"`date +%T`\" >> .ver
+ @echo \#define LINUX_COMPILE_BY \"`whoami`\" >> .ver
+ @echo \#define LINUX_COMPILE_HOST \"`hostname`\" >> .ver
+ @if [ -x /bin/dnsdomainname ]; then \
+ echo \#define LINUX_COMPILE_DOMAIN \"`dnsdomainname`\"; \
+ elif [ -x /bin/domainname ]; then \
+ echo \#define LINUX_COMPILE_DOMAIN \"`domainname`\"; \
+ else \
+ echo \#define LINUX_COMPILE_DOMAIN ; \
+ fi >> .ver
+ @echo \#define LINUX_COMPILER \"`$(CC) $(CFLAGS) -v 2>&1 | tail -1`\" >> .ver
+ @mv -f .ver $@
+
+include/linux/version.h: ./Makefile
+ @echo \#define UTS_RELEASE \"$(KERNELRELEASE)\" > .ver
+ @echo \#define LINUX_VERSION_CODE `expr $(VERSION) \\* 65536 + $(PATCHLEVEL) \\* 256 + $(SUBLEVEL)` >> .ver
+ @echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))' >>.ver
+ @mv -f .ver $@
+
+init/version.o: init/version.c include/linux/compile.h include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) -DUTS_MACHINE='"$(HW_ARCH)"' -c -o init/version.o init/version.c
+
+init/main.o: init/main.c include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -c -o $*.o $<
+
+fs lib mm ipc kernel drivers net: dummy
+ $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" $(subst $@, _dir_$@, $@)
+
+TAGS: dummy
+ etags `find include/asm-$(ARCH) -name '*.h'`
+ find include -type d \( -name "asm-*" -o -name config \) -prune -o -name '*.h' -print | xargs etags -a
+ find $(SUBDIRS) init -name '*.[ch]' | xargs etags -a
+
+# Exuberant ctags works better with -I
+tags: dummy
+ CTAGSF=`ctags --version | grep -i exuberant >/dev/null && echo "-I __initdata,__exitdata,EXPORT_SYMBOL,EXPORT_SYMBOL_NOVERS"`; \
+ ctags $$CTAGSF `find include/asm-$(ARCH) -name '*.h'` && \
+ find include -type d \( -name "asm-*" -o -name config \) -prune -o -name '*.h' -print | xargs ctags $$CTAGSF -a && \
+ find $(SUBDIRS) init -name '*.[ch]' | xargs ctags $$CTAGSF -a
+
+ifdef CONFIG_MODULES
+ifdef CONFIG_MODVERSIONS
+MODFLAGS += -DMODVERSIONS -include $(HPATH)/linux/modversions.h
+endif
+
+.PHONY: modules
+modules: $(patsubst %, _mod_%, $(SUBDIRS))
+
+.PHONY: $(patsubst %, _mod_%, $(SUBDIRS))
+$(patsubst %, _mod_%, $(SUBDIRS)) : include/linux/version.h include/config/MARKER
+ $(MAKE) -C $(patsubst _mod_%, %, $@) CFLAGS="$(CFLAGS) $(MODFLAGS)" MAKING_MODULES=1 modules
+
+.PHONY: modules_install
+modules_install: _modinst_ $(patsubst %, _modinst_%, $(SUBDIRS)) _modinst_post
+
+.PHONY: _modinst_
+_modinst_:
+ @rm -rf $(MODLIB)/kernel
+ @rm -f $(MODLIB)/build
+ @mkdir -p $(MODLIB)/kernel
+ @ln -s $(TOPDIR) $(MODLIB)/build
+
+# If System.map exists, run depmod. This deliberately does not have a
+# dependency on System.map since that would run the dependency tree on
+# vmlinux. This depmod is only for convenience to give the initial
+# boot a modules.dep even before / is mounted read-write. However the
+# boot script depmod is the master version.
+ifeq "$(strip $(INSTALL_MOD_PATH))" ""
+depmod_opts :=
+else
+depmod_opts := -b $(INSTALL_MOD_PATH) -r
+endif
+.PHONY: _modinst_post
+_modinst_post: _modinst_post_pcmcia
+# if [ -r System.map ]; then $(DEPMOD) -ae -F System.map $(depmod_opts) $(KERNELRELEASE); fi
+
+# Backwards compatibilty symlinks for people still using old versions
+# of pcmcia-cs with hard coded pathnames on insmod. Remove
+# _modinst_post_pcmcia for kernel 2.4.1.
+.PHONY: _modinst_post_pcmcia
+_modinst_post_pcmcia:
+ cd $(MODLIB); \
+ mkdir -p pcmcia; \
+ find kernel -path '*/pcmcia/*' -name '*.o' | xargs -i -r ln -sf ../{} pcmcia
+
+.PHONY: $(patsubst %, _modinst_%, $(SUBDIRS))
+$(patsubst %, _modinst_%, $(SUBDIRS)) :
+ $(MAKE) -C $(patsubst _modinst_%, %, $@) modules_install
+
+# modules disabled....
+
+else
+modules modules_install: dummy
+ @echo
+ @echo "The present kernel configuration has modules disabled."
+ @echo "Type 'make config' and enable loadable module support."
+ @echo "Then build a kernel with module support enabled."
+ @echo
+ @exit 1
+endif
+
+clean: archclean
+ find . \( -name '*.[oas]' -o -name core -o -name '.*.flags' \) -type f -print \
+ | grep -v lxdialog/ | xargs rm -f
+ rm -f $(CLEAN_FILES)
+ rm -rf $(CLEAN_DIRS)
+ $(MAKE) -C Documentation/DocBook clean
+
+mrproper: clean archmrproper
+ find . \( -size 0 -o -name .depend \) -type f -print | xargs rm -f
+ rm -f $(MRPROPER_FILES)
+ rm -rf $(MRPROPER_DIRS)
+ $(MAKE) -C Documentation/DocBook mrproper
+
+distclean: mrproper
+ rm -f core `find . \( -not -type d \) -and \
+ \( -name '*.orig' -o -name '*.rej' -o -name '*~' \
+ -o -name '*.bak' -o -name '#*#' -o -name '.*.orig' \
+ -o -name '.*.rej' -o -name '.SUMS' -o -size 0 \) -type f -print` TAGS tags
+
+backup: mrproper
+ cd .. && tar cf - linux/ | gzip -9 > backup.gz
+ sync
+
+sgmldocs:
+ chmod 755 $(TOPDIR)/scripts/docgen
+ chmod 755 $(TOPDIR)/scripts/gen-all-syms
+ chmod 755 $(TOPDIR)/scripts/kernel-doc
+ $(MAKE) -C $(TOPDIR)/Documentation/DocBook books
+
+psdocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook ps
+
+pdfdocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook pdf
+
+htmldocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook html
+
+sums:
+ find . -type f -print | sort | xargs sum > .SUMS
+
+dep-files: scripts/mkdep archdep include/linux/version.h
+ scripts/mkdep -- init/*.c > .depend
+ scripts/mkdep -- `find $(FINDHPATH) -name SCCS -prune -o -follow -name \*.h ! -name modversions.h -print` > .hdepend
+ $(MAKE) $(patsubst %,_sfdep_%,$(SUBDIRS)) _FASTDEP_ALL_SUB_DIRS="$(SUBDIRS)"
+ifdef CONFIG_MODVERSIONS
+ $(MAKE) update-modverfile
+endif
+
+ifdef CONFIG_MODVERSIONS
+MODVERFILE := $(TOPDIR)/include/linux/modversions.h
+else
+MODVERFILE :=
+endif
+export MODVERFILE
+
+depend dep: dep-files
+
+checkconfig:
+ find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w scripts/checkconfig.pl
+
+checkhelp:
+ find * -name [cC]onfig.in -print | sort | xargs $(PERL) -w scripts/checkhelp.pl
+
+checkincludes:
+ find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w scripts/checkincludes.pl
+
+ifdef CONFIGURATION
+..$(CONFIGURATION):
+ @echo
+ @echo "You have a bad or nonexistent" .$(CONFIGURATION) ": running 'make" $(CONFIGURATION)"'"
+ @echo
+ $(MAKE) $(CONFIGURATION)
+ @echo
+ @echo "Successful. Try re-making (ignore the error that follows)"
+ @echo
+ exit 1
+
+#dummy: ..$(CONFIGURATION)
+dummy:
+
+else
+
+dummy:
+
+endif
+
+include Rules.make
+
+#
+# This generates dependencies for the .h files.
+#
+
+scripts/mkdep: scripts/mkdep.c
+ $(HOSTCC) $(HOSTCFLAGS) -o scripts/mkdep scripts/mkdep.c
+
+scripts/split-include: scripts/split-include.c
+ $(HOSTCC) $(HOSTCFLAGS) -o scripts/split-include scripts/split-include.c
+
+#
+# RPM target
+#
+# If you do a make spec before packing the tarball you can rpm -ta it
+#
+spec:
+ . scripts/mkspec >kernel.spec
+
+#
+# Build a tar ball, generate an rpm from it and pack the result
+# There arw two bits of magic here
+# 1) The use of /. to avoid tar packing just the symlink
+# 2) Removing the .dep files as they have source paths in them that
+# will become invalid
+#
+rpm: clean spec
+ find . \( -size 0 -o -name .depend -o -name .hdepend \) -type f -print | xargs rm -f
+ set -e; \
+ cd $(TOPDIR)/.. ; \
+ ln -sf $(TOPDIR) $(KERNELPATH) ; \
+ tar -cvz --exclude CVS -f $(KERNELPATH).tar.gz $(KERNELPATH)/. ; \
+ rm $(KERNELPATH) ; \
+ cd $(TOPDIR) ; \
+ . scripts/mkversion > .version ; \
+ rpm -ta $(TOPDIR)/../$(KERNELPATH).tar.gz ; \
+ rm $(TOPDIR)/../$(KERNELPATH).tar.gz
--- /dev/null
+#
+# xeno/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina <skawina@geocities.com>
+# Added '-march' and '-mpreferred-stack-boundary' support
+#
+
+LD=$(CROSS_COMPILE)ld -m elf_i386
+OBJCOPY=$(CROSS_COMPILE)objcopy -O binary -R .note -R .comment -S
+LDFLAGS=-e stext
+LINKFLAGS =-T $(TOPDIR)/arch/xeno/vmlinux.lds $(LDFLAGS)
+
+CFLAGS += -pipe
+
+# prevent gcc from keeping the stack 16 byte aligned
+CFLAGS += $(shell if $(CC) -mpreferred-stack-boundary=2 -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-mpreferred-stack-boundary=2"; fi)
+
+ifdef CONFIG_M686
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MPENTIUMIII
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MPENTIUM4
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MK7
+CFLAGS += $(shell if $(CC) -march=athlon -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-march=athlon"; else echo "-march=i686 -malign-functions=4"; fi)
+endif
+
+HEAD := arch/xeno/kernel/head.o arch/xeno/kernel/init_task.o
+
+SUBDIRS += arch/xeno/kernel arch/xeno/mm arch/xeno/lib
+SUBDIRS += arch/xeno/drivers/console arch/xeno/drivers/network
+SUBDIRS += arch/xeno/drivers/dom0 arch/xeno/drivers/block
+
+CORE_FILES += arch/xeno/kernel/kernel.o arch/xeno/mm/mm.o
+CORE_FILES += arch/xeno/drivers/console/con.o
+CORE_FILES += arch/xeno/drivers/block/blk.o
+CORE_FILES += arch/xeno/drivers/network/net.o
+CORE_FILES += arch/xeno/drivers/dom0/dom0.o
+LIBS := $(TOPDIR)/arch/xeno/lib/lib.a $(LIBS) $(TOPDIR)/arch/xeno/lib/lib.a
+
+arch/xeno/kernel: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/kernel
+
+arch/xeno/mm: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/mm
+
+arch/xeno/drivers/console: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/console
+
+arch/xeno/drivers/network: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/network
+
+arch/xeno/drivers/block: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/block
+
+arch/xeno/drivers/dom0: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/dom0
+
+ifdef CONFIG_KDB
+arch/xeno/kdb: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/kdb
+endif
+
+MAKEBOOT = $(MAKE) -C arch/$(ARCH)/boot
+
+vmlinux: arch/xeno/vmlinux.lds
+
+FORCE: ;
+
+.PHONY: bzImage compressed clean archclean archmrproper archdep
+
+bzImage: vmlinux
+ @$(MAKEBOOT) image.gz
+
+archclean:
+ @$(MAKEBOOT) clean
+
+archmrproper:
+
+archdep:
+ @$(MAKEBOOT) dep
--- /dev/null
+#
+# arch/xeno/boot/Makefile
+#
+
+image.gz: image
+ gzip -f -9 < $< > $@
+
+image: $(TOPDIR)/vmlinux
+ # Guest OS header -- first 8 bytes are identifier 'XenoGues'.
+ echo -e -n 'XenoGues' >$@
+ # Guest OS header -- next 4 bytes are load address (0xC0000000).
+ echo -e -n '\000\000\000\300' >>$@
+ $(OBJCOPY) $< image.body
+ # Guest OS header is immediately followed by raw OS image.
+ # Start address must be at byte 0.
+ cat image.body >>$@
+ rm -f image.body
+
+dep:
+
+clean:
+ rm -f image image.gz
--- /dev/null
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/config-language.txt.
+#
+mainmenu_name "Linux Kernel Configuration"
+
+define_bool CONFIG_XENO y
+
+define_bool CONFIG_X86 y
+define_bool CONFIG_ISA y
+define_bool CONFIG_SBUS n
+
+define_bool CONFIG_UID16 y
+
+mainmenu_option next_comment
+comment 'Code maturity level options'
+bool 'Prompt for development and/or incomplete code/drivers' CONFIG_EXPERIMENTAL
+endmenu
+
+mainmenu_option next_comment
+comment 'Loadable module support'
+bool 'Enable loadable module support' CONFIG_MODULES
+if [ "$CONFIG_MODULES" = "y" ]; then
+ bool ' Set version information on all module symbols' CONFIG_MODVERSIONS
+ bool ' Kernel module loader' CONFIG_KMOD
+fi
+endmenu
+
+mainmenu_option next_comment
+comment 'Processor type and features'
+choice 'Processor family' \
+ "Pentium-Pro/Celeron/Pentium-II CONFIG_M686 \
+ Pentium-III/Celeron(Coppermine) CONFIG_MPENTIUMIII \
+ Pentium-4 CONFIG_MPENTIUM4 \
+ Athlon/Duron/K7 CONFIG_MK7" Pentium-Pro
+
+ define_bool CONFIG_X86_WP_WORKS_OK y
+ define_bool CONFIG_X86_INVLPG y
+ define_bool CONFIG_X86_CMPXCHG y
+ define_bool CONFIG_X86_XADD y
+ define_bool CONFIG_X86_BSWAP y
+ define_bool CONFIG_X86_POPAD_OK y
+ define_bool CONFIG_RWSEM_GENERIC_SPINLOCK n
+ define_bool CONFIG_RWSEM_XCHGADD_ALGORITHM y
+
+ define_bool CONFIG_X86_GOOD_APIC y
+ define_bool CONFIG_X86_PGE y
+ define_bool CONFIG_X86_USE_PPRO_CHECKSUM y
+ define_bool CONFIG_X86_TSC y
+
+if [ "$CONFIG_M686" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+if [ "$CONFIG_MPENTIUMIII" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+if [ "$CONFIG_MPENTIUM4" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 7
+fi
+if [ "$CONFIG_MK7" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 6
+ define_bool CONFIG_X86_USE_3DNOW y
+fi
+
+choice 'High Memory Support' \
+ "off CONFIG_NOHIGHMEM \
+ 4GB CONFIG_HIGHMEM4G \
+ 64GB CONFIG_HIGHMEM64G" off
+if [ "$CONFIG_HIGHMEM4G" = "y" ]; then
+ define_bool CONFIG_HIGHMEM y
+fi
+if [ "$CONFIG_HIGHMEM64G" = "y" ]; then
+ define_bool CONFIG_HIGHMEM y
+ define_bool CONFIG_X86_PAE y
+fi
+
+#bool 'Symmetric multi-processing support' CONFIG_SMP
+#if [ "$CONFIG_SMP" = "y" -a "$CONFIG_X86_CMPXCHG" = "y" ]; then
+# define_bool CONFIG_HAVE_DEC_LOCK y
+#fi
+endmenu
+
+mainmenu_option next_comment
+comment 'General setup'
+
+bool 'Networking support' CONFIG_NET
+
+bool 'System V IPC' CONFIG_SYSVIPC
+bool 'BSD Process Accounting' CONFIG_BSD_PROCESS_ACCT
+bool 'Sysctl support' CONFIG_SYSCTL
+if [ "$CONFIG_PROC_FS" = "y" ]; then
+ choice 'Kernel core (/proc/kcore) format' \
+ "ELF CONFIG_KCORE_ELF \
+ A.OUT CONFIG_KCORE_AOUT" ELF
+fi
+tristate 'Kernel support for a.out binaries' CONFIG_BINFMT_AOUT
+tristate 'Kernel support for ELF binaries' CONFIG_BINFMT_ELF
+tristate 'Kernel support for MISC binaries' CONFIG_BINFMT_MISC
+
+endmenu
+
+if [ "$CONFIG_NET" = "y" ]; then
+ source net/Config.in
+fi
+
+source drivers/block/Config.in
+define_bool CONFIG_BLK_DEV_IDE_MODES n
+define_bool CONFIG_BLK_DEV_HD n
+
+source fs/Config.in
+
+mainmenu_option next_comment
+comment 'Kernel hacking'
+
+bool 'Kernel debugging' CONFIG_DEBUG_KERNEL
+if [ "$CONFIG_DEBUG_KERNEL" != "n" ]; then
+ bool ' Debug high memory support' CONFIG_DEBUG_HIGHMEM
+ bool ' Debug memory allocations' CONFIG_DEBUG_SLAB
+ bool ' Memory mapped I/O debugging' CONFIG_DEBUG_IOVIRT
+ bool ' Magic SysRq key' CONFIG_MAGIC_SYSRQ
+ bool ' Spinlock debugging' CONFIG_DEBUG_SPINLOCK
+ bool ' Verbose BUG() reporting (adds 70K)' CONFIG_DEBUG_BUGVERBOSE
+ bool ' Built-in Kernel Debugger support' CONFIG_KDB
+ dep_tristate ' KDB modules' CONFIG_KDB_MODULES $CONFIG_KDB
+ if [ "$CONFIG_KDB" = "y" ]; then
+ bool ' KDB off by default' CONFIG_KDB_OFF
+ comment ' Load all symbols for debugging is required for KDB'
+ define_bool CONFIG_KALLSYMS y
+ else
+ bool ' Load all symbols for debugging' CONFIG_KALLSYMS
+ fi
+ bool ' Compile the kernel with frame pointers' CONFIG_FRAME_POINTER
+fi
+
+endmenu
--- /dev/null
+#
+# Automatically generated make config: don't edit
+#
+CONFIG_X86=y
+CONFIG_ISA=y
+# CONFIG_SBUS is not set
+CONFIG_UID16=y
+
+#
+# Code maturity level options
+#
+# CONFIG_EXPERIMENTAL is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODVERSIONS=y
+CONFIG_KMOD=y
+
+#
+# Processor type and features
+#
+# CONFIG_M386 is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+CONFIG_M686=y
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP2 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MCYRIXIII is not set
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_L1_CACHE_SHIFT=5
+CONFIG_X86_TSC=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_PGE=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
+# CONFIG_X86_CPUID is not set
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
+# CONFIG_MATH_EMULATION is not set
+# CONFIG_MTRR is not set
+# CONFIG_SMP is not set
+# CONFIG_X86_UP_APIC is not set
+
+#
+# General setup
+#
+CONFIG_NET=y
+# CONFIG_PCI is not set
+# CONFIG_EISA is not set
+# CONFIG_MCA is not set
+# CONFIG_HOTPLUG is not set
+# CONFIG_PCMCIA is not set
+# CONFIG_HOTPLUG_PCI is not set
+CONFIG_SYSVIPC=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_KCORE_ELF=y
+# CONFIG_KCORE_AOUT is not set
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_MISC is not set
+# CONFIG_PM is not set
+# CONFIG_APM_IGNORE_USER_SUSPEND is not set
+# CONFIG_APM_DO_ENABLE is not set
+# CONFIG_APM_CPU_IDLE is not set
+# CONFIG_APM_DISPLAY_BLANK is not set
+# CONFIG_APM_RTC_IS_GMT is not set
+# CONFIG_APM_ALLOW_INTS is not set
+# CONFIG_APM_REAL_MODE_POWER_OFF is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play configuration
+#
+# CONFIG_PNP is not set
+
+#
+# Block devices
+#
+# CONFIG_BLK_DEV_FD is not set
+# CONFIG_BLK_DEV_XD is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=4096
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_XENOLINUX_BLOCK=y
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+CONFIG_NETLINK=y
+CONFIG_RTNETLINK=y
+# CONFIG_NETLINK_DEV is not set
+# CONFIG_NETFILTER is not set
+CONFIG_FILTER=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_PNP=y
+# CONFIG_IP_PNP_DHCP is not set
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_INET_ECN is not set
+# CONFIG_SYN_COOKIES is not set
+
+#
+#
+#
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_DECNET is not set
+# CONFIG_BRIDGE is not set
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# ATA/IDE/MFM/RLL support
+#
+# CONFIG_IDE is not set
+# CONFIG_BLK_DEV_IDE_MODES is not set
+# CONFIG_BLK_DEV_HD is not set
+
+#
+# SCSI support
+#
+# CONFIG_SCSI is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION_BOOT is not set
+# CONFIG_FUSION_ISENSE is not set
+# CONFIG_FUSION_CTL is not set
+# CONFIG_FUSION_LAN is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+
+#
+# Network device support
+#
+# CONFIG_NETDEVICES is not set
+
+#
+# Amateur Radio support
+#
+# CONFIG_HAMRADIO is not set
+
+#
+# IrDA (infrared) support
+#
+# CONFIG_IRDA is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Old CD-ROM drivers (not SCSI, not IDE)
+#
+# CONFIG_CD_NO_IDESCSI is not set
+
+#
+# Input core support
+#
+# CONFIG_INPUT is not set
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+# CONFIG_SERIAL is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_UNIX98_PTYS is not set
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# Mice
+#
+# CONFIG_BUSMOUSE is not set
+# CONFIG_MOUSE is not set
+
+#
+# Joysticks
+#
+# CONFIG_INPUT_GAMEPORT is not set
+
+#
+# Input core support is needed for gameports
+#
+
+#
+# Input core support is needed for joysticks
+#
+# CONFIG_QIC02_TAPE is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_FTAPE is not set
+# CONFIG_AGP is not set
+# CONFIG_DRM is not set
+# CONFIG_MWAVE is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# File systems
+#
+# CONFIG_QUOTA is not set
+CONFIG_AUTOFS_FS=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_JBD=y
+# CONFIG_FAT_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_TMPFS is not set
+# CONFIG_RAMFS is not set
+# CONFIG_ISO9660_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_NTFS_FS is not set
+# CONFIG_HPFS_FS is not set
+CONFIG_PROC_FS=y
+# CONFIG_ROMFS_FS is not set
+CONFIG_EXT2_FS=y
+# CONFIG_SYSV_FS is not set
+# CONFIG_UDF_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+# CONFIG_CODA_FS is not set
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V3=y
+CONFIG_SUNRPC=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+# CONFIG_SMB_FS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_ZISOFS_FS is not set
+# CONFIG_ZLIB_FS_INFLATE is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_SMB_NLS is not set
+# CONFIG_NLS is not set
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+
+#
+# USB Controllers
+#
+
+#
+# USB Device Class drivers
+#
+
+#
+# USB Human Interface Devices (HID)
+#
+
+#
+# Input core support is needed for USB HID
+#
+
+#
+# USB Imaging devices
+#
+
+#
+# USB Multimedia devices
+#
+
+#
+# Video4Linux support is needed for USB Multimedia device support
+#
+
+#
+# USB Network adaptors
+#
+
+#
+# USB port drivers
+#
+
+#
+# USB Serial Converter support
+#
+
+#
+# USB Miscellaneous drivers
+#
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_HIGHMEM is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_IOVIRT is not set
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_KDB is not set
+CONFIG_KALLSYMS=y
+# CONFIG_FRAME_POINTER is not set
--- /dev/null
+O_TARGET := blk.o
+obj-y := xl_block.o xl_block_test.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/******************************************************************************
+ * xl_block.c
+ *
+ * Xenolinux virtual block-device driver.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+
+#include <linux/fs.h>
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/major.h>
+
+#include <asm/hypervisor-ifs/block.h>
+#include <asm/hypervisor-ifs/hypervisor-if.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+#define MAJOR_NR XLBLK_MAJOR /* force defns in blk.h, must precede include */
+static int xlblk_major = XLBLK_MAJOR;
+#include <linux/blk.h>
+
+/* Copied from linux/ide.h */
+typedef unsigned char byte;
+
+void xlblk_ide_register_disk(int, unsigned long);
+
+#define XLBLK_MAX 32 /* Maximum minor devices we support */
+#define XLBLK_MAJOR_NAME "xhd"
+#define IDE_PARTN_BITS 6 /* from ide.h::PARTN_BITS */
+#define IDE_PARTN_MASK ((1<<IDE_PARTN_BITS)-1) /* from ide.h::PARTN_MASK */
+static int xlblk_blk_size[XLBLK_MAX];
+static int xlblk_blksize_size[XLBLK_MAX];
+static int xlblk_read_ahead;
+static int xlblk_hardsect_size[XLBLK_MAX];
+static int xlblk_max_sectors[XLBLK_MAX];
+
+#define XLBLK_RESPONSE_IRQ _EVENT_BLK_RESP
+
+#define DEBUG_IRQ _EVENT_DEBUG
+
+#if 0
+#define DPRINTK(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#define DPRINTK_IOCTL(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#else
+#define DPRINTK(_f, _a...) ((void)0)
+#define DPRINTK_IOCTL(_f, _a...) ((void)0)
+#endif
+
+static blk_ring_t *blk_ring;
+static unsigned int resp_cons; /* Response consumer for comms ring. */
+static xen_disk_info_t xen_disk_info;
+
+int hypervisor_request(void * id,
+ int operation,
+ char * buffer,
+ unsigned long block_number,
+ unsigned short block_size,
+ kdev_t device);
+
+
+/* ------------------------------------------------------------------------
+ */
+
+static int xenolinux_block_open(struct inode *inode, struct file *filep)
+{
+ DPRINTK("xenolinux_block_open\n");
+ return 0;
+}
+
+static int xenolinux_block_release(struct inode *inode, struct file *filep)
+{
+ DPRINTK("xenolinux_block_release\n");
+ return 0;
+}
+
+static int xenolinux_block_ioctl(struct inode *inode, struct file *filep,
+ unsigned command, unsigned long argument)
+{
+ int minor_dev;
+ struct hd_geometry *geo = (struct hd_geometry *)argument;
+
+ DPRINTK("xenolinux_block_ioctl\n");
+
+ /* check permissions */
+ if (!capable(CAP_SYS_ADMIN)) return -EPERM;
+ if (!inode) return -EINVAL;
+ minor_dev = MINOR(inode->i_rdev);
+ if (minor_dev >= XLBLK_MAX) return -ENODEV;
+
+ DPRINTK_IOCTL("command: 0x%x, argument: 0x%lx, minor: 0x%x\n",
+ command, (long) argument, minor_dev);
+
+ switch (command)
+ {
+ case BLKGETSIZE:
+ DPRINTK_IOCTL(" BLKGETSIZE: %x %lx\n", BLKGETSIZE,
+ (long) xen_disk_info.disks[0].capacity);
+ return put_user(xen_disk_info.disks[0].capacity,
+ (unsigned long *) argument);
+
+ case BLKRRPART:
+ DPRINTK_IOCTL(" BLKRRPART: %x\n", BLKRRPART);
+ break;
+
+ case BLKSSZGET:
+ DPRINTK_IOCTL(" BLKSSZGET: %x 0x%x\n", BLKSSZGET,
+ xlblk_hardsect_size[minor_dev]);
+ return xlblk_hardsect_size[minor_dev];
+
+ case HDIO_GETGEO:
+ DPRINTK_IOCTL(" HDIO_GETGEO: %x\n", HDIO_GETGEO);
+ if (!argument) return -EINVAL;
+ if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
+ if (put_user(0xff, (byte *)&geo->heads)) return -EFAULT;
+ if (put_user(0x3f, (byte *)&geo->sectors)) return -EFAULT;
+ if (put_user(0x106, (unsigned short *)&geo->cylinders)) return -EFAULT;
+ return 0;
+
+ case HDIO_GETGEO_BIG:
+ DPRINTK_IOCTL(" HDIO_GETGEO_BIG: %x\n", HDIO_GETGEO_BIG);
+ if (!argument) return -EINVAL;
+ if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
+ if (put_user(0xff, (byte *)&geo->heads)) return -EFAULT;
+ if (put_user(0x3f, (byte *)&geo->sectors)) return -EFAULT;
+ if (put_user(0x106, (unsigned int *) &geo->cylinders)) return -EFAULT;
+
+ return 0;
+
+ default:
+ DPRINTK_IOCTL(" eh? unknown ioctl\n");
+ break;
+ }
+
+ return 0;
+}
+
+static int xenolinux_block_check(kdev_t dev)
+{
+ DPRINTK("xenolinux_block_check\n");
+ return 0;
+}
+
+static int xenolinux_block_revalidate(kdev_t dev)
+{
+ DPRINTK("xenolinux_block_revalidate\n");
+ return 0;
+}
+
+/*
+ * hypervisor_request
+ *
+ * request block io
+ *
+ * id: for guest use only.
+ * operation: XEN_BLOCK_READ, XEN_BLOCK_WRITE or XEN_BLOCK_PROBE
+ * buffer: buffer to read/write into. this should be a
+ * virtual address in the guest os.
+ * block_number: block to read
+ * block_size: size of each block
+ * device: ide/hda is 768 or 0x300
+ */
+int hypervisor_request(void * id,
+ int operation,
+ char * buffer,
+ unsigned long block_number,
+ unsigned short block_size,
+ kdev_t device)
+{
+ int position;
+ void *buffer_ma;
+ kdev_t phys_device = (kdev_t) 0;
+ unsigned long sector_number = 0;
+ struct gendisk *gd;
+
+ /*
+ * Bail if there's no room in the request communication ring. This may be
+ * because we have a whole bunch of outstanding responses to process. No
+ * matter, as the response handler will kick the request queue.
+ */
+ if ( BLK_RING_INC(blk_ring->req_prod) == resp_cons )
+ return 1;
+
+ buffer_ma = (void *)phys_to_machine(virt_to_phys(buffer));
+
+ switch ( operation )
+ {
+ case XEN_BLOCK_PROBE:
+ phys_device = (kdev_t) 0;
+ sector_number = 0;
+ break;
+
+ case XEN_BLOCK_READ:
+ case XEN_BLOCK_WRITE:
+ if ( MAJOR(device) != XLBLK_MAJOR )
+ panic("error: xl_block::hypervisor_request: "
+ "unknown device [0x%x]\n", device);
+ phys_device = MKDEV(IDE0_MAJOR, 0);
+ /* Compute real buffer location on disk */
+ sector_number = block_number;
+ if ( (gd = (struct gendisk *)xen_disk_info.disks[0].gendisk) != NULL )
+ sector_number += gd->part[MINOR(device)&IDE_PARTN_MASK].start_sect;
+ break;
+
+ default:
+ panic("unknown op %d\n", operation);
+ }
+
+ /* Fill out a communications ring structure & trap to the hypervisor */
+ position = blk_ring->req_prod;
+ blk_ring->ring[position].req.id = id;
+ blk_ring->ring[position].req.operation = operation;
+ blk_ring->ring[position].req.buffer = buffer_ma;
+ blk_ring->ring[position].req.block_number = block_number;
+ blk_ring->ring[position].req.block_size = block_size;
+ blk_ring->ring[position].req.device = phys_device;
+ blk_ring->ring[position].req.sector_number = sector_number;
+
+ blk_ring->req_prod = BLK_RING_INC(position);
+
+ return 0;
+}
+
+
+/*
+ * do_xlblk_request
+ * read a block; request is in a request queue
+ */
+static void do_xlblk_request (request_queue_t *rq)
+{
+ struct request *req;
+ struct buffer_head *bh;
+ int rw, nsect, full, queued = 0;
+
+ DPRINTK("xlblk.c::do_xlblk_request for '%s'\n", DEVICE_NAME);
+
+ while ( !rq->plugged && !QUEUE_EMPTY )
+ {
+ if ( (req = CURRENT) == NULL ) goto out;
+
+ DPRINTK("do_xlblk_request %p: cmd %i, sec %lx, (%li/%li) bh:%p\n",
+ req, req->cmd, req->sector,
+ req->current_nr_sectors, req->nr_sectors, req->bh);
+
+ rw = req->cmd;
+ if ( rw == READA ) rw = READ;
+ if ((rw != READ) && (rw != WRITE))
+ panic("XenoLinux Virtual Block Device: bad cmd: %d\n", rw);
+
+ req->errors = 0;
+
+ bh = req->bh;
+ while ( bh != NULL )
+ {
+ full = hypervisor_request(
+ bh, (rw == READ) ? XEN_BLOCK_READ : XEN_BLOCK_WRITE,
+ bh->b_data, bh->b_rsector, bh->b_size, bh->b_dev);
+
+ if ( full ) goto out;
+
+ queued++;
+
+ /* Dequeue the buffer head from the request. */
+ nsect = bh->b_size >> 9;
+ req->bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+ bh = req->bh;
+
+ if ( bh != NULL )
+ {
+ /* There's another buffer head to do. Update the request. */
+ req->hard_sector += nsect;
+ req->hard_nr_sectors -= nsect;
+ req->sector = req->hard_sector;
+ req->nr_sectors = req->hard_nr_sectors;
+ req->current_nr_sectors = bh->b_size >> 9;
+ req->buffer = bh->b_data;
+ }
+ else
+ {
+ /* That was the last buffer head. Finalise the request. */
+ if ( end_that_request_first(req, 1, "XenBlk") ) BUG();
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+ }
+ }
+ }
+
+ out:
+ if ( queued != 0 ) HYPERVISOR_block_io_op();
+}
+
+
+static struct block_device_operations xenolinux_block_fops =
+{
+ open: xenolinux_block_open,
+ release: xenolinux_block_release,
+ ioctl: xenolinux_block_ioctl,
+ check_media_change: xenolinux_block_check,
+ revalidate: xenolinux_block_revalidate,
+};
+
+static void xlblk_response_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ int i;
+ unsigned long flags;
+ struct buffer_head *bh;
+
+ spin_lock_irqsave(&io_request_lock, flags);
+
+ for ( i = resp_cons;
+ i != blk_ring->resp_prod;
+ i = BLK_RING_INC(i) )
+ {
+ blk_ring_resp_entry_t *bret = &blk_ring->ring[i].resp;
+ if ( (bh = bret->id) != NULL ) bh->b_end_io(bh, 1);
+ }
+
+ resp_cons = i;
+
+ /* KAF: We can push work down at this point. We have the lock. */
+ do_xlblk_request(BLK_DEFAULT_QUEUE(MAJOR_NR));
+
+ spin_unlock_irqrestore(&io_request_lock, flags);
+}
+
+
+int __init xlblk_init(void)
+{
+ int i, error, result;
+
+ /* This mapping was created early at boot time. */
+ blk_ring = (blk_ring_t *)fix_to_virt(FIX_BLKRING_BASE);
+ blk_ring->req_prod = blk_ring->resp_prod = resp_cons = 0;
+
+ error = request_irq(XLBLK_RESPONSE_IRQ, xlblk_response_int, 0,
+ "xlblk-response", NULL);
+ if (error) {
+ printk(KERN_ALERT "Could not allocate receive interrupt\n");
+ goto fail;
+ }
+
+ memset (&xen_disk_info, 0, sizeof(xen_disk_info));
+ xen_disk_info.count = 0;
+
+ if ( hypervisor_request(NULL, XEN_BLOCK_PROBE, (char *) &xen_disk_info,
+ 0, 0, (kdev_t) 0) )
+ BUG();
+ HYPERVISOR_block_io_op();
+ while ( blk_ring->resp_prod != 1 ) barrier();
+ for ( i = 0; i < xen_disk_info.count; i++ )
+ {
+ printk (KERN_ALERT " %2d: type: %d, capacity: %ld\n",
+ i, xen_disk_info.disks[i].type,
+ xen_disk_info.disks[i].capacity);
+ }
+
+ SET_MODULE_OWNER(&xenolinux_block_fops);
+ result = register_blkdev(xlblk_major, "block", &xenolinux_block_fops);
+ if (result < 0) {
+ printk (KERN_ALERT "xenolinux block: can't get major %d\n",
+ xlblk_major);
+ return result;
+ }
+
+ /* initialize global arrays in drivers/block/ll_rw_block.c */
+ for (i = 0; i < XLBLK_MAX; i++) {
+ xlblk_blk_size[i] = xen_disk_info.disks[0].capacity;
+ xlblk_blksize_size[i] = 512;
+ xlblk_hardsect_size[i] = 512;
+ xlblk_max_sectors[i] = 128;
+ }
+ xlblk_read_ahead = 8;
+
+ blk_size[xlblk_major] = xlblk_blk_size;
+ blksize_size[xlblk_major] = xlblk_blksize_size;
+ hardsect_size[xlblk_major] = xlblk_hardsect_size;
+ read_ahead[xlblk_major] = xlblk_read_ahead;
+ max_sectors[xlblk_major] = xlblk_max_sectors;
+
+ blk_init_queue(BLK_DEFAULT_QUEUE(xlblk_major), do_xlblk_request);
+
+ /*
+ * Turn off barking 'headactive' mode. We dequeue buffer heads as
+ * soon as we pass them down to Xen.
+ */
+ blk_queue_headactive(BLK_DEFAULT_QUEUE(xlblk_major), 0);
+
+ xlblk_ide_register_disk(0, xen_disk_info.disks[0].capacity);
+
+ printk(KERN_ALERT
+ "XenoLinux Virtual Block Device Driver installed [device: %d]\n",
+ xlblk_major);
+ return 0;
+
+ fail:
+ return error;
+}
+
+void xlblk_ide_register_disk(int idx, unsigned long capacity)
+{
+ int units;
+ int minors;
+ struct gendisk *gd;
+
+ /* plagarized from ide-probe.c::init_gendisk */
+
+ units = 2; /* from ide.h::MAX_DRIVES */
+
+ minors = units * (1<<IDE_PARTN_BITS);
+ gd = kmalloc (sizeof(struct gendisk), GFP_KERNEL);
+ gd->sizes = kmalloc (minors * sizeof(int), GFP_KERNEL);
+ gd->part = kmalloc (minors * sizeof(struct hd_struct), GFP_KERNEL);
+ memset(gd->part, 0, minors * sizeof(struct hd_struct));
+
+ gd->major = xlblk_major;
+ gd->major_name = XLBLK_MAJOR_NAME;
+ gd->minor_shift = IDE_PARTN_BITS;
+ gd->max_p = 1<<IDE_PARTN_BITS;
+ gd->nr_real = units;
+ gd->real_devices = NULL;
+ gd->next = NULL;
+ gd->fops = &xenolinux_block_fops;
+ gd->de_arr = kmalloc (sizeof *gd->de_arr * units, GFP_KERNEL);
+ gd->flags = kmalloc (sizeof *gd->flags * units, GFP_KERNEL);
+
+ if (gd->de_arr)
+ memset (gd->de_arr, 0, sizeof *gd->de_arr * units);
+
+ if (gd->flags)
+ memset (gd->flags, 0, sizeof *gd->flags * units);
+
+ add_gendisk(gd);
+
+ xen_disk_info.disks[idx].gendisk = gd;
+
+ /* default disk size is just a big number. in the future, we
+ need a message to probe the devices to determine the actual size */
+ register_disk(gd, MKDEV(xlblk_major, 0), 1<<IDE_PARTN_BITS,
+ &xenolinux_block_fops, capacity);
+
+ return;
+}
+
+
+
+static void __exit xlblk_cleanup(void)
+{
+ /* CHANGE FOR MULTIQUEUE */
+ blk_cleanup_queue(BLK_DEFAULT_QUEUE(xlblk_major));
+
+ /* clean up global arrays */
+ read_ahead[xlblk_major] = 0;
+
+ if (blk_size[xlblk_major])
+ kfree(blk_size[xlblk_major]);
+ blk_size[xlblk_major] = NULL;
+
+ if (blksize_size[xlblk_major])
+ kfree(blksize_size[xlblk_major]);
+ blksize_size[xlblk_major] = NULL;
+
+ if (hardsect_size[xlblk_major])
+ kfree(hardsect_size[xlblk_major]);
+ hardsect_size[xlblk_major] = NULL;
+
+ /* XXX: free each gendisk */
+ if (unregister_blkdev(xlblk_major, "block"))
+ printk(KERN_ALERT
+ "XenoLinux Virtual Block Device Driver uninstalled w/ errs\n");
+ else
+ printk(KERN_ALERT
+ "XenoLinux Virtual Block Device Driver uninstalled\n");
+
+ return;
+}
+
+
+#ifdef MODULE
+module_init(xlblk_init);
+module_exit(xlblk_cleanup);
+#endif
--- /dev/null
+/******************************************************************************
+ * xenolinux_block_test.c
+ *
+ */
+#define EXPORT_SYMTAB
+
+#include <linux/config.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <asm/uaccess.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+
+#include <asm/hypervisor-ifs/block.h>
+#include <asm/hypervisor-ifs/hypervisor-if.h>
+
+/******************************************************************/
+
+static struct proc_dir_entry *bdt;
+static blk_ring_req_entry_t meta;
+static char * data;
+
+static int proc_read_bdt(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ switch (meta.operation)
+ {
+ case XEN_BLOCK_READ :
+ case XEN_BLOCK_WRITE :
+ {
+ return proc_dump_block(page, start, off, count, eof, data);
+ }
+ case XEN_BLOCK_DEBUG :
+ {
+ return proc_dump_debug(page, start, off, count, eof, data);
+ }
+ default :
+ {
+ printk(KERN_ALERT
+ "block device test error: unknown operation [%c]\n",
+ meta.operation);
+ return -EINVAL;
+ }
+ }
+}
+
+int proc_dump_debug(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ char header[100];
+ char dump[1024];
+
+ sprintf (header, "Block Device Test: Debug Dump\n\n");
+
+ sprintf (dump, "%s\n", meta.buffer);
+
+ if (data)
+ {
+ kfree(data);
+ }
+
+ strncpy (page, dump, count);
+ return strlen(page);
+}
+
+int proc_dump_block(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ char header[100];
+ char dump[1024];
+ char temp[100];
+ int loop;
+
+ sprintf (header, "Block Device Test\n\n%s blk num: %ld 0x%lx; size: %d 0x%x; device: 0x%x\n",
+ meta.operation == XEN_BLOCK_WRITE ? "write" : "read",
+ meta.block_number, meta.block_number,
+ meta.block_size, meta.block_size,
+ meta.device);
+
+ sprintf (dump, "%s", header);
+
+ if (meta.buffer)
+ {
+ for (loop = 0; loop < 100; loop++)
+ {
+ int i = meta.buffer[loop];
+
+ if (loop % 8 == 0)
+ {
+ sprintf (temp, "[%2d] ", loop);
+ strcat(dump, temp);
+ }
+ else if (loop % 2 == 0)
+ {
+ strcat(dump, " ");
+ }
+
+ sprintf (temp, " 0x%02x", i & 255);
+ strcat(dump, temp);
+ if ((loop + 1) % 8 == 0)
+ {
+ strcat(dump, "\n");
+ }
+ }
+ strcat(dump, "\n\n");
+ }
+
+ if (data)
+ {
+ kfree(data);
+ }
+
+ strncpy (page, dump, count);
+ return strlen(page);
+}
+
+int proc_write_bdt(struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ char *local = kmalloc((count + 1) * sizeof(char), GFP_KERNEL);
+ char opcode;
+ int block_number = 0;
+ int block_size = 0;
+ int device = 0;
+
+ if (copy_from_user(local, buffer, count))
+ {
+ return -EFAULT;
+ }
+ local[count] = '\0';
+
+ sscanf(local, "%c %i %i %i",
+ &opcode, &block_number, &block_size, &device);
+
+ if (opcode == 'r' || opcode == 'R')
+ {
+ meta.operation = XEN_BLOCK_READ;
+ }
+ else if (opcode == 'w' || opcode == 'W')
+ {
+ meta.operation = XEN_BLOCK_WRITE;
+ }
+ else if (opcode == 'd' || opcode == 'D')
+ {
+ meta.operation = XEN_BLOCK_DEBUG;
+ block_size = 10000;
+ }
+ else
+ {
+ printk(KERN_ALERT
+ "block device test error: unknown opcode [%c]\n", opcode);
+ return -EINVAL;
+ }
+
+ if (data)
+ {
+ kfree(data);
+ }
+ data = kmalloc(block_size * sizeof(char), GFP_KERNEL);
+ if (data == NULL)
+ {
+ kfree(local);
+ return -ENOMEM;
+ }
+
+ meta.block_number = block_number;
+ meta.block_size = block_size;
+ meta.device = device;
+ meta.buffer = data;
+
+ /* submit request */
+ hypervisor_request(0, meta.operation, meta.buffer,
+ meta.block_number, meta.block_size,
+ meta.device);
+ HYPERVISOR_block_io_op();
+ mdelay(1000); /* should wait for a proper acknowledgement/response. */
+
+ kfree(local);
+ return count;
+}
+
+
+static int __init init_module(void)
+{
+ int return_value = 0;
+
+ /* create proc entry */
+ bdt = create_proc_entry("bdt", 0644, NULL);
+ if (bdt == NULL)
+ {
+ return_value = -ENOMEM;
+ goto error;
+ }
+ bdt->data = NULL;
+ bdt->read_proc = proc_read_bdt;
+ bdt->write_proc = proc_write_bdt;
+ bdt->owner = THIS_MODULE;
+
+ memset(&meta, 0, sizeof(meta));
+
+ /* success */
+ printk(KERN_ALERT "XenoLinux Block Device Test installed\n");
+ return 0;
+
+ error:
+ return return_value;
+}
+
+static void __exit cleanup_module(void)
+{
+ if (data)
+ {
+ kfree(data);
+ }
+ printk(KERN_ALERT "XenoLinux Block Device Test uninstalled\n");
+}
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+O_TARGET := con.o
+obj-y := console.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/******************************************************************************
+ * console.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/serial.h>
+#include <linux/major.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/console.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/uaccess.h>
+#include <asm/hypervisor.h>
+
+/******************** Kernel console driver ********************************/
+
+static void kconsole_write(struct console *co, const char *s, unsigned count)
+{
+#define STRLEN 256
+ static char str[STRLEN];
+ static int pos = 0;
+ int len;
+
+ /* We buffer output until we see a newline, or until the buffer is full. */
+ while ( count != 0 )
+ {
+ len = ((STRLEN - pos) > count) ? count : STRLEN - pos;
+ memcpy(str + pos, s, len);
+ pos += len;
+ s += len;
+ count -= len;
+ if ( (pos == STRLEN) || (str[pos-1] == '\n') )
+ {
+ (void)HYPERVISOR_console_write(str, pos);
+ pos = 0;
+ }
+ }
+}
+
+static kdev_t kconsole_device(struct console *c)
+{
+ /*
+ * This is the magic that binds our "struct console" to our
+ * "tty_struct", defined below.
+ */
+ return MKDEV(TTY_MAJOR, 0);
+}
+
+static struct console kconsole_info = {
+ name: "xenocon",
+ write: kconsole_write,
+ device: kconsole_device,
+ flags: CON_PRINTBUFFER,
+ index: -1,
+};
+
+void xeno_console_init(void)
+{
+ register_console(&kconsole_info);
+}
+
+
+/******************** Initial /dev/console *********************************/
+
+
+static struct tty_driver console_driver;
+static int console_refcount;
+static struct tty_struct *console_table[1];
+static struct termios *console_termios[1];
+static struct termios *console_termios_locked[1];
+
+static int console_write_room(struct tty_struct *tty)
+{
+ return INT_MAX;
+}
+
+static int console_chars_in_buffer(struct tty_struct *tty)
+{
+ return 0;
+}
+
+static inline int console_xmit(int ch)
+{
+ char _ch = ch;
+ kconsole_write(NULL, &_ch, 1);
+ return 1;
+}
+
+static int console_write(struct tty_struct *tty, int from_user,
+ const u_char * buf, int count)
+{
+ int i;
+
+ if ( from_user && verify_area(VERIFY_READ, buf, count) )
+ {
+ return -EINVAL;
+ }
+
+ for ( i = 0; i < count; i++ )
+ {
+ char ch;
+ if ( from_user )
+ {
+ __get_user(ch, buf + i);
+ }
+ else
+ {
+ ch = buf[i];
+ }
+ console_xmit(ch);
+ }
+ return i;
+}
+
+static void console_put_char(struct tty_struct *tty, u_char ch)
+{
+ console_xmit(ch);
+}
+
+static int console_open(struct tty_struct *tty, struct file *filp)
+{
+ int line;
+
+ MOD_INC_USE_COUNT;
+ line = MINOR(tty->device) - tty->driver.minor_start;
+ if ( line )
+ {
+ MOD_DEC_USE_COUNT;
+ return -ENODEV;
+ }
+
+ tty->driver_data = NULL;
+
+ return 0;
+}
+
+static void console_close(struct tty_struct *tty, struct file *filp)
+{
+ MOD_DEC_USE_COUNT;
+}
+
+static int __init console_ini(void)
+{
+ memset(&console_driver, 0, sizeof(struct tty_driver));
+ console_driver.magic = TTY_DRIVER_MAGIC;
+ console_driver.driver_name = "xeno_console";
+ console_driver.name = "console";
+ console_driver.major = TTY_MAJOR;
+ console_driver.minor_start = 0;
+ console_driver.num = 1;
+ console_driver.type = TTY_DRIVER_TYPE_SERIAL;
+ console_driver.subtype = SERIAL_TYPE_NORMAL;
+ console_driver.init_termios = tty_std_termios;
+ console_driver.flags = TTY_DRIVER_REAL_RAW;
+ console_driver.refcount = &console_refcount;
+ console_driver.table = console_table;
+ console_driver.termios = console_termios;
+ console_driver.termios_locked = console_termios_locked;
+ /* Functions */
+ console_driver.open = console_open;
+ console_driver.close = console_close;
+ console_driver.write = console_write;
+ console_driver.write_room = console_write_room;
+ console_driver.put_char = console_put_char;
+ console_driver.chars_in_buffer = console_chars_in_buffer;
+
+ if ( tty_register_driver(&console_driver) )
+ {
+ printk(KERN_ERR "Couldn't register Xeno console driver\n");
+ }
+ else
+ {
+ printk("Xeno console successfully installed\n");
+ }
+
+ return 0;
+}
+
+static void __exit console_fin(void)
+{
+ int ret;
+
+ ret = tty_unregister_driver(&console_driver);
+ if ( ret != 0 )
+ {
+ printk(KERN_ERR "Unable to unregister Xeno console driver: %d\n", ret);
+ }
+}
+
+module_init(console_ini);
+module_exit(console_fin);
+
--- /dev/null
+O_TARGET := dom0.o
+obj-y := dom0_memory.o dom0_core.o vfr.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * domain 0 block driver interface
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
+static int __init init_module(void)
+{
+ request_module("xl_block");
+ printk("Successfully installed domain 0 block interface\n");
+
+
+ return 0;
+}
+
+static void __exit cleanup_module(void)
+{
+ printk("Successfully de-installed domain-0 block interface\n");
+ return 0;
+}
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+/******************************************************************************
+ * dom0_core.c
+ *
+ * Interface to privileged domain-0 commands.
+ *
+ * Copyright (c) 2002, K A Fraser, B Dragovic
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+
+#include "dom0_ops.h"
+
+/* Private proc-file data structures. */
+typedef struct proc_data {
+ unsigned int domain;
+ unsigned long map_size;
+} dom_procdata_t;
+
+typedef struct proc_mem_data {
+ unsigned long pfn;
+ int tot_pages;
+} proc_memdata_t;
+
+#define XENO_BASE "xeno"
+#define DOM0_CMD_INTF "dom0_cmd"
+#define DOM0_NEWDOM "new_dom_data"
+
+#define MAX_LEN 16
+#define DOM_DIR "dom"
+#define DOM_MEM "mem"
+#define DOM_VIF "vif"
+
+#define MAP_DISCONT 1
+
+static struct proc_dir_entry *xeno_base;
+static struct proc_dir_entry *dom0_cmd_intf;
+static struct proc_dir_entry *proc_ft;
+
+unsigned long direct_mmap(unsigned long, unsigned long, pgprot_t, int, int);
+int direct_unmap(unsigned long, unsigned long);
+int direct_disc_unmap(unsigned long, unsigned long, int);
+
+static unsigned char readbuf[1204];
+
+static int cmd_read_proc(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ strcpy(page, readbuf);
+ *readbuf = '\0';
+ *eof = 1;
+ *start = page;
+ return strlen(page);
+}
+
+static ssize_t dom_vif_read(struct file * file, char * buff, size_t size, loff_t * off)
+{
+ char hyp_buf[128]; // Hypervisor is going to write its reply here.
+ network_op_t op;
+ static int finished = 0;
+
+ // This seems to be the only way to make the OS stop making read requests
+ // to the file. When we use the fileoperations version of read, offset
+ // seems to be ignored altogether.
+
+ if (finished)
+ {
+ finished = 0;
+ return 0;
+ }
+
+ op.cmd = NETWORK_OP_VIFQUERY;
+ op.u.vif_query.domain = (unsigned int) ((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
+ op.u.vif_query.buf = hyp_buf;
+
+ strcpy(hyp_buf, "Error getting domain's vif list from hypervisor.\n"); // This will be replaced if everything works.
+
+ (void)HYPERVISOR_network_op(&op);
+
+ if (*off >= (strlen(hyp_buf)+1)) return 0;
+
+ copy_to_user(buff, hyp_buf, strlen(hyp_buf));
+
+ finished = 1;
+
+ return strlen(hyp_buf)+1;
+}
+
+struct file_operations dom_vif_ops = {
+ read: dom_vif_read
+};
+
+
+static void create_proc_dom_entries(int dom)
+{
+ struct proc_dir_entry * dir;
+ dom_procdata_t * dom_data;
+ char dir_name[MAX_LEN];
+ struct proc_dir_entry * file;
+
+ snprintf(dir_name, MAX_LEN, "%s%d", DOM_DIR, dom);
+
+ dom_data = (dom_procdata_t *)kmalloc(sizeof(dom_procdata_t), GFP_KERNEL);
+ dom_data->domain = dom;
+
+ dir = proc_mkdir(dir_name, xeno_base);
+ dir->data = dom_data;
+
+ file = create_proc_entry(DOM_VIF, 0600, dir);
+ if (file != NULL)
+ {
+ file->owner = THIS_MODULE;
+ file->nlink = 1;
+ file->proc_fops = &dom_vif_ops;
+ file->data = (void *) dom;
+ }
+}
+
+static ssize_t dom_mem_write(struct file * file, const char * buff,
+ size_t size , loff_t * off)
+{
+ dom_mem_t mem_data;
+
+ copy_from_user(&mem_data, (dom_mem_t *)buff, sizeof(dom_mem_t));
+
+ if(direct_disc_unmap(mem_data.vaddr, mem_data.start_pfn,
+ mem_data.tot_pages) == 0){
+ return sizeof(sizeof(dom_mem_t));
+ } else {
+ return -1;
+ }
+}
+
+static ssize_t dom_mem_read(struct file * file, char * buff, size_t size, loff_t * off)
+{
+ unsigned long addr;
+ pgprot_t prot;
+
+ proc_memdata_t * mem_data = (proc_memdata_t *)((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
+
+ prot = PAGE_SHARED;
+
+ /* remap the range using xen specific routines */
+
+ addr = direct_mmap(mem_data->pfn << PAGE_SHIFT, mem_data->tot_pages << PAGE_SHIFT, prot, MAP_DISCONT, mem_data->tot_pages);
+
+ copy_to_user((unsigned long *)buff, &addr, sizeof(addr));
+
+ return sizeof(addr);
+}
+
+struct file_operations dom_mem_ops = {
+ read: dom_mem_read,
+ write: dom_mem_write,
+};
+
+static int dom_map_mem(unsigned int dom, unsigned long pfn, int tot_pages)
+{
+ int ret = -ENOENT;
+ struct proc_dir_entry * pd = xeno_base->subdir;
+ struct proc_dir_entry * file;
+ proc_memdata_t * memdata;
+
+ while(pd != NULL){
+
+ if((pd->mode & S_IFDIR) && ((dom_procdata_t *)pd->data)->domain == dom){
+
+ /* check if there is already an entry for mem and if so
+ * remove it.
+ */
+ remove_proc_entry(DOM_MEM, pd);
+
+ /* create new entry with parameters describing what to do
+ * when it is mmaped.
+ */
+ file = create_proc_entry(DOM_MEM, 0600, pd);
+ if(file != NULL)
+ {
+ file->owner = THIS_MODULE;
+ file->nlink = 1;
+ file->proc_fops = &dom_mem_ops;
+
+ memdata = (proc_memdata_t *)kmalloc(sizeof(proc_memdata_t), GFP_KERNEL);
+ memdata->pfn = pfn;
+ memdata->tot_pages = tot_pages;
+ file->data = memdata;
+
+ ret = 0;
+ break;
+ }
+
+ ret = -EAGAIN;
+ break;
+ }
+ pd = pd->next;
+ }
+
+ return ret;
+}
+
+/* function used to retrieve data associated with new domain */
+static ssize_t dom_data_read(struct file * file, char * buff, size_t size, loff_t * off)
+{
+ dom0_newdomain_t * dom_data = (dom0_newdomain_t *)
+ ((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
+
+ copy_to_user((dom0_newdomain_t *)buff, dom_data, sizeof(dom0_newdomain_t));
+
+ remove_proc_entry(DOM0_NEWDOM, xeno_base);
+
+ kfree(dom_data);
+
+ return sizeof(dom0_newdomain_t);
+}
+
+struct file_operations newdom_data_fops = {
+ read: dom_data_read,
+};
+
+static int cmd_write_proc(struct file *file, const char *buffer,
+ u_long count, void *data)
+{
+ dom0_op_t op;
+ int ret = 0;
+ struct proc_dir_entry * new_dom_id;
+ dom0_newdomain_t * params;
+ int i;
+ unsigned long p;
+
+ copy_from_user(&op, buffer, sizeof(dom0_op_t));
+
+ /* do some sanity checks */
+ if(op.cmd > MAX_CMD){
+ ret = -ENOSYS;
+ goto out;
+ }
+
+ if ( op.cmd == MAP_DOM_MEM )
+ {
+ ret = dom_map_mem(op.u.dommem.domain, op.u.dommem.start_pfn,
+ op.u.dommem.tot_pages);
+ }
+ else if ( op.cmd == DO_PGUPDATES )
+ {
+ ret = HYPERVISOR_pt_update(op.u.pgupdate.pgt_update_arr,
+ op.u.pgupdate.num_pgt_updates);
+ }
+ else
+ {
+ ret = HYPERVISOR_dom0_op(&op);
+
+ /* if new domain created, create proc entries */
+ if(op.cmd == DOM0_NEWDOMAIN){
+ create_proc_dom_entries(ret);
+
+ params = (dom0_newdomain_t *)kmalloc(sizeof(dom0_newdomain_t),
+ GFP_KERNEL);
+ params->memory_kb = op.u.newdomain.memory_kb;
+ params->pg_head = op.u.newdomain.pg_head;
+ params->num_vifs = op.u.newdomain.num_vifs;
+ params->domain = op.u.newdomain.domain;
+
+ /* now notify user space of the new domain's id */
+ new_dom_id = create_proc_entry(DOM0_NEWDOM, 0600, xeno_base);
+ if ( new_dom_id != NULL )
+ {
+ new_dom_id->owner = THIS_MODULE;
+ new_dom_id->nlink = 1;
+ new_dom_id->proc_fops = &newdom_data_fops;
+ new_dom_id->data = (void *)params;
+ }
+
+ }
+
+ }
+
+out:
+ return ret;
+
+}
+
+static int __init init_module(void)
+{
+ /* xeno proc root setup */
+ xeno_base = proc_mkdir(XENO_BASE, &proc_root);
+
+ /* xeno control interface */
+ *readbuf = '\0';
+ dom0_cmd_intf = create_proc_entry (DOM0_CMD_INTF, 0600, xeno_base);
+ if ( dom0_cmd_intf != NULL )
+ {
+ dom0_cmd_intf->owner = THIS_MODULE;
+ dom0_cmd_intf->nlink = 1;
+ dom0_cmd_intf->read_proc = cmd_read_proc;
+ dom0_cmd_intf->write_proc = cmd_write_proc;
+ }
+
+ /* set up /proc entries for dom 0 */
+ create_proc_dom_entries(0);
+
+ return 0;
+}
+
+
+static void __exit cleanup_module(void)
+{
+ if ( dom0_cmd_intf == NULL ) return;
+ remove_proc_entry("dom0", &proc_root);
+ dom0_cmd_intf = NULL;
+}
+
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/list.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <asm/mmu.h>
+
+#include "dom0_ops.h"
+
+#define MAP_CONT 0
+#define MAP_DISCONT 1
+
+extern struct list_head * find_direct(struct list_head *, unsigned long);
+
+/*
+ * bd240: functions below perform direct mapping to the real physical pages
+ * needed for mapping various hypervisor specific structures needed in dom0
+ * userspace by various management applications such as domain builder etc.
+ */
+
+#define direct_set_pte(pteptr, pteval) queue_l1_entry_update(__pa(pteptr)|PGREQ_UNCHECKED_UPDATE, (pteval).pte_low)
+
+#define direct_pte_clear(pteptr) queue_l1_entry_update(__pa(pteptr)|PGREQ_UNCHECKED_UPDATE, 0)
+
+#define __direct_pte(x) ((pte_t) { (x) } )
+#define __direct_mk_pte(page_nr,pgprot) __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+#define direct_mk_pte_phys(physpage, pgprot) __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline void forget_pte(pte_t page)
+{
+ if (!pte_none(page)) {
+ printk("forget_pte: old mapping existed!\n");
+ BUG();
+ }
+}
+
+static inline void direct_remappte_range(pte_t * pte, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ pte_t oldpage;
+ oldpage = ptep_get_and_clear(pte);
+
+ direct_set_pte(pte, direct_mk_pte_phys(phys_addr, prot));
+
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ phys_addr += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+
+}
+
+static inline int direct_remappmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ phys_addr -= address;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ direct_remappte_range(pte, address, end - address, address + phys_addr, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+/* Note: this is only safe if the mm semaphore is held when called. */
+int direct_remap_page_range(unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = from;
+ unsigned long end = from + size;
+ struct mm_struct *mm = current->mm;
+
+ phys_addr -= from;
+ dir = pgd_offset(mm, from);
+ flush_cache_range(mm, beg, end);
+ if (from >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, from);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = direct_remappmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
+ if (error)
+ break;
+ from = (from + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (from && (from < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * used for remapping discontiguous bits of domain's memory, pages to map are
+ * found from frame table beginning at the given first_pg index
+ */
+int direct_remap_disc_page_range(unsigned long from,
+ unsigned long first_pg, int tot_pages, pgprot_t prot)
+{
+ dom0_op_t dom0_op;
+ unsigned long *pfns = get_free_page(GFP_KERNEL);
+ unsigned long start = from;
+ int pages, i;
+
+ while ( tot_pages != 0 )
+ {
+ dom0_op.cmd = DOM0_GETMEMLIST;
+ dom0_op.u.getmemlist.start_pfn = first_pg;
+ pages = 1023;
+ dom0_op.u.getmemlist.num_pfns = 1024;
+ if ( tot_pages < 1024 )
+ dom0_op.u.getmemlist.num_pfns = pages = tot_pages;
+ dom0_op.u.getmemlist.buffer = pfns;
+ (void)HYPERVISOR_dom0_op(&dom0_op);
+ first_pg = pfns[1023];
+
+ for ( i = 0; i < pages; i++ )
+ {
+ if(direct_remap_page_range(start, pfns[i] << PAGE_SHIFT,
+ PAGE_SIZE, prot))
+ goto out;
+ start += PAGE_SIZE;
+ tot_pages--;
+ }
+ }
+
+out:
+ free_page(pfns);
+ return tot_pages;
+}
+
+/* below functions replace standard sys_mmap and sys_munmap which are absolutely useless
+ * for direct memory mapping. direct_zap* functions are minor ammendments to the
+ * original versions in mm/memory.c. the changes are to enable unmapping of real physical
+ * addresses.
+ */
+
+unsigned long direct_mmap(unsigned long phys_addr, unsigned long size,
+ pgprot_t prot, int flag, int tot_pages)
+{
+ direct_mmap_node_t * dmmap;
+ struct list_head * entry;
+ unsigned long addr;
+ int ret = 0;
+
+ if(!capable(CAP_SYS_ADMIN)){
+ ret = -EPERM;
+ goto out;
+ }
+
+ /* get unmapped area invokes xen specific arch_get_unmapped_area */
+ addr = get_unmapped_area(NULL, 0, size, 0, 0);
+ if(addr & ~PAGE_MASK){
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* add node on the list of directly mapped areas, make sure the
+ * list remains sorted.
+ */
+ dmmap = (direct_mmap_node_t *)kmalloc(sizeof(direct_mmap_node_t), GFP_KERNEL);
+ dmmap->vm_start = addr;
+ dmmap->vm_end = addr + size;
+ entry = find_direct(¤t->mm->context.direct_list, addr);
+ if(entry != ¤t->mm->context.direct_list){
+ list_add_tail(&dmmap->list, entry);
+ } else {
+ list_add_tail(&dmmap->list, ¤t->mm->context.direct_list);
+ }
+
+ /* and perform the mapping */
+ if(flag == MAP_DISCONT){
+ ret = direct_remap_disc_page_range(addr, phys_addr >> PAGE_SHIFT,
+ tot_pages, prot);
+ } else {
+ ret = direct_remap_page_range(addr, phys_addr, size, prot);
+ }
+
+ if(ret == 0)
+ ret = addr;
+
+out:
+ return ret;
+}
+
+/* most of the checks, refcnt updates, cache stuff have been thrown out as they are not
+ * needed
+ */
+static inline int direct_zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address,
+ unsigned long size)
+{
+ unsigned long offset;
+ pte_t * ptep;
+ int freed = 0;
+
+ if (pmd_none(*pmd))
+ return 0;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return 0;
+ }
+ ptep = pte_offset(pmd, address);
+ offset = address & ~PMD_MASK;
+ if (offset + size > PMD_SIZE)
+ size = PMD_SIZE - offset;
+ size &= PAGE_MASK;
+ for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
+ pte_t pte = *ptep;
+ if (pte_none(pte))
+ continue;
+ freed ++;
+ direct_pte_clear(ptep);
+ }
+
+ return freed;
+}
+
+static inline int direct_zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir,
+ unsigned long address, unsigned long size)
+{
+ pmd_t * pmd;
+ unsigned long end;
+ int freed;
+
+ if (pgd_none(*dir))
+ return 0;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return 0;
+ }
+ pmd = pmd_offset(dir, address);
+ end = address + size;
+ if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
+ end = ((address + PGDIR_SIZE) & PGDIR_MASK);
+ freed = 0;
+ do {
+ freed += direct_zap_pte_range(tlb, pmd, address, end - address);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address < end);
+ return freed;
+}
+
+/*
+ * remove user pages in a given range.
+ */
+void direct_zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
+{
+ mmu_gather_t *tlb;
+ pgd_t * dir;
+ unsigned long start = address, end = address + size;
+ int freed = 0;
+
+ dir = pgd_offset(mm, address);
+
+ /*
+ * This is a long-lived spinlock. That's fine.
+ * There's no contention, because the page table
+ * lock only protects against kswapd anyway, and
+ * even if kswapd happened to be looking at this
+ * process we _want_ it to get stuck.
+ */
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ flush_cache_range(mm, address, end);
+ tlb = tlb_gather_mmu(mm);
+
+ do {
+ freed += direct_zap_pmd_range(tlb, dir, address, end - address);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+
+ /* this will flush any remaining tlb entries */
+ tlb_finish_mmu(tlb, start, end);
+
+ /* decrementing rss removed */
+
+ spin_unlock(&mm->page_table_lock);
+}
+
+int direct_unmap(unsigned long addr, unsigned long size)
+{
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if(node->vm_start == addr)
+ break;
+ curr = curr->next;
+ }
+
+ if(curr == direct_list)
+ return -1;
+
+ list_del(&node->list);
+ kfree(node);
+
+ direct_zap_page_range(current->mm, addr, size);
+
+ return 0;
+}
+
+int direct_disc_unmap(unsigned long from, unsigned long first_pg, int tot_pages)
+{
+ int count = 0;
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+
+ if(node->vm_start == from)
+ break;
+ curr = curr->next;
+ }
+
+ if(curr == direct_list)
+ return -1;
+
+ list_del(&node->list);
+ kfree(node);
+
+ while(count < tot_pages){
+ direct_zap_page_range(current->mm, from, PAGE_SIZE);
+ from += PAGE_SIZE;
+ count++;
+ }
+
+ return 0;
+}
--- /dev/null
+/******************************************************************************
+ * dom0_ops.h
+ *
+ * Process command requests from domain-0 guest OS.
+ *
+ * Copyright (c) 2002, K A Fraser, B Dragovic
+ */
+
+#define DOM0_NEWDOMAIN 0
+#define DOM0_KILLDOMAIN 1
+#define DOM0_GETMEMLIST 2
+#define DOM0_STARTDOM 4
+#define MAP_DOM_MEM 6 /* Not passed down to Xen */
+#define DO_PGUPDATES 7 /* Not passed down to Xen */
+#define MAX_CMD 8
+
+#define MAX_CMD_LEN 256
+
+typedef struct dom0_newdomain_st
+{
+ unsigned int domain;
+ unsigned int memory_kb;
+ unsigned int num_vifs; // temporary
+ unsigned long pg_head; // return parameter
+} dom0_newdomain_t;
+
+typedef struct dom0_killdomain_st
+{
+ unsigned int domain;
+} dom0_killdomain_t;
+
+typedef struct dom0_getmemlist_st
+{
+ unsigned long start_pfn;
+ unsigned long num_pfns;
+ void *buffer;
+} dom0_getmemlist_t;
+
+/* This is entirely processed by XenoLinux */
+typedef struct dom_mem
+{
+ unsigned int domain;
+ unsigned long vaddr;
+ unsigned long start_pfn;
+ int tot_pages;
+} dom_mem_t;
+
+/* This is entirely processed by XenoLinux */
+typedef struct dom_pgupdate
+{
+ unsigned long pgt_update_arr;
+ unsigned long num_pgt_updates;
+} dom_pgupdate_t;
+
+typedef struct domain_launch
+{
+ unsigned int domain;
+ unsigned long l2_pgt_addr;
+ unsigned long virt_load_addr;
+ unsigned long virt_shinfo_addr;
+ unsigned long virt_startinfo_addr;
+ unsigned int num_vifs;
+ char cmd_line[MAX_CMD_LEN];
+} dom_meminfo_t;
+
+typedef struct dom0_op_st
+{
+ unsigned long cmd;
+ union
+ {
+ dom0_newdomain_t newdomain;
+ dom0_killdomain_t killdomain;
+ dom0_getmemlist_t getmemlist;
+ dom_mem_t dommem;
+ dom_pgupdate_t pgupdate;
+ dom_meminfo_t meminfo;
+ }
+ u;
+} dom0_op_t;
+
--- /dev/null
+/******************************************************************************
+ * vfr.c
+ *
+ * Interface to the virtual firewall/router.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+
+#include <asm/hypervisor-ifs/network.h>
+
+static struct proc_dir_entry *proc_vfr;
+
+static unsigned char readbuf[1024];
+
+/* Helpers, implemented at the bottom. */
+u32 getipaddr(const char *buff, unsigned int len);
+u16 antous(const char *buff, int len);
+int anton(const char *buff, int len);
+
+static int vfr_read_proc(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ strcpy(page, readbuf);
+ *readbuf = '\0';
+ *eof = 1;
+ *start = page;
+ return strlen(page);
+}
+
+/* The format for the vfr interface is as follows:
+ *
+ * COMMAND <field>=<val> [<field>=<val> [...]]
+ *
+ * where:
+ *
+ * COMMAND = { ACCEPT | COUNT }
+ *
+ * field=val pairs are as follows:
+ *
+ * field = { srcaddr | dstaddr }
+ * val is a dot seperated, numeric IP address.
+ *
+ * field = { srcport | dstport }
+ * val is a (16-bit) unsigned int
+ *
+ * field = { proto }
+ * val = { IP | TCP | UDP | ARP }
+ *
+ */
+
+#define isspace(_x) ( ((_x)==' ') || ((_x)=='\t') || ((_x)=='\v') || \
+ ((_x)=='\f') || ((_x)=='\r') || ((_x)=='\n') )
+
+static int vfr_write_proc(struct file *file, const char *buffer,
+ u_long count, void *data)
+{
+ network_op_t op;
+ int ret, len;
+ int ts, te, tl; // token start, end, and length
+ int fs, fe, fl; // field.
+
+ len = count;
+ ts = te = 0;
+
+ memset(&op, 0, sizeof(network_op_t));
+
+ // get the command:
+ while ( count && isspace(buffer[ts]) ) { ts++; count--; } // skip spaces.
+ te = ts;
+ while ( count && !isspace(buffer[te]) ) { te++; count--; } // command end
+ if ( te <= ts ) goto bad;
+ tl = te - ts;
+
+ if ( strncmp(&buffer[ts], "ADD", tl) == 0 )
+ {
+ op.cmd = NETWORK_OP_ADDRULE;
+ }
+ else if ( strncmp(&buffer[ts], "DELETE", tl) == 0 )
+ {
+ op.cmd = NETWORK_OP_DELETERULE;
+ }
+ else if ( strncmp(&buffer[ts], "PRINT", tl) == 0 )
+ {
+ op.cmd = NETWORK_OP_GETRULELIST;
+ goto doneparsing;
+ }
+
+ ts = te;
+
+ // get the action
+ while ( count && (buffer[ts] == ' ') ) { ts++; count--; } // skip spaces.
+ te = ts;
+ while ( count && (buffer[te] != ' ') ) { te++; count--; } // command end
+ if ( te <= ts ) goto bad;
+ tl = te - ts;
+
+ if ( strncmp(&buffer[ts], "ACCEPT", tl) == 0 )
+ {
+ op.u.net_rule.action = NETWORK_ACTION_ACCEPT;
+ goto keyval;
+ }
+ if ( strncmp(&buffer[ts], "COUNT", tl) == 0 )
+ {
+ op.u.net_rule.action = NETWORK_ACTION_COUNT;
+ goto keyval;
+ }
+
+ // default case;
+ return (len);
+
+
+ // get the key=val pairs.
+ keyval:
+ while (count)
+ {
+ //get field
+ ts = te; while ( count && isspace(buffer[ts]) ) { ts++; count--; }
+ te = ts;
+ while ( count && !isspace(buffer[te]) && (buffer[te] != '=') )
+ { te++; count--; }
+ if ( te <= ts )
+ goto doneparsing;
+ tl = te - ts;
+ fs = ts; fe = te; fl = tl; // save the field markers.
+ // skip " = " (ignores extra equals.)
+ while ( count && (isspace(buffer[te]) || (buffer[te] == '=')) )
+ { te++; count--; }
+ ts = te;
+ while ( count && !isspace(buffer[te]) ) { te++; count--; }
+ tl = te - ts;
+
+ if ( (fl <= 0) || (tl <= 0) ) goto bad;
+
+ if (strncmp(&buffer[fs], "srcaddr", fl) == 0)
+ {
+ op.u.net_rule.src_addr = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstaddr", fl) == 0)
+ {
+ op.u.net_rule.dst_addr = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcaddrmask", fl) == 0)
+ {
+ op.u.net_rule.src_addr_mask = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstaddrmask", fl) == 0)
+ {
+ op.u.net_rule.dst_addr_mask = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcport", fl) == 0)
+ {
+ op.u.net_rule.src_port = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstport", fl) == 0)
+ {
+ op.u.net_rule.dst_port = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcportmask", fl) == 0)
+ {
+ op.u.net_rule.src_port_mask = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstportmask", fl) == 0)
+ {
+ op.u.net_rule.dst_port_mask = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcint", fl) == 0)
+ {
+ op.u.net_rule.src_interface = anton(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstint", fl) == 0)
+ {
+ op.u.net_rule.dst_interface = anton(&buffer[ts], tl);
+ }
+ else if ( (strncmp(&buffer[fs], "proto", fl) == 0))
+ {
+ if (strncmp(&buffer[ts], "any", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_ANY;
+ if (strncmp(&buffer[ts], "ip", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_IP;
+ if (strncmp(&buffer[ts], "tcp", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_TCP;
+ if (strncmp(&buffer[ts], "udp", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_UDP;
+ if (strncmp(&buffer[ts], "arp", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_ARP;
+
+ }
+ }
+
+ doneparsing:
+ ret = HYPERVISOR_network_op(&op);
+ return(len);
+
+ bad:
+ return(len);
+
+
+}
+
+static int __init init_module(void)
+{
+ *readbuf = '\0';
+ proc_vfr = create_proc_entry ("vfr", 0600, &proc_root);
+ if ( proc_vfr != NULL )
+ {
+ proc_vfr->owner = THIS_MODULE;
+ proc_vfr->nlink = 1;
+ proc_vfr->read_proc = vfr_read_proc;
+ proc_vfr->write_proc = vfr_write_proc;
+ printk("Successfully installed virtual firewall/router interface\n");
+ }
+ return 0;
+}
+
+static void __exit cleanup_module(void)
+{
+ if ( proc_vfr == NULL ) return;
+ remove_proc_entry("vfr", &proc_root);
+ proc_vfr = NULL;
+}
+
+module_init(init_module);
+module_exit(cleanup_module);
+
+/* Helper functions start here: */
+
+int anton(const char *buff, int len)
+{
+ int ret;
+ char c;
+ int sign = 1;
+
+ ret = 0;
+
+ if (len == 0) return 0;
+ if (*buff == '-') { sign = -1; buff++; len--; }
+
+ while ( (len) && ((c = *buff) >= '0') && (c <= '9') )
+ {
+ ret *= 10;
+ ret += c - '0';
+ buff++; len--;
+ }
+
+ ret *= sign;
+ return ret;
+}
+
+u16 antous(const char *buff, int len)
+{
+ u16 ret;
+ char c;
+
+ ret = 0;
+
+ while ( (len) && ((c = *buff) >= '0') && (c <= '9') )
+ {
+ ret *= 10;
+ ret += c - '0';
+ buff++; len--;
+ }
+
+ return ret;
+}
+
+u32 getipaddr(const char *buff, unsigned int len)
+{
+ int i;
+ char c;
+ u32 ret, val;
+
+ ret = 0; val = 0;
+
+ while ( len )
+ {
+ if (!((((c = *buff) >= '0') && ( c <= '9')) || ( c == '.' ) ) )
+ {
+ return(0); // malformed.
+ }
+
+ if ( c == '.' ) {
+ if (val > 255) return (0); //malformed.
+ ret = ret << 8;
+ ret += val;
+ val = 0;
+ len--; buff++;
+ continue;
+ }
+ val *= 10;
+ val += c - '0';
+ buff++; len--;
+ }
+ ret = ret << 8;
+ ret += val;
+
+ return (ret);
+}
+
--- /dev/null
+O_TARGET := net.o
+obj-y := network.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/******************************************************************************
+ * network.c
+ *
+ * Virtual network driver for XenoLinux.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+
+#include <asm/io.h>
+#include <net/sock.h>
+
+#define NET_TX_IRQ _EVENT_NET_TX
+#define NET_RX_IRQ _EVENT_NET_RX
+
+#define TX_MAX_ENTRIES (TX_RING_SIZE - 2)
+#define RX_MAX_ENTRIES (RX_RING_SIZE - 2)
+
+#define TX_RING_INC(_i) (((_i)+1) & (TX_RING_SIZE-1))
+#define RX_RING_INC(_i) (((_i)+1) & (RX_RING_SIZE-1))
+#define TX_RING_ADD(_i,_j) (((_i)+(_j)) & (TX_RING_SIZE-1))
+#define RX_RING_ADD(_i,_j) (((_i)+(_j)) & (RX_RING_SIZE-1))
+
+#define RX_BUF_SIZE ((PAGE_SIZE/2)+1) /* Fool the slab allocator :-) */
+
+static void network_rx_int(int irq, void *dev_id, struct pt_regs *ptregs);
+static void network_tx_int(int irq, void *dev_id, struct pt_regs *ptregs);
+static void network_tx_buf_gc(struct net_device *dev);
+static void network_alloc_rx_buffers(struct net_device *dev);
+static void network_free_rx_buffers(struct net_device *dev);
+static void cleanup_module(void);
+
+static struct list_head dev_list;
+
+/*
+ * RX RING: RX_IDX <= rx_cons <= rx_prod
+ * TX RING: TX_IDX <= tx_cons <= tx_prod
+ * (*_IDX allocated privately here, *_cons & *_prod shared with hypervisor)
+ */
+struct net_private
+{
+ struct list_head list;
+ struct net_device *dev;
+
+ struct net_device_stats stats;
+ struct sk_buff **tx_skb_ring;
+ struct sk_buff **rx_skb_ring;
+ atomic_t tx_entries;
+ unsigned int rx_idx, tx_idx, tx_full;
+ net_ring_t *net_ring;
+ spinlock_t tx_lock;
+};
+
+
+static int network_open(struct net_device *dev)
+{
+ struct net_private *np = dev->priv;
+ int error = 0;
+
+ np->rx_idx = np->tx_idx = np->tx_full = 0;
+
+ memset(&np->stats, 0, sizeof(np->stats));
+
+ spin_lock_init(&np->tx_lock);
+
+ atomic_set(&np->tx_entries, 0);
+
+ np->net_ring->tx_prod = np->net_ring->tx_cons = np->net_ring->tx_event = 0;
+ np->net_ring->rx_prod = np->net_ring->rx_cons = np->net_ring->rx_event = 0;
+ np->net_ring->tx_ring = NULL;
+ np->net_ring->rx_ring = NULL;
+
+ np->tx_skb_ring = kmalloc(TX_RING_SIZE * sizeof(struct sk_buff *),
+ GFP_KERNEL);
+ np->rx_skb_ring = kmalloc(RX_RING_SIZE * sizeof(struct sk_buff *),
+ GFP_KERNEL);
+ np->net_ring->tx_ring = kmalloc(TX_RING_SIZE * sizeof(tx_entry_t),
+ GFP_KERNEL);
+ np->net_ring->rx_ring = kmalloc(RX_RING_SIZE * sizeof(rx_entry_t),
+ GFP_KERNEL);
+ if ( (np->tx_skb_ring == NULL) || (np->rx_skb_ring == NULL) ||
+ (np->net_ring->tx_ring == NULL) || (np->net_ring->rx_ring == NULL) )
+ {
+ printk(KERN_WARNING "%s; Could not allocate ring memory\n", dev->name);
+ error = -ENOBUFS;
+ goto fail;
+ }
+
+ network_alloc_rx_buffers(dev);
+
+ error = request_irq(NET_RX_IRQ, network_rx_int, 0,
+ "net-rx", dev);
+ if ( error )
+ {
+ printk(KERN_WARNING "%s: Could not allocate receive interrupt\n",
+ dev->name);
+ network_free_rx_buffers(dev);
+ goto fail;
+ }
+
+ error = request_irq(NET_TX_IRQ, network_tx_int, 0,
+ "net-tx", dev);
+ if ( error )
+ {
+ printk(KERN_WARNING "%s: Could not allocate transmit interrupt\n",
+ dev->name);
+ free_irq(NET_RX_IRQ, dev);
+ network_free_rx_buffers(dev);
+ goto fail;
+ }
+
+ printk("XenoLinux Virtual Network Driver installed as %s\n", dev->name);
+
+ netif_start_queue(dev);
+
+ MOD_INC_USE_COUNT;
+
+ return 0;
+
+ fail:
+ if ( np->net_ring->rx_ring ) kfree(np->net_ring->rx_ring);
+ if ( np->net_ring->tx_ring ) kfree(np->net_ring->tx_ring);
+ if ( np->rx_skb_ring ) kfree(np->rx_skb_ring);
+ if ( np->tx_skb_ring ) kfree(np->tx_skb_ring);
+ kfree(np);
+ return error;
+}
+
+
+static void network_tx_buf_gc(struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+ unsigned long flags;
+
+ spin_lock_irqsave(&np->tx_lock, flags);
+
+ for ( i = np->tx_idx; i != np->net_ring->tx_cons; i = TX_RING_INC(i) )
+ {
+ skb = np->tx_skb_ring[i];
+ dev_kfree_skb_any(skb);
+ atomic_dec(&np->tx_entries);
+ }
+
+ np->tx_idx = i;
+
+ if ( np->tx_full && (atomic_read(&np->tx_entries) < TX_MAX_ENTRIES) )
+ {
+ np->tx_full = 0;
+ netif_wake_queue(dev);
+ }
+
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+}
+
+inline unsigned long get_ppte(unsigned long addr)
+{
+ unsigned long ppte;
+ pgd_t *pgd; pmd_t *pmd; pte_t *ptep;
+ pgd = pgd_offset_k(addr);
+
+ if ( pgd_none(*pgd) || pgd_bad(*pgd) ) BUG();
+
+ pmd = pmd_offset(pgd, addr);
+ if ( pmd_none(*pmd) || pmd_bad(*pmd) ) BUG();
+
+ ptep = pte_offset(pmd, addr);
+ ppte = (unsigned long)phys_to_machine(virt_to_phys(ptep));
+
+ return ppte;
+}
+
+static void network_alloc_rx_buffers(struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+ unsigned int end = RX_RING_ADD(np->rx_idx, RX_MAX_ENTRIES);
+
+ for ( i = np->net_ring->rx_prod; i != end; i = RX_RING_INC(i) )
+ {
+ skb = dev_alloc_skb(RX_BUF_SIZE);
+ if ( skb == NULL ) break;
+ skb->dev = dev;
+ skb_reserve(skb, 2); /* word align the IP header */
+ np->rx_skb_ring[i] = skb;
+ np->net_ring->rx_ring[i].addr = get_ppte((unsigned long)skb->head);
+ np->net_ring->rx_ring[i].size = RX_BUF_SIZE - 16; /* arbitrary */
+ }
+
+ np->net_ring->rx_prod = i;
+
+ np->net_ring->rx_event = RX_RING_INC(np->rx_idx);
+
+ HYPERVISOR_net_update();
+}
+
+
+static void network_free_rx_buffers(struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+
+ for ( i = np->rx_idx; i != np->net_ring->rx_prod; i = RX_RING_INC(i) )
+ {
+ skb = np->rx_skb_ring[i];
+ dev_kfree_skb(skb);
+ }
+}
+
+static int network_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = (struct net_private *)dev->priv;
+
+ if ( np->tx_full )
+ {
+ printk(KERN_WARNING "%s: full queue wasn't stopped!\n", dev->name);
+ netif_stop_queue(dev);
+ return -ENOBUFS;
+ }
+ i = np->net_ring->tx_prod;
+
+ if ( (((unsigned long)skb->data & ~PAGE_MASK) + skb->len) >= PAGE_SIZE )
+ {
+ struct sk_buff *new_skb = alloc_skb(RX_BUF_SIZE, GFP_KERNEL);
+ skb_put(new_skb, skb->len);
+ memcpy(new_skb->data, skb->data, skb->len);
+ kfree_skb(skb);
+ skb = new_skb;
+ }
+
+ np->tx_skb_ring[i] = skb;
+ np->net_ring->tx_ring[i].addr =
+ (unsigned long)phys_to_machine(virt_to_phys(skb->data));
+ np->net_ring->tx_ring[i].size = skb->len;
+ np->net_ring->tx_prod = TX_RING_INC(i);
+ atomic_inc(&np->tx_entries);
+
+ np->stats.tx_bytes += skb->len;
+ np->stats.tx_packets++;
+
+ spin_lock_irq(&np->tx_lock);
+ if ( atomic_read(&np->tx_entries) >= TX_MAX_ENTRIES )
+ {
+ np->tx_full = 1;
+ netif_stop_queue(dev);
+ np->net_ring->tx_event =
+ TX_RING_ADD(np->tx_idx, atomic_read(&np->tx_entries) >> 1);
+ }
+ else
+ {
+ /* Avoid unnecessary tx interrupts. */
+ np->net_ring->tx_event = TX_RING_INC(np->net_ring->tx_prod);
+ }
+ spin_unlock_irq(&np->tx_lock);
+
+ /* Must do this after setting tx_event: race with updates of tx_cons. */
+ network_tx_buf_gc(dev);
+
+ HYPERVISOR_net_update();
+
+ return 0;
+}
+
+
+static void network_rx_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ unsigned int i;
+ struct net_device *dev = (struct net_device *)dev_id;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+
+ again:
+ for ( i = np->rx_idx; i != np->net_ring->rx_cons; i = RX_RING_INC(i) )
+ {
+ if (np->net_ring->rx_ring[i].status != RING_STATUS_OK)
+ {
+ printk("bad buffer on RX ring!(%d)\n",
+ np->net_ring->rx_ring[i].status);
+ continue;
+ }
+ skb = np->rx_skb_ring[i];
+
+ phys_to_machine_mapping[virt_to_phys(skb->head) >> PAGE_SHIFT] =
+ (*(unsigned long *)phys_to_virt(
+ machine_to_phys(np->net_ring->rx_ring[i].addr))
+ ) >> PAGE_SHIFT;
+
+ skb_put(skb, np->net_ring->rx_ring[i].size);
+ skb->protocol = eth_type_trans(skb, dev);
+
+ /*
+ * Set up shinfo -- from alloc_skb This was particularily nasty: the
+ * shared info is hidden at the back of the data area (presumably so it
+ * can be shared), but on page flip it gets very spunked.
+ */
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+
+ np->stats.rx_packets++;
+
+ np->stats.rx_bytes += np->net_ring->rx_ring[i].size;
+ netif_rx(skb);
+ dev->last_rx = jiffies;
+ }
+
+ np->rx_idx = i;
+
+ network_alloc_rx_buffers(dev);
+
+ /* Deal with hypervisor racing our resetting of rx_event. */
+ smp_mb();
+ if ( np->net_ring->rx_cons != i ) goto again;
+}
+
+
+static void network_tx_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ struct net_device *dev = (struct net_device *)dev_id;
+ network_tx_buf_gc(dev);
+}
+
+
+int network_close(struct net_device *dev)
+{
+ struct net_private *np = dev->priv;
+
+ netif_stop_queue(dev);
+
+ free_irq(NET_RX_IRQ, dev);
+ free_irq(NET_TX_IRQ, dev);
+
+ /*
+ * XXXX This cannot be done safely until be have a proper interface
+ * for setting up and tearing down virtual interfaces on the fly.
+ * Currently the receive buffers are locked down by Xen and we have
+ * no sensible way of retrieving them.
+ */
+#if 0
+ network_free_rx_buffers(dev);
+ kfree(np->net_ring->rx_ring);
+ kfree(np->net_ring->tx_ring);
+#endif
+
+ kfree(np->rx_skb_ring);
+ kfree(np->tx_skb_ring);
+
+ MOD_DEC_USE_COUNT;
+
+ return 0;
+}
+
+
+static struct net_device_stats *network_get_stats(struct net_device *dev)
+{
+ struct net_private *np = (struct net_private *)dev->priv;
+ return &np->stats;
+}
+
+
+int __init init_module(void)
+{
+ int i, err;
+ struct net_device *dev;
+ struct net_private *np;
+
+ INIT_LIST_HEAD(&dev_list);
+
+ for ( i = 0; i < start_info.num_net_rings; i++ )
+ {
+ dev = alloc_etherdev(sizeof(struct net_private));
+ if ( dev == NULL )
+ {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ np = dev->priv;
+ np->net_ring = start_info.net_rings + i;
+
+ SET_MODULE_OWNER(dev);
+ dev->open = network_open;
+ dev->hard_start_xmit = network_start_xmit;
+ dev->stop = network_close;
+ dev->get_stats = network_get_stats;
+
+ memset(dev->dev_addr, 0, ETH_ALEN);
+ *(unsigned int *)(dev->dev_addr + 1) = i;
+
+ if ( (err = register_netdev(dev)) != 0 )
+ {
+ kfree(dev);
+ goto fail;
+ }
+
+ np->dev = dev;
+ list_add(&np->list, &dev_list);
+ }
+
+ return 0;
+
+ fail:
+ cleanup_module();
+ return err;
+}
+
+
+static void cleanup_module(void)
+{
+ struct net_private *np;
+ struct net_device *dev;
+
+ while ( !list_empty(&dev_list) )
+ {
+ np = list_entry(dev_list.next, struct net_private, list);
+ list_del(&np->list);
+ dev = np->dev;
+ unregister_netdev(dev);
+ kfree(dev);
+ }
+}
+
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+
+.S.o:
+ $(CC) $(AFLAGS) -traditional -c $< -o $*.o
+
+all: kernel.o head.o init_task.o
+
+O_TARGET := kernel.o
+
+export-objs := i386_ksyms.o
+
+obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \
+ ptrace.o ioport.o ldt.o setup.o time.o sys_i386.o \
+ i386_ksyms.o i387.o hypervisor.o
+
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * linux/arch/i386/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * entry.S contains the system-call and fault low-level handling routines.
+ * This also contains the timer-interrupt handler, as well as all interrupts
+ * and faults that can result in a task-switch.
+ *
+ * NOTE: This code handles signal-recognition, which happens every time
+ * after a timer-interrupt and after each system call.
+ *
+ * I changed all the .align's to 4 (16 byte alignment), as that's faster
+ * on a 486.
+ *
+ * Stack layout in 'ret_from_system_call':
+ * ptrace needs to have all regs on the stack.
+ * if the order here is changed, it needs to be
+ * updated in fork.c:copy_process, signal.c:do_signal,
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - orig_eax
+ * 28(%esp) - %eip
+ * 2C(%esp) - %cs
+ * 30(%esp) - %eflags
+ * 34(%esp) - %oldesp
+ * 38(%esp) - %oldss
+ *
+ * "current" is in register %ebx during any slow entries.
+ */
+
+#include <linux/config.h>
+#include <linux/sys.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+
+EBX = 0x00
+ECX = 0x04
+EDX = 0x08
+ESI = 0x0C
+EDI = 0x10
+EBP = 0x14
+EAX = 0x18
+DS = 0x1C
+ES = 0x20
+ORIG_EAX = 0x24
+EIP = 0x28
+CS = 0x2C
+EFLAGS = 0x30
+OLDESP = 0x34
+OLDSS = 0x38
+
+CF_MASK = 0x00000001
+IF_MASK = 0x00000200
+NT_MASK = 0x00004000
+
+/*
+ * these are offsets into the task-struct.
+ */
+state = 0
+flags = 4
+sigpending = 8
+addr_limit = 12
+exec_domain = 16
+need_resched = 20
+tsk_ptrace = 24
+processor = 52
+
+ENOSYS = 38
+
+
+#define SAVE_ALL \
+ cld; \
+ pushl %es; \
+ pushl %ds; \
+ pushl %eax; \
+ pushl %ebp; \
+ pushl %edi; \
+ pushl %esi; \
+ pushl %edx; \
+ pushl %ecx; \
+ pushl %ebx; \
+ movl $(__KERNEL_DS),%edx; \
+ movl %edx,%ds; \
+ movl %edx,%es;
+
+#define RESTORE_ALL \
+ popl %ebx; \
+ popl %ecx; \
+ popl %edx; \
+ popl %esi; \
+ popl %edi; \
+ popl %ebp; \
+ popl %eax; \
+1: popl %ds; \
+2: popl %es; \
+ addl $4,%esp; \
+3: iret; \
+.section .fixup,"ax"; \
+4: movl $0,(%esp); \
+ jmp 1b; \
+5: movl $0,(%esp); \
+ jmp 2b; \
+6: pushl %ss; \
+ popl %ds; \
+ pushl %ss; \
+ popl %es; \
+ pushl $11; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,4b; \
+ .long 2b,5b; \
+ .long 3b,6b; \
+.previous
+
+#define GET_CURRENT(reg) \
+ movl $-8192, reg; \
+ andl %esp, reg
+
+
+ENTRY(ret_from_fork)
+ pushl %ebx
+ call SYMBOL_NAME(schedule_tail)
+ addl $4, %esp
+ GET_CURRENT(%ebx)
+ testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
+ jne tracesys_exit
+ jmp ret_from_sys_call
+
+#if defined(CONFIG_KDB)
+ENTRY(kdb_call)
+ pushl %eax # save orig EAX
+ SAVE_ALL
+ pushl %esp # struct pt_regs
+ pushl $0 # error_code
+ pushl $7 # KDB_REASON_ENTRY
+ call SYMBOL_NAME(kdb)
+ addl $12,%esp # remove args
+ RESTORE_ALL
+#endif
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ENTRY(system_call)
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
+ jne tracesys
+ cmpl $(NR_syscalls),%eax
+ jae badsys
+ call *SYMBOL_NAME(sys_call_table)(,%eax,4)
+ movl %eax,EAX(%esp) # save the return value
+ENTRY(ret_from_sys_call)
+ movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
+ xorl %eax,%eax
+ movl %eax,4(%esi) # need_resched and signals atomic test
+ret_syscall_tests:
+ cmpl $0,need_resched(%ebx)
+ jne reschedule
+ cmpl $0,sigpending(%ebx)
+ je safesti # ensure need_resched updates are seen
+signal_return:
+ btsl %eax,4(%esi) # reenable event callbacks
+ movl %esp,%eax
+ xorl %edx,%edx
+ call SYMBOL_NAME(do_signal)
+ jmp ret_from_sys_call
+
+ ALIGN
+restore_all:
+ RESTORE_ALL
+
+ ALIGN
+tracesys:
+ movl $-ENOSYS,EAX(%esp)
+ call SYMBOL_NAME(syscall_trace)
+ movl ORIG_EAX(%esp),%eax
+ cmpl $(NR_syscalls),%eax
+ jae tracesys_exit
+ call *SYMBOL_NAME(sys_call_table)(,%eax,4)
+ movl %eax,EAX(%esp) # save the return value
+tracesys_exit:
+ call SYMBOL_NAME(syscall_trace)
+ jmp ret_from_sys_call
+badsys:
+ movl $-ENOSYS,EAX(%esp)
+ jmp ret_from_sys_call
+
+ ALIGN
+ENTRY(ret_from_intr)
+ GET_CURRENT(%ebx)
+ret_from_exception:
+ movb CS(%esp),%al
+ testl $2,%eax
+ jne ret_from_sys_call
+ jmp restore_all
+
+ ALIGN
+reschedule:
+ btsl %eax,4(%esi) # reenable event callbacks
+ call SYMBOL_NAME(schedule) # test
+ jmp ret_from_sys_call
+
+ENTRY(divide_error)
+ pushl $0 # no error code
+ pushl $ SYMBOL_NAME(do_divide_error)
+ ALIGN
+error_code:
+ pushl %ds
+ pushl %eax
+ xorl %eax,%eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax # eax = -1
+ pushl %ecx
+ pushl %ebx
+ GET_CURRENT(%ebx)
+ cld
+ movl %es,%ecx
+ movl ORIG_EAX(%esp), %esi # get the error code
+ movl ES(%esp), %edi # get the function address
+ movl %eax, ORIG_EAX(%esp)
+ movl %ecx, ES(%esp)
+ movl %esp,%edx
+ pushl %esi # push the error code
+ pushl %edx # push the pt_regs pointer
+ movl $(__KERNEL_DS),%edx
+ movl %edx,%ds
+ movl %edx,%es
+ call *%edi
+ addl $8,%esp
+ jmp ret_from_exception
+
+# A note on the "critical region" in our callback handler.
+# We want to avoid stacking callback handlers due to events occurring
+# during handling of the last event. To do this, we keep events disabled
+# until we've done all processing. HOWEVER, we must enable events before
+# popping the stack frame (can't be done atomically) and so it would still
+# be possible to get enough handler activations to overflow the stack.
+# Although unlikely, bugs of that kind are hard to track down, so we'd
+# like to avoid the possibility.
+# So, on entry to the handler we detect whether we interrupted an
+# existing activation in its critical region -- if so, we pop the current
+# activation and restart the handler using the previous one.
+ENTRY(hypervisor_callback)
+ pushl %eax
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ movl EIP(%esp),%eax
+ cmpl $scrit,%eax
+ jb 11f
+ cmpl $ecrit,%eax
+ jb critical_region_fixup
+11: push %esp
+ call do_hypervisor_callback
+ add $4,%esp
+ movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
+ xorl %eax,%eax
+ movb CS(%esp),%cl
+ test $2,%cl # slow return to ring 2 or 3
+ jne ret_syscall_tests
+safesti:btsl %eax,4(%esi) # reenable event callbacks
+scrit: /**** START OF CRITICAL REGION ****/
+ cmpl %eax,(%esi)
+ jne 14f # process more events if necessary...
+ RESTORE_ALL
+14: btrl %eax,4(%esi)
+ jmp 11b
+ecrit: /**** END OF CRITICAL REGION ****/
+# [How we do the fixup]. We want to merge the current stack frame with the
+# just-interrupted frame. How we do this depends on where in the critical
+# region the interrupted handler was executing, and so how many saved
+# registers are in each frame. We do this quickly using the lookup table
+# 'critical_fixup_table'. For each byte offset in the critical region, it
+# provides the number of bytes which have already been popped from the
+# interrupted stack frame.
+critical_region_fixup:
+ addl $critical_fixup_table-scrit,%eax
+ movzbl (%eax),%eax # %eax contains num bytes popped
+ mov %esp,%esi
+ add %eax,%esi # %esi points at end of src region
+ mov %esp,%edi
+ add $0x34,%edi # %edi points at end of dst region
+ mov %eax,%ecx
+ shr $2,%ecx # convert words to bytes
+ je 16f # skip loop if nothing to copy
+15: subl $4,%esi # pre-decrementing copy loop
+ subl $4,%edi
+ movl (%esi),%eax
+ movl %eax,(%edi)
+ loop 15b
+16: movl %edi,%esp # final %edi is top of merged stack
+ jmp 11b
+
+critical_fixup_table:
+ .byte 0x00,0x00 # cmpl %eax,(%esi)
+ .byte 0x00,0x00 # jne 14f
+ .byte 0x00 # pop %ebx
+ .byte 0x04 # pop %ecx
+ .byte 0x08 # pop %edx
+ .byte 0x0c # pop %esi
+ .byte 0x10 # pop %edi
+ .byte 0x14 # pop %ebp
+ .byte 0x18 # pop %eax
+ .byte 0x1c # pop %ds
+ .byte 0x20 # pop %es
+ .byte 0x24,0x24,0x24 # add $4,%esp
+ .byte 0x28 # iret
+ .byte 0x00,0x00,0x00,0x00 # btrl %eax,4(%esi)
+ .byte 0x00,0x00 # jmp 11b
+
+# Hypervisor uses this for application faults while it executes.
+ENTRY(failsafe_callback)
+1: pop %ds
+2: pop %es
+3: iret
+.section .fixup,"ax"; \
+4: movl $0,(%esp); \
+ jmp 1b; \
+5: movl $0,(%esp); \
+ jmp 2b; \
+6: pushl %ss; \
+ popl %ds; \
+ pushl %ss; \
+ popl %es; \
+ pushl $11; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,4b; \
+ .long 2b,5b; \
+ .long 3b,6b; \
+.previous
+
+ENTRY(coprocessor_error)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_coprocessor_error)
+ jmp error_code
+
+ENTRY(simd_coprocessor_error)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_simd_coprocessor_error)
+ jmp error_code
+
+ENTRY(device_not_available)
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ call SYMBOL_NAME(math_state_restore)
+ jmp ret_from_exception
+
+ENTRY(debug)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_debug)
+ jmp error_code
+
+ENTRY(int3)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_int3)
+ jmp error_code
+
+ENTRY(overflow)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_overflow)
+ jmp error_code
+
+ENTRY(bounds)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_bounds)
+ jmp error_code
+
+ENTRY(invalid_op)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_invalid_op)
+ jmp error_code
+
+ENTRY(coprocessor_segment_overrun)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_coprocessor_segment_overrun)
+ jmp error_code
+
+ENTRY(double_fault)
+ pushl $ SYMBOL_NAME(do_double_fault)
+ jmp error_code
+
+ENTRY(invalid_TSS)
+ pushl $ SYMBOL_NAME(do_invalid_TSS)
+ jmp error_code
+
+ENTRY(segment_not_present)
+ pushl $ SYMBOL_NAME(do_segment_not_present)
+ jmp error_code
+
+ENTRY(stack_segment)
+ pushl $ SYMBOL_NAME(do_stack_segment)
+ jmp error_code
+
+ENTRY(general_protection)
+ pushl $ SYMBOL_NAME(do_general_protection)
+ jmp error_code
+
+ENTRY(alignment_check)
+ pushl $ SYMBOL_NAME(do_alignment_check)
+ jmp error_code
+
+#if defined(CONFIG_KDB)
+ENTRY(page_fault_mca)
+ pushl %ecx
+ pushl %edx
+ pushl %eax
+ movl $473,%ecx
+ rdmsr
+ andl $0xfffffffe,%eax /* Disable last branch recording */
+ wrmsr
+ popl %eax
+ popl %edx
+ popl %ecx
+ pushl $ SYMBOL_NAME(do_page_fault)
+ jmp error_code
+#endif
+
+# This handler is special, because it gets an extra value on its stack,
+# which is the linear faulting address.
+ENTRY(page_fault)
+ pushl %ds
+ pushl %eax
+ xorl %eax,%eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax # eax = -1
+ pushl %ecx
+ pushl %ebx
+ GET_CURRENT(%ebx)
+ cld
+ movl %es,%ecx
+ movl ORIG_EAX(%esp), %esi # get the error code
+ movl ES(%esp), %edi # get the faulting address
+ movl %eax, ORIG_EAX(%esp)
+ movl %ecx, ES(%esp)
+ movl %esp,%edx
+ pushl %edi # push the faulting address
+ pushl %esi # push the error code
+ pushl %edx # push the pt_regs pointer
+ movl $(__KERNEL_DS),%edx
+ movl %edx,%ds
+ movl %edx,%es
+ call SYMBOL_NAME(do_page_fault)
+ addl $12,%esp
+ jmp ret_from_exception
+
+ENTRY(machine_check)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_machine_check)
+ jmp error_code
+
+ENTRY(spurious_interrupt_bug)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_spurious_interrupt_bug)
+ jmp error_code
+
+.data
+ENTRY(sys_call_table)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 0 - old "setup()" system call*/
+ .long SYMBOL_NAME(sys_exit)
+ .long SYMBOL_NAME(sys_fork)
+ .long SYMBOL_NAME(sys_read)
+ .long SYMBOL_NAME(sys_write)
+ .long SYMBOL_NAME(sys_open) /* 5 */
+ .long SYMBOL_NAME(sys_close)
+ .long SYMBOL_NAME(sys_waitpid)
+ .long SYMBOL_NAME(sys_creat)
+ .long SYMBOL_NAME(sys_link)
+ .long SYMBOL_NAME(sys_unlink) /* 10 */
+ .long SYMBOL_NAME(sys_execve)
+ .long SYMBOL_NAME(sys_chdir)
+ .long SYMBOL_NAME(sys_time)
+ .long SYMBOL_NAME(sys_mknod)
+ .long SYMBOL_NAME(sys_chmod) /* 15 */
+ .long SYMBOL_NAME(sys_lchown16)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old break syscall holder */
+ .long SYMBOL_NAME(sys_stat)
+ .long SYMBOL_NAME(sys_lseek)
+ .long SYMBOL_NAME(sys_getpid) /* 20 */
+ .long SYMBOL_NAME(sys_mount)
+ .long SYMBOL_NAME(sys_oldumount)
+ .long SYMBOL_NAME(sys_setuid16)
+ .long SYMBOL_NAME(sys_getuid16)
+ .long SYMBOL_NAME(sys_stime) /* 25 */
+ .long SYMBOL_NAME(sys_ptrace)
+ .long SYMBOL_NAME(sys_alarm)
+ .long SYMBOL_NAME(sys_fstat)
+ .long SYMBOL_NAME(sys_pause)
+ .long SYMBOL_NAME(sys_utime) /* 30 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old stty syscall holder */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old gtty syscall holder */
+ .long SYMBOL_NAME(sys_access)
+ .long SYMBOL_NAME(sys_nice)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 35 */ /* old ftime syscall holder */
+ .long SYMBOL_NAME(sys_sync)
+ .long SYMBOL_NAME(sys_kill)
+ .long SYMBOL_NAME(sys_rename)
+ .long SYMBOL_NAME(sys_mkdir)
+ .long SYMBOL_NAME(sys_rmdir) /* 40 */
+ .long SYMBOL_NAME(sys_dup)
+ .long SYMBOL_NAME(sys_pipe)
+ .long SYMBOL_NAME(sys_times)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old prof syscall holder */
+ .long SYMBOL_NAME(sys_brk) /* 45 */
+ .long SYMBOL_NAME(sys_setgid16)
+ .long SYMBOL_NAME(sys_getgid16)
+ .long SYMBOL_NAME(sys_signal)
+ .long SYMBOL_NAME(sys_geteuid16)
+ .long SYMBOL_NAME(sys_getegid16) /* 50 */
+ .long SYMBOL_NAME(sys_acct)
+ .long SYMBOL_NAME(sys_umount) /* recycled never used phys() */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old lock syscall holder */
+ .long SYMBOL_NAME(sys_ioctl)
+ .long SYMBOL_NAME(sys_fcntl) /* 55 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old mpx syscall holder */
+ .long SYMBOL_NAME(sys_setpgid)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old ulimit syscall holder */
+ .long SYMBOL_NAME(sys_olduname)
+ .long SYMBOL_NAME(sys_umask) /* 60 */
+ .long SYMBOL_NAME(sys_chroot)
+ .long SYMBOL_NAME(sys_ustat)
+ .long SYMBOL_NAME(sys_dup2)
+ .long SYMBOL_NAME(sys_getppid)
+ .long SYMBOL_NAME(sys_getpgrp) /* 65 */
+ .long SYMBOL_NAME(sys_setsid)
+ .long SYMBOL_NAME(sys_sigaction)
+ .long SYMBOL_NAME(sys_sgetmask)
+ .long SYMBOL_NAME(sys_ssetmask)
+ .long SYMBOL_NAME(sys_setreuid16) /* 70 */
+ .long SYMBOL_NAME(sys_setregid16)
+ .long SYMBOL_NAME(sys_sigsuspend)
+ .long SYMBOL_NAME(sys_sigpending)
+ .long SYMBOL_NAME(sys_sethostname)
+ .long SYMBOL_NAME(sys_setrlimit) /* 75 */
+ .long SYMBOL_NAME(sys_old_getrlimit)
+ .long SYMBOL_NAME(sys_getrusage)
+ .long SYMBOL_NAME(sys_gettimeofday)
+ .long SYMBOL_NAME(sys_settimeofday)
+ .long SYMBOL_NAME(sys_getgroups16) /* 80 */
+ .long SYMBOL_NAME(sys_setgroups16)
+ .long SYMBOL_NAME(old_select)
+ .long SYMBOL_NAME(sys_symlink)
+ .long SYMBOL_NAME(sys_lstat)
+ .long SYMBOL_NAME(sys_readlink) /* 85 */
+ .long SYMBOL_NAME(sys_uselib)
+ .long SYMBOL_NAME(sys_swapon)
+ .long SYMBOL_NAME(sys_reboot)
+ .long SYMBOL_NAME(old_readdir)
+ .long SYMBOL_NAME(old_mmap) /* 90 */
+ .long SYMBOL_NAME(sys_munmap)
+ .long SYMBOL_NAME(sys_truncate)
+ .long SYMBOL_NAME(sys_ftruncate)
+ .long SYMBOL_NAME(sys_fchmod)
+ .long SYMBOL_NAME(sys_fchown16) /* 95 */
+ .long SYMBOL_NAME(sys_getpriority)
+ .long SYMBOL_NAME(sys_setpriority)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old profil syscall holder */
+ .long SYMBOL_NAME(sys_statfs)
+ .long SYMBOL_NAME(sys_fstatfs) /* 100 */
+ .long SYMBOL_NAME(sys_ioperm)
+ .long SYMBOL_NAME(sys_socketcall)
+ .long SYMBOL_NAME(sys_syslog)
+ .long SYMBOL_NAME(sys_setitimer)
+ .long SYMBOL_NAME(sys_getitimer) /* 105 */
+ .long SYMBOL_NAME(sys_newstat)
+ .long SYMBOL_NAME(sys_newlstat)
+ .long SYMBOL_NAME(sys_newfstat)
+ .long SYMBOL_NAME(sys_uname)
+ .long SYMBOL_NAME(sys_iopl) /* 110 */
+ .long SYMBOL_NAME(sys_vhangup)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old "idle" system call */
+ .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
+ .long SYMBOL_NAME(sys_wait4)
+ .long SYMBOL_NAME(sys_swapoff) /* 115 */
+ .long SYMBOL_NAME(sys_sysinfo)
+ .long SYMBOL_NAME(sys_ipc)
+ .long SYMBOL_NAME(sys_fsync)
+ .long SYMBOL_NAME(sys_sigreturn)
+ .long SYMBOL_NAME(sys_clone) /* 120 */
+ .long SYMBOL_NAME(sys_setdomainname)
+ .long SYMBOL_NAME(sys_newuname)
+ .long SYMBOL_NAME(sys_modify_ldt)
+ .long SYMBOL_NAME(sys_adjtimex)
+ .long SYMBOL_NAME(sys_mprotect) /* 125 */
+ .long SYMBOL_NAME(sys_sigprocmask)
+ .long SYMBOL_NAME(sys_create_module)
+ .long SYMBOL_NAME(sys_init_module)
+ .long SYMBOL_NAME(sys_delete_module)
+ .long SYMBOL_NAME(sys_get_kernel_syms) /* 130 */
+ .long SYMBOL_NAME(sys_quotactl)
+ .long SYMBOL_NAME(sys_getpgid)
+ .long SYMBOL_NAME(sys_fchdir)
+ .long SYMBOL_NAME(sys_bdflush)
+ .long SYMBOL_NAME(sys_sysfs) /* 135 */
+ .long SYMBOL_NAME(sys_personality)
+ .long SYMBOL_NAME(sys_ni_syscall) /* for afs_syscall */
+ .long SYMBOL_NAME(sys_setfsuid16)
+ .long SYMBOL_NAME(sys_setfsgid16)
+ .long SYMBOL_NAME(sys_llseek) /* 140 */
+ .long SYMBOL_NAME(sys_getdents)
+ .long SYMBOL_NAME(sys_select)
+ .long SYMBOL_NAME(sys_flock)
+ .long SYMBOL_NAME(sys_msync)
+ .long SYMBOL_NAME(sys_readv) /* 145 */
+ .long SYMBOL_NAME(sys_writev)
+ .long SYMBOL_NAME(sys_getsid)
+ .long SYMBOL_NAME(sys_fdatasync)
+ .long SYMBOL_NAME(sys_sysctl)
+ .long SYMBOL_NAME(sys_mlock) /* 150 */
+ .long SYMBOL_NAME(sys_munlock)
+ .long SYMBOL_NAME(sys_mlockall)
+ .long SYMBOL_NAME(sys_munlockall)
+ .long SYMBOL_NAME(sys_sched_setparam)
+ .long SYMBOL_NAME(sys_sched_getparam) /* 155 */
+ .long SYMBOL_NAME(sys_sched_setscheduler)
+ .long SYMBOL_NAME(sys_sched_getscheduler)
+ .long SYMBOL_NAME(sys_sched_yield)
+ .long SYMBOL_NAME(sys_sched_get_priority_max)
+ .long SYMBOL_NAME(sys_sched_get_priority_min) /* 160 */
+ .long SYMBOL_NAME(sys_sched_rr_get_interval)
+ .long SYMBOL_NAME(sys_nanosleep)
+ .long SYMBOL_NAME(sys_mremap)
+ .long SYMBOL_NAME(sys_setresuid16)
+ .long SYMBOL_NAME(sys_getresuid16) /* 165 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
+ .long SYMBOL_NAME(sys_query_module)
+ .long SYMBOL_NAME(sys_poll)
+ .long SYMBOL_NAME(sys_nfsservctl)
+ .long SYMBOL_NAME(sys_setresgid16) /* 170 */
+ .long SYMBOL_NAME(sys_getresgid16)
+ .long SYMBOL_NAME(sys_prctl)
+ .long SYMBOL_NAME(sys_rt_sigreturn)
+ .long SYMBOL_NAME(sys_rt_sigaction)
+ .long SYMBOL_NAME(sys_rt_sigprocmask) /* 175 */
+ .long SYMBOL_NAME(sys_rt_sigpending)
+ .long SYMBOL_NAME(sys_rt_sigtimedwait)
+ .long SYMBOL_NAME(sys_rt_sigqueueinfo)
+ .long SYMBOL_NAME(sys_rt_sigsuspend)
+ .long SYMBOL_NAME(sys_pread) /* 180 */
+ .long SYMBOL_NAME(sys_pwrite)
+ .long SYMBOL_NAME(sys_chown16)
+ .long SYMBOL_NAME(sys_getcwd)
+ .long SYMBOL_NAME(sys_capget)
+ .long SYMBOL_NAME(sys_capset) /* 185 */
+ .long SYMBOL_NAME(sys_sigaltstack)
+ .long SYMBOL_NAME(sys_sendfile)
+ .long SYMBOL_NAME(sys_ni_syscall) /* streams1 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* streams2 */
+ .long SYMBOL_NAME(sys_vfork) /* 190 */
+ .long SYMBOL_NAME(sys_getrlimit)
+ .long SYMBOL_NAME(sys_mmap2)
+ .long SYMBOL_NAME(sys_truncate64)
+ .long SYMBOL_NAME(sys_ftruncate64)
+ .long SYMBOL_NAME(sys_stat64) /* 195 */
+ .long SYMBOL_NAME(sys_lstat64)
+ .long SYMBOL_NAME(sys_fstat64)
+ .long SYMBOL_NAME(sys_lchown)
+ .long SYMBOL_NAME(sys_getuid)
+ .long SYMBOL_NAME(sys_getgid) /* 200 */
+ .long SYMBOL_NAME(sys_geteuid)
+ .long SYMBOL_NAME(sys_getegid)
+ .long SYMBOL_NAME(sys_setreuid)
+ .long SYMBOL_NAME(sys_setregid)
+ .long SYMBOL_NAME(sys_getgroups) /* 205 */
+ .long SYMBOL_NAME(sys_setgroups)
+ .long SYMBOL_NAME(sys_fchown)
+ .long SYMBOL_NAME(sys_setresuid)
+ .long SYMBOL_NAME(sys_getresuid)
+ .long SYMBOL_NAME(sys_setresgid) /* 210 */
+ .long SYMBOL_NAME(sys_getresgid)
+ .long SYMBOL_NAME(sys_chown)
+ .long SYMBOL_NAME(sys_setuid)
+ .long SYMBOL_NAME(sys_setgid)
+ .long SYMBOL_NAME(sys_setfsuid) /* 215 */
+ .long SYMBOL_NAME(sys_setfsgid)
+ .long SYMBOL_NAME(sys_pivot_root)
+ .long SYMBOL_NAME(sys_mincore)
+ .long SYMBOL_NAME(sys_madvise)
+ .long SYMBOL_NAME(sys_getdents64) /* 220 */
+ .long SYMBOL_NAME(sys_fcntl64)
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for TUX */
+ .long SYMBOL_NAME(sys_ni_syscall) /* Reserved for Security */
+ .long SYMBOL_NAME(sys_gettid)
+ .long SYMBOL_NAME(sys_readahead) /* 225 */
+
+ .rept NR_syscalls-(.-sys_call_table)/4
+ .long SYMBOL_NAME(sys_ni_syscall)
+ .endr
--- /dev/null
+
+.text
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+/* Offsets in start_info structure */
+#define SHARED_INFO 4
+#define MOD_START 12
+#define MOD_LEN 16
+
+startup_32:
+ cld
+
+ lss stack_start,%esp
+
+ /* Copy initrd somewhere safe before it's clobbered by BSS. */
+ mov MOD_LEN(%esi),%ecx
+ shr $2,%ecx
+ jz 2f /* bail from copy loop if no initrd */
+ mov $SYMBOL_NAME(_end),%edi
+ add MOD_LEN(%esi),%edi
+ mov MOD_START(%esi),%eax
+ add MOD_LEN(%esi),%eax
+1: sub $4,%eax
+ sub $4,%edi
+ mov (%eax),%ebx
+ mov %ebx,(%edi)
+ loop 1b
+ mov %edi,MOD_START(%esi)
+
+ /* Clear BSS first so that there are no surprises... */
+2: xorl %eax,%eax
+ movl $SYMBOL_NAME(__bss_start),%edi
+ movl $SYMBOL_NAME(_end),%ecx
+ subl %edi,%ecx
+ rep stosb
+
+ /* Copy the necessary stuff from start_info structure. */
+ /* We need to copy shared_info early, so that sti/cli work */
+ mov SHARED_INFO(%esi),%eax
+ mov %eax,SYMBOL_NAME(HYPERVISOR_shared_info)
+ mov $SYMBOL_NAME(start_info_union),%edi
+ mov $128,%ecx
+ rep movsl
+
+ jmp SYMBOL_NAME(start_kernel)
+
+ENTRY(stack_start)
+ .long SYMBOL_NAME(init_task_union)+8192, __KERNEL_DS
+
+.org 0x1000
+ENTRY(empty_zero_page)
+
+.org 0x2000
+ENTRY(cpu0_pte_quicklist)
+
+.org 0x2400
+ENTRY(cpu0_pgd_quicklist)
+
+.org 0x2800
+ENTRY(stext)
+ENTRY(_stext)
--- /dev/null
+/******************************************************************************
+ * hypervisor.c
+ *
+ * Communication to/from hypervisor.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <asm/atomic.h>
+#include <linux/irq.h>
+#include <asm/hypervisor.h>
+#include <asm/system.h>
+#include <asm/ptrace.h>
+
+static unsigned long event_mask = 0;
+
+void frobb(void) {}
+
+void do_hypervisor_callback(struct pt_regs *regs)
+{
+ unsigned long events, flags;
+ shared_info_t *shared = HYPERVISOR_shared_info;
+
+ do {
+ /* Specialised local_irq_save(). */
+ flags = shared->events_enable;
+ shared->events_enable = 0;
+ barrier();
+
+ events = xchg(&shared->events, 0);
+ events &= event_mask;
+
+ __asm__ __volatile__ (
+ " push %1 ;"
+ " sub $4,%%esp ;"
+ " jmp 2f ;"
+ "1: btrl %%eax,%0 ;" /* clear bit */
+ " mov %%eax,(%%esp) ;"
+ " call do_IRQ ;" /* do_IRQ(event) */
+ "2: bsfl %0,%%eax ;" /* %eax == bit # */
+ " jnz 1b ;"
+ " add $8,%%esp ;"
+ /* we use %ebx because it is callee-saved */
+ : : "b" (events), "r" (regs)
+ /* clobbered by callback function calls */
+ : "eax", "ecx", "edx", "memory" );
+
+ /* Specialised local_irq_restore(). */
+ shared->events_enable = flags;
+ barrier();
+ }
+ while ( shared->events );
+}
+
+
+
+/*
+ * Define interface to generic handling in irq.c
+ */
+
+static unsigned int startup_hypervisor_event(unsigned int irq)
+{
+ set_bit(irq, &event_mask);
+ return 0;
+}
+
+static void shutdown_hypervisor_event(unsigned int irq)
+{
+ clear_bit(irq, &event_mask);
+}
+
+static void enable_hypervisor_event(unsigned int irq)
+{
+ set_bit(irq, &event_mask);
+}
+
+static void disable_hypervisor_event(unsigned int irq)
+{
+ clear_bit(irq, &event_mask);
+}
+
+static void ack_hypervisor_event(unsigned int irq)
+{
+ if ( !(event_mask & (1<<irq)) )
+ {
+ printk("Unexpected hypervisor event %d\n", irq);
+ atomic_inc(&irq_err_count);
+ }
+}
+
+static void end_hypervisor_event(unsigned int irq)
+{
+}
+
+static struct hw_interrupt_type hypervisor_irq_type = {
+ "Hypervisor-event",
+ startup_hypervisor_event,
+ shutdown_hypervisor_event,
+ enable_hypervisor_event,
+ disable_hypervisor_event,
+ ack_hypervisor_event,
+ end_hypervisor_event,
+ NULL
+};
+
+void __init init_IRQ(void)
+{
+ int i;
+
+ for ( i = 0; i < NR_IRQS; i++ )
+ {
+ irq_desc[i].status = IRQ_DISABLED;
+ irq_desc[i].action = 0;
+ irq_desc[i].depth = 1;
+ irq_desc[i].handler = &hypervisor_irq_type;
+ }
+}
--- /dev/null
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/user.h>
+#include <linux/elfcore.h>
+#include <linux/mca.h>
+#include <linux/sched.h>
+#include <linux/in6.h>
+#include <linux/interrupt.h>
+#include <linux/smp_lock.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/apm_bios.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/tty.h>
+
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include <asm/io.h>
+#include <asm/hardirq.h>
+#include <asm/delay.h>
+#include <asm/irq.h>
+#include <asm/mmx.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+
+extern void dump_thread(struct pt_regs *, struct user *);
+extern spinlock_t rtc_lock;
+
+#ifdef CONFIG_SMP
+extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
+extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
+#endif
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
+extern struct drive_info_struct drive_info;
+EXPORT_SYMBOL(drive_info);
+#endif
+
+//extern unsigned long get_cmos_time(void);
+
+/* platform dependent support */
+EXPORT_SYMBOL(boot_cpu_data);
+EXPORT_SYMBOL(MCA_bus);
+EXPORT_SYMBOL(__verify_write);
+EXPORT_SYMBOL(dump_thread);
+EXPORT_SYMBOL(dump_fpu);
+EXPORT_SYMBOL(dump_extended_fpu);
+EXPORT_SYMBOL(enable_irq);
+EXPORT_SYMBOL(disable_irq);
+EXPORT_SYMBOL(disable_irq_nosync);
+EXPORT_SYMBOL(probe_irq_mask);
+EXPORT_SYMBOL(kernel_thread);
+EXPORT_SYMBOL(pm_idle);
+EXPORT_SYMBOL(pm_power_off);
+//EXPORT_SYMBOL(get_cmos_time);
+EXPORT_SYMBOL(apm_info);
+
+#ifdef CONFIG_DEBUG_IOVIRT
+EXPORT_SYMBOL(__io_virt_debug);
+#endif
+
+EXPORT_SYMBOL_NOVERS(__down_failed);
+EXPORT_SYMBOL_NOVERS(__down_failed_interruptible);
+EXPORT_SYMBOL_NOVERS(__down_failed_trylock);
+EXPORT_SYMBOL_NOVERS(__up_wakeup);
+/* Networking helper routines. */
+EXPORT_SYMBOL(csum_partial_copy_generic);
+/* Delay loops */
+EXPORT_SYMBOL(__udelay);
+EXPORT_SYMBOL(__delay);
+EXPORT_SYMBOL(__const_udelay);
+
+EXPORT_SYMBOL_NOVERS(__get_user_1);
+EXPORT_SYMBOL_NOVERS(__get_user_2);
+EXPORT_SYMBOL_NOVERS(__get_user_4);
+
+EXPORT_SYMBOL(strtok);
+EXPORT_SYMBOL(strpbrk);
+EXPORT_SYMBOL(simple_strtol);
+EXPORT_SYMBOL(strstr);
+
+EXPORT_SYMBOL(strncpy_from_user);
+EXPORT_SYMBOL(__strncpy_from_user);
+EXPORT_SYMBOL(clear_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__generic_copy_from_user);
+EXPORT_SYMBOL(__generic_copy_to_user);
+EXPORT_SYMBOL(strnlen_user);
+
+#ifdef CONFIG_X86_USE_3DNOW
+EXPORT_SYMBOL(_mmx_memcpy);
+EXPORT_SYMBOL(mmx_clear_page);
+EXPORT_SYMBOL(mmx_copy_page);
+#endif
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(cpu_data);
+EXPORT_SYMBOL(kernel_flag);
+EXPORT_SYMBOL(smp_num_cpus);
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL_NOVERS(__write_lock_failed);
+EXPORT_SYMBOL_NOVERS(__read_lock_failed);
+
+/* Global SMP irq stuff */
+EXPORT_SYMBOL(synchronize_irq);
+EXPORT_SYMBOL(global_irq_holder);
+EXPORT_SYMBOL(__global_cli);
+EXPORT_SYMBOL(__global_sti);
+EXPORT_SYMBOL(__global_save_flags);
+EXPORT_SYMBOL(__global_restore_flags);
+EXPORT_SYMBOL(smp_call_function);
+
+/* TLB flushing */
+EXPORT_SYMBOL(flush_tlb_page);
+#endif
+
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(screen_info);
+#endif
+
+EXPORT_SYMBOL(get_wchan);
+
+EXPORT_SYMBOL(rtc_lock);
+
+#undef memcpy
+#undef memset
+extern void * memset(void *,int,__kernel_size_t);
+extern void * memcpy(void *,const void *,__kernel_size_t);
+EXPORT_SYMBOL_NOVERS(memcpy);
+EXPORT_SYMBOL_NOVERS(memset);
+
+#ifdef CONFIG_HAVE_DEC_LOCK
+EXPORT_SYMBOL(atomic_dec_and_lock);
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+EXPORT_SYMBOL(do_BUG);
+#endif
--- /dev/null
+/*
+ * linux/arch/i386/kernel/i387.c
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/math_emu.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+#define HAVE_HWFP 1
+
+/*
+ * The _current_ task is using the FPU for the first time
+ * so initialize it and set the mxcsr to its default
+ * value at reset if we support XMM instructions and then
+ * remeber the current task has used the FPU.
+ */
+void init_fpu(void)
+{
+ __asm__("fninit");
+ if ( cpu_has_xmm )
+ load_mxcsr(0x1f80);
+
+ current->used_math = 1;
+}
+
+/*
+ * FPU lazy state save handling.
+ */
+
+static inline void __save_init_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxsave %0 ; fnclex"
+ : "=m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "fnsave %0 ; fwait"
+ : "=m" (tsk->thread.i387.fsave) );
+ }
+ tsk->flags &= ~PF_USEDFPU;
+}
+
+void save_init_fpu( struct task_struct *tsk )
+{
+ __save_init_fpu(tsk);
+ stts();
+}
+
+void kernel_fpu_begin(void)
+{
+ struct task_struct *tsk = current;
+
+ if (tsk->flags & PF_USEDFPU) {
+ __save_init_fpu(tsk);
+ return;
+ }
+ clts();
+}
+
+void restore_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxrstor %0"
+ : : "m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "frstor %0"
+ : : "m" (tsk->thread.i387.fsave) );
+ }
+}
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr( unsigned short twd )
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+ return tmp;
+}
+
+static inline unsigned long twd_fxsr_to_i387( struct i387_fxsave_struct *fxsave )
+{
+ struct _fpxreg *st = NULL;
+ unsigned long twd = (unsigned long) fxsave->twd;
+ unsigned long tag;
+ unsigned long ret = 0xffff0000;
+ int i;
+
+#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16);
+
+ for ( i = 0 ; i < 8 ; i++ ) {
+ if ( twd & 0x1 ) {
+ st = (struct _fpxreg *) FPREG_ADDR( fxsave, i );
+
+ switch ( st->exponent & 0x7fff ) {
+ case 0x7fff:
+ tag = 2; /* Special */
+ break;
+ case 0x0000:
+ if ( !st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3] ) {
+ tag = 1; /* Zero */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ default:
+ if ( st->significand[3] & 0x8000 ) {
+ tag = 0; /* Valid */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ }
+ } else {
+ tag = 3; /* Empty */
+ }
+ ret |= (tag << (2 * i));
+ twd = twd >> 1;
+ }
+ return ret;
+}
+
+/*
+ * FPU state interaction.
+ */
+
+unsigned short get_fpu_cwd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.cwd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.cwd;
+ }
+}
+
+unsigned short get_fpu_swd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.swd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.swd;
+ }
+}
+
+unsigned short get_fpu_twd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.twd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.twd;
+ }
+}
+
+unsigned short get_fpu_mxcsr( struct task_struct *tsk )
+{
+ if ( cpu_has_xmm ) {
+ return tsk->thread.i387.fxsave.mxcsr;
+ } else {
+ return 0x1f80;
+ }
+}
+
+void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.cwd = cwd;
+ } else {
+ tsk->thread.i387.fsave.cwd = ((long)cwd | 0xffff0000);
+ }
+}
+
+void set_fpu_swd( struct task_struct *tsk, unsigned short swd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.swd = swd;
+ } else {
+ tsk->thread.i387.fsave.swd = ((long)swd | 0xffff0000);
+ }
+}
+
+void set_fpu_twd( struct task_struct *tsk, unsigned short twd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.twd = twd_i387_to_fxsr(twd);
+ } else {
+ tsk->thread.i387.fsave.twd = ((long)twd | 0xffff0000);
+ }
+}
+
+void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr )
+{
+ if ( cpu_has_xmm ) {
+ tsk->thread.i387.fxsave.mxcsr = (mxcsr & 0xffbf);
+ }
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+static inline int convert_fxsr_to_user( struct _fpstate *buf,
+ struct i387_fxsave_struct *fxsave )
+{
+ unsigned long env[7];
+ struct _fpreg *to;
+ struct _fpxreg *from;
+ int i;
+
+ env[0] = (unsigned long)fxsave->cwd | 0xffff0000;
+ env[1] = (unsigned long)fxsave->swd | 0xffff0000;
+ env[2] = twd_fxsr_to_i387(fxsave);
+ env[3] = fxsave->fip;
+ env[4] = fxsave->fcs | ((unsigned long)fxsave->fop << 16);
+ env[5] = fxsave->foo;
+ env[6] = fxsave->fos;
+
+ if ( __copy_to_user( buf, env, 7 * sizeof(unsigned long) ) )
+ return 1;
+
+ to = &buf->_st[0];
+ from = (struct _fpxreg *) &fxsave->st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if ( __copy_to_user( to, from, sizeof(*to) ) )
+ return 1;
+ }
+ return 0;
+}
+
+static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave,
+ struct _fpstate *buf )
+{
+ unsigned long env[7];
+ struct _fpxreg *to;
+ struct _fpreg *from;
+ int i;
+
+ if ( __copy_from_user( env, buf, 7 * sizeof(long) ) )
+ return 1;
+
+ fxsave->cwd = (unsigned short)(env[0] & 0xffff);
+ fxsave->swd = (unsigned short)(env[1] & 0xffff);
+ fxsave->twd = twd_i387_to_fxsr((unsigned short)(env[2] & 0xffff));
+ fxsave->fip = env[3];
+ fxsave->fop = (unsigned short)((env[4] & 0xffff0000) >> 16);
+ fxsave->fcs = (env[4] & 0xffff);
+ fxsave->foo = env[5];
+ fxsave->fos = env[6];
+
+ to = (struct _fpxreg *) &fxsave->st_space[0];
+ from = &buf->_st[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if ( __copy_from_user( to, from, sizeof(*from) ) )
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+
+static inline int save_i387_fsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+
+ unlazy_fpu( tsk );
+ tsk->thread.i387.fsave.status = tsk->thread.i387.fsave.swd;
+ if ( __copy_to_user( buf, &tsk->thread.i387.fsave,
+ sizeof(struct i387_fsave_struct) ) )
+ return -1;
+ return 1;
+}
+
+static inline int save_i387_fxsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ int err = 0;
+
+ unlazy_fpu( tsk );
+
+ if ( convert_fxsr_to_user( buf, &tsk->thread.i387.fxsave ) )
+ return -1;
+
+ err |= __put_user( tsk->thread.i387.fxsave.swd, &buf->status );
+ err |= __put_user( X86_FXSR_MAGIC, &buf->magic );
+ if ( err )
+ return -1;
+
+ if ( __copy_to_user( &buf->_fxsr_env[0], &tsk->thread.i387.fxsave,
+ sizeof(struct i387_fxsave_struct) ) )
+ return -1;
+ return 1;
+}
+
+int save_i387( struct _fpstate *buf )
+{
+ if ( !current->used_math )
+ return 0;
+
+ /* This will cause a "finit" to be triggered by the next
+ * attempted FPU operation by the 'current' process.
+ */
+ current->used_math = 0;
+
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return save_i387_fxsave( buf );
+ } else {
+ return save_i387_fsave( buf );
+ }
+ } else {
+ return save_i387_soft( ¤t->thread.i387.soft, buf );
+ }
+}
+
+static inline int restore_i387_fsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ clear_fpu( tsk );
+ return __copy_from_user( &tsk->thread.i387.fsave, buf,
+ sizeof(struct i387_fsave_struct) );
+}
+
+static inline int restore_i387_fxsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ clear_fpu( tsk );
+ if ( __copy_from_user( &tsk->thread.i387.fxsave, &buf->_fxsr_env[0],
+ sizeof(struct i387_fxsave_struct) ) )
+ return 1;
+ /* mxcsr bit 6 and 31-16 must be zero for security reasons */
+ tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+ return convert_fxsr_from_user( &tsk->thread.i387.fxsave, buf );
+}
+
+int restore_i387( struct _fpstate *buf )
+{
+ int err;
+
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ err = restore_i387_fxsave( buf );
+ } else {
+ err = restore_i387_fsave( buf );
+ }
+ } else {
+ err = restore_i387_soft( ¤t->thread.i387.soft, buf );
+ }
+ current->used_math = 1;
+ return err;
+}
+
+/*
+ * ptrace request handlers.
+ */
+
+static inline int get_fpregs_fsave( struct user_i387_struct *buf,
+ struct task_struct *tsk )
+{
+ return __copy_to_user( buf, &tsk->thread.i387.fsave,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline int get_fpregs_fxsave( struct user_i387_struct *buf,
+ struct task_struct *tsk )
+{
+ return convert_fxsr_to_user( (struct _fpstate *)buf,
+ &tsk->thread.i387.fxsave );
+}
+
+int get_fpregs( struct user_i387_struct *buf, struct task_struct *tsk )
+{
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return get_fpregs_fxsave( buf, tsk );
+ } else {
+ return get_fpregs_fsave( buf, tsk );
+ }
+ } else {
+ return save_i387_soft( &tsk->thread.i387.soft,
+ (struct _fpstate *)buf );
+ }
+}
+
+static inline int set_fpregs_fsave( struct task_struct *tsk,
+ struct user_i387_struct *buf )
+{
+ return __copy_from_user( &tsk->thread.i387.fsave, buf,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline int set_fpregs_fxsave( struct task_struct *tsk,
+ struct user_i387_struct *buf )
+{
+ return convert_fxsr_from_user( &tsk->thread.i387.fxsave,
+ (struct _fpstate *)buf );
+}
+
+int set_fpregs( struct task_struct *tsk, struct user_i387_struct *buf )
+{
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return set_fpregs_fxsave( tsk, buf );
+ } else {
+ return set_fpregs_fsave( tsk, buf );
+ }
+ } else {
+ return restore_i387_soft( &tsk->thread.i387.soft,
+ (struct _fpstate *)buf );
+ }
+}
+
+int get_fpxregs( struct user_fxsr_struct *buf, struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ if (__copy_to_user( (void *)buf, &tsk->thread.i387.fxsave,
+ sizeof(struct user_fxsr_struct) ))
+ return -EFAULT;
+ return 0;
+ } else {
+ return -EIO;
+ }
+}
+
+int set_fpxregs( struct task_struct *tsk, struct user_fxsr_struct *buf )
+{
+ if ( cpu_has_fxsr ) {
+ __copy_from_user( &tsk->thread.i387.fxsave, (void *)buf,
+ sizeof(struct user_fxsr_struct) );
+ /* mxcsr bit 6 and 31-16 must be zero for security reasons */
+ tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+ return 0;
+ } else {
+ return -EIO;
+ }
+}
+
+/*
+ * FPU state for core dumps.
+ */
+
+static inline void copy_fpu_fsave( struct task_struct *tsk,
+ struct user_i387_struct *fpu )
+{
+ memcpy( fpu, &tsk->thread.i387.fsave,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline void copy_fpu_fxsave( struct task_struct *tsk,
+ struct user_i387_struct *fpu )
+{
+ unsigned short *to;
+ unsigned short *from;
+ int i;
+
+ memcpy( fpu, &tsk->thread.i387.fxsave, 7 * sizeof(long) );
+
+ to = (unsigned short *)&fpu->st_space[0];
+ from = (unsigned short *)&tsk->thread.i387.fxsave.st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to += 5, from += 8 ) {
+ memcpy( to, from, 5 * sizeof(unsigned short) );
+ }
+}
+
+int dump_fpu( struct pt_regs *regs, struct user_i387_struct *fpu )
+{
+ int fpvalid;
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk->used_math;
+ if ( fpvalid ) {
+ unlazy_fpu( tsk );
+ if ( cpu_has_fxsr ) {
+ copy_fpu_fxsave( tsk, fpu );
+ } else {
+ copy_fpu_fsave( tsk, fpu );
+ }
+ }
+
+ return fpvalid;
+}
+
+int dump_extended_fpu( struct pt_regs *regs, struct user_fxsr_struct *fpu )
+{
+ int fpvalid;
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk->used_math && cpu_has_fxsr;
+ if ( fpvalid ) {
+ unlazy_fpu( tsk );
+ memcpy( fpu, &tsk->thread.i387.fxsave,
+ sizeof(struct user_fxsr_struct) );
+ }
+
+ return fpvalid;
+}
--- /dev/null
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+static struct fs_struct init_fs = INIT_FS;
+static struct files_struct init_files = INIT_FILES;
+static struct signal_struct init_signals = INIT_SIGNALS;
+struct mm_struct init_mm = INIT_MM(init_mm);
+
+/*
+ * Initial task structure.
+ *
+ * We need to make sure that this is 8192-byte aligned due to the
+ * way process stacks are handled. This is done by having a special
+ * "init_task" linker map entry..
+ */
+union task_union init_task_union
+ __attribute__((__section__(".data.init_task"))) =
+ { INIT_TASK(init_task_union.task) };
+
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data.cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+struct tss_struct init_tss[NR_CPUS] __cacheline_aligned = { [0 ... NR_CPUS-1] = INIT_TSS };
+
--- /dev/null
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+
+asmlinkage int sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+{
+ /* No IO permission! */
+ return -EPERM;
+}
+
+
+asmlinkage int sys_iopl(unsigned long unused)
+{
+ /* The hypervisor won't allow it! */
+ return -EPERM;
+}
--- /dev/null
+/*
+ * linux/arch/i386/kernel/irq.c
+ *
+ * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ */
+
+/*
+ * (mostly architecture independent, will move to kernel/irq.c in 2.5.)
+ *
+ * IRQs are in fact implemented a bit like signal handlers for the kernel.
+ * Naturally it's not a 1:1 relation, but there are similarities.
+ */
+
+#include <linux/config.h>
+#include <linux/ptrace.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+#include <linux/kdb.h>
+
+#include <asm/atomic.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/irq.h>
+
+
+
+/*
+ * Linux has a controller-independent x86 interrupt architecture.
+ * every controller has a 'controller-template', that is used
+ * by the main code to do the right thing. Each driver-visible
+ * interrupt source is transparently wired to the apropriate
+ * controller. Thus drivers need not be aware of the
+ * interrupt-controller.
+ *
+ * Various interrupt controllers we handle: 8259 PIC, SMP IO-APIC,
+ * PIIX4's internal 8259 PIC and SGI's Visual Workstation Cobalt (IO-)APIC.
+ * (IO-APICs assumed to be messaging to Pentium local-APICs)
+ *
+ * the code is designed to be easily extended with new/different
+ * interrupt controllers, without having to do assembly magic.
+ */
+
+/*
+ * Controller mappings for all interrupt sources:
+ */
+irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned =
+ { [0 ... NR_IRQS-1] = { 0, &no_irq_type, NULL, 0, SPIN_LOCK_UNLOCKED}};
+
+static void register_irq_proc (unsigned int irq);
+
+/*
+ * Special irq handlers.
+ */
+
+void no_action(int cpl, void *dev_id, struct pt_regs *regs) { }
+
+/*
+ * Generic no controller code
+ */
+
+static void enable_none(unsigned int irq) { }
+static unsigned int startup_none(unsigned int irq) { return 0; }
+static void disable_none(unsigned int irq) { }
+static void ack_none(unsigned int irq)
+{
+ printk("unexpected IRQ trap at vector %02x\n", irq);
+}
+
+/* startup is the same as "enable", shutdown is same as "disable" */
+#define shutdown_none disable_none
+#define end_none enable_none
+
+struct hw_interrupt_type no_irq_type = {
+ "none",
+ startup_none,
+ shutdown_none,
+ enable_none,
+ disable_none,
+ ack_none,
+ end_none
+};
+
+atomic_t irq_err_count;
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+atomic_t irq_mis_count;
+#endif
+#endif
+
+/*
+ * Generic, controller-independent functions:
+ */
+
+int get_irq_list(char *buf)
+{
+ int i, j;
+ struct irqaction * action;
+ char *p = buf;
+
+ p += sprintf(p, " ");
+ for (j=0; j<smp_num_cpus; j++)
+ p += sprintf(p, "CPU%d ",j);
+ *p++ = '\n';
+
+ for (i = 0 ; i < NR_IRQS ; i++) {
+ action = irq_desc[i].action;
+ if (!action)
+ continue;
+ p += sprintf(p, "%3d: ",i);
+#ifndef CONFIG_SMP
+ p += sprintf(p, "%10u ", kstat_irqs(i));
+#else
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ kstat.irqs[cpu_logical_map(j)][i]);
+#endif
+ p += sprintf(p, " %14s", irq_desc[i].handler->typename);
+ p += sprintf(p, " %s", action->name);
+
+ for (action=action->next; action; action = action->next)
+ p += sprintf(p, ", %s", action->name);
+ *p++ = '\n';
+ }
+ p += sprintf(p, "NMI: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ nmi_count(cpu_logical_map(j)));
+ p += sprintf(p, "\n");
+#if CONFIG_X86_LOCAL_APIC
+ p += sprintf(p, "LOC: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ apic_timer_irqs[cpu_logical_map(j)]);
+ p += sprintf(p, "\n");
+#endif
+ p += sprintf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+ p += sprintf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
+#endif
+#endif
+ return p - buf;
+}
+
+
+/*
+ * Global interrupt locks for SMP. Allow interrupts to come in on any
+ * CPU, yet make cli/sti act globally to protect critical regions..
+ */
+
+#ifdef CONFIG_SMP
+unsigned char global_irq_holder = NO_PROC_ID;
+unsigned volatile long global_irq_lock; /* pendantic: long for set_bit --RR */
+
+extern void show_stack(unsigned long* esp);
+
+static void show(char * str)
+{
+ int i;
+ int cpu = smp_processor_id();
+
+ printk("\n%s, CPU %d:\n", str, cpu);
+ printk("irq: %d [",irqs_running());
+ for(i=0;i < smp_num_cpus;i++)
+ printk(" %d",local_irq_count(i));
+ printk(" ]\nbh: %d [",spin_is_locked(&global_bh_lock) ? 1 : 0);
+ for(i=0;i < smp_num_cpus;i++)
+ printk(" %d",local_bh_count(i));
+
+ printk(" ]\nStack dumps:");
+ for(i = 0; i < smp_num_cpus; i++) {
+ unsigned long esp;
+ if (i == cpu)
+ continue;
+ printk("\nCPU %d:",i);
+ esp = init_tss[i].esp0;
+ if (!esp) {
+ /* tss->esp0 is set to NULL in cpu_init(),
+ * it's initialized when the cpu returns to user
+ * space. -- manfreds
+ */
+ printk(" <unknown> ");
+ continue;
+ }
+ esp &= ~(THREAD_SIZE-1);
+ esp += sizeof(struct task_struct);
+ show_stack((void*)esp);
+ }
+ printk("\nCPU %d:",cpu);
+ show_stack(NULL);
+ printk("\n");
+}
+
+#define MAXCOUNT 100000000
+
+/*
+ * I had a lockup scenario where a tight loop doing
+ * spin_unlock()/spin_lock() on CPU#1 was racing with
+ * spin_lock() on CPU#0. CPU#0 should have noticed spin_unlock(), but
+ * apparently the spin_unlock() information did not make it
+ * through to CPU#0 ... nasty, is this by design, do we have to limit
+ * 'memory update oscillation frequency' artificially like here?
+ *
+ * Such 'high frequency update' races can be avoided by careful design, but
+ * some of our major constructs like spinlocks use similar techniques,
+ * it would be nice to clarify this issue. Set this define to 0 if you
+ * want to check whether your system freezes. I suspect the delay done
+ * by SYNC_OTHER_CORES() is in correlation with 'snooping latency', but
+ * i thought that such things are guaranteed by design, since we use
+ * the 'LOCK' prefix.
+ */
+#define SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND 0
+
+#if SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND
+# define SYNC_OTHER_CORES(x) udelay(x+1)
+#else
+/*
+ * We have to allow irqs to arrive between __sti and __cli
+ */
+# define SYNC_OTHER_CORES(x) __asm__ __volatile__ ("nop")
+#endif
+
+static inline void wait_on_irq(int cpu)
+{
+ int count = MAXCOUNT;
+
+ for (;;) {
+
+ /*
+ * Wait until all interrupts are gone. Wait
+ * for bottom half handlers unless we're
+ * already executing in one..
+ */
+ if (!irqs_running())
+ if (local_bh_count(cpu) || !spin_is_locked(&global_bh_lock))
+ break;
+
+ /* Duh, we have to loop. Release the lock to avoid deadlocks */
+ clear_bit(0,&global_irq_lock);
+
+ for (;;) {
+ if (!--count) {
+ show("wait_on_irq");
+ count = ~0;
+ }
+ __sti();
+ SYNC_OTHER_CORES(cpu);
+ __cli();
+ if (irqs_running())
+ continue;
+ if (global_irq_lock)
+ continue;
+ if (!local_bh_count(cpu) && spin_is_locked(&global_bh_lock))
+ continue;
+ if (!test_and_set_bit(0,&global_irq_lock))
+ break;
+ }
+ }
+}
+
+/*
+ * This is called when we want to synchronize with
+ * interrupts. We may for example tell a device to
+ * stop sending interrupts: but to make sure there
+ * are no interrupts that are executing on another
+ * CPU we need to call this function.
+ */
+void synchronize_irq(void)
+{
+ if (irqs_running()) {
+ /* Stupid approach */
+ cli();
+ sti();
+ }
+}
+
+static inline void get_irqlock(int cpu)
+{
+#ifdef CONFIG_KDB
+ static int kdb_rate;
+ if (KDB_IS_RUNNING() && kdb_rate++ < 10)
+ kdb_printf("Warning: get_irqlock on cpu %d while kdb is running, may hang\n", smp_processor_id());
+#endif /* CONFIG_KDB */
+ if (test_and_set_bit(0,&global_irq_lock)) {
+ /* do we already hold the lock? */
+ if ((unsigned char) cpu == global_irq_holder)
+ return;
+ /* Uhhuh.. Somebody else got it. Wait.. */
+ do {
+ do {
+ rep_nop();
+ } while (test_bit(0,&global_irq_lock));
+ } while (test_and_set_bit(0,&global_irq_lock));
+ }
+ /*
+ * We also to make sure that nobody else is running
+ * in an interrupt context.
+ */
+ wait_on_irq(cpu);
+
+ /*
+ * Ok, finally..
+ */
+ global_irq_holder = cpu;
+}
+
+void __global_cli(void)
+{
+ panic("__global_cli");
+}
+
+void __global_sti(void)
+{
+ panic("__global_sti");
+}
+
+/*
+ * SMP flags value to restore to:
+ * 0 - global cli
+ * 1 - global sti
+ * 2 - local cli
+ * 3 - local sti
+ */
+unsigned long __global_save_flags(void)
+{
+ panic("__global_save_flags");
+}
+
+void __global_restore_flags(unsigned long flags)
+{
+ panic("__global_restore_flags");
+}
+
+#endif
+
+/*
+ * This should really return information about whether
+ * we should do bottom half handling etc. Right now we
+ * end up _always_ checking the bottom half, which is a
+ * waste of time and is not what some drivers would
+ * prefer.
+ */
+int handle_IRQ_event(unsigned int irq, struct pt_regs * regs, struct irqaction * action)
+{
+ int status;
+ int cpu = smp_processor_id();
+
+ irq_enter(cpu, irq);
+
+ status = 1; /* Force the "do bottom halves" bit */
+
+ if (!(action->flags & SA_INTERRUPT))
+ __sti();
+
+ do {
+ status |= action->flags;
+ action->handler(irq, action->dev_id, regs);
+ action = action->next;
+ } while (action);
+ if (status & SA_SAMPLE_RANDOM)
+ add_interrupt_randomness(irq);
+ __cli();
+
+ irq_exit(cpu, irq);
+
+ return status;
+}
+
+/*
+ * Generic enable/disable code: this just calls
+ * down into the PIC-specific version for the actual
+ * hardware disable after having gotten the irq
+ * controller lock.
+ */
+
+/**
+ * disable_irq_nosync - disable an irq without waiting
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Disables and Enables are
+ * nested.
+ * Unlike disable_irq(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
+ *
+ * This function may be called from IRQ context.
+ */
+
+inline void disable_irq_nosync(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->depth++) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->disable(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/**
+ * disable_irq - disable an irq and wait for completion
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Enables and Disables are
+ * nested.
+ * This function waits for any pending IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while
+ * holding a resource the IRQ handler may need you will deadlock.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+
+void disable_irq(unsigned int irq)
+{
+ disable_irq_nosync(irq);
+
+ if (!local_irq_count(smp_processor_id())) {
+ do {
+ barrier();
+ cpu_relax();
+ } while (irq_desc[irq].status & IRQ_INPROGRESS);
+ }
+}
+
+/**
+ * enable_irq - enable handling of an irq
+ * @irq: Interrupt to enable
+ *
+ * Undoes the effect of one call to disable_irq(). If this
+ * matches the last disable, processing of interrupts on this
+ * IRQ line is re-enabled.
+ *
+ * This function may be called from IRQ context.
+ */
+
+void enable_irq(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ switch (desc->depth) {
+ case 1: {
+ unsigned int status = desc->status & ~IRQ_DISABLED;
+ desc->status = status;
+ if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
+ desc->status = status | IRQ_REPLAY;
+ hw_resend_irq(desc->handler,irq);
+ }
+ desc->handler->enable(irq);
+ /* fall-through */
+ }
+ default:
+ desc->depth--;
+ break;
+ case 0:
+ printk("enable_irq(%u) unbalanced from %p\n", irq,
+ __builtin_return_address(0));
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+asmlinkage unsigned int do_IRQ(int irq, struct pt_regs *regs)
+{
+ /*
+ * We ack quickly, we don't want the irq controller
+ * thinking we're snobs just because some other CPU has
+ * disabled global interrupts (we have already done the
+ * INT_ACK cycles, it's too late to try to pretend to the
+ * controller that we aren't taking the interrupt).
+ *
+ * 0 return value means that this irq is already being
+ * handled by some other CPU. (or is disabled)
+ */
+ int cpu = smp_processor_id();
+ irq_desc_t *desc = irq_desc + irq;
+ struct irqaction * action;
+ unsigned int status;
+
+ kstat.irqs[cpu][irq]++;
+ spin_lock(&desc->lock);
+ desc->handler->ack(irq);
+ /*
+ REPLAY is when Linux resends an IRQ that was dropped earlier
+ WAITING is used by probe to mark irqs that are being tested
+ */
+ status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
+ status |= IRQ_PENDING; /* we _want_ to handle it */
+
+ /*
+ * If the IRQ is disabled for whatever reason, we cannot
+ * use the action we have.
+ */
+ action = NULL;
+ if (!(status & (IRQ_DISABLED | IRQ_INPROGRESS))) {
+ action = desc->action;
+ status &= ~IRQ_PENDING; /* we commit to handling */
+ status |= IRQ_INPROGRESS; /* we are handling it */
+ }
+ desc->status = status;
+
+ /*
+ * If there is no IRQ handler or it was disabled, exit early.
+ Since we set PENDING, if another processor is handling
+ a different instance of this same irq, the other processor
+ will take care of it.
+ */
+ if (!action)
+ goto out;
+
+ /*
+ * Edge triggered interrupts need to remember
+ * pending events.
+ * This applies to any hw interrupts that allow a second
+ * instance of the same irq to arrive while we are in do_IRQ
+ * or in the handler. But the code here only handles the _second_
+ * instance of the irq, not the third or fourth. So it is mostly
+ * useful for irq hardware that does not mask cleanly in an
+ * SMP environment.
+ */
+ for (;;) {
+ spin_unlock(&desc->lock);
+ handle_IRQ_event(irq, regs, action);
+ spin_lock(&desc->lock);
+
+ if (!(desc->status & IRQ_PENDING))
+ break;
+ desc->status &= ~IRQ_PENDING;
+ }
+ desc->status &= ~IRQ_INPROGRESS;
+out:
+ /*
+ * The ->end() handler has to deal with interrupts which got
+ * disabled while the handler was running.
+ */
+ desc->handler->end(irq);
+ spin_unlock(&desc->lock);
+
+ if (softirq_pending(cpu))
+ do_softirq();
+
+ return 1;
+}
+
+/**
+ * request_irq - allocate an interrupt line
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs
+ * @irqflags: Interrupt type flags
+ * @devname: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the
+ * interrupt line and IRQ handling. From the point this
+ * call is made your handler function may be invoked. Since
+ * your handler function must clear any interrupt the board
+ * raises, you must take care both to initialise your hardware
+ * and to set up the interrupt handler in the right order.
+ *
+ * Dev_id must be globally unique. Normally the address of the
+ * device data structure is used as the cookie. Since the handler
+ * receives this value it makes sense to use it.
+ *
+ * If your interrupt is shared you must pass a non NULL dev_id
+ * as this is required when freeing the interrupt.
+ *
+ * Flags:
+ *
+ * SA_SHIRQ Interrupt is shared
+ *
+ * SA_INTERRUPT Disable local interrupts while processing
+ *
+ * SA_SAMPLE_RANDOM The interrupt can be used for entropy
+ *
+ */
+
+int request_irq(unsigned int irq,
+ void (*handler)(int, void *, struct pt_regs *),
+ unsigned long irqflags,
+ const char * devname,
+ void *dev_id)
+{
+ int retval;
+ struct irqaction * action;
+
+#if 1
+ /*
+ * Sanity-check: shared interrupts should REALLY pass in
+ * a real dev-ID, otherwise we'll have trouble later trying
+ * to figure out which interrupt is which (messes up the
+ * interrupt freeing logic etc).
+ */
+ if (irqflags & SA_SHIRQ) {
+ if (!dev_id)
+ printk("Bad boy: %s (at 0x%x) called us without a dev_id!\n", devname, (&irq)[-1]);
+ }
+#endif
+
+ if (irq >= NR_IRQS)
+ return -EINVAL;
+ if (!handler)
+ return -EINVAL;
+
+ action = (struct irqaction *)
+ kmalloc(sizeof(struct irqaction), GFP_KERNEL);
+ if (!action)
+ return -ENOMEM;
+
+ action->handler = handler;
+ action->flags = irqflags;
+ action->mask = 0;
+ action->name = devname;
+ action->next = NULL;
+ action->dev_id = dev_id;
+
+ retval = setup_irq(irq, action);
+ if (retval)
+ kfree(action);
+ return retval;
+}
+
+/**
+ * free_irq - free an interrupt
+ * @irq: Interrupt line to free
+ * @dev_id: Device identity to free
+ *
+ * Remove an interrupt handler. The handler is removed and if the
+ * interrupt line is no longer in use by any driver it is disabled.
+ * On a shared IRQ the caller must ensure the interrupt is disabled
+ * on the card it drives before calling this function. The function
+ * does not return until any executing interrupts for this IRQ
+ * have completed.
+ *
+ * This function may be called from interrupt context.
+ *
+ * Bugs: Attempting to free an irq in a handler for the same irq hangs
+ * the machine.
+ */
+
+void free_irq(unsigned int irq, void *dev_id)
+{
+ irq_desc_t *desc;
+ struct irqaction **p;
+ unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return;
+
+ desc = irq_desc + irq;
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ for (;;) {
+ struct irqaction * action = *p;
+ if (action) {
+ struct irqaction **pp = p;
+ p = &action->next;
+ if (action->dev_id != dev_id)
+ continue;
+
+ /* Found it - now remove it from the list of entries */
+ *pp = action->next;
+ if (!desc->action) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->shutdown(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+#ifdef CONFIG_SMP
+ /* Wait to make sure it's not being used on another CPU */
+ while (desc->status & IRQ_INPROGRESS) {
+ barrier();
+ cpu_relax();
+ }
+#endif
+ kfree(action);
+ return;
+ }
+ printk("Trying to free free IRQ%d\n",irq);
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return;
+ }
+}
+
+/*
+ * IRQ autodetection code..
+ *
+ * This depends on the fact that any interrupt that
+ * comes in on to an unassigned handler will get stuck
+ * with "IRQ_WAITING" cleared and the interrupt
+ * disabled.
+ */
+
+static DECLARE_MUTEX(probe_sem);
+
+/**
+ * probe_irq_on - begin an interrupt autodetect
+ *
+ * Commence probing for an interrupt. The interrupts are scanned
+ * and a mask of potential interrupt lines is returned.
+ *
+ */
+
+unsigned long probe_irq_on(void)
+{
+ unsigned int i;
+ irq_desc_t *desc;
+ unsigned long val;
+ unsigned long delay;
+
+ down(&probe_sem);
+ /*
+ * something may have generated an irq long ago and we want to
+ * flush such a longstanding irq before considering it as spurious.
+ */
+ for (i = NR_IRQS-1; i > 0; i--) {
+ desc = irq_desc + i;
+
+ spin_lock_irq(&desc->lock);
+ if (!irq_desc[i].action)
+ irq_desc[i].handler->startup(i);
+ spin_unlock_irq(&desc->lock);
+ }
+
+ /* Wait for longstanding interrupts to trigger. */
+ for (delay = jiffies + HZ/50; time_after(delay, jiffies); )
+ /* about 20ms delay */ synchronize_irq();
+
+ /*
+ * enable any unassigned irqs
+ * (we must startup again here because if a longstanding irq
+ * happened in the previous stage, it may have masked itself)
+ */
+ for (i = NR_IRQS-1; i > 0; i--) {
+ desc = irq_desc + i;
+
+ spin_lock_irq(&desc->lock);
+ if (!desc->action) {
+ desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
+ if (desc->handler->startup(i))
+ desc->status |= IRQ_PENDING;
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+
+ /*
+ * Wait for spurious interrupts to trigger
+ */
+ for (delay = jiffies + HZ/10; time_after(delay, jiffies); )
+ /* about 100ms delay */ synchronize_irq();
+
+ /*
+ * Now filter out any obviously spurious interrupts
+ */
+ val = 0;
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ /* It triggered already - consider it spurious. */
+ if (!(status & IRQ_WAITING)) {
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ } else
+ if (i < 32)
+ val |= 1 << i;
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+
+ return val;
+}
+
+/*
+ * Return a mask of triggered interrupts (this
+ * can handle only legacy ISA interrupts).
+ */
+
+/**
+ * probe_irq_mask - scan a bitmap of interrupt lines
+ * @val: mask of interrupts to consider
+ *
+ * Scan the ISA bus interrupt lines and return a bitmap of
+ * active interrupts. The interrupt probe logic state is then
+ * returned to its previous value.
+ *
+ * Note: we need to scan all the irq's even though we will
+ * only return ISA irq numbers - just so that we reset them
+ * all to a known state.
+ */
+unsigned int probe_irq_mask(unsigned long val)
+{
+ int i;
+ unsigned int mask;
+
+ mask = 0;
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ if (i < 16 && !(status & IRQ_WAITING))
+ mask |= 1 << i;
+
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+ up(&probe_sem);
+
+ return mask & val;
+}
+
+/*
+ * Return the one interrupt that triggered (this can
+ * handle any interrupt source).
+ */
+
+/**
+ * probe_irq_off - end an interrupt autodetect
+ * @val: mask of potential interrupts (unused)
+ *
+ * Scans the unused interrupt lines and returns the line which
+ * appears to have triggered the interrupt. If no interrupt was
+ * found then zero is returned. If more than one interrupt is
+ * found then minus the first candidate is returned to indicate
+ * their is doubt.
+ *
+ * The interrupt probe logic state is returned to its previous
+ * value.
+ *
+ * BUGS: When used in a module (which arguably shouldnt happen)
+ * nothing prevents two IRQ probe callers from overlapping. The
+ * results of this are non-optimal.
+ */
+
+int probe_irq_off(unsigned long val)
+{
+ int i, irq_found, nr_irqs;
+
+ nr_irqs = 0;
+ irq_found = 0;
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ if (!(status & IRQ_WAITING)) {
+ if (!nr_irqs)
+ irq_found = i;
+ nr_irqs++;
+ }
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+ up(&probe_sem);
+
+ if (nr_irqs > 1)
+ irq_found = -irq_found;
+ return irq_found;
+}
+
+/* this was setup_x86_irq but it seems pretty generic */
+int setup_irq(unsigned int irq, struct irqaction * new)
+{
+ int shared = 0;
+ unsigned long flags;
+ struct irqaction *old, **p;
+ irq_desc_t *desc = irq_desc + irq;
+
+ /*
+ * Some drivers like serial.c use request_irq() heavily,
+ * so we have to be careful not to interfere with a
+ * running system.
+ */
+ if (new->flags & SA_SAMPLE_RANDOM) {
+ /*
+ * This function might sleep, we want to call it first,
+ * outside of the atomic block.
+ * Yes, this might clear the entropy pool if the wrong
+ * driver is attempted to be loaded, without actually
+ * installing a new handler, but is this really a problem,
+ * only the sysadmin is able to do this.
+ */
+ rand_initialize_irq(irq);
+ }
+
+ /*
+ * The following block of code has to be executed atomically
+ */
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ if ((old = *p) != NULL) {
+ /* Can't share interrupts unless both agree to */
+ if (!(old->flags & new->flags & SA_SHIRQ)) {
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return -EBUSY;
+ }
+
+ /* add new interrupt at end of irq queue */
+ do {
+ p = &old->next;
+ old = *p;
+ } while (old);
+ shared = 1;
+ }
+
+ *p = new;
+
+ if (!shared) {
+ desc->depth = 0;
+ desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | IRQ_WAITING);
+ desc->handler->startup(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+ register_irq_proc(irq);
+ return 0;
+}
+
+static struct proc_dir_entry * root_irq_dir;
+static struct proc_dir_entry * irq_dir [NR_IRQS];
+
+#define HEX_DIGITS 8
+
+static unsigned int parse_hex_value (const char *buffer,
+ unsigned long count, unsigned long *ret)
+{
+ unsigned char hexnum [HEX_DIGITS];
+ unsigned long value;
+ int i;
+
+ if (!count)
+ return -EINVAL;
+ if (count > HEX_DIGITS)
+ count = HEX_DIGITS;
+ if (copy_from_user(hexnum, buffer, count))
+ return -EFAULT;
+
+ /*
+ * Parse the first 8 characters as a hex string, any non-hex char
+ * is end-of-string. '00e1', 'e1', '00E1', 'E1' are all the same.
+ */
+ value = 0;
+
+ for (i = 0; i < count; i++) {
+ unsigned int c = hexnum[i];
+
+ switch (c) {
+ case '0' ... '9': c -= '0'; break;
+ case 'a' ... 'f': c -= 'a'-10; break;
+ case 'A' ... 'F': c -= 'A'-10; break;
+ default:
+ goto out;
+ }
+ value = (value << 4) | c;
+ }
+out:
+ *ret = value;
+ return 0;
+}
+
+#if CONFIG_SMP
+
+static struct proc_dir_entry * smp_affinity_entry [NR_IRQS];
+
+static unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL };
+static int irq_affinity_read_proc (char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ if (count < HEX_DIGITS+1)
+ return -EINVAL;
+ return sprintf (page, "%08lx\n", irq_affinity[(long)data]);
+}
+
+static int irq_affinity_write_proc (struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ int irq = (long) data, full_count = count, err;
+ unsigned long new_value;
+
+ if (!irq_desc[irq].handler->set_affinity)
+ return -EIO;
+
+ err = parse_hex_value(buffer, count, &new_value);
+
+ /*
+ * Do not allow disabling IRQs completely - it's a too easy
+ * way to make the system unusable accidentally :-) At least
+ * one online CPU still has to be targeted.
+ */
+ if (!(new_value & cpu_online_map))
+ return -EINVAL;
+
+ irq_affinity[irq] = new_value;
+ irq_desc[irq].handler->set_affinity(irq, new_value);
+
+ return full_count;
+}
+
+#endif
+
+static int prof_cpu_mask_read_proc (char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ unsigned long *mask = (unsigned long *) data;
+ if (count < HEX_DIGITS+1)
+ return -EINVAL;
+ return sprintf (page, "%08lx\n", *mask);
+}
+
+static int prof_cpu_mask_write_proc (struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ unsigned long *mask = (unsigned long *) data, full_count = count, err;
+ unsigned long new_value;
+
+ err = parse_hex_value(buffer, count, &new_value);
+ if (err)
+ return err;
+
+ *mask = new_value;
+ return full_count;
+}
+
+#define MAX_NAMELEN 10
+
+static void register_irq_proc (unsigned int irq)
+{
+ char name [MAX_NAMELEN];
+
+ if (!root_irq_dir || (irq_desc[irq].handler == &no_irq_type) ||
+ irq_dir[irq])
+ return;
+
+ memset(name, 0, MAX_NAMELEN);
+ sprintf(name, "%d", irq);
+
+ /* create /proc/irq/1234 */
+ irq_dir[irq] = proc_mkdir(name, root_irq_dir);
+
+#if CONFIG_SMP
+ {
+ struct proc_dir_entry *entry;
+
+ /* create /proc/irq/1234/smp_affinity */
+ entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]);
+
+ if (entry) {
+ entry->nlink = 1;
+ entry->data = (void *)(long)irq;
+ entry->read_proc = irq_affinity_read_proc;
+ entry->write_proc = irq_affinity_write_proc;
+ }
+
+ smp_affinity_entry[irq] = entry;
+ }
+#endif
+}
+
+unsigned long prof_cpu_mask = -1;
+
+void init_irq_proc (void)
+{
+ struct proc_dir_entry *entry;
+ int i;
+
+ /* create /proc/irq */
+ root_irq_dir = proc_mkdir("irq", 0);
+
+ /* create /proc/irq/prof_cpu_mask */
+ entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
+
+ if (!entry)
+ return;
+
+ entry->nlink = 1;
+ entry->data = (void *)&prof_cpu_mask;
+ entry->read_proc = prof_cpu_mask_read_proc;
+ entry->write_proc = prof_cpu_mask_write_proc;
+
+ /*
+ * Create entries for all existing IRQs.
+ */
+ for (i = 0; i < NR_IRQS; i++)
+ register_irq_proc(i);
+}
+
--- /dev/null
+/*
+ * linux/kernel/ldt.c
+ *
+ * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+
+/*
+ * XXX KAF (28/7/02): This stuff is only used for DOS emulation, and is
+ * the default way of finding current TCB in linuxthreads. Supporting
+ * table update svia the hypervisor is feasible, but a hassle: for now,
+ * recompiling linuxthreads is the most sensible option.
+ *
+ * Oh, this may become an issue depending on what JVM we use for
+ * running the xeno-daemon.
+ */
+
+asmlinkage int sys_modify_ldt(int func, void *ptr, unsigned long bytecount)
+{
+ return -ENOSYS;
+}
--- /dev/null
+/*
+ * linux/arch/i386/kernel/process.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+
+#define __KERNEL_SYSCALLS__
+#include <stdarg.h>
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/mc146818rtc.h>
+#include <linux/kdb.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/ldt.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+#include <linux/irq.h>
+
+asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+
+int hlt_counter;
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+
+/*
+ * Power off function, if any
+ */
+void (*pm_power_off)(void);
+
+void disable_hlt(void)
+{
+ hlt_counter++;
+}
+
+void enable_hlt(void)
+{
+ hlt_counter--;
+}
+
+/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle (void)
+{
+ /* endless idle loop with no priority at all */
+ init_idle();
+ current->nice = 20;
+ current->counter = -100;
+
+ while (1) {
+ while (!current->need_resched)
+ HYPERVISOR_do_sched_op(NULL);
+ schedule();
+ check_pgt_cache();
+ }
+}
+
+void machine_restart(char * __unused)
+{
+ HYPERVISOR_exit();
+}
+
+void machine_halt(void)
+{
+ HYPERVISOR_exit();
+}
+
+void machine_power_off(void)
+{
+ HYPERVISOR_exit();
+}
+
+extern void show_trace(unsigned long* esp);
+
+void show_regs(struct pt_regs * regs)
+{
+ printk("\n");
+ printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
+ printk("EIP: %04x:[<%08lx>] CPU: %d",0xffff & regs->xcs,regs->eip, smp_processor_id());
+ if (regs->xcs & 2)
+ printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
+ printk(" EFLAGS: %08lx %s\n",regs->eflags, print_tainted());
+ printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+ regs->eax,regs->ebx,regs->ecx,regs->edx);
+ printk("ESI: %08lx EDI: %08lx EBP: %08lx",
+ regs->esi, regs->edi, regs->ebp);
+ printk(" DS: %04x ES: %04x\n",
+ 0xffff & regs->xds,0xffff & regs->xes);
+
+ show_trace(®s->esp);
+}
+
+/*
+ * No need to lock the MM as we are the last user
+ */
+void release_segments(struct mm_struct *mm)
+{
+ void * ldt = mm->context.segments;
+
+ /*
+ * free the LDT
+ */
+ if (ldt) {
+ mm->context.segments = NULL;
+ clear_LDT();
+ vfree(ldt);
+ }
+}
+
+/*
+ * Create a kernel thread
+ */
+int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+{
+ long retval, d0;
+
+ __asm__ __volatile__(
+ "movl %%esp,%%esi\n\t"
+ "int $0x80\n\t" /* Linux/i386 system call */
+ "cmpl %%esp,%%esi\n\t" /* child or parent? */
+ "je 1f\n\t" /* parent - jump */
+ /* Load the argument into eax, and push it. That way, it does
+ * not matter whether the called function is compiled with
+ * -mregparm or not. */
+ "movl %4,%%eax\n\t"
+ "pushl %%eax\n\t"
+ "call *%5\n\t" /* call fn */
+ "movl %3,%0\n\t" /* exit */
+ "int $0x80\n"
+ "1:\t"
+ :"=&a" (retval), "=&S" (d0)
+ :"0" (__NR_clone), "i" (__NR_exit),
+ "r" (arg), "r" (fn),
+ "b" (flags | CLONE_VM)
+ : "memory");
+
+ return retval;
+}
+
+/*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+ /* nothing to do ... */
+}
+
+void flush_thread(void)
+{
+ struct task_struct *tsk = current;
+
+ memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
+
+ /*
+ * Forget coprocessor state..
+ */
+ clear_fpu(tsk);
+ tsk->used_math = 0;
+}
+
+void release_thread(struct task_struct *dead_task)
+{
+ if (dead_task->mm) {
+ void * ldt = dead_task->mm->context.segments;
+
+ // temporary debugging check
+ if (ldt) {
+ printk("WARNING: dead process %8s still has LDT? <%p>\n",
+ dead_task->comm, ldt);
+ BUG();
+ }
+ }
+}
+
+/*
+ * we do not have to muck with descriptors here, that is
+ * done in switch_mm() as needed.
+ */
+void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
+{
+ struct mm_struct * old_mm;
+ void *old_ldt, *ldt;
+
+ ldt = NULL;
+ old_mm = current->mm;
+ if (old_mm && (old_ldt = old_mm->context.segments) != NULL) {
+ /*
+ * Completely new LDT, we initialize it from the parent:
+ */
+ ldt = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE);
+ if (!ldt)
+ printk(KERN_WARNING "ldt allocation failed\n");
+ else
+ memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_SIZE);
+ }
+ new_mm->context.segments = ldt;
+ new_mm->context.cpuvalid = ~0UL; /* valid on all CPU's - they can't have stale data */
+}
+
+/*
+ * Save a segment.
+ */
+#define savesegment(seg,value) \
+ asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))
+
+int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
+ unsigned long unused,
+ struct task_struct * p, struct pt_regs * regs)
+{
+ struct pt_regs * childregs;
+
+ childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;
+ struct_cpy(childregs, regs);
+ childregs->eax = 0;
+ childregs->esp = esp;
+
+ p->thread.esp = (unsigned long) childregs;
+ p->thread.esp0 = (unsigned long) (childregs+1);
+
+ p->thread.eip = (unsigned long) ret_from_fork;
+
+ savesegment(fs,p->thread.fs);
+ savesegment(gs,p->thread.gs);
+
+ unlazy_fpu(current);
+ struct_cpy(&p->thread.i387, ¤t->thread.i387);
+
+ return 0;
+}
+
+/*
+ * fill in the user structure for a core dump..
+ */
+void dump_thread(struct pt_regs * regs, struct user * dump)
+{
+ int i;
+
+/* changed the size calculations - should hopefully work better. lbt */
+ dump->magic = CMAGIC;
+ dump->start_code = 0;
+ dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
+ dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
+ dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
+ dump->u_dsize -= dump->u_tsize;
+ dump->u_ssize = 0;
+ for (i = 0; i < 8; i++)
+ dump->u_debugreg[i] = current->thread.debugreg[i];
+
+ if (dump->start_stack < TASK_SIZE)
+ dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;
+
+ dump->regs.ebx = regs->ebx;
+ dump->regs.ecx = regs->ecx;
+ dump->regs.edx = regs->edx;
+ dump->regs.esi = regs->esi;
+ dump->regs.edi = regs->edi;
+ dump->regs.ebp = regs->ebp;
+ dump->regs.eax = regs->eax;
+ dump->regs.ds = regs->xds;
+ dump->regs.es = regs->xes;
+ savesegment(fs,dump->regs.fs);
+ savesegment(gs,dump->regs.gs);
+ dump->regs.orig_eax = regs->orig_eax;
+ dump->regs.eip = regs->eip;
+ dump->regs.cs = regs->xcs;
+ dump->regs.eflags = regs->eflags;
+ dump->regs.esp = regs->esp;
+ dump->regs.ss = regs->xss;
+
+ dump->u_fpvalid = dump_fpu (regs, &dump->i387);
+}
+
+/*
+ * switch_to(x,yn) should switch tasks from x to y.
+ *
+ * We fsave/fwait so that an exception goes off at the right time
+ * (as a call from the fsave or fwait in effect) rather than to
+ * the wrong process. Lazy FP saving no longer makes any sense
+ * with modern CPU's, and this simplifies a lot of things (SMP
+ * and UP become the same).
+ *
+ * NOTE! We used to use the x86 hardware context switching. The
+ * reason for not using it any more becomes apparent when you
+ * try to recover gracefully from saved state that is no longer
+ * valid (stale segment register values in particular). With the
+ * hardware task-switch, there is no way to fix up bad state in
+ * a reasonable manner.
+ *
+ * The fact that Intel documents the hardware task-switching to
+ * be slow is a fairly red herring - this code is not noticeably
+ * faster. However, there _is_ some room for improvement here,
+ * so the performance issues may eventually be a valid point.
+ * More important, however, is the fact that this allows us much
+ * more flexibility.
+ */
+void __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
+{
+ struct thread_struct *prev = &prev_p->thread,
+ *next = &next_p->thread;
+
+ unlazy_fpu(prev_p);
+
+ HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, next->esp0, 0);
+
+ /*
+ * Save away %fs and %gs. No need to save %es and %ds, as
+ * those are always kernel segments while inside the kernel.
+ */
+ asm volatile("movl %%fs,%0":"=m" (*(int *)&prev->fs));
+ asm volatile("movl %%gs,%0":"=m" (*(int *)&prev->gs));
+
+ /*
+ * Restore %fs and %gs.
+ */
+ loadsegment(fs, next->fs);
+ loadsegment(gs, next->gs);
+
+ /*
+ * Now maybe reload the debug registers
+ */
+ if ( next->debugreg[7] != 0 )
+ {
+ HYPERVISOR_set_debugreg(0, next->debugreg[0]);
+ HYPERVISOR_set_debugreg(1, next->debugreg[1]);
+ HYPERVISOR_set_debugreg(2, next->debugreg[2]);
+ HYPERVISOR_set_debugreg(3, next->debugreg[3]);
+ /* no 4 and 5 */
+ HYPERVISOR_set_debugreg(6, next->debugreg[6]);
+ HYPERVISOR_set_debugreg(7, next->debugreg[7]);
+ }
+}
+
+asmlinkage int sys_fork(struct pt_regs regs)
+{
+ return do_fork(SIGCHLD, regs.esp, ®s, 0);
+}
+
+asmlinkage int sys_clone(struct pt_regs regs)
+{
+ unsigned long clone_flags;
+ unsigned long newsp;
+
+ clone_flags = regs.ebx;
+ newsp = regs.ecx;
+ if (!newsp)
+ newsp = regs.esp;
+ return do_fork(clone_flags, newsp, ®s, 0);
+}
+
+/*
+ * This is trivial, and on the face of it looks like it
+ * could equally well be done in user mode.
+ *
+ * Not so, for quite unobvious reasons - register pressure.
+ * In user mode vfork() cannot have a stack frame, and if
+ * done by calling the "clone()" system call directly, you
+ * do not have enough call-clobbered registers to hold all
+ * the information you need.
+ */
+asmlinkage int sys_vfork(struct pt_regs regs)
+{
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0);
+}
+
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage int sys_execve(struct pt_regs regs)
+{
+ int error;
+ char * filename;
+
+ filename = getname((char *) regs.ebx);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ goto out;
+ error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, ®s);
+ if (error == 0)
+ current->ptrace &= ~PT_DTRACE;
+ putname(filename);
+ out:
+ return error;
+}
+
+/*
+ * These bracket the sleeping functions..
+ */
+extern void scheduling_functions_start_here(void);
+extern void scheduling_functions_end_here(void);
+#define first_sched ((unsigned long) scheduling_functions_start_here)
+#define last_sched ((unsigned long) scheduling_functions_end_here)
+
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ebp, esp, eip;
+ unsigned long stack_page;
+ int count = 0;
+ if (!p || p == current || p->state == TASK_RUNNING)
+ return 0;
+ stack_page = (unsigned long)p;
+ esp = p->thread.esp;
+ if (!stack_page || esp < stack_page || esp > 8188+stack_page)
+ return 0;
+ /* include/asm-i386/system.h:switch_to() pushes ebp last. */
+ ebp = *(unsigned long *) esp;
+ do {
+ if (ebp < stack_page || ebp > 8184+stack_page)
+ return 0;
+ eip = *(unsigned long *) (ebp+4);
+ if (eip < first_sched || eip >= last_sched)
+ return eip;
+ ebp = *(unsigned long *) ebp;
+ } while (count++ < 16);
+ return 0;
+}
+#undef last_sched
+#undef first_sched
--- /dev/null
+/* ptrace.c */
+/* By Ross Biro 1/23/92 */
+/*
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/debugreg.h>
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+/* determines which flags the user has access to. */
+/* 1 = access 0 = no access */
+#define FLAG_MASK 0x00044dd5
+
+/* set's the trap flag. */
+#define TRAP_FLAG 0x100
+
+/*
+ * Offset of eflags on child stack..
+ */
+#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))
+
+/*
+ * this routine will get a word off of the processes privileged stack.
+ * the offset is how far from the base addr as stored in the TSS.
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int get_stack_long(struct task_struct *task, int offset)
+{
+ unsigned char *stack;
+
+ stack = (unsigned char *)task->thread.esp0;
+ stack += offset;
+ return (*((int *)stack));
+}
+
+/*
+ * this routine will put a word on the processes privileged stack.
+ * the offset is how far from the base addr as stored in the TSS.
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int put_stack_long(struct task_struct *task, int offset,
+ unsigned long data)
+{
+ unsigned char * stack;
+
+ stack = (unsigned char *) task->thread.esp0;
+ stack += offset;
+ *(unsigned long *) stack = data;
+ return 0;
+}
+
+static int putreg(struct task_struct *child,
+ unsigned long regno, unsigned long value)
+{
+ switch (regno >> 2) {
+ case FS:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ child->thread.fs = value;
+ return 0;
+ case GS:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ child->thread.gs = value;
+ return 0;
+ case DS:
+ case ES:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ value &= 0xffff;
+ break;
+ case SS:
+ case CS:
+ if ((value & 3) != 3)
+ return -EIO;
+ value &= 0xffff;
+ break;
+ case EFL:
+ value &= FLAG_MASK;
+ value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
+ break;
+ }
+ if (regno > GS*4)
+ regno -= 2*4;
+ put_stack_long(child, regno - sizeof(struct pt_regs), value);
+ return 0;
+}
+
+static unsigned long getreg(struct task_struct *child,
+ unsigned long regno)
+{
+ unsigned long retval = ~0UL;
+
+ switch (regno >> 2) {
+ case FS:
+ retval = child->thread.fs;
+ break;
+ case GS:
+ retval = child->thread.gs;
+ break;
+ case DS:
+ case ES:
+ case SS:
+ case CS:
+ retval = 0xffff;
+ /* fall through */
+ default:
+ if (regno > GS*4)
+ regno -= 2*4;
+ regno = regno - sizeof(struct pt_regs);
+ retval &= get_stack_long(child, regno);
+ }
+ return retval;
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure the single step bit is not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+ long tmp;
+
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+}
+
+asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
+{
+ struct task_struct *child;
+ struct user * dummy = NULL;
+ int i, ret;
+
+ lock_kernel();
+ ret = -EPERM;
+ if (request == PTRACE_TRACEME) {
+ /* are we already being traced? */
+ if (current->ptrace & PT_PTRACED)
+ goto out;
+ /* set the ptrace bit in the process flags. */
+ current->ptrace |= PT_PTRACED;
+ ret = 0;
+ goto out;
+ }
+ ret = -ESRCH;
+ read_lock(&tasklist_lock);
+ child = find_task_by_pid(pid);
+ if (child)
+ get_task_struct(child);
+ read_unlock(&tasklist_lock);
+ if (!child)
+ goto out;
+
+ ret = -EPERM;
+ if (pid == 1) /* you may not mess with init */
+ goto out_tsk;
+
+ if (request == PTRACE_ATTACH) {
+ ret = ptrace_attach(child);
+ goto out_tsk;
+ }
+
+ ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ if (ret < 0)
+ goto out_tsk;
+
+ switch (request) {
+ /* when I and D space are separate, these will need to be fixed. */
+ case PTRACE_PEEKTEXT: /* read word at location addr. */
+ case PTRACE_PEEKDATA: {
+ unsigned long tmp;
+ int copied;
+
+ copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+ ret = -EIO;
+ if (copied != sizeof(tmp))
+ break;
+ ret = put_user(tmp,(unsigned long *) data);
+ break;
+ }
+
+ /* read the word at location addr in the USER area. */
+ case PTRACE_PEEKUSR: {
+ unsigned long tmp;
+
+ ret = -EIO;
+ if ((addr & 3) || addr < 0 ||
+ addr > sizeof(struct user) - 3)
+ break;
+
+ tmp = 0; /* Default return condition */
+ if(addr < FRAME_SIZE*sizeof(long))
+ tmp = getreg(child, addr);
+ if(addr >= (long) &dummy->u_debugreg[0] &&
+ addr <= (long) &dummy->u_debugreg[7]){
+ addr -= (long) &dummy->u_debugreg[0];
+ addr = addr >> 2;
+ tmp = child->thread.debugreg[addr];
+ }
+ ret = put_user(tmp,(unsigned long *) data);
+ break;
+ }
+
+ /* when I and D space are separate, this will have to be fixed. */
+ case PTRACE_POKETEXT: /* write the word at location addr. */
+ case PTRACE_POKEDATA:
+ ret = 0;
+ if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
+ break;
+ ret = -EIO;
+ break;
+
+ case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
+ ret = -EIO;
+ if ((addr & 3) || addr < 0 ||
+ addr > sizeof(struct user) - 3)
+ break;
+
+ if (addr < FRAME_SIZE*sizeof(long)) {
+ ret = putreg(child, addr, data);
+ break;
+ }
+ /* We need to be very careful here. We implicitly
+ want to modify a portion of the task_struct, and we
+ have to be selective about what portions we allow someone
+ to modify. */
+
+ ret = -EIO;
+ if(addr >= (long) &dummy->u_debugreg[0] &&
+ addr <= (long) &dummy->u_debugreg[7]){
+
+ if(addr == (long) &dummy->u_debugreg[4]) break;
+ if(addr == (long) &dummy->u_debugreg[5]) break;
+ if(addr < (long) &dummy->u_debugreg[4] &&
+ ((unsigned long) data) >= TASK_SIZE-3) break;
+
+ if(addr == (long) &dummy->u_debugreg[7]) {
+ data &= ~DR_CONTROL_RESERVED;
+ for(i=0; i<4; i++)
+ if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
+ goto out_tsk;
+ }
+
+ addr -= (long) &dummy->u_debugreg;
+ addr = addr >> 2;
+ child->thread.debugreg[addr] = data;
+ ret = 0;
+ }
+ break;
+
+ case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
+ case PTRACE_CONT: { /* restart after signal. */
+ long tmp;
+
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ if (request == PTRACE_SYSCALL)
+ child->ptrace |= PT_TRACESYS;
+ else
+ child->ptrace &= ~PT_TRACESYS;
+ child->exit_code = data;
+ /* make sure the single step bit is not set. */
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET,tmp);
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+/*
+ * make the child exit. Best I can do is send it a sigkill.
+ * perhaps it should be put in the status that it wants to
+ * exit.
+ */
+ case PTRACE_KILL: {
+ long tmp;
+
+ ret = 0;
+ if (child->state == TASK_ZOMBIE) /* already dead */
+ break;
+ child->exit_code = SIGKILL;
+ /* make sure the single step bit is not set. */
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+ wake_up_process(child);
+ break;
+ }
+
+ case PTRACE_SINGLESTEP: { /* set the trap flag. */
+ long tmp;
+
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ child->ptrace &= ~PT_TRACESYS;
+ if ((child->ptrace & PT_DTRACE) == 0) {
+ /* Spurious delayed TF traps may occur */
+ child->ptrace |= PT_DTRACE;
+ }
+ tmp = get_stack_long(child, EFL_OFFSET) | TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+ child->exit_code = data;
+ /* give it a chance to run. */
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_DETACH:
+ /* detach a process that was attached. */
+ ret = ptrace_detach(child, data);
+ break;
+
+ case PTRACE_GETREGS: { /* Get all gp regs from the child. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
+ ret = -EIO;
+ break;
+ }
+ for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+ __put_user(getreg(child, i),(unsigned long *) data);
+ data += sizeof(long);
+ }
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_SETREGS: { /* Set all gp regs in the child. */
+ unsigned long tmp;
+ if (!access_ok(VERIFY_READ, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
+ ret = -EIO;
+ break;
+ }
+ for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+ __get_user(tmp, (unsigned long *) data);
+ putreg(child, i, tmp);
+ data += sizeof(long);
+ }
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETFPREGS: { /* Get the child FPU state. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data,
+ sizeof(struct user_i387_struct))) {
+ ret = -EIO;
+ break;
+ }
+ ret = 0;
+ if ( !child->used_math ) {
+ /* Simulate an empty FPU. */
+ set_fpu_cwd(child, 0x037f);
+ set_fpu_swd(child, 0x0000);
+ set_fpu_twd(child, 0xffff);
+ }
+ get_fpregs((struct user_i387_struct *)data, child);
+ break;
+ }
+
+ case PTRACE_SETFPREGS: { /* Set the child FPU state. */
+ if (!access_ok(VERIFY_READ, (unsigned *)data,
+ sizeof(struct user_i387_struct))) {
+ ret = -EIO;
+ break;
+ }
+ child->used_math = 1;
+ set_fpregs(child, (struct user_i387_struct *)data);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data,
+ sizeof(struct user_fxsr_struct))) {
+ ret = -EIO;
+ break;
+ }
+ if ( !child->used_math ) {
+ /* Simulate an empty FPU. */
+ set_fpu_cwd(child, 0x037f);
+ set_fpu_swd(child, 0x0000);
+ set_fpu_twd(child, 0xffff);
+ set_fpu_mxcsr(child, 0x1f80);
+ }
+ ret = get_fpxregs((struct user_fxsr_struct *)data, child);
+ break;
+ }
+
+ case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
+ if (!access_ok(VERIFY_READ, (unsigned *)data,
+ sizeof(struct user_fxsr_struct))) {
+ ret = -EIO;
+ break;
+ }
+ child->used_math = 1;
+ ret = set_fpxregs(child, (struct user_fxsr_struct *)data);
+ break;
+ }
+
+ case PTRACE_SETOPTIONS: {
+ if (data & PTRACE_O_TRACESYSGOOD)
+ child->ptrace |= PT_TRACESYSGOOD;
+ else
+ child->ptrace &= ~PT_TRACESYSGOOD;
+ ret = 0;
+ break;
+ }
+
+ default:
+ ret = -EIO;
+ break;
+ }
+out_tsk:
+ free_task_struct(child);
+out:
+ unlock_kernel();
+ return ret;
+}
+
+asmlinkage void syscall_trace(void)
+{
+ if ((current->ptrace & (PT_PTRACED|PT_TRACESYS)) !=
+ (PT_PTRACED|PT_TRACESYS))
+ return;
+ /* the 0x80 provides a way for the tracing parent to distinguish
+ between a syscall stop and SIGTRAP delivery */
+ current->exit_code = SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
+ ? 0x80 : 0);
+ current->state = TASK_STOPPED;
+ notify_parent(current, SIGCHLD);
+ schedule();
+ /*
+ * this isn't the same as continuing with a signal, but it will do
+ * for normal use. strace only continues with a signal if the
+ * stopping signal is not SIGTRAP. -brl
+ */
+ if (current->exit_code) {
+ send_sig(current->exit_code, current, 1);
+ current->exit_code = 0;
+ }
+}
--- /dev/null
+/*
+ * i386 semaphore implementation.
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ *
+ * Portions Copyright 1999 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@redhat.com>
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/semaphore.h>
+
+/*
+ * Semaphores are implemented using a two-way counter:
+ * The "count" variable is decremented for each process
+ * that tries to acquire the semaphore, while the "sleeping"
+ * variable is a count of such acquires.
+ *
+ * Notably, the inline "up()" and "down()" functions can
+ * efficiently test if they need to do any extra work (up
+ * needs to do something only if count was negative before
+ * the increment operation.
+ *
+ * "sleeping" and the contention routine ordering is
+ * protected by the semaphore spinlock.
+ *
+ * Note that these functions are only called when there is
+ * contention on the lock, and as such all this is the
+ * "non-critical" part of the whole semaphore business. The
+ * critical part is the inline stuff in <asm/semaphore.h>
+ * where we want to avoid any extra jumps and calls.
+ */
+
+/*
+ * Logic:
+ * - only on a boundary condition do we need to care. When we go
+ * from a negative count to a non-negative, we wake people up.
+ * - when we go from a non-negative count to a negative do we
+ * (a) synchronize with the "sleeper" count and (b) make sure
+ * that we're on the wakeup list before we synchronize so that
+ * we cannot lose wakeup events.
+ */
+
+void __up(struct semaphore *sem)
+{
+ wake_up(&sem->wait);
+}
+
+static spinlock_t semaphore_lock = SPIN_LOCK_UNLOCKED;
+
+void __down(struct semaphore * sem)
+{
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+
+ spin_lock_irq(&semaphore_lock);
+ sem->sleepers++;
+ for (;;) {
+ int sleepers = sem->sleepers;
+
+ /*
+ * Add "everybody else" into it. They aren't
+ * playing, because we own the spinlock.
+ */
+ if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+ sem->sleepers = 0;
+ break;
+ }
+ sem->sleepers = 1; /* us - see -1 above */
+ spin_unlock_irq(&semaphore_lock);
+
+ schedule();
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ spin_lock_irq(&semaphore_lock);
+ }
+ spin_unlock_irq(&semaphore_lock);
+ remove_wait_queue(&sem->wait, &wait);
+ tsk->state = TASK_RUNNING;
+ wake_up(&sem->wait);
+}
+
+int __down_interruptible(struct semaphore * sem)
+{
+ int retval = 0;
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+ tsk->state = TASK_INTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+
+ spin_lock_irq(&semaphore_lock);
+ sem->sleepers ++;
+ for (;;) {
+ int sleepers = sem->sleepers;
+
+ /*
+ * With signals pending, this turns into
+ * the trylock failure case - we won't be
+ * sleeping, and we* can't get the lock as
+ * it has contention. Just correct the count
+ * and exit.
+ */
+ if (signal_pending(current)) {
+ retval = -EINTR;
+ sem->sleepers = 0;
+ atomic_add(sleepers, &sem->count);
+ break;
+ }
+
+ /*
+ * Add "everybody else" into it. They aren't
+ * playing, because we own the spinlock. The
+ * "-1" is because we're still hoping to get
+ * the lock.
+ */
+ if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+ sem->sleepers = 0;
+ break;
+ }
+ sem->sleepers = 1; /* us - see -1 above */
+ spin_unlock_irq(&semaphore_lock);
+
+ schedule();
+ tsk->state = TASK_INTERRUPTIBLE;
+ spin_lock_irq(&semaphore_lock);
+ }
+ spin_unlock_irq(&semaphore_lock);
+ tsk->state = TASK_RUNNING;
+ remove_wait_queue(&sem->wait, &wait);
+ wake_up(&sem->wait);
+ return retval;
+}
+
+/*
+ * Trylock failed - make sure we correct for
+ * having decremented the count.
+ *
+ * We could have done the trylock with a
+ * single "cmpxchg" without failure cases,
+ * but then it wouldn't work on a 386.
+ */
+int __down_trylock(struct semaphore * sem)
+{
+ int sleepers;
+ unsigned long flags;
+
+ spin_lock_irqsave(&semaphore_lock, flags);
+ sleepers = sem->sleepers + 1;
+ sem->sleepers = 0;
+
+ /*
+ * Add "everybody else" and us into it. They aren't
+ * playing, because we own the spinlock.
+ */
+ if (!atomic_add_negative(sleepers, &sem->count))
+ wake_up(&sem->wait);
+
+ spin_unlock_irqrestore(&semaphore_lock, flags);
+ return 1;
+}
+
+
+/*
+ * The semaphore operations have a special calling sequence that
+ * allow us to do a simpler in-line version of them. These routines
+ * need to convert that sequence back into the C sequence when
+ * there is contention on the semaphore.
+ *
+ * %ecx contains the semaphore pointer on entry. Save the C-clobbered
+ * registers (%eax, %edx and %ecx) except %eax when used as a return
+ * value..
+ */
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed\n"
+"__down_failed:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %eax\n\t"
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+ "popl %eax\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed_interruptible\n"
+"__down_failed_interruptible:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down_interruptible\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed_trylock\n"
+"__down_failed_trylock:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down_trylock\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __up_wakeup\n"
+"__up_wakeup:\n\t"
+ "pushl %eax\n\t"
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __up\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+ "popl %eax\n\t"
+ "ret"
+);
+
+/*
+ * rw spinlock fallbacks
+ */
+#if defined(CONFIG_SMP)
+asm(
+"
+.align 4
+.globl __write_lock_failed
+__write_lock_failed:
+ " LOCK "addl $" RW_LOCK_BIAS_STR ",(%eax)
+1: rep; nop
+ cmpl $" RW_LOCK_BIAS_STR ",(%eax)
+ jne 1b
+
+ " LOCK "subl $" RW_LOCK_BIAS_STR ",(%eax)
+ jnz __write_lock_failed
+ ret
+
+
+.align 4
+.globl __read_lock_failed
+__read_lock_failed:
+ lock ; incl (%eax)
+1: rep; nop
+ cmpl $1,(%eax)
+ js 1b
+
+ lock ; decl (%eax)
+ js __read_lock_failed
+ ret
+"
+);
+#endif
--- /dev/null
+/*
+ * linux/arch/i386/kernel/setup.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/tty.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/apm_bios.h>
+#ifdef CONFIG_BLK_DEV_RAM
+#include <linux/blk.h>
+#endif
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <asm/processor.h>
+#include <linux/console.h>
+#include <asm/mtrr.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/msr.h>
+#include <asm/desc.h>
+#include <asm/dma.h>
+#include <asm/mpspec.h>
+#include <asm/mmu_context.h>
+#include <asm/hypervisor.h>
+
+shared_info_t *HYPERVISOR_shared_info;
+
+unsigned long *phys_to_machine_mapping;
+
+/*
+ * Machine setup..
+ */
+
+char ignore_irq13; /* set if exception 16 works */
+struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
+
+unsigned long mmu_cr4_features;
+
+/*
+ * Bus types ..
+ */
+#ifdef CONFIG_EISA
+int EISA_bus;
+#endif
+int MCA_bus;
+
+/* for MCA, but anyone else can use it if they want */
+unsigned int machine_id;
+unsigned int machine_submodel_id;
+unsigned int BIOS_revision;
+unsigned int mca_pentium_flag;
+
+/* For PCI or other memory-mapped resources */
+unsigned long pci_mem_start = 0x10000000;
+
+/*
+ * Setup options
+ */
+struct drive_info_struct { char dummy[32]; } drive_info;
+struct screen_info screen_info;
+struct apm_info apm_info;
+struct sys_desc_table_struct {
+ unsigned short length;
+ unsigned char table[0];
+};
+
+unsigned char aux_device_present;
+
+extern int root_mountflags;
+extern char _text, _etext, _edata, _end;
+
+int enable_acpi_smp_table;
+
+/* Raw start-of-day parameters from the hypervisor. */
+union start_info_union start_info_union;
+
+#define COMMAND_LINE_SIZE 256
+static char command_line[COMMAND_LINE_SIZE];
+char saved_command_line[COMMAND_LINE_SIZE];
+
+static void __init parse_mem_cmdline (char ** cmdline_p)
+{
+ char c = ' ', *to = command_line, *from = saved_command_line;
+ int len = 0;
+
+ /* Save unparsed command line copy for /proc/cmdline */
+ memcpy(saved_command_line, start_info.cmd_line, COMMAND_LINE_SIZE);
+ saved_command_line[COMMAND_LINE_SIZE-1] = '\0';
+
+ for (;;) {
+ /*
+ * "mem=nopentium" disables the 4MB page tables.
+ * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
+ * to <mem>, overriding the bios size.
+ * "mem=XXX[KkmM]@XXX[KkmM]" defines a memory region from
+ * <start> to <start>+<mem>, overriding the bios size.
+ */
+ if (c == ' ' && !memcmp(from, "mem=", 4)) {
+ if (to != command_line)
+ to--;
+ if (!memcmp(from+4, "nopentium", 9)) {
+ from += 9+4;
+ } else if (!memcmp(from+4, "exactmap", 8)) {
+ from += 8+4;
+ } else {
+ (void)memparse(from+4, &from);
+ if (*from == '@')
+ (void)memparse(from+1, &from);
+ }
+ }
+
+ c = *(from++);
+ if (!c)
+ break;
+ if (COMMAND_LINE_SIZE <= ++len)
+ break;
+ *(to++) = c;
+ }
+ *to = '\0';
+ *cmdline_p = command_line;
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+ unsigned long start_pfn, max_pfn, max_low_pfn;
+ unsigned long bootmap_size;
+ unsigned long i;
+
+ extern void hypervisor_callback(void);
+ extern void failsafe_callback(void);
+
+ extern unsigned long cpu0_pte_quicklist[];
+ extern unsigned long cpu0_pgd_quicklist[];
+
+ HYPERVISOR_shared_info->event_address =
+ (unsigned long)hypervisor_callback;
+ HYPERVISOR_shared_info->failsafe_address =
+ (unsigned long)failsafe_callback;
+
+ boot_cpu_data.pgd_quick = cpu0_pgd_quicklist;
+ boot_cpu_data.pte_quick = cpu0_pte_quicklist;
+
+ ROOT_DEV = MKDEV(RAMDISK_MAJOR,0);
+ memset(&drive_info, 0, sizeof(drive_info));
+ memset(&screen_info, 0, sizeof(screen_info));
+ memset(&apm_info.bios, 0, sizeof(apm_info.bios));
+ aux_device_present = 0;
+
+#ifdef CONFIG_BLK_DEV_RAM
+ rd_image_start = 0;
+ rd_prompt = 0;
+ rd_doload = 0;
+#endif
+
+ root_mountflags &= ~MS_RDONLY;
+ init_mm.start_code = (unsigned long) &_text;
+ init_mm.end_code = (unsigned long) &_etext;
+ init_mm.end_data = (unsigned long) &_edata;
+ init_mm.brk = (unsigned long) &_end;
+
+ parse_mem_cmdline(cmdline_p);
+
+#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
+#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
+#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
+
+/*
+ * 128MB for vmalloc and initrd
+ */
+#define VMALLOC_RESERVE (unsigned long)(128 << 20)
+#define MAXMEM (unsigned long)(HYPERVISOR_VIRT_START-PAGE_OFFSET-VMALLOC_RESERVE)
+#define MAXMEM_PFN PFN_DOWN(MAXMEM)
+#define MAX_NONPAE_PFN (1 << 20)
+
+ /*
+ * partially used pages are not usable - thus
+ * we are rounding upwards:
+ */
+#ifdef CONFIG_BLK_DEV_INITRD
+ if ( start_info.mod_start )
+ start_pfn = PFN_UP(__pa(start_info.mod_start + start_info.mod_len));
+ else
+#endif
+ start_pfn = PFN_UP(__pa(&_end));
+ max_pfn = start_info.nr_pages;
+
+ /*
+ * Determine low and high memory ranges:
+ */
+ max_low_pfn = max_pfn;
+ if (max_low_pfn > MAXMEM_PFN) {
+ max_low_pfn = MAXMEM_PFN;
+#ifndef CONFIG_HIGHMEM
+ /* Maximum memory usable is what is directly addressable */
+ printk(KERN_WARNING "Warning only %ldMB will be used.\n",
+ MAXMEM>>20);
+ if (max_pfn > MAX_NONPAE_PFN)
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ else
+ printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+#else /* !CONFIG_HIGHMEM */
+#ifndef CONFIG_X86_PAE
+ if (max_pfn > MAX_NONPAE_PFN) {
+ max_pfn = MAX_NONPAE_PFN;
+ printk(KERN_WARNING "Warning only 4GB will be used.\n");
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ }
+#endif /* !CONFIG_X86_PAE */
+#endif /* !CONFIG_HIGHMEM */
+ }
+
+#ifdef CONFIG_HIGHMEM
+ highstart_pfn = highend_pfn = max_pfn;
+ if (max_pfn > MAXMEM_PFN) {
+ highstart_pfn = MAXMEM_PFN;
+ printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
+ pages_to_mb(highend_pfn - highstart_pfn));
+ }
+#endif
+
+ /*
+ * Initialize the boot-time allocator, and free up all RAM.
+ * Then reserve space for OS image, and the bootmem bitmap.
+ */
+ bootmap_size = init_bootmem(start_pfn, max_low_pfn);
+ free_bootmem(0, PFN_PHYS(max_low_pfn));
+ reserve_bootmem(0, PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1);
+
+ /* Now reserve space for the hypervisor-provided page tables. */
+ {
+ unsigned long *pgd = (unsigned long *)start_info.pt_base;
+ unsigned long pte;
+ int i;
+ reserve_bootmem(__pa(pgd), PAGE_SIZE);
+ for ( i = 0; i < (HYPERVISOR_VIRT_START>>22); i++ )
+ {
+ unsigned long pgde = *pgd++;
+ if ( !(pgde & 1) ) continue;
+ pte = machine_to_phys(pgde & PAGE_MASK);
+ reserve_bootmem(pte, PAGE_SIZE);
+ }
+ }
+ cur_pgd = init_mm.pgd = (pgd_t *)start_info.pt_base;
+
+ /* Now initialise the physical->machine mapping table. */
+ phys_to_machine_mapping = alloc_bootmem(max_pfn * sizeof(unsigned long));
+ for ( i = 0; i < max_pfn; i++ )
+ {
+ unsigned long pgde, *ppte;
+ unsigned long pfn = i + (PAGE_OFFSET >> PAGE_SHIFT);
+ pgde = *((unsigned long *)start_info.pt_base + (pfn >> 10));
+ ppte = (unsigned long *)machine_to_phys(pgde & PAGE_MASK) + (pfn&1023);
+ phys_to_machine_mapping[i] =
+ (*(unsigned long *)__va(ppte)) >> PAGE_SHIFT;
+ }
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (start_info.mod_start) {
+ if ((__pa(start_info.mod_start) + start_info.mod_len) <=
+ (max_low_pfn << PAGE_SHIFT)) {
+ initrd_start = start_info.mod_start;
+ initrd_end = initrd_start + start_info.mod_len;
+ initrd_below_start_ok = 1;
+ }
+ else {
+ printk(KERN_ERR "initrd extends beyond end of memory "
+ "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
+ __pa(start_info.mod_start) + start_info.mod_len,
+ max_low_pfn << PAGE_SHIFT);
+ initrd_start = 0;
+ }
+ }
+#endif
+
+ paging_init();
+}
+
+static int cachesize_override __initdata = -1;
+static int __init cachesize_setup(char *str)
+{
+ get_option (&str, &cachesize_override);
+ return 1;
+}
+__setup("cachesize=", cachesize_setup);
+
+
+static int __init get_model_name(struct cpuinfo_x86 *c)
+{
+ unsigned int *v;
+ char *p, *q;
+
+ if (cpuid_eax(0x80000000) < 0x80000004)
+ return 0;
+
+ v = (unsigned int *) c->x86_model_id;
+ cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
+ cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
+ cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
+ c->x86_model_id[48] = 0;
+
+ /* Intel chips right-justify this string for some dumb reason;
+ undo that brain damage */
+ p = q = &c->x86_model_id[0];
+ while ( *p == ' ' )
+ p++;
+ if ( p != q ) {
+ while ( *p )
+ *q++ = *p++;
+ while ( q <= &c->x86_model_id[48] )
+ *q++ = '\0'; /* Zero-pad the rest */
+ }
+
+ return 1;
+}
+
+
+static void __init display_cacheinfo(struct cpuinfo_x86 *c)
+{
+ unsigned int n, dummy, ecx, edx, l2size;
+
+ n = cpuid_eax(0x80000000);
+
+ if (n >= 0x80000005) {
+ cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
+ printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
+ edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+ c->x86_cache_size=(ecx>>24)+(edx>>24);
+ }
+
+ if (n < 0x80000006) /* Some chips just has a large L1. */
+ return;
+
+ ecx = cpuid_ecx(0x80000006);
+ l2size = ecx >> 16;
+
+ /* AMD errata T13 (order #21922) */
+ if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) {
+ if (c->x86_model == 3 && c->x86_mask == 0) /* Duron Rev A0 */
+ l2size = 64;
+ if (c->x86_model == 4 &&
+ (c->x86_mask==0 || c->x86_mask==1)) /* Tbird rev A1/A2 */
+ l2size = 256;
+ }
+
+ /* Intel PIII Tualatin. This comes in two flavours.
+ * One has 256kb of cache, the other 512. We have no way
+ * to determine which, so we use a boottime override
+ * for the 512kb model, and assume 256 otherwise.
+ */
+ if ((c->x86_vendor == X86_VENDOR_INTEL) && (c->x86 == 6) &&
+ (c->x86_model == 11) && (l2size == 0))
+ l2size = 256;
+
+ /* VIA C3 CPUs (670-68F) need further shifting. */
+ if (c->x86_vendor == X86_VENDOR_CENTAUR && (c->x86 == 6) &&
+ ((c->x86_model == 7) || (c->x86_model == 8))) {
+ l2size = l2size >> 8;
+ }
+
+ /* Allow user to override all this if necessary. */
+ if (cachesize_override != -1)
+ l2size = cachesize_override;
+
+ if ( l2size == 0 )
+ return; /* Again, no L2 cache is possible */
+
+ c->x86_cache_size = l2size;
+
+ printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
+ l2size, ecx & 0xFF);
+}
+
+
+static int __init init_amd(struct cpuinfo_x86 *c)
+{
+ int r;
+
+ /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+ clear_bit(0*32+31, &c->x86_capability);
+
+ r = get_model_name(c);
+
+ switch(c->x86)
+ {
+ case 6: /* An Athlon/Duron. We can trust the BIOS probably */
+ break;
+ default:
+ panic("Unsupported AMD processor\n");
+ }
+
+ display_cacheinfo(c);
+ return r;
+}
+
+
+static void __init init_intel(struct cpuinfo_x86 *c)
+{
+ char *p = NULL;
+ unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */
+
+ if (c->cpuid_level > 1) {
+ /* supports eax=2 call */
+ int i, j, n;
+ int regs[4];
+ unsigned char *dp = (unsigned char *)regs;
+
+ /* Number of times to iterate */
+ n = cpuid_eax(2) & 0xFF;
+
+ for ( i = 0 ; i < n ; i++ ) {
+ cpuid(2, ®s[0], ®s[1], ®s[2], ®s[3]);
+
+ /* If bit 31 is set, this is an unknown format */
+ for ( j = 0 ; j < 3 ; j++ ) {
+ if ( regs[j] < 0 ) regs[j] = 0;
+ }
+
+ /* Byte 0 is level count, not a descriptor */
+ for ( j = 1 ; j < 16 ; j++ ) {
+ unsigned char des = dp[j];
+ unsigned char dl, dh;
+ unsigned int cs;
+
+ dh = des >> 4;
+ dl = des & 0x0F;
+
+ /* Black magic... */
+
+ switch ( dh )
+ {
+ case 0:
+ switch ( dl ) {
+ case 6:
+ /* L1 I cache */
+ l1i += 8;
+ break;
+ case 8:
+ /* L1 I cache */
+ l1i += 16;
+ break;
+ case 10:
+ /* L1 D cache */
+ l1d += 8;
+ break;
+ case 12:
+ /* L1 D cache */
+ l1d += 16;
+ break;
+ default:;
+ /* TLB, or unknown */
+ }
+ break;
+ case 2:
+ if ( dl ) {
+ /* L3 cache */
+ cs = (dl-1) << 9;
+ l3 += cs;
+ }
+ break;
+ case 4:
+ if ( c->x86 > 6 && dl ) {
+ /* P4 family */
+ /* L3 cache */
+ cs = 128 << (dl-1);
+ l3 += cs;
+ break;
+ }
+ /* else same as 8 - fall through */
+ case 8:
+ if ( dl ) {
+ /* L2 cache */
+ cs = 128 << (dl-1);
+ l2 += cs;
+ }
+ break;
+ case 6:
+ if (dl > 5) {
+ /* L1 D cache */
+ cs = 8<<(dl-6);
+ l1d += cs;
+ }
+ break;
+ case 7:
+ if ( dl >= 8 )
+ {
+ /* L2 cache */
+ cs = 64<<(dl-8);
+ l2 += cs;
+ } else {
+ /* L0 I cache, count as L1 */
+ cs = dl ? (16 << (dl-1)) : 12;
+ l1i += cs;
+ }
+ break;
+ default:
+ /* TLB, or something else we don't know about */
+ break;
+ }
+ }
+ }
+ if ( l1i || l1d )
+ printk(KERN_INFO "CPU: L1 I cache: %dK, L1 D cache: %dK\n",
+ l1i, l1d);
+ if ( l2 )
+ printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);
+ if ( l3 )
+ printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);
+
+ /*
+ * This assumes the L3 cache is shared; it typically lives in
+ * the northbridge. The L1 caches are included by the L2
+ * cache, and so should not be included for the purpose of
+ * SMP switching weights.
+ */
+ c->x86_cache_size = l2 ? l2 : (l1i+l1d);
+ }
+
+ /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it */
+ if ( c->x86 == 6 && c->x86_model < 3 && c->x86_mask < 3 )
+ clear_bit(X86_FEATURE_SEP, &c->x86_capability);
+
+ /* Names for the Pentium II/Celeron processors
+ detectable only by also checking the cache size.
+ Dixon is NOT a Celeron. */
+ if (c->x86 == 6) {
+ switch (c->x86_model) {
+ case 5:
+ if (l2 == 0)
+ p = "Celeron (Covington)";
+ if (l2 == 256)
+ p = "Mobile Pentium II (Dixon)";
+ break;
+
+ case 6:
+ if (l2 == 128)
+ p = "Celeron (Mendocino)";
+ break;
+
+ case 8:
+ if (l2 == 128)
+ p = "Celeron (Coppermine)";
+ break;
+ }
+ }
+
+ if ( p )
+ strcpy(c->x86_model_id, p);
+}
+
+void __init get_cpu_vendor(struct cpuinfo_x86 *c)
+{
+ char *v = c->x86_vendor_id;
+
+ if (!strcmp(v, "GenuineIntel"))
+ c->x86_vendor = X86_VENDOR_INTEL;
+ else if (!strcmp(v, "AuthenticAMD"))
+ c->x86_vendor = X86_VENDOR_AMD;
+ else
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+}
+
+struct cpu_model_info {
+ int vendor;
+ int family;
+ char *model_names[16];
+};
+
+/* Naming convention should be: <Name> [(<Codename>)] */
+/* This table only is used unless init_<vendor>() below doesn't set it; */
+/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */
+static struct cpu_model_info cpu_models[] __initdata = {
+ { X86_VENDOR_INTEL, 6,
+ { "Pentium Pro A-step", "Pentium Pro", NULL, "Pentium II (Klamath)",
+ NULL, "Pentium II (Deschutes)", "Mobile Pentium II",
+ "Pentium III (Katmai)", "Pentium III (Coppermine)", NULL,
+ "Pentium III (Cascades)", NULL, NULL, NULL, NULL }},
+ { X86_VENDOR_AMD, 6, /* Is this this really necessary?? */
+ { "Athlon", "Athlon",
+ "Athlon", NULL, "Athlon", NULL,
+ NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL }}
+};
+
+/* Look up CPU names by table lookup. */
+static char __init *table_lookup_model(struct cpuinfo_x86 *c)
+{
+ struct cpu_model_info *info = cpu_models;
+ int i;
+
+ if ( c->x86_model >= 16 )
+ return NULL; /* Range check */
+
+ for ( i = 0 ; i < sizeof(cpu_models)/sizeof(struct cpu_model_info) ; i++ ) {
+ if ( info->vendor == c->x86_vendor &&
+ info->family == c->x86 ) {
+ return info->model_names[c->x86_model];
+ }
+ info++;
+ }
+ return NULL; /* Not found */
+}
+
+
+
+/* Standard macro to see if a specific flag is changeable */
+static inline int flag_is_changeable_p(u32 flag)
+{
+ u32 f1, f2;
+
+ asm("pushfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "movl %0,%1\n\t"
+ "xorl %2,%0\n\t"
+ "pushl %0\n\t"
+ "popfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "popfl\n\t"
+ : "=&r" (f1), "=&r" (f2)
+ : "ir" (flag));
+
+ return ((f1^f2) & flag) != 0;
+}
+
+
+/* Probe for the CPUID instruction */
+static int __init have_cpuid_p(void)
+{
+ return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+
+
+
+/*
+ * This does the hard work of actually picking apart the CPU stuff...
+ */
+void __init identify_cpu(struct cpuinfo_x86 *c)
+{
+ int junk, i;
+ u32 xlvl, tfms;
+
+ c->loops_per_jiffy = loops_per_jiffy;
+ c->x86_cache_size = -1;
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+ c->cpuid_level = -1; /* CPUID not detected */
+ c->x86_model = c->x86_mask = 0; /* So far unknown... */
+ c->x86_vendor_id[0] = '\0'; /* Unset */
+ c->x86_model_id[0] = '\0'; /* Unset */
+ memset(&c->x86_capability, 0, sizeof c->x86_capability);
+ c->hard_math = 1;
+
+ if ( !have_cpuid_p() ) {
+ panic("Processor must support CPUID\n");
+ } else {
+ /* CPU does have CPUID */
+
+ /* Get vendor name */
+ cpuid(0x00000000, &c->cpuid_level,
+ (int *)&c->x86_vendor_id[0],
+ (int *)&c->x86_vendor_id[8],
+ (int *)&c->x86_vendor_id[4]);
+
+ get_cpu_vendor(c);
+ /* Initialize the standard set of capabilities */
+ /* Note that the vendor-specific code below might override */
+
+ /* Intel-defined flags: level 0x00000001 */
+ if ( c->cpuid_level >= 0x00000001 ) {
+ cpuid(0x00000001, &tfms, &junk, &junk,
+ &c->x86_capability[0]);
+ c->x86 = (tfms >> 8) & 15;
+ c->x86_model = (tfms >> 4) & 15;
+ c->x86_mask = tfms & 15;
+ } else {
+ /* Have CPUID level 0 only - unheard of */
+ c->x86 = 4;
+ }
+
+ /* AMD-defined flags: level 0x80000001 */
+ xlvl = cpuid_eax(0x80000000);
+ if ( (xlvl & 0xffff0000) == 0x80000000 ) {
+ if ( xlvl >= 0x80000001 )
+ c->x86_capability[1] = cpuid_edx(0x80000001);
+ if ( xlvl >= 0x80000004 )
+ get_model_name(c); /* Default name */
+ }
+
+ /* Transmeta-defined flags: level 0x80860001 */
+ xlvl = cpuid_eax(0x80860000);
+ if ( (xlvl & 0xffff0000) == 0x80860000 ) {
+ if ( xlvl >= 0x80860001 )
+ c->x86_capability[2] = cpuid_edx(0x80860001);
+ }
+ }
+
+ printk(KERN_DEBUG "CPU: Before vendor init, caps: %08x %08x %08x, vendor = %d\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_vendor);
+
+ /*
+ * Vendor-specific initialization. In this section we
+ * canonicalize the feature flags, meaning if there are
+ * features a certain CPU supports which CPUID doesn't
+ * tell us, CPUID claiming incorrect flags, or other bugs,
+ * we handle them here.
+ *
+ * At the end of this section, c->x86_capability better
+ * indicate the features this CPU genuinely supports!
+ */
+ switch ( c->x86_vendor ) {
+ case X86_VENDOR_AMD:
+ init_amd(c);
+ break;
+
+ case X86_VENDOR_INTEL:
+ init_intel(c);
+ break;
+
+ default:
+ panic("Unsupported CPU vendor\n");
+ }
+
+ printk(KERN_DEBUG "CPU: After vendor init, caps: %08x %08x %08x %08x\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_capability[3]);
+
+
+ /* If the model name is still unset, do table lookup. */
+ if ( !c->x86_model_id[0] ) {
+ char *p;
+ p = table_lookup_model(c);
+ if ( p )
+ strcpy(c->x86_model_id, p);
+ else
+ /* Last resort... */
+ sprintf(c->x86_model_id, "%02x/%02x",
+ c->x86_vendor, c->x86_model);
+ }
+
+ /* Now the feature flags better reflect actual CPU features! */
+
+ printk(KERN_DEBUG "CPU: After generic, caps: %08x %08x %08x %08x\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_capability[3]);
+
+ /*
+ * On SMP, boot_cpu_data holds the common feature set between
+ * all CPUs; so make sure that we indicate which features are
+ * common between the CPUs. The first time this routine gets
+ * executed, c == &boot_cpu_data.
+ */
+ if ( c != &boot_cpu_data ) {
+ /* AND the already accumulated flags with these */
+ for ( i = 0 ; i < NCAPINTS ; i++ )
+ boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+ }
+
+ printk(KERN_DEBUG "CPU: Common caps: %08x %08x %08x %08x\n",
+ boot_cpu_data.x86_capability[0],
+ boot_cpu_data.x86_capability[1],
+ boot_cpu_data.x86_capability[2],
+ boot_cpu_data.x86_capability[3]);
+}
+
+
+/* These need to match <asm/processor.h> */
+static char *cpu_vendor_names[] __initdata = {
+ "Intel", "Cyrix", "AMD", "UMC", "NexGen", "Centaur", "Rise", "Transmeta" };
+
+
+void __init print_cpu_info(struct cpuinfo_x86 *c)
+{
+ char *vendor = NULL;
+
+ if (c->x86_vendor < sizeof(cpu_vendor_names)/sizeof(char *))
+ vendor = cpu_vendor_names[c->x86_vendor];
+ else if (c->cpuid_level >= 0)
+ vendor = c->x86_vendor_id;
+
+ if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
+ printk("%s ", vendor);
+
+ if (!c->x86_model_id[0])
+ printk("%d86", c->x86);
+ else
+ printk("%s", c->x86_model_id);
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ printk(" stepping %02x\n", c->x86_mask);
+ else
+ printk("\n");
+}
+
+/*
+ * Get CPU information for use by the procfs.
+ */
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+ /*
+ * These flag bits must match the definitions in <asm/cpufeature.h>.
+ * NULL means this bit is undefined or reserved; either way it doesn't
+ * have meaning as far as Linux is concerned. Note that it's important
+ * to realize there is a difference between this table and CPUID -- if
+ * applications want to get the raw CPUID data, they should access
+ * /dev/cpu/<cpu_nr>/cpuid instead.
+ */
+ static char *x86_cap_flags[] = {
+ /* Intel-defined */
+ "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
+ "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
+ "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
+ "fxsr", "sse", "sse2", "ss", NULL, "tm", "ia64", NULL,
+
+ /* AMD-defined */
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, "mmxext", NULL,
+ NULL, NULL, NULL, NULL, NULL, "lm", "3dnowext", "3dnow",
+
+ /* Transmeta-defined */
+ "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* Other (Linux-defined) */
+ "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ };
+ struct cpuinfo_x86 *c = v;
+ int i, n = c - cpu_data;
+ int fpu_exception;
+
+#ifdef CONFIG_SMP
+ if (!(cpu_online_map & (1<<n)))
+ return 0;
+#endif
+ seq_printf(m, "processor\t: %d\n"
+ "vendor_id\t: %s\n"
+ "cpu family\t: %d\n"
+ "model\t\t: %d\n"
+ "model name\t: %s\n",
+ n,
+ c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown",
+ c->x86,
+ c->x86_model,
+ c->x86_model_id[0] ? c->x86_model_id : "unknown");
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ seq_printf(m, "stepping\t: %d\n", c->x86_mask);
+ else
+ seq_printf(m, "stepping\t: unknown\n");
+
+ if ( test_bit(X86_FEATURE_TSC, &c->x86_capability) ) {
+ seq_printf(m, "cpu MHz\t\t: %lu.%03lu\n",
+ cpu_khz / 1000, (cpu_khz % 1000));
+ }
+
+ /* Cache size */
+ if (c->x86_cache_size >= 0)
+ seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
+
+ /* We use exception 16 if we have hardware math and we've either seen it or the CPU claims it is internal */
+ fpu_exception = c->hard_math && (ignore_irq13 || cpu_has_fpu);
+ seq_printf(m, "fdiv_bug\t: %s\n"
+ "hlt_bug\t\t: %s\n"
+ "f00f_bug\t: %s\n"
+ "coma_bug\t: %s\n"
+ "fpu\t\t: %s\n"
+ "fpu_exception\t: %s\n"
+ "cpuid level\t: %d\n"
+ "wp\t\t: %s\n"
+ "flags\t\t:",
+ c->fdiv_bug ? "yes" : "no",
+ c->hlt_works_ok ? "no" : "yes",
+ c->f00f_bug ? "yes" : "no",
+ c->coma_bug ? "yes" : "no",
+ c->hard_math ? "yes" : "no",
+ fpu_exception ? "yes" : "no",
+ c->cpuid_level,
+ c->wp_works_ok ? "yes" : "no");
+
+ for ( i = 0 ; i < 32*NCAPINTS ; i++ )
+ if ( test_bit(i, &c->x86_capability) &&
+ x86_cap_flags[i] != NULL )
+ seq_printf(m, " %s", x86_cap_flags[i]);
+
+ seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n",
+ c->loops_per_jiffy/(500000/HZ),
+ (c->loops_per_jiffy/(5000/HZ)) % 100);
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ return *pos < NR_CPUS ? cpu_data + *pos : NULL;
+}
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return c_start(m, pos);
+}
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+struct seq_operations cpuinfo_op = {
+ start: c_start,
+ next: c_next,
+ stop: c_stop,
+ show: show_cpuinfo,
+};
+
+unsigned long cpu_initialized __initdata = 0;
+
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ */
+void __init cpu_init (void)
+{
+ int nr = smp_processor_id();
+
+ if (test_and_set_bit(nr, &cpu_initialized)) {
+ printk(KERN_WARNING "CPU#%d already initialized!\n", nr);
+ for (;;) __sti();
+ }
+ printk(KERN_INFO "Initializing CPU#%d\n", nr);
+
+ /*
+ * set up and load the per-CPU TSS and LDT
+ */
+ atomic_inc(&init_mm.mm_count);
+ current->active_mm = &init_mm;
+ if(current->mm)
+ BUG();
+ enter_lazy_tlb(&init_mm, current, nr);
+
+ HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, current->thread.esp0, 0);
+
+ /* Force FPU initialization. */
+ current->flags &= ~PF_USEDFPU;
+ current->used_math = 0;
+ stts();
+}
+
+
+/******************************************************************************
+ * Time-to-die callback handling.
+ */
+
+static void time_to_die(int irq, void *unused, struct pt_regs *regs)
+{
+ extern void ctrl_alt_del(void);
+ ctrl_alt_del();
+}
+
+static int __init setup_death_event(void)
+{
+ (void)request_irq(_EVENT_DIE, time_to_die, 0, "die", NULL);
+ return 0;
+}
+
+__initcall(setup_death_event);
--- /dev/null
+/*
+ * linux/arch/i386/kernel/signal.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/tty.h>
+#include <linux/personality.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+
+#define DEBUG_SIG 0
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+int FASTCALL(do_signal(struct pt_regs *regs, sigset_t *oldset));
+
+int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from)
+{
+ if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
+ return -EFAULT;
+ if (from->si_code < 0)
+ return __copy_to_user(to, from, sizeof(siginfo_t));
+ else {
+ int err;
+
+ /* If you change siginfo_t structure, please be sure
+ this code is fixed accordingly.
+ It should never copy any pad contained in the structure
+ to avoid security leaks, but must copy the generic
+ 3 ints plus the relevant union member. */
+ err = __put_user(from->si_signo, &to->si_signo);
+ err |= __put_user(from->si_errno, &to->si_errno);
+ err |= __put_user((short)from->si_code, &to->si_code);
+ /* First 32bits of unions are always present. */
+ err |= __put_user(from->si_pid, &to->si_pid);
+ switch (from->si_code >> 16) {
+ case __SI_FAULT >> 16:
+ break;
+ case __SI_CHLD >> 16:
+ err |= __put_user(from->si_utime, &to->si_utime);
+ err |= __put_user(from->si_stime, &to->si_stime);
+ err |= __put_user(from->si_status, &to->si_status);
+ default:
+ err |= __put_user(from->si_uid, &to->si_uid);
+ break;
+ /* case __SI_RT: This is not generated by the kernel as of now. */
+ }
+ return err;
+ }
+}
+
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+asmlinkage int
+sys_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+ struct pt_regs * regs = (struct pt_regs *) &history0;
+ sigset_t saveset;
+
+ mask &= _BLOCKABLE;
+ spin_lock_irq(¤t->sigmask_lock);
+ saveset = current->blocked;
+ siginitset(¤t->blocked, mask);
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize)
+{
+ struct pt_regs * regs = (struct pt_regs *) &unewset;
+ sigset_t saveset, newset;
+
+ /* XXX: Don't preclude handling different sized sigset_t's. */
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&newset, unewset, sizeof(newset)))
+ return -EFAULT;
+ sigdelsetmask(&newset, ~_BLOCKABLE);
+
+ spin_lock_irq(¤t->sigmask_lock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_sigaction(int sig, const struct old_sigaction *act,
+ struct old_sigaction *oact)
+{
+ struct k_sigaction new_ka, old_ka;
+ int ret;
+
+ if (act) {
+ old_sigset_t mask;
+ if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
+ __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+ __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ return -EFAULT;
+ __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ __get_user(mask, &act->sa_mask);
+ siginitset(&new_ka.sa.sa_mask, mask);
+ }
+
+ ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+ if (!ret && oact) {
+ if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
+ __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+ __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ return -EFAULT;
+ __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ }
+
+ return ret;
+}
+
+asmlinkage int
+sys_sigaltstack(const stack_t *uss, stack_t *uoss)
+{
+ struct pt_regs *regs = (struct pt_regs *) &uss;
+ return do_sigaltstack(uss, uoss, regs->esp);
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+struct sigframe
+{
+ char *pretcode;
+ int sig;
+ struct sigcontext sc;
+ struct _fpstate fpstate;
+ unsigned long extramask[_NSIG_WORDS-1];
+ char retcode[8];
+};
+
+struct rt_sigframe
+{
+ char *pretcode;
+ int sig;
+ struct siginfo *pinfo;
+ void *puc;
+ struct siginfo info;
+ struct ucontext uc;
+ struct _fpstate fpstate;
+ char retcode[8];
+};
+
+static int
+restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc, int *peax)
+{
+ unsigned int err = 0;
+
+#define COPY(x) err |= __get_user(regs->x, &sc->x)
+
+#define COPY_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp; }
+
+#define COPY_SEG_STRICT(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp|3; }
+
+#define GET_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ loadsegment(seg,tmp); }
+
+ GET_SEG(gs);
+ GET_SEG(fs);
+ COPY_SEG(es);
+ COPY_SEG(ds);
+ COPY(edi);
+ COPY(esi);
+ COPY(ebp);
+ COPY(esp);
+ COPY(ebx);
+ COPY(edx);
+ COPY(ecx);
+ COPY(eip);
+ COPY_SEG_STRICT(cs);
+ COPY_SEG_STRICT(ss);
+
+ {
+ unsigned int tmpflags;
+ err |= __get_user(tmpflags, &sc->eflags);
+ regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5);
+ regs->orig_eax = -1; /* disable syscall checks */
+ }
+
+ {
+ struct _fpstate * buf;
+ err |= __get_user(buf, &sc->fpstate);
+ if (buf) {
+ if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
+ goto badframe;
+ err |= restore_i387(buf);
+ }
+ }
+
+ err |= __get_user(*peax, &sc->eax);
+ return err;
+
+badframe:
+ return 1;
+}
+
+asmlinkage int sys_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct sigframe *frame = (struct sigframe *)(regs->esp - 8);
+ sigset_t set;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__get_user(set.sig[0], &frame->sc.oldmask)
+ || (_NSIG_WORDS > 1
+ && __copy_from_user(&set.sig[1], &frame->extramask,
+ sizeof(frame->extramask))))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (restore_sigcontext(regs, &frame->sc, &eax))
+ goto badframe;
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct rt_sigframe *frame = (struct rt_sigframe *)(regs->esp - 4);
+ sigset_t set;
+ stack_t st;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax))
+ goto badframe;
+
+ if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
+ goto badframe;
+ /* It is more difficult to avoid calling this function than to
+ call it and ignore errors. */
+ do_sigaltstack(&st, NULL, regs->esp);
+
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+/*
+ * Set up a signal frame.
+ */
+
+static int
+setup_sigcontext(struct sigcontext *sc, struct _fpstate *fpstate,
+ struct pt_regs *regs, unsigned long mask)
+{
+ int tmp, err = 0;
+
+ tmp = 0;
+ __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int *)&sc->gs);
+ __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int *)&sc->fs);
+
+ err |= __put_user(regs->xes, (unsigned int *)&sc->es);
+ err |= __put_user(regs->xds, (unsigned int *)&sc->ds);
+ err |= __put_user(regs->edi, &sc->edi);
+ err |= __put_user(regs->esi, &sc->esi);
+ err |= __put_user(regs->ebp, &sc->ebp);
+ err |= __put_user(regs->esp, &sc->esp);
+ err |= __put_user(regs->ebx, &sc->ebx);
+ err |= __put_user(regs->edx, &sc->edx);
+ err |= __put_user(regs->ecx, &sc->ecx);
+ err |= __put_user(regs->eax, &sc->eax);
+ err |= __put_user(current->thread.trap_no, &sc->trapno);
+ err |= __put_user(current->thread.error_code, &sc->err);
+ err |= __put_user(regs->eip, &sc->eip);
+ err |= __put_user(regs->xcs, (unsigned int *)&sc->cs);
+ err |= __put_user(regs->eflags, &sc->eflags);
+ err |= __put_user(regs->esp, &sc->esp_at_signal);
+ err |= __put_user(regs->xss, (unsigned int *)&sc->ss);
+
+ tmp = save_i387(fpstate);
+ if (tmp < 0)
+ err = 1;
+ else
+ err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
+
+ /* non-iBCS2 extensions.. */
+ err |= __put_user(mask, &sc->oldmask);
+ err |= __put_user(current->thread.cr2, &sc->cr2);
+
+ return err;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
+{
+ unsigned long esp;
+
+ /* Default to using normal stack */
+ esp = regs->esp;
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ if (ka->sa.sa_flags & SA_ONSTACK) {
+ if (sas_ss_flags(esp) == 0)
+ esp = current->sas_ss_sp + current->sas_ss_size;
+ }
+
+ /* This is the legacy signal stack switching. */
+ else if ((regs->xss & 0xffff) != __USER_DS &&
+ !(ka->sa.sa_flags & SA_RESTORER) &&
+ ka->sa.sa_restorer) {
+ esp = (unsigned long) ka->sa.sa_restorer;
+ }
+
+ return (void *)((esp - frame_size) & -8ul);
+}
+
+static void setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct sigframe *frame;
+ int err = 0;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ err |= __put_user((current->exec_domain
+ && current->exec_domain->signal_invmap
+ && sig < 32
+ ? current->exec_domain->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ if (err)
+ goto give_sigsegv;
+
+ err |= setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+ if (err)
+ goto give_sigsegv;
+
+ if (_NSIG_WORDS > 1) {
+ err |= __copy_to_user(frame->extramask, &set->sig[1],
+ sizeof(frame->extramask));
+ }
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ err |= __put_user(frame->retcode, &frame->pretcode);
+ /* This is popl %eax ; movl $,%eax ; int $0x80 */
+ err |= __put_user(0xb858, (short *)(frame->retcode+0));
+ err |= __put_user(__NR_sigreturn, (int *)(frame->retcode+2));
+ err |= __put_user(0x80cd, (short *)(frame->retcode+6));
+ }
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+ regs->eflags &= ~TF_MASK;
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ if (sig == SIGSEGV)
+ ka->sa.sa_handler = SIG_DFL;
+ force_sig(SIGSEGV, current);
+}
+
+static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct rt_sigframe *frame;
+ int err = 0;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ err |= __put_user((current->exec_domain
+ && current->exec_domain->signal_invmap
+ && sig < 32
+ ? current->exec_domain->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ err |= __put_user(&frame->info, &frame->pinfo);
+ err |= __put_user(&frame->uc, &frame->puc);
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err)
+ goto give_sigsegv;
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(regs->esp),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ err |= __put_user(frame->retcode, &frame->pretcode);
+ /* This is movl $,%eax ; int $0x80 */
+ err |= __put_user(0xb8, (char *)(frame->retcode+0));
+ err |= __put_user(__NR_rt_sigreturn, (int *)(frame->retcode+1));
+ err |= __put_user(0x80cd, (short *)(frame->retcode+5));
+ }
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+ regs->eflags &= ~TF_MASK;
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ if (sig == SIGSEGV)
+ ka->sa.sa_handler = SIG_DFL;
+ force_sig(SIGSEGV, current);
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+
+static void
+handle_signal(unsigned long sig, struct k_sigaction *ka,
+ siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
+{
+ /* Are we from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* If so, check system call restarting.. */
+ switch (regs->eax) {
+ case -ERESTARTNOHAND:
+ regs->eax = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ka->sa.sa_flags & SA_RESTART)) {
+ regs->eax = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+
+ /* Set up the stack frame */
+ if (ka->sa.sa_flags & SA_SIGINFO)
+ setup_rt_frame(sig, ka, info, oldset, regs);
+ else
+ setup_frame(sig, ka, oldset, regs);
+
+ if (ka->sa.sa_flags & SA_ONESHOT)
+ ka->sa.sa_handler = SIG_DFL;
+
+ if (!(ka->sa.sa_flags & SA_NODEFER)) {
+ spin_lock_irq(¤t->sigmask_lock);
+ sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
+ sigaddset(¤t->blocked,sig);
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+ }
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int do_signal(struct pt_regs *regs, sigset_t *oldset)
+{
+ siginfo_t info;
+ struct k_sigaction *ka;
+
+ /*
+ * We want the common case to go fast, which
+ * is why we may in certain cases get here from
+ * kernel mode. Just return without doing anything
+ * if so.
+ */
+ if ((regs->xcs & 2) != 2)
+ return 1;
+
+ if (!oldset)
+ oldset = ¤t->blocked;
+
+ for (;;) {
+ unsigned long signr;
+
+ spin_lock_irq(¤t->sigmask_lock);
+ signr = dequeue_signal(¤t->blocked, &info);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (!signr)
+ break;
+
+ if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
+ /* Let the debugger run. */
+ current->exit_code = signr;
+ current->state = TASK_STOPPED;
+ notify_parent(current, SIGCHLD);
+ schedule();
+
+ /* We're back. Did the debugger cancel the sig? */
+ if (!(signr = current->exit_code))
+ continue;
+ current->exit_code = 0;
+
+ /* The debugger continued. Ignore SIGSTOP. */
+ if (signr == SIGSTOP)
+ continue;
+
+ /* Update the siginfo structure. Is this good? */
+ if (signr != info.si_signo) {
+ info.si_signo = signr;
+ info.si_errno = 0;
+ info.si_code = SI_USER;
+ info.si_pid = current->p_pptr->pid;
+ info.si_uid = current->p_pptr->uid;
+ }
+
+ /* If the (new) signal is now blocked, requeue it. */
+ if (sigismember(¤t->blocked, signr)) {
+ send_sig_info(signr, &info, current);
+ continue;
+ }
+ }
+
+ ka = ¤t->sig->action[signr-1];
+ if (ka->sa.sa_handler == SIG_IGN) {
+ if (signr != SIGCHLD)
+ continue;
+ /* Check for SIGCHLD: it's special. */
+ while (sys_wait4(-1, NULL, WNOHANG, NULL) > 0)
+ /* nothing */;
+ continue;
+ }
+
+ if (ka->sa.sa_handler == SIG_DFL) {
+ int exit_code = signr;
+
+ /* Init gets no signals it doesn't want. */
+ if (current->pid == 1)
+ continue;
+
+ switch (signr) {
+ case SIGCONT: case SIGCHLD: case SIGWINCH:
+ continue;
+
+ case SIGTSTP: case SIGTTIN: case SIGTTOU:
+ if (is_orphaned_pgrp(current->pgrp))
+ continue;
+ /* FALLTHRU */
+
+ case SIGSTOP: {
+ struct signal_struct *sig;
+ current->state = TASK_STOPPED;
+ current->exit_code = signr;
+ sig = current->p_pptr->sig;
+ if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
+ notify_parent(current, SIGCHLD);
+ schedule();
+ continue;
+ }
+
+ case SIGQUIT: case SIGILL: case SIGTRAP:
+ case SIGABRT: case SIGFPE: case SIGSEGV:
+ case SIGBUS: case SIGSYS: case SIGXCPU: case SIGXFSZ:
+ if (do_coredump(signr, regs))
+ exit_code |= 0x80;
+ /* FALLTHRU */
+
+ default:
+ sigaddset(¤t->pending.signal, signr);
+ recalc_sigpending(current);
+ current->flags |= PF_SIGNALED;
+ do_exit(exit_code);
+ /* NOTREACHED */
+ }
+ }
+
+ /* Reenable any watchpoints before delivering the
+ * signal to user space. The processor register will
+ * have been cleared if the watchpoint triggered
+ * inside the kernel.
+ */
+ if ( current->thread.debugreg[7] != 0 )
+ HYPERVISOR_set_debugreg(7, current->thread.debugreg[7]);
+
+ /* Whee! Actually deliver the signal. */
+ handle_signal(signr, ka, &info, oldset, regs);
+ return 1;
+ }
+
+ /* Did we come from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* Restart the system call - no handlers present */
+ if (regs->eax == -ERESTARTNOHAND ||
+ regs->eax == -ERESTARTSYS ||
+ regs->eax == -ERESTARTNOINTR) {
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+ return 0;
+}
--- /dev/null
+/*
+ * linux/arch/i386/kernel/sys_i386.c
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/i386
+ * platform.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+
+#include <asm/uaccess.h>
+#include <asm/ipc.h>
+
+/*
+ * sys_pipe() is the normal C calling standard for creating
+ * a pipe. It's not the way Unix traditionally does this, though.
+ */
+asmlinkage int sys_pipe(unsigned long * fildes)
+{
+ int fd[2];
+ int error;
+
+ error = do_pipe(fd);
+ if (!error) {
+ if (copy_to_user(fildes, fd, 2*sizeof(int)))
+ error = -EFAULT;
+ }
+ return error;
+}
+
+/* common code for old and new mmaps */
+static inline long do_mmap2(
+ unsigned long addr, unsigned long len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ int error = -EBADF;
+ struct file * file = NULL;
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+ if (!(flags & MAP_ANONYMOUS)) {
+ file = fget(fd);
+ if (!file)
+ goto out;
+ }
+
+ down_write(¤t->mm->mmap_sem);
+ error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(¤t->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+out:
+ return error;
+}
+
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ return do_mmap2(addr, len, prot, flags, fd, pgoff);
+}
+
+/*
+ * Perform the select(nd, in, out, ex, tv) and mmap() system
+ * calls. Linux/i386 didn't use to be able to handle more than
+ * 4 system call parameters, so these system calls used a memory
+ * block for parameter passing..
+ */
+
+struct mmap_arg_struct {
+ unsigned long addr;
+ unsigned long len;
+ unsigned long prot;
+ unsigned long flags;
+ unsigned long fd;
+ unsigned long offset;
+};
+
+asmlinkage int old_mmap(struct mmap_arg_struct *arg)
+{
+ struct mmap_arg_struct a;
+ int err = -EFAULT;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ goto out;
+
+ err = -EINVAL;
+ if (a.offset & ~PAGE_MASK)
+ goto out;
+
+ err = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT);
+out:
+ return err;
+}
+
+
+extern asmlinkage int sys_select(int, fd_set *, fd_set *, fd_set *, struct timeval *);
+
+struct sel_arg_struct {
+ unsigned long n;
+ fd_set *inp, *outp, *exp;
+ struct timeval *tvp;
+};
+
+asmlinkage int old_select(struct sel_arg_struct *arg)
+{
+ struct sel_arg_struct a;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ return -EFAULT;
+ /* sys_select() does the appropriate kernel locking */
+ return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
+}
+
+/*
+ * sys_ipc() is the de-multiplexer for the SysV IPC calls..
+ *
+ * This is really horribly ugly.
+ */
+asmlinkage int sys_ipc (uint call, int first, int second,
+ int third, void *ptr, long fifth)
+{
+ int version, ret;
+
+ version = call >> 16; /* hack for backward compatibility */
+ call &= 0xffff;
+
+ switch (call) {
+ case SEMOP:
+ return sys_semop (first, (struct sembuf *)ptr, second);
+ case SEMGET:
+ return sys_semget (first, second, third);
+ case SEMCTL: {
+ union semun fourth;
+ if (!ptr)
+ return -EINVAL;
+ if (get_user(fourth.__pad, (void **) ptr))
+ return -EFAULT;
+ return sys_semctl (first, second, third, fourth);
+ }
+
+ case MSGSND:
+ return sys_msgsnd (first, (struct msgbuf *) ptr,
+ second, third);
+ case MSGRCV:
+ switch (version) {
+ case 0: {
+ struct ipc_kludge tmp;
+ if (!ptr)
+ return -EINVAL;
+
+ if (copy_from_user(&tmp,
+ (struct ipc_kludge *) ptr,
+ sizeof (tmp)))
+ return -EFAULT;
+ return sys_msgrcv (first, tmp.msgp, second,
+ tmp.msgtyp, third);
+ }
+ default:
+ return sys_msgrcv (first,
+ (struct msgbuf *) ptr,
+ second, fifth, third);
+ }
+ case MSGGET:
+ return sys_msgget ((key_t) first, second);
+ case MSGCTL:
+ return sys_msgctl (first, second, (struct msqid_ds *) ptr);
+
+ case SHMAT:
+ switch (version) {
+ default: {
+ ulong raddr;
+ ret = sys_shmat (first, (char *) ptr, second, &raddr);
+ if (ret)
+ return ret;
+ return put_user (raddr, (ulong *) third);
+ }
+ case 1: /* iBCS2 emulator entry point */
+ if (!segment_eq(get_fs(), get_ds()))
+ return -EINVAL;
+ return sys_shmat (first, (char *) ptr, second, (ulong *) third);
+ }
+ case SHMDT:
+ return sys_shmdt ((char *)ptr);
+ case SHMGET:
+ return sys_shmget (first, second, third);
+ case SHMCTL:
+ return sys_shmctl (first, second,
+ (struct shmid_ds *) ptr);
+ default:
+ return -EINVAL;
+ }
+}
+
+/*
+ * Old cruft
+ */
+asmlinkage int sys_uname(struct old_utsname * name)
+{
+ int err;
+ if (!name)
+ return -EFAULT;
+ down_read(&uts_sem);
+ err=copy_to_user(name, &system_utsname, sizeof (*name));
+ up_read(&uts_sem);
+ return err?-EFAULT:0;
+}
+
+asmlinkage int sys_olduname(struct oldold_utsname * name)
+{
+ int error;
+
+ if (!name)
+ return -EFAULT;
+ if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
+ return -EFAULT;
+
+ down_read(&uts_sem);
+
+ error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN);
+ error |= __put_user(0,name->sysname+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN);
+ error |= __put_user(0,name->nodename+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN);
+ error |= __put_user(0,name->release+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN);
+ error |= __put_user(0,name->version+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN);
+ error |= __put_user(0,name->machine+__OLD_UTS_LEN);
+
+ up_read(&uts_sem);
+
+ error = error ? -EFAULT : 0;
+
+ return error;
+}
+
+asmlinkage int sys_pause(void)
+{
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ return -ERESTARTNOHAND;
+}
+
--- /dev/null
+/* -*- Mode:C; c-basic-offset:4; tab-width:4 -*-
+ ****************************************************************************
+ * (C) 2002 - Rolf Neugebauer - Intel Research Cambridge
+ ****************************************************************************
+ *
+ * File: arch.xeno/time.c
+ * Author: Rolf Neugebauer
+ * Changes:
+ *
+ * Date: Nov 2002
+ *
+ * Environment: XenoLinux
+ * Description: Interface with Hypervisor to get correct notion of time
+ * Currently supports Systemtime and WallClock time.
+ *
+ * (This has hardly any resemblence with the Linux code but left the
+ * copyright notice anyway. Ignore the comments in the copyright notice.)
+ ****************************************************************************
+ * $Id: c-insert.c,v 1.7 2002/11/08 16:04:34 rn Exp $
+ ****************************************************************************
+ */
+
+/*
+ * linux/arch/i386/kernel/time.c
+ *
+ * Copyright (C) 1991, 1992, 1995 Linus Torvalds
+ *
+ * This file contains the PC-specific time handling details:
+ * reading the RTC at bootup, etc..
+ * 1994-07-02 Alan Modra
+ * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
+ * 1995-03-26 Markus Kuhn
+ * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
+ * precision CMOS clock update
+ * 1996-05-03 Ingo Molnar
+ * fixed time warps in do_[slow|fast]_gettimeoffset()
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * 1998-09-05 (Various)
+ * More robust do_fast_gettimeoffset() algorithm implemented
+ * (works with APM, Cyrix 6x86MX and Centaur C6),
+ * monotonic gettimeofday() with fast_get_timeoffset(),
+ * drift-proof precision TSC calibration on boot
+ * (C. Scott Ananian <cananian@alumni.princeton.edu>, Andrew D.
+ * Balsa <andrebalsa@altern.org>, Philip Gladstone <philip@raptor.com>;
+ * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@tu-harburg.de>).
+ * 1998-12-16 Andrea Arcangeli
+ * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
+ * because was not accounting lost_ticks.
+ * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli
+ * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ * serialize accesses to xtime/lost_ticks).
+ */
+
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/msr.h>
+#include <asm/delay.h>
+#include <asm/mpspec.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+
+#include <asm/div64.h>
+#include <asm/hypervisor.h>
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+
+#undef XENO_TIME_DEBUG /* adds sanity checks and periodic printouts */
+
+spinlock_t rtc_lock = SPIN_LOCK_UNLOCKED;
+extern rwlock_t xtime_lock;
+
+unsigned long cpu_khz; /* get this from Xen, used elsewhere */
+static spinlock_t hyp_stime_lock = SPIN_LOCK_UNLOCKED;
+static spinlock_t hyp_wctime_lock = SPIN_LOCK_UNLOCKED;
+
+static u32 st_scale_f;
+static u32 st_scale_i;
+static u32 shadow_st_pcc;
+static s64 shadow_st;
+
+/*
+ * System time.
+ * Although the rest of the Linux kernel doesn't know about this, we
+ * we use it to extrapolate passage of wallclock time.
+ * We need to read the values from the shared info page "atomically"
+ * and use the cycle counter value as the "version" number. Clashes
+ * should be very rare.
+ */
+static inline long long get_s_time(void)
+{
+ unsigned long flags;
+ u32 delta_tsc, low, pcc;
+ u64 delta;
+ s64 now;
+
+ spin_lock_irqsave(&hyp_stime_lock, flags);
+
+ while ((pcc = HYPERVISOR_shared_info->st_timestamp) != shadow_st_pcc)
+ {
+ barrier();
+ shadow_st_pcc = pcc;
+ shadow_st = HYPERVISOR_shared_info->system_time;
+ barrier();
+ }
+
+ now = shadow_st;
+ /* only use bottom 32bits of TSC. This should be sufficient */
+ rdtscl(low);
+ delta_tsc = low - pcc;
+ delta = ((u64)delta_tsc * st_scale_f);
+ delta >>= 32;
+ delta += ((u64)delta_tsc * st_scale_i);
+
+ spin_unlock_irqrestore(&hyp_time_lock, flags);
+
+ return now + delta;
+
+}
+#define NOW() ((long long)get_s_time())
+
+/*
+ * Wallclock time.
+ * Based on what the hypervisor tells us, extrapolated using system time.
+ * Again need to read a number of values from the shared page "atomically".
+ * this time using a version number.
+ */
+static u32 shadow_wc_version=0;
+static long shadow_tv_sec;
+static long shadow_tv_usec;
+static long long shadow_wc_timestamp;
+void do_gettimeofday(struct timeval *tv)
+{
+ unsigned long flags;
+ long usec, sec;
+ u32 version;
+ u64 now;
+
+ spin_lock_irqsave(&hyp_wctime_lock, flags);
+
+ while ((version = HYPERVISOR_shared_info->wc_version)!= shadow_wc_version)
+ {
+ barrier();
+ shadow_wc_version = version;
+ shadow_tv_sec = HYPERVISOR_shared_info->tv_sec;
+ shadow_tv_usec = HYPERVISOR_shared_info->tv_usec;
+ shadow_wc_timestamp = HYPERVISOR_shared_info->wc_timestamp;
+ barrier();
+ }
+
+ now = NOW();
+ usec = ((unsigned long)(now-shadow_wc_timestamp))/1000;
+ sec = shadow_tv_sec;
+ usec += shadow_tv_usec;
+
+ while ( usec >= 1000000 )
+ {
+ usec -= 1000000;
+ sec++;
+ }
+
+ tv->tv_sec = sec;
+ tv->tv_usec = usec;
+
+ spin_unlock_irqrestore(&hyp_time_lock, flags);
+
+#ifdef XENO_TIME_DEBUG
+ {
+ static long long old_now=0;
+ static long long wct=0, old_wct=0;
+
+ /* This debug code checks if time increase over two subsequent calls */
+ wct=(((long long)sec) * 1000000) + usec;
+ /* wall clock time going backwards */
+ if ((wct < old_wct) ) {
+ printk("Urgh1: wc diff=%6ld, usec = %ld (0x%lX)\n",
+ (long)(wct-old_wct), usec, usec);
+ printk(" st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
+ now-old_now, now, old_now);
+ }
+
+ /* system time going backwards */
+ if (now<=old_now) {
+ printk("Urgh2: st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
+ now-old_now, now, old_now);
+ }
+ old_wct = wct;
+ old_now = now;
+ }
+#endif
+
+}
+
+void do_settimeofday(struct timeval *tv)
+{
+/* XXX RN: should do something special here for dom0 */
+#if 0
+ write_lock_irq(&xtime_lock);
+ /*
+ * This is revolting. We need to set "xtime" correctly. However, the
+ * value in this location is the value at the most recent update of
+ * wall time. Discover what correction gettimeofday() would have
+ * made, and then undo it!
+ */
+ tv->tv_usec -= do_gettimeoffset();
+ tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ);
+
+ while ( tv->tv_usec < 0 )
+ {
+ tv->tv_usec += 1000000;
+ tv->tv_sec--;
+ }
+
+ xtime = *tv;
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+ write_unlock_irq(&xtime_lock);
+#endif
+}
+
+
+/*
+ * Timer ISR.
+ * Unlike normal Linux these don't come in at a fixed rate of HZ.
+ * In here we wrok out how often it should have been called and then call
+ * the architecture independent part (do_timer()) the appropriate number of
+ * times. A bit of a nasty hack, to keep the "other" notion of wallclock time
+ * happy.
+ */
+static long long us_per_tick=1000000/HZ;
+static long long last_irq;
+static inline void do_timer_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ struct timeval tv;
+ long long time, delta;
+
+#ifdef XENO_TIME_DEBUG
+ static u32 foo_count = 0;
+ foo_count++;
+ if (foo_count>= 1000) {
+ s64 n = NOW();
+ struct timeval tv;
+ do_gettimeofday(&tv);
+ printk("0x%08X%08X %ld:%ld\n",
+ (u32)(n>>32), (u32)n, tv.tv_sec, tv.tv_usec);
+ foo_count = 0;
+ }
+#endif
+ /*
+ * The next bit really sucks:
+ * Linux not only uses do_gettimeofday() to keep a notion of
+ * wallclock time, but also maintains the xtime struct and jiffies.
+ * (Even worse some userland code accesses this via the sys_time()
+ * system call)
+ * Unfortunately, xtime is maintain in the architecture independent
+ * part of the timer ISR (./kernel/timer.c sic!). So, although we have
+ * perfectly valid notion of wallclock time from the hypervisor we here
+ * fake missed timer interrupts so that the arch independent part of
+ * the Timer ISR updates jiffies for us *and* once the bh gets run
+ * updates xtime accordingly. Yuck!
+ */
+
+ /* work out the number of jiffies past and update them */
+ do_gettimeofday(&tv);
+ time = (((long long)tv.tv_sec) * 1000000) + tv.tv_usec;
+ delta = time - last_irq;
+ if (delta <= 0) {
+ printk ("Timer ISR: Time went backwards: %lld\n", delta);
+ return;
+ }
+ while (delta >= us_per_tick) {
+ do_timer(regs);
+ delta -= us_per_tick;
+ last_irq += us_per_tick;
+ }
+
+#if 0
+ if (!user_mode(regs))
+ x86_do_profile(regs->eip);
+#endif
+}
+
+static void timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+ write_lock(&xtime_lock);
+ do_timer_interrupt(irq, NULL, regs);
+ write_unlock(&xtime_lock);
+}
+
+static struct irqaction irq_timer = {
+ timer_interrupt,
+ SA_INTERRUPT,
+ 0,
+ "timer",
+ NULL,
+ NULL
+};
+
+void __init time_init(void)
+{
+ unsigned long long alarm;
+ u64 cpu_freq = HYPERVISOR_shared_info->cpu_freq;
+ u64 scale;
+
+ do_get_fast_time = do_gettimeofday;
+
+ cpu_khz = (u32)cpu_freq/1000;
+ printk("Xen reported: %lu.%03lu MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
+
+ /*
+ * calculate systemtime scaling factor
+ * XXX RN: have to cast cpu_freq to u32 limits it to 4.29 GHz.
+ * Get a better do_div!
+ */
+ scale = 1000000000LL << 32;
+ do_div(scale,(u32)cpu_freq);
+ st_scale_f = scale & 0xffffffff;
+ st_scale_i = scale >> 32;
+ printk("System Time scale: %X %X\n",st_scale_i, st_scale_f);
+
+ do_gettimeofday(&xtime);
+ last_irq = (((long long)xtime.tv_sec) * 1000000) + xtime.tv_usec;
+
+ setup_irq(TIMER_IRQ, &irq_timer);
+
+ /*
+ * Start ticker. Note that timing runs of wall clock, not virtual
+ * 'domain' time. This means that clock sshould run at the correct
+ * rate. For things like scheduling, it's not clear whether it
+ * matters which sort of time we use.
+ * XXX RN: unimplemented.
+ */
+
+ rdtscll(alarm);
+#if 0
+ alarm += (1000/HZ)*HYPERVISOR_shared_info->ticks_per_ms;
+ HYPERVISOR_shared_info->wall_timeout = alarm;
+ HYPERVISOR_shared_info->domain_timeout = ~0ULL;
+#endif
+ clear_bit(_EVENT_TIMER, &HYPERVISOR_shared_info->events);
+}
--- /dev/null
+/*
+ * linux/arch/i386/traps.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * 'Traps.c' handles hardware traps and faults after we have saved some
+ * state in 'asm.s'.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/highmem.h>
+
+#include <linux/kdb.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+#include <asm/smp.h>
+#include <asm/pgalloc.h>
+
+#include <asm/hypervisor.h>
+
+#include <linux/irq.h>
+#include <linux/module.h>
+
+asmlinkage int system_call(void);
+
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void double_fault(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void alignment_check(void);
+asmlinkage void spurious_interrupt_bug(void);
+asmlinkage void machine_check(void);
+
+int kstack_depth_to_print = 24;
+
+
+/*
+ * If the address is either in the .text section of the
+ * kernel, or in the vmalloc'ed module regions, it *may*
+ * be the address of a calling routine
+ */
+
+#ifdef CONFIG_MODULES
+
+extern struct module *module_list;
+extern struct module kernel_module;
+
+static inline int kernel_text_address(unsigned long addr)
+{
+ int retval = 0;
+ struct module *mod;
+
+ if (addr >= (unsigned long) &_stext &&
+ addr <= (unsigned long) &_etext)
+ return 1;
+
+ for (mod = module_list; mod != &kernel_module; mod = mod->next) {
+ /* mod_bound tests for addr being inside the vmalloc'ed
+ * module area. Of course it'd be better to test only
+ * for the .text subset... */
+ if (mod_bound(addr, 0, mod)) {
+ retval = 1;
+ break;
+ }
+ }
+
+ return retval;
+}
+
+#else
+
+static inline int kernel_text_address(unsigned long addr)
+{
+ return (addr >= (unsigned long) &_stext &&
+ addr <= (unsigned long) &_etext);
+}
+
+#endif
+
+void show_trace(unsigned long * stack)
+{
+ int i;
+ unsigned long addr;
+
+ if (!stack)
+ stack = (unsigned long*)&stack;
+
+ printk("Call Trace: ");
+ i = 1;
+ while (((long) stack & (THREAD_SIZE-1)) != 0) {
+ addr = *stack++;
+ if (kernel_text_address(addr)) {
+ if (i && ((i % 6) == 0))
+ printk("\n ");
+ printk("[<%08lx>] ", addr);
+ i++;
+ }
+ }
+ printk("\n");
+}
+
+void show_trace_task(struct task_struct *tsk)
+{
+ unsigned long esp = tsk->thread.esp;
+
+ /* User space on another CPU? */
+ if ((esp ^ (unsigned long)tsk) & (PAGE_MASK<<1))
+ return;
+ show_trace((unsigned long *)esp);
+}
+
+void show_stack(unsigned long * esp)
+{
+ unsigned long *stack;
+ int i;
+
+ // debugging aid: "show_stack(NULL);" prints the
+ // back trace for this cpu.
+
+ if(esp==NULL)
+ esp=(unsigned long*)&esp;
+
+ stack = esp;
+ for(i=0; i < kstack_depth_to_print; i++) {
+ if (((long) stack & (THREAD_SIZE-1)) == 0)
+ break;
+ if (i && ((i % 8) == 0))
+ printk("\n ");
+ printk("%08lx ", *stack++);
+ }
+ printk("\n");
+ show_trace(esp);
+}
+
+void show_registers(struct pt_regs *regs)
+{
+ int i;
+ int in_kernel = 1;
+ unsigned long esp;
+ unsigned short ss;
+
+ esp = (unsigned long) (®s->esp);
+ ss = __KERNEL_DS;
+ if (regs->xcs & 2) {
+ in_kernel = 0;
+ esp = regs->esp;
+ ss = regs->xss & 0xffff;
+ }
+ printk("CPU: %d\nEIP: %04x:[<%08lx>] %s\nEFLAGS: %08lx\n",
+ smp_processor_id(), 0xffff & regs->xcs, regs->eip, print_tainted(), regs->eflags);
+ printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n",
+ regs->eax, regs->ebx, regs->ecx, regs->edx);
+ printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n",
+ regs->esi, regs->edi, regs->ebp, esp);
+ printk("ds: %04x es: %04x ss: %04x\n",
+ regs->xds & 0xffff, regs->xes & 0xffff, ss);
+ printk("Process %s (pid: %d, stackpage=%08lx)",
+ current->comm, current->pid, 4096+(unsigned long)current);
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (in_kernel) {
+
+ printk("\nStack: ");
+ show_stack((unsigned long*)esp);
+
+#if 0
+ printk("\nCode: ");
+ if(regs->eip < PAGE_OFFSET)
+ goto bad;
+
+ for(i=0;i<20;i++)
+ {
+ unsigned char c;
+ if(__get_user(c, &((unsigned char*)regs->eip)[i])) {
+bad:
+ printk(" Bad EIP value.");
+ break;
+ }
+ printk("%02x ", c);
+ }
+#endif
+ }
+ printk("\n");
+}
+
+spinlock_t die_lock = SPIN_LOCK_UNLOCKED;
+
+void die(const char * str, struct pt_regs * regs, long err)
+{
+ console_verbose();
+ spin_lock_irq(&die_lock);
+ bust_spinlocks(1);
+ printk("%s: %04lx\n", str, err & 0xffff);
+ show_registers(regs);
+ bust_spinlocks(0);
+ spin_unlock_irq(&die_lock);
+ do_exit(SIGSEGV);
+}
+
+static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
+{
+ if (!(2 & regs->xcs))
+ die(str, regs, err);
+}
+
+
+static void inline do_trap(int trapnr, int signr, char *str,
+ struct pt_regs * regs, long error_code,
+ siginfo_t *info)
+{
+ if (!(regs->xcs & 2))
+ goto kernel_trap;
+
+ /*trap_signal:*/ {
+ struct task_struct *tsk = current;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
+ if (info)
+ force_sig_info(signr, info, tsk);
+ else
+ force_sig(signr, tsk);
+ return;
+ }
+
+ kernel_trap: {
+ unsigned long fixup = search_exception_table(regs->eip);
+ if (fixup)
+ regs->eip = fixup;
+ else
+ die(str, regs, error_code);
+ return;
+ }
+}
+
+#define DO_ERROR(trapnr, signr, str, name) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ do_trap(trapnr, signr, str, regs, error_code, NULL); \
+}
+
+#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ siginfo_t info; \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void *)siaddr; \
+ do_trap(trapnr, signr, str, regs, error_code, &info); \
+}
+
+DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip)
+DO_ERROR( 3, SIGTRAP, "int3", int3)
+DO_ERROR( 4, SIGSEGV, "overflow", overflow)
+DO_ERROR( 5, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip)
+DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
+DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
+DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
+DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR(18, SIGBUS, "machine check", machine_check)
+
+asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
+{
+ if (!(regs->xcs & 2))
+ goto gp_in_kernel;
+
+ current->thread.error_code = error_code;
+ current->thread.trap_no = 13;
+ force_sig(SIGSEGV, current);
+ return;
+
+gp_in_kernel:
+ {
+ unsigned long fixup;
+ fixup = search_exception_table(regs->eip);
+ if (fixup) {
+ regs->eip = fixup;
+ return;
+ }
+ die("general protection fault", regs, error_code);
+ }
+}
+
+
+asmlinkage void do_debug(struct pt_regs * regs, long error_code)
+{
+ unsigned int condition;
+ struct task_struct *tsk = current;
+ siginfo_t info;
+
+ condition = HYPERVISOR_get_debugreg(6);
+
+ /* Mask out spurious debug traps due to lazy DR7 setting */
+ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
+ if (!tsk->thread.debugreg[7])
+ goto clear_dr7;
+ }
+
+ /* Save debug status register where ptrace can see it */
+ tsk->thread.debugreg[6] = condition;
+
+ /* Mask out spurious TF errors due to lazy TF clearing */
+ if (condition & DR_STEP) {
+ /*
+ * The TF error should be masked out only if the current
+ * process is not traced and if the TRAP flag has been set
+ * previously by a tracing process (condition detected by
+ * the PT_DTRACE flag); remember that the i386 TRAP flag
+ * can be modified by the process itself in user mode,
+ * allowing programs to debug themselves without the ptrace()
+ * interface.
+ */
+ if ((tsk->ptrace & (PT_DTRACE|PT_PTRACED)) == PT_DTRACE)
+ goto clear_TF;
+ }
+
+ /* Ok, finally something we can handle */
+ tsk->thread.trap_no = 1;
+ tsk->thread.error_code = error_code;
+ info.si_signo = SIGTRAP;
+ info.si_errno = 0;
+ info.si_code = TRAP_BRKPT;
+
+ /* If this is a kernel mode trap, save the user PC on entry to
+ * the kernel, that's what the debugger can make sense of.
+ */
+ info.si_addr = ((regs->xcs & 3) == 0) ? (void *)tsk->thread.eip :
+ (void *)regs->eip;
+ force_sig_info(SIGTRAP, &info, tsk);
+
+ /* Disable additional traps. They'll be re-enabled when
+ * the signal is delivered.
+ */
+ clear_dr7:
+ HYPERVISOR_set_debugreg(7, 0);
+ return;
+
+ clear_TF:
+ regs->eflags &= ~TF_MASK;
+ return;
+}
+
+
+/*
+ * Note that we play around with the 'TS' bit in an attempt to get
+ * the correct behaviour even in the presence of the asynchronous
+ * IRQ13 behaviour
+ */
+void math_error(void *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short cwd, swd;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 16;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't syncronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(task);
+ swd = get_fpu_swd(task);
+ switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ case 0x040: /* Stack Fault */
+ case 0x240: /* Stack Fault | Direction */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_coprocessor_error(struct pt_regs * regs, long error_code)
+{
+ ignore_irq13 = 1;
+ math_error((void *)regs->eip);
+}
+
+void simd_math_error(void *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short mxcsr;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 19;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ mxcsr = get_fpu_mxcsr(task);
+ switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_simd_coprocessor_error(struct pt_regs * regs,
+ long error_code)
+{
+ if (cpu_has_xmm) {
+ /* Handle SIMD FPU exceptions on PIII+ processors. */
+ ignore_irq13 = 1;
+ simd_math_error((void *)regs->eip);
+ } else {
+ die_if_kernel("cache flush denied", regs, error_code);
+ current->thread.trap_no = 19;
+ current->thread.error_code = error_code;
+ force_sig(SIGSEGV, current);
+ }
+}
+
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs,
+ long error_code)
+{
+}
+
+/*
+ * 'math_state_restore()' saves the current math information in the
+ * old math state array, and gets the new ones from the current task
+ *
+ * Careful.. There are problems with IBM-designed IRQ13 behaviour.
+ * Don't touch unless you *really* know how it works.
+ */
+asmlinkage void math_state_restore(struct pt_regs regs)
+{
+ if (current->used_math) {
+ restore_fpu(current);
+ } else {
+ init_fpu();
+ }
+ current->flags |= PF_USEDFPU; /* So we fnsave on switch_to() */
+}
+
+static trap_info_t trap_table[] = {
+ { 0, 0, __KERNEL_CS, (unsigned long)divide_error },
+ { 1, 0, __KERNEL_CS, (unsigned long)debug },
+ { 3, 3, __KERNEL_CS, (unsigned long)int3 },
+ { 4, 3, __KERNEL_CS, (unsigned long)overflow },
+ { 5, 3, __KERNEL_CS, (unsigned long)bounds },
+ { 6, 0, __KERNEL_CS, (unsigned long)invalid_op },
+ { 7, 0, __KERNEL_CS, (unsigned long)device_not_available },
+ { 8, 0, __KERNEL_CS, (unsigned long)double_fault },
+ { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun },
+ { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS },
+ { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present },
+ { 12, 0, __KERNEL_CS, (unsigned long)stack_segment },
+ { 13, 0, __KERNEL_CS, (unsigned long)general_protection },
+ { 14, 0, __KERNEL_CS, (unsigned long)page_fault },
+ { 15, 0, __KERNEL_CS, (unsigned long)spurious_interrupt_bug },
+ { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error },
+ { 17, 0, __KERNEL_CS, (unsigned long)alignment_check },
+ { 18, 0, __KERNEL_CS, (unsigned long)machine_check },
+ { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error },
+ { SYSCALL_VECTOR,
+ 3, __KERNEL_CS, (unsigned long)system_call },
+ { 0, 0, 0, 0 }
+};
+
+
+
+void __init trap_init(void)
+{
+ HYPERVISOR_set_trap_table(trap_table);
+ HYPERVISOR_set_fast_trap(SYSCALL_VECTOR);
+ cpu_init();
+}
--- /dev/null
+
+.S.o:
+ $(CC) $(AFLAGS) -c $< -o $*.o
+
+L_TARGET = lib.a
+
+obj-y = checksum.o old-checksum.o delay.o \
+ usercopy.o getuser.o \
+ memcpy.o strstr.o
+
+obj-$(CONFIG_X86_USE_3DNOW) += mmx.o
+obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
+obj-$(CONFIG_DEBUG_IOVIRT) += iodebug.o
+
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * IP/TCP/UDP checksumming routines
+ *
+ * Authors: Jorge Cwik, <jorge@laser.satlink.net>
+ * Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ * Tom May, <ftom@netcom.com>
+ * Pentium Pro/II routines:
+ * Alexander Kjeldaas <astor@guardian.no>
+ * Finn Arne Gangstad <finnag@guardian.no>
+ * Lots of code moved from tcp.c and ip.c; see those files
+ * for more names.
+ *
+ * Changes: Ingo Molnar, converted csum_partial_copy() to 2.1 exception
+ * handling.
+ * Andi Kleen, add zeroing on error
+ * converted to pure assembler
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <asm/errno.h>
+
+/*
+ * computes a partial checksum, e.g. for TCP/UDP fragments
+ */
+
+/*
+unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
+ */
+
+.text
+.align 4
+.globl csum_partial
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+ /*
+ * Experiments with Ethernet and SLIP connections show that buff
+ * is aligned on either a 2-byte or 4-byte boundary. We get at
+ * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
+ * Fortunately, it is easy to convert 2-byte alignment to 4-byte
+ * alignment for the unrolled loop.
+ */
+csum_partial:
+ pushl %esi
+ pushl %ebx
+ movl 20(%esp),%eax # Function arg: unsigned int sum
+ movl 16(%esp),%ecx # Function arg: int len
+ movl 12(%esp),%esi # Function arg: unsigned char *buff
+ testl $2, %esi # Check alignment.
+ jz 2f # Jump if alignment is ok.
+ subl $2, %ecx # Alignment uses up two bytes.
+ jae 1f # Jump if we had at least two bytes.
+ addl $2, %ecx # ecx was < 2. Deal with it.
+ jmp 4f
+1: movw (%esi), %bx
+ addl $2, %esi
+ addw %bx, %ax
+ adcl $0, %eax
+2:
+ movl %ecx, %edx
+ shrl $5, %ecx
+ jz 2f
+ testl %esi, %esi
+1: movl (%esi), %ebx
+ adcl %ebx, %eax
+ movl 4(%esi), %ebx
+ adcl %ebx, %eax
+ movl 8(%esi), %ebx
+ adcl %ebx, %eax
+ movl 12(%esi), %ebx
+ adcl %ebx, %eax
+ movl 16(%esi), %ebx
+ adcl %ebx, %eax
+ movl 20(%esi), %ebx
+ adcl %ebx, %eax
+ movl 24(%esi), %ebx
+ adcl %ebx, %eax
+ movl 28(%esi), %ebx
+ adcl %ebx, %eax
+ lea 32(%esi), %esi
+ dec %ecx
+ jne 1b
+ adcl $0, %eax
+2: movl %edx, %ecx
+ andl $0x1c, %edx
+ je 4f
+ shrl $2, %edx # This clears CF
+3: adcl (%esi), %eax
+ lea 4(%esi), %esi
+ dec %edx
+ jne 3b
+ adcl $0, %eax
+4: andl $3, %ecx
+ jz 7f
+ cmpl $2, %ecx
+ jb 5f
+ movw (%esi),%cx
+ leal 2(%esi),%esi
+ je 6f
+ shll $16,%ecx
+5: movb (%esi),%cl
+6: addl %ecx,%eax
+ adcl $0, %eax
+7:
+ popl %ebx
+ popl %esi
+ ret
+
+#else
+
+/* Version for PentiumII/PPro */
+
+csum_partial:
+ pushl %esi
+ pushl %ebx
+ movl 20(%esp),%eax # Function arg: unsigned int sum
+ movl 16(%esp),%ecx # Function arg: int len
+ movl 12(%esp),%esi # Function arg: const unsigned char *buf
+
+ testl $2, %esi
+ jnz 30f
+10:
+ movl %ecx, %edx
+ movl %ecx, %ebx
+ andl $0x7c, %ebx
+ shrl $7, %ecx
+ addl %ebx,%esi
+ shrl $2, %ebx
+ negl %ebx
+ lea 45f(%ebx,%ebx,2), %ebx
+ testl %esi, %esi
+ jmp *%ebx
+
+ # Handle 2-byte-aligned regions
+20: addw (%esi), %ax
+ lea 2(%esi), %esi
+ adcl $0, %eax
+ jmp 10b
+
+30: subl $2, %ecx
+ ja 20b
+ je 32f
+ movzbl (%esi),%ebx # csumming 1 byte, 2-aligned
+ addl %ebx, %eax
+ adcl $0, %eax
+ jmp 80f
+32:
+ addw (%esi), %ax # csumming 2 bytes, 2-aligned
+ adcl $0, %eax
+ jmp 80f
+
+40:
+ addl -128(%esi), %eax
+ adcl -124(%esi), %eax
+ adcl -120(%esi), %eax
+ adcl -116(%esi), %eax
+ adcl -112(%esi), %eax
+ adcl -108(%esi), %eax
+ adcl -104(%esi), %eax
+ adcl -100(%esi), %eax
+ adcl -96(%esi), %eax
+ adcl -92(%esi), %eax
+ adcl -88(%esi), %eax
+ adcl -84(%esi), %eax
+ adcl -80(%esi), %eax
+ adcl -76(%esi), %eax
+ adcl -72(%esi), %eax
+ adcl -68(%esi), %eax
+ adcl -64(%esi), %eax
+ adcl -60(%esi), %eax
+ adcl -56(%esi), %eax
+ adcl -52(%esi), %eax
+ adcl -48(%esi), %eax
+ adcl -44(%esi), %eax
+ adcl -40(%esi), %eax
+ adcl -36(%esi), %eax
+ adcl -32(%esi), %eax
+ adcl -28(%esi), %eax
+ adcl -24(%esi), %eax
+ adcl -20(%esi), %eax
+ adcl -16(%esi), %eax
+ adcl -12(%esi), %eax
+ adcl -8(%esi), %eax
+ adcl -4(%esi), %eax
+45:
+ lea 128(%esi), %esi
+ adcl $0, %eax
+ dec %ecx
+ jge 40b
+ movl %edx, %ecx
+50: andl $3, %ecx
+ jz 80f
+
+ # Handle the last 1-3 bytes without jumping
+ notl %ecx # 1->2, 2->1, 3->0, higher bits are masked
+ movl $0xffffff,%ebx # by the shll and shrl instructions
+ shll $3,%ecx
+ shrl %cl,%ebx
+ andl -128(%esi),%ebx # esi is 4-aligned so should be ok
+ addl %ebx,%eax
+ adcl $0,%eax
+80:
+ popl %ebx
+ popl %esi
+ ret
+
+#endif
+
+/*
+unsigned int csum_partial_copy_generic (const char *src, char *dst,
+ int len, int sum, int *src_err_ptr, int *dst_err_ptr)
+ */
+
+/*
+ * Copy from ds while checksumming, otherwise like csum_partial
+ *
+ * The macros SRC and DST specify the type of access for the instruction.
+ * thus we can call a custom exception handler for all access types.
+ *
+ * FIXME: could someone double-check whether I haven't mixed up some SRC and
+ * DST definitions? It's damn hard to trigger all cases. I hope I got
+ * them all but there's no guarantee.
+ */
+
+#define SRC(y...) \
+ 9999: y; \
+ .section __ex_table, "a"; \
+ .long 9999b, 6001f ; \
+ .previous
+
+#define DST(y...) \
+ 9999: y; \
+ .section __ex_table, "a"; \
+ .long 9999b, 6002f ; \
+ .previous
+
+.align 4
+.globl csum_partial_copy_generic
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+#define ARGBASE 16
+#define FP 12
+
+csum_partial_copy_generic:
+ subl $4,%esp
+ pushl %edi
+ pushl %esi
+ pushl %ebx
+ movl ARGBASE+16(%esp),%eax # sum
+ movl ARGBASE+12(%esp),%ecx # len
+ movl ARGBASE+4(%esp),%esi # src
+ movl ARGBASE+8(%esp),%edi # dst
+
+ testl $2, %edi # Check alignment.
+ jz 2f # Jump if alignment is ok.
+ subl $2, %ecx # Alignment uses up two bytes.
+ jae 1f # Jump if we had at least two bytes.
+ addl $2, %ecx # ecx was < 2. Deal with it.
+ jmp 4f
+SRC(1: movw (%esi), %bx )
+ addl $2, %esi
+DST( movw %bx, (%edi) )
+ addl $2, %edi
+ addw %bx, %ax
+ adcl $0, %eax
+2:
+ movl %ecx, FP(%esp)
+ shrl $5, %ecx
+ jz 2f
+ testl %esi, %esi
+SRC(1: movl (%esi), %ebx )
+SRC( movl 4(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, (%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 4(%edi) )
+
+SRC( movl 8(%esi), %ebx )
+SRC( movl 12(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, 8(%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 12(%edi) )
+
+SRC( movl 16(%esi), %ebx )
+SRC( movl 20(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, 16(%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 20(%edi) )
+
+SRC( movl 24(%esi), %ebx )
+SRC( movl 28(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, 24(%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 28(%edi) )
+
+ lea 32(%esi), %esi
+ lea 32(%edi), %edi
+ dec %ecx
+ jne 1b
+ adcl $0, %eax
+2: movl FP(%esp), %edx
+ movl %edx, %ecx
+ andl $0x1c, %edx
+ je 4f
+ shrl $2, %edx # This clears CF
+SRC(3: movl (%esi), %ebx )
+ adcl %ebx, %eax
+DST( movl %ebx, (%edi) )
+ lea 4(%esi), %esi
+ lea 4(%edi), %edi
+ dec %edx
+ jne 3b
+ adcl $0, %eax
+4: andl $3, %ecx
+ jz 7f
+ cmpl $2, %ecx
+ jb 5f
+SRC( movw (%esi), %cx )
+ leal 2(%esi), %esi
+DST( movw %cx, (%edi) )
+ leal 2(%edi), %edi
+ je 6f
+ shll $16,%ecx
+SRC(5: movb (%esi), %cl )
+DST( movb %cl, (%edi) )
+6: addl %ecx, %eax
+ adcl $0, %eax
+7:
+5000:
+
+# Exception handler:
+.section .fixup, "ax"
+
+6001:
+ movl ARGBASE+20(%esp), %ebx # src_err_ptr
+ movl $-EFAULT, (%ebx)
+
+ # zero the complete destination - computing the rest
+ # is too much work
+ movl ARGBASE+8(%esp), %edi # dst
+ movl ARGBASE+12(%esp), %ecx # len
+ xorl %eax,%eax
+ rep ; stosb
+
+ jmp 5000b
+
+6002:
+ movl ARGBASE+24(%esp), %ebx # dst_err_ptr
+ movl $-EFAULT,(%ebx)
+ jmp 5000b
+
+.previous
+
+ popl %ebx
+ popl %esi
+ popl %edi
+ popl %ecx # equivalent to addl $4,%esp
+ ret
+
+#else
+
+/* Version for PentiumII/PPro */
+
+#define ROUND1(x) \
+ SRC(movl x(%esi), %ebx ) ; \
+ addl %ebx, %eax ; \
+ DST(movl %ebx, x(%edi) ) ;
+
+#define ROUND(x) \
+ SRC(movl x(%esi), %ebx ) ; \
+ adcl %ebx, %eax ; \
+ DST(movl %ebx, x(%edi) ) ;
+
+#define ARGBASE 12
+
+csum_partial_copy_generic:
+ pushl %ebx
+ pushl %edi
+ pushl %esi
+ movl ARGBASE+4(%esp),%esi #src
+ movl ARGBASE+8(%esp),%edi #dst
+ movl ARGBASE+12(%esp),%ecx #len
+ movl ARGBASE+16(%esp),%eax #sum
+# movl %ecx, %edx
+ movl %ecx, %ebx
+ movl %esi, %edx
+ shrl $6, %ecx
+ andl $0x3c, %ebx
+ negl %ebx
+ subl %ebx, %esi
+ subl %ebx, %edi
+ lea -1(%esi),%edx
+ andl $-32,%edx
+ lea 3f(%ebx,%ebx), %ebx
+ testl %esi, %esi
+ jmp *%ebx
+1: addl $64,%esi
+ addl $64,%edi
+ SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
+ ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)
+ ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)
+ ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)
+ ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4)
+3: adcl $0,%eax
+ addl $64, %edx
+ dec %ecx
+ jge 1b
+4: movl ARGBASE+12(%esp),%edx #len
+ andl $3, %edx
+ jz 7f
+ cmpl $2, %edx
+ jb 5f
+SRC( movw (%esi), %dx )
+ leal 2(%esi), %esi
+DST( movw %dx, (%edi) )
+ leal 2(%edi), %edi
+ je 6f
+ shll $16,%edx
+5:
+SRC( movb (%esi), %dl )
+DST( movb %dl, (%edi) )
+6: addl %edx, %eax
+ adcl $0, %eax
+7:
+.section .fixup, "ax"
+6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr
+ movl $-EFAULT, (%ebx)
+ # zero the complete destination (computing the rest is too much work)
+ movl ARGBASE+8(%esp),%edi # dst
+ movl ARGBASE+12(%esp),%ecx # len
+ xorl %eax,%eax
+ rep; stosb
+ jmp 7b
+6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr
+ movl $-EFAULT, (%ebx)
+ jmp 7b
+.previous
+
+ popl %esi
+ popl %edi
+ popl %ebx
+ ret
+
+#undef ROUND
+#undef ROUND1
+
+#endif
--- /dev/null
+/*
+ * x86 version of "atomic_dec_and_lock()" using
+ * the atomic "cmpxchg" instruction.
+ *
+ * (For CPU's lacking cmpxchg, we use the slow
+ * generic version, and this one never even gets
+ * compiled).
+ */
+
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+
+int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
+{
+ int counter;
+ int newcount;
+
+repeat:
+ counter = atomic_read(atomic);
+ newcount = counter-1;
+
+ if (!newcount)
+ goto slow_path;
+
+ asm volatile("lock; cmpxchgl %1,%2"
+ :"=a" (newcount)
+ :"r" (newcount), "m" (atomic->counter), "0" (counter));
+
+ /* If the above failed, "eax" will have changed */
+ if (newcount != counter)
+ goto repeat;
+ return 0;
+
+slow_path:
+ spin_lock(lock);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ spin_unlock(lock);
+ return 0;
+}
--- /dev/null
+/*
+ * Precise Delay Loops for i386
+ *
+ * Copyright (C) 1993 Linus Torvalds
+ * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ * The __delay function must _NOT_ be inlined as its execution time
+ * depends wildly on alignment on many x86 processors. The additional
+ * jump magic is needed to get the timing stable on all the CPU's
+ * we have to worry about.
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <asm/processor.h>
+#include <asm/delay.h>
+
+#ifdef CONFIG_SMP
+#include <asm/smp.h>
+#endif
+
+void __delay(unsigned long loops)
+{
+ unsigned long bclock, now;
+
+ rdtscl(bclock);
+ do
+ {
+ rep_nop();
+ rdtscl(now);
+ } while ((now-bclock) < loops);
+}
+
+inline void __const_udelay(unsigned long xloops)
+{
+ int d0;
+ __asm__("mull %0"
+ :"=d" (xloops), "=&a" (d0)
+ :"1" (xloops),"0" (current_cpu_data.loops_per_jiffy));
+ __delay(xloops * HZ);
+}
+
+void __udelay(unsigned long usecs)
+{
+ __const_udelay(usecs * 0x000010c6); /* 2**32 / 1000000 */
+}
--- /dev/null
+/*
+ * __get_user functions.
+ *
+ * (C) Copyright 1998 Linus Torvalds
+ *
+ * These functions have a non-standard call interface
+ * to make them more efficient, especially as they
+ * return an error value in addition to the "real"
+ * return value.
+ */
+
+/*
+ * __get_user_X
+ *
+ * Inputs: %eax contains the address
+ *
+ * Outputs: %eax is error code (0 or -EFAULT)
+ * %edx contains zero-extended value
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+addr_limit = 12
+
+.text
+.align 4
+.globl __get_user_1
+__get_user_1:
+ movl %esp,%edx
+ andl $0xffffe000,%edx
+ cmpl addr_limit(%edx),%eax
+ jae bad_get_user
+1: movzbl (%eax),%edx
+ xorl %eax,%eax
+ ret
+
+.align 4
+.globl __get_user_2
+__get_user_2:
+ addl $1,%eax
+ movl %esp,%edx
+ jc bad_get_user
+ andl $0xffffe000,%edx
+ cmpl addr_limit(%edx),%eax
+ jae bad_get_user
+2: movzwl -1(%eax),%edx
+ xorl %eax,%eax
+ ret
+
+.align 4
+.globl __get_user_4
+__get_user_4:
+ addl $3,%eax
+ movl %esp,%edx
+ jc bad_get_user
+ andl $0xffffe000,%edx
+ cmpl addr_limit(%edx),%eax
+ jae bad_get_user
+3: movl -3(%eax),%edx
+ xorl %eax,%eax
+ ret
+
+bad_get_user:
+ xorl %edx,%edx
+ movl $-14,%eax
+ ret
+
+.section __ex_table,"a"
+ .long 1b,bad_get_user
+ .long 2b,bad_get_user
+ .long 3b,bad_get_user
+.previous
--- /dev/null
+#include <asm/io.h>
+
+void * __io_virt_debug(unsigned long x, const char *file, int line)
+{
+ if (x < PAGE_OFFSET) {
+ printk("io mapaddr 0x%05lx not valid at %s:%d!\n", x, file, line);
+ return __va(x);
+ }
+ return (void *)x;
+}
+
+unsigned long __io_phys_debug(unsigned long x, const char *file, int line)
+{
+ if (x < PAGE_OFFSET) {
+ printk("io mapaddr 0x%05lx not valid at %s:%d!\n", x, file, line);
+ return x;
+ }
+ return __pa(x);
+}
--- /dev/null
+#include <linux/config.h>
+#include <linux/string.h>
+
+#undef memcpy
+#undef memset
+
+void * memcpy(void * to, const void * from, size_t n)
+{
+#ifdef CONFIG_X86_USE_3DNOW
+ return __memcpy3d(to, from, n);
+#else
+ return __memcpy(to, from, n);
+#endif
+}
+
+void * memset(void * s, int c, size_t count)
+{
+ return __memset(s, c, count);
+}
--- /dev/null
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+
+#include <asm/i387.h>
+#include <asm/hardirq.h>
+
+
+/*
+ * MMX 3DNow! library helper functions
+ *
+ * To do:
+ * We can use MMX just for prefetch in IRQ's. This may be a win.
+ * (reported so on K6-III)
+ * We should use a better code neutral filler for the short jump
+ * leal ebx. [ebx] is apparently best for K6-2, but Cyrix ??
+ * We also want to clobber the filler register so we dont get any
+ * register forwarding stalls on the filler.
+ *
+ * Add *user handling. Checksums are not a win with MMX on any CPU
+ * tested so far for any MMX solution figured.
+ *
+ * 22/09/2000 - Arjan van de Ven
+ * Improved for non-egineering-sample Athlons
+ *
+ */
+
+void *_mmx_memcpy(void *to, const void *from, size_t len)
+{
+ void *p;
+ int i;
+
+ if (in_interrupt())
+ return __memcpy(to, from, len);
+
+ p = to;
+ i = len >> 6; /* len/64 */
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n" /* This set is 28 bytes */
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+
+ for(; i>0; i--)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movq 8(%0), %%mm1\n"
+ " movq 16(%0), %%mm2\n"
+ " movq 24(%0), %%mm3\n"
+ " movq %%mm0, (%1)\n"
+ " movq %%mm1, 8(%1)\n"
+ " movq %%mm2, 16(%1)\n"
+ " movq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm0\n"
+ " movq 40(%0), %%mm1\n"
+ " movq 48(%0), %%mm2\n"
+ " movq 56(%0), %%mm3\n"
+ " movq %%mm0, 32(%1)\n"
+ " movq %%mm1, 40(%1)\n"
+ " movq %%mm2, 48(%1)\n"
+ " movq %%mm3, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ /*
+ * Now do the tail of the block
+ */
+ __memcpy(to, from, len&63);
+ kernel_fpu_end();
+ return p;
+}
+
+#ifdef CONFIG_MK7
+
+/*
+ * The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
+ * other MMX using processors do not.
+ */
+
+static void fast_clear_page(void *page)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ " pxor %%mm0, %%mm0\n" : :
+ );
+
+ for(i=0;i<4096/64;i++)
+ {
+ __asm__ __volatile__ (
+ " movntq %%mm0, (%0)\n"
+ " movntq %%mm0, 8(%0)\n"
+ " movntq %%mm0, 16(%0)\n"
+ " movntq %%mm0, 24(%0)\n"
+ " movntq %%mm0, 32(%0)\n"
+ " movntq %%mm0, 40(%0)\n"
+ " movntq %%mm0, 48(%0)\n"
+ " movntq %%mm0, 56(%0)\n"
+ : : "r" (page) : "memory");
+ page+=64;
+ }
+ /* since movntq is weakly-ordered, a "sfence" is needed to become
+ * ordered again.
+ */
+ __asm__ __volatile__ (
+ " sfence \n" : :
+ );
+ kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ /* maybe the prefetch stuff can go before the expensive fnsave...
+ * but that is for later. -AV
+ */
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n"
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+ for(i=0; i<(4096-320)/64; i++)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movntq %%mm0, (%1)\n"
+ " movq 8(%0), %%mm1\n"
+ " movntq %%mm1, 8(%1)\n"
+ " movq 16(%0), %%mm2\n"
+ " movntq %%mm2, 16(%1)\n"
+ " movq 24(%0), %%mm3\n"
+ " movntq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm4\n"
+ " movntq %%mm4, 32(%1)\n"
+ " movq 40(%0), %%mm5\n"
+ " movntq %%mm5, 40(%1)\n"
+ " movq 48(%0), %%mm6\n"
+ " movntq %%mm6, 48(%1)\n"
+ " movq 56(%0), %%mm7\n"
+ " movntq %%mm7, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ for(i=(4096-320)/64; i<4096/64; i++)
+ {
+ __asm__ __volatile__ (
+ "2: movq (%0), %%mm0\n"
+ " movntq %%mm0, (%1)\n"
+ " movq 8(%0), %%mm1\n"
+ " movntq %%mm1, 8(%1)\n"
+ " movq 16(%0), %%mm2\n"
+ " movntq %%mm2, 16(%1)\n"
+ " movq 24(%0), %%mm3\n"
+ " movntq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm4\n"
+ " movntq %%mm4, 32(%1)\n"
+ " movq 40(%0), %%mm5\n"
+ " movntq %%mm5, 40(%1)\n"
+ " movq 48(%0), %%mm6\n"
+ " movntq %%mm6, 48(%1)\n"
+ " movq 56(%0), %%mm7\n"
+ " movntq %%mm7, 56(%1)\n"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ /* since movntq is weakly-ordered, a "sfence" is needed to become
+ * ordered again.
+ */
+ __asm__ __volatile__ (
+ " sfence \n" : :
+ );
+ kernel_fpu_end();
+}
+
+#else
+
+/*
+ * Generic MMX implementation without K7 specific streaming
+ */
+
+static void fast_clear_page(void *page)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ " pxor %%mm0, %%mm0\n" : :
+ );
+
+ for(i=0;i<4096/128;i++)
+ {
+ __asm__ __volatile__ (
+ " movq %%mm0, (%0)\n"
+ " movq %%mm0, 8(%0)\n"
+ " movq %%mm0, 16(%0)\n"
+ " movq %%mm0, 24(%0)\n"
+ " movq %%mm0, 32(%0)\n"
+ " movq %%mm0, 40(%0)\n"
+ " movq %%mm0, 48(%0)\n"
+ " movq %%mm0, 56(%0)\n"
+ " movq %%mm0, 64(%0)\n"
+ " movq %%mm0, 72(%0)\n"
+ " movq %%mm0, 80(%0)\n"
+ " movq %%mm0, 88(%0)\n"
+ " movq %%mm0, 96(%0)\n"
+ " movq %%mm0, 104(%0)\n"
+ " movq %%mm0, 112(%0)\n"
+ " movq %%mm0, 120(%0)\n"
+ : : "r" (page) : "memory");
+ page+=128;
+ }
+
+ kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+ int i;
+
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n"
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+ for(i=0; i<4096/64; i++)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movq 8(%0), %%mm1\n"
+ " movq 16(%0), %%mm2\n"
+ " movq 24(%0), %%mm3\n"
+ " movq %%mm0, (%1)\n"
+ " movq %%mm1, 8(%1)\n"
+ " movq %%mm2, 16(%1)\n"
+ " movq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm0\n"
+ " movq 40(%0), %%mm1\n"
+ " movq 48(%0), %%mm2\n"
+ " movq 56(%0), %%mm3\n"
+ " movq %%mm0, 32(%1)\n"
+ " movq %%mm1, 40(%1)\n"
+ " movq %%mm2, 48(%1)\n"
+ " movq %%mm3, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ kernel_fpu_end();
+}
+
+
+#endif
+
+/*
+ * Favour MMX for page clear and copy.
+ */
+
+static void slow_zero_page(void * page)
+{
+ int d0, d1;
+ __asm__ __volatile__( \
+ "cld\n\t" \
+ "rep ; stosl" \
+ : "=&c" (d0), "=&D" (d1)
+ :"a" (0),"1" (page),"0" (1024)
+ :"memory");
+}
+
+void mmx_clear_page(void * page)
+{
+ if(in_interrupt())
+ slow_zero_page(page);
+ else
+ fast_clear_page(page);
+}
+
+static void slow_copy_page(void *to, void *from)
+{
+ int d0, d1, d2;
+ __asm__ __volatile__( \
+ "cld\n\t" \
+ "rep ; movsl" \
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2) \
+ : "0" (1024),"1" ((long) to),"2" ((long) from) \
+ : "memory");
+}
+
+
+void mmx_copy_page(void *to, void *from)
+{
+ if(in_interrupt())
+ slow_copy_page(to, from);
+ else
+ fast_copy_page(to, from);
+}
--- /dev/null
+/*
+ * FIXME: old compatibility stuff, will be removed soon.
+ */
+
+#include <net/checksum.h>
+
+unsigned int csum_partial_copy( const char *src, char *dst, int len, int sum)
+{
+ int src_err=0, dst_err=0;
+
+ sum = csum_partial_copy_generic ( src, dst, len, sum, &src_err, &dst_err);
+
+ if (src_err || dst_err)
+ printk("old csum_partial_copy_fromuser(), tell mingo to convert me.\n");
+
+ return sum;
+}
+
+
--- /dev/null
+#include <linux/string.h>
+
+char * strstr(const char * cs,const char * ct)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movl %6,%%edi\n\t"
+ "repne\n\t"
+ "scasb\n\t"
+ "notl %%ecx\n\t"
+ "decl %%ecx\n\t" /* NOTE! This also sets Z if searchstring='' */
+ "movl %%ecx,%%edx\n"
+ "1:\tmovl %6,%%edi\n\t"
+ "movl %%esi,%%eax\n\t"
+ "movl %%edx,%%ecx\n\t"
+ "repe\n\t"
+ "cmpsb\n\t"
+ "je 2f\n\t" /* also works for empty string, see above */
+ "xchgl %%eax,%%esi\n\t"
+ "incl %%esi\n\t"
+ "cmpb $0,-1(%%eax)\n\t"
+ "jne 1b\n\t"
+ "xorl %%eax,%%eax\n\t"
+ "2:"
+ :"=a" (__res), "=&c" (d0), "=&S" (d1)
+ :"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
+ :"dx", "di");
+return __res;
+}
+
--- /dev/null
+/*
+ * User address space access functions.
+ * The non inlined parts of asm-i386/uaccess.h are here.
+ *
+ * Copyright 1997 Andi Kleen <ak@muc.de>
+ * Copyright 1997 Linus Torvalds
+ */
+#include <linux/config.h>
+#include <asm/uaccess.h>
+#include <asm/mmx.h>
+
+#ifdef CONFIG_X86_USE_3DNOW_AND_WORKS
+
+unsigned long
+__generic_copy_to_user(void *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_WRITE, to, n))
+ {
+ if(n<512)
+ __copy_user(to,from,n);
+ else
+ mmx_copy_user(to,from,n);
+ }
+ return n;
+}
+
+unsigned long
+__generic_copy_from_user(void *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_READ, from, n))
+ {
+ if(n<512)
+ __copy_user_zeroing(to,from,n);
+ else
+ mmx_copy_user_zeroing(to, from, n);
+ }
+ else
+ memset(to, 0, n);
+ return n;
+}
+
+#else
+
+unsigned long
+__generic_copy_to_user(void *to, const void *from, unsigned long n)
+{
+ prefetch(from);
+ if (access_ok(VERIFY_WRITE, to, n))
+ __copy_user(to,from,n);
+ return n;
+}
+
+unsigned long
+__generic_copy_from_user(void *to, const void *from, unsigned long n)
+{
+ prefetchw(to);
+ if (access_ok(VERIFY_READ, from, n))
+ __copy_user_zeroing(to,from,n);
+ else
+ memset(to, 0, n);
+ return n;
+}
+
+#endif
+
+/*
+ * Copy a null terminated string from userspace.
+ */
+
+#define __do_strncpy_from_user(dst,src,count,res) \
+do { \
+ int __d0, __d1, __d2; \
+ __asm__ __volatile__( \
+ " testl %1,%1\n" \
+ " jz 2f\n" \
+ "0: lodsb\n" \
+ " stosb\n" \
+ " testb %%al,%%al\n" \
+ " jz 1f\n" \
+ " decl %1\n" \
+ " jnz 0b\n" \
+ "1: subl %1,%0\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl %5,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ ".previous" \
+ : "=d"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1), \
+ "=&D" (__d2) \
+ : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
+ : "memory"); \
+} while (0)
+
+long
+__strncpy_from_user(char *dst, const char *src, long count)
+{
+ long res;
+ __do_strncpy_from_user(dst, src, count, res);
+ return res;
+}
+
+long
+strncpy_from_user(char *dst, const char *src, long count)
+{
+ long res = -EFAULT;
+ if (access_ok(VERIFY_READ, src, 1))
+ __do_strncpy_from_user(dst, src, count, res);
+ return res;
+}
+
+
+/*
+ * Zero Userspace
+ */
+
+#define __do_clear_user(addr,size) \
+do { \
+ int __d0; \
+ __asm__ __volatile__( \
+ "0: rep; stosl\n" \
+ " movl %2,%0\n" \
+ "1: rep; stosb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: lea 0(%2,%0,4),%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,2b\n" \
+ ".previous" \
+ : "=&c"(size), "=&D" (__d0) \
+ : "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
+} while (0)
+
+unsigned long
+clear_user(void *to, unsigned long n)
+{
+ if (access_ok(VERIFY_WRITE, to, n))
+ __do_clear_user(to, n);
+ return n;
+}
+
+unsigned long
+__clear_user(void *to, unsigned long n)
+{
+ __do_clear_user(to, n);
+ return n;
+}
+
+/*
+ * Return the size of a string (including the ending 0)
+ *
+ * Return 0 on exception, a value greater than N if too long
+ */
+
+long strnlen_user(const char *s, long n)
+{
+ unsigned long mask = -__addr_ok(s);
+ unsigned long res, tmp;
+
+ __asm__ __volatile__(
+ " testl %0, %0\n"
+ " jz 3f\n"
+ " andl %0,%%ecx\n"
+ "0: repne; scasb\n"
+ " setne %%al\n"
+ " subl %%ecx,%0\n"
+ " addl %0,%%eax\n"
+ "1:\n"
+ ".section .fixup,\"ax\"\n"
+ "2: xorl %%eax,%%eax\n"
+ " jmp 1b\n"
+ "3: movb $1,%%al\n"
+ " jmp 1b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 0b,2b\n"
+ ".previous"
+ :"=r" (n), "=D" (s), "=a" (res), "=c" (tmp)
+ :"0" (n), "1" (s), "2" (0), "3" (mask)
+ :"cc");
+ return res & mask;
+}
--- /dev/null
+
+
+O_TARGET := mm.o
+
+obj-y := init.o fault.o extable.o hypervisor.o get_unmapped_area.o mmu_context.o
+
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * linux/arch/i386/mm/extable.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <asm/uaccess.h>
+
+extern const struct exception_table_entry __start___ex_table[];
+extern const struct exception_table_entry __stop___ex_table[];
+
+static inline unsigned long
+search_one_table(const struct exception_table_entry *first,
+ const struct exception_table_entry *last,
+ unsigned long value)
+{
+ while (first <= last) {
+ const struct exception_table_entry *mid;
+ long diff;
+
+ mid = (last - first) / 2 + first;
+ diff = mid->insn - value;
+ if (diff == 0)
+ return mid->fixup;
+ else if (diff < 0)
+ first = mid+1;
+ else
+ last = mid-1;
+ }
+ return 0;
+}
+
+extern spinlock_t modlist_lock;
+
+unsigned long
+search_exception_table(unsigned long addr)
+{
+ unsigned long ret = 0;
+
+#ifndef CONFIG_MODULES
+ /* There is only the kernel to search. */
+ ret = search_one_table(__start___ex_table, __stop___ex_table-1, addr);
+ return ret;
+#else
+ unsigned long flags;
+ /* The kernel is the last "module" -- no need to treat it special. */
+ struct module *mp;
+
+ spin_lock_irqsave(&modlist_lock, flags);
+ for (mp = module_list; mp != NULL; mp = mp->next) {
+ if (mp->ex_table_start == NULL || !(mp->flags&(MOD_RUNNING|MOD_INITIALIZING)))
+ continue;
+ ret = search_one_table(mp->ex_table_start,
+ mp->ex_table_end - 1, addr);
+ if (ret)
+ break;
+ }
+ spin_unlock_irqrestore(&modlist_lock, flags);
+ return ret;
+#endif
+}
--- /dev/null
+/*
+ * linux/arch/i386/mm/fault.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h> /* For unblank_screen() */
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/hardirq.h>
+
+extern void die(const char *,struct pt_regs *,long);
+
+extern int console_loglevel;
+
+pgd_t *cur_pgd;
+
+/*
+ * Ugly, ugly, but the goto's result in better assembly..
+ */
+int __verify_write(const void * addr, unsigned long size)
+{
+ struct vm_area_struct * vma;
+ unsigned long start = (unsigned long) addr;
+
+ if (!size)
+ return 1;
+
+ vma = find_vma(current->mm, start);
+ if (!vma)
+ goto bad_area;
+ if (vma->vm_start > start)
+ goto check_stack;
+
+good_area:
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ size--;
+ size += start & ~PAGE_MASK;
+ size >>= PAGE_SHIFT;
+ start &= PAGE_MASK;
+
+ for (;;) {
+ survive:
+ {
+ int fault = handle_mm_fault(current->mm, vma, start, 1);
+ if (!fault)
+ goto bad_area;
+ if (fault < 0)
+ goto out_of_memory;
+ }
+ if (!size)
+ break;
+ size--;
+ start += PAGE_SIZE;
+ if (start < vma->vm_end)
+ continue;
+ vma = vma->vm_next;
+ if (!vma || vma->vm_start != start)
+ goto bad_area;
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;;
+ }
+ return 1;
+
+check_stack:
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (expand_stack(vma, start) == 0)
+ goto good_area;
+
+bad_area:
+ return 0;
+
+out_of_memory:
+ if (current->pid == 1) {
+ current->policy |= SCHED_YIELD;
+ schedule();
+ goto survive;
+ }
+ goto bad_area;
+}
+
+extern spinlock_t timerlist_lock;
+
+/*
+ * Unlock any spinlocks which will prevent us from getting the
+ * message out (timerlist_lock is acquired through the
+ * console unblank code)
+ */
+void bust_spinlocks(int yes)
+{
+ spin_lock_init(&timerlist_lock);
+ if (yes) {
+ oops_in_progress = 1;
+ } else {
+ int loglevel_save = console_loglevel;
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ oops_in_progress = 0;
+ /*
+ * OK, the message is on the console. Now we call printk()
+ * without oops_in_progress set so that printk will give klogd
+ * a poke. Hold onto your hats...
+ */
+ console_loglevel = 15; /* NMI oopser may have shut the console up */
+ printk(" ");
+ console_loglevel = loglevel_save;
+ }
+}
+
+void do_BUG(const char *file, int line)
+{
+ bust_spinlocks(1);
+ printk("kernel BUG at %s:%d!\n", file, line);
+}
+
+/*
+ * This routine handles page faults. It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ *
+ * error_code:
+ * bit 0 == 0 means no page found, 1 means protection fault
+ * bit 1 == 0 means read, 1 means write
+ * bit 2 == 0 means kernel, 1 means user-mode
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs,
+ unsigned long error_code,
+ unsigned long address)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ unsigned long page;
+ unsigned long fixup;
+ int write;
+ siginfo_t info;
+
+ /* Set the "privileged fault" bit to something sane. */
+ error_code &= 3;
+ error_code |= (regs->xcs & 2) << 1;
+
+#if PT_UPDATE_DEBUG > 0
+ if ( (error_code == 0) && (address >= TASK_SIZE) )
+ {
+ unsigned long paddr = __pa(address);
+ int i;
+ for ( i = 0; i < pt_update_queue_idx; i++ )
+ {
+ if ( update_debug_queue[i].ptr == paddr )
+ {
+ printk("XXX now(EIP=%08lx:ptr=%08lx) "
+ "then(%s/%d:p/v=%08lx/%08lx)\n",
+ regs->eip, address,
+ update_debug_queue[i].file,
+ update_debug_queue[i].line,
+ update_debug_queue[i].ptr,
+ update_debug_queue[i].val);
+ }
+ }
+ }
+#endif
+
+ if ( flush_page_update_queue() != 0 ) return;
+
+ /*
+ * We fault-in kernel-space virtual memory on-demand. The
+ * 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ *
+ * This verifies that the fault happens in kernel space
+ * (error_code & 4) == 0, and that the fault was not a
+ * protection error (error_code & 1) == 0.
+ */
+ if (address >= TASK_SIZE && !(error_code & 5))
+ goto vmalloc_fault;
+
+ mm = tsk->mm;
+ info.si_code = SEGV_MAPERR;
+
+ /*
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+ if (in_interrupt() || !mm)
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+
+ vma = find_vma(mm, address);
+ if (!vma)
+ goto bad_area;
+ if (vma->vm_start <= address)
+ goto good_area;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (error_code & 4) {
+ /*
+ * accessing the stack below %esp is always a bug.
+ * The "+ 32" is there due to some instructions (like
+ * pusha) doing post-decrement on the stack and that
+ * doesn't show up until later..
+ */
+ if (address + 32 < regs->esp)
+ goto bad_area;
+ }
+ if (expand_stack(vma, address))
+ goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+ info.si_code = SEGV_ACCERR;
+ write = 0;
+ switch (error_code & 3) {
+ default: /* 3: write, present */
+ /* fall through */
+ case 2: /* write, not present */
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ write++;
+ break;
+ case 1: /* read, present */
+ goto bad_area;
+ case 0: /* read, not present */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto bad_area;
+ }
+
+ survive:
+ /*
+ * If for any reason at all we couldn't handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ switch (handle_mm_fault(mm, vma, address, write)) {
+ case 1:
+ tsk->min_flt++;
+ break;
+ case 2:
+ tsk->maj_flt++;
+ break;
+ case 0:
+ goto do_sigbus;
+ default:
+ goto out_of_memory;
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & 4) {
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ /* info.si_code has been set above */
+ info.si_addr = (void *)address;
+ force_sig_info(SIGSEGV, &info, tsk);
+ return;
+ }
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if ((fixup = search_exception_table(regs->eip)) != 0) {
+ regs->eip = fixup;
+ return;
+ }
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+ bust_spinlocks(1);
+
+ if (address < PAGE_SIZE)
+ printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
+ else
+ printk(KERN_ALERT "Unable to handle kernel paging request");
+ printk(" at virtual address %08lx\n",address);
+ printk(" printing eip:\n");
+ printk("%08lx\n", regs->eip);
+ page = ((unsigned long *) cur_pgd)[address >> 22];
+ printk(KERN_ALERT "*pde=%08lx(%08lx)\n", page, machine_to_phys(page));
+ if (page & 1) {
+ page &= PAGE_MASK;
+ address &= 0x003ff000;
+ page = machine_to_phys(page);
+ page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
+ printk(KERN_ALERT "*pte=%08lx(%08lx)\n", page,
+ machine_to_phys(page));
+ }
+ die("Oops", regs, error_code);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+ if (tsk->pid == 1) {
+ tsk->policy |= SCHED_YIELD;
+ schedule();
+ down_read(&mm->mmap_sem);
+ goto survive;
+ }
+ printk("VM: killing process %s\n", tsk->comm);
+ if (error_code & 4)
+ do_exit(SIGKILL);
+ goto no_context;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+
+ /*
+ * Send a sigbus, regardless of whether we were in kernel
+ * or user mode.
+ */
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void *)address;
+ force_sig_info(SIGBUS, &info, tsk);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & 4))
+ goto no_context;
+ return;
+
+vmalloc_fault:
+ {
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk" here. We might be inside
+ * an interrupt in the middle of a task switch..
+ */
+ int offset = __pgd_offset(address);
+ pgd_t *pgd, *pgd_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+
+ pgd = offset + cur_pgd;
+ pgd_k = init_mm.pgd + offset;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
+ pmd = pmd_offset(pgd, address);
+ pmd_k = pmd_offset(pgd_k, address);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+ XENO_flush_page_update_queue(); /* flush PMD update */
+
+ pte_k = pte_offset(pmd_k, address);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
--- /dev/null
+
+#include <linux/slab.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/swapctl.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/personality.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+
+/*
+static int direct_mapped(unsigned long addr)
+{
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if(node->addr == addr)
+ break;
+ curr = curr->next;
+ }
+
+ if(curr == direct_list)
+ return 0;
+
+ return 1;
+}
+*/
+/*
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct vm_area_struct *vma;
+
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(current->mm, addr);
+ if (TASK_SIZE - len >= addr &&
+ (!vma || addr + len <= vma->vm_start))
+ return addr;
+ }
+ addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);
+
+ for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
+ if (TASK_SIZE - len < addr)
+ return -ENOMEM;
+
+ if ((!vma || addr + len <= vma->vm_start) && !direct_mapped(addr))
+ return addr;
+
+ addr = vma->vm_end;
+ }
+}
+*/
+struct list_head *find_direct(struct list_head *list, unsigned long addr)
+{
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+ direct_mmap_node_t * node;
+
+ for ( curr = direct_list->next; curr != direct_list; curr = curr->next )
+ {
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if ( node->vm_start >= addr ) break;
+ }
+
+ return curr;
+}
+
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long
+addr, unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct vm_area_struct *vma;
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ if ( addr )
+ {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(current->mm, addr);
+ curr = find_direct(direct_list, addr);
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if ( (TASK_SIZE - len >= addr) &&
+ (!vma || addr + len <= vma->vm_start) &&
+ ((curr == direct_list) || addr + len <= node->vm_start) )
+ return addr;
+ }
+
+ addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);
+
+
+ /* Find first VMA and direct_map nodes with vm_start > addr */
+ vma = find_vma(current->mm, addr);
+ curr = find_direct(direct_list, addr);
+ node = list_entry(curr, direct_mmap_node_t, list);
+
+ for ( ; ; )
+ {
+ if ( TASK_SIZE - len < addr ) return -ENOMEM;
+
+ if ( vma && ((curr == direct_list) || (vma->vm_start < node->vm_start)))
+ {
+ /* Do we fit before VMA node? */
+ if ( addr + len <= vma->vm_start ) return addr;
+ addr = vma->vm_end;
+ vma = vma->vm_next;
+ }
+ else if ( curr != direct_list )
+ {
+ /* Do we fit before direct_map node? */
+ if ( addr + len <= node->vm_start) return addr;
+ addr = node->vm_end;
+ curr = curr->next;
+ node = list_entry(curr, direct_mmap_node_t, list);
+ }
+ else
+ {
+ /* !vma && curr == direct_list */
+ return addr;
+ }
+ }
+}
--- /dev/null
+/******************************************************************************
+ * xeno/mm/hypervisor.c
+ *
+ * Update page tables via the hypervisor.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/hypervisor.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+#define QUEUE_SIZE 2048
+static page_update_request_t update_queue[QUEUE_SIZE];
+unsigned int pt_update_queue_idx = 0;
+#define idx pt_update_queue_idx
+
+#if PT_UPDATE_DEBUG > 0
+page_update_debug_t update_debug_queue[QUEUE_SIZE] = {{0}};
+#undef queue_l1_entry_update
+#undef queue_l2_entry_update
+static void DEBUG_allow_pt_reads(void)
+{
+ pte_t *pte;
+ page_update_request_t update;
+ int i;
+ for ( i = idx-1; i >= 0; i-- )
+ {
+ pte = update_debug_queue[i].ptep;
+ if ( pte == NULL ) continue;
+ update_debug_queue[i].ptep = NULL;
+ update.ptr = phys_to_machine(__pa(pte));
+ update.val = update_debug_queue[i].pteval;
+ HYPERVISOR_pt_update(&update, 1);
+ }
+}
+static void DEBUG_disallow_pt_read(unsigned long pa)
+{
+ pte_t *pte;
+ pmd_t *pmd;
+ pgd_t *pgd;
+ unsigned long pteval;
+ /*
+ * We may fault because of an already outstanding update.
+ * That's okay -- it'll get fixed up in the fault handler.
+ */
+ page_update_request_t update;
+ unsigned long va = (unsigned long)__va(pa);
+ pgd = pgd_offset_k(va);
+ pmd = pmd_offset(pgd, va);
+ pte = pte_offset(pmd, va);
+ update.ptr = phys_to_machine(__pa(pte));
+ pteval = *(unsigned long *)pte;
+ update.val = pteval & ~_PAGE_PRESENT;
+ HYPERVISOR_pt_update(&update, 1);
+ update_debug_queue[idx].ptep = pte;
+ update_debug_queue[idx].pteval = pteval;
+}
+#endif
+
+#if PT_UPDATE_DEBUG > 1
+#undef queue_pt_switch
+#undef queue_tlb_flush
+#undef queue_invlpg
+#undef queue_pgd_pin
+#undef queue_pgd_unpin
+#undef queue_pte_pin
+#undef queue_pte_unpin
+#endif
+
+
+/*
+ * This is the current pagetable base pointer, which is updated
+ * on context switch.
+ */
+unsigned long pt_baseptr;
+
+void _flush_page_update_queue(void)
+{
+ if ( idx == 0 ) return;
+#if PT_UPDATE_DEBUG > 1
+ printk("Flushing %d entries from pt update queue\n", idx);
+#endif
+#if PT_UPDATE_DEBUG > 0
+ DEBUG_allow_pt_reads();
+#endif
+ HYPERVISOR_pt_update(update_queue, idx);
+ idx = 0;
+}
+
+static void increment_index(void)
+{
+ if ( ++idx == QUEUE_SIZE ) _flush_page_update_queue();
+}
+
+void queue_l1_entry_update(unsigned long ptr, unsigned long val)
+{
+#if PT_UPDATE_DEBUG > 0
+ DEBUG_disallow_pt_read(ptr);
+#endif
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].val = val;
+ increment_index();
+}
+
+void queue_l2_entry_update(unsigned long ptr, unsigned long val)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].val = val;
+ increment_index();
+}
+
+void queue_pt_switch(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_NEW_BASEPTR;
+ increment_index();
+}
+
+void queue_tlb_flush(void)
+{
+ update_queue[idx].ptr = PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_TLB_FLUSH;
+ increment_index();
+}
+
+void queue_invlpg(unsigned long ptr)
+{
+ update_queue[idx].ptr = PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = ptr & PAGE_MASK;
+ update_queue[idx].val |= PGEXT_INVLPG;
+ increment_index();
+}
+
+void queue_pgd_pin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_PIN_L2_TABLE;
+ increment_index();
+}
+
+void queue_pgd_unpin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_UNPIN_TABLE;
+ increment_index();
+}
+
+void queue_pte_pin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_PIN_L1_TABLE;
+ increment_index();
+}
+
+void queue_pte_unpin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_UNPIN_TABLE;
+ increment_index();
+}
--- /dev/null
+/*
+ * linux/arch/i386/mm/init.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#ifdef CONFIG_BLK_DEV_INITRD
+#include <linux/blk.h>
+#endif
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/dma.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+
+mmu_gather_t mmu_gathers[NR_CPUS];
+unsigned long highstart_pfn, highend_pfn;
+static unsigned long totalram_pages;
+static unsigned long totalhigh_pages;
+
+int do_check_pgt_cache(int low, int high)
+{
+ int freed = 0;
+ if(pgtable_cache_size > high) {
+ do {
+ if (!QUICKLIST_EMPTY(pgd_quicklist)) {
+ free_pgd_slow(get_pgd_fast());
+ freed++;
+ }
+ if (!QUICKLIST_EMPTY(pte_quicklist)) {
+ pte_free_slow(pte_alloc_one_fast(NULL, 0));
+ freed++;
+ }
+ } while(pgtable_cache_size > low);
+ }
+ return freed;
+}
+
+void show_mem(void)
+{
+ int i, total = 0, reserved = 0;
+ int shared = 0, cached = 0;
+ int highmem = 0;
+
+ printk("Mem-info:\n");
+ show_free_areas();
+ printk("Free swap: %6dkB\n",nr_swap_pages<<(PAGE_SHIFT-10));
+ i = max_mapnr;
+ while (i-- > 0) {
+ total++;
+ if (PageHighMem(mem_map+i))
+ highmem++;
+ if (PageReserved(mem_map+i))
+ reserved++;
+ else if (PageSwapCache(mem_map+i))
+ cached++;
+ else if (page_count(mem_map+i))
+ shared += page_count(mem_map+i) - 1;
+ }
+ printk("%d pages of RAM\n", total);
+ printk("%d pages of HIGHMEM\n",highmem);
+ printk("%d reserved pages\n",reserved);
+ printk("%d pages shared\n",shared);
+ printk("%d pages swap cached\n",cached);
+ printk("%ld pages in page table cache\n",pgtable_cache_size);
+ show_buffers();
+}
+
+/* References to section boundaries */
+
+extern char _text, _etext, _edata, __bss_start, _end;
+extern char __init_begin, __init_end;
+
+static inline void set_pte_phys (unsigned long vaddr,
+ unsigned long phys, pgprot_t flags)
+{
+ pgprot_t prot;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = init_mm.pgd + __pgd_offset(vaddr);
+ if (pgd_none(*pgd)) {
+ printk("PAE BUG #00!\n");
+ return;
+ }
+ pmd = pmd_offset(pgd, vaddr);
+ if (pmd_none(*pmd)) {
+ printk("PAE BUG #01!\n");
+ return;
+ }
+ pte = pte_offset(pmd, vaddr);
+ if (pte_val(*pte))
+ pte_ERROR(*pte);
+ pgprot_val(prot) = pgprot_val(PAGE_KERNEL) | pgprot_val(flags);
+
+ /* We queue directly, avoiding hidden phys->machine translation. */
+ queue_l1_entry_update(__pa(pte), phys | pgprot_val(prot));
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+void __set_fixmap (enum fixed_addresses idx, unsigned long phys,
+ pgprot_t flags)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ printk("Invalid __set_fixmap\n");
+ return;
+ }
+ set_pte_phys(address, phys, flags);
+}
+
+static void __init fixrange_init (unsigned long start,
+ unsigned long end, pgd_t *pgd_base)
+{
+ pgd_t *pgd, *kpgd;
+ pmd_t *pmd, *kpmd;
+ pte_t *pte, *kpte;
+ int i, j;
+ unsigned long vaddr;
+
+ vaddr = start;
+ i = __pgd_offset(vaddr);
+ j = __pmd_offset(vaddr);
+ pgd = pgd_base + i;
+
+ for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
+ pmd = (pmd_t *)pgd;
+ for (; (j < PTRS_PER_PMD) && (vaddr != end); pmd++, j++) {
+ if (pmd_none(*pmd)) {
+ pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ clear_page(pte);
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ queue_l1_entry_update(__pa(kpte),
+ (*(unsigned long *)kpte)&~_PAGE_RW);
+ set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
+ }
+ vaddr += PMD_SIZE;
+ }
+ j = 0;
+ }
+
+ XENO_flush_page_update_queue();
+}
+
+void __init paging_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+ unsigned int max_dma, high, low;
+ unsigned long vaddr;
+
+ max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+ low = max_low_pfn;
+ high = highend_pfn;
+
+ if (low < max_dma)
+ {
+ zones_size[ZONE_DMA] = low;
+ }
+ else
+ {
+ zones_size[ZONE_DMA] = max_dma;
+ zones_size[ZONE_NORMAL] = low - max_dma;
+ }
+ free_area_init(zones_size);
+
+ /*
+ * Fixed mappings, only the page table structure has to be created -
+ * mappings will be set by set_fixmap():
+ */
+ vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+ fixrange_init(vaddr, HYPERVISOR_VIRT_START, init_mm.pgd);
+
+ /*
+ * XXX We do this conversion early, so that all other page tables
+ * will automatically get this mapping.
+ */
+ set_fixmap(FIX_BLKRING_BASE, start_info.blk_ring);
+}
+
+
+static inline int page_is_ram (unsigned long pagenr)
+{
+ return 1;
+}
+
+void __init mem_init(void)
+{
+ int codesize, reservedpages, datasize, initsize;
+ int tmp;
+
+ max_mapnr = num_physpages = max_low_pfn;
+ high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+
+ /* clear the zero-page */
+ memset(empty_zero_page, 0, PAGE_SIZE);
+
+ /* this will put all low memory onto the freelists */
+ totalram_pages += free_all_bootmem();
+
+ reservedpages = 0;
+ for (tmp = 0; tmp < max_low_pfn; tmp++)
+ /*
+ * Only count reserved RAM pages
+ */
+ if (page_is_ram(tmp) && PageReserved(mem_map+tmp))
+ reservedpages++;
+ codesize = (unsigned long) &_etext - (unsigned long) &_text;
+ datasize = (unsigned long) &_edata - (unsigned long) &_etext;
+ initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
+
+ printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n",
+ (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+ max_mapnr << (PAGE_SHIFT-10),
+ codesize >> 10,
+ reservedpages << (PAGE_SHIFT-10),
+ datasize >> 10,
+ initsize >> 10,
+ (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
+ );
+
+ boot_cpu_data.wp_works_ok = 1;
+}
+
+void free_initmem(void)
+{
+ unsigned long addr;
+
+ addr = (unsigned long)(&__init_begin);
+ for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(addr));
+ set_page_count(virt_to_page(addr), 1);
+ free_page(addr);
+ totalram_pages++;
+ }
+ printk ("Freeing unused kernel memory: %dk freed\n", (&__init_end - &__init_begin) >> 10);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+ if (start < end)
+ printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+ for (; start < end; start += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(start));
+ set_page_count(virt_to_page(start), 1);
+ free_page(start);
+ totalram_pages++;
+ }
+}
+#endif
+
+void si_meminfo(struct sysinfo *val)
+{
+ val->totalram = totalram_pages;
+ val->sharedram = 0;
+ val->freeram = nr_free_pages();
+ val->bufferram = atomic_read(&buffermem_pages);
+ val->totalhigh = totalhigh_pages;
+ val->freehigh = nr_free_highpages();
+ val->mem_unit = PAGE_SIZE;
+ return;
+}
--- /dev/null
+
+#include <linux/slab.h>
+#include <linux/list.h>
+
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+ INIT_LIST_HEAD(&mm->context.direct_list);
+ return 0;
+}
+
+/* just free all elements of list identifying directly mapped areas */
+void destroy_context(struct mm_struct *mm)
+{
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = &mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+ curr = curr->next;
+ list_del(&node->list);
+ kfree(node);
+ }
+
+}
--- /dev/null
+/* ld script to make i386 Linux kernel
+ * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
+ */
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+ENTRY(_start)
+SECTIONS
+{
+ . = 0xC0000000 + 0x000000;
+ _text = .; /* Text and read-only data */
+ .text : {
+ *(.text)
+ *(.fixup)
+ *(.gnu.warning)
+ } = 0x9090
+ .text.lock : { *(.text.lock) } /* out-of-line lock text */
+
+ _etext = .; /* End of text section */
+
+ .rodata : { *(.rodata) *(.rodata.*) }
+ .kstrtab : { *(.kstrtab) }
+
+ . = ALIGN(16); /* Exception table */
+ __start___ex_table = .;
+ __ex_table : { *(__ex_table) }
+ __stop___ex_table = .;
+
+ __start___ksymtab = .; /* Kernel symbol table */
+ __ksymtab : { *(__ksymtab) }
+ __stop___ksymtab = .;
+
+ __start___kallsyms = .; /* All kernel symbols */
+ __kallsyms : { *(__kallsyms) }
+ __stop___kallsyms = .;
+
+ .data : { /* Data */
+ *(.data)
+ CONSTRUCTORS
+ }
+
+ _edata = .; /* End of data section */
+
+ . = ALIGN(8192); /* init_task */
+ .data.init_task : { *(.data.init_task) }
+
+ . = ALIGN(4096); /* Init code and data */
+ __init_begin = .;
+ .text.init : { *(.text.init) }
+ .data.init : { *(.data.init) }
+ . = ALIGN(16);
+ __setup_start = .;
+ .setup.init : { *(.setup.init) }
+ __setup_end = .;
+ __initcall_start = .;
+ .initcall.init : { *(.initcall.init) }
+ __initcall_end = .;
+ . = ALIGN(4096);
+ __init_end = .;
+
+ . = ALIGN(4096);
+ .data.page_aligned : { *(.data.idt) }
+
+ . = ALIGN(32);
+ .data.cacheline_aligned : { *(.data.cacheline_aligned) }
+
+ __bss_start = .; /* BSS */
+ .bss : {
+ *(.bss)
+ }
+ _end = . ;
+
+ /* Sections to be discarded */
+ /DISCARD/ : {
+ *(.text.exit)
+ *(.data.exit)
+ *(.exitcall.exit)
+ }
+
+ /* Stabs debugging sections. */
+ .stab 0 : { *(.stab) }
+ .stabstr 0 : { *(.stabstr) }
+ .stab.excl 0 : { *(.stab.excl) }
+ .stab.exclstr 0 : { *(.stab.exclstr) }
+ .stab.index 0 : { *(.stab.index) }
+ .stab.indexstr 0 : { *(.stab.indexstr) }
+ .comment 0 : { *(.comment) }
+}
--- /dev/null
+#
+# Block device driver configuration
+#
+mainmenu_option next_comment
+comment 'Block devices'
+
+tristate 'Normal PC floppy disk support' CONFIG_BLK_DEV_FD
+if [ "$CONFIG_AMIGA" = "y" ]; then
+ tristate 'Amiga floppy support' CONFIG_AMIGA_FLOPPY
+fi
+if [ "$CONFIG_ATARI" = "y" ]; then
+ tristate 'Atari floppy support' CONFIG_ATARI_FLOPPY
+fi
+if [ "$CONFIG_MAC" = "y" ]; then
+ dep_bool 'Macintosh IIfx/Quadra 900/Quadra 950 floppy support (EXPERIMENTAL)' CONFIG_BLK_DEV_SWIM_IOP $CONFIG_EXPERIMENTAL
+fi
+if [ "$CONFIG_MCA" = "y" ]; then
+ tristate 'PS/2 ESDI hard disk support' CONFIG_BLK_DEV_PS2
+fi
+if [ "$CONFIG_ZORRO" = "y" ]; then
+ tristate 'Amiga Zorro II ramdisk support' CONFIG_AMIGA_Z2RAM
+fi
+if [ "$CONFIG_ATARI" = "y" ]; then
+ tristate 'Atari ACSI support' CONFIG_ATARI_ACSI
+ if [ "$CONFIG_ATARI_ACSI" != "n" ]; then
+ comment 'Some devices (e.g. CD jukebox) support multiple LUNs'
+ bool ' Probe all LUNs on each ACSI device' CONFIG_ACSI_MULTI_LUN
+ tristate ' Atari SLM laser printer support' CONFIG_ATARI_SLM
+ fi
+fi
+dep_tristate 'XT hard disk support' CONFIG_BLK_DEV_XD $CONFIG_ISA
+dep_tristate 'Parallel port IDE device support' CONFIG_PARIDE $CONFIG_PARPORT
+if [ "$CONFIG_PARIDE" = "y" -o "$CONFIG_PARIDE" = "m" ]; then
+ source drivers/block/paride/Config.in
+fi
+dep_tristate 'Compaq SMART2 support' CONFIG_BLK_CPQ_DA $CONFIG_PCI
+dep_tristate 'Compaq Smart Array 5xxx support' CONFIG_BLK_CPQ_CISS_DA $CONFIG_PCI
+dep_tristate 'Mylex DAC960/DAC1100 PCI RAID Controller support' CONFIG_BLK_DEV_DAC960 $CONFIG_PCI
+
+tristate 'Loopback device support' CONFIG_BLK_DEV_LOOP
+dep_tristate 'Network block device support' CONFIG_BLK_DEV_NBD $CONFIG_NET
+
+tristate 'RAM disk support' CONFIG_BLK_DEV_RAM
+if [ "$CONFIG_BLK_DEV_RAM" = "y" -o "$CONFIG_BLK_DEV_RAM" = "m" ]; then
+ int ' Default RAM disk size' CONFIG_BLK_DEV_RAM_SIZE 4096
+fi
+dep_bool ' Initial RAM disk (initrd) support' CONFIG_BLK_DEV_INITRD $CONFIG_BLK_DEV_RAM
+
+bool 'XenoLinux virtual block device support' CONFIG_XENOLINUX_BLOCK
+
+endmenu
--- /dev/null
+/*
+ * linux/drivers/block/ll_rw_blk.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 1994, Karl Keyte: Added support for disk statistics
+ * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
+ * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> - July2000
+ */
+
+/*
+ * This handles all read/write requests to block devices
+ */
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/config.h>
+#include <linux/locks.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/init.h>
+#include <linux/smp_lock.h>
+#include <linux/completion.h>
+
+#include <asm/system.h>
+#include <asm/io.h>
+#include <linux/blk.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+/*
+ * MAC Floppy IWM hooks
+ */
+
+#ifdef CONFIG_MAC_FLOPPY_IWM
+extern int mac_floppy_init(void);
+#endif
+
+/*
+ * For the allocated request tables
+ */
+static kmem_cache_t *request_cachep;
+
+/*
+ * The "disk" task queue is used to start the actual requests
+ * after a plug
+ */
+DECLARE_TASK_QUEUE(tq_disk);
+
+/*
+ * Protect the request list against multiple users..
+ *
+ * With this spinlock the Linux block IO subsystem is 100% SMP threaded
+ * from the IRQ event side, and almost 100% SMP threaded from the syscall
+ * side (we still have protect against block device array operations, and
+ * the do_request() side is casually still unsafe. The kernel lock protects
+ * this part currently.).
+ *
+ * there is a fair chance that things will work just OK if these functions
+ * are called with no global kernel lock held ...
+ */
+spinlock_t io_request_lock = SPIN_LOCK_UNLOCKED;
+
+/* This specifies how many sectors to read ahead on the disk. */
+
+int read_ahead[MAX_BLKDEV];
+
+/* blk_dev_struct is:
+ * *request_fn
+ * *current_request
+ */
+struct blk_dev_struct blk_dev[MAX_BLKDEV]; /* initialized by blk_dev_init() */
+
+/*
+ * blk_size contains the size of all block-devices in units of 1024 byte
+ * sectors:
+ *
+ * blk_size[MAJOR][MINOR]
+ *
+ * if (!blk_size[MAJOR]) then no minor size checking is done.
+ */
+int * blk_size[MAX_BLKDEV];
+
+/*
+ * blksize_size contains the size of all block-devices:
+ *
+ * blksize_size[MAJOR][MINOR]
+ *
+ * if (!blksize_size[MAJOR]) then 1024 bytes is assumed.
+ */
+int * blksize_size[MAX_BLKDEV];
+
+/*
+ * hardsect_size contains the size of the hardware sector of a device.
+ *
+ * hardsect_size[MAJOR][MINOR]
+ *
+ * if (!hardsect_size[MAJOR])
+ * then 512 bytes is assumed.
+ * else
+ * sector_size is hardsect_size[MAJOR][MINOR]
+ * This is currently set by some scsi devices and read by the msdos fs driver.
+ * Other uses may appear later.
+ */
+int * hardsect_size[MAX_BLKDEV];
+
+/*
+ * The following tunes the read-ahead algorithm in mm/filemap.c
+ */
+int * max_readahead[MAX_BLKDEV];
+
+/*
+ * Max number of sectors per request
+ */
+int * max_sectors[MAX_BLKDEV];
+
+/*
+ * How many reqeusts do we allocate per queue,
+ * and how many do we "batch" on freeing them?
+ */
+static int queue_nr_requests, batch_requests;
+
+static inline int get_max_sectors(kdev_t dev)
+{
+ if (!max_sectors[MAJOR(dev)])
+ return MAX_SECTORS;
+ return max_sectors[MAJOR(dev)][MINOR(dev)];
+}
+
+inline request_queue_t *blk_get_queue(kdev_t dev)
+{
+ struct blk_dev_struct *bdev = blk_dev + MAJOR(dev);
+
+ if (bdev->queue)
+ return bdev->queue(dev);
+ else
+ return &blk_dev[MAJOR(dev)].request_queue;
+}
+
+static int __blk_cleanup_queue(struct request_list *list)
+{
+ struct list_head *head = &list->free;
+ struct request *rq;
+ int i = 0;
+
+ while (!list_empty(head)) {
+ rq = list_entry(head->next, struct request, queue);
+ list_del(&rq->queue);
+ kmem_cache_free(request_cachep, rq);
+ i++;
+ };
+
+ if (i != list->count)
+ printk("request list leak!\n");
+
+ list->count = 0;
+ return i;
+}
+
+/**
+ * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
+ * @q: the request queue to be released
+ *
+ * Description:
+ * blk_cleanup_queue is the pair to blk_init_queue(). It should
+ * be called when a request queue is being released; typically
+ * when a block device is being de-registered. Currently, its
+ * primary task it to free all the &struct request structures that
+ * were allocated to the queue.
+ * Caveat:
+ * Hopefully the low level driver will have finished any
+ * outstanding requests first...
+ **/
+void blk_cleanup_queue(request_queue_t * q)
+{
+ int count = queue_nr_requests;
+
+ count -= __blk_cleanup_queue(&q->rq[READ]);
+ count -= __blk_cleanup_queue(&q->rq[WRITE]);
+
+ if (count)
+ printk("blk_cleanup_queue: leaked requests (%d)\n", count);
+
+ memset(q, 0, sizeof(*q));
+}
+
+/**
+ * blk_queue_headactive - indicate whether head of request queue may be active
+ * @q: The queue which this applies to.
+ * @active: A flag indication where the head of the queue is active.
+ *
+ * Description:
+ * The driver for a block device may choose to leave the currently active
+ * request on the request queue, removing it only when it has completed.
+ * The queue handling routines assume this by default for safety reasons
+ * and will not involve the head of the request queue in any merging or
+ * reordering of requests when the queue is unplugged (and thus may be
+ * working on this particular request).
+ *
+ * If a driver removes requests from the queue before processing them, then
+ * it may indicate that it does so, there by allowing the head of the queue
+ * to be involved in merging and reordering. This is done be calling
+ * blk_queue_headactive() with an @active flag of %0.
+ *
+ * If a driver processes several requests at once, it must remove them (or
+ * at least all but one of them) from the request queue.
+ *
+ * When a queue is plugged the head will be assumed to be inactive.
+ **/
+
+void blk_queue_headactive(request_queue_t * q, int active)
+{
+ q->head_active = active;
+}
+
+/**
+ * blk_queue_make_request - define an alternate make_request function for a device
+ * @q: the request queue for the device to be affected
+ * @mfn: the alternate make_request function
+ *
+ * Description:
+ * The normal way for &struct buffer_heads to be passed to a device
+ * driver is for them to be collected into requests on a request
+ * queue, and then to allow the device driver to select requests
+ * off that queue when it is ready. This works well for many block
+ * devices. However some block devices (typically virtual devices
+ * such as md or lvm) do not benefit from the processing on the
+ * request queue, and are served best by having the requests passed
+ * directly to them. This can be achieved by providing a function
+ * to blk_queue_make_request().
+ *
+ * Caveat:
+ * The driver that does this *must* be able to deal appropriately
+ * with buffers in "highmemory", either by calling bh_kmap() to get
+ * a kernel mapping, to by calling create_bounce() to create a
+ * buffer in normal memory.
+ **/
+
+void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
+{
+ q->make_request_fn = mfn;
+}
+
+static inline int ll_new_segment(request_queue_t *q, struct request *req, int max_segments)
+{
+ if (req->nr_segments < max_segments) {
+ req->nr_segments++;
+ return 1;
+ }
+ return 0;
+}
+
+static int ll_back_merge_fn(request_queue_t *q, struct request *req,
+ struct buffer_head *bh, int max_segments)
+{
+ if (req->bhtail->b_data + req->bhtail->b_size == bh->b_data)
+ return 1;
+ return ll_new_segment(q, req, max_segments);
+}
+
+static int ll_front_merge_fn(request_queue_t *q, struct request *req,
+ struct buffer_head *bh, int max_segments)
+{
+ if (bh->b_data + bh->b_size == req->bh->b_data)
+ return 1;
+ return ll_new_segment(q, req, max_segments);
+}
+
+static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
+ struct request *next, int max_segments)
+{
+ int total_segments = req->nr_segments + next->nr_segments;
+
+ if (req->bhtail->b_data + req->bhtail->b_size == next->bh->b_data)
+ total_segments--;
+
+ if (total_segments > max_segments)
+ return 0;
+
+ req->nr_segments = total_segments;
+ return 1;
+}
+
+/*
+ * "plug" the device if there are no outstanding requests: this will
+ * force the transfer to start only after we have put all the requests
+ * on the list.
+ *
+ * This is called with interrupts off and no requests on the queue.
+ * (and with the request spinlock acquired)
+ */
+static void generic_plug_device(request_queue_t *q, kdev_t dev)
+{
+ /*
+ * no need to replug device
+ */
+ if (!list_empty(&q->queue_head) || q->plugged)
+ return;
+
+ q->plugged = 1;
+ queue_task(&q->plug_tq, &tq_disk);
+}
+
+/*
+ * remove the plug and let it rip..
+ */
+static inline void __generic_unplug_device(request_queue_t *q)
+{
+ if (q->plugged) {
+ q->plugged = 0;
+ if (!list_empty(&q->queue_head))
+ q->request_fn(q);
+ }
+}
+
+void generic_unplug_device(void *data)
+{
+ request_queue_t *q = (request_queue_t *) data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&io_request_lock, flags);
+ __generic_unplug_device(q);
+ spin_unlock_irqrestore(&io_request_lock, flags);
+}
+
+static void blk_init_free_list(request_queue_t *q)
+{
+ struct request *rq;
+ int i;
+
+ INIT_LIST_HEAD(&q->rq[READ].free);
+ INIT_LIST_HEAD(&q->rq[WRITE].free);
+ q->rq[READ].count = 0;
+ q->rq[WRITE].count = 0;
+
+ /*
+ * Divide requests in half between read and write
+ */
+ for (i = 0; i < queue_nr_requests; i++) {
+ rq = kmem_cache_alloc(request_cachep, SLAB_KERNEL);
+ if (rq == NULL) {
+ /* We'll get a `leaked requests' message from blk_cleanup_queue */
+ printk(KERN_EMERG "blk_init_free_list: error allocating requests\n");
+ break;
+ }
+ memset(rq, 0, sizeof(struct request));
+ rq->rq_status = RQ_INACTIVE;
+ list_add(&rq->queue, &q->rq[i&1].free);
+ q->rq[i&1].count++;
+ }
+
+ init_waitqueue_head(&q->wait_for_request);
+ spin_lock_init(&q->queue_lock);
+}
+
+static int __make_request(request_queue_t * q, int rw, struct buffer_head * bh);
+
+/**
+ * blk_init_queue - prepare a request queue for use with a block device
+ * @q: The &request_queue_t to be initialised
+ * @rfn: The function to be called to process requests that have been
+ * placed on the queue.
+ *
+ * Description:
+ * If a block device wishes to use the standard request handling procedures,
+ * which sorts requests and coalesces adjacent requests, then it must
+ * call blk_init_queue(). The function @rfn will be called when there
+ * are requests on the queue that need to be processed. If the device
+ * supports plugging, then @rfn may not be called immediately when requests
+ * are available on the queue, but may be called at some time later instead.
+ * Plugged queues are generally unplugged when a buffer belonging to one
+ * of the requests on the queue is needed, or due to memory pressure.
+ *
+ * @rfn is not required, or even expected, to remove all requests off the
+ * queue, but only as many as it can handle at a time. If it does leave
+ * requests on the queue, it is responsible for arranging that the requests
+ * get dealt with eventually.
+ *
+ * A global spin lock $io_request_lock must be held while manipulating the
+ * requests on the request queue.
+ *
+ * The request on the head of the queue is by default assumed to be
+ * potentially active, and it is not considered for re-ordering or merging
+ * whenever the given queue is unplugged. This behaviour can be changed with
+ * blk_queue_headactive().
+ *
+ * Note:
+ * blk_init_queue() must be paired with a blk_cleanup_queue() call
+ * when the block device is deactivated (such as at module unload).
+ **/
+void blk_init_queue(request_queue_t * q, request_fn_proc * rfn)
+{
+ INIT_LIST_HEAD(&q->queue_head);
+ elevator_init(&q->elevator, ELEVATOR_LINUS);
+ blk_init_free_list(q);
+ q->request_fn = rfn;
+ q->back_merge_fn = ll_back_merge_fn;
+ q->front_merge_fn = ll_front_merge_fn;
+ q->merge_requests_fn = ll_merge_requests_fn;
+ q->make_request_fn = __make_request;
+ q->plug_tq.sync = 0;
+ q->plug_tq.routine = &generic_unplug_device;
+ q->plug_tq.data = q;
+ q->plugged = 0;
+ /*
+ * These booleans describe the queue properties. We set the
+ * default (and most common) values here. Other drivers can
+ * use the appropriate functions to alter the queue properties.
+ * as appropriate.
+ */
+ q->plug_device_fn = generic_plug_device;
+ q->head_active = 1;
+}
+
+#define blkdev_free_rq(list) list_entry((list)->next, struct request, queue);
+/*
+ * Get a free request. io_request_lock must be held and interrupts
+ * disabled on the way in.
+ */
+static inline struct request *get_request(request_queue_t *q, int rw)
+{
+ struct request *rq = NULL;
+ struct request_list *rl = q->rq + rw;
+
+ if (!list_empty(&rl->free)) {
+ rq = blkdev_free_rq(&rl->free);
+ list_del(&rq->queue);
+ rl->count--;
+ rq->rq_status = RQ_ACTIVE;
+ rq->special = NULL;
+ rq->q = q;
+ }
+
+ return rq;
+}
+
+/*
+ * No available requests for this queue, unplug the device.
+ */
+static struct request *__get_request_wait(request_queue_t *q, int rw)
+{
+ register struct request *rq;
+ DECLARE_WAITQUEUE(wait, current);
+
+ generic_unplug_device(q);
+ add_wait_queue(&q->wait_for_request, &wait);
+ do {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (q->rq[rw].count < batch_requests)
+ schedule();
+ spin_lock_irq(&io_request_lock);
+ rq = get_request(q,rw);
+ spin_unlock_irq(&io_request_lock);
+ } while (rq == NULL);
+ remove_wait_queue(&q->wait_for_request, &wait);
+ current->state = TASK_RUNNING;
+ return rq;
+}
+
+static inline struct request *get_request_wait(request_queue_t *q, int rw)
+{
+ register struct request *rq;
+
+ spin_lock_irq(&io_request_lock);
+ rq = get_request(q, rw);
+ spin_unlock_irq(&io_request_lock);
+ if (rq)
+ return rq;
+ return __get_request_wait(q, rw);
+}
+
+/* RO fail safe mechanism */
+
+static long ro_bits[MAX_BLKDEV][8];
+
+int is_read_only(kdev_t dev)
+{
+ int minor,major;
+
+ major = MAJOR(dev);
+ minor = MINOR(dev);
+ if (major < 0 || major >= MAX_BLKDEV) return 0;
+ return ro_bits[major][minor >> 5] & (1 << (minor & 31));
+}
+
+void set_device_ro(kdev_t dev,int flag)
+{
+ int minor,major;
+
+ major = MAJOR(dev);
+ minor = MINOR(dev);
+ if (major < 0 || major >= MAX_BLKDEV) return;
+ if (flag) ro_bits[major][minor >> 5] |= 1 << (minor & 31);
+ else ro_bits[major][minor >> 5] &= ~(1 << (minor & 31));
+}
+
+inline void drive_stat_acct (kdev_t dev, int rw,
+ unsigned long nr_sectors, int new_io)
+{
+ unsigned int major = MAJOR(dev);
+ unsigned int index;
+
+ index = disk_index(dev);
+ if ((index >= DK_MAX_DISK) || (major >= DK_MAX_MAJOR))
+ return;
+
+ kstat.dk_drive[major][index] += new_io;
+ if (rw == READ) {
+ kstat.dk_drive_rio[major][index] += new_io;
+ kstat.dk_drive_rblk[major][index] += nr_sectors;
+ } else if (rw == WRITE) {
+ kstat.dk_drive_wio[major][index] += new_io;
+ kstat.dk_drive_wblk[major][index] += nr_sectors;
+ } else
+ printk(KERN_ERR "drive_stat_acct: cmd not R/W?\n");
+}
+
+/*
+ * add-request adds a request to the linked list.
+ * io_request_lock is held and interrupts disabled, as we muck with the
+ * request queue list.
+ *
+ * By this point, req->cmd is always either READ/WRITE, never READA,
+ * which is important for drive_stat_acct() above.
+ */
+static inline void add_request(request_queue_t * q, struct request * req,
+ struct list_head *insert_here)
+{
+ drive_stat_acct(req->rq_dev, req->cmd, req->nr_sectors, 1);
+
+ if (!q->plugged && q->head_active && insert_here == &q->queue_head) {
+ spin_unlock_irq(&io_request_lock);
+ printk("list_empty(&q->queue_head) is %d\n",
+ list_empty(&q->queue_head));
+ BUG();
+ }
+
+ /*
+ * elevator indicated where it wants this request to be
+ * inserted at elevator_merge time
+ */
+ list_add(&req->queue, insert_here);
+}
+
+/*
+ * Must be called with io_request_lock held and interrupts disabled
+ */
+inline void blkdev_release_request(struct request *req)
+{
+ request_queue_t *q = req->q;
+ int rw = req->cmd;
+
+ req->rq_status = RQ_INACTIVE;
+ req->q = NULL;
+
+ /*
+ * Request may not have originated from ll_rw_blk. if not,
+ * assume it has free buffers and check waiters
+ */
+ if (q) {
+ list_add(&req->queue, &q->rq[rw].free);
+ if (++q->rq[rw].count >= batch_requests && waitqueue_active(&q->wait_for_request))
+ wake_up(&q->wait_for_request);
+ }
+}
+
+/*
+ * Has to be called with the request spinlock acquired
+ */
+static void attempt_merge(request_queue_t * q,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ struct request *next;
+
+ next = blkdev_next_request(req);
+ if (req->sector + req->nr_sectors != next->sector)
+ return;
+ if (req->cmd != next->cmd
+ || req->rq_dev != next->rq_dev
+ || req->nr_sectors + next->nr_sectors > max_sectors
+ || next->waiting)
+ return;
+ /*
+ * If we are not allowed to merge these requests, then
+ * return. If we are allowed to merge, then the count
+ * will have been updated to the appropriate number,
+ * and we shouldn't do it here too.
+ */
+ if (!q->merge_requests_fn(q, req, next, max_segments))
+ return;
+
+ q->elevator.elevator_merge_req_fn(req, next);
+ req->bhtail->b_reqnext = next->bh;
+ req->bhtail = next->bhtail;
+ req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+ list_del(&next->queue);
+ blkdev_release_request(next);
+}
+
+static inline void attempt_back_merge(request_queue_t * q,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ if (&req->queue == q->queue_head.prev)
+ return;
+ attempt_merge(q, req, max_sectors, max_segments);
+}
+
+static inline void attempt_front_merge(request_queue_t * q,
+ struct list_head * head,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ struct list_head * prev;
+
+ prev = req->queue.prev;
+ if (head == prev)
+ return;
+ attempt_merge(q, blkdev_entry_to_request(prev), max_sectors, max_segments);
+}
+
+static int __make_request(request_queue_t * q, int rw,
+ struct buffer_head * bh)
+{
+ unsigned int sector, count;
+ int max_segments = MAX_SEGMENTS;
+ struct request * req, *freereq = NULL;
+ int rw_ahead, max_sectors, el_ret;
+ struct list_head *head, *insert_here;
+ int latency;
+ elevator_t *elevator = &q->elevator;
+
+ count = bh->b_size >> 9;
+ sector = bh->b_rsector;
+
+ rw_ahead = 0; /* normal case; gets changed below for READA */
+ switch (rw) {
+ case READA:
+ rw_ahead = 1;
+ rw = READ; /* drop into READ */
+ case READ:
+ case WRITE:
+ latency = elevator_request_latency(elevator, rw);
+ break;
+ default:
+ BUG();
+ goto end_io;
+ }
+
+ /* We'd better have a real physical mapping!
+ Check this bit only if the buffer was dirty and just locked
+ down by us so at this point flushpage will block and
+ won't clear the mapped bit under us. */
+ if (!buffer_mapped(bh))
+ BUG();
+
+ /*
+ * Temporary solution - in 2.5 this will be done by the lowlevel
+ * driver. Create a bounce buffer if the buffer data points into
+ * high memory - keep the original buffer otherwise.
+ */
+#if CONFIG_HIGHMEM
+ bh = create_bounce(rw, bh);
+#endif
+
+/* look for a free request. */
+ /*
+ * Try to coalesce the new request with old requests
+ */
+ max_sectors = get_max_sectors(bh->b_rdev);
+
+again:
+ req = NULL;
+ head = &q->queue_head;
+ /*
+ * Now we acquire the request spinlock, we have to be mega careful
+ * not to schedule or do something nonatomic
+ */
+ spin_lock_irq(&io_request_lock);
+
+ insert_here = head->prev;
+ if (list_empty(head)) {
+ q->plug_device_fn(q, bh->b_rdev); /* is atomic */
+ goto get_rq;
+ } else if (q->head_active && !q->plugged)
+ head = head->next;
+
+ el_ret = elevator->elevator_merge_fn(q, &req, head, bh, rw,max_sectors);
+ switch (el_ret) {
+
+ case ELEVATOR_BACK_MERGE:
+ if (!q->back_merge_fn(q, req, bh, max_segments))
+ break;
+ elevator->elevator_merge_cleanup_fn(q, req, count);
+ req->bhtail->b_reqnext = bh;
+ req->bhtail = bh;
+ req->nr_sectors = req->hard_nr_sectors += count;
+ blk_started_io(count);
+ drive_stat_acct(req->rq_dev, req->cmd, count, 0);
+ attempt_back_merge(q, req, max_sectors, max_segments);
+ goto out;
+
+ case ELEVATOR_FRONT_MERGE:
+ if (!q->front_merge_fn(q, req, bh, max_segments))
+ break;
+ elevator->elevator_merge_cleanup_fn(q, req, count);
+ bh->b_reqnext = req->bh;
+ req->bh = bh;
+ req->buffer = bh->b_data;
+ req->current_nr_sectors = count;
+ req->sector = req->hard_sector = sector;
+ req->nr_sectors = req->hard_nr_sectors += count;
+ blk_started_io(count);
+ drive_stat_acct(req->rq_dev, req->cmd, count, 0);
+ attempt_front_merge(q, head, req, max_sectors, max_segments);
+ goto out;
+
+ /*
+ * elevator says don't/can't merge. get new request
+ */
+ case ELEVATOR_NO_MERGE:
+ /*
+ * use elevator hints as to where to insert the
+ * request. if no hints, just add it to the back
+ * of the queue
+ */
+ if (req)
+ insert_here = &req->queue;
+ break;
+
+ default:
+ printk("elevator returned crap (%d)\n", el_ret);
+ BUG();
+ }
+
+ /*
+ * Grab a free request from the freelist - if that is empty, check
+ * if we are doing read ahead and abort instead of blocking for
+ * a free slot.
+ */
+get_rq:
+ if (freereq) {
+ req = freereq;
+ freereq = NULL;
+ } else if ((req = get_request(q, rw)) == NULL) {
+ spin_unlock_irq(&io_request_lock);
+ if (rw_ahead)
+ goto end_io;
+
+ freereq = __get_request_wait(q, rw);
+ goto again;
+ }
+
+/* fill up the request-info, and add it to the queue */
+ req->elevator_sequence = latency;
+ req->cmd = rw;
+ req->errors = 0;
+ req->hard_sector = req->sector = sector;
+ req->hard_nr_sectors = req->nr_sectors = count;
+ req->current_nr_sectors = count;
+ req->nr_segments = 1; /* Always 1 for a new request. */
+ req->nr_hw_segments = 1; /* Always 1 for a new request. */
+ req->buffer = bh->b_data;
+ req->waiting = NULL;
+ req->bh = bh;
+ req->bhtail = bh;
+ req->rq_dev = bh->b_rdev;
+ blk_started_io(count);
+
+ add_request(q, req, insert_here);
+out:
+ if (freereq)
+ blkdev_release_request(freereq);
+ spin_unlock_irq(&io_request_lock);
+ return 0;
+end_io:
+ bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
+ return 0;
+}
+
+/**
+ * generic_make_request: hand a buffer head to it's device driver for I/O
+ * @rw: READ, WRITE, or READA - what sort of I/O is desired.
+ * @bh: The buffer head describing the location in memory and on the device.
+ *
+ * generic_make_request() is used to make I/O requests of block
+ * devices. It is passed a &struct buffer_head and a &rw value. The
+ * %READ and %WRITE options are (hopefully) obvious in meaning. The
+ * %READA value means that a read is required, but that the driver is
+ * free to fail the request if, for example, it cannot get needed
+ * resources immediately.
+ *
+ * generic_make_request() does not return any status. The
+ * success/failure status of the request, along with notification of
+ * completion, is delivered asynchronously through the bh->b_end_io
+ * function described (one day) else where.
+ *
+ * The caller of generic_make_request must make sure that b_page,
+ * b_addr, b_size are set to describe the memory buffer, that b_rdev
+ * and b_rsector are set to describe the device address, and the
+ * b_end_io and optionally b_private are set to describe how
+ * completion notification should be signaled. BH_Mapped should also
+ * be set (to confirm that b_dev and b_blocknr are valid).
+ *
+ * generic_make_request and the drivers it calls may use b_reqnext,
+ * and may change b_rdev and b_rsector. So the values of these fields
+ * should NOT be depended on after the call to generic_make_request.
+ * Because of this, the caller should record the device address
+ * information in b_dev and b_blocknr.
+ *
+ * Apart from those fields mentioned above, no other fields, and in
+ * particular, no other flags, are changed by generic_make_request or
+ * any lower level drivers.
+ * */
+void generic_make_request (int rw, struct buffer_head * bh)
+{
+ int major = MAJOR(bh->b_rdev);
+ int minorsize = 0;
+ request_queue_t *q;
+
+ if (!bh->b_end_io)
+ BUG();
+
+ /* Test device size, when known. */
+ if (blk_size[major])
+ minorsize = blk_size[major][MINOR(bh->b_rdev)];
+ if (minorsize) {
+ unsigned long maxsector = (minorsize << 1) + 1;
+ unsigned long sector = bh->b_rsector;
+ unsigned int count = bh->b_size >> 9;
+
+ if (maxsector < count || maxsector - count < sector) {
+ /* Yecch */
+ bh->b_state &= (1 << BH_Lock) | (1 << BH_Mapped);
+
+ /* This may well happen - the kernel calls bread()
+ without checking the size of the device, e.g.,
+ when mounting a device. */
+ printk(KERN_INFO
+ "attempt to access beyond end of device\n");
+ printk(KERN_INFO "%s: rw=%d, want=%ld, limit=%d\n",
+ kdevname(bh->b_rdev), rw,
+ (sector + count)>>1, minorsize);
+
+ /* Yecch again */
+ bh->b_end_io(bh, 0);
+ return;
+ }
+ }
+
+ /*
+ * Resolve the mapping until finished. (drivers are
+ * still free to implement/resolve their own stacking
+ * by explicitly returning 0)
+ */
+ /* NOTE: we don't repeat the blk_size check for each new device.
+ * Stacking drivers are expected to know what they are doing.
+ */
+ do {
+ q = blk_get_queue(bh->b_rdev);
+ if (!q) {
+ printk(KERN_ERR
+ "generic_make_request: Trying to access "
+ "nonexistent block-device %s (%ld)\n",
+ kdevname(bh->b_rdev), bh->b_rsector);
+ buffer_IO_error(bh);
+ break;
+ }
+ } while (q->make_request_fn(q, rw, bh));
+}
+
+
+/**
+ * submit_bh: submit a buffer_head to the block device later for I/O
+ * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
+ * @bh: The &struct buffer_head which describes the I/O
+ *
+ * submit_bh() is very similar in purpose to generic_make_request(), and
+ * uses that function to do most of the work.
+ *
+ * The extra functionality provided by submit_bh is to determine
+ * b_rsector from b_blocknr and b_size, and to set b_rdev from b_dev.
+ * This is is appropriate for IO requests that come from the buffer
+ * cache and page cache which (currently) always use aligned blocks.
+ */
+void submit_bh(int rw, struct buffer_head * bh)
+{
+ int count = bh->b_size >> 9;
+
+ if (!test_bit(BH_Lock, &bh->b_state))
+ BUG();
+
+ set_bit(BH_Req, &bh->b_state);
+
+ /*
+ * First step, 'identity mapping' - RAID or LVM might
+ * further remap this.
+ */
+ bh->b_rdev = bh->b_dev;
+ bh->b_rsector = bh->b_blocknr * count;
+
+ generic_make_request(rw, bh);
+
+ switch (rw) {
+ case WRITE:
+ kstat.pgpgout += count;
+ break;
+ default:
+ kstat.pgpgin += count;
+ break;
+ }
+}
+
+/**
+ * ll_rw_block: low-level access to block devices
+ * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
+ * @nr: number of &struct buffer_heads in the array
+ * @bhs: array of pointers to &struct buffer_head
+ *
+ * ll_rw_block() takes an array of pointers to &struct buffer_heads,
+ * and requests an I/O operation on them, either a %READ or a %WRITE.
+ * The third %READA option is described in the documentation for
+ * generic_make_request() which ll_rw_block() calls.
+ *
+ * This function provides extra functionality that is not in
+ * generic_make_request() that is relevant to buffers in the buffer
+ * cache or page cache. In particular it drops any buffer that it
+ * cannot get a lock on (with the BH_Lock state bit), any buffer that
+ * appears to be clean when doing a write request, and any buffer that
+ * appears to be up-to-date when doing read request. Further it marks
+ * as clean buffers that are processed for writing (the buffer cache
+ * wont assume that they are actually clean until the buffer gets
+ * unlocked).
+ *
+ * ll_rw_block sets b_end_io to simple completion handler that marks
+ * the buffer up-to-date (if approriate), unlocks the buffer and wakes
+ * any waiters. As client that needs a more interesting completion
+ * routine should call submit_bh() (or generic_make_request())
+ * directly.
+ *
+ * Caveat:
+ * All of the buffers must be for the same device, and must also be
+ * of the current approved size for the device. */
+
+void ll_rw_block(int rw, int nr, struct buffer_head * bhs[])
+{
+ unsigned int major;
+ int correct_size;
+ int i;
+
+ if (!nr)
+ return;
+
+ major = MAJOR(bhs[0]->b_dev);
+
+ /* Determine correct block size for this device. */
+ correct_size = get_hardsect_size(bhs[0]->b_dev);
+
+ /* Verify requested block sizes. */
+ for (i = 0; i < nr; i++) {
+ struct buffer_head *bh = bhs[i];
+ if (bh->b_size % correct_size) {
+ printk(KERN_NOTICE "ll_rw_block: device %s: "
+ "only %d-char blocks implemented (%u)\n",
+ kdevname(bhs[0]->b_dev),
+ correct_size, bh->b_size);
+ goto sorry;
+ }
+ }
+
+ if ((rw & WRITE) && is_read_only(bhs[0]->b_dev)) {
+ printk(KERN_NOTICE "Can't write to read-only device %s\n",
+ kdevname(bhs[0]->b_dev));
+ goto sorry;
+ }
+
+ for (i = 0; i < nr; i++) {
+ struct buffer_head *bh = bhs[i];
+
+ /* Only one thread can actually submit the I/O. */
+ if (test_and_set_bit(BH_Lock, &bh->b_state))
+ continue;
+
+ /* We have the buffer lock */
+ atomic_inc(&bh->b_count);
+ bh->b_end_io = end_buffer_io_sync;
+
+ switch(rw) {
+ case WRITE:
+ if (!atomic_set_buffer_clean(bh))
+ /* Hmmph! Nothing to write */
+ goto end_io;
+ __mark_buffer_clean(bh);
+ break;
+
+ case READA:
+ case READ:
+ if (buffer_uptodate(bh))
+ /* Hmmph! Already have it */
+ goto end_io;
+ break;
+ default:
+ BUG();
+ end_io:
+ bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
+ continue;
+ }
+
+ submit_bh(rw, bh);
+ }
+ return;
+
+sorry:
+ /* Make sure we don't get infinite dirty retries.. */
+ for (i = 0; i < nr; i++)
+ mark_buffer_clean(bhs[i]);
+}
+
+#ifdef CONFIG_STRAM_SWAP
+extern int stram_device_init (void);
+#endif
+
+
+/**
+ * end_that_request_first - end I/O on one buffer.
+ * @req: the request being processed
+ * @uptodate: 0 for I/O error
+ * @name: the name printed for an I/O error
+ *
+ * Description:
+ * Ends I/O on the first buffer attached to @req, and sets it up
+ * for the next buffer_head (if any) in the cluster.
+ *
+ * Return:
+ * 0 - we are done with this request, call end_that_request_last()
+ * 1 - still buffers pending for this request
+ *
+ * Caveat:
+ * Drivers implementing their own end_request handling must call
+ * blk_finished_io() appropriately.
+ **/
+
+int end_that_request_first (struct request *req, int uptodate, char *name)
+{
+ struct buffer_head * bh;
+ int nsect;
+
+ req->errors = 0;
+ if (!uptodate)
+ printk("end_request: I/O error, dev %s (%s), sector %lu\n",
+ kdevname(req->rq_dev), name, req->sector);
+
+ if ((bh = req->bh) != NULL) {
+ nsect = bh->b_size >> 9;
+ blk_finished_io(nsect);
+ req->bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+ bh->b_end_io(bh, uptodate);
+ if ((bh = req->bh) != NULL) {
+ req->hard_sector += nsect;
+ req->hard_nr_sectors -= nsect;
+ req->sector = req->hard_sector;
+ req->nr_sectors = req->hard_nr_sectors;
+
+ req->current_nr_sectors = bh->b_size >> 9;
+ if (req->nr_sectors < req->current_nr_sectors) {
+ req->nr_sectors = req->current_nr_sectors;
+ printk("end_request: buffer-list destroyed\n");
+ }
+ req->buffer = bh->b_data;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+void end_that_request_last(struct request *req)
+{
+ if (req->waiting != NULL)
+ complete(req->waiting);
+
+ blkdev_release_request(req);
+}
+
+#define MB(kb) ((kb) << 10)
+
+int __init blk_dev_init(void)
+{
+ struct blk_dev_struct *dev;
+ int total_ram;
+
+ request_cachep = kmem_cache_create("blkdev_requests",
+ sizeof(struct request),
+ 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
+
+ if (!request_cachep)
+ panic("Can't create request pool slab cache\n");
+
+ for (dev = blk_dev + MAX_BLKDEV; dev-- != blk_dev;)
+ dev->queue = NULL;
+
+ memset(ro_bits,0,sizeof(ro_bits));
+ memset(max_readahead, 0, sizeof(max_readahead));
+ memset(max_sectors, 0, sizeof(max_sectors));
+
+ total_ram = nr_free_pages() << (PAGE_SHIFT - 10);
+
+ /*
+ * Free request slots per queue.
+ * (Half for reads, half for writes)
+ */
+ queue_nr_requests = 64;
+ if (total_ram > MB(32))
+ queue_nr_requests = 128;
+
+ /*
+ * Batch frees according to queue length
+ */
+ batch_requests = queue_nr_requests/4;
+ printk("block: %d slots per queue, batch=%d\n", queue_nr_requests, batch_requests);
+
+#ifdef CONFIG_AMIGA_Z2RAM
+ z2_init();
+#endif
+#ifdef CONFIG_STRAM_SWAP
+ stram_device_init();
+#endif
+#ifdef CONFIG_BLK_DEV_RAM
+ rd_init();
+#endif
+#ifdef CONFIG_ISP16_CDI
+ isp16_init();
+#endif
+#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_IDE)
+ ide_init(); /* this MUST precede hd_init */
+#endif
+#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_HD)
+ hd_init();
+#endif
+#ifdef CONFIG_BLK_DEV_PS2
+ ps2esdi_init();
+#endif
+#ifdef CONFIG_BLK_DEV_XD
+ xd_init();
+#endif
+#ifdef CONFIG_BLK_DEV_MFM
+ mfm_init();
+#endif
+#ifdef CONFIG_PARIDE
+ { extern void paride_init(void); paride_init(); };
+#endif
+#ifdef CONFIG_MAC_FLOPPY
+ swim3_init();
+#endif
+#ifdef CONFIG_BLK_DEV_SWIM_IOP
+ swimiop_init();
+#endif
+#ifdef CONFIG_AMIGA_FLOPPY
+ amiga_floppy_init();
+#endif
+#ifdef CONFIG_ATARI_FLOPPY
+ atari_floppy_init();
+#endif
+#ifdef CONFIG_BLK_DEV_FD
+ floppy_init();
+#else
+#if defined(__i386__) && !defined(CONFIG_XENO) /* Do we even need this? */
+ outb_p(0xc, 0x3f2);
+#endif
+#endif
+#ifdef CONFIG_CDU31A
+ cdu31a_init();
+#endif
+#ifdef CONFIG_ATARI_ACSI
+ acsi_init();
+#endif
+#ifdef CONFIG_MCD
+ mcd_init();
+#endif
+#ifdef CONFIG_MCDX
+ mcdx_init();
+#endif
+#ifdef CONFIG_SBPCD
+ sbpcd_init();
+#endif
+#ifdef CONFIG_AZTCD
+ aztcd_init();
+#endif
+#ifdef CONFIG_CDU535
+ sony535_init();
+#endif
+#ifdef CONFIG_GSCD
+ gscd_init();
+#endif
+#ifdef CONFIG_CM206
+ cm206_init();
+#endif
+#ifdef CONFIG_OPTCD
+ optcd_init();
+#endif
+#ifdef CONFIG_SJCD
+ sjcd_init();
+#endif
+#ifdef CONFIG_APBLOCK
+ ap_init();
+#endif
+#ifdef CONFIG_DDV
+ ddv_init();
+#endif
+#ifdef CONFIG_MDISK
+ mdisk_init();
+#endif
+#ifdef CONFIG_DASD
+ dasd_init();
+#endif
+#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_BLOCK)
+ tapeblock_init();
+#endif
+#ifdef CONFIG_BLK_DEV_XPRAM
+ xpram_init();
+#endif
+
+#ifdef CONFIG_SUN_JSFLASH
+ jsfd_init();
+#endif
+
+#ifdef CONFIG_XENOLINUX_BLOCK
+ xlblk_init();
+#endif
+
+ return 0;
+};
+
+EXPORT_SYMBOL(io_request_lock);
+EXPORT_SYMBOL(end_that_request_first);
+EXPORT_SYMBOL(end_that_request_last);
+EXPORT_SYMBOL(blk_init_queue);
+EXPORT_SYMBOL(blk_get_queue);
+EXPORT_SYMBOL(blk_cleanup_queue);
+EXPORT_SYMBOL(blk_queue_headactive);
+EXPORT_SYMBOL(blk_queue_make_request);
+EXPORT_SYMBOL(generic_make_request);
+EXPORT_SYMBOL(blkdev_release_request);
+EXPORT_SYMBOL(generic_unplug_device);
--- /dev/null
+/*
+ * ramdisk.c - Multiple RAM disk driver - gzip-loading version - v. 0.8 beta.
+ *
+ * (C) Chad Page, Theodore Ts'o, et. al, 1995.
+ *
+ * This RAM disk is designed to have filesystems created on it and mounted
+ * just like a regular floppy disk.
+ *
+ * It also does something suggested by Linus: use the buffer cache as the
+ * RAM disk data. This makes it possible to dynamically allocate the RAM disk
+ * buffer - with some consequences I have to deal with as I write this.
+ *
+ * This code is based on the original ramdisk.c, written mostly by
+ * Theodore Ts'o (TYT) in 1991. The code was largely rewritten by
+ * Chad Page to use the buffer cache to store the RAM disk data in
+ * 1995; Theodore then took over the driver again, and cleaned it up
+ * for inclusion in the mainline kernel.
+ *
+ * The original CRAMDISK code was written by Richard Lyons, and
+ * adapted by Chad Page to use the new RAM disk interface. Theodore
+ * Ts'o rewrote it so that both the compressed RAM disk loader and the
+ * kernel decompressor uses the same inflate.c codebase. The RAM disk
+ * loader now also loads into a dynamic (buffer cache based) RAM disk,
+ * not the old static RAM disk. Support for the old static RAM disk has
+ * been completely removed.
+ *
+ * Loadable module support added by Tom Dyas.
+ *
+ * Further cleanups by Chad Page (page0588@sundance.sjsu.edu):
+ * Cosmetic changes in #ifdef MODULE, code movement, etc.
+ * When the RAM disk module is removed, free the protected buffers
+ * Default RAM disk size changed to 2.88 MB
+ *
+ * Added initrd: Werner Almesberger & Hans Lermen, Feb '96
+ *
+ * 4/25/96 : Made RAM disk size a parameter (default is now 4 MB)
+ * - Chad Page
+ *
+ * Add support for fs images split across >1 disk, Paul Gortmaker, Mar '98
+ *
+ * Make block size and block size shift for RAM disks a global macro
+ * and set blk_size for -ENOSPC, Werner Fink <werner@suse.de>, Apr '99
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/minix_fs.h>
+#include <linux/ext2_fs.h>
+#include <linux/romfs_fs.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/hdreg.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/ioctl.h>
+#include <linux/fd.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/devfs_fs_kernel.h>
+#include <linux/smp_lock.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/byteorder.h>
+
+extern void wait_for_keypress(void);
+
+/*
+ * 35 has been officially registered as the RAMDISK major number, but
+ * so is the original MAJOR number of 1. We're using 1 in
+ * include/linux/major.h for now
+ */
+#define MAJOR_NR RAMDISK_MAJOR
+#include <linux/blk.h>
+#include <linux/blkpg.h>
+
+/* The RAM disk size is now a parameter */
+#define NUM_RAMDISKS 16 /* This cannot be overridden (yet) */
+
+#ifndef MODULE
+/* We don't have to load RAM disks or gunzip them in a module. */
+#define RD_LOADER
+#define BUILD_CRAMDISK
+
+void rd_load(void);
+static int crd_load(struct file *fp, struct file *outfp);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static int initrd_users;
+#endif
+#endif
+
+/* Various static variables go here. Most are used only in the RAM disk code.
+ */
+
+static unsigned long rd_length[NUM_RAMDISKS]; /* Size of RAM disks in bytes */
+static int rd_hardsec[NUM_RAMDISKS]; /* Size of real blocks in bytes */
+static int rd_blocksizes[NUM_RAMDISKS]; /* Size of 1024 byte blocks :) */
+static int rd_kbsize[NUM_RAMDISKS]; /* Size in blocks of 1024 bytes */
+static devfs_handle_t devfs_handle;
+static struct block_device *rd_bdev[NUM_RAMDISKS];/* Protected device data */
+
+/*
+ * Parameters for the boot-loading of the RAM disk. These are set by
+ * init/main.c (from arguments to the kernel command line) or from the
+ * architecture-specific setup routine (from the stored boot sector
+ * information).
+ */
+int rd_size = CONFIG_BLK_DEV_RAM_SIZE; /* Size of the RAM disks */
+/*
+ * It would be very desiderable to have a soft-blocksize (that in the case
+ * of the ramdisk driver is also the hardblocksize ;) of PAGE_SIZE because
+ * doing that we'll achieve a far better MM footprint. Using a rd_blocksize of
+ * BLOCK_SIZE in the worst case we'll make PAGE_SIZE/BLOCK_SIZE buffer-pages
+ * unfreeable. With a rd_blocksize of PAGE_SIZE instead we are sure that only
+ * 1 page will be protected. Depending on the size of the ramdisk you
+ * may want to change the ramdisk blocksize to achieve a better or worse MM
+ * behaviour. The default is still BLOCK_SIZE (needed by rd_load_image that
+ * supposes the filesystem in the image uses a BLOCK_SIZE blocksize).
+ */
+int rd_blocksize = BLOCK_SIZE; /* blocksize of the RAM disks */
+
+#ifndef MODULE
+
+int rd_doload; /* 1 = load RAM disk, 0 = don't load */
+int rd_prompt = 1; /* 1 = prompt for RAM disk, 0 = don't prompt */
+int rd_image_start; /* starting block # of image */
+#ifdef CONFIG_BLK_DEV_INITRD
+unsigned long initrd_start, initrd_end;
+int mount_initrd = 1; /* zero if initrd should not be mounted */
+int initrd_below_start_ok;
+
+static int __init no_initrd(char *str)
+{
+ mount_initrd = 0;
+ return 1;
+}
+
+__setup("noinitrd", no_initrd);
+
+#endif
+
+static int __init ramdisk_start_setup(char *str)
+{
+ rd_image_start = simple_strtol(str,NULL,0);
+ return 1;
+}
+
+static int __init load_ramdisk(char *str)
+{
+ rd_doload = simple_strtol(str,NULL,0) & 3;
+ return 1;
+}
+
+static int __init prompt_ramdisk(char *str)
+{
+ rd_prompt = simple_strtol(str,NULL,0) & 1;
+ return 1;
+}
+
+static int __init ramdisk_size(char *str)
+{
+ rd_size = simple_strtol(str,NULL,0);
+ return 1;
+}
+
+static int __init ramdisk_size2(char *str)
+{
+ return ramdisk_size(str);
+}
+
+static int __init ramdisk_blocksize(char *str)
+{
+ rd_blocksize = simple_strtol(str,NULL,0);
+ return 1;
+}
+
+__setup("ramdisk_start=", ramdisk_start_setup);
+__setup("load_ramdisk=", load_ramdisk);
+__setup("prompt_ramdisk=", prompt_ramdisk);
+__setup("ramdisk=", ramdisk_size);
+__setup("ramdisk_size=", ramdisk_size2);
+__setup("ramdisk_blocksize=", ramdisk_blocksize);
+
+#endif
+
+/*
+ * Copyright (C) 2000 Linus Torvalds.
+ * 2000 Transmeta Corp.
+ * aops copied from ramfs.
+ */
+static int ramdisk_readpage(struct file *file, struct page * page)
+{
+ if (!Page_Uptodate(page)) {
+ memset(kmap(page), 0, PAGE_CACHE_SIZE);
+ kunmap(page);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ }
+ UnlockPage(page);
+ return 0;
+}
+
+static int ramdisk_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+{
+ if (!Page_Uptodate(page)) {
+ void *addr = page_address(page);
+ memset(addr, 0, PAGE_CACHE_SIZE);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ }
+ SetPageDirty(page);
+ return 0;
+}
+
+static int ramdisk_commit_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+{
+ return 0;
+}
+
+static struct address_space_operations ramdisk_aops = {
+ readpage: ramdisk_readpage,
+ writepage: fail_writepage,
+ prepare_write: ramdisk_prepare_write,
+ commit_write: ramdisk_commit_write,
+};
+
+static int rd_blkdev_pagecache_IO(int rw, struct buffer_head * sbh, int minor)
+{
+ struct address_space * mapping;
+ unsigned long index;
+ int offset, size, err;
+
+ err = -EIO;
+ err = 0;
+ mapping = rd_bdev[minor]->bd_inode->i_mapping;
+
+ index = sbh->b_rsector >> (PAGE_CACHE_SHIFT - 9);
+ offset = (sbh->b_rsector << 9) & ~PAGE_CACHE_MASK;
+ size = sbh->b_size;
+
+ do {
+ int count;
+ struct page ** hash;
+ struct page * page;
+ char * src, * dst;
+ int unlock = 0;
+
+ count = PAGE_CACHE_SIZE - offset;
+ if (count > size)
+ count = size;
+ size -= count;
+
+ hash = page_hash(mapping, index);
+ page = __find_get_page(mapping, index, hash);
+ if (!page) {
+ page = grab_cache_page(mapping, index);
+ err = -ENOMEM;
+ if (!page)
+ goto out;
+ err = 0;
+
+ if (!Page_Uptodate(page)) {
+ memset(kmap(page), 0, PAGE_CACHE_SIZE);
+ kunmap(page);
+ SetPageUptodate(page);
+ }
+
+ unlock = 1;
+ }
+
+ index++;
+
+ if (rw == READ) {
+ src = kmap(page);
+ src += offset;
+ dst = bh_kmap(sbh);
+ } else {
+ dst = kmap(page);
+ dst += offset;
+ src = bh_kmap(sbh);
+ }
+ offset = 0;
+
+ memcpy(dst, src, count);
+
+ kunmap(page);
+ bh_kunmap(sbh);
+
+ if (rw == READ) {
+ flush_dcache_page(page);
+ } else {
+ SetPageDirty(page);
+ }
+ if (unlock)
+ UnlockPage(page);
+ __free_page(page);
+ } while (size);
+
+ out:
+ return err;
+}
+
+/*
+ * Basically, my strategy here is to set up a buffer-head which can't be
+ * deleted, and make that my Ramdisk. If the request is outside of the
+ * allocated size, we must get rid of it...
+ *
+ * 19-JAN-1998 Richard Gooch <rgooch@atnf.csiro.au> Added devfs support
+ *
+ */
+static int rd_make_request(request_queue_t * q, int rw, struct buffer_head *sbh)
+{
+ unsigned int minor;
+ unsigned long offset, len;
+
+ minor = MINOR(sbh->b_rdev);
+
+ if (minor >= NUM_RAMDISKS)
+ goto fail;
+
+
+ offset = sbh->b_rsector << 9;
+ len = sbh->b_size;
+
+ if ((offset + len) > rd_length[minor])
+ goto fail;
+
+ if (rw==READA)
+ rw=READ;
+ if ((rw != READ) && (rw != WRITE)) {
+ printk(KERN_INFO "RAMDISK: bad command: %d\n", rw);
+ goto fail;
+ }
+
+ if (rd_blkdev_pagecache_IO(rw, sbh, minor))
+ goto fail;
+
+ sbh->b_end_io(sbh,1);
+ return 0;
+ fail:
+ sbh->b_end_io(sbh,0);
+ return 0;
+}
+
+static int rd_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg)
+{
+ int error = -EINVAL;
+ unsigned int minor;
+
+ if (!inode || !inode->i_rdev)
+ goto out;
+
+ minor = MINOR(inode->i_rdev);
+
+ switch (cmd) {
+ case BLKFLSBUF:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ /* special: we want to release the ramdisk memory,
+ it's not like with the other blockdevices where
+ this ioctl only flushes away the buffer cache. */
+ error = -EBUSY;
+ down(&inode->i_bdev->bd_sem);
+ if (inode->i_bdev->bd_openers <= 2) {
+ truncate_inode_pages(inode->i_mapping, 0);
+ error = 0;
+ }
+ up(&inode->i_bdev->bd_sem);
+ break;
+ case BLKGETSIZE: /* Return device size */
+ if (!arg)
+ break;
+ error = put_user(rd_kbsize[minor] << 1, (unsigned long *) arg);
+ break;
+ case BLKGETSIZE64:
+ error = put_user((u64)rd_kbsize[minor]<<10, (u64*)arg);
+ break;
+ case BLKROSET:
+ case BLKROGET:
+ case BLKSSZGET:
+ error = blk_ioctl(inode->i_rdev, cmd, arg);
+ };
+out:
+ return error;
+}
+
+
+#ifdef CONFIG_BLK_DEV_INITRD
+
+static ssize_t initrd_read(struct file *file, char *buf,
+ size_t count, loff_t *ppos)
+{
+ int left;
+
+ left = initrd_end - initrd_start - *ppos;
+ if (count > left) count = left;
+ if (count == 0) return 0;
+ copy_to_user(buf, (char *)initrd_start + *ppos, count);
+ *ppos += count;
+ return count;
+}
+
+
+static int initrd_release(struct inode *inode,struct file *file)
+{
+ extern void free_initrd_mem(unsigned long, unsigned long);
+
+ lock_kernel();
+ if (!--initrd_users) {
+ free_initrd_mem(initrd_start, initrd_end);
+ initrd_start = 0;
+ }
+ unlock_kernel();
+ blkdev_put(inode->i_bdev, BDEV_FILE);
+ return 0;
+}
+
+
+static struct file_operations initrd_fops = {
+ read: initrd_read,
+ release: initrd_release,
+};
+
+#endif
+
+
+static int rd_open(struct inode * inode, struct file * filp)
+{
+ int unit = DEVICE_NR(inode->i_rdev);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (unit == INITRD_MINOR) {
+ if (!initrd_start) return -ENODEV;
+ initrd_users++;
+ filp->f_op = &initrd_fops;
+ return 0;
+ }
+#endif
+
+ if (unit >= NUM_RAMDISKS)
+ return -ENXIO;
+
+ /*
+ * Immunize device against invalidate_buffers() and prune_icache().
+ */
+ if (rd_bdev[unit] == NULL) {
+ rd_bdev[unit] = bdget(kdev_t_to_nr(inode->i_rdev));
+ rd_bdev[unit]->bd_openers++;
+ rd_bdev[unit]->bd_inode->i_mapping->a_ops = &ramdisk_aops;
+ }
+
+ return 0;
+}
+
+static struct block_device_operations rd_bd_op = {
+ owner: THIS_MODULE,
+ open: rd_open,
+ ioctl: rd_ioctl,
+};
+
+#ifdef MODULE
+/* Before freeing the module, invalidate all of the protected buffers! */
+static void __exit rd_cleanup (void)
+{
+ int i;
+
+ for (i = 0 ; i < NUM_RAMDISKS; i++) {
+ struct block_device *bdev = rd_bdev[i];
+ rd_bdev[i] = NULL;
+ if (bdev)
+ blkdev_put(bdev, BDEV_FILE);
+ destroy_buffers(MKDEV(MAJOR_NR, i));
+ }
+
+ devfs_unregister (devfs_handle);
+ unregister_blkdev( MAJOR_NR, "ramdisk" );
+ hardsect_size[MAJOR_NR] = NULL;
+ blksize_size[MAJOR_NR] = NULL;
+ blk_size[MAJOR_NR] = NULL;
+}
+#endif
+
+/* This is the registration and initialization section of the RAM disk driver */
+int __init rd_init (void)
+{
+ int i;
+
+ if (rd_blocksize > PAGE_SIZE || rd_blocksize < 512 ||
+ (rd_blocksize & (rd_blocksize-1)))
+ {
+ printk("RAMDISK: wrong blocksize %d, reverting to defaults\n",
+ rd_blocksize);
+ rd_blocksize = BLOCK_SIZE;
+ }
+
+ if (register_blkdev(MAJOR_NR, "ramdisk", &rd_bd_op)) {
+ printk("RAMDISK: Could not get major %d", MAJOR_NR);
+ return -EIO;
+ }
+
+ blk_queue_make_request(BLK_DEFAULT_QUEUE(MAJOR_NR), &rd_make_request);
+
+ for (i = 0; i < NUM_RAMDISKS; i++) {
+ /* rd_size is given in kB */
+ rd_length[i] = rd_size << 10;
+ rd_hardsec[i] = rd_blocksize;
+ rd_blocksizes[i] = rd_blocksize;
+ rd_kbsize[i] = rd_size;
+ }
+ devfs_handle = devfs_mk_dir (NULL, "rd", NULL);
+ devfs_register_series (devfs_handle, "%u", NUM_RAMDISKS,
+ DEVFS_FL_DEFAULT, MAJOR_NR, 0,
+ S_IFBLK | S_IRUSR | S_IWUSR,
+ &rd_bd_op, NULL);
+
+ for (i = 0; i < NUM_RAMDISKS; i++)
+ register_disk(NULL, MKDEV(MAJOR_NR,i), 1, &rd_bd_op, rd_size<<1);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ /* We ought to separate initrd operations here */
+ register_disk(NULL, MKDEV(MAJOR_NR,INITRD_MINOR), 1, &rd_bd_op, rd_size<<1);
+#endif
+
+ hardsect_size[MAJOR_NR] = rd_hardsec; /* Size of the RAM disk blocks */
+ blksize_size[MAJOR_NR] = rd_blocksizes; /* Avoid set_blocksize() check */
+ blk_size[MAJOR_NR] = rd_kbsize; /* Size of the RAM disk in kB */
+
+ /* rd_size is given in kB */
+ printk("RAMDISK driver initialized: "
+ "%d RAM disks of %dK size %d blocksize\n",
+ NUM_RAMDISKS, rd_size, rd_blocksize);
+
+ return 0;
+}
+
+#ifdef MODULE
+module_init(rd_init);
+module_exit(rd_cleanup);
+#endif
+
+/* loadable module support */
+MODULE_PARM (rd_size, "1i");
+MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
+MODULE_PARM (rd_blocksize, "i");
+MODULE_PARM_DESC(rd_blocksize, "Blocksize of each RAM disk in bytes.");
+
+MODULE_LICENSE("GPL");
+
+/* End of non-loading portions of the RAM disk driver */
+
+#ifdef RD_LOADER
+/*
+ * This routine tries to find a RAM disk image to load, and returns the
+ * number of blocks to read for a non-compressed image, 0 if the image
+ * is a compressed image, and -1 if an image with the right magic
+ * numbers could not be found.
+ *
+ * We currently check for the following magic numbers:
+ * minix
+ * ext2
+ * romfs
+ * gzip
+ */
+static int __init
+identify_ramdisk_image(kdev_t device, struct file *fp, int start_block)
+{
+ const int size = 512;
+ struct minix_super_block *minixsb;
+ struct ext2_super_block *ext2sb;
+ struct romfs_super_block *romfsb;
+ int nblocks = -1;
+ unsigned char *buf;
+
+ buf = kmalloc(size, GFP_KERNEL);
+ if (buf == 0)
+ return -1;
+
+ minixsb = (struct minix_super_block *) buf;
+ ext2sb = (struct ext2_super_block *) buf;
+ romfsb = (struct romfs_super_block *) buf;
+ memset(buf, 0xe5, size);
+
+ /*
+ * Read block 0 to test for gzipped kernel
+ */
+ if (fp->f_op->llseek)
+ fp->f_op->llseek(fp, start_block * BLOCK_SIZE, 0);
+ fp->f_pos = start_block * BLOCK_SIZE;
+
+ fp->f_op->read(fp, buf, size, &fp->f_pos);
+
+ /*
+ * If it matches the gzip magic numbers, return -1
+ */
+ if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) {
+ printk(KERN_NOTICE
+ "RAMDISK: Compressed image found at block %d\n",
+ start_block);
+ nblocks = 0;
+ goto done;
+ }
+
+ /* romfs is at block zero too */
+ if (romfsb->word0 == ROMSB_WORD0 &&
+ romfsb->word1 == ROMSB_WORD1) {
+ printk(KERN_NOTICE
+ "RAMDISK: romfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ /*
+ * Read block 1 to test for minix and ext2 superblock
+ */
+ if (fp->f_op->llseek)
+ fp->f_op->llseek(fp, (start_block+1) * BLOCK_SIZE, 0);
+ fp->f_pos = (start_block+1) * BLOCK_SIZE;
+
+ fp->f_op->read(fp, buf, size, &fp->f_pos);
+
+ /* Try minix */
+ if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
+ minixsb->s_magic == MINIX_SUPER_MAGIC2) {
+ printk(KERN_NOTICE
+ "RAMDISK: Minix filesystem found at block %d\n",
+ start_block);
+ nblocks = minixsb->s_nzones << minixsb->s_log_zone_size;
+ goto done;
+ }
+
+ /* Try ext2 */
+ if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) {
+ printk(KERN_NOTICE
+ "RAMDISK: ext2 filesystem found at block %d\n",
+ start_block);
+ nblocks = le32_to_cpu(ext2sb->s_blocks_count);
+ goto done;
+ }
+
+ printk(KERN_NOTICE
+ "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
+ start_block);
+
+done:
+ if (fp->f_op->llseek)
+ fp->f_op->llseek(fp, start_block * BLOCK_SIZE, 0);
+ fp->f_pos = start_block * BLOCK_SIZE;
+
+ kfree(buf);
+ return nblocks;
+}
+
+/*
+ * This routine loads in the RAM disk image.
+ */
+static void __init rd_load_image(kdev_t device, int offset, int unit)
+{
+ struct inode *inode, *out_inode;
+ struct file infile, outfile;
+ struct dentry in_dentry, out_dentry;
+ mm_segment_t fs;
+ kdev_t ram_device;
+ int nblocks, i;
+ char *buf;
+ unsigned short rotate = 0;
+ unsigned short devblocks = 0;
+#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES) && !defined(CONFIG_XENO)
+ char rotator[4] = { '|' , '/' , '-' , '\\' };
+#endif
+ ram_device = MKDEV(MAJOR_NR, unit);
+
+ if ((inode = get_empty_inode()) == NULL)
+ return;
+ memset(&infile, 0, sizeof(infile));
+ memset(&in_dentry, 0, sizeof(in_dentry));
+ infile.f_mode = 1; /* read only */
+ infile.f_dentry = &in_dentry;
+ in_dentry.d_inode = inode;
+ infile.f_op = &def_blk_fops;
+ init_special_inode(inode, S_IFBLK | S_IRUSR, kdev_t_to_nr(device));
+
+ if ((out_inode = get_empty_inode()) == NULL)
+ goto free_inode;
+ memset(&outfile, 0, sizeof(outfile));
+ memset(&out_dentry, 0, sizeof(out_dentry));
+ outfile.f_mode = 3; /* read/write */
+ outfile.f_dentry = &out_dentry;
+ out_dentry.d_inode = out_inode;
+ outfile.f_op = &def_blk_fops;
+ init_special_inode(out_inode, S_IFBLK | S_IRUSR | S_IWUSR, kdev_t_to_nr(ram_device));
+
+ if (blkdev_open(inode, &infile) != 0) {
+ iput(out_inode);
+ goto free_inode;
+ }
+ if (blkdev_open(out_inode, &outfile) != 0)
+ goto free_inodes;
+
+ fs = get_fs();
+ set_fs(KERNEL_DS);
+
+ nblocks = identify_ramdisk_image(device, &infile, offset);
+ if (nblocks < 0)
+ goto done;
+
+ if (nblocks == 0) {
+#ifdef BUILD_CRAMDISK
+ if (crd_load(&infile, &outfile) == 0)
+ goto successful_load;
+#else
+ printk(KERN_NOTICE
+ "RAMDISK: Kernel does not support compressed "
+ "RAM disk images\n");
+#endif
+ goto done;
+ }
+
+ /*
+ * NOTE NOTE: nblocks suppose that the blocksize is BLOCK_SIZE, so
+ * rd_load_image will work only with filesystem BLOCK_SIZE wide!
+ * So make sure to use 1k blocksize while generating ext2fs
+ * ramdisk-images.
+ */
+ if (nblocks > (rd_length[unit] >> BLOCK_SIZE_BITS)) {
+ printk("RAMDISK: image too big! (%d/%ld blocks)\n",
+ nblocks, rd_length[unit] >> BLOCK_SIZE_BITS);
+ goto done;
+ }
+
+ /*
+ * OK, time to copy in the data
+ */
+ buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
+ if (buf == 0) {
+ printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
+ goto done;
+ }
+
+ if (blk_size[MAJOR(device)])
+ devblocks = blk_size[MAJOR(device)][MINOR(device)];
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (MAJOR(device) == MAJOR_NR && MINOR(device) == INITRD_MINOR)
+ devblocks = nblocks;
+#endif
+
+ if (devblocks == 0) {
+ printk(KERN_ERR "RAMDISK: could not determine device size\n");
+ goto done;
+ }
+
+ printk(KERN_NOTICE "RAMDISK: Loading %d blocks [%d disk%s] into ram disk... ",
+ nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
+ for (i=0; i < nblocks; i++) {
+ if (i && (i % devblocks == 0)) {
+ printk("done disk #%d.\n", i/devblocks);
+ rotate = 0;
+ if (infile.f_op->release(inode, &infile) != 0) {
+ printk("Error closing the disk.\n");
+ goto noclose_input;
+ }
+ printk("Please insert disk #%d and press ENTER\n", i/devblocks+1);
+ wait_for_keypress();
+ if (blkdev_open(inode, &infile) != 0) {
+ printk("Error opening disk.\n");
+ goto noclose_input;
+ }
+ infile.f_pos = 0;
+ printk("Loading disk #%d... ", i/devblocks+1);
+ }
+ infile.f_op->read(&infile, buf, BLOCK_SIZE, &infile.f_pos);
+ outfile.f_op->write(&outfile, buf, BLOCK_SIZE, &outfile.f_pos);
+#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES) && !defined(CONFIG_XENO)
+ if (!(i % 16)) {
+ printk("%c\b", rotator[rotate & 0x3]);
+ rotate++;
+ }
+#endif
+ }
+ printk("done.\n");
+ kfree(buf);
+
+successful_load:
+ ROOT_DEV = MKDEV(MAJOR_NR, unit);
+ if (ROOT_DEVICE_NAME != NULL) strcpy (ROOT_DEVICE_NAME, "rd/0");
+
+done:
+ infile.f_op->release(inode, &infile);
+noclose_input:
+ blkdev_close(out_inode, &outfile);
+ iput(inode);
+ iput(out_inode);
+ set_fs(fs);
+ return;
+free_inodes: /* free inodes on error */
+ iput(out_inode);
+ infile.f_op->release(inode, &infile);
+free_inode:
+ iput(inode);
+}
+
+#ifdef CONFIG_MAC_FLOPPY
+int swim3_fd_eject(int devnum);
+#endif
+
+static void __init rd_load_disk(int n)
+{
+
+ if (rd_doload == 0)
+ return;
+
+ if (MAJOR(ROOT_DEV) != FLOPPY_MAJOR
+#ifdef CONFIG_BLK_DEV_INITRD
+ && MAJOR(real_root_dev) != FLOPPY_MAJOR
+#endif
+ )
+ return;
+
+ if (rd_prompt) {
+#ifdef CONFIG_BLK_DEV_FD
+ floppy_eject();
+#endif
+#ifdef CONFIG_MAC_FLOPPY
+ if(MAJOR(ROOT_DEV) == FLOPPY_MAJOR)
+ swim3_fd_eject(MINOR(ROOT_DEV));
+ else if(MAJOR(real_root_dev) == FLOPPY_MAJOR)
+ swim3_fd_eject(MINOR(real_root_dev));
+#endif
+ printk(KERN_NOTICE
+ "VFS: Insert root floppy disk to be loaded into RAM disk and press ENTER\n");
+ wait_for_keypress();
+ }
+
+ rd_load_image(ROOT_DEV,rd_image_start, n);
+
+}
+
+void __init rd_load(void)
+{
+ rd_load_disk(0);
+}
+
+void __init rd_load_secondary(void)
+{
+ rd_load_disk(1);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init initrd_load(void)
+{
+ rd_load_image(MKDEV(MAJOR_NR, INITRD_MINOR),rd_image_start,0);
+}
+#endif
+
+#endif /* RD_LOADER */
+
+#ifdef BUILD_CRAMDISK
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args) args
+
+#ifndef memzero
+#define memzero(s, n) memset ((s), 0, (n))
+#endif
+
+typedef unsigned char uch;
+typedef unsigned short ush;
+typedef unsigned long ulg;
+
+#define INBUFSIZ 4096
+#define WSIZE 0x8000 /* window size--must be a power of two, and */
+ /* at least 32K for zip's deflate method */
+
+static uch *inbuf;
+static uch *window;
+
+static unsigned insize; /* valid bytes in inbuf */
+static unsigned inptr; /* index of next byte to be processed in inbuf */
+static unsigned outcnt; /* bytes in output buffer */
+static int exit_code;
+static long bytes_out;
+static struct file *crd_infp, *crd_outfp;
+
+#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+
+/* Diagnostic functions (stubbed out) */
+#define Assert(cond,msg)
+#define Trace(x)
+#define Tracev(x)
+#define Tracevv(x)
+#define Tracec(c,x)
+#define Tracecv(c,x)
+
+#define STATIC static
+
+static int fill_inbuf(void);
+static void flush_window(void);
+static void *malloc(int size);
+static void free(void *where);
+static void error(char *m);
+static void gzip_mark(void **);
+static void gzip_release(void **);
+
+#include "../../lib/inflate.c"
+
+static void __init *malloc(int size)
+{
+ return kmalloc(size, GFP_KERNEL);
+}
+
+static void __init free(void *where)
+{
+ kfree(where);
+}
+
+static void __init gzip_mark(void **ptr)
+{
+}
+
+static void __init gzip_release(void **ptr)
+{
+}
+
+
+/* ===========================================================================
+ * Fill the input buffer. This is called only when the buffer is empty
+ * and at least one byte is really needed.
+ */
+static int __init fill_inbuf(void)
+{
+ if (exit_code) return -1;
+
+ insize = crd_infp->f_op->read(crd_infp, inbuf, INBUFSIZ,
+ &crd_infp->f_pos);
+ if (insize == 0) return -1;
+
+ inptr = 1;
+
+ return inbuf[0];
+}
+
+/* ===========================================================================
+ * Write the output window window[0..outcnt-1] and update crc and bytes_out.
+ * (Used for the decompressed data only.)
+ */
+static void __init flush_window(void)
+{
+ ulg c = crc; /* temporary variable */
+ unsigned n;
+ uch *in, ch;
+
+ crd_outfp->f_op->write(crd_outfp, window, outcnt, &crd_outfp->f_pos);
+ in = window;
+ for (n = 0; n < outcnt; n++) {
+ ch = *in++;
+ c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
+ }
+ crc = c;
+ bytes_out += (ulg)outcnt;
+ outcnt = 0;
+}
+
+static void __init error(char *x)
+{
+ printk(KERN_ERR "%s", x);
+ exit_code = 1;
+}
+
+static int __init
+crd_load(struct file * fp, struct file *outfp)
+{
+ int result;
+
+ insize = 0; /* valid bytes in inbuf */
+ inptr = 0; /* index of next byte to be processed in inbuf */
+ outcnt = 0; /* bytes in output buffer */
+ exit_code = 0;
+ bytes_out = 0;
+ crc = (ulg)0xffffffffL; /* shift register contents */
+
+ crd_infp = fp;
+ crd_outfp = outfp;
+ inbuf = kmalloc(INBUFSIZ, GFP_KERNEL);
+ if (inbuf == 0) {
+ printk(KERN_ERR "RAMDISK: Couldn't allocate gzip buffer\n");
+ return -1;
+ }
+ window = kmalloc(WSIZE, GFP_KERNEL);
+ if (window == 0) {
+ printk(KERN_ERR "RAMDISK: Couldn't allocate gzip window\n");
+ kfree(inbuf);
+ return -1;
+ }
+ makecrc();
+ result = gunzip();
+ kfree(inbuf);
+ kfree(window);
+ return result;
+}
+
+#endif /* BUILD_CRAMDISK */
+
--- /dev/null
+/*
+ * linux/drivers/char/tty_io.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles
+ * or rs-channels. It also implements echoing, cooked mode etc.
+ *
+ * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0.
+ *
+ * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the
+ * tty_struct and tty_queue structures. Previously there was an array
+ * of 256 tty_struct's which was statically allocated, and the
+ * tty_queue structures were allocated at boot time. Both are now
+ * dynamically allocated only when the tty is open.
+ *
+ * Also restructured routines so that there is more of a separation
+ * between the high-level tty routines (tty_io.c and tty_ioctl.c) and
+ * the low-level tty routines (serial.c, pty.c, console.c). This
+ * makes for cleaner and more compact code. -TYT, 9/17/92
+ *
+ * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines
+ * which can be dynamically activated and de-activated by the line
+ * discipline handling modules (like SLIP).
+ *
+ * NOTE: pay no attention to the line discipline code (yet); its
+ * interface is still subject to change in this version...
+ * -- TYT, 1/31/92
+ *
+ * Added functionality to the OPOST tty handling. No delays, but all
+ * other bits should be there.
+ * -- Nick Holloway <alfie@dcs.warwick.ac.uk>, 27th May 1993.
+ *
+ * Rewrote canonical mode and added more termios flags.
+ * -- julian@uhunix.uhcc.hawaii.edu (J. Cowley), 13Jan94
+ *
+ * Reorganized FASYNC support so mouse code can share it.
+ * -- ctm@ardi.com, 9Sep95
+ *
+ * New TIOCLINUX variants added.
+ * -- mj@k332.feld.cvut.cz, 19-Nov-95
+ *
+ * Restrict vt switching via ioctl()
+ * -- grif@cs.ucr.edu, 5-Dec-95
+ *
+ * Move console and virtual terminal code to more appropriate files,
+ * implement CONFIG_VT and generalize console device interface.
+ * -- Marko Kohtala <Marko.Kohtala@hut.fi>, March 97
+ *
+ * Rewrote init_dev and release_dev to eliminate races.
+ * -- Bill Hawes <whawes@star.net>, June 97
+ *
+ * Added devfs support.
+ * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 13-Jan-1998
+ *
+ * Added support for a Unix98-style ptmx device.
+ * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998
+ *
+ * Reduced memory usage for older ARM systems
+ * -- Russell King <rmk@arm.linux.org.uk>
+ *
+ * Move do_SAK() into process context. Less stack use in devfs functions.
+ * alloc_tty_struct() always uses kmalloc() -- Andrew Morton <andrewm@uow.edu.eu> 17Mar01
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/major.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/fcntl.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <linux/devpts_fs.h>
+#include <linux/file.h>
+#include <linux/console.h>
+#include <linux/timer.h>
+#include <linux/ctype.h>
+#include <linux/kd.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+
+#include <linux/kbd_kern.h>
+#include <linux/vt_kern.h>
+#include <linux/selection.h>
+#include <linux/devfs_fs_kernel.h>
+
+#include <linux/kmod.h>
+
+#ifdef CONFIG_XENO
+extern void xeno_console_init(void);
+#endif
+
+#ifdef CONFIG_VT
+extern void con_init_devfs (void);
+#endif
+
+#define CONSOLE_DEV MKDEV(TTY_MAJOR,0)
+#define TTY_DEV MKDEV(TTYAUX_MAJOR,0)
+#define SYSCONS_DEV MKDEV(TTYAUX_MAJOR,1)
+#define PTMX_DEV MKDEV(TTYAUX_MAJOR,2)
+
+#undef TTY_DEBUG_HANGUP
+
+#define TTY_PARANOIA_CHECK 1
+#define CHECK_TTY_COUNT 1
+
+struct termios tty_std_termios; /* for the benefit of tty drivers */
+struct tty_driver *tty_drivers; /* linked list of tty drivers */
+struct tty_ldisc ldiscs[NR_LDISCS]; /* line disc dispatch table */
+
+#ifdef CONFIG_UNIX98_PTYS
+extern struct tty_driver ptm_driver[]; /* Unix98 pty masters; for /dev/ptmx */
+extern struct tty_driver pts_driver[]; /* Unix98 pty slaves; for /dev/ptmx */
+#endif
+
+/*
+ * redirect is the pseudo-tty that console output
+ * is redirected to if asked by TIOCCONS.
+ */
+struct tty_struct * redirect;
+
+static void initialize_tty_struct(struct tty_struct *tty);
+
+static ssize_t tty_read(struct file *, char *, size_t, loff_t *);
+static ssize_t tty_write(struct file *, const char *, size_t, loff_t *);
+static unsigned int tty_poll(struct file *, poll_table *);
+static int tty_open(struct inode *, struct file *);
+static int tty_release(struct inode *, struct file *);
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg);
+static int tty_fasync(int fd, struct file * filp, int on);
+extern int vme_scc_init (void);
+extern long vme_scc_console_init(void);
+extern int serial167_init(void);
+extern long serial167_console_init(void);
+extern void console_8xx_init(void);
+extern int rs_8xx_init(void);
+extern void mac_scc_console_init(void);
+extern void hwc_console_init(void);
+extern void hwc_tty_init(void);
+extern void con3215_init(void);
+extern void tty3215_init(void);
+extern void tub3270_con_init(void);
+extern void tub3270_init(void);
+extern void rs285_console_init(void);
+extern void sa1100_rs_console_init(void);
+extern void sgi_serial_console_init(void);
+extern void sci_console_init(void);
+extern void tx3912_console_init(void);
+extern void tx3912_rs_init(void);
+
+#ifndef MIN
+#define MIN(a,b) ((a) < (b) ? (a) : (b))
+#endif
+#ifndef MAX
+#define MAX(a,b) ((a) < (b) ? (b) : (a))
+#endif
+
+static struct tty_struct *alloc_tty_struct(void)
+{
+ struct tty_struct *tty;
+
+ tty = kmalloc(sizeof(struct tty_struct), GFP_KERNEL);
+ if (tty)
+ memset(tty, 0, sizeof(struct tty_struct));
+ return tty;
+}
+
+static inline void free_tty_struct(struct tty_struct *tty)
+{
+ kfree(tty);
+}
+
+/*
+ * This routine returns the name of tty.
+ */
+static char *
+_tty_make_name(struct tty_struct *tty, const char *name, char *buf)
+{
+ int idx = (tty)?MINOR(tty->device) - tty->driver.minor_start:0;
+
+ if (!tty) /* Hmm. NULL pointer. That's fun. */
+ strcpy(buf, "NULL tty");
+ else
+ sprintf(buf, name,
+ idx + tty->driver.name_base);
+
+ return buf;
+}
+
+#define TTY_NUMBER(tty) (MINOR((tty)->device) - (tty)->driver.minor_start + \
+ (tty)->driver.name_base)
+
+char *tty_name(struct tty_struct *tty, char *buf)
+{
+ return _tty_make_name(tty, (tty)?tty->driver.name:NULL, buf);
+}
+
+inline int tty_paranoia_check(struct tty_struct *tty, kdev_t device,
+ const char *routine)
+{
+#ifdef TTY_PARANOIA_CHECK
+ static const char badmagic[] = KERN_WARNING
+ "Warning: bad magic number for tty struct (%s) in %s\n";
+ static const char badtty[] = KERN_WARNING
+ "Warning: null TTY for (%s) in %s\n";
+
+ if (!tty) {
+ printk(badtty, kdevname(device), routine);
+ return 1;
+ }
+ if (tty->magic != TTY_MAGIC) {
+ printk(badmagic, kdevname(device), routine);
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+static int check_tty_count(struct tty_struct *tty, const char *routine)
+{
+#ifdef CHECK_TTY_COUNT
+ struct list_head *p;
+ int count = 0;
+
+ file_list_lock();
+ for(p = tty->tty_files.next; p != &tty->tty_files; p = p->next) {
+ if(list_entry(p, struct file, f_list)->private_data == tty)
+ count++;
+ }
+ file_list_unlock();
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_SLAVE &&
+ tty->link && tty->link->count)
+ count++;
+ if (tty->count != count) {
+ printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) "
+ "!= #fd's(%d) in %s\n",
+ kdevname(tty->device), tty->count, count, routine);
+ return count;
+ }
+#endif
+ return 0;
+}
+
+int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc)
+{
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ return -EINVAL;
+
+ if (new_ldisc) {
+ ldiscs[disc] = *new_ldisc;
+ ldiscs[disc].flags |= LDISC_FLAG_DEFINED;
+ ldiscs[disc].num = disc;
+ } else
+ memset(&ldiscs[disc], 0, sizeof(struct tty_ldisc));
+
+ return 0;
+}
+
+EXPORT_SYMBOL(tty_register_ldisc);
+
+/* Set the discipline of a tty line. */
+static int tty_set_ldisc(struct tty_struct *tty, int ldisc)
+{
+ int retval = 0;
+ struct tty_ldisc o_ldisc;
+ char buf[64];
+
+ if ((ldisc < N_TTY) || (ldisc >= NR_LDISCS))
+ return -EINVAL;
+ /* Eduardo Blanco <ejbs@cs.cs.com.uy> */
+ /* Cyrus Durgin <cider@speakeasy.org> */
+ if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED)) {
+ char modname [20];
+ sprintf(modname, "tty-ldisc-%d", ldisc);
+ request_module (modname);
+ }
+ if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED))
+ return -EINVAL;
+
+ if (tty->ldisc.num == ldisc)
+ return 0; /* We are already in the desired discipline */
+ o_ldisc = tty->ldisc;
+
+ tty_wait_until_sent(tty, 0);
+
+ /* Shutdown the current discipline. */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+
+ /* Now set up the new line discipline. */
+ tty->ldisc = ldiscs[ldisc];
+ tty->termios->c_line = ldisc;
+ if (tty->ldisc.open)
+ retval = (tty->ldisc.open)(tty);
+ if (retval < 0) {
+ tty->ldisc = o_ldisc;
+ tty->termios->c_line = tty->ldisc.num;
+ if (tty->ldisc.open && (tty->ldisc.open(tty) < 0)) {
+ tty->ldisc = ldiscs[N_TTY];
+ tty->termios->c_line = N_TTY;
+ if (tty->ldisc.open) {
+ int r = tty->ldisc.open(tty);
+
+ if (r < 0)
+ panic("Couldn't open N_TTY ldisc for "
+ "%s --- error %d.",
+ tty_name(tty, buf), r);
+ }
+ }
+ }
+ if (tty->ldisc.num != o_ldisc.num && tty->driver.set_ldisc)
+ tty->driver.set_ldisc(tty);
+ return retval;
+}
+
+/*
+ * This routine returns a tty driver structure, given a device number
+ */
+struct tty_driver *get_tty_driver(kdev_t device)
+{
+ int major, minor;
+ struct tty_driver *p;
+
+ minor = MINOR(device);
+ major = MAJOR(device);
+
+ for (p = tty_drivers; p; p = p->next) {
+ if (p->major != major)
+ continue;
+ if (minor < p->minor_start)
+ continue;
+ if (minor >= p->minor_start + p->num)
+ continue;
+ return p;
+ }
+ return NULL;
+}
+
+/*
+ * If we try to write to, or set the state of, a terminal and we're
+ * not in the foreground, send a SIGTTOU. If the signal is blocked or
+ * ignored, go ahead and perform the operation. (POSIX 7.2)
+ */
+int tty_check_change(struct tty_struct * tty)
+{
+ if (current->tty != tty)
+ return 0;
+ if (tty->pgrp <= 0) {
+ printk(KERN_WARNING "tty_check_change: tty->pgrp <= 0!\n");
+ return 0;
+ }
+ if (current->pgrp == tty->pgrp)
+ return 0;
+ if (is_ignored(SIGTTOU))
+ return 0;
+ if (is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ (void) kill_pg(current->pgrp,SIGTTOU,1);
+ return -ERESTARTSYS;
+}
+
+static ssize_t hung_up_tty_read(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ /* Can't seek (pread) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+ return 0;
+}
+
+static ssize_t hung_up_tty_write(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ /* Can't seek (pwrite) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+ return -EIO;
+}
+
+/* No kernel lock held - none needed ;) */
+static unsigned int hung_up_tty_poll(struct file * filp, poll_table * wait)
+{
+ return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM;
+}
+
+static int hung_up_tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
+}
+
+static struct file_operations tty_fops = {
+ llseek: no_llseek,
+ read: tty_read,
+ write: tty_write,
+ poll: tty_poll,
+ ioctl: tty_ioctl,
+ open: tty_open,
+ release: tty_release,
+ fasync: tty_fasync,
+};
+
+static struct file_operations hung_up_tty_fops = {
+ llseek: no_llseek,
+ read: hung_up_tty_read,
+ write: hung_up_tty_write,
+ poll: hung_up_tty_poll,
+ ioctl: hung_up_tty_ioctl,
+ release: tty_release,
+};
+
+/*
+ * This can be called by the "eventd" kernel thread. That is process synchronous,
+ * but doesn't hold any locks, so we need to make sure we have the appropriate
+ * locks for what we're doing..
+ */
+void do_tty_hangup(void *data)
+{
+ struct tty_struct *tty = (struct tty_struct *) data;
+ struct file * cons_filp = NULL;
+ struct task_struct *p;
+ struct list_head *l;
+ int closecount = 0, n;
+
+ if (!tty)
+ return;
+
+ /* inuse_filps is protected by the single kernel lock */
+ lock_kernel();
+
+ check_tty_count(tty, "do_tty_hangup");
+ file_list_lock();
+ for (l = tty->tty_files.next; l != &tty->tty_files; l = l->next) {
+ struct file * filp = list_entry(l, struct file, f_list);
+ if (filp->f_dentry->d_inode->i_rdev == CONSOLE_DEV ||
+ filp->f_dentry->d_inode->i_rdev == SYSCONS_DEV) {
+ cons_filp = filp;
+ continue;
+ }
+ if (filp->f_op != &tty_fops)
+ continue;
+ closecount++;
+ tty_fasync(-1, filp, 0); /* can't block */
+ filp->f_op = &hung_up_tty_fops;
+ }
+ file_list_unlock();
+
+ /* FIXME! What are the locking issues here? This may me overdoing things.. */
+ {
+ unsigned long flags;
+
+ save_flags(flags); cli();
+ if (tty->ldisc.flush_buffer)
+ tty->ldisc.flush_buffer(tty);
+ if (tty->driver.flush_buffer)
+ tty->driver.flush_buffer(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+ tty->ldisc.write_wakeup)
+ (tty->ldisc.write_wakeup)(tty);
+ restore_flags(flags);
+ }
+
+ wake_up_interruptible(&tty->write_wait);
+ wake_up_interruptible(&tty->read_wait);
+
+ /*
+ * Shutdown the current line discipline, and reset it to
+ * N_TTY.
+ */
+ if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS)
+ *tty->termios = tty->driver.init_termios;
+ if (tty->ldisc.num != ldiscs[N_TTY].num) {
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ tty->ldisc = ldiscs[N_TTY];
+ tty->termios->c_line = N_TTY;
+ if (tty->ldisc.open) {
+ int i = (tty->ldisc.open)(tty);
+ if (i < 0)
+ printk(KERN_ERR "do_tty_hangup: N_TTY open: "
+ "error %d\n", -i);
+ }
+ }
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((tty->session > 0) && (p->session == tty->session) &&
+ p->leader) {
+ send_sig(SIGHUP,p,1);
+ send_sig(SIGCONT,p,1);
+ if (tty->pgrp > 0)
+ p->tty_old_pgrp = tty->pgrp;
+ }
+ if (p->tty == tty)
+ p->tty = NULL;
+ }
+ read_unlock(&tasklist_lock);
+
+ tty->flags = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+ tty->ctrl_status = 0;
+ /*
+ * If one of the devices matches a console pointer, we
+ * cannot just call hangup() because that will cause
+ * tty->count and state->count to go out of sync.
+ * So we just call close() the right number of times.
+ */
+ if (cons_filp) {
+ if (tty->driver.close)
+ for (n = 0; n < closecount; n++)
+ tty->driver.close(tty, cons_filp);
+ } else if (tty->driver.hangup)
+ (tty->driver.hangup)(tty);
+ unlock_kernel();
+}
+
+void tty_hangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s hangup...\n", tty_name(tty, buf));
+#endif
+ schedule_task(&tty->tq_hangup);
+}
+
+void tty_vhangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s vhangup...\n", tty_name(tty, buf));
+#endif
+ do_tty_hangup((void *) tty);
+}
+
+int tty_hung_up_p(struct file * filp)
+{
+ return (filp->f_op == &hung_up_tty_fops);
+}
+
+/*
+ * This function is typically called only by the session leader, when
+ * it wants to disassociate itself from its controlling tty.
+ *
+ * It performs the following functions:
+ * (1) Sends a SIGHUP and SIGCONT to the foreground process group
+ * (2) Clears the tty from being controlling the session
+ * (3) Clears the controlling tty for all processes in the
+ * session group.
+ *
+ * The argument on_exit is set to 1 if called when a process is
+ * exiting; it is 0 if called by the ioctl TIOCNOTTY.
+ */
+void disassociate_ctty(int on_exit)
+{
+ struct tty_struct *tty = current->tty;
+ struct task_struct *p;
+ int tty_pgrp = -1;
+
+ if (tty) {
+ tty_pgrp = tty->pgrp;
+ if (on_exit && tty->driver.type != TTY_DRIVER_TYPE_PTY)
+ tty_vhangup(tty);
+ } else {
+ if (current->tty_old_pgrp) {
+ kill_pg(current->tty_old_pgrp, SIGHUP, on_exit);
+ kill_pg(current->tty_old_pgrp, SIGCONT, on_exit);
+ }
+ return;
+ }
+ if (tty_pgrp > 0) {
+ kill_pg(tty_pgrp, SIGHUP, on_exit);
+ if (!on_exit)
+ kill_pg(tty_pgrp, SIGCONT, on_exit);
+ }
+
+ current->tty_old_pgrp = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p)
+ if (p->session == current->session)
+ p->tty = NULL;
+ read_unlock(&tasklist_lock);
+}
+
+void wait_for_keypress(void)
+{
+ struct console *c = console_drivers;
+ if (c) c->wait_key(c);
+}
+
+void stop_tty(struct tty_struct *tty)
+{
+ if (tty->stopped)
+ return;
+ tty->stopped = 1;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_START;
+ tty->ctrl_status |= TIOCPKT_STOP;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver.stop)
+ (tty->driver.stop)(tty);
+}
+
+void start_tty(struct tty_struct *tty)
+{
+ if (!tty->stopped || tty->flow_stopped)
+ return;
+ tty->stopped = 0;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_STOP;
+ tty->ctrl_status |= TIOCPKT_START;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver.start)
+ (tty->driver.start)(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+ tty->ldisc.write_wakeup)
+ (tty->ldisc.write_wakeup)(tty);
+ wake_up_interruptible(&tty->write_wait);
+}
+
+static ssize_t tty_read(struct file * file, char * buf, size_t count,
+ loff_t *ppos)
+{
+ int i;
+ struct tty_struct * tty;
+ struct inode *inode;
+
+ /* Can't seek (pread) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+
+ tty = (struct tty_struct *)file->private_data;
+ inode = file->f_dentry->d_inode;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_read"))
+ return -EIO;
+ if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+
+ /* This check not only needs to be done before reading, but also
+ whenever read_chan() gets woken up after sleeping, so I've
+ moved it to there. This should only be done for the N_TTY
+ line discipline, anyway. Same goes for write_chan(). -- jlc. */
+#if 0
+ if ((inode->i_rdev != CONSOLE_DEV) && /* don't stop on /dev/console */
+ (tty->pgrp > 0) &&
+ (current->tty == tty) &&
+ (tty->pgrp != current->pgrp))
+ if (is_ignored(SIGTTIN) || is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ else {
+ (void) kill_pg(current->pgrp, SIGTTIN, 1);
+ return -ERESTARTSYS;
+ }
+#endif
+ lock_kernel();
+ if (tty->ldisc.read)
+ i = (tty->ldisc.read)(tty,file,buf,count);
+ else
+ i = -EIO;
+ unlock_kernel();
+ if (i > 0)
+ inode->i_atime = CURRENT_TIME;
+ return i;
+}
+
+/*
+ * Split writes up in sane blocksizes to avoid
+ * denial-of-service type attacks
+ */
+static inline ssize_t do_tty_write(
+ ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t),
+ struct tty_struct *tty,
+ struct file *file,
+ const unsigned char *buf,
+ size_t count)
+{
+ ssize_t ret = 0, written = 0;
+
+ if (down_interruptible(&tty->atomic_write)) {
+ return -ERESTARTSYS;
+ }
+ if ( test_bit(TTY_NO_WRITE_SPLIT, &tty->flags) ) {
+ lock_kernel();
+ written = write(tty, file, buf, count);
+ unlock_kernel();
+ } else {
+ for (;;) {
+ unsigned long size = MAX(PAGE_SIZE*2,16384);
+ if (size > count)
+ size = count;
+ lock_kernel();
+ ret = write(tty, file, buf, size);
+ unlock_kernel();
+ if (ret <= 0)
+ break;
+ written += ret;
+ buf += ret;
+ count -= ret;
+ if (!count)
+ break;
+ ret = -ERESTARTSYS;
+ if (signal_pending(current))
+ break;
+ if (current->need_resched)
+ schedule();
+ }
+ }
+ if (written) {
+ file->f_dentry->d_inode->i_mtime = CURRENT_TIME;
+ ret = written;
+ }
+ up(&tty->atomic_write);
+ return ret;
+}
+
+
+static ssize_t tty_write(struct file * file, const char * buf, size_t count,
+ loff_t *ppos)
+{
+ int is_console;
+ struct tty_struct * tty;
+ struct inode *inode;
+
+ /* Can't seek (pwrite) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+
+ /*
+ * For now, we redirect writes from /dev/console as
+ * well as /dev/tty0.
+ */
+ inode = file->f_dentry->d_inode;
+ is_console = (inode->i_rdev == SYSCONS_DEV ||
+ inode->i_rdev == CONSOLE_DEV);
+
+ if (is_console && redirect)
+ tty = redirect;
+ else
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_write"))
+ return -EIO;
+ if (!tty || !tty->driver.write || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+#if 0
+ if (!is_console && L_TOSTOP(tty) && (tty->pgrp > 0) &&
+ (current->tty == tty) && (tty->pgrp != current->pgrp)) {
+ if (is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ if (!is_ignored(SIGTTOU)) {
+ (void) kill_pg(current->pgrp, SIGTTOU, 1);
+ return -ERESTARTSYS;
+ }
+ }
+#endif
+ if (!tty->ldisc.write)
+ return -EIO;
+ return do_tty_write(tty->ldisc.write, tty, file,
+ (const unsigned char *)buf, count);
+}
+
+/* Semaphore to protect creating and releasing a tty */
+static DECLARE_MUTEX(tty_sem);
+
+static void down_tty_sem(int index)
+{
+ down(&tty_sem);
+}
+
+static void up_tty_sem(int index)
+{
+ up(&tty_sem);
+}
+
+static void release_mem(struct tty_struct *tty, int idx);
+
+/*
+ * WSH 06/09/97: Rewritten to remove races and properly clean up after a
+ * failed open. The new code protects the open with a semaphore, so it's
+ * really quite straightforward. The semaphore locking can probably be
+ * relaxed for the (most common) case of reopening a tty.
+ */
+static int init_dev(kdev_t device, struct tty_struct **ret_tty)
+{
+ struct tty_struct *tty, *o_tty;
+ struct termios *tp, **tp_loc, *o_tp, **o_tp_loc;
+ struct termios *ltp, **ltp_loc, *o_ltp, **o_ltp_loc;
+ struct tty_driver *driver;
+ int retval=0;
+ int idx;
+
+ driver = get_tty_driver(device);
+ if (!driver)
+ return -ENODEV;
+
+ idx = MINOR(device) - driver->minor_start;
+
+ /*
+ * Check whether we need to acquire the tty semaphore to avoid
+ * race conditions. For now, play it safe.
+ */
+ down_tty_sem(idx);
+
+ /* check whether we're reopening an existing tty */
+ tty = driver->table[idx];
+ if (tty) goto fast_track;
+
+ /*
+ * First time open is complex, especially for PTY devices.
+ * This code guarantees that either everything succeeds and the
+ * TTY is ready for operation, or else the table slots are vacated
+ * and the allocated memory released. (Except that the termios
+ * and locked termios may be retained.)
+ */
+
+ o_tty = NULL;
+ tp = o_tp = NULL;
+ ltp = o_ltp = NULL;
+
+ tty = alloc_tty_struct();
+ if(!tty)
+ goto fail_no_mem;
+ initialize_tty_struct(tty);
+ tty->device = device;
+ tty->driver = *driver;
+
+ tp_loc = &driver->termios[idx];
+ if (!*tp_loc) {
+ tp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!tp)
+ goto free_mem_out;
+ *tp = driver->init_termios;
+ }
+
+ ltp_loc = &driver->termios_locked[idx];
+ if (!*ltp_loc) {
+ ltp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!ltp)
+ goto free_mem_out;
+ memset(ltp, 0, sizeof(struct termios));
+ }
+
+ if (driver->type == TTY_DRIVER_TYPE_PTY) {
+ o_tty = alloc_tty_struct();
+ if (!o_tty)
+ goto free_mem_out;
+ initialize_tty_struct(o_tty);
+ o_tty->device = (kdev_t) MKDEV(driver->other->major,
+ driver->other->minor_start + idx);
+ o_tty->driver = *driver->other;
+
+ o_tp_loc = &driver->other->termios[idx];
+ if (!*o_tp_loc) {
+ o_tp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_tp)
+ goto free_mem_out;
+ *o_tp = driver->other->init_termios;
+ }
+
+ o_ltp_loc = &driver->other->termios_locked[idx];
+ if (!*o_ltp_loc) {
+ o_ltp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_ltp)
+ goto free_mem_out;
+ memset(o_ltp, 0, sizeof(struct termios));
+ }
+
+ /*
+ * Everything allocated ... set up the o_tty structure.
+ */
+ driver->other->table[idx] = o_tty;
+ if (!*o_tp_loc)
+ *o_tp_loc = o_tp;
+ if (!*o_ltp_loc)
+ *o_ltp_loc = o_ltp;
+ o_tty->termios = *o_tp_loc;
+ o_tty->termios_locked = *o_ltp_loc;
+ (*driver->other->refcount)++;
+ if (driver->subtype == PTY_TYPE_MASTER)
+ o_tty->count++;
+
+ /* Establish the links in both directions */
+ tty->link = o_tty;
+ o_tty->link = tty;
+ }
+
+ /*
+ * All structures have been allocated, so now we install them.
+ * Failures after this point use release_mem to clean up, so
+ * there's no need to null out the local pointers.
+ */
+ driver->table[idx] = tty;
+
+ if (!*tp_loc)
+ *tp_loc = tp;
+ if (!*ltp_loc)
+ *ltp_loc = ltp;
+ tty->termios = *tp_loc;
+ tty->termios_locked = *ltp_loc;
+ (*driver->refcount)++;
+ tty->count++;
+
+ /*
+ * Structures all installed ... call the ldisc open routines.
+ * If we fail here just call release_mem to clean up. No need
+ * to decrement the use counts, as release_mem doesn't care.
+ */
+ if (tty->ldisc.open) {
+ retval = (tty->ldisc.open)(tty);
+ if (retval)
+ goto release_mem_out;
+ }
+ if (o_tty && o_tty->ldisc.open) {
+ retval = (o_tty->ldisc.open)(o_tty);
+ if (retval) {
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ goto release_mem_out;
+ }
+ }
+ goto success;
+
+ /*
+ * This fast open can be used if the tty is already open.
+ * No memory is allocated, and the only failures are from
+ * attempting to open a closing tty or attempting multiple
+ * opens on a pty master.
+ */
+fast_track:
+ if (test_bit(TTY_CLOSING, &tty->flags)) {
+ retval = -EIO;
+ goto end_init;
+ }
+ if (driver->type == TTY_DRIVER_TYPE_PTY &&
+ driver->subtype == PTY_TYPE_MASTER) {
+ /*
+ * special case for PTY masters: only one open permitted,
+ * and the slave side open count is incremented as well.
+ */
+ if (tty->count) {
+ retval = -EIO;
+ goto end_init;
+ }
+ tty->link->count++;
+ }
+ tty->count++;
+ tty->driver = *driver; /* N.B. why do this every time?? */
+
+success:
+ *ret_tty = tty;
+
+ /* All paths come through here to release the semaphore */
+end_init:
+ up_tty_sem(idx);
+ return retval;
+
+ /* Release locally allocated memory ... nothing placed in slots */
+free_mem_out:
+ if (o_tp)
+ kfree(o_tp);
+ if (o_tty)
+ free_tty_struct(o_tty);
+ if (ltp)
+ kfree(ltp);
+ if (tp)
+ kfree(tp);
+ free_tty_struct(tty);
+
+fail_no_mem:
+ retval = -ENOMEM;
+ goto end_init;
+
+ /* call the tty release_mem routine to clean out this slot */
+release_mem_out:
+ printk(KERN_INFO "init_dev: ldisc open failed, "
+ "clearing slot %d\n", idx);
+ release_mem(tty, idx);
+ goto end_init;
+}
+
+/*
+ * Releases memory associated with a tty structure, and clears out the
+ * driver table slots.
+ */
+static void release_mem(struct tty_struct *tty, int idx)
+{
+ struct tty_struct *o_tty;
+ struct termios *tp;
+
+ if ((o_tty = tty->link) != NULL) {
+ o_tty->driver.table[idx] = NULL;
+ if (o_tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = o_tty->driver.termios[idx];
+ o_tty->driver.termios[idx] = NULL;
+ kfree(tp);
+ }
+ o_tty->magic = 0;
+ (*o_tty->driver.refcount)--;
+ list_del(&o_tty->tty_files);
+ free_tty_struct(o_tty);
+ }
+
+ tty->driver.table[idx] = NULL;
+ if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = tty->driver.termios[idx];
+ tty->driver.termios[idx] = NULL;
+ kfree(tp);
+ }
+ tty->magic = 0;
+ (*tty->driver.refcount)--;
+ list_del(&tty->tty_files);
+ free_tty_struct(tty);
+}
+
+/*
+ * Even releasing the tty structures is a tricky business.. We have
+ * to be very careful that the structures are all released at the
+ * same time, as interrupts might otherwise get the wrong pointers.
+ *
+ * WSH 09/09/97: rewritten to avoid some nasty race conditions that could
+ * lead to double frees or releasing memory still in use.
+ */
+static void release_dev(struct file * filp)
+{
+ struct tty_struct *tty, *o_tty;
+ int pty_master, tty_closing, o_tty_closing, do_sleep;
+ int idx;
+ char buf[64];
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "release_dev"))
+ return;
+
+ check_tty_count(tty, "release_dev");
+
+ tty_fasync(-1, filp, 0);
+
+ idx = MINOR(tty->device) - tty->driver.minor_start;
+ pty_master = (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER);
+ o_tty = tty->link;
+
+#ifdef TTY_PARANOIA_CHECK
+ if (idx < 0 || idx >= tty->driver.num) {
+ printk(KERN_DEBUG "release_dev: bad idx when trying to "
+ "free (%s)\n", kdevname(tty->device));
+ return;
+ }
+ if (tty != tty->driver.table[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.table[%d] not tty "
+ "for (%s)\n", idx, kdevname(tty->device));
+ return;
+ }
+ if (tty->termios != tty->driver.termios[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios[%d] not termios "
+ "for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (tty->termios_locked != tty->driver.termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios_locked[%d] not "
+ "termios_locked for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+#endif
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "release_dev of %s (tty count=%d)...",
+ tty_name(tty, buf), tty->count);
+#endif
+
+#ifdef TTY_PARANOIA_CHECK
+ if (tty->driver.other) {
+ if (o_tty != tty->driver.other->table[idx]) {
+ printk(KERN_DEBUG "release_dev: other->table[%d] "
+ "not o_tty for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->termios != tty->driver.other->termios[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios[%d] "
+ "not o_termios for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->termios_locked !=
+ tty->driver.other->termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios_locked["
+ "%d] not o_termios_locked for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->link != tty) {
+ printk(KERN_DEBUG "release_dev: bad pty pointers\n");
+ return;
+ }
+ }
+#endif
+
+ if (tty->driver.close)
+ tty->driver.close(tty, filp);
+
+ /*
+ * Sanity check: if tty->count is going to zero, there shouldn't be
+ * any waiters on tty->read_wait or tty->write_wait. We test the
+ * wait queues and kick everyone out _before_ actually starting to
+ * close. This ensures that we won't block while releasing the tty
+ * structure.
+ *
+ * The test for the o_tty closing is necessary, since the master and
+ * slave sides may close in any order. If the slave side closes out
+ * first, its count will be one, since the master side holds an open.
+ * Thus this test wouldn't be triggered at the time the slave closes,
+ * so we do it now.
+ *
+ * Note that it's possible for the tty to be opened again while we're
+ * flushing out waiters. By recalculating the closing flags before
+ * each iteration we avoid any problems.
+ */
+ while (1) {
+ tty_closing = tty->count <= 1;
+ o_tty_closing = o_tty &&
+ (o_tty->count <= (pty_master ? 1 : 0));
+ do_sleep = 0;
+
+ if (tty_closing) {
+ if (waitqueue_active(&tty->read_wait)) {
+ wake_up(&tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&tty->write_wait)) {
+ wake_up(&tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (o_tty_closing) {
+ if (waitqueue_active(&o_tty->read_wait)) {
+ wake_up(&o_tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&o_tty->write_wait)) {
+ wake_up(&o_tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (!do_sleep)
+ break;
+
+ printk(KERN_WARNING "release_dev: %s: read/write wait queue "
+ "active!\n", tty_name(tty, buf));
+ schedule();
+ }
+
+ /*
+ * The closing flags are now consistent with the open counts on
+ * both sides, and we've completed the last operation that could
+ * block, so it's safe to proceed with closing.
+ */
+ if (pty_master) {
+ if (--o_tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad pty slave count "
+ "(%d) for %s\n",
+ o_tty->count, tty_name(o_tty, buf));
+ o_tty->count = 0;
+ }
+ }
+ if (--tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad tty->count (%d) for %s\n",
+ tty->count, tty_name(tty, buf));
+ tty->count = 0;
+ }
+
+ /*
+ * We've decremented tty->count, so we should zero out
+ * filp->private_data, to break the link between the tty and
+ * the file descriptor. Otherwise if filp_close() blocks before
+ * the file descriptor is removed from the inuse_filp
+ * list, check_tty_count() could observe a discrepancy and
+ * printk a warning message to the user.
+ */
+ filp->private_data = 0;
+
+ /*
+ * Perform some housekeeping before deciding whether to return.
+ *
+ * Set the TTY_CLOSING flag if this was the last open. In the
+ * case of a pty we may have to wait around for the other side
+ * to close, and TTY_CLOSING makes sure we can't be reopened.
+ */
+ if(tty_closing)
+ set_bit(TTY_CLOSING, &tty->flags);
+ if(o_tty_closing)
+ set_bit(TTY_CLOSING, &o_tty->flags);
+
+ /*
+ * If _either_ side is closing, make sure there aren't any
+ * processes that still think tty or o_tty is their controlling
+ * tty. Also, clear redirect if it points to either tty.
+ */
+ if (tty_closing || o_tty_closing) {
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if (p->tty == tty || (o_tty && p->tty == o_tty))
+ p->tty = NULL;
+ }
+ read_unlock(&tasklist_lock);
+
+ if (redirect == tty || (o_tty && redirect == o_tty))
+ redirect = NULL;
+ }
+
+ /* check whether both sides are closing ... */
+ if (!tty_closing || (o_tty && !o_tty_closing))
+ return;
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "freeing tty structure...");
+#endif
+
+ /*
+ * Shutdown the current line discipline, and reset it to N_TTY.
+ * N.B. why reset ldisc when we're releasing the memory??
+ */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ tty->ldisc = ldiscs[N_TTY];
+ tty->termios->c_line = N_TTY;
+ if (o_tty) {
+ if (o_tty->ldisc.close)
+ (o_tty->ldisc.close)(o_tty);
+ o_tty->ldisc = ldiscs[N_TTY];
+ }
+
+ /*
+ * Make sure that the tty's task queue isn't activated.
+ */
+ run_task_queue(&tq_timer);
+ flush_scheduled_tasks();
+
+ /*
+ * The release_mem function takes care of the details of clearing
+ * the slots and preserving the termios structure.
+ */
+ release_mem(tty, idx);
+}
+
+/*
+ * tty_open and tty_release keep up the tty count that contains the
+ * number of opens done on a tty. We cannot use the inode-count, as
+ * different inodes might point to the same tty.
+ *
+ * Open-counting is needed for pty masters, as well as for keeping
+ * track of serial lines: DTR is dropped when the last close happens.
+ * (This is not done solely through tty->count, now. - Ted 1/27/92)
+ *
+ * The termios state of a pty is reset on first open so that
+ * settings don't persist across reuse.
+ */
+static int tty_open(struct inode * inode, struct file * filp)
+{
+ struct tty_struct *tty;
+ int noctty, retval;
+ kdev_t device;
+ unsigned short saved_flags;
+ char buf[64];
+
+ saved_flags = filp->f_flags;
+retry_open:
+ noctty = filp->f_flags & O_NOCTTY;
+ device = inode->i_rdev;
+ if (device == TTY_DEV) {
+ if (!current->tty)
+ return -ENXIO;
+ device = current->tty->device;
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */
+ /* noctty = 1; */
+ }
+#ifdef CONFIG_VT
+ if (device == CONSOLE_DEV) {
+ extern int fg_console;
+ device = MKDEV(TTY_MAJOR, fg_console + 1);
+ noctty = 1;
+ }
+#endif
+ if (device == SYSCONS_DEV) {
+ struct console *c = console_drivers;
+ while(c && !c->device)
+ c = c->next;
+ if (!c)
+ return -ENODEV;
+ device = c->device(c);
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/console block */
+ noctty = 1;
+ }
+
+ if (device == PTMX_DEV) {
+#ifdef CONFIG_UNIX98_PTYS
+
+ /* find a free pty. */
+ int major, minor;
+ struct tty_driver *driver;
+
+ /* find a device that is not in use. */
+ retval = -1;
+ for ( major = 0 ; major < UNIX98_NR_MAJORS ; major++ ) {
+ driver = &ptm_driver[major];
+ for (minor = driver->minor_start ;
+ minor < driver->minor_start + driver->num ;
+ minor++) {
+ device = MKDEV(driver->major, minor);
+ if (!init_dev(device, &tty)) goto ptmx_found; /* ok! */
+ }
+ }
+ return -EIO; /* no free ptys */
+ ptmx_found:
+ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
+ minor -= driver->minor_start;
+ devpts_pty_new(driver->other->name_base + minor, MKDEV(driver->other->major, minor + driver->other->minor_start));
+ tty_register_devfs(&pts_driver[major], DEVFS_FL_NO_PERSISTENCE,
+ pts_driver[major].minor_start + minor);
+ noctty = 1;
+ goto init_dev_done;
+
+#else /* CONFIG_UNIX_98_PTYS */
+
+ return -ENODEV;
+
+#endif /* CONFIG_UNIX_98_PTYS */
+ }
+
+ retval = init_dev(device, &tty);
+ if (retval)
+ return retval;
+
+#ifdef CONFIG_UNIX98_PTYS
+init_dev_done:
+#endif
+ filp->private_data = tty;
+ file_move(filp, &tty->tty_files);
+ check_tty_count(tty, "tty_open");
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER)
+ noctty = 1;
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "opening %s...", tty_name(tty, buf));
+#endif
+ if (tty->driver.open)
+ retval = tty->driver.open(tty, filp);
+ else
+ retval = -ENODEV;
+ filp->f_flags = saved_flags;
+
+ if (!retval && test_bit(TTY_EXCLUSIVE, &tty->flags) && !suser())
+ retval = -EBUSY;
+
+ if (retval) {
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "error %d in opening %s...", retval,
+ tty_name(tty, buf));
+#endif
+
+ release_dev(filp);
+ if (retval != -ERESTARTSYS)
+ return retval;
+ if (signal_pending(current))
+ return retval;
+ schedule();
+ /*
+ * Need to reset f_op in case a hangup happened.
+ */
+ filp->f_op = &tty_fops;
+ goto retry_open;
+ }
+ if (!noctty &&
+ current->leader &&
+ !current->tty &&
+ tty->session == 0) {
+ task_lock(current);
+ current->tty = tty;
+ task_unlock(current);
+ current->tty_old_pgrp = 0;
+ tty->session = current->session;
+ tty->pgrp = current->pgrp;
+ }
+ if ((tty->driver.type == TTY_DRIVER_TYPE_SERIAL) &&
+ (tty->driver.subtype == SERIAL_TYPE_CALLOUT) &&
+ (tty->count == 1)) {
+ static int nr_warns;
+ if (nr_warns < 5) {
+ printk(KERN_WARNING "tty_io.c: "
+ "process %d (%s) used obsolete /dev/%s - "
+ "update software to use /dev/ttyS%d\n",
+ current->pid, current->comm,
+ tty_name(tty, buf), TTY_NUMBER(tty));
+ nr_warns++;
+ }
+ }
+ return 0;
+}
+
+static int tty_release(struct inode * inode, struct file * filp)
+{
+ lock_kernel();
+ release_dev(filp);
+ unlock_kernel();
+ return 0;
+}
+
+/* No kernel lock held - fine */
+static unsigned int tty_poll(struct file * filp, poll_table * wait)
+{
+ struct tty_struct * tty;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_poll"))
+ return 0;
+
+ if (tty->ldisc.poll)
+ return (tty->ldisc.poll)(tty, filp, wait);
+ return 0;
+}
+
+static int tty_fasync(int fd, struct file * filp, int on)
+{
+ struct tty_struct * tty;
+ int retval;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_fasync"))
+ return 0;
+
+ retval = fasync_helper(fd, filp, on, &tty->fasync);
+ if (retval <= 0)
+ return retval;
+
+ if (on) {
+ if (!waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = 1;
+ if (filp->f_owner.pid == 0) {
+ filp->f_owner.pid = (-tty->pgrp) ? : current->pid;
+ filp->f_owner.uid = current->uid;
+ filp->f_owner.euid = current->euid;
+ }
+ } else {
+ if (!tty->fasync && !waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = N_TTY_BUF_SIZE;
+ }
+ return 0;
+}
+
+static int tiocsti(struct tty_struct *tty, char * arg)
+{
+ char ch, mbz = 0;
+
+ if ((current->tty != tty) && !suser())
+ return -EPERM;
+ if (get_user(ch, arg))
+ return -EFAULT;
+ tty->ldisc.receive_buf(tty, &ch, &mbz, 1);
+ return 0;
+}
+
+static int tiocgwinsz(struct tty_struct *tty, struct winsize * arg)
+{
+ if (copy_to_user(arg, &tty->winsize, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocswinsz(struct tty_struct *tty, struct tty_struct *real_tty,
+ struct winsize * arg)
+{
+ struct winsize tmp_ws;
+
+ if (copy_from_user(&tmp_ws, arg, sizeof(*arg)))
+ return -EFAULT;
+ if (!memcmp(&tmp_ws, &tty->winsize, sizeof(*arg)))
+ return 0;
+ if (tty->pgrp > 0)
+ kill_pg(tty->pgrp, SIGWINCH, 1);
+ if ((real_tty->pgrp != tty->pgrp) && (real_tty->pgrp > 0))
+ kill_pg(real_tty->pgrp, SIGWINCH, 1);
+ tty->winsize = tmp_ws;
+ real_tty->winsize = tmp_ws;
+ return 0;
+}
+
+static int tioccons(struct inode *inode,
+ struct tty_struct *tty, struct tty_struct *real_tty)
+{
+ if (inode->i_rdev == SYSCONS_DEV ||
+ inode->i_rdev == CONSOLE_DEV) {
+ if (!suser())
+ return -EPERM;
+ redirect = NULL;
+ return 0;
+ }
+ if (redirect)
+ return -EBUSY;
+ redirect = real_tty;
+ return 0;
+}
+
+
+static int fionbio(struct file *file, int *arg)
+{
+ int nonblock;
+
+ if (get_user(nonblock, arg))
+ return -EFAULT;
+
+ if (nonblock)
+ file->f_flags |= O_NONBLOCK;
+ else
+ file->f_flags &= ~O_NONBLOCK;
+ return 0;
+}
+
+static int tiocsctty(struct tty_struct *tty, int arg)
+{
+ if (current->leader &&
+ (current->session == tty->session))
+ return 0;
+ /*
+ * The process must be a session leader and
+ * not have a controlling tty already.
+ */
+ if (!current->leader || current->tty)
+ return -EPERM;
+ if (tty->session > 0) {
+ /*
+ * This tty is already the controlling
+ * tty for another session group!
+ */
+ if ((arg == 1) && suser()) {
+ /*
+ * Steal it away
+ */
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p)
+ if (p->tty == tty)
+ p->tty = NULL;
+ read_unlock(&tasklist_lock);
+ } else
+ return -EPERM;
+ }
+ task_lock(current);
+ current->tty = tty;
+ task_unlock(current);
+ current->tty_old_pgrp = 0;
+ tty->session = current->session;
+ tty->pgrp = current->pgrp;
+ return 0;
+}
+
+static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->tty != real_tty)
+ return -ENOTTY;
+ return put_user(real_tty->pgrp, arg);
+}
+
+static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
+{
+ pid_t pgrp;
+ int retval = tty_check_change(real_tty);
+
+ if (retval == -EIO)
+ return -ENOTTY;
+ if (retval)
+ return retval;
+ if (!current->tty ||
+ (current->tty != real_tty) ||
+ (real_tty->session != current->session))
+ return -ENOTTY;
+ if (get_user(pgrp, (pid_t *) arg))
+ return -EFAULT;
+ if (pgrp < 0)
+ return -EINVAL;
+ if (session_of_pgrp(pgrp) != current->session)
+ return -EPERM;
+ real_tty->pgrp = pgrp;
+ return 0;
+}
+
+static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->tty != real_tty)
+ return -ENOTTY;
+ if (real_tty->session <= 0)
+ return -ENOTTY;
+ return put_user(real_tty->session, arg);
+}
+
+static int tiocttygstruct(struct tty_struct *tty, struct tty_struct *arg)
+{
+ if (copy_to_user(arg, tty, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocsetd(struct tty_struct *tty, int *arg)
+{
+ int ldisc;
+
+ if (get_user(ldisc, arg))
+ return -EFAULT;
+ return tty_set_ldisc(tty, ldisc);
+}
+
+static int send_break(struct tty_struct *tty, int duration)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ tty->driver.break_ctl(tty, -1);
+ if (!signal_pending(current))
+ schedule_timeout(duration);
+ tty->driver.break_ctl(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ return 0;
+}
+
+/*
+ * Split this up, as gcc can choke on it otherwise..
+ */
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ struct tty_struct *tty, *real_tty;
+ int retval;
+
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_ioctl"))
+ return -EINVAL;
+
+ real_tty = tty;
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER)
+ real_tty = tty->link;
+
+ /*
+ * Break handling by driver
+ */
+ if (!tty->driver.break_ctl) {
+ switch(cmd) {
+ case TIOCSBRK:
+ case TIOCCBRK:
+ if (tty->driver.ioctl)
+ return tty->driver.ioctl(tty, file, cmd, arg);
+ return -EINVAL;
+
+ /* These two ioctl's always return success; even if */
+ /* the driver doesn't support them. */
+ case TCSBRK:
+ case TCSBRKP:
+ if (!tty->driver.ioctl)
+ return 0;
+ retval = tty->driver.ioctl(tty, file, cmd, arg);
+ if (retval == -ENOIOCTLCMD)
+ retval = 0;
+ return retval;
+ }
+ }
+
+ /*
+ * Factor out some common prep work
+ */
+ switch (cmd) {
+ case TIOCSETD:
+ case TIOCSBRK:
+ case TIOCCBRK:
+ case TCSBRK:
+ case TCSBRKP:
+ retval = tty_check_change(tty);
+ if (retval)
+ return retval;
+ if (cmd != TIOCCBRK) {
+ tty_wait_until_sent(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ break;
+ }
+
+ switch (cmd) {
+ case TIOCSTI:
+ return tiocsti(tty, (char *)arg);
+ case TIOCGWINSZ:
+ return tiocgwinsz(tty, (struct winsize *) arg);
+ case TIOCSWINSZ:
+ return tiocswinsz(tty, real_tty, (struct winsize *) arg);
+ case TIOCCONS:
+ return tioccons(inode, tty, real_tty);
+ case FIONBIO:
+ return fionbio(file, (int *) arg);
+ case TIOCEXCL:
+ set_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNXCL:
+ clear_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNOTTY:
+ if (current->tty != tty)
+ return -ENOTTY;
+ if (current->leader)
+ disassociate_ctty(0);
+ task_lock(current);
+ current->tty = NULL;
+ task_unlock(current);
+ return 0;
+ case TIOCSCTTY:
+ return tiocsctty(tty, arg);
+ case TIOCGPGRP:
+ return tiocgpgrp(tty, real_tty, (pid_t *) arg);
+ case TIOCSPGRP:
+ return tiocspgrp(tty, real_tty, (pid_t *) arg);
+ case TIOCGSID:
+ return tiocgsid(tty, real_tty, (pid_t *) arg);
+ case TIOCGETD:
+ return put_user(tty->ldisc.num, (int *) arg);
+ case TIOCSETD:
+ return tiocsetd(tty, (int *) arg);
+#ifdef CONFIG_VT
+ case TIOCLINUX:
+ return tioclinux(tty, arg);
+#endif
+ case TIOCTTYGSTRUCT:
+ return tiocttygstruct(tty, (struct tty_struct *) arg);
+
+ /*
+ * Break handling
+ */
+ case TIOCSBRK: /* Turn break on, unconditionally */
+ tty->driver.break_ctl(tty, -1);
+ return 0;
+
+ case TIOCCBRK: /* Turn break off, unconditionally */
+ tty->driver.break_ctl(tty, 0);
+ return 0;
+ case TCSBRK: /* SVID version: non-zero arg --> no break */
+ /*
+ * XXX is the above comment correct, or the
+ * code below correct? Is this ioctl used at
+ * all by anyone?
+ */
+ if (!arg)
+ return send_break(tty, HZ/4);
+ return 0;
+ case TCSBRKP: /* support for POSIX tcsendbreak() */
+ return send_break(tty, arg ? arg*(HZ/10) : HZ/4);
+ }
+ if (tty->driver.ioctl) {
+ int retval = (tty->driver.ioctl)(tty, file, cmd, arg);
+ if (retval != -ENOIOCTLCMD)
+ return retval;
+ }
+ if (tty->ldisc.ioctl) {
+ int retval = (tty->ldisc.ioctl)(tty, file, cmd, arg);
+ if (retval != -ENOIOCTLCMD)
+ return retval;
+ }
+ return -EINVAL;
+}
+
+
+/*
+ * This implements the "Secure Attention Key" --- the idea is to
+ * prevent trojan horses by killing all processes associated with this
+ * tty when the user hits the "Secure Attention Key". Required for
+ * super-paranoid applications --- see the Orange Book for more details.
+ *
+ * This code could be nicer; ideally it should send a HUP, wait a few
+ * seconds, then send a INT, and then a KILL signal. But you then
+ * have to coordinate with the init process, since all processes associated
+ * with the current tty must be dead before the new getty is allowed
+ * to spawn.
+ *
+ * Now, if it would be correct ;-/ The current code has a nasty hole -
+ * it doesn't catch files in flight. We may send the descriptor to ourselves
+ * via AF_UNIX socket, close it and later fetch from socket. FIXME.
+ *
+ * Nasty bug: do_SAK is being called in interrupt context. This can
+ * deadlock. We punt it up to process context. AKPM - 16Mar2001
+ */
+static void __do_SAK(void *arg)
+{
+#ifdef TTY_SOFT_SAK
+ tty_hangup(tty);
+#else
+ struct tty_struct *tty = arg;
+ struct task_struct *p;
+ int session;
+ int i;
+ struct file *filp;
+
+ if (!tty)
+ return;
+ session = tty->session;
+ if (tty->ldisc.flush_buffer)
+ tty->ldisc.flush_buffer(tty);
+ if (tty->driver.flush_buffer)
+ tty->driver.flush_buffer(tty);
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((p->tty == tty) ||
+ ((session > 0) && (p->session == session))) {
+ send_sig(SIGKILL, p, 1);
+ continue;
+ }
+ task_lock(p);
+ if (p->files) {
+ read_lock(&p->files->file_lock);
+ for (i=0; i < p->files->max_fds; i++) {
+ filp = fcheck_files(p->files, i);
+ if (filp && (filp->f_op == &tty_fops) &&
+ (filp->private_data == tty)) {
+ send_sig(SIGKILL, p, 1);
+ break;
+ }
+ }
+ read_unlock(&p->files->file_lock);
+ }
+ task_unlock(p);
+ }
+ read_unlock(&tasklist_lock);
+#endif
+}
+
+/*
+ * The tq handling here is a little racy - tty->SAK_tq may already be queued.
+ * But there's no mechanism to fix that without futzing with tqueue_lock.
+ * Fortunately we don't need to worry, because if ->SAK_tq is already queued,
+ * the values which we write to it will be identical to the values which it
+ * already has. --akpm
+ */
+void do_SAK(struct tty_struct *tty)
+{
+ if (!tty)
+ return;
+ PREPARE_TQUEUE(&tty->SAK_tq, __do_SAK, tty);
+ schedule_task(&tty->SAK_tq);
+}
+
+/*
+ * This routine is called out of the software interrupt to flush data
+ * from the flip buffer to the line discipline.
+ */
+static void flush_to_ldisc(void *private_)
+{
+ struct tty_struct *tty = (struct tty_struct *) private_;
+ unsigned char *cp;
+ char *fp;
+ int count;
+ unsigned long flags;
+
+ if (test_bit(TTY_DONT_FLIP, &tty->flags)) {
+ queue_task(&tty->flip.tqueue, &tq_timer);
+ return;
+ }
+ if (tty->flip.buf_num) {
+ cp = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ fp = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.buf_num = 0;
+
+ save_flags(flags); cli();
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ } else {
+ cp = tty->flip.char_buf;
+ fp = tty->flip.flag_buf;
+ tty->flip.buf_num = 1;
+
+ save_flags(flags); cli();
+ tty->flip.char_buf_ptr = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ }
+ count = tty->flip.count;
+ tty->flip.count = 0;
+ restore_flags(flags);
+
+ tty->ldisc.receive_buf(tty, cp, fp, count);
+}
+
+/*
+ * Routine which returns the baud rate of the tty
+ *
+ * Note that the baud_table needs to be kept in sync with the
+ * include/asm/termbits.h file.
+ */
+static int baud_table[] = {
+ 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800,
+ 9600, 19200, 38400, 57600, 115200, 230400, 460800,
+#ifdef __sparc__
+ 76800, 153600, 307200, 614400, 921600
+#else
+ 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000,
+ 2500000, 3000000, 3500000, 4000000
+#endif
+};
+
+static int n_baud_table = sizeof(baud_table)/sizeof(int);
+
+int tty_get_baud_rate(struct tty_struct *tty)
+{
+ unsigned int cflag, i;
+
+ cflag = tty->termios->c_cflag;
+
+ i = cflag & CBAUD;
+ if (i & CBAUDEX) {
+ i &= ~CBAUDEX;
+ if (i < 1 || i+15 >= n_baud_table)
+ tty->termios->c_cflag &= ~CBAUDEX;
+ else
+ i += 15;
+ }
+ if (i==15 && tty->alt_speed) {
+ if (!tty->warned) {
+ printk(KERN_WARNING "Use of setserial/setrocket to "
+ "set SPD_* flags is deprecated\n");
+ tty->warned = 1;
+ }
+ return(tty->alt_speed);
+ }
+
+ return baud_table[i];
+}
+
+void tty_flip_buffer_push(struct tty_struct *tty)
+{
+ if (tty->low_latency)
+ flush_to_ldisc((void *) tty);
+ else
+ queue_task(&tty->flip.tqueue, &tq_timer);
+}
+
+/*
+ * This subroutine initializes a tty structure.
+ */
+static void initialize_tty_struct(struct tty_struct *tty)
+{
+ memset(tty, 0, sizeof(struct tty_struct));
+ tty->magic = TTY_MAGIC;
+ tty->ldisc = ldiscs[N_TTY];
+ tty->pgrp = -1;
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ tty->flip.tqueue.routine = flush_to_ldisc;
+ tty->flip.tqueue.data = tty;
+ init_MUTEX(&tty->flip.pty_sem);
+ init_waitqueue_head(&tty->write_wait);
+ init_waitqueue_head(&tty->read_wait);
+ tty->tq_hangup.routine = do_tty_hangup;
+ tty->tq_hangup.data = tty;
+ sema_init(&tty->atomic_read, 1);
+ sema_init(&tty->atomic_write, 1);
+ spin_lock_init(&tty->read_lock);
+ INIT_LIST_HEAD(&tty->tty_files);
+ INIT_TQUEUE(&tty->SAK_tq, 0, 0);
+}
+
+/*
+ * The default put_char routine if the driver did not define one.
+ */
+void tty_default_put_char(struct tty_struct *tty, unsigned char ch)
+{
+ tty->driver.write(tty, 0, &ch, 1);
+}
+
+/*
+ * Register a tty device described by <driver>, with minor number <minor>.
+ */
+void tty_register_devfs (struct tty_driver *driver, unsigned int flags, unsigned minor)
+{
+#ifdef CONFIG_DEVFS_FS
+ umode_t mode = S_IFCHR | S_IRUSR | S_IWUSR;
+ kdev_t device = MKDEV (driver->major, minor);
+ int idx = minor - driver->minor_start;
+ char buf[32];
+
+ switch (device) {
+ case TTY_DEV:
+ case PTMX_DEV:
+ mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+ break;
+ default:
+ if (driver->major == PTY_MASTER_MAJOR)
+ mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+ break;
+ }
+ if ( (minor < driver->minor_start) ||
+ (minor >= driver->minor_start + driver->num) ) {
+ printk(KERN_ERR "Attempt to register invalid minor number "
+ "with devfs (%d:%d).\n", (int)driver->major,(int)minor);
+ return;
+ }
+# ifdef CONFIG_UNIX98_PTYS
+ if ( (driver->major >= UNIX98_PTY_SLAVE_MAJOR) &&
+ (driver->major < UNIX98_PTY_SLAVE_MAJOR + UNIX98_NR_MAJORS) )
+ flags |= DEVFS_FL_CURRENT_OWNER;
+# endif
+ sprintf(buf, driver->name, idx + driver->name_base);
+ devfs_register (NULL, buf, flags | DEVFS_FL_DEFAULT,
+ driver->major, minor, mode, &tty_fops, NULL);
+#endif /* CONFIG_DEVFS_FS */
+}
+
+void tty_unregister_devfs (struct tty_driver *driver, unsigned minor)
+{
+#ifdef CONFIG_DEVFS_FS
+ void * handle;
+ int idx = minor - driver->minor_start;
+ char buf[32];
+
+ sprintf(buf, driver->name, idx + driver->name_base);
+ handle = devfs_find_handle (NULL, buf, driver->major, minor,
+ DEVFS_SPECIAL_CHR, 0);
+ devfs_unregister (handle);
+#endif /* CONFIG_DEVFS_FS */
+}
+
+EXPORT_SYMBOL(tty_register_devfs);
+EXPORT_SYMBOL(tty_unregister_devfs);
+
+/*
+ * Called by a tty driver to register itself.
+ */
+int tty_register_driver(struct tty_driver *driver)
+{
+ int error;
+ int i;
+
+ if (driver->flags & TTY_DRIVER_INSTALLED)
+ return 0;
+
+ error = devfs_register_chrdev(driver->major, driver->name, &tty_fops);
+ if (error < 0)
+ return error;
+ else if(driver->major == 0)
+ driver->major = error;
+
+ if (!driver->put_char)
+ driver->put_char = tty_default_put_char;
+
+ driver->prev = 0;
+ driver->next = tty_drivers;
+ if (tty_drivers) tty_drivers->prev = driver;
+ tty_drivers = driver;
+
+ if ( !(driver->flags & TTY_DRIVER_NO_DEVFS) ) {
+ for(i = 0; i < driver->num; i++)
+ tty_register_devfs(driver, 0, driver->minor_start + i);
+ }
+ proc_tty_register_driver(driver);
+ return error;
+}
+
+/*
+ * Called by a tty driver to unregister itself.
+ */
+int tty_unregister_driver(struct tty_driver *driver)
+{
+ int retval;
+ struct tty_driver *p;
+ int i, found = 0;
+ struct termios *tp;
+ const char *othername = NULL;
+
+ if (*driver->refcount)
+ return -EBUSY;
+
+ for (p = tty_drivers; p; p = p->next) {
+ if (p == driver)
+ found++;
+ else if (p->major == driver->major)
+ othername = p->name;
+ }
+
+ if (!found)
+ return -ENOENT;
+
+ if (othername == NULL) {
+ retval = devfs_unregister_chrdev(driver->major, driver->name);
+ if (retval)
+ return retval;
+ } else
+ devfs_register_chrdev(driver->major, othername, &tty_fops);
+
+ if (driver->prev)
+ driver->prev->next = driver->next;
+ else
+ tty_drivers = driver->next;
+
+ if (driver->next)
+ driver->next->prev = driver->prev;
+
+ /*
+ * Free the termios and termios_locked structures because
+ * we don't want to get memory leaks when modular tty
+ * drivers are removed from the kernel.
+ */
+ for (i = 0; i < driver->num; i++) {
+ tp = driver->termios[i];
+ if (tp) {
+ driver->termios[i] = NULL;
+ kfree(tp);
+ }
+ tp = driver->termios_locked[i];
+ if (tp) {
+ driver->termios_locked[i] = NULL;
+ kfree(tp);
+ }
+ tty_unregister_devfs(driver, driver->minor_start + i);
+ }
+ proc_tty_unregister_driver(driver);
+ return 0;
+}
+
+
+/*
+ * Initialize the console device. This is called *early*, so
+ * we can't necessarily depend on lots of kernel help here.
+ * Just do some early initializations, and do the complex setup
+ * later.
+ */
+void __init console_init(void)
+{
+ /* Setup the default TTY line discipline. */
+ memset(ldiscs, 0, sizeof(ldiscs));
+ (void) tty_register_ldisc(N_TTY, &tty_ldisc_N_TTY);
+
+ /*
+ * Set up the standard termios. Individual tty drivers may
+ * deviate from this; this is used as a template.
+ */
+ memset(&tty_std_termios, 0, sizeof(struct termios));
+ memcpy(tty_std_termios.c_cc, INIT_C_CC, NCCS);
+ tty_std_termios.c_iflag = ICRNL | IXON;
+ tty_std_termios.c_oflag = OPOST | ONLCR;
+ tty_std_termios.c_cflag = B38400 | CS8 | CREAD | HUPCL;
+ tty_std_termios.c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK |
+ ECHOCTL | ECHOKE | IEXTEN;
+
+ /*
+ * set up the console device so that later boot sequences can
+ * inform about problems etc..
+ */
+#ifdef CONFIG_XENO
+ xeno_console_init();
+#endif
+#ifdef CONFIG_VT
+ con_init();
+#endif
+#ifdef CONFIG_AU1000_SERIAL_CONSOLE
+ au1000_serial_console_init();
+#endif
+#ifdef CONFIG_SERIAL_CONSOLE
+#if (defined(CONFIG_8xx) || defined(CONFIG_8260))
+ console_8xx_init();
+#elif defined(CONFIG_MAC_SERIAL)
+ mac_scc_console_init();
+#elif defined(CONFIG_PARISC)
+ pdc_console_init();
+#elif defined(CONFIG_SERIAL)
+ serial_console_init();
+#endif /* CONFIG_8xx */
+#ifdef CONFIG_SGI_SERIAL
+ sgi_serial_console_init();
+#endif
+#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC)
+ vme_scc_console_init();
+#endif
+#if defined(CONFIG_SERIAL167)
+ serial167_console_init();
+#endif
+#if defined(CONFIG_SH_SCI)
+ sci_console_init();
+#endif
+#endif
+#ifdef CONFIG_TN3270_CONSOLE
+ tub3270_con_init();
+#endif
+#ifdef CONFIG_TN3215
+ con3215_init();
+#endif
+#ifdef CONFIG_HWC
+ hwc_console_init();
+#endif
+#ifdef CONFIG_STDIO_CONSOLE
+ stdio_console_init();
+#endif
+#ifdef CONFIG_SERIAL_21285_CONSOLE
+ rs285_console_init();
+#endif
+#ifdef CONFIG_SERIAL_SA1100_CONSOLE
+ sa1100_rs_console_init();
+#endif
+#ifdef CONFIG_ARC_CONSOLE
+ arc_console_init();
+#endif
+#ifdef CONFIG_SERIAL_AMBA_CONSOLE
+ ambauart_console_init();
+#endif
+#ifdef CONFIG_SERIAL_TX3912_CONSOLE
+ tx3912_console_init();
+#endif
+}
+
+static struct tty_driver dev_tty_driver, dev_syscons_driver;
+#ifdef CONFIG_UNIX98_PTYS
+static struct tty_driver dev_ptmx_driver;
+#endif
+#ifdef CONFIG_VT
+static struct tty_driver dev_console_driver;
+#endif
+
+/*
+ * Ok, now we can initialize the rest of the tty devices and can count
+ * on memory allocations, interrupts etc..
+ */
+void __init tty_init(void)
+{
+ /*
+ * dev_tty_driver and dev_console_driver are actually magic
+ * devices which get redirected at open time. Nevertheless,
+ * we register them so that register_chrdev is called
+ * appropriately.
+ */
+ memset(&dev_tty_driver, 0, sizeof(struct tty_driver));
+ dev_tty_driver.magic = TTY_DRIVER_MAGIC;
+ dev_tty_driver.driver_name = "/dev/tty";
+ dev_tty_driver.name = dev_tty_driver.driver_name + 5;
+ dev_tty_driver.name_base = 0;
+ dev_tty_driver.major = TTYAUX_MAJOR;
+ dev_tty_driver.minor_start = 0;
+ dev_tty_driver.num = 1;
+ dev_tty_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_tty_driver.subtype = SYSTEM_TYPE_TTY;
+
+ if (tty_register_driver(&dev_tty_driver))
+ panic("Couldn't register /dev/tty driver\n");
+
+ dev_syscons_driver = dev_tty_driver;
+ dev_syscons_driver.driver_name = "/dev/console";
+ dev_syscons_driver.name = dev_syscons_driver.driver_name + 5;
+ dev_syscons_driver.major = TTYAUX_MAJOR;
+ dev_syscons_driver.minor_start = 1;
+ dev_syscons_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_syscons_driver.subtype = SYSTEM_TYPE_SYSCONS;
+
+ if (tty_register_driver(&dev_syscons_driver))
+ panic("Couldn't register /dev/console driver\n");
+
+ /* console calls tty_register_driver() before kmalloc() works.
+ * Thus, we can't devfs_register() then. Do so now, instead.
+ */
+#ifdef CONFIG_VT
+ con_init_devfs();
+#endif
+
+#ifdef CONFIG_UNIX98_PTYS
+ dev_ptmx_driver = dev_tty_driver;
+ dev_ptmx_driver.driver_name = "/dev/ptmx";
+ dev_ptmx_driver.name = dev_ptmx_driver.driver_name + 5;
+ dev_ptmx_driver.major= MAJOR(PTMX_DEV);
+ dev_ptmx_driver.minor_start = MINOR(PTMX_DEV);
+ dev_ptmx_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_ptmx_driver.subtype = SYSTEM_TYPE_SYSPTMX;
+
+ if (tty_register_driver(&dev_ptmx_driver))
+ panic("Couldn't register /dev/ptmx driver\n");
+#endif
+
+#ifdef CONFIG_VT
+ dev_console_driver = dev_tty_driver;
+ dev_console_driver.driver_name = "/dev/vc/0";
+ dev_console_driver.name = dev_console_driver.driver_name + 5;
+ dev_console_driver.major = TTY_MAJOR;
+ dev_console_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_console_driver.subtype = SYSTEM_TYPE_CONSOLE;
+
+ if (tty_register_driver(&dev_console_driver))
+ panic("Couldn't register /dev/tty0 driver\n");
+
+ kbd_init();
+#endif
+
+#ifdef CONFIG_ESPSERIAL /* init ESP before rs, so rs doesn't see the port */
+ espserial_init();
+#endif
+#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC)
+ vme_scc_init();
+#endif
+#ifdef CONFIG_SERIAL_TX3912
+ tx3912_rs_init();
+#endif
+#ifdef CONFIG_ROCKETPORT
+ rp_init();
+#endif
+#ifdef CONFIG_SERIAL167
+ serial167_init();
+#endif
+#ifdef CONFIG_CYCLADES
+ cy_init();
+#endif
+#ifdef CONFIG_STALLION
+ stl_init();
+#endif
+#ifdef CONFIG_ISTALLION
+ stli_init();
+#endif
+#ifdef CONFIG_DIGI
+ pcxe_init();
+#endif
+#ifdef CONFIG_DIGIEPCA
+ pc_init();
+#endif
+#ifdef CONFIG_SPECIALIX
+ specialix_init();
+#endif
+#if (defined(CONFIG_8xx) || defined(CONFIG_8260))
+ rs_8xx_init();
+#endif /* CONFIG_8xx */
+ pty_init();
+#ifdef CONFIG_MOXA_SMARTIO
+ mxser_init();
+#endif
+#ifdef CONFIG_MOXA_INTELLIO
+ moxa_init();
+#endif
+#ifdef CONFIG_VT
+ vcs_init();
+#endif
+#ifdef CONFIG_TN3270
+ tub3270_init();
+#endif
+#ifdef CONFIG_TN3215
+ tty3215_init();
+#endif
+#ifdef CONFIG_HWC
+ hwc_tty_init();
+#endif
+#ifdef CONFIG_A2232
+ a2232board_init();
+#endif
+}
--- /dev/null
+/*
+ * linux/fs/exec.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * #!-checking implemented by tytso.
+ */
+/*
+ * Demand-loading implemented 01.12.91 - no need to read anything but
+ * the header into memory. The inode of the executable is put into
+ * "current->executable", and page faults do the actual loading. Clean.
+ *
+ * Once more I can proudly say that linux stood up to being changed: it
+ * was less than 2 hours work to get demand-loading completely implemented.
+ *
+ * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead,
+ * current->executable is only used by the procfs. This allows a dispatch
+ * table to check for several different types of binary formats. We keep
+ * trying until we recognize the file or we run out of supported binary
+ * formats.
+ */
+
+#include <linux/config.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/mman.h>
+#include <linux/a.out.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+#include <linux/personality.h>
+#define __NO_VERSION__
+#include <linux/module.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/mmu_context.h>
+
+#ifdef CONFIG_KMOD
+#include <linux/kmod.h>
+#endif
+
+int core_uses_pid;
+
+static struct linux_binfmt *formats;
+static rwlock_t binfmt_lock = RW_LOCK_UNLOCKED;
+
+int register_binfmt(struct linux_binfmt * fmt)
+{
+ struct linux_binfmt ** tmp = &formats;
+
+ if (!fmt)
+ return -EINVAL;
+ if (fmt->next)
+ return -EBUSY;
+ write_lock(&binfmt_lock);
+ while (*tmp) {
+ if (fmt == *tmp) {
+ write_unlock(&binfmt_lock);
+ return -EBUSY;
+ }
+ tmp = &(*tmp)->next;
+ }
+ fmt->next = formats;
+ formats = fmt;
+ write_unlock(&binfmt_lock);
+ return 0;
+}
+
+int unregister_binfmt(struct linux_binfmt * fmt)
+{
+ struct linux_binfmt ** tmp = &formats;
+
+ write_lock(&binfmt_lock);
+ while (*tmp) {
+ if (fmt == *tmp) {
+ *tmp = fmt->next;
+ write_unlock(&binfmt_lock);
+ return 0;
+ }
+ tmp = &(*tmp)->next;
+ }
+ write_unlock(&binfmt_lock);
+ return -EINVAL;
+}
+
+static inline void put_binfmt(struct linux_binfmt * fmt)
+{
+ if (fmt->module)
+ __MOD_DEC_USE_COUNT(fmt->module);
+}
+
+/*
+ * Note that a shared library must be both readable and executable due to
+ * security reasons.
+ *
+ * Also note that we take the address to load from from the file itself.
+ */
+asmlinkage long sys_uselib(const char * library)
+{
+ struct file * file;
+ struct nameidata nd;
+ int error;
+
+ error = user_path_walk(library, &nd);
+ if (error)
+ goto out;
+
+ error = -EINVAL;
+ if (!S_ISREG(nd.dentry->d_inode->i_mode))
+ goto exit;
+
+ error = permission(nd.dentry->d_inode, MAY_READ | MAY_EXEC);
+ if (error)
+ goto exit;
+
+ file = dentry_open(nd.dentry, nd.mnt, O_RDONLY);
+ error = PTR_ERR(file);
+ if (IS_ERR(file))
+ goto out;
+
+ error = -ENOEXEC;
+ if(file->f_op && file->f_op->read) {
+ struct linux_binfmt * fmt;
+
+ read_lock(&binfmt_lock);
+ for (fmt = formats ; fmt ; fmt = fmt->next) {
+ if (!fmt->load_shlib)
+ continue;
+ if (!try_inc_mod_count(fmt->module))
+ continue;
+ read_unlock(&binfmt_lock);
+ error = fmt->load_shlib(file);
+ read_lock(&binfmt_lock);
+ put_binfmt(fmt);
+ if (error != -ENOEXEC)
+ break;
+ }
+ read_unlock(&binfmt_lock);
+ }
+ fput(file);
+out:
+ return error;
+exit:
+ path_release(&nd);
+ goto out;
+}
+
+/*
+ * count() counts the number of arguments/envelopes
+ */
+static int count(char ** argv, int max)
+{
+ int i = 0;
+
+ if (argv != NULL) {
+ for (;;) {
+ char * p;
+
+ if (get_user(p, argv))
+ return -EFAULT;
+ if (!p)
+ break;
+ argv++;
+ if(++i > max)
+ return -E2BIG;
+ }
+ }
+ return i;
+}
+
+/*
+ * 'copy_strings()' copies argument/envelope strings from user
+ * memory to free pages in kernel mem. These are in a format ready
+ * to be put directly into the top of new user memory.
+ */
+int copy_strings(int argc,char ** argv, struct linux_binprm *bprm)
+{
+ while (argc-- > 0) {
+ char *str;
+ int len;
+ unsigned long pos;
+
+ if (get_user(str, argv+argc) || !(len = strnlen_user(str, bprm->p)))
+ return -EFAULT;
+ if (bprm->p < len)
+ return -E2BIG;
+
+ bprm->p -= len;
+ /* XXX: add architecture specific overflow check here. */
+
+ pos = bprm->p;
+ while (len > 0) {
+ char *kaddr;
+ int i, new, err;
+ struct page *page;
+ int offset, bytes_to_copy;
+
+ offset = pos % PAGE_SIZE;
+ i = pos/PAGE_SIZE;
+ page = bprm->page[i];
+ new = 0;
+ if (!page) {
+ page = alloc_page(GFP_HIGHUSER);
+ bprm->page[i] = page;
+ if (!page)
+ return -ENOMEM;
+ new = 1;
+ }
+ kaddr = kmap(page);
+
+ if (new && offset)
+ memset(kaddr, 0, offset);
+ bytes_to_copy = PAGE_SIZE - offset;
+ if (bytes_to_copy > len) {
+ bytes_to_copy = len;
+ if (new)
+ memset(kaddr+offset+len, 0, PAGE_SIZE-offset-len);
+ }
+ err = copy_from_user(kaddr + offset, str, bytes_to_copy);
+ kunmap(page);
+
+ if (err)
+ return -EFAULT;
+
+ pos += bytes_to_copy;
+ str += bytes_to_copy;
+ len -= bytes_to_copy;
+ }
+ }
+ return 0;
+}
+
+/*
+ * Like copy_strings, but get argv and its values from kernel memory.
+ */
+int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm)
+{
+ int r;
+ mm_segment_t oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ r = copy_strings(argc, argv, bprm);
+ set_fs(oldfs);
+ return r;
+}
+
+/*
+ * This routine is used to map in a page into an address space: needed by
+ * execve() for the initial stack and environment pages.
+ *
+ * tsk->mmap_sem is held for writing.
+ */
+void put_dirty_page(struct task_struct * tsk, struct page *page, unsigned long address)
+{
+ pgd_t * pgd;
+ pmd_t * pmd;
+ pte_t * pte;
+
+ if (page_count(page) != 1)
+ printk(KERN_ERR "mem_map disagrees with %p at %08lx\n", page, address);
+ pgd = pgd_offset(tsk->mm, address);
+
+ spin_lock(&tsk->mm->page_table_lock);
+ pmd = pmd_alloc(tsk->mm, pgd, address);
+ if (!pmd)
+ goto out;
+ pte = pte_alloc(tsk->mm, pmd, address);
+ if (!pte)
+ goto out;
+ if (!pte_none(*pte))
+ goto out;
+ lru_cache_add(page);
+ flush_dcache_page(page);
+ flush_page_to_ram(page);
+ set_pte(pte, pte_mkdirty(pte_mkwrite(mk_pte(page, PAGE_COPY))));
+ XENO_flush_page_update_queue();
+ tsk->mm->rss++;
+ spin_unlock(&tsk->mm->page_table_lock);
+
+ /* no need for flush_tlb */
+ return;
+out:
+ spin_unlock(&tsk->mm->page_table_lock);
+ __free_page(page);
+ force_sig(SIGKILL, tsk);
+ return;
+}
+
+int setup_arg_pages(struct linux_binprm *bprm)
+{
+ unsigned long stack_base;
+ struct vm_area_struct *mpnt;
+ int i;
+
+ stack_base = STACK_TOP - MAX_ARG_PAGES*PAGE_SIZE;
+
+ bprm->p += stack_base;
+ if (bprm->loader)
+ bprm->loader += stack_base;
+ bprm->exec += stack_base;
+
+ mpnt = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!mpnt)
+ return -ENOMEM;
+
+ down_write(¤t->mm->mmap_sem);
+ {
+ mpnt->vm_mm = current->mm;
+ mpnt->vm_start = PAGE_MASK & (unsigned long) bprm->p;
+ mpnt->vm_end = STACK_TOP;
+ mpnt->vm_page_prot = PAGE_COPY;
+ mpnt->vm_flags = VM_STACK_FLAGS;
+ mpnt->vm_ops = NULL;
+ mpnt->vm_pgoff = 0;
+ mpnt->vm_file = NULL;
+ mpnt->vm_private_data = (void *) 0;
+ insert_vm_struct(current->mm, mpnt);
+ current->mm->total_vm = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
+ }
+
+ for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
+ struct page *page = bprm->page[i];
+ if (page) {
+ bprm->page[i] = NULL;
+ put_dirty_page(current,page,stack_base);
+ }
+ stack_base += PAGE_SIZE;
+ }
+ up_write(¤t->mm->mmap_sem);
+
+ return 0;
+}
+
+struct file *open_exec(const char *name)
+{
+ struct nameidata nd;
+ struct inode *inode;
+ struct file *file;
+ int err = 0;
+
+ if (path_init(name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, &nd))
+ err = path_walk(name, &nd);
+ file = ERR_PTR(err);
+ if (!err) {
+ inode = nd.dentry->d_inode;
+ file = ERR_PTR(-EACCES);
+ if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
+ S_ISREG(inode->i_mode)) {
+ int err = permission(inode, MAY_EXEC);
+ if (!err && !(inode->i_mode & 0111))
+ err = -EACCES;
+ file = ERR_PTR(err);
+ if (!err) {
+ file = dentry_open(nd.dentry, nd.mnt, O_RDONLY);
+ if (!IS_ERR(file)) {
+ err = deny_write_access(file);
+ if (err) {
+ fput(file);
+ file = ERR_PTR(err);
+ }
+ }
+out:
+ return file;
+ }
+ }
+ path_release(&nd);
+ }
+ goto out;
+}
+
+int kernel_read(struct file *file, unsigned long offset,
+ char * addr, unsigned long count)
+{
+ mm_segment_t old_fs;
+ loff_t pos = offset;
+ int result = -ENOSYS;
+
+ if (!file->f_op->read)
+ goto fail;
+ old_fs = get_fs();
+ set_fs(get_ds());
+ result = file->f_op->read(file, addr, count, &pos);
+ set_fs(old_fs);
+fail:
+ return result;
+}
+
+static int exec_mmap(void)
+{
+ struct mm_struct * mm, * old_mm;
+
+ old_mm = current->mm;
+ if (old_mm && atomic_read(&old_mm->mm_users) == 1) {
+ mm_release();
+ exit_mmap(old_mm);
+ return 0;
+ }
+
+ mm = mm_alloc();
+ if (mm) {
+ struct mm_struct *active_mm;
+
+ if (init_new_context(current, mm)) {
+ mmdrop(mm);
+ return -ENOMEM;
+ }
+
+ /* Add it to the list of mm's */
+ spin_lock(&mmlist_lock);
+ list_add(&mm->mmlist, &init_mm.mmlist);
+ mmlist_nr++;
+ spin_unlock(&mmlist_lock);
+
+ task_lock(current);
+ active_mm = current->active_mm;
+ current->mm = mm;
+ current->active_mm = mm;
+ task_unlock(current);
+ activate_mm(active_mm, mm);
+ mm_release();
+ if (old_mm) {
+ if (active_mm != old_mm) BUG();
+ mmput(old_mm);
+ return 0;
+ }
+ mmdrop(active_mm);
+ return 0;
+ }
+ return -ENOMEM;
+}
+
+/*
+ * This function makes sure the current process has its own signal table,
+ * so that flush_signal_handlers can later reset the handlers without
+ * disturbing other processes. (Other processes might share the signal
+ * table via the CLONE_SIGNAL option to clone().)
+ */
+
+static inline int make_private_signals(void)
+{
+ struct signal_struct * newsig;
+
+ if (atomic_read(¤t->sig->count) <= 1)
+ return 0;
+ newsig = kmem_cache_alloc(sigact_cachep, GFP_KERNEL);
+ if (newsig == NULL)
+ return -ENOMEM;
+ spin_lock_init(&newsig->siglock);
+ atomic_set(&newsig->count, 1);
+ memcpy(newsig->action, current->sig->action, sizeof(newsig->action));
+ spin_lock_irq(¤t->sigmask_lock);
+ current->sig = newsig;
+ spin_unlock_irq(¤t->sigmask_lock);
+ return 0;
+}
+
+/*
+ * If make_private_signals() made a copy of the signal table, decrement the
+ * refcount of the original table, and free it if necessary.
+ * We don't do that in make_private_signals() so that we can back off
+ * in flush_old_exec() if an error occurs after calling make_private_signals().
+ */
+
+static inline void release_old_signals(struct signal_struct * oldsig)
+{
+ if (current->sig == oldsig)
+ return;
+ if (atomic_dec_and_test(&oldsig->count))
+ kmem_cache_free(sigact_cachep, oldsig);
+}
+
+/*
+ * These functions flushes out all traces of the currently running executable
+ * so that a new one can be started
+ */
+
+static inline void flush_old_files(struct files_struct * files)
+{
+ long j = -1;
+
+ write_lock(&files->file_lock);
+ for (;;) {
+ unsigned long set, i;
+
+ j++;
+ i = j * __NFDBITS;
+ if (i >= files->max_fds || i >= files->max_fdset)
+ break;
+ set = files->close_on_exec->fds_bits[j];
+ if (!set)
+ continue;
+ files->close_on_exec->fds_bits[j] = 0;
+ write_unlock(&files->file_lock);
+ for ( ; set ; i++,set >>= 1) {
+ if (set & 1) {
+ sys_close(i);
+ }
+ }
+ write_lock(&files->file_lock);
+
+ }
+ write_unlock(&files->file_lock);
+}
+
+/*
+ * An execve() will automatically "de-thread" the process.
+ * Note: we don't have to hold the tasklist_lock to test
+ * whether we migth need to do this. If we're not part of
+ * a thread group, there is no way we can become one
+ * dynamically. And if we are, we only need to protect the
+ * unlink - even if we race with the last other thread exit,
+ * at worst the list_del_init() might end up being a no-op.
+ */
+static inline void de_thread(struct task_struct *tsk)
+{
+ if (!list_empty(&tsk->thread_group)) {
+ write_lock_irq(&tasklist_lock);
+ list_del_init(&tsk->thread_group);
+ write_unlock_irq(&tasklist_lock);
+ }
+
+ /* Minor oddity: this might stay the same. */
+ tsk->tgid = tsk->pid;
+}
+
+int flush_old_exec(struct linux_binprm * bprm)
+{
+ char * name;
+ int i, ch, retval;
+ struct signal_struct * oldsig;
+
+ /*
+ * Make sure we have a private signal table
+ */
+ oldsig = current->sig;
+ retval = make_private_signals();
+ if (retval) goto flush_failed;
+
+ /*
+ * Release all of the old mmap stuff
+ */
+ retval = exec_mmap();
+ if (retval) goto mmap_failed;
+
+ /* This is the point of no return */
+ release_old_signals(oldsig);
+
+ current->sas_ss_sp = current->sas_ss_size = 0;
+
+ if (current->euid == current->uid && current->egid == current->gid)
+ current->mm->dumpable = 1;
+ name = bprm->filename;
+ for (i=0; (ch = *(name++)) != '\0';) {
+ if (ch == '/')
+ i = 0;
+ else
+ if (i < 15)
+ current->comm[i++] = ch;
+ }
+ current->comm[i] = '\0';
+
+ flush_thread();
+
+ de_thread(current);
+
+ if (bprm->e_uid != current->euid || bprm->e_gid != current->egid ||
+ permission(bprm->file->f_dentry->d_inode,MAY_READ))
+ current->mm->dumpable = 0;
+
+ /* An exec changes our domain. We are no longer part of the thread
+ group */
+
+ current->self_exec_id++;
+
+ flush_signal_handlers(current);
+ flush_old_files(current->files);
+
+ return 0;
+
+mmap_failed:
+flush_failed:
+ spin_lock_irq(¤t->sigmask_lock);
+ if (current->sig != oldsig) {
+ kfree(current->sig);
+ current->sig = oldsig;
+ }
+ spin_unlock_irq(¤t->sigmask_lock);
+ return retval;
+}
+
+/*
+ * We mustn't allow tracing of suid binaries, unless
+ * the tracer has the capability to trace anything..
+ */
+static inline int must_not_trace_exec(struct task_struct * p)
+{
+ return (p->ptrace & PT_PTRACED) && !(p->ptrace & PT_PTRACE_CAP);
+}
+
+/*
+ * Fill the binprm structure from the inode.
+ * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
+ */
+int prepare_binprm(struct linux_binprm *bprm)
+{
+ int mode;
+ struct inode * inode = bprm->file->f_dentry->d_inode;
+
+ mode = inode->i_mode;
+ /*
+ * Check execute perms again - if the caller has CAP_DAC_OVERRIDE,
+ * vfs_permission lets a non-executable through
+ */
+ if (!(mode & 0111)) /* with at least _one_ execute bit set */
+ return -EACCES;
+ if (bprm->file->f_op == NULL)
+ return -EACCES;
+
+ bprm->e_uid = current->euid;
+ bprm->e_gid = current->egid;
+
+ if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
+ /* Set-uid? */
+ if (mode & S_ISUID)
+ bprm->e_uid = inode->i_uid;
+
+ /* Set-gid? */
+ /*
+ * If setgid is set but no group execute bit then this
+ * is a candidate for mandatory locking, not a setgid
+ * executable.
+ */
+ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
+ bprm->e_gid = inode->i_gid;
+ }
+
+ /* We don't have VFS support for capabilities yet */
+ cap_clear(bprm->cap_inheritable);
+ cap_clear(bprm->cap_permitted);
+ cap_clear(bprm->cap_effective);
+
+ /* To support inheritance of root-permissions and suid-root
+ * executables under compatibility mode, we raise all three
+ * capability sets for the file.
+ *
+ * If only the real uid is 0, we only raise the inheritable
+ * and permitted sets of the executable file.
+ */
+
+ if (!issecure(SECURE_NOROOT)) {
+ if (bprm->e_uid == 0 || current->uid == 0) {
+ cap_set_full(bprm->cap_inheritable);
+ cap_set_full(bprm->cap_permitted);
+ }
+ if (bprm->e_uid == 0)
+ cap_set_full(bprm->cap_effective);
+ }
+
+ memset(bprm->buf,0,BINPRM_BUF_SIZE);
+ return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
+}
+
+/*
+ * This function is used to produce the new IDs and capabilities
+ * from the old ones and the file's capabilities.
+ *
+ * The formula used for evolving capabilities is:
+ *
+ * pI' = pI
+ * (***) pP' = (fP & X) | (fI & pI)
+ * pE' = pP' & fE [NB. fE is 0 or ~0]
+ *
+ * I=Inheritable, P=Permitted, E=Effective // p=process, f=file
+ * ' indicates post-exec(), and X is the global 'cap_bset'.
+ *
+ */
+
+void compute_creds(struct linux_binprm *bprm)
+{
+ kernel_cap_t new_permitted, working;
+ int do_unlock = 0;
+
+ new_permitted = cap_intersect(bprm->cap_permitted, cap_bset);
+ working = cap_intersect(bprm->cap_inheritable,
+ current->cap_inheritable);
+ new_permitted = cap_combine(new_permitted, working);
+
+ if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
+ !cap_issubset(new_permitted, current->cap_permitted)) {
+ current->mm->dumpable = 0;
+
+ lock_kernel();
+ if (must_not_trace_exec(current)
+ || atomic_read(¤t->fs->count) > 1
+ || atomic_read(¤t->files->count) > 1
+ || atomic_read(¤t->sig->count) > 1) {
+ if(!capable(CAP_SETUID)) {
+ bprm->e_uid = current->uid;
+ bprm->e_gid = current->gid;
+ }
+ if(!capable(CAP_SETPCAP)) {
+ new_permitted = cap_intersect(new_permitted,
+ current->cap_permitted);
+ }
+ }
+ do_unlock = 1;
+ }
+
+
+ /* For init, we want to retain the capabilities set
+ * in the init_task struct. Thus we skip the usual
+ * capability rules */
+ if (current->pid != 1) {
+ current->cap_permitted = new_permitted;
+ current->cap_effective =
+ cap_intersect(new_permitted, bprm->cap_effective);
+ }
+
+ /* AUD: Audit candidate if current->cap_effective is set */
+
+ current->suid = current->euid = current->fsuid = bprm->e_uid;
+ current->sgid = current->egid = current->fsgid = bprm->e_gid;
+
+ if(do_unlock)
+ unlock_kernel();
+ current->keep_capabilities = 0;
+}
+
+
+void remove_arg_zero(struct linux_binprm *bprm)
+{
+ if (bprm->argc) {
+ unsigned long offset;
+ char * kaddr;
+ struct page *page;
+
+ offset = bprm->p % PAGE_SIZE;
+ goto inside;
+
+ while (bprm->p++, *(kaddr+offset++)) {
+ if (offset != PAGE_SIZE)
+ continue;
+ offset = 0;
+ kunmap(page);
+inside:
+ page = bprm->page[bprm->p/PAGE_SIZE];
+ kaddr = kmap(page);
+ }
+ kunmap(page);
+ bprm->argc--;
+ }
+}
+
+/*
+ * cycle the list of binary formats handler, until one recognizes the image
+ */
+int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
+{
+ int try,retval=0;
+ struct linux_binfmt *fmt;
+#ifdef __alpha__
+ /* handle /sbin/loader.. */
+ {
+ struct exec * eh = (struct exec *) bprm->buf;
+
+ if (!bprm->loader && eh->fh.f_magic == 0x183 &&
+ (eh->fh.f_flags & 0x3000) == 0x3000)
+ {
+ struct file * file;
+ unsigned long loader;
+
+ allow_write_access(bprm->file);
+ fput(bprm->file);
+ bprm->file = NULL;
+
+ loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
+
+ file = open_exec("/sbin/loader");
+ retval = PTR_ERR(file);
+ if (IS_ERR(file))
+ return retval;
+
+ /* Remember if the application is TASO. */
+ bprm->sh_bang = eh->ah.entry < 0x100000000;
+
+ bprm->file = file;
+ bprm->loader = loader;
+ retval = prepare_binprm(bprm);
+ if (retval<0)
+ return retval;
+ /* should call search_binary_handler recursively here,
+ but it does not matter */
+ }
+ }
+#endif
+ /* kernel module loader fixup */
+ /* so we don't try to load run modprobe in kernel space. */
+ set_fs(USER_DS);
+ for (try=0; try<2; try++) {
+ read_lock(&binfmt_lock);
+ for (fmt = formats ; fmt ; fmt = fmt->next) {
+ int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
+ if (!fn)
+ continue;
+ if (!try_inc_mod_count(fmt->module))
+ continue;
+ read_unlock(&binfmt_lock);
+ retval = fn(bprm, regs);
+ if (retval >= 0) {
+ put_binfmt(fmt);
+ allow_write_access(bprm->file);
+ if (bprm->file)
+ fput(bprm->file);
+ bprm->file = NULL;
+ current->did_exec = 1;
+ return retval;
+ }
+ read_lock(&binfmt_lock);
+ put_binfmt(fmt);
+ if (retval != -ENOEXEC)
+ break;
+ if (!bprm->file) {
+ read_unlock(&binfmt_lock);
+ return retval;
+ }
+ }
+ read_unlock(&binfmt_lock);
+ if (retval != -ENOEXEC) {
+ break;
+#ifdef CONFIG_KMOD
+ }else{
+#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
+ char modname[20];
+ if (printable(bprm->buf[0]) &&
+ printable(bprm->buf[1]) &&
+ printable(bprm->buf[2]) &&
+ printable(bprm->buf[3]))
+ break; /* -ENOEXEC */
+ sprintf(modname, "binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
+ request_module(modname);
+#endif
+ }
+ }
+ return retval;
+}
+
+
+/*
+ * sys_execve() executes a new program.
+ */
+int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs)
+{
+ struct linux_binprm bprm;
+ struct file *file;
+ int retval;
+ int i;
+
+ file = open_exec(filename);
+
+ retval = PTR_ERR(file);
+ if (IS_ERR(file))
+ return retval;
+
+ bprm.p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
+ memset(bprm.page, 0, MAX_ARG_PAGES*sizeof(bprm.page[0]));
+
+ bprm.file = file;
+ bprm.filename = filename;
+ bprm.sh_bang = 0;
+ bprm.loader = 0;
+ bprm.exec = 0;
+ if ((bprm.argc = count(argv, bprm.p / sizeof(void *))) < 0) {
+ allow_write_access(file);
+ fput(file);
+ return bprm.argc;
+ }
+
+ if ((bprm.envc = count(envp, bprm.p / sizeof(void *))) < 0) {
+ allow_write_access(file);
+ fput(file);
+ return bprm.envc;
+ }
+
+ retval = prepare_binprm(&bprm);
+ if (retval < 0)
+ goto out;
+
+ retval = copy_strings_kernel(1, &bprm.filename, &bprm);
+ if (retval < 0)
+ goto out;
+
+ bprm.exec = bprm.p;
+ retval = copy_strings(bprm.envc, envp, &bprm);
+ if (retval < 0)
+ goto out;
+
+ retval = copy_strings(bprm.argc, argv, &bprm);
+ if (retval < 0)
+ goto out;
+
+ retval = search_binary_handler(&bprm,regs);
+ if (retval >= 0)
+ /* execve success */
+ return retval;
+
+out:
+ /* Something went wrong, return the inode and free the argument pages*/
+ allow_write_access(bprm.file);
+ if (bprm.file)
+ fput(bprm.file);
+
+ for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
+ struct page * page = bprm.page[i];
+ if (page)
+ __free_page(page);
+ }
+
+ return retval;
+}
+
+void set_binfmt(struct linux_binfmt *new)
+{
+ struct linux_binfmt *old = current->binfmt;
+ if (new && new->module)
+ __MOD_INC_USE_COUNT(new->module);
+ current->binfmt = new;
+ if (old && old->module)
+ __MOD_DEC_USE_COUNT(old->module);
+}
+
+int do_coredump(long signr, struct pt_regs * regs)
+{
+ struct linux_binfmt * binfmt;
+ char corename[6+sizeof(current->comm)+10];
+ struct file * file;
+ struct inode * inode;
+ int retval = 0;
+
+ lock_kernel();
+ binfmt = current->binfmt;
+ if (!binfmt || !binfmt->core_dump)
+ goto fail;
+ if (!current->mm->dumpable)
+ goto fail;
+ current->mm->dumpable = 0;
+ if (current->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump)
+ goto fail;
+
+ memcpy(corename,"core.", 5);
+ corename[4] = '\0';
+ if (core_uses_pid || atomic_read(¤t->mm->mm_users) != 1)
+ sprintf(&corename[4], ".%d", current->pid);
+ file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW, 0600);
+ if (IS_ERR(file))
+ goto fail;
+ inode = file->f_dentry->d_inode;
+ if (inode->i_nlink > 1)
+ goto close_fail; /* multiple links - don't dump */
+ if (d_unhashed(file->f_dentry))
+ goto close_fail;
+
+ if (!S_ISREG(inode->i_mode))
+ goto close_fail;
+ if (!file->f_op)
+ goto close_fail;
+ if (!file->f_op->write)
+ goto close_fail;
+ if (do_truncate(file->f_dentry, 0) != 0)
+ goto close_fail;
+
+ down_read(¤t->mm->mmap_sem);
+ retval = binfmt->core_dump(signr, regs, file);
+ up_read(¤t->mm->mmap_sem);
+
+close_fail:
+ filp_close(file, NULL);
+fail:
+ unlock_kernel();
+ return retval;
+}
--- /dev/null
+#ifndef __I386_A_OUT_H__
+#define __I386_A_OUT_H__
+
+struct exec
+{
+ unsigned long a_info; /* Use macros N_MAGIC, etc for access */
+ unsigned a_text; /* length of text, in bytes */
+ unsigned a_data; /* length of data, in bytes */
+ unsigned a_bss; /* length of uninitialized data area for file, in bytes */
+ unsigned a_syms; /* length of symbol table data in file, in bytes */
+ unsigned a_entry; /* start address */
+ unsigned a_trsize; /* length of relocation info for text, in bytes */
+ unsigned a_drsize; /* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a) ((a).a_trsize)
+#define N_DRSIZE(a) ((a).a_drsize)
+#define N_SYMSIZE(a) ((a).a_syms)
+
+#ifdef __KERNEL__
+
+#define STACK_TOP TASK_SIZE
+
+#endif
+
+#endif /* __A_OUT_GNU_H__ */
--- /dev/null
+#ifndef __ASM_APIC_H
+#define __ASM_APIC_H
+
+#include <linux/config.h>
+#include <linux/pm.h>
+#include <asm/apicdef.h>
+#include <asm/system.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#define APIC_DEBUG 0
+
+#if APIC_DEBUG
+#define Dprintk(x...) printk(x)
+#else
+#define Dprintk(x...)
+#endif
+
+/*
+ * Basic functions accessing APICs.
+ */
+
+static __inline void apic_write(unsigned long reg, unsigned long v)
+{
+ *((volatile unsigned long *)(APIC_BASE+reg)) = v;
+}
+
+static __inline void apic_write_atomic(unsigned long reg, unsigned long v)
+{
+ xchg((volatile unsigned long *)(APIC_BASE+reg), v);
+}
+
+static __inline unsigned long apic_read(unsigned long reg)
+{
+ return *((volatile unsigned long *)(APIC_BASE+reg));
+}
+
+static __inline__ void apic_wait_icr_idle(void)
+{
+ do { } while ( apic_read( APIC_ICR ) & APIC_ICR_BUSY );
+}
+
+#ifdef CONFIG_X86_GOOD_APIC
+# define FORCE_READ_AROUND_WRITE 0
+# define apic_read_around(x)
+# define apic_write_around(x,y) apic_write((x),(y))
+#else
+# define FORCE_READ_AROUND_WRITE 1
+# define apic_read_around(x) apic_read(x)
+# define apic_write_around(x,y) apic_write_atomic((x),(y))
+#endif
+
+static inline void ack_APIC_irq(void)
+{
+ /*
+ * ack_APIC_irq() actually gets compiled as a single instruction:
+ * - a single rmw on Pentium/82489DX
+ * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+ * ... yummie.
+ */
+
+ /* Docs say use 0 for future compatibility */
+ apic_write_around(APIC_EOI, 0);
+}
+
+extern int get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void connect_bsp_APIC (void);
+extern void disconnect_bsp_APIC (void);
+extern void disable_local_APIC (void);
+extern int verify_local_APIC (void);
+extern void cache_APIC_registers (void);
+extern void sync_Arb_IDs (void);
+extern void init_bsp_APIC (void);
+extern void setup_local_APIC (void);
+extern void init_apic_mappings (void);
+extern void smp_local_timer_interrupt (struct pt_regs * regs);
+extern void setup_APIC_clocks (void);
+extern void setup_apic_nmi_watchdog (void);
+extern inline void nmi_watchdog_tick (struct pt_regs * regs);
+extern int APIC_init_uniprocessor (void);
+
+extern struct pm_dev *apic_pm_register(pm_dev_t, unsigned long, pm_callback);
+extern void apic_pm_unregister(struct pm_dev*);
+
+extern unsigned int apic_timer_irqs [NR_CPUS];
+extern int check_nmi_watchdog (void);
+
+extern unsigned int nmi_watchdog;
+#define NMI_NONE 0
+#define NMI_IO_APIC 1
+#define NMI_LOCAL_APIC 2
+#define NMI_INVALID 3
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#endif /* __ASM_APIC_H */
--- /dev/null
+#ifndef __ASM_APICDEF_H
+#define __ASM_APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define APIC_DEFAULT_PHYS_BASE 0xfee00000
+
+#define APIC_ID 0x20
+#define APIC_ID_MASK (0x0F<<24)
+#define GET_APIC_ID(x) (((x)>>24)&0x0F)
+#define APIC_LVR 0x30
+#define APIC_LVR_MASK 0xFF00FF
+#define GET_APIC_VERSION(x) ((x)&0xFF)
+#define GET_APIC_MAXLVT(x) (((x)>>16)&0xFF)
+#define APIC_INTEGRATED(x) ((x)&0xF0)
+#define APIC_TASKPRI 0x80
+#define APIC_TPRI_MASK 0xFF
+#define APIC_ARBPRI 0x90
+#define APIC_ARBPRI_MASK 0xFF
+#define APIC_PROCPRI 0xA0
+#define APIC_EOI 0xB0
+#define APIC_EIO_ACK 0x0 /* Write this to the EOI register */
+#define APIC_RRR 0xC0
+#define APIC_LDR 0xD0
+#define APIC_LDR_MASK (0xFF<<24)
+#define GET_APIC_LOGICAL_ID(x) (((x)>>24)&0xFF)
+#define SET_APIC_LOGICAL_ID(x) (((x)<<24))
+#define APIC_ALL_CPUS 0xFF
+#define APIC_DFR 0xE0
+#define APIC_SPIV 0xF0
+#define APIC_SPIV_FOCUS_DISABLED (1<<9)
+#define APIC_SPIV_APIC_ENABLED (1<<8)
+#define APIC_ISR 0x100
+#define APIC_TMR 0x180
+#define APIC_IRR 0x200
+#define APIC_ESR 0x280
+#define APIC_ESR_SEND_CS 0x00001
+#define APIC_ESR_RECV_CS 0x00002
+#define APIC_ESR_SEND_ACC 0x00004
+#define APIC_ESR_RECV_ACC 0x00008
+#define APIC_ESR_SENDILL 0x00020
+#define APIC_ESR_RECVILL 0x00040
+#define APIC_ESR_ILLREGA 0x00080
+#define APIC_ICR 0x300
+#define APIC_DEST_SELF 0x40000
+#define APIC_DEST_ALLINC 0x80000
+#define APIC_DEST_ALLBUT 0xC0000
+#define APIC_ICR_RR_MASK 0x30000
+#define APIC_ICR_RR_INVALID 0x00000
+#define APIC_ICR_RR_INPROG 0x10000
+#define APIC_ICR_RR_VALID 0x20000
+#define APIC_INT_LEVELTRIG 0x08000
+#define APIC_INT_ASSERT 0x04000
+#define APIC_ICR_BUSY 0x01000
+#define APIC_DEST_LOGICAL 0x00800
+#define APIC_DM_FIXED 0x00000
+#define APIC_DM_LOWEST 0x00100
+#define APIC_DM_SMI 0x00200
+#define APIC_DM_REMRD 0x00300
+#define APIC_DM_NMI 0x00400
+#define APIC_DM_INIT 0x00500
+#define APIC_DM_STARTUP 0x00600
+#define APIC_DM_EXTINT 0x00700
+#define APIC_VECTOR_MASK 0x000FF
+#define APIC_ICR2 0x310
+#define GET_APIC_DEST_FIELD(x) (((x)>>24)&0xFF)
+#define SET_APIC_DEST_FIELD(x) ((x)<<24)
+#define APIC_LVTT 0x320
+#define APIC_LVTPC 0x340
+#define APIC_LVT0 0x350
+#define APIC_LVT_TIMER_BASE_MASK (0x3<<18)
+#define GET_APIC_TIMER_BASE(x) (((x)>>18)&0x3)
+#define SET_APIC_TIMER_BASE(x) (((x)<<18))
+#define APIC_TIMER_BASE_CLKIN 0x0
+#define APIC_TIMER_BASE_TMBASE 0x1
+#define APIC_TIMER_BASE_DIV 0x2
+#define APIC_LVT_TIMER_PERIODIC (1<<17)
+#define APIC_LVT_MASKED (1<<16)
+#define APIC_LVT_LEVEL_TRIGGER (1<<15)
+#define APIC_LVT_REMOTE_IRR (1<<14)
+#define APIC_INPUT_POLARITY (1<<13)
+#define APIC_SEND_PENDING (1<<12)
+#define GET_APIC_DELIVERY_MODE(x) (((x)>>8)&0x7)
+#define SET_APIC_DELIVERY_MODE(x,y) (((x)&~0x700)|((y)<<8))
+#define APIC_MODE_FIXED 0x0
+#define APIC_MODE_NMI 0x4
+#define APIC_MODE_EXINT 0x7
+#define APIC_LVT1 0x360
+#define APIC_LVTERR 0x370
+#define APIC_TMICT 0x380
+#define APIC_TMCCT 0x390
+#define APIC_TDCR 0x3E0
+#define APIC_TDR_DIV_TMBASE (1<<2)
+#define APIC_TDR_DIV_1 0xB
+#define APIC_TDR_DIV_2 0x0
+#define APIC_TDR_DIV_4 0x1
+#define APIC_TDR_DIV_8 0x2
+#define APIC_TDR_DIV_16 0x3
+#define APIC_TDR_DIV_32 0x8
+#define APIC_TDR_DIV_64 0x9
+#define APIC_TDR_DIV_128 0xA
+
+#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+
+#define MAX_IO_APICS 8
+
+/*
+ * the local APIC register structure, memory mapped. Not terribly well
+ * tested, but we might eventually use this one in the future - the
+ * problem why we cannot use it right now is the P5 APIC, it has an
+ * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
+ */
+#define u32 unsigned int
+
+#define lapic ((volatile struct local_apic *)APIC_BASE)
+
+struct local_apic {
+
+/*000*/ struct { u32 __reserved[4]; } __reserved_01;
+
+/*010*/ struct { u32 __reserved[4]; } __reserved_02;
+
+/*020*/ struct { /* APIC ID Register */
+ u32 __reserved_1 : 24,
+ phys_apic_id : 4,
+ __reserved_2 : 4;
+ u32 __reserved[3];
+ } id;
+
+/*030*/ const
+ struct { /* APIC Version Register */
+ u32 version : 8,
+ __reserved_1 : 8,
+ max_lvt : 8,
+ __reserved_2 : 8;
+ u32 __reserved[3];
+ } version;
+
+/*040*/ struct { u32 __reserved[4]; } __reserved_03;
+
+/*050*/ struct { u32 __reserved[4]; } __reserved_04;
+
+/*060*/ struct { u32 __reserved[4]; } __reserved_05;
+
+/*070*/ struct { u32 __reserved[4]; } __reserved_06;
+
+/*080*/ struct { /* Task Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } tpr;
+
+/*090*/ const
+ struct { /* Arbitration Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } apr;
+
+/*0A0*/ const
+ struct { /* Processor Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } ppr;
+
+/*0B0*/ struct { /* End Of Interrupt Register */
+ u32 eoi;
+ u32 __reserved[3];
+ } eoi;
+
+/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
+
+/*0D0*/ struct { /* Logical Destination Register */
+ u32 __reserved_1 : 24,
+ logical_dest : 8;
+ u32 __reserved_2[3];
+ } ldr;
+
+/*0E0*/ struct { /* Destination Format Register */
+ u32 __reserved_1 : 28,
+ model : 4;
+ u32 __reserved_2[3];
+ } dfr;
+
+/*0F0*/ struct { /* Spurious Interrupt Vector Register */
+ u32 spurious_vector : 8,
+ apic_enabled : 1,
+ focus_cpu : 1,
+ __reserved_2 : 22;
+ u32 __reserved_3[3];
+ } svr;
+
+/*100*/ struct { /* In Service Register */
+/*170*/ u32 bitfield;
+ u32 __reserved[3];
+ } isr [8];
+
+/*180*/ struct { /* Trigger Mode Register */
+/*1F0*/ u32 bitfield;
+ u32 __reserved[3];
+ } tmr [8];
+
+/*200*/ struct { /* Interrupt Request Register */
+/*270*/ u32 bitfield;
+ u32 __reserved[3];
+ } irr [8];
+
+/*280*/ union { /* Error Status Register */
+ struct {
+ u32 send_cs_error : 1,
+ receive_cs_error : 1,
+ send_accept_error : 1,
+ receive_accept_error : 1,
+ __reserved_1 : 1,
+ send_illegal_vector : 1,
+ receive_illegal_vector : 1,
+ illegal_register_address : 1,
+ __reserved_2 : 24;
+ u32 __reserved_3[3];
+ } error_bits;
+ struct {
+ u32 errors;
+ u32 __reserved_3[3];
+ } all_errors;
+ } esr;
+
+/*290*/ struct { u32 __reserved[4]; } __reserved_08;
+
+/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
+
+/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
+
+/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
+
+/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
+
+/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
+
+/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
+
+/*300*/ struct { /* Interrupt Command Register 1 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ destination_mode : 1,
+ delivery_status : 1,
+ __reserved_1 : 1,
+ level : 1,
+ trigger : 1,
+ __reserved_2 : 2,
+ shorthand : 2,
+ __reserved_3 : 12;
+ u32 __reserved_4[3];
+ } icr1;
+
+/*310*/ struct { /* Interrupt Command Register 2 */
+ union {
+ u32 __reserved_1 : 24,
+ phys_dest : 4,
+ __reserved_2 : 4;
+ u32 __reserved_3 : 24,
+ logical_dest : 8;
+ } dest;
+ u32 __reserved_4[3];
+ } icr2;
+
+/*320*/ struct { /* LVT - Timer */
+ u32 vector : 8,
+ __reserved_1 : 4,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ timer_mode : 1,
+ __reserved_3 : 14;
+ u32 __reserved_4[3];
+ } lvt_timer;
+
+/*330*/ struct { u32 __reserved[4]; } __reserved_15;
+
+/*340*/ struct { /* LVT - Performance Counter */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_pc;
+
+/*350*/ struct { /* LVT - LINT0 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ polarity : 1,
+ remote_irr : 1,
+ trigger : 1,
+ mask : 1,
+ __reserved_2 : 15;
+ u32 __reserved_3[3];
+ } lvt_lint0;
+
+/*360*/ struct { /* LVT - LINT1 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ polarity : 1,
+ remote_irr : 1,
+ trigger : 1,
+ mask : 1,
+ __reserved_2 : 15;
+ u32 __reserved_3[3];
+ } lvt_lint1;
+
+/*370*/ struct { /* LVT - Error */
+ u32 vector : 8,
+ __reserved_1 : 4,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_error;
+
+/*380*/ struct { /* Timer Initial Count Register */
+ u32 initial_count;
+ u32 __reserved_2[3];
+ } timer_icr;
+
+/*390*/ const
+ struct { /* Timer Current Count Register */
+ u32 curr_count;
+ u32 __reserved_2[3];
+ } timer_ccr;
+
+/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
+
+/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
+
+/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
+
+/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
+
+/*3E0*/ struct { /* Timer Divide Configuration Register */
+ u32 divisor : 4,
+ __reserved_1 : 28;
+ u32 __reserved_2[3];
+ } timer_dcr;
+
+/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
+
+} __attribute__ ((packed));
+
+#undef u32
+
+#endif
--- /dev/null
+#ifndef __ARCH_I386_ATOMIC__
+#define __ARCH_I386_ATOMIC__
+
+#include <linux/config.h>
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK "lock ; "
+#else
+#define LOCK ""
+#endif
+
+/*
+ * Make sure gcc doesn't try to be clever and move things around
+ * on us. We need to use _exactly_ the address the user gave us,
+ * not some alias that contains the same information.
+ */
+typedef struct { volatile int counter; } atomic_t;
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+#define atomic_read(v) ((v)->counter)
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+#define atomic_set(v,i) (((v)->counter) = (i))
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v. Note that the guaranteed useful range
+ * of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_add(int i, atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "addl %1,%0"
+ :"=m" (v->counter)
+ :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub - subtract the atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_sub(int i, atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "subl %1,%0"
+ :"=m" (v->counter)
+ :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "subl %2,%0; sete %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"ir" (i), "m" (v->counter) : "memory");
+ return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_inc(atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "incl %0"
+ :"=m" (v->counter)
+ :"m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_dec(atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "decl %0"
+ :"=m" (v->counter)
+ :"m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_dec_and_test(atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "decl %0; sete %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"m" (v->counter) : "memory");
+ return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_inc_and_test(atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "incl %0; sete %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"m" (v->counter) : "memory");
+ return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @v: pointer of type atomic_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_add_negative(int i, atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "addl %2,%0; sets %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"ir" (i), "m" (v->counter) : "memory");
+ return c;
+}
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr) \
+__asm__ __volatile__(LOCK "andl %0,%1" \
+: : "r" (~(mask)),"m" (*addr) : "memory")
+
+#define atomic_set_mask(mask, addr) \
+__asm__ __volatile__(LOCK "orl %0,%1" \
+: : "r" (mask),"m" (*addr) : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec() barrier()
+#define smp_mb__after_atomic_dec() barrier()
+#define smp_mb__before_atomic_inc() barrier()
+#define smp_mb__after_atomic_inc() barrier()
+
+#endif
--- /dev/null
+#ifndef _I386_BITOPS_H
+#define _I386_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#include <linux/config.h>
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX "lock ; "
+#else
+#define LOCK_PREFIX ""
+#endif
+
+#define ADDR (*(volatile long *) addr)
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered. See __set_bit()
+ * if you do not require the atomic guarantees.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __inline__ void set_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__( LOCK_PREFIX
+ "btsl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __inline__ void __set_bit(int nr, volatile void * addr)
+{
+ __asm__(
+ "btsl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered. However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static __inline__ void clear_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__( LOCK_PREFIX
+ "btrl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+#define smp_mb__before_clear_bit() barrier()
+#define smp_mb__after_clear_bit() barrier()
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __inline__ void __change_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__(
+ "btcl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __inline__ void change_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__( LOCK_PREFIX
+ "btcl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static __inline__ int test_and_set_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__( LOCK_PREFIX
+ "btsl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static __inline__ int __test_and_set_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__(
+ "btsl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr));
+ return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static __inline__ int test_and_clear_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__( LOCK_PREFIX
+ "btrl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static __inline__ int __test_and_clear_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__(
+ "btrl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr));
+ return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __inline__ int __test_and_change_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__(
+ "btcl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its new value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static __inline__ int test_and_change_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__( LOCK_PREFIX
+ "btcl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static int test_bit(int nr, const volatile void * addr);
+#endif
+
+static __inline__ int constant_test_bit(int nr, const volatile void * addr)
+{
+ return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
+}
+
+static __inline__ int variable_test_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__(
+ "btl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit)
+ :"m" (ADDR),"Ir" (nr));
+ return oldbit;
+}
+
+#define test_bit(nr,addr) \
+(__builtin_constant_p(nr) ? \
+ constant_test_bit((nr),(addr)) : \
+ variable_test_bit((nr),(addr)))
+
+/**
+ * find_first_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit-number of the first zero bit, not the number of the byte
+ * containing a bit.
+ */
+static __inline__ int find_first_zero_bit(void * addr, unsigned size)
+{
+ int d0, d1, d2;
+ int res;
+
+ if (!size)
+ return 0;
+ /* This looks at memory. Mark it volatile to tell gcc not to move it around */
+ __asm__ __volatile__(
+ "movl $-1,%%eax\n\t"
+ "xorl %%edx,%%edx\n\t"
+ "repe; scasl\n\t"
+ "je 1f\n\t"
+ "xorl -4(%%edi),%%eax\n\t"
+ "subl $4,%%edi\n\t"
+ "bsfl %%eax,%%edx\n"
+ "1:\tsubl %%ebx,%%edi\n\t"
+ "shll $3,%%edi\n\t"
+ "addl %%edi,%%edx"
+ :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
+ :"1" ((size + 31) >> 5), "2" (addr), "b" (addr));
+ return res;
+}
+
+/**
+ * find_next_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+static __inline__ int find_next_zero_bit (void * addr, int size, int offset)
+{
+ unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
+ int set = 0, bit = offset & 31, res;
+
+ if (bit) {
+ /*
+ * Look for zero in first byte
+ */
+ __asm__("bsfl %1,%0\n\t"
+ "jne 1f\n\t"
+ "movl $32, %0\n"
+ "1:"
+ : "=r" (set)
+ : "r" (~(*p >> bit)));
+ if (set < (32 - bit))
+ return set + offset;
+ set = 32 - bit;
+ p++;
+ }
+ /*
+ * No zero yet, search remaining full bytes for a zero
+ */
+ res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
+ return (offset + set + res);
+}
+
+/**
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static __inline__ unsigned long ffz(unsigned long word)
+{
+ __asm__("bsfl %1,%0"
+ :"=r" (word)
+ :"r" (~word));
+ return word;
+}
+
+#ifdef __KERNEL__
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz (man ffs).
+ */
+static __inline__ int ffs(int x)
+{
+ int r;
+
+ __asm__("bsfl %1,%0\n\t"
+ "jnz 1f\n\t"
+ "movl $-1,%0\n"
+ "1:" : "=r" (r) : "g" (x));
+ return r+1;
+}
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+#define hweight32(x) generic_hweight32(x)
+#define hweight16(x) generic_hweight16(x)
+#define hweight8(x) generic_hweight8(x)
+
+#endif /* __KERNEL__ */
+
+#ifdef __KERNEL__
+
+#define ext2_set_bit __test_and_set_bit
+#define ext2_clear_bit __test_and_clear_bit
+#define ext2_test_bit test_bit
+#define ext2_find_first_zero_bit find_first_zero_bit
+#define ext2_find_next_zero_bit find_next_zero_bit
+
+/* Bitmap functions for the minix filesystem. */
+#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,addr)
+#define minix_set_bit(nr,addr) __set_bit(nr,addr)
+#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,addr)
+#define minix_test_bit(nr,addr) test_bit(nr,addr)
+#define minix_find_first_zero_bit(addr,size) find_first_zero_bit(addr,size)
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_BITOPS_H */
--- /dev/null
+#ifndef _LINUX_BOOT_H
+#define _LINUX_BOOT_H
+
+/* Don't touch these, unless you really know what you're doing. */
+#define DEF_INITSEG 0x9000
+#define DEF_SYSSEG 0x1000
+#define DEF_SETUPSEG 0x9020
+#define DEF_SYSSIZE 0x7F00
+
+/* Internal svga startup constants */
+#define NORMAL_VGA 0xffff /* 80x25 mode */
+#define EXTENDED_VGA 0xfffe /* 80x50 mode */
+#define ASK_VGA 0xfffd /* ask for it at bootup */
+
+#endif
--- /dev/null
+/*
+ * include/asm-i386/bugs.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Cyrix stuff, June 1998 by:
+ * - Rafael R. Reilova (moved everything from head.S),
+ * <rreilova@ececs.uc.edu>
+ * - Channing Corn (tests & fixes),
+ * - Andrew D. Balsa (code cleanup).
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ * void check_bugs(void);
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+
+
+static void __init check_fpu(void)
+{
+ boot_cpu_data.fdiv_bug = 0;
+}
+
+static void __init check_hlt(void)
+{
+ boot_cpu_data.hlt_works_ok = 1;
+}
+
+static void __init check_bugs(void)
+{
+ identify_cpu(&boot_cpu_data);
+#ifndef CONFIG_SMP
+ printk("CPU: ");
+ print_cpu_info(&boot_cpu_data);
+#endif
+ check_fpu();
+ check_hlt();
+ system_utsname.machine[1] = '0' +
+ (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+}
--- /dev/null
+#ifndef _I386_BYTEORDER_H
+#define _I386_BYTEORDER_H
+
+#include <asm/types.h>
+
+#ifdef __GNUC__
+
+/* For avoiding bswap on i386 */
+#ifdef __KERNEL__
+#include <linux/config.h>
+#endif
+
+static __inline__ __const__ __u32 ___arch__swab32(__u32 x)
+{
+#ifdef CONFIG_X86_BSWAP
+ __asm__("bswap %0" : "=r" (x) : "0" (x));
+#else
+ __asm__("xchgb %b0,%h0\n\t" /* swap lower bytes */
+ "rorl $16,%0\n\t" /* swap words */
+ "xchgb %b0,%h0" /* swap higher bytes */
+ :"=q" (x)
+ : "0" (x));
+#endif
+ return x;
+}
+
+static __inline__ __const__ __u16 ___arch__swab16(__u16 x)
+{
+ __asm__("xchgb %b0,%h0" /* swap bytes */ \
+ : "=q" (x) \
+ : "0" (x)); \
+ return x;
+}
+
+#define __arch__swab32(x) ___arch__swab32(x)
+#define __arch__swab16(x) ___arch__swab16(x)
+
+#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
+# define __BYTEORDER_HAS_U64__
+# define __SWAB_64_THRU_32__
+#endif
+
+#endif /* __GNUC__ */
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _I386_BYTEORDER_H */
--- /dev/null
+/*
+ * include/asm-i386/cache.h
+ */
+#ifndef __ARCH_I386_CACHE_H
+#define __ARCH_I386_CACHE_H
+
+#include <linux/config.h>
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#endif
--- /dev/null
+#ifndef _I386_CHECKSUM_H
+#define _I386_CHECKSUM_H
+
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+asmlinkage unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums, and handles user-space pointer exceptions correctly, when needed.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+
+asmlinkage unsigned int csum_partial_copy_generic( const char *src, char *dst, int len, int sum,
+ int *src_err_ptr, int *dst_err_ptr);
+
+/*
+ * Note: when you get a NULL pointer exception here this means someone
+ * passed in an incorrect kernel address to one of these functions.
+ *
+ * If you use these functions directly please don't forget the
+ * verify_area().
+ */
+static __inline__
+unsigned int csum_partial_copy_nocheck ( const char *src, char *dst,
+ int len, int sum)
+{
+ return csum_partial_copy_generic ( src, dst, len, sum, NULL, NULL);
+}
+
+static __inline__
+unsigned int csum_partial_copy_from_user ( const char *src, char *dst,
+ int len, int sum, int *err_ptr)
+{
+ return csum_partial_copy_generic ( src, dst, len, sum, err_ptr, NULL);
+}
+
+/*
+ * These are the old (and unsafe) way of doing checksums, a warning message will be
+ * printed if they are used and an exeption occurs.
+ *
+ * these functions should go away after some time.
+ */
+
+#define csum_partial_copy_fromuser csum_partial_copy
+unsigned int csum_partial_copy( const char *src, char *dst, int len, int sum);
+
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.
+ *
+ * By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
+ * Arnt Gulbrandsen.
+ */
+static inline unsigned short ip_fast_csum(unsigned char * iph,
+ unsigned int ihl) {
+ unsigned int sum;
+
+ __asm__ __volatile__("
+ movl (%1), %0
+ subl $4, %2
+ jbe 2f
+ addl 4(%1), %0
+ adcl 8(%1), %0
+ adcl 12(%1), %0
+1: adcl 16(%1), %0
+ lea 4(%1), %1
+ decl %2
+ jne 1b
+ adcl $0, %0
+ movl %0, %2
+ shrl $16, %0
+ addw %w2, %w0
+ adcl $0, %0
+ notl %0
+2:
+ "
+ /* Since the input registers which are loaded with iph and ipl
+ are modified, we must also specify them as outputs, or gcc
+ will assume they contain their original values. */
+ : "=r" (sum), "=r" (iph), "=r" (ihl)
+ : "1" (iph), "2" (ihl));
+ return(sum);
+}
+
+/*
+ * Fold a partial checksum
+ */
+
+static inline unsigned int csum_fold(unsigned int sum)
+{
+ __asm__("
+ addl %1, %0
+ adcl $0xffff, %0
+ "
+ : "=r" (sum)
+ : "r" (sum << 16), "0" (sum & 0xffff0000)
+ );
+ return (~sum) >> 16;
+}
+
+static inline unsigned long csum_tcpudp_nofold(unsigned long saddr,
+ unsigned long daddr,
+ unsigned short len,
+ unsigned short proto,
+ unsigned int sum)
+{
+ __asm__("
+ addl %1, %0
+ adcl %2, %0
+ adcl %3, %0
+ adcl $0, %0
+ "
+ : "=r" (sum)
+ : "g" (daddr), "g"(saddr), "g"((ntohs(len)<<16)+proto*256), "0"(sum));
+ return sum;
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline unsigned short int csum_tcpudp_magic(unsigned long saddr,
+ unsigned long daddr,
+ unsigned short len,
+ unsigned short proto,
+ unsigned int sum)
+{
+ return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+
+static inline unsigned short ip_compute_csum(unsigned char * buff, int len) {
+ return csum_fold (csum_partial(buff, len, 0));
+}
+
+#define _HAVE_ARCH_IPV6_CSUM
+static __inline__ unsigned short int csum_ipv6_magic(struct in6_addr *saddr,
+ struct in6_addr *daddr,
+ __u32 len,
+ unsigned short proto,
+ unsigned int sum)
+{
+ __asm__("
+ addl 0(%1), %0
+ adcl 4(%1), %0
+ adcl 8(%1), %0
+ adcl 12(%1), %0
+ adcl 0(%2), %0
+ adcl 4(%2), %0
+ adcl 8(%2), %0
+ adcl 12(%2), %0
+ adcl %3, %0
+ adcl %4, %0
+ adcl $0, %0
+ "
+ : "=&r" (sum)
+ : "r" (saddr), "r" (daddr),
+ "r"(htonl(len)), "r"(htonl(proto)), "0"(sum));
+
+ return csum_fold(sum);
+}
+
+/*
+ * Copy and checksum to user
+ */
+#define HAVE_CSUM_COPY_USER
+static __inline__ unsigned int csum_and_copy_to_user (const char *src, char *dst,
+ int len, int sum, int *err_ptr)
+{
+ if (access_ok(VERIFY_WRITE, dst, len))
+ return csum_partial_copy_generic(src, dst, len, sum, NULL, err_ptr);
+
+ if (len)
+ *err_ptr = -EFAULT;
+
+ return -1; /* invalid checksum */
+}
+
+#endif
--- /dev/null
+/*
+ * cpufeature.h
+ *
+ * Defines x86 CPU feature bits
+ */
+
+#ifndef __ASM_I386_CPUFEATURE_H
+#define __ASM_I386_CPUFEATURE_H
+
+/* Sample usage: CPU_FEATURE_P(cpu.x86_capability, FPU) */
+#define CPU_FEATURE_P(CAP, FEATURE) test_bit(CAP, X86_FEATURE_##FEATURE ##_BIT)
+
+#define NCAPINTS 4 /* Currently we have 4 32-bit words worth of info */
+
+/* Intel-defined CPU features, CPUID level 0x00000001, word 0 */
+#define X86_FEATURE_FPU (0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME (0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE (0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE (0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
+#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC (0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP (0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR (0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE (0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA (0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
+#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN (0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLSH (0*32+19) /* Supports the CLFLUSH instruction */
+#define X86_FEATURE_DTES (0*32+21) /* Debug Trace Store */
+#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
+ /* of FPU context), and CR4.OSFXSR available */
+#define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */
+#define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */
+#define X86_FEATURE_SELFSNOOP (0*32+27) /* CPU self snoop */
+#define X86_FEATURE_ACC (0*32+29) /* Automatic clock control */
+#define X86_FEATURE_IA64 (0*32+30) /* IA-64 processor */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL (1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW (1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY (2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN (2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI (2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX (3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR (3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+#endif /* __ASM_I386_CPUFEATURE_H */
+
+/*
+ * Local Variables:
+ * mode:c
+ * comment-column:42
+ * End:
+ */
--- /dev/null
+#ifndef _I386_CURRENT_H
+#define _I386_CURRENT_H
+
+struct task_struct;
+
+static inline struct task_struct * get_current(void)
+{
+ struct task_struct *current;
+ __asm__("andl %%esp,%0; ":"=r" (current) : "0" (~8191UL));
+ return current;
+ }
+
+#define current get_current()
+
+#endif /* !(_I386_CURRENT_H) */
--- /dev/null
+#ifndef _I386_DEBUGREG_H
+#define _I386_DEBUGREG_H
+
+
+/* Indicate the register numbers for a number of the specific
+ debug registers. Registers 0-3 contain the addresses we wish to trap on */
+#define DR_FIRSTADDR 0 /* u_debugreg[DR_FIRSTADDR] */
+#define DR_LASTADDR 3 /* u_debugreg[DR_LASTADDR] */
+
+#define DR_STATUS 6 /* u_debugreg[DR_STATUS] */
+#define DR_CONTROL 7 /* u_debugreg[DR_CONTROL] */
+
+/* Define a few things for the status register. We can use this to determine
+ which debugging register was responsible for the trap. The other bits
+ are either reserved or not of interest to us. */
+
+#define DR_TRAP0 (0x1) /* db0 */
+#define DR_TRAP1 (0x2) /* db1 */
+#define DR_TRAP2 (0x4) /* db2 */
+#define DR_TRAP3 (0x8) /* db3 */
+
+#define DR_STEP (0x4000) /* single-step */
+#define DR_SWITCH (0x8000) /* task switch */
+
+/* Now define a bunch of things for manipulating the control register.
+ The top two bytes of the control register consist of 4 fields of 4
+ bits - each field corresponds to one of the four debug registers,
+ and indicates what types of access we trap on, and how large the data
+ field is that we are looking at */
+
+#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
+#define DR_CONTROL_SIZE 4 /* 4 control bits per register */
+
+#define DR_RW_EXECUTE (0x0) /* Settings for the access types to trap on */
+#define DR_RW_WRITE (0x1)
+#define DR_RW_READ (0x3)
+
+#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
+#define DR_LEN_2 (0x4)
+#define DR_LEN_4 (0xC)
+
+/* The low byte to the control register determine which registers are
+ enabled. There are 4 fields of two bits. One bit is "local", meaning
+ that the processor will reset the bit after a task switch and the other
+ is global meaning that we have to explicitly reset the bit. With linux,
+ you can use either one, since we explicitly zero the register when we enter
+ kernel mode. */
+
+#define DR_LOCAL_ENABLE_SHIFT 0 /* Extra shift to the local enable bit */
+#define DR_GLOBAL_ENABLE_SHIFT 1 /* Extra shift to the global enable bit */
+#define DR_ENABLE_SIZE 2 /* 2 enable bits per register */
+
+#define DR_LOCAL_ENABLE_MASK (0x55) /* Set local bits for all 4 regs */
+#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
+
+/* The second byte to the control register has a few special things.
+ We can slow the instruction pipeline for instructions coming via the
+ gdt or the ldt if we want to. I am not sure why this is an advantage */
+
+#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
+#define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */
+#define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */
+
+#endif
--- /dev/null
+#ifndef _I386_DELAY_H
+#define _I386_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/i386/lib/delay.c
+ */
+
+extern void __bad_udelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __const_udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+#define udelay(n) (__builtin_constant_p(n) ? \
+ ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c6ul)) : \
+ __udelay(n))
+
+#endif /* defined(_I386_DELAY_H) */
--- /dev/null
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <asm/ldt.h>
+
+#define __LDT(_X) (0)
+
+#define clear_LDT() ((void)0)
+#define load_LDT(_mm) ((void)0)
+
+#endif
--- /dev/null
+#ifndef __I386_DIV64
+#define __I386_DIV64
+
+#define do_div(n,base) ({ \
+ unsigned long __upper, __low, __high, __mod; \
+ asm("":"=a" (__low), "=d" (__high):"A" (n)); \
+ __upper = __high; \
+ if (__high) { \
+ __upper = __high % (base); \
+ __high = __high / (base); \
+ } \
+ asm("divl %2":"=a" (__low), "=d" (__mod):"rm" (base), "0" (__low), "1" (__upper)); \
+ asm("":"=A" (n):"a" (__low),"d" (__high)); \
+ __mod; \
+})
+
+#endif
--- /dev/null
+/* $Id: dma.h,v 1.7 1992/12/14 00:29:34 root Exp root $
+ * linux/include/asm/dma.h: Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ */
+
+#ifndef _ASM_DMA_H
+#define _ASM_DMA_H
+
+#include <linux/config.h>
+#include <linux/spinlock.h> /* And spinlocks */
+#include <asm/io.h> /* need byte IO */
+#include <linux/delay.h>
+
+
+#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
+#define dma_outb outb_p
+#else
+#define dma_outb outb
+#endif
+
+#define dma_inb inb
+
+/*
+ * NOTES about DMA transfers:
+ *
+ * controller 1: channels 0-3, byte operations, ports 00-1F
+ * controller 2: channels 4-7, word operations, ports C0-DF
+ *
+ * - ALL registers are 8 bits only, regardless of transfer size
+ * - channel 4 is not used - cascades 1 into 2.
+ * - channels 0-3 are byte - addresses/counts are for physical bytes
+ * - channels 5-7 are word - addresses/counts are for physical words
+ * - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
+ * - transfer count loaded to registers is 1 less than actual count
+ * - controller 2 offsets are all even (2x offsets for controller 1)
+ * - page registers for 5-7 don't use data bit 0, represent 128K pages
+ * - page registers for 0-3 use bit 0, represent 64K pages
+ *
+ * DMA transfers are limited to the lower 16MB of _physical_ memory.
+ * Note that addresses loaded into registers must be _physical_ addresses,
+ * not logical addresses (which may differ if paging is active).
+ *
+ * Address mapping for channels 0-3:
+ *
+ * A23 ... A16 A15 ... A8 A7 ... A0 (Physical addresses)
+ * | ... | | ... | | ... |
+ * | ... | | ... | | ... |
+ * | ... | | ... | | ... |
+ * P7 ... P0 A7 ... A0 A7 ... A0
+ * | Page | Addr MSB | Addr LSB | (DMA registers)
+ *
+ * Address mapping for channels 5-7:
+ *
+ * A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0 (Physical addresses)
+ * | ... | \ \ ... \ \ \ ... \ \
+ * | ... | \ \ ... \ \ \ ... \ (not used)
+ * | ... | \ \ ... \ \ \ ... \
+ * P7 ... P1 (0) A7 A6 ... A0 A7 A6 ... A0
+ * | Page | Addr MSB | Addr LSB | (DMA registers)
+ *
+ * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
+ * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
+ * the hardware level, so odd-byte transfers aren't possible).
+ *
+ * Transfer count (_not # bytes_) is limited to 64K, represented as actual
+ * count - 1 : 64K => 0xFFFF, 1 => 0x0000. Thus, count is always 1 or more,
+ * and up to 128K bytes may be transferred on channels 5-7 in one operation.
+ *
+ */
+
+#define MAX_DMA_CHANNELS 8
+
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS (PAGE_OFFSET+0x1000000)
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE 0x00 /* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE 0xC0 /* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG 0x08 /* command register (w) */
+#define DMA1_STAT_REG 0x08 /* status register (r) */
+#define DMA1_REQ_REG 0x09 /* request register (w) */
+#define DMA1_MASK_REG 0x0A /* single-channel mask (w) */
+#define DMA1_MODE_REG 0x0B /* mode register (w) */
+#define DMA1_CLEAR_FF_REG 0x0C /* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG 0x0D /* Temporary Register (r) */
+#define DMA1_RESET_REG 0x0D /* Master Clear (w) */
+#define DMA1_CLR_MASK_REG 0x0E /* Clear Mask */
+#define DMA1_MASK_ALL_REG 0x0F /* all-channels mask (w) */
+
+#define DMA2_CMD_REG 0xD0 /* command register (w) */
+#define DMA2_STAT_REG 0xD0 /* status register (r) */
+#define DMA2_REQ_REG 0xD2 /* request register (w) */
+#define DMA2_MASK_REG 0xD4 /* single-channel mask (w) */
+#define DMA2_MODE_REG 0xD6 /* mode register (w) */
+#define DMA2_CLEAR_FF_REG 0xD8 /* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG 0xDA /* Temporary Register (r) */
+#define DMA2_RESET_REG 0xDA /* Master Clear (w) */
+#define DMA2_CLR_MASK_REG 0xDC /* Clear Mask */
+#define DMA2_MASK_ALL_REG 0xDE /* all-channels mask (w) */
+
+#define DMA_ADDR_0 0x00 /* DMA address registers */
+#define DMA_ADDR_1 0x02
+#define DMA_ADDR_2 0x04
+#define DMA_ADDR_3 0x06
+#define DMA_ADDR_4 0xC0
+#define DMA_ADDR_5 0xC4
+#define DMA_ADDR_6 0xC8
+#define DMA_ADDR_7 0xCC
+
+#define DMA_CNT_0 0x01 /* DMA count registers */
+#define DMA_CNT_1 0x03
+#define DMA_CNT_2 0x05
+#define DMA_CNT_3 0x07
+#define DMA_CNT_4 0xC2
+#define DMA_CNT_5 0xC6
+#define DMA_CNT_6 0xCA
+#define DMA_CNT_7 0xCE
+
+#define DMA_PAGE_0 0x87 /* DMA page registers */
+#define DMA_PAGE_1 0x83
+#define DMA_PAGE_2 0x81
+#define DMA_PAGE_3 0x82
+#define DMA_PAGE_5 0x8B
+#define DMA_PAGE_6 0x89
+#define DMA_PAGE_7 0x8A
+
+#define DMA_MODE_READ 0x44 /* I/O to memory, no autoinit, increment, single mode */
+#define DMA_MODE_WRITE 0x48 /* memory to I/O, no autoinit, increment, single mode */
+#define DMA_MODE_CASCADE 0xC0 /* pass thru DREQ->HRQ, DACK<-HLDA only */
+
+#define DMA_AUTOINIT 0x10
+
+
+extern spinlock_t dma_spin_lock;
+
+static __inline__ unsigned long claim_dma_lock(void)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&dma_spin_lock, flags);
+ return flags;
+}
+
+static __inline__ void release_dma_lock(unsigned long flags)
+{
+ spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* enable/disable a specific DMA channel */
+static __inline__ void enable_dma(unsigned int dmanr)
+{
+ if (dmanr<=3)
+ dma_outb(dmanr, DMA1_MASK_REG);
+ else
+ dma_outb(dmanr & 3, DMA2_MASK_REG);
+}
+
+static __inline__ void disable_dma(unsigned int dmanr)
+{
+ if (dmanr<=3)
+ dma_outb(dmanr | 4, DMA1_MASK_REG);
+ else
+ dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while holding the DMA lock ! ---
+ */
+static __inline__ void clear_dma_ff(unsigned int dmanr)
+{
+ if (dmanr<=3)
+ dma_outb(0, DMA1_CLEAR_FF_REG);
+ else
+ dma_outb(0, DMA2_CLEAR_FF_REG);
+}
+
+/* set mode (above) for a specific DMA channel */
+static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
+{
+ if (dmanr<=3)
+ dma_outb(mode | dmanr, DMA1_MODE_REG);
+ else
+ dma_outb(mode | (dmanr&3), DMA2_MODE_REG);
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
+{
+ switch(dmanr) {
+ case 0:
+ dma_outb(pagenr, DMA_PAGE_0);
+ break;
+ case 1:
+ dma_outb(pagenr, DMA_PAGE_1);
+ break;
+ case 2:
+ dma_outb(pagenr, DMA_PAGE_2);
+ break;
+ case 3:
+ dma_outb(pagenr, DMA_PAGE_3);
+ break;
+ case 5:
+ dma_outb(pagenr & 0xfe, DMA_PAGE_5);
+ break;
+ case 6:
+ dma_outb(pagenr & 0xfe, DMA_PAGE_6);
+ break;
+ case 7:
+ dma_outb(pagenr & 0xfe, DMA_PAGE_7);
+ break;
+ }
+}
+
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+ set_dma_page(dmanr, a>>16);
+ if (dmanr <= 3) {
+ dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+ dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+ } else {
+ dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+ dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+ }
+}
+
+
+/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+ count--;
+ if (dmanr <= 3) {
+ dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+ dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+ } else {
+ dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+ dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+ }
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static __inline__ int get_dma_residue(unsigned int dmanr)
+{
+ unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
+ : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
+
+ /* using short to get 16-bit wrap around */
+ unsigned short count;
+
+ count = 1 + dma_inb(io_port);
+ count += dma_inb(io_port) << 8;
+
+ return (dmanr<=3)? count : (count<<1);
+}
+
+
+/* These are in kernel/dma.c: */
+extern int request_dma(unsigned int dmanr, const char * device_id); /* reserve a DMA channel */
+extern void free_dma(unsigned int dmanr); /* release it again */
+
+/* From PCI */
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy (0)
+#endif
+
+#endif /* _ASM_DMA_H */
--- /dev/null
+#ifndef __ASMi386_ELF_H
+#define __ASMi386_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+#include <linux/utsname.h>
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+typedef struct user_fxsr_struct elf_fpxregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+ (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS ELFCLASS32
+#define ELF_DATA ELFDATA2LSB
+#define ELF_ARCH EM_386
+
+/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
+ contains a pointer to a function which might be registered using `atexit'.
+ This provides a mean for the dynamic linker to call DT_FINI functions for
+ shared libraries that have been loaded before the code runs.
+
+ A value of 0 tells we have no such handler.
+
+ We might as well make sure everything else is cleared too (except for %esp),
+ just to make things more deterministic.
+ */
+#define ELF_PLAT_INIT(_r) do { \
+ _r->ebx = 0; _r->ecx = 0; _r->edx = 0; \
+ _r->esi = 0; _r->edi = 0; _r->ebp = 0; \
+ _r->eax = 0; \
+} while (0)
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE 4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ use of this is to invoke "./ld.so someprog" to test out a new version of
+ the loader. We need to make sure that it is out of the way of the program
+ that it will "exec", and that there is sufficient room for the brk. */
+
+#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
+
+/* Wow, the "main" arch needs arch dependent functions too.. :) */
+
+/* regs is struct pt_regs, pr_reg is elf_gregset_t (which is
+ now struct_user_regs, they are different) */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) \
+ pr_reg[0] = regs->ebx; \
+ pr_reg[1] = regs->ecx; \
+ pr_reg[2] = regs->edx; \
+ pr_reg[3] = regs->esi; \
+ pr_reg[4] = regs->edi; \
+ pr_reg[5] = regs->ebp; \
+ pr_reg[6] = regs->eax; \
+ pr_reg[7] = regs->xds; \
+ pr_reg[8] = regs->xes; \
+ /* fake once used fs and gs selectors? */ \
+ pr_reg[9] = regs->xds; /* was fs and __fs */ \
+ pr_reg[10] = regs->xds; /* was gs and __gs */ \
+ pr_reg[11] = regs->orig_eax; \
+ pr_reg[12] = regs->eip; \
+ pr_reg[13] = regs->xcs; \
+ pr_reg[14] = regs->eflags; \
+ pr_reg[15] = regs->esp; \
+ pr_reg[16] = regs->xss;
+
+/* This yields a mask that user programs can use to figure out what
+ instruction set this CPU supports. This could be done in user space,
+ but it's not easy, and we've already done it here. */
+
+#define ELF_HWCAP (boot_cpu_data.x86_capability[0])
+
+/* This yields a string that ld.so will use to load implementation
+ specific libraries for optimization. This is more specific in
+ intent than poking at uname or /proc/cpuinfo.
+
+ For the moment, we have only optimizations for the Intel generations,
+ but that could change... */
+
+#define ELF_PLATFORM (system_utsname.machine)
+
+#ifdef __KERNEL__
+#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX)
+#endif
+
+#endif
--- /dev/null
+#ifndef _I386_ERRNO_H
+#define _I386_ERRNO_H
+
+#define EPERM 1 /* Operation not permitted */
+#define ENOENT 2 /* No such file or directory */
+#define ESRCH 3 /* No such process */
+#define EINTR 4 /* Interrupted system call */
+#define EIO 5 /* I/O error */
+#define ENXIO 6 /* No such device or address */
+#define E2BIG 7 /* Arg list too long */
+#define ENOEXEC 8 /* Exec format error */
+#define EBADF 9 /* Bad file number */
+#define ECHILD 10 /* No child processes */
+#define EAGAIN 11 /* Try again */
+#define ENOMEM 12 /* Out of memory */
+#define EACCES 13 /* Permission denied */
+#define EFAULT 14 /* Bad address */
+#define ENOTBLK 15 /* Block device required */
+#define EBUSY 16 /* Device or resource busy */
+#define EEXIST 17 /* File exists */
+#define EXDEV 18 /* Cross-device link */
+#define ENODEV 19 /* No such device */
+#define ENOTDIR 20 /* Not a directory */
+#define EISDIR 21 /* Is a directory */
+#define EINVAL 22 /* Invalid argument */
+#define ENFILE 23 /* File table overflow */
+#define EMFILE 24 /* Too many open files */
+#define ENOTTY 25 /* Not a typewriter */
+#define ETXTBSY 26 /* Text file busy */
+#define EFBIG 27 /* File too large */
+#define ENOSPC 28 /* No space left on device */
+#define ESPIPE 29 /* Illegal seek */
+#define EROFS 30 /* Read-only file system */
+#define EMLINK 31 /* Too many links */
+#define EPIPE 32 /* Broken pipe */
+#define EDOM 33 /* Math argument out of domain of func */
+#define ERANGE 34 /* Math result not representable */
+#define EDEADLK 35 /* Resource deadlock would occur */
+#define ENAMETOOLONG 36 /* File name too long */
+#define ENOLCK 37 /* No record locks available */
+#define ENOSYS 38 /* Function not implemented */
+#define ENOTEMPTY 39 /* Directory not empty */
+#define ELOOP 40 /* Too many symbolic links encountered */
+#define EWOULDBLOCK EAGAIN /* Operation would block */
+#define ENOMSG 42 /* No message of desired type */
+#define EIDRM 43 /* Identifier removed */
+#define ECHRNG 44 /* Channel number out of range */
+#define EL2NSYNC 45 /* Level 2 not synchronized */
+#define EL3HLT 46 /* Level 3 halted */
+#define EL3RST 47 /* Level 3 reset */
+#define ELNRNG 48 /* Link number out of range */
+#define EUNATCH 49 /* Protocol driver not attached */
+#define ENOCSI 50 /* No CSI structure available */
+#define EL2HLT 51 /* Level 2 halted */
+#define EBADE 52 /* Invalid exchange */
+#define EBADR 53 /* Invalid request descriptor */
+#define EXFULL 54 /* Exchange full */
+#define ENOANO 55 /* No anode */
+#define EBADRQC 56 /* Invalid request code */
+#define EBADSLT 57 /* Invalid slot */
+
+#define EDEADLOCK EDEADLK
+
+#define EBFONT 59 /* Bad font file format */
+#define ENOSTR 60 /* Device not a stream */
+#define ENODATA 61 /* No data available */
+#define ETIME 62 /* Timer expired */
+#define ENOSR 63 /* Out of streams resources */
+#define ENONET 64 /* Machine is not on the network */
+#define ENOPKG 65 /* Package not installed */
+#define EREMOTE 66 /* Object is remote */
+#define ENOLINK 67 /* Link has been severed */
+#define EADV 68 /* Advertise error */
+#define ESRMNT 69 /* Srmount error */
+#define ECOMM 70 /* Communication error on send */
+#define EPROTO 71 /* Protocol error */
+#define EMULTIHOP 72 /* Multihop attempted */
+#define EDOTDOT 73 /* RFS specific error */
+#define EBADMSG 74 /* Not a data message */
+#define EOVERFLOW 75 /* Value too large for defined data type */
+#define ENOTUNIQ 76 /* Name not unique on network */
+#define EBADFD 77 /* File descriptor in bad state */
+#define EREMCHG 78 /* Remote address changed */
+#define ELIBACC 79 /* Can not access a needed shared library */
+#define ELIBBAD 80 /* Accessing a corrupted shared library */
+#define ELIBSCN 81 /* .lib section in a.out corrupted */
+#define ELIBMAX 82 /* Attempting to link in too many shared libraries */
+#define ELIBEXEC 83 /* Cannot exec a shared library directly */
+#define EILSEQ 84 /* Illegal byte sequence */
+#define ERESTART 85 /* Interrupted system call should be restarted */
+#define ESTRPIPE 86 /* Streams pipe error */
+#define EUSERS 87 /* Too many users */
+#define ENOTSOCK 88 /* Socket operation on non-socket */
+#define EDESTADDRREQ 89 /* Destination address required */
+#define EMSGSIZE 90 /* Message too long */
+#define EPROTOTYPE 91 /* Protocol wrong type for socket */
+#define ENOPROTOOPT 92 /* Protocol not available */
+#define EPROTONOSUPPORT 93 /* Protocol not supported */
+#define ESOCKTNOSUPPORT 94 /* Socket type not supported */
+#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */
+#define EPFNOSUPPORT 96 /* Protocol family not supported */
+#define EAFNOSUPPORT 97 /* Address family not supported by protocol */
+#define EADDRINUSE 98 /* Address already in use */
+#define EADDRNOTAVAIL 99 /* Cannot assign requested address */
+#define ENETDOWN 100 /* Network is down */
+#define ENETUNREACH 101 /* Network is unreachable */
+#define ENETRESET 102 /* Network dropped connection because of reset */
+#define ECONNABORTED 103 /* Software caused connection abort */
+#define ECONNRESET 104 /* Connection reset by peer */
+#define ENOBUFS 105 /* No buffer space available */
+#define EISCONN 106 /* Transport endpoint is already connected */
+#define ENOTCONN 107 /* Transport endpoint is not connected */
+#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */
+#define ETOOMANYREFS 109 /* Too many references: cannot splice */
+#define ETIMEDOUT 110 /* Connection timed out */
+#define ECONNREFUSED 111 /* Connection refused */
+#define EHOSTDOWN 112 /* Host is down */
+#define EHOSTUNREACH 113 /* No route to host */
+#define EALREADY 114 /* Operation already in progress */
+#define EINPROGRESS 115 /* Operation now in progress */
+#define ESTALE 116 /* Stale NFS file handle */
+#define EUCLEAN 117 /* Structure needs cleaning */
+#define ENOTNAM 118 /* Not a XENIX named type file */
+#define ENAVAIL 119 /* No XENIX semaphores available */
+#define EISNAM 120 /* Is a named type file */
+#define EREMOTEIO 121 /* Remote I/O error */
+#define EDQUOT 122 /* Quota exceeded */
+
+#define ENOMEDIUM 123 /* No medium found */
+#define EMEDIUMTYPE 124 /* Wrong medium type */
+
+#endif
--- /dev/null
+#ifndef _I386_FCNTL_H
+#define _I386_FCNTL_H
+
+/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
+ located on an ext2 file system */
+#define O_ACCMODE 0003
+#define O_RDONLY 00
+#define O_WRONLY 01
+#define O_RDWR 02
+#define O_CREAT 0100 /* not fcntl */
+#define O_EXCL 0200 /* not fcntl */
+#define O_NOCTTY 0400 /* not fcntl */
+#define O_TRUNC 01000 /* not fcntl */
+#define O_APPEND 02000
+#define O_NONBLOCK 04000
+#define O_NDELAY O_NONBLOCK
+#define O_SYNC 010000
+#define FASYNC 020000 /* fcntl, for BSD compatibility */
+#define O_DIRECT 040000 /* direct disk access hint */
+#define O_LARGEFILE 0100000
+#define O_DIRECTORY 0200000 /* must be a directory */
+#define O_NOFOLLOW 0400000 /* don't follow links */
+
+#define F_DUPFD 0 /* dup */
+#define F_GETFD 1 /* get close_on_exec */
+#define F_SETFD 2 /* set/clear close_on_exec */
+#define F_GETFL 3 /* get file->f_flags */
+#define F_SETFL 4 /* set file->f_flags */
+#define F_GETLK 5
+#define F_SETLK 6
+#define F_SETLKW 7
+
+#define F_SETOWN 8 /* for sockets. */
+#define F_GETOWN 9 /* for sockets. */
+#define F_SETSIG 10 /* for sockets. */
+#define F_GETSIG 11 /* for sockets. */
+
+#define F_GETLK64 12 /* using 'struct flock64' */
+#define F_SETLK64 13
+#define F_SETLKW64 14
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC 1 /* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#define F_RDLCK 0
+#define F_WRLCK 1
+#define F_UNLCK 2
+
+/* for old implementation of bsd flock () */
+#define F_EXLCK 4 /* or 3 */
+#define F_SHLCK 8 /* or 4 */
+
+/* for leases */
+#define F_INPROGRESS 16
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH 1 /* shared lock */
+#define LOCK_EX 2 /* exclusive lock */
+#define LOCK_NB 4 /* or'd with one of the above to prevent
+ blocking */
+#define LOCK_UN 8 /* remove lock */
+
+#define LOCK_MAND 32 /* This is a mandatory flock */
+#define LOCK_READ 64 /* ... Which allows concurrent read operations */
+#define LOCK_WRITE 128 /* ... Which allows concurrent write operations */
+#define LOCK_RW 192 /* ... Which allows concurrent read & write ops */
+
+struct flock {
+ short l_type;
+ short l_whence;
+ off_t l_start;
+ off_t l_len;
+ pid_t l_pid;
+};
+
+struct flock64 {
+ short l_type;
+ short l_whence;
+ loff_t l_start;
+ loff_t l_len;
+ pid_t l_pid;
+};
+
+#define F_LINUX_SPECIFIC_BASE 1024
+
+#endif
--- /dev/null
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
+ FIX_BLKRING_BASE,
+ __end_of_fixed_addresses
+};
+
+extern void __set_fixmap (enum fixed_addresses idx,
+ unsigned long phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+/*
+ * used by vmalloc.c.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap, and leave one page empty
+ * at the top of mem..
+ */
+#define FIXADDR_TOP (HYPERVISOR_VIRT_START - 2*PAGE_SIZE)
+#define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE)
+
+#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static inline unsigned long fix_to_virt(const unsigned int idx)
+{
+ /*
+ * this branch gets completely eliminated after inlining,
+ * except when someone tries to use fixaddr indices in an
+ * illegal way. (such as mixing up address types or using
+ * out-of-range indices).
+ *
+ * If it doesn't get removed, the linker will complain
+ * loudly with a reasonably clear error message..
+ */
+ if (idx >= __end_of_fixed_addresses)
+ __this_fixmap_does_not_exist();
+
+ return __fix_to_virt(idx);
+}
+
+#endif
--- /dev/null
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995
+ */
+#ifndef __ASM_I386_FLOPPY_H
+#define __ASM_I386_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma&1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port) inb_p(port)
+#define fd_outb(port,value) outb_p(port,value)
+
+#define fd_request_dma() CSW._request_dma(FLOPPY_DMA,"floppy")
+#define fd_free_dma() CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq() enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq() disable_irq(FLOPPY_IRQ)
+#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue() SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size) SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static void floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
+{
+ register unsigned char st;
+
+#undef TRACE_FLPY_INT
+#define NO_FLOPPY_ASSEMBLER
+
+#ifdef TRACE_FLPY_INT
+ static int calls=0;
+ static int bytes=0;
+ static int dma_wait=0;
+#endif
+ if(!doing_pdma) {
+ floppy_interrupt(irq, dev_id, regs);
+ return;
+ }
+
+#ifdef TRACE_FLPY_INT
+ if(!calls)
+ bytes = virtual_dma_count;
+#endif
+
+#ifndef NO_FLOPPY_ASSEMBLER
+ __asm__ (
+ "testl %1,%1
+ je 3f
+1: inb %w4,%b0
+ andb $160,%b0
+ cmpb $160,%b0
+ jne 2f
+ incw %w4
+ testl %3,%3
+ jne 4f
+ inb %w4,%b0
+ movb %0,(%2)
+ jmp 5f
+4: movb (%2),%0
+ outb %b0,%w4
+5: decw %w4
+ outb %0,$0x80
+ decl %1
+ incl %2
+ testl %1,%1
+ jne 1b
+3: inb %w4,%b0
+2: "
+ : "=a" ((char) st),
+ "=c" ((long) virtual_dma_count),
+ "=S" ((long) virtual_dma_addr)
+ : "b" ((long) virtual_dma_mode),
+ "d" ((short) virtual_dma_port+4),
+ "1" ((long) virtual_dma_count),
+ "2" ((long) virtual_dma_addr));
+#else
+ {
+ register int lcount;
+ register char *lptr;
+
+ st = 1;
+ for(lcount=virtual_dma_count, lptr=virtual_dma_addr;
+ lcount; lcount--, lptr++) {
+ st=inb(virtual_dma_port+4) & 0xa0 ;
+ if(st != 0xa0)
+ break;
+ if(virtual_dma_mode)
+ outb_p(*lptr, virtual_dma_port+5);
+ else
+ *lptr = inb_p(virtual_dma_port+5);
+ }
+ virtual_dma_count = lcount;
+ virtual_dma_addr = lptr;
+ st = inb(virtual_dma_port+4);
+ }
+#endif
+
+#ifdef TRACE_FLPY_INT
+ calls++;
+#endif
+ if(st == 0x20)
+ return;
+ if(!(st & 0x20)) {
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+#ifdef TRACE_FLPY_INT
+ printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+ virtual_dma_count, virtual_dma_residue, calls, bytes,
+ dma_wait);
+ calls = 0;
+ dma_wait=0;
+#endif
+ doing_pdma = 0;
+ floppy_interrupt(irq, dev_id, regs);
+ return;
+ }
+#ifdef TRACE_FLPY_INT
+ if(!virtual_dma_count)
+ dma_wait++;
+#endif
+}
+
+static void fd_disable_dma(void)
+{
+ if(! (can_use_virtual_dma & 1))
+ disable_dma(FLOPPY_DMA);
+ doing_pdma = 0;
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char * device_id)
+{
+ return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+ return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+ if(can_use_virtual_dma)
+ return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT,
+ "floppy", NULL);
+ else
+ return request_irq(FLOPPY_IRQ, floppy_interrupt,
+ SA_INTERRUPT|SA_SAMPLE_RANDOM,
+ "floppy", NULL);
+
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+ return __get_dma_pages(GFP_KERNEL,get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+ return (unsigned long) vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+ if((unsigned int) addr >= (unsigned int) high_memory)
+ return vfree((void *)addr);
+ else
+ free_pages(addr, get_order(size));
+}
+
+#define fd_dma_mem_free(addr, size) _fd_dma_mem_free(addr, size)
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+ if(can_use_virtual_dma == 2) {
+ if((unsigned int) addr >= (unsigned int) high_memory ||
+ virt_to_bus(addr) >= 0x1000000 ||
+ _CROSS_64KB(addr, size, 0))
+ use_virtual_dma = 1;
+ else
+ use_virtual_dma = 0;
+ } else {
+ use_virtual_dma = can_use_virtual_dma & 1;
+ }
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+ doing_pdma = 1;
+ virtual_dma_port = io;
+ virtual_dma_mode = (mode == DMA_MODE_WRITE);
+ virtual_dma_addr = addr;
+ virtual_dma_count = size;
+ virtual_dma_residue = 0;
+ return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+ if (CROSS_64KB(addr, size)) {
+ printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+ return -1;
+ }
+#endif
+ /* actual, physical DMA */
+ doing_pdma = 0;
+ clear_dma_ff(FLOPPY_DMA);
+ set_dma_mode(FLOPPY_DMA,mode);
+ set_dma_addr(FLOPPY_DMA,virt_to_bus(addr));
+ set_dma_count(FLOPPY_DMA,size);
+ enable_dma(FLOPPY_DMA);
+ return 0;
+}
+
+struct fd_routine_l {
+ int (*_request_dma)(unsigned int dmanr, const char * device_id);
+ void (*_free_dma)(unsigned int dmanr);
+ int (*_get_dma_residue)(unsigned int dummy);
+ unsigned long (*_dma_mem_alloc) (unsigned long size);
+ int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+ {
+ request_dma,
+ free_dma,
+ get_dma_residue,
+ dma_mem_alloc,
+ hard_dma_setup
+ },
+ {
+ vdma_request_dma,
+ vdma_nop,
+ vdma_get_dma_residue,
+ vdma_mem_alloc,
+ vdma_dma_setup
+ }
+};
+
+
+static int FDC1 = 0x3f0;
+static int FDC2 = -1;
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user. Paul G.
+ */
+#define FLOPPY0_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = (CMOS_READ(0x10) >> 4) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define FLOPPY1_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = CMOS_READ(0x10) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define FLOPPY_MOTOR_MASK 0xf0
+
+#define AUTO_DMA
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_I386_FLOPPY_H */
--- /dev/null
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+/* assembly code in softirq.h is sensitive to the offsets of these fields */
+typedef struct {
+ unsigned int __softirq_pending;
+ unsigned int __local_irq_count;
+ unsigned int __local_bh_count;
+ unsigned int __syscall_count;
+ struct task_struct * __ksoftirqd_task; /* waitqueue is too large */
+ unsigned int __nmi_count; /* arch dependent */
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */
+
+/*
+ * Are we in an interrupt context? Either doing bottom half
+ * or hardware interrupt processing?
+ */
+#define in_interrupt() ({ int __cpu = smp_processor_id(); \
+ (local_irq_count(__cpu) + local_bh_count(__cpu) != 0); })
+
+#define in_irq() (local_irq_count(smp_processor_id()) != 0)
+
+#ifndef CONFIG_SMP
+
+#define hardirq_trylock(cpu) (local_irq_count(cpu) == 0)
+#define hardirq_endlock(cpu) do { } while (0)
+
+#define irq_enter(cpu, irq) (local_irq_count(cpu)++)
+#define irq_exit(cpu, irq) (local_irq_count(cpu)--)
+
+#define synchronize_irq() barrier()
+
+#else
+
+#include <asm/atomic.h>
+#include <asm/smp.h>
+
+extern unsigned char global_irq_holder;
+extern unsigned volatile long global_irq_lock; /* long for set_bit -RR */
+
+static inline int irqs_running (void)
+{
+ int i;
+
+ for (i = 0; i < smp_num_cpus; i++)
+ if (local_irq_count(i))
+ return 1;
+ return 0;
+}
+
+static inline void release_irqlock(int cpu)
+{
+ /* if we didn't own the irq lock, just ignore.. */
+ if (global_irq_holder == (unsigned char) cpu) {
+ global_irq_holder = NO_PROC_ID;
+ clear_bit(0,&global_irq_lock);
+ }
+}
+
+static inline void irq_enter(int cpu, int irq)
+{
+ ++local_irq_count(cpu);
+
+ while (test_bit(0,&global_irq_lock)) {
+ cpu_relax();
+ }
+}
+
+static inline void irq_exit(int cpu, int irq)
+{
+ --local_irq_count(cpu);
+}
+
+static inline int hardirq_trylock(int cpu)
+{
+ return !local_irq_count(cpu) && !test_bit(0,&global_irq_lock);
+}
+
+#define hardirq_endlock(cpu) do { } while (0)
+
+extern void synchronize_irq(void);
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_HARDIRQ_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/hdreg.h
+ *
+ * Copyright (C) 1994-1996 Linus Torvalds & authors
+ */
+
+#ifndef __ASMi386_HDREG_H
+#define __ASMi386_HDREG_H
+
+typedef unsigned short ide_ioreg_t;
+
+#endif /* __ASMi386_HDREG_H */
--- /dev/null
+
+#error "Highmem unsupported!"
--- /dev/null
+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ * linux/include/asm/hw_irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ */
+
+#include <linux/config.h>
+#include <linux/smp.h>
+#include <asm/atomic.h>
+#include <asm/irq.h>
+
+#define SYSCALL_VECTOR 0x80
+#define KDBENTER_VECTOR 0x81
+
+extern int irq_vector[NR_IRQS];
+
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+extern char _stext, _etext;
+
+extern unsigned long prof_cpu_mask;
+extern unsigned int * prof_buffer;
+extern unsigned long prof_len;
+extern unsigned long prof_shift;
+
+/*
+ * x86 profiling function, SMP safe. We might want to do this in
+ * assembly totally?
+ */
+static inline void x86_do_profile (unsigned long eip)
+{
+ if (!prof_buffer)
+ return;
+
+ /*
+ * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
+ * (default is all CPUs.)
+ */
+ if (!((1<<smp_processor_id()) & prof_cpu_mask))
+ return;
+
+ eip -= (unsigned long) &_stext;
+ eip >>= prof_shift;
+ /*
+ * Don't ignore out-of-bounds EIP values silently,
+ * put them into the last histogram slot, so if
+ * present, they will show up as a sharp peak.
+ */
+ if (eip > prof_len-1)
+ eip = prof_len-1;
+ atomic_inc((atomic_t *)&prof_buffer[eip]);
+}
+
+static inline void hw_resend_irq(struct hw_interrupt_type *h,
+ unsigned int i)
+{}
+
+#endif /* _ASM_HW_IRQ_H */
--- /dev/null
+/******************************************************************************
+ * hypervisor.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#ifndef __HYPERVISOR_H__
+#define __HYPERVISOR_H__
+
+#include <asm/hypervisor-ifs/hypervisor-if.h>
+#include <asm/ptrace.h>
+
+/* arch/xeno/kernel/setup.c */
+union start_info_union
+{
+ start_info_t start_info;
+ char padding[512];
+};
+extern union start_info_union start_info_union;
+#define start_info (start_info_union.start_info)
+
+/* arch/xeno/kernel/hypervisor.c */
+void do_hypervisor_callback(struct pt_regs *regs);
+
+
+/* arch/xeno/mm/hypervisor.c */
+/*
+ * NB. ptr values should be PHYSICAL, not MACHINE. 'vals' should be already
+ * be MACHINE addresses.
+ */
+
+extern unsigned int pt_update_queue_idx;
+
+void queue_l1_entry_update(unsigned long ptr, unsigned long val);
+void queue_l2_entry_update(unsigned long ptr, unsigned long val);
+void queue_pt_switch(unsigned long ptr);
+void queue_tlb_flush(void);
+void queue_invlpg(unsigned long ptr);
+void queue_pgd_pin(unsigned long ptr);
+void queue_pgd_unpin(unsigned long ptr);
+void queue_pte_pin(unsigned long ptr);
+void queue_pte_unpin(unsigned long ptr);
+
+#define PT_UPDATE_DEBUG 0
+
+#if PT_UPDATE_DEBUG > 0
+typedef struct {
+ unsigned long ptr, val, pteval;
+ void *ptep;
+ int line; char *file;
+} page_update_debug_t;
+extern page_update_debug_t update_debug_queue[];
+#define queue_l1_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ queue_l1_entry_update((_p),(_v)); \
+})
+#define queue_l2_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ queue_l2_entry_update((_p),(_v)); \
+})
+#endif
+
+#if PT_UPDATE_DEBUG > 1
+#undef queue_l1_entry_update
+#undef queue_l2_entry_update
+#define queue_l1_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ printk("L1 %s %d: %08lx (%08lx -> %08lx)\n", __FILE__, __LINE__, \
+ phys_to_machine(_p), *(unsigned long *)__va(_p), \
+ (unsigned long)(_v)); \
+ queue_l1_entry_update((_p),(_v)); \
+})
+#define queue_l2_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ printk("L2 %s %d: %08lx (%08lx -> %08lx)\n", __FILE__, __LINE__, \
+ phys_to_machine(_p), *(unsigned long *)__va(_p), \
+ (unsigned long)(_v)); \
+ queue_l2_entry_update((_p),(_v)); \
+})
+#define queue_pt_switch(_p) ({ \
+ printk("PTSWITCH %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pt_switch(_p); \
+})
+#define queue_tlb_flush() ({ \
+ printk("TLB FLUSH %s %d\n", __FILE__, __LINE__); \
+ queue_tlb_flush(); \
+})
+#define queue_invlpg(_p) ({ \
+ printk("INVLPG %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_invlpg(_p); \
+})
+#define queue_pgd_pin(_p) ({ \
+ printk("PGD PIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pgd_pin(_p); \
+})
+#define queue_pgd_unpin(_p) ({ \
+ printk("PGD UNPIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pgd_unpin(_p); \
+})
+#define queue_pte_pin(_p) ({ \
+ printk("PTE PIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pte_pin(_p); \
+})
+#define queue_pte_unpin(_p) ({ \
+ printk("PTE UNPIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pte_unpin(_p); \
+})
+#endif
+
+void _flush_page_update_queue(void);
+static inline int flush_page_update_queue(void)
+{
+ unsigned int idx = pt_update_queue_idx;
+ if ( idx != 0 ) _flush_page_update_queue();
+ return idx;
+}
+#define XENO_flush_page_update_queue() (_flush_page_update_queue())
+
+
+/*
+ * Assembler stubs for hyper-calls.
+ */
+
+static inline int HYPERVISOR_set_trap_table(trap_info_t *table)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_trap_table),
+ "b" (table) );
+
+ return ret;
+}
+
+
+static inline int HYPERVISOR_pt_update(page_update_request_t *req, int count)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_pt_update),
+ "b" (req), "c" (count) );
+
+ return ret;
+}
+
+
+static inline int HYPERVISOR_console_write(const char *str, int count)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_console_write),
+ "b" (str), "c" (count) );
+
+
+ return ret;
+}
+
+static inline int HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_gdt),
+ "b" (frame_list), "c" (entries) );
+
+
+ return ret;
+}
+
+static inline int HYPERVISOR_stack_and_ldt_switch(
+ unsigned long ss, unsigned long esp, unsigned long ldts)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_stack_and_ldt_switch),
+ "b" (ss), "c" (esp), "d" (ldts) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_net_update(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_net_update) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_fpu_taskswitch(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_fpu_taskswitch) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_do_sched_op(void *sched_op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_sched_op),
+ "b" (sched_op) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_exit(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_exit) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_dom0_op(void *dom0_op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_dom0_op),
+ "b" (dom0_op) : "memory" );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_network_op(void *network_op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_network_op),
+ "b" (network_op) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_block_io_op(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_block_io_op) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_set_debugreg(int reg, unsigned long value)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_debugreg),
+ "b" (reg), "c" (value) );
+
+ return ret;
+}
+
+static inline unsigned long HYPERVISOR_get_debugreg(int reg)
+{
+ unsigned long ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_get_debugreg),
+ "b" (reg) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_update_descriptor(
+ unsigned long pa, unsigned long word1, unsigned long word2)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_gdt),
+ "b" (pa), "c" (word1), "d" (word2) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_set_fast_trap(int idx)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_fast_trap),
+ "b" (idx) );
+
+ return ret;
+}
+
+#endif /* __HYPERVISOR_H__ */
--- /dev/null
+/*
+ * include/asm-i386/i387.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#ifndef __ASM_I386_I387_H
+#define __ASM_I386_I387_H
+
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+
+extern void init_fpu(void);
+/*
+ * FPU lazy state save handling...
+ */
+extern void save_init_fpu( struct task_struct *tsk );
+extern void restore_fpu( struct task_struct *tsk );
+
+extern void kernel_fpu_begin(void);
+#define kernel_fpu_end() stts()
+
+
+#define unlazy_fpu( tsk ) do { \
+ if ( tsk->flags & PF_USEDFPU ) \
+ save_init_fpu( tsk ); \
+} while (0)
+
+#define clear_fpu( tsk ) do { \
+ if ( tsk->flags & PF_USEDFPU ) { \
+ asm volatile("fwait"); \
+ tsk->flags &= ~PF_USEDFPU; \
+ stts(); \
+ } \
+} while (0)
+
+/*
+ * FPU state interaction...
+ */
+extern unsigned short get_fpu_cwd( struct task_struct *tsk );
+extern unsigned short get_fpu_swd( struct task_struct *tsk );
+extern unsigned short get_fpu_twd( struct task_struct *tsk );
+extern unsigned short get_fpu_mxcsr( struct task_struct *tsk );
+
+extern void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd );
+extern void set_fpu_swd( struct task_struct *tsk, unsigned short swd );
+extern void set_fpu_twd( struct task_struct *tsk, unsigned short twd );
+extern void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr );
+
+#define load_mxcsr( val ) do { \
+ unsigned long __mxcsr = ((unsigned long)(val) & 0xffbf); \
+ asm volatile( "ldmxcsr %0" : : "m" (__mxcsr) ); \
+} while (0)
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387( struct _fpstate *buf );
+extern int restore_i387( struct _fpstate *buf );
+
+/*
+ * ptrace request handers...
+ */
+extern int get_fpregs( struct user_i387_struct *buf,
+ struct task_struct *tsk );
+extern int set_fpregs( struct task_struct *tsk,
+ struct user_i387_struct *buf );
+
+extern int get_fpxregs( struct user_fxsr_struct *buf,
+ struct task_struct *tsk );
+extern int set_fpxregs( struct task_struct *tsk,
+ struct user_fxsr_struct *buf );
+
+/*
+ * FPU state for core dumps...
+ */
+extern int dump_fpu( struct pt_regs *regs,
+ struct user_i387_struct *fpu );
+extern int dump_extended_fpu( struct pt_regs *regs,
+ struct user_fxsr_struct *fpu );
+
+#endif /* __ASM_I386_I387_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/ide.h
+ *
+ * Copyright (C) 1994-1996 Linus Torvalds & authors
+ */
+
+/*
+ * This file contains the i386 architecture specific IDE code.
+ */
+
+#ifndef __ASMi386_IDE_H
+#define __ASMi386_IDE_H
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+
+#ifndef MAX_HWIFS
+# ifdef CONFIG_BLK_DEV_IDEPCI
+#define MAX_HWIFS 10
+# else
+#define MAX_HWIFS 6
+# endif
+#endif
+
+#define ide__sti() __sti()
+
+static __inline__ int ide_default_irq(ide_ioreg_t base)
+{
+ switch (base) {
+ case 0x1f0: return 14;
+ case 0x170: return 15;
+ case 0x1e8: return 11;
+ case 0x168: return 10;
+ case 0x1e0: return 8;
+ case 0x160: return 12;
+ default:
+ return 0;
+ }
+}
+
+static __inline__ ide_ioreg_t ide_default_io_base(int index)
+{
+ switch (index) {
+ case 0: return 0x1f0;
+ case 1: return 0x170;
+ case 2: return 0x1e8;
+ case 3: return 0x168;
+ case 4: return 0x1e0;
+ case 5: return 0x160;
+ default:
+ return 0;
+ }
+}
+
+static __inline__ void ide_init_hwif_ports(hw_regs_t *hw, ide_ioreg_t data_port, ide_ioreg_t ctrl_port, int *irq)
+{
+ ide_ioreg_t reg = data_port;
+ int i;
+
+ for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
+ hw->io_ports[i] = reg;
+ reg += 1;
+ }
+ if (ctrl_port) {
+ hw->io_ports[IDE_CONTROL_OFFSET] = ctrl_port;
+ } else {
+ hw->io_ports[IDE_CONTROL_OFFSET] = hw->io_ports[IDE_DATA_OFFSET] + 0x206;
+ }
+ if (irq != NULL)
+ *irq = 0;
+ hw->io_ports[IDE_IRQ_OFFSET] = 0;
+}
+
+static __inline__ void ide_init_default_hwifs(void)
+{
+#ifndef CONFIG_BLK_DEV_IDEPCI
+ hw_regs_t hw;
+ int index;
+
+ for(index = 0; index < MAX_HWIFS; index++) {
+ ide_init_hwif_ports(&hw, ide_default_io_base(index), 0, NULL);
+ hw.irq = ide_default_irq(ide_default_io_base(index));
+ ide_register_hw(&hw, NULL);
+ }
+#endif /* CONFIG_BLK_DEV_IDEPCI */
+}
+
+typedef union {
+ unsigned all : 8; /* all of the bits together */
+ struct {
+ unsigned head : 4; /* always zeros here */
+ unsigned unit : 1; /* drive select number, 0 or 1 */
+ unsigned bit5 : 1; /* always 1 */
+ unsigned lba : 1; /* using LBA instead of CHS */
+ unsigned bit7 : 1; /* always 1 */
+ } b;
+ } select_t;
+
+#define ide_request_irq(irq,hand,flg,dev,id) request_irq((irq),(hand),(flg),(dev),(id))
+#define ide_free_irq(irq,dev_id) free_irq((irq), (dev_id))
+#define ide_check_region(from,extent) check_region((from), (extent))
+#define ide_request_region(from,extent,name) request_region((from), (extent), (name))
+#define ide_release_region(from,extent) release_region((from), (extent))
+
+/*
+ * The following are not needed for the non-m68k ports
+ */
+#define ide_ack_intr(hwif) (1)
+#define ide_fix_driveid(id) do {} while (0)
+#define ide_release_lock(lock) do {} while (0)
+#define ide_get_lock(lock, hdlr, data) do {} while (0)
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASMi386_IDE_H */
--- /dev/null
+#error "<asm/init.h> should never be used - use <linux/init.h> instead"
--- /dev/null
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ * Linus
+ */
+
+ /*
+ * Bit simplified and optimized by Jan Hubicka
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+ *
+ * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+ * isa_read[wl] and isa_write[wl] fixed
+ * - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ */
+
+#define IO_SPACE_LIMIT 0xffff
+
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_LEN 0x40000 /* 256k per quad. Only remapping 1st */
+
+#ifdef __KERNEL__
+
+#include <linux/vmalloc.h>
+
+/*
+ * Temporary debugging check to catch old code using
+ * unmapped ISA addresses. Will be removed in 2.4.
+ */
+#if CONFIG_DEBUG_IOVIRT
+ extern void *__io_virt_debug(unsigned long x, const char *file, int line);
+ extern unsigned long __io_phys_debug(unsigned long x, const char *file, int line);
+ #define __io_virt(x) __io_virt_debug((unsigned long)(x), __FILE__, __LINE__)
+//#define __io_phys(x) __io_phys_debug((unsigned long)(x), __FILE__, __LINE__)
+#else
+ #define __io_virt(x) ((void *)(x))
+//#define __io_phys(x) __pa(x)
+#endif
+
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+ return __pa(address);
+}
+
+static inline void * phys_to_virt(unsigned long address)
+{
+ return __va(address);
+}
+
+/*
+ * Change virtual addresses to machine addresses and vv.
+ * These are equally trivial.
+ */
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page) ((page - mem_map) << PAGE_SHIFT)
+
+/*
+ * IO bus memory addresses are also 1:1 with the physical address
+ */
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+#define page_to_bus page_to_phys
+
+/*
+ * readX/writeX() are used to access memory mapped devices. On some
+ * architectures the memory mapped IO stuff needs to be accessed
+ * differently. On the x86 architecture, we just read/write the
+ * memory location directly.
+ */
+
+#define readb(addr) (*(volatile unsigned char *) __io_virt(addr))
+#define readw(addr) (*(volatile unsigned short *) __io_virt(addr))
+#define readl(addr) (*(volatile unsigned int *) __io_virt(addr))
+#define __raw_readb readb
+#define __raw_readw readw
+#define __raw_readl readl
+
+#define writeb(b,addr) (*(volatile unsigned char *) __io_virt(addr) = (b))
+#define writew(b,addr) (*(volatile unsigned short *) __io_virt(addr) = (b))
+#define writel(b,addr) (*(volatile unsigned int *) __io_virt(addr) = (b))
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+
+#define memset_io(a,b,c) memset(__io_virt(a),(b),(c))
+#define memcpy_fromio(a,b,c) memcpy((a),__io_virt(b),(c))
+#define memcpy_toio(a,b,c) memcpy(__io_virt(a),(b),(c))
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char *)(PAGE_OFFSET))
+
+#define isa_readb(a) readb(__ISA_IO_base + (a))
+#define isa_readw(a) readw(__ISA_IO_base + (a))
+#define isa_readl(a) readl(__ISA_IO_base + (a))
+#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
+#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
+#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
+#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c))
+#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c))
+#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c))
+
+
+/*
+ * Again, i386 does not require mem IO specific function.
+ */
+
+#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),__io_virt(b),(c),(d))
+#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),__io_virt(__ISA_IO_base + (b)),(c),(d))
+
+static inline int check_signature(unsigned long io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+static inline int isa_check_signature(unsigned long io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (isa_readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/*
+ * Cache management
+ *
+ * This needed for two cases
+ * 1. Out of order aware processors
+ * 2. Accidentally out of order processors (PPro errata #51)
+ */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void flush_write_buffers(void)
+{
+ __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
+}
+
+#define dma_cache_inv(_start,_size) flush_write_buffers()
+#define dma_cache_wback(_start,_size) flush_write_buffers()
+#define dma_cache_wback_inv(_start,_size) flush_write_buffers()
+
+#else
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size) do { } while (0)
+#define dma_cache_wback(_start,_size) do { } while (0)
+#define dma_cache_wback_inv(_start,_size) do { } while (0)
+#define flush_write_buffers()
+
+#endif
+
+#endif /* __KERNEL__ */
+
+#ifdef SLOW_IO_BY_JUMPING
+#define __SLOW_DOWN_IO "\njmp 1f\n1:\tjmp 1f\n1:"
+#else
+#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
+#endif
+
+#ifdef REALLY_SLOW_IO
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
+#else
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
+#endif
+
+#ifdef CONFIG_MULTIQUAD
+extern void *xquad_portio; /* Where the IO area was mapped */
+#endif /* CONFIG_MULTIQUAD */
+
+/*
+ * Talk about misusing macros..
+ */
+#define __OUT1(s,x) \
+static inline void out##s(unsigned x value, unsigned short port) {
+
+#define __OUT2(s,s1,s2) \
+__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"
+
+#ifdef CONFIG_MULTIQUAD
+/* Make the default portio routines operate on quad 0 for now */
+#define __OUT(s,s1,x) \
+__OUT1(s##_local,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p_local,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \
+__OUTQ0(s,s,x) \
+__OUTQ0(s,s##_p,x)
+#else
+#define __OUT(s,s1,x) \
+__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));}
+#endif /* CONFIG_MULTIQUAD */
+
+#ifdef CONFIG_MULTIQUAD
+#define __OUTQ0(s,ss,x) /* Do the equivalent of the portio op on quad 0 */ \
+static inline void out##ss(unsigned x value, unsigned short port) { \
+ if (xquad_portio) \
+ write##s(value, (unsigned long) xquad_portio + port); \
+ else /* We're still in early boot, running on quad 0 */ \
+ out##ss##_local(value, port); \
+}
+
+#define __INQ0(s,ss) /* Do the equivalent of the portio op on quad 0 */ \
+static inline RETURN_TYPE in##ss(unsigned short port) { \
+ if (xquad_portio) \
+ return read##s((unsigned long) xquad_portio + port); \
+ else /* We're still in early boot, running on quad 0 */ \
+ return in##ss##_local(port); \
+}
+#endif /* CONFIG_MULTIQUAD */
+
+#define __IN1(s) \
+static inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;
+
+#define __IN2(s,s1,s2) \
+__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"
+
+#ifdef CONFIG_MULTIQUAD
+#define __IN(s,s1,i...) \
+__IN1(s##_local) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p_local) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__INQ0(s,s) \
+__INQ0(s,s##_p)
+#else
+#define __IN(s,s1,i...) \
+__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; }
+#endif /* CONFIG_MULTIQUAD */
+
+#define __INS(s) \
+static inline void ins##s(unsigned short port, void * addr, unsigned long count) \
+{ __asm__ __volatile__ ("rep ; ins" #s \
+: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define __OUTS(s) \
+static inline void outs##s(unsigned short port, const void * addr, unsigned long count) \
+{ __asm__ __volatile__ ("rep ; outs" #s \
+: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define RETURN_TYPE unsigned char
+__IN(b,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned short
+__IN(w,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned int
+__IN(l,"")
+#undef RETURN_TYPE
+
+__OUT(b,"b",char)
+__OUT(w,"w",short)
+__OUT(l,,int)
+
+__INS(b)
+__INS(w)
+__INS(l)
+
+__OUTS(b)
+__OUTS(w)
+__OUTS(l)
+
+#endif
--- /dev/null
+#ifndef __ASM_IO_APIC_H
+#define __ASM_IO_APIC_H
+
+#include <linux/config.h>
+#include <asm/types.h>
+
+/*
+ * Intel IO-APIC support for SMP and UP systems.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
+ */
+
+#ifdef CONFIG_X86_IO_APIC
+
+#define APIC_MISMATCH_DEBUG
+
+#define IO_APIC_BASE(idx) \
+ ((volatile int *)__fix_to_virt(FIX_IO_APIC_BASE_0 + idx))
+
+/*
+ * The structure of the IO-APIC:
+ */
+struct IO_APIC_reg_00 {
+ __u32 __reserved_2 : 24,
+ ID : 4,
+ __reserved_1 : 4;
+} __attribute__ ((packed));
+
+struct IO_APIC_reg_01 {
+ __u32 version : 8,
+ __reserved_2 : 7,
+ PRQ : 1,
+ entries : 8,
+ __reserved_1 : 8;
+} __attribute__ ((packed));
+
+struct IO_APIC_reg_02 {
+ __u32 __reserved_2 : 24,
+ arbitration : 4,
+ __reserved_1 : 4;
+} __attribute__ ((packed));
+
+/*
+ * # of IO-APICs and # of IRQ routing registers
+ */
+extern int nr_ioapics;
+extern int nr_ioapic_registers[MAX_IO_APICS];
+
+enum ioapic_irq_destination_types {
+ dest_Fixed = 0,
+ dest_LowestPrio = 1,
+ dest_SMI = 2,
+ dest__reserved_1 = 3,
+ dest_NMI = 4,
+ dest_INIT = 5,
+ dest__reserved_2 = 6,
+ dest_ExtINT = 7
+};
+
+struct IO_APIC_route_entry {
+ __u32 vector : 8,
+ delivery_mode : 3, /* 000: FIXED
+ * 001: lowest prio
+ * 111: ExtINT
+ */
+ dest_mode : 1, /* 0: physical, 1: logical */
+ delivery_status : 1,
+ polarity : 1,
+ irr : 1,
+ trigger : 1, /* 0: edge, 1: level */
+ mask : 1, /* 0: enabled, 1: disabled */
+ __reserved_2 : 15;
+
+ union { struct { __u32
+ __reserved_1 : 24,
+ physical_dest : 4,
+ __reserved_2 : 4;
+ } physical;
+
+ struct { __u32
+ __reserved_1 : 24,
+ logical_dest : 8;
+ } logical;
+ } dest;
+
+} __attribute__ ((packed));
+
+/*
+ * MP-BIOS irq configuration table structures:
+ */
+
+/* I/O APIC entries */
+extern struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+
+/* # of MP IRQ source entries */
+extern int mp_irq_entries;
+
+/* MP IRQ source entries */
+extern struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+
+/* non-0 if default (table-less) MP configuration */
+extern int mpc_default_type;
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+ *IO_APIC_BASE(apic) = reg;
+ return *(IO_APIC_BASE(apic)+4);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+ *IO_APIC_BASE(apic) = reg;
+ *(IO_APIC_BASE(apic)+4) = value;
+}
+
+/*
+ * Re-write a value: to be used for read-modify-write
+ * cycles where the read already set up the index register.
+ */
+static inline void io_apic_modify(unsigned int apic, unsigned int value)
+{
+ *(IO_APIC_BASE(apic)+4) = value;
+}
+
+/*
+ * Synchronize the IO-APIC and the CPU by doing
+ * a dummy read from the IO-APIC
+ */
+static inline void io_apic_sync(unsigned int apic)
+{
+ (void) *(IO_APIC_BASE(apic)+4);
+}
+
+/* 1 if "noapic" boot option passed */
+extern int skip_ioapic_setup;
+
+/*
+ * If we use the IO-APIC for IRQ routing, disable automatic
+ * assignment of PCI IRQ's.
+ */
+#define io_apic_assign_pci_irqs (mp_irq_entries && !skip_ioapic_setup)
+
+#else /* !CONFIG_X86_IO_APIC */
+#define io_apic_assign_pci_irqs 0
+#endif
+
+#endif
--- /dev/null
+/* $Id: ioctl.h,v 1.5 1993/07/19 21:53:50 root Exp root $
+ *
+ * linux/ioctl.h for Linux by H.H. Bergman.
+ */
+
+#ifndef _ASMI386_IOCTL_H
+#define _ASMI386_IOCTL_H
+
+/* ioctl command encoding: 32 bits total, command in lower 16 bits,
+ * size of the parameter structure in the lower 14 bits of the
+ * upper 16 bits.
+ * Encoding the size of the parameter structure in the ioctl request
+ * is useful for catching programs compiled with old versions
+ * and to avoid overwriting user space outside the user buffer area.
+ * The highest 2 bits are reserved for indicating the ``access mode''.
+ * NOTE: This limits the max parameter size to 16kB -1 !
+ */
+
+/*
+ * The following is for compatibility across the various Linux
+ * platforms. The i386 ioctl numbering scheme doesn't really enforce
+ * a type field. De facto, however, the top 8 bits of the lower 16
+ * bits are indeed used as a type field, so we might just as well make
+ * this explicit here. Please be sure to use the decoding macros
+ * below from now on.
+ */
+#define _IOC_NRBITS 8
+#define _IOC_TYPEBITS 8
+#define _IOC_SIZEBITS 14
+#define _IOC_DIRBITS 2
+
+#define _IOC_NRMASK ((1 << _IOC_NRBITS)-1)
+#define _IOC_TYPEMASK ((1 << _IOC_TYPEBITS)-1)
+#define _IOC_SIZEMASK ((1 << _IOC_SIZEBITS)-1)
+#define _IOC_DIRMASK ((1 << _IOC_DIRBITS)-1)
+
+#define _IOC_NRSHIFT 0
+#define _IOC_TYPESHIFT (_IOC_NRSHIFT+_IOC_NRBITS)
+#define _IOC_SIZESHIFT (_IOC_TYPESHIFT+_IOC_TYPEBITS)
+#define _IOC_DIRSHIFT (_IOC_SIZESHIFT+_IOC_SIZEBITS)
+
+/*
+ * Direction bits.
+ */
+#define _IOC_NONE 0U
+#define _IOC_WRITE 1U
+#define _IOC_READ 2U
+
+#define _IOC(dir,type,nr,size) \
+ (((dir) << _IOC_DIRSHIFT) | \
+ ((type) << _IOC_TYPESHIFT) | \
+ ((nr) << _IOC_NRSHIFT) | \
+ ((size) << _IOC_SIZESHIFT))
+
+/* used to create numbers */
+#define _IO(type,nr) _IOC(_IOC_NONE,(type),(nr),0)
+#define _IOR(type,nr,size) _IOC(_IOC_READ,(type),(nr),sizeof(size))
+#define _IOW(type,nr,size) _IOC(_IOC_WRITE,(type),(nr),sizeof(size))
+#define _IOWR(type,nr,size) _IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
+
+/* used to decode ioctl numbers.. */
+#define _IOC_DIR(nr) (((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
+#define _IOC_TYPE(nr) (((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
+#define _IOC_NR(nr) (((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
+#define _IOC_SIZE(nr) (((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
+
+/* ...and for the drivers/sound files... */
+
+#define IOC_IN (_IOC_WRITE << _IOC_DIRSHIFT)
+#define IOC_OUT (_IOC_READ << _IOC_DIRSHIFT)
+#define IOC_INOUT ((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
+#define IOCSIZE_MASK (_IOC_SIZEMASK << _IOC_SIZESHIFT)
+#define IOCSIZE_SHIFT (_IOC_SIZESHIFT)
+
+#endif /* _ASMI386_IOCTL_H */
--- /dev/null
+#ifndef __ARCH_I386_IOCTLS_H__
+#define __ARCH_I386_IOCTLS_H__
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS 0x5401
+#define TCSETS 0x5402
+#define TCSETSW 0x5403
+#define TCSETSF 0x5404
+#define TCGETA 0x5405
+#define TCSETA 0x5406
+#define TCSETAW 0x5407
+#define TCSETAF 0x5408
+#define TCSBRK 0x5409
+#define TCXONC 0x540A
+#define TCFLSH 0x540B
+#define TIOCEXCL 0x540C
+#define TIOCNXCL 0x540D
+#define TIOCSCTTY 0x540E
+#define TIOCGPGRP 0x540F
+#define TIOCSPGRP 0x5410
+#define TIOCOUTQ 0x5411
+#define TIOCSTI 0x5412
+#define TIOCGWINSZ 0x5413
+#define TIOCSWINSZ 0x5414
+#define TIOCMGET 0x5415
+#define TIOCMBIS 0x5416
+#define TIOCMBIC 0x5417
+#define TIOCMSET 0x5418
+#define TIOCGSOFTCAR 0x5419
+#define TIOCSSOFTCAR 0x541A
+#define FIONREAD 0x541B
+#define TIOCINQ FIONREAD
+#define TIOCLINUX 0x541C
+#define TIOCCONS 0x541D
+#define TIOCGSERIAL 0x541E
+#define TIOCSSERIAL 0x541F
+#define TIOCPKT 0x5420
+#define FIONBIO 0x5421
+#define TIOCNOTTY 0x5422
+#define TIOCSETD 0x5423
+#define TIOCGETD 0x5424
+#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */
+#define TIOCTTYGSTRUCT 0x5426 /* For debugging only */
+#define TIOCSBRK 0x5427 /* BSD compatibility */
+#define TIOCCBRK 0x5428 /* BSD compatibility */
+#define TIOCGSID 0x5429 /* Return the session ID of FD */
+#define TIOCGPTN _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK _IOW('T',0x31, int) /* Lock/unlock Pty */
+
+#define FIONCLEX 0x5450 /* these numbers need to be adjusted. */
+#define FIOCLEX 0x5451
+#define FIOASYNC 0x5452
+#define TIOCSERCONFIG 0x5453
+#define TIOCSERGWILD 0x5454
+#define TIOCSERSWILD 0x5455
+#define TIOCGLCKTRMIOS 0x5456
+#define TIOCSLCKTRMIOS 0x5457
+#define TIOCSERGSTRUCT 0x5458 /* For debugging only */
+#define TIOCSERGETLSR 0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */
+#define TIOCGHAYESESP 0x545E /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP 0x545F /* Set Hayes ESP configuration */
+
+/* Used for packet mode */
+#define TIOCPKT_DATA 0
+#define TIOCPKT_FLUSHREAD 1
+#define TIOCPKT_FLUSHWRITE 2
+#define TIOCPKT_STOP 4
+#define TIOCPKT_START 8
+#define TIOCPKT_NOSTOP 16
+#define TIOCPKT_DOSTOP 32
+
+#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */
+
+#endif
--- /dev/null
+#ifndef __i386_IPC_H__
+#define __i386_IPC_H__
+
+/*
+ * These are used to wrap system calls on x86.
+ *
+ * See arch/i386/kernel/sys_i386.c for ugly details..
+ */
+struct ipc_kludge {
+ struct msgbuf *msgp;
+ long msgtyp;
+};
+
+#define SEMOP 1
+#define SEMGET 2
+#define SEMCTL 3
+#define MSGSND 11
+#define MSGRCV 12
+#define MSGGET 13
+#define MSGCTL 14
+#define SHMAT 21
+#define SHMDT 22
+#define SHMGET 23
+#define SHMCTL 24
+
+/* Used by the DIPC package, try and avoid reusing it */
+#define DIPC 25
+
+#define IPCCALL(version,op) ((version)<<16 | (op))
+
+#endif
--- /dev/null
+#ifndef __i386_IPCBUF_H__
+#define __i386_IPCBUF_H__
+
+/*
+ * The ipc64_perm structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 32-bit mode_t and seq
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct ipc64_perm
+{
+ __kernel_key_t key;
+ __kernel_uid32_t uid;
+ __kernel_gid32_t gid;
+ __kernel_uid32_t cuid;
+ __kernel_gid32_t cgid;
+ __kernel_mode_t mode;
+ unsigned short __pad1;
+ unsigned short seq;
+ unsigned short __pad2;
+ unsigned long __unused1;
+ unsigned long __unused2;
+};
+
+#endif /* __i386_IPCBUF_H__ */
--- /dev/null
+#ifndef _ASM_IRQ_H
+#define _ASM_IRQ_H
+
+/*
+ * linux/include/asm/irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ */
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+#include <asm/ptrace.h>
+
+#define NET_TX_IRQ _EVENT_NET_TX
+#define NET_RX_IRQ _EVENT_NET_RX
+#define NET2_TX_IRQ _EVENT_NET2_TX
+#define NET2_RX_IRQ _EVENT_NET2_RX
+#define TIMER_IRQ _EVENT_TIMER
+
+#define NR_IRQS (sizeof(HYPERVISOR_shared_info->events) * 8)
+
+#define irq_cannonicalize(_irq) (_irq)
+
+extern void disable_irq(unsigned int);
+extern void disable_irq_nosync(unsigned int);
+extern void enable_irq(unsigned int);
+extern unsigned int do_IRQ(int, struct pt_regs *);
+
+#endif /* _ASM_IRQ_H */
--- /dev/null
+/*
+ * Minimalist Kernel Debugger
+ *
+ * Copyright (C) 1999 Silicon Graphics, Inc.
+ * Copyright (C) Scott Lurndal (slurn@engr.sgi.com)
+ * Copyright (C) Scott Foehner (sfoehner@engr.sgi.com)
+ * Copyright (C) Srinivasa Thirumalachar (sprasad@engr.sgi.com)
+ *
+ * See the file LIA-COPYRIGHT for additional information.
+ *
+ * Written March 1999 by Scott Lurndal at Silicon Graphics, Inc.
+ *
+ * Modifications from:
+ * Richard Bass 1999/07/20
+ * Many bug fixes and enhancements.
+ * Scott Foehner
+ * Port to ia64
+ * Scott Lurndal 1999/12/12
+ * v1.0 restructuring.
+ */
+#if !defined(_ASM_KDB_H)
+#define _ASM_KDB_H
+
+ /*
+ * KDB_ENTER() is a macro which causes entry into the kernel
+ * debugger from any point in the kernel code stream. If it
+ * is intended to be used from interrupt level, it must use
+ * a non-maskable entry method.
+ */
+#define KDB_ENTER() asm("\tint $129\n")
+
+ /*
+ * Define the exception frame for this architeture
+ */
+struct pt_regs;
+typedef struct pt_regs *kdb_eframe_t;
+
+ /*
+ * Needed for exported symbols.
+ */
+typedef unsigned long kdb_machreg_t;
+
+#define kdb_machreg_fmt "0x%lx"
+#define kdb_machreg_fmt0 "0x%08lx"
+#define kdb_bfd_vma_fmt "0x%lx"
+#define kdb_bfd_vma_fmt0 "0x%08lx"
+#define kdb_elfw_addr_fmt "0x%x"
+#define kdb_elfw_addr_fmt0 "0x%08x"
+
+ /*
+ * Per cpu arch specific kdb state. Must be in range 0xff000000.
+ */
+#define KDB_STATE_A_IF 0x01000000 /* Saved IF flag */
+
+ /*
+ * Interface from kernel trap handling code to kernel debugger.
+ */
+extern int kdba_callback_die(struct pt_regs *, int, long, void*);
+extern int kdba_callback_bp(struct pt_regs *, int, long, void*);
+extern int kdba_callback_debug(struct pt_regs *, int, long, void *);
+
+#endif /* ASM_KDB_H */
--- /dev/null
+/*
+ * Minimalist Kernel Debugger
+ *
+ * Copyright (C) 1999 Silicon Graphics, Inc.
+ * Copyright (C) Scott Lurndal (slurn@engr.sgi.com)
+ * Copyright (C) Scott Foehner (sfoehner@engr.sgi.com)
+ * Copyright (C) Srinivasa Thirumalachar (sprasad@engr.sgi.com)
+ *
+ * See the file LIA-COPYRIGHT for additional information.
+ *
+ * Written March 1999 by Scott Lurndal at Silicon Graphics, Inc.
+ *
+ * Modifications from:
+ * Richard Bass 1999/07/20
+ * Many bug fixes and enhancements.
+ * Scott Foehner
+ * Port to ia64
+ * Scott Lurndal 1999/12/12
+ * v1.0 restructuring.
+ * Keith Owens 2000/05/23
+ * KDB v1.2
+ */
+#if !defined(_ASM_KDBPRIVATE_H)
+#define _ASM_KDBPRIVATE_H
+
+typedef unsigned char kdb_machinst_t;
+
+ /*
+ * KDB_MAXBPT describes the total number of breakpoints
+ * supported by this architecure.
+ */
+#define KDB_MAXBPT 16
+ /*
+ * KDB_MAXHARDBPT describes the total number of hardware
+ * breakpoint registers that exist.
+ */
+#define KDB_MAXHARDBPT 4
+ /*
+ * Provide space for KDB_MAX_COMMANDS commands.
+ */
+#define KDB_MAX_COMMANDS 125
+
+ /*
+ * Platform specific environment entries
+ */
+#define KDB_PLATFORM_ENV "IDMODE=x86", "BYTESPERWORD=4", "IDCOUNT=16"
+
+ /*
+ * Define the direction that the stack grows
+ */
+#define KDB_STACK_DIRECTION (-1) /* Stack grows down */
+
+ /*
+ * Support for ia32 debug registers
+ */
+typedef struct _kdbhard_bp {
+ kdb_machreg_t bph_reg; /* Register this breakpoint uses */
+
+ unsigned int bph_free:1; /* Register available for use */
+ unsigned int bph_data:1; /* Data Access breakpoint */
+
+ unsigned int bph_write:1; /* Write Data breakpoint */
+ unsigned int bph_mode:2; /* 0=inst, 1=write, 2=io, 3=read */
+ unsigned int bph_length:2; /* 0=1, 1=2, 2=BAD, 3=4 (bytes) */
+} kdbhard_bp_t;
+
+extern kdbhard_bp_t kdb_hardbreaks[/* KDB_MAXHARDBPT */];
+
+#define IA32_BREAKPOINT_INSTRUCTION 0xcc
+
+#define DR6_BT 0x00008000
+#define DR6_BS 0x00004000
+#define DR6_BD 0x00002000
+
+#define DR6_B3 0x00000008
+#define DR6_B2 0x00000004
+#define DR6_B1 0x00000002
+#define DR6_B0 0x00000001
+
+#define DR7_RW_VAL(dr, drnum) \
+ (((dr) >> (16 + (4 * (drnum)))) & 0x3)
+
+#define DR7_RW_SET(dr, drnum, rw) \
+ do { \
+ (dr) &= ~(0x3 << (16 + (4 * (drnum)))); \
+ (dr) |= (((rw) & 0x3) << (16 + (4 * (drnum)))); \
+ } while (0)
+
+#define DR7_RW0(dr) DR7_RW_VAL(dr, 0)
+#define DR7_RW0SET(dr,rw) DR7_RW_SET(dr, 0, rw)
+#define DR7_RW1(dr) DR7_RW_VAL(dr, 1)
+#define DR7_RW1SET(dr,rw) DR7_RW_SET(dr, 1, rw)
+#define DR7_RW2(dr) DR7_RW_VAL(dr, 2)
+#define DR7_RW2SET(dr,rw) DR7_RW_SET(dr, 2, rw)
+#define DR7_RW3(dr) DR7_RW_VAL(dr, 3)
+#define DR7_RW3SET(dr,rw) DR7_RW_SET(dr, 3, rw)
+
+
+#define DR7_LEN_VAL(dr, drnum) \
+ (((dr) >> (18 + (4 * (drnum)))) & 0x3)
+
+#define DR7_LEN_SET(dr, drnum, rw) \
+ do { \
+ (dr) &= ~(0x3 << (18 + (4 * (drnum)))); \
+ (dr) |= (((rw) & 0x3) << (18 + (4 * (drnum)))); \
+ } while (0)
+#define DR7_LEN0(dr) DR7_LEN_VAL(dr, 0)
+#define DR7_LEN0SET(dr,len) DR7_LEN_SET(dr, 0, len)
+#define DR7_LEN1(dr) DR7_LEN_VAL(dr, 1)
+#define DR7_LEN1SET(dr,len) DR7_LEN_SET(dr, 1, len)
+#define DR7_LEN2(dr) DR7_LEN_VAL(dr, 2)
+#define DR7_LEN2SET(dr,len) DR7_LEN_SET(dr, 2, len)
+#define DR7_LEN3(dr) DR7_LEN_VAL(dr, 3)
+#define DR7_LEN3SET(dr,len) DR7_LEN_SET(dr, 3, len)
+
+#define DR7_G0(dr) (((dr)>>1)&0x1)
+#define DR7_G0SET(dr) ((dr) |= 0x2)
+#define DR7_G0CLR(dr) ((dr) &= ~0x2)
+#define DR7_G1(dr) (((dr)>>3)&0x1)
+#define DR7_G1SET(dr) ((dr) |= 0x8)
+#define DR7_G1CLR(dr) ((dr) &= ~0x8)
+#define DR7_G2(dr) (((dr)>>5)&0x1)
+#define DR7_G2SET(dr) ((dr) |= 0x20)
+#define DR7_G2CLR(dr) ((dr) &= ~0x20)
+#define DR7_G3(dr) (((dr)>>7)&0x1)
+#define DR7_G3SET(dr) ((dr) |= 0x80)
+#define DR7_G3CLR(dr) ((dr) &= ~0x80)
+
+#define DR7_L0(dr) (((dr))&0x1)
+#define DR7_L0SET(dr) ((dr) |= 0x1)
+#define DR7_L0CLR(dr) ((dr) &= ~0x1)
+#define DR7_L1(dr) (((dr)>>2)&0x1)
+#define DR7_L1SET(dr) ((dr) |= 0x4)
+#define DR7_L1CLR(dr) ((dr) &= ~0x4)
+#define DR7_L2(dr) (((dr)>>4)&0x1)
+#define DR7_L2SET(dr) ((dr) |= 0x10)
+#define DR7_L2CLR(dr) ((dr) &= ~0x10)
+#define DR7_L3(dr) (((dr)>>6)&0x1)
+#define DR7_L3SET(dr) ((dr) |= 0x40)
+#define DR7_L3CLR(dr) ((dr) &= ~0x40)
+
+#define DR7_GD 0x00002000 /* General Detect Enable */
+#define DR7_GE 0x00000200 /* Global exact */
+#define DR7_LE 0x00000100 /* Local exact */
+
+extern kdb_machreg_t kdba_getdr6(void);
+extern void kdba_putdr6(kdb_machreg_t);
+
+extern kdb_machreg_t kdba_getdr7(void);
+
+extern kdb_machreg_t kdba_getdr(int);
+extern void kdba_putdr(int, kdb_machreg_t);
+
+extern kdb_machreg_t kdb_getcr(int);
+
+#define KDB_HAVE_LONGJMP
+#ifdef KDB_HAVE_LONGJMP
+/*
+ * Support for setjmp/longjmp
+ */
+#define JB_BX 0
+#define JB_SI 1
+#define JB_DI 2
+#define JB_BP 3
+#define JB_SP 4
+#define JB_PC 5
+
+typedef struct __kdb_jmp_buf {
+ unsigned long regs[6]; /* kdba_setjmp assumes fixed offsets here */
+} kdb_jmp_buf;
+
+extern int kdba_setjmp(kdb_jmp_buf *);
+extern void kdba_longjmp(kdb_jmp_buf *, int);
+
+extern kdb_jmp_buf kdbjmpbuf[];
+#endif /* KDB_HAVE_LONGJMP */
+
+#endif /* !_ASM_KDBPRIVATE_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/keyboard.h
+ *
+ * Created 3 Nov 1996 by Geert Uytterhoeven
+ */
+
+/*
+ * This file contains the i386 architecture specific keyboard definitions
+ */
+
+#ifndef _I386_KEYBOARD_H
+#define _I386_KEYBOARD_H
+
+#ifdef __KERNEL__
+
+#include <linux/kernel.h>
+#include <linux/ioport.h>
+#include <linux/kd.h>
+#include <linux/pm.h>
+#include <asm/io.h>
+
+#define KEYBOARD_IRQ 1
+#define DISABLE_KBD_DURING_INTERRUPTS 0
+
+extern int pckbd_setkeycode(unsigned int scancode, unsigned int keycode);
+extern int pckbd_getkeycode(unsigned int scancode);
+extern int pckbd_translate(unsigned char scancode, unsigned char *keycode,
+ char raw_mode);
+extern char pckbd_unexpected_up(unsigned char keycode);
+extern void pckbd_leds(unsigned char leds);
+extern void pckbd_init_hw(void);
+extern int pckbd_pm_resume(struct pm_dev *, pm_request_t, void *);
+extern pm_callback pm_kbd_request_override;
+extern unsigned char pckbd_sysrq_xlate[128];
+
+#define kbd_setkeycode pckbd_setkeycode
+#define kbd_getkeycode pckbd_getkeycode
+#define kbd_translate pckbd_translate
+#define kbd_unexpected_up pckbd_unexpected_up
+#define kbd_leds pckbd_leds
+#define kbd_init_hw pckbd_init_hw
+#define kbd_sysrq_xlate pckbd_sysrq_xlate
+
+#define SYSRQ_KEY 0x54
+#define E1_PAUSE 119 /* PAUSE key */
+
+/* resource allocation */
+#define kbd_request_region()
+#define kbd_request_irq(handler) request_irq(KEYBOARD_IRQ, handler, 0, \
+ "keyboard", NULL)
+
+/* How to access the keyboard macros on this platform. */
+#define kbd_read_input() inb(KBD_DATA_REG)
+#define kbd_read_status() inb(KBD_STATUS_REG)
+#define kbd_write_output(val) outb(val, KBD_DATA_REG)
+#define kbd_write_command(val) outb(val, KBD_CNTL_REG)
+
+/* Some stoneage hardware needs delays after some operations. */
+#define kbd_pause() do { } while(0)
+
+/*
+ * Machine specific bits for the PS/2 driver
+ */
+
+#define AUX_IRQ 12
+
+#define aux_request_irq(hand, dev_id) \
+ request_irq(AUX_IRQ, hand, SA_SHIRQ, "PS/2 Mouse", dev_id)
+
+#define aux_free_irq(dev_id) free_irq(AUX_IRQ, dev_id)
+
+#endif /* __KERNEL__ */
+#endif /* _I386_KEYBOARD_H */
--- /dev/null
+#ifndef _ASM_KMAP_TYPES_H
+#define _ASM_KMAP_TYPES_H
+
+enum km_type {
+ KM_BOUNCE_READ,
+ KM_SKB_DATA,
+ KM_SKB_DATA_SOFTIRQ,
+ KM_USER0,
+ KM_USER1,
+ KM_TYPE_NR
+};
+
+#endif
--- /dev/null
+/*
+ * ldt.h
+ *
+ * Definitions of structures used with the modify_ldt system call.
+ */
+#ifndef _LINUX_LDT_H
+#define _LINUX_LDT_H
+
+/* Maximum number of LDT entries supported. */
+#define LDT_ENTRIES 8192
+/* The size of each LDT entry. */
+#define LDT_ENTRY_SIZE 8
+
+#ifndef __ASSEMBLY__
+struct modify_ldt_ldt_s {
+ unsigned int entry_number;
+ unsigned long base_addr;
+ unsigned int limit;
+ unsigned int seg_32bit:1;
+ unsigned int contents:2;
+ unsigned int read_exec_only:1;
+ unsigned int limit_in_pages:1;
+ unsigned int seg_not_present:1;
+ unsigned int useable:1;
+};
+
+#define MODIFY_LDT_CONTENTS_DATA 0
+#define MODIFY_LDT_CONTENTS_STACK 1
+#define MODIFY_LDT_CONTENTS_CODE 2
+
+#endif /* !__ASSEMBLY__ */
+#endif
--- /dev/null
+/* $Id: linux_logo.h,v 1.8 1998/07/30 16:30:24 jj Exp $
+ * include/asm-i386/linux_logo.h: This is a linux logo
+ * to be displayed on boot.
+ *
+ * Copyright (C) 1996 Larry Ewing (lewing@isc.tamu.edu)
+ * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ *
+ * You can put anything here, but:
+ * LINUX_LOGO_COLORS has to be less than 224
+ * image size has to be 80x80
+ * values have to start from 0x20
+ * (i.e. RGB(linux_logo_red[0],
+ * linux_logo_green[0],
+ * linux_logo_blue[0]) is color 0x20)
+ * BW image has to be 80x80 as well, with MS bit
+ * on the left
+ * Serial_console ascii image can be any size,
+ * but should contain %s to display the version
+ */
+
+#include <linux/init.h>
+#include <linux/version.h>
+
+#define linux_logo_banner "Linux/ia32 version " UTS_RELEASE
+
+#include <linux/linux_logo.h>
+
--- /dev/null
+/*
+ * SMP locks primitives for building ix86 locks
+ * (not yet used).
+ *
+ * Alan Cox, alan@redhat.com, 1995
+ */
+
+/*
+ * This would be much easier but far less clear and easy
+ * to borrow for other processors if it was just assembler.
+ */
+
+static __inline__ void prim_spin_lock(struct spinlock *sp)
+{
+ int processor=smp_processor_id();
+
+ /*
+ * Grab the lock bit
+ */
+
+ while(lock_set_bit(0,&sp->lock))
+ {
+ /*
+ * Failed, but that's cos we own it!
+ */
+
+ if(sp->cpu==processor)
+ {
+ sp->users++;
+ return 0;
+ }
+ /*
+ * Spin in the cache S state if possible
+ */
+ while(sp->lock)
+ {
+ /*
+ * Wait for any invalidates to go off
+ */
+
+ if(smp_invalidate_needed&(1<<processor))
+ while(lock_clear_bit(processor,&smp_invalidate_needed))
+ local_flush_tlb();
+ sp->spins++;
+ }
+ /*
+ * Someone wrote the line, we go 'I' and get
+ * the cache entry. Now try to regrab
+ */
+ }
+ sp->users++;sp->cpu=processor;
+ return 1;
+}
+
+/*
+ * Release a spin lock
+ */
+
+static __inline__ int prim_spin_unlock(struct spinlock *sp)
+{
+ /* This is safe. The decrement is still guarded by the lock. A multilock would
+ not be safe this way */
+ if(!--sp->users)
+ {
+ sp->cpu= NO_PROC_ID;lock_clear_bit(0,&sp->lock);
+ return 1;
+ }
+ return 0;
+}
+
+
+/*
+ * Non blocking lock grab
+ */
+
+static __inline__ int prim_spin_lock_nb(struct spinlock *sp)
+{
+ if(lock_set_bit(0,&sp->lock))
+ return 0; /* Locked already */
+ sp->users++;
+ return 1; /* We got the lock */
+}
+
+
+/*
+ * These wrap the locking primitives up for usage
+ */
+
+static __inline__ void spinlock(struct spinlock *sp)
+{
+ if(sp->priority<current->lock_order)
+ panic("lock order violation: %s (%d)\n", sp->name, current->lock_order);
+ if(prim_spin_lock(sp))
+ {
+ /*
+ * We got a new lock. Update the priority chain
+ */
+ sp->oldpri=current->lock_order;
+ current->lock_order=sp->priority;
+ }
+}
+
+static __inline__ void spinunlock(struct spinlock *sp)
+{
+ int pri;
+ if(current->lock_order!=sp->priority)
+ panic("lock release order violation %s (%d)\n", sp->name, current->lock_order);
+ pri=sp->oldpri;
+ if(prim_spin_unlock(sp))
+ {
+ /*
+ * Update the debugging lock priority chain. We dumped
+ * our last right to the lock.
+ */
+ current->lock_order=sp->pri;
+ }
+}
+
+static __inline__ void spintestlock(struct spinlock *sp)
+{
+ /*
+ * We do no sanity checks, it's legal to optimistically
+ * get a lower lock.
+ */
+ prim_spin_lock_nb(sp);
+}
+
+static __inline__ void spintestunlock(struct spinlock *sp)
+{
+ /*
+ * A testlock doesn't update the lock chain so we
+ * must not update it on free
+ */
+ prim_spin_unlock(sp);
+}
--- /dev/null
+#ifndef _I386_MATH_EMU_H
+#define _I386_MATH_EMU_H
+
+#include <asm/sigcontext.h>
+
+int restore_i387_soft(void *s387, struct _fpstate *buf);
+int save_i387_soft(void *s387, struct _fpstate * buf);
+
+/* This structure matches the layout of the data saved to the stack
+ following a device-not-present interrupt, part of it saved
+ automatically by the 80386/80486.
+ */
+struct info {
+ long ___orig_eip;
+ long ___ebx;
+ long ___ecx;
+ long ___edx;
+ long ___esi;
+ long ___edi;
+ long ___ebp;
+ long ___eax;
+ long ___ds;
+ long ___es;
+ long ___orig_eax;
+ long ___eip;
+ long ___cs;
+ long ___eflags;
+ long ___esp;
+ long ___ss;
+ long ___vm86_es; /* This and the following only in vm86 mode */
+ long ___vm86_ds;
+ long ___vm86_fs;
+ long ___vm86_gs;
+};
+#endif
--- /dev/null
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+#include <asm/io.h>
+
+#ifndef RTC_PORT
+#define RTC_PORT(x) (0x70 + (x))
+#define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */
+#endif
+
+/*
+ * The yet supported machines all access the RTC index register via
+ * an ISA port access but the way to access the date register differs ...
+ */
+#define CMOS_READ(addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+inb_p(RTC_PORT(1)); \
+})
+#define CMOS_WRITE(val, addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+outb_p((val),RTC_PORT(1)); \
+})
+
+#define RTC_IRQ 8
+
+#endif /* _ASM_MC146818RTC_H */
--- /dev/null
+#ifndef MCA_DMA_H
+#define MCA_DMA_H
+
+#include <asm/io.h>
+#include <linux/ioport.h>
+
+/*
+ * Microchannel specific DMA stuff. DMA on an MCA machine is fairly similar to
+ * standard PC dma, but it certainly has its quirks. DMA register addresses
+ * are in a different place and there are some added functions. Most of this
+ * should be pretty obvious on inspection. Note that the user must divide
+ * count by 2 when using 16-bit dma; that is not handled by these functions.
+ *
+ * Ramen Noodles are yummy.
+ *
+ * 1998 Tymm Twillman <tymm@computer.org>
+ */
+
+/*
+ * Registers that are used by the DMA controller; FN is the function register
+ * (tell the controller what to do) and EXE is the execution register (how
+ * to do it)
+ */
+
+#define MCA_DMA_REG_FN 0x18
+#define MCA_DMA_REG_EXE 0x1A
+
+/*
+ * Functions that the DMA controller can do
+ */
+
+#define MCA_DMA_FN_SET_IO 0x00
+#define MCA_DMA_FN_SET_ADDR 0x20
+#define MCA_DMA_FN_GET_ADDR 0x30
+#define MCA_DMA_FN_SET_COUNT 0x40
+#define MCA_DMA_FN_GET_COUNT 0x50
+#define MCA_DMA_FN_GET_STATUS 0x60
+#define MCA_DMA_FN_SET_MODE 0x70
+#define MCA_DMA_FN_SET_ARBUS 0x80
+#define MCA_DMA_FN_MASK 0x90
+#define MCA_DMA_FN_RESET_MASK 0xA0
+#define MCA_DMA_FN_MASTER_CLEAR 0xD0
+
+/*
+ * Modes (used by setting MCA_DMA_FN_MODE in the function register)
+ *
+ * Note that the MODE_READ is read from memory (write to device), and
+ * MODE_WRITE is vice-versa.
+ */
+
+#define MCA_DMA_MODE_XFER 0x04 /* read by default */
+#define MCA_DMA_MODE_READ 0x04 /* same as XFER */
+#define MCA_DMA_MODE_WRITE 0x08 /* OR with MODE_XFER to use */
+#define MCA_DMA_MODE_IO 0x01 /* DMA from IO register */
+#define MCA_DMA_MODE_16 0x40 /* 16 bit xfers */
+
+
+/**
+ * mca_enable_dma - channel to enable DMA on
+ * @dmanr: DMA channel
+ *
+ * Enable the MCA bus DMA on a channel. This can be called from
+ * IRQ context.
+ */
+
+static __inline__ void mca_enable_dma(unsigned int dmanr)
+{
+ outb(MCA_DMA_FN_RESET_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ * mca_disble_dma - channel to disable DMA on
+ * @dmanr: DMA channel
+ *
+ * Enable the MCA bus DMA on a channel. This can be called from
+ * IRQ context.
+ */
+
+static __inline__ void mca_disable_dma(unsigned int dmanr)
+{
+ outb(MCA_DMA_FN_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ * mca_set_dma_addr - load a 24bit DMA address
+ * @dmanr: DMA channel
+ * @a: 24bit bus address
+ *
+ * Load the address register in the DMA controller. This has a 24bit
+ * limitation (16Mb).
+ */
+
+static __inline__ void mca_set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+ outb(MCA_DMA_FN_SET_ADDR | dmanr, MCA_DMA_REG_FN);
+ outb(a & 0xff, MCA_DMA_REG_EXE);
+ outb((a >> 8) & 0xff, MCA_DMA_REG_EXE);
+ outb((a >> 16) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ * mca_get_dma_addr - load a 24bit DMA address
+ * @dmanr: DMA channel
+ *
+ * Read the address register in the DMA controller. This has a 24bit
+ * limitation (16Mb). The return is a bus address.
+ */
+
+static __inline__ unsigned int mca_get_dma_addr(unsigned int dmanr)
+{
+ unsigned int addr;
+
+ outb(MCA_DMA_FN_GET_ADDR | dmanr, MCA_DMA_REG_FN);
+ addr = inb(MCA_DMA_REG_EXE);
+ addr |= inb(MCA_DMA_REG_EXE) << 8;
+ addr |= inb(MCA_DMA_REG_EXE) << 16;
+
+ return addr;
+}
+
+/**
+ * mca_set_dma_count - load a 16bit transfer count
+ * @dmanr: DMA channel
+ * @count: count
+ *
+ * Set the DMA count for this channel. This can be up to 64Kbytes.
+ * Setting a count of zero will not do what you expect.
+ */
+
+static __inline__ void mca_set_dma_count(unsigned int dmanr, unsigned int count)
+{
+ count--; /* transfers one more than count -- correct for this */
+
+ outb(MCA_DMA_FN_SET_COUNT | dmanr, MCA_DMA_REG_FN);
+ outb(count & 0xff, MCA_DMA_REG_EXE);
+ outb((count >> 8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ * mca_get_dma_residue - get the remaining bytes to transfer
+ * @dmanr: DMA channel
+ *
+ * This function returns the number of bytes left to transfer
+ * on this DMA channel.
+ */
+
+static __inline__ unsigned int mca_get_dma_residue(unsigned int dmanr)
+{
+ unsigned short count;
+
+ outb(MCA_DMA_FN_GET_COUNT | dmanr, MCA_DMA_REG_FN);
+ count = 1 + inb(MCA_DMA_REG_EXE);
+ count += inb(MCA_DMA_REG_EXE) << 8;
+
+ return count;
+}
+
+/**
+ * mca_set_dma_io - set the port for an I/O transfer
+ * @dmanr: DMA channel
+ * @io_addr: an I/O port number
+ *
+ * Unlike the ISA bus DMA controllers the DMA on MCA bus can transfer
+ * with an I/O port target.
+ */
+
+static __inline__ void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
+{
+ /*
+ * DMA from a port address -- set the io address
+ */
+
+ outb(MCA_DMA_FN_SET_IO | dmanr, MCA_DMA_REG_FN);
+ outb(io_addr & 0xff, MCA_DMA_REG_EXE);
+ outb((io_addr >> 8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ * mca_set_dma_mode - set the DMA mode
+ * @dmanr: DMA channel
+ * @mode: mode to set
+ *
+ * The DMA controller supports several modes. The mode values you can
+ * set are :
+ *
+ * %MCA_DMA_MODE_READ when reading from the DMA device.
+ *
+ * %MCA_DMA_MODE_WRITE to writing to the DMA device.
+ *
+ * %MCA_DMA_MODE_IO to do DMA to or from an I/O port.
+ *
+ * %MCA_DMA_MODE_16 to do 16bit transfers.
+ *
+ */
+
+static __inline__ void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
+{
+ outb(MCA_DMA_FN_SET_MODE | dmanr, MCA_DMA_REG_FN);
+ outb(mode, MCA_DMA_REG_EXE);
+}
+
+#endif /* MCA_DMA_H */
--- /dev/null
+#ifndef __I386_MMAN_H__
+#define __I386_MMAN_H__
+
+#define PROT_READ 0x1 /* page can be read */
+#define PROT_WRITE 0x2 /* page can be written */
+#define PROT_EXEC 0x4 /* page can be executed */
+#define PROT_NONE 0x0 /* page can not be accessed */
+
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_TYPE 0x0f /* Mask for type of mapping */
+#define MAP_FIXED 0x10 /* Interpret addr exactly */
+#define MAP_ANONYMOUS 0x20 /* don't use a file */
+
+#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
+#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
+#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
+#define MAP_LOCKED 0x2000 /* pages are locked */
+#define MAP_NORESERVE 0x4000 /* don't check for reservations */
+
+#define MS_ASYNC 1 /* sync memory asynchronously */
+#define MS_INVALIDATE 2 /* invalidate the caches */
+#define MS_SYNC 4 /* synchronous memory sync */
+
+#define MCL_CURRENT 1 /* lock all current mappings */
+#define MCL_FUTURE 2 /* lock all future mappings */
+
+#define MADV_NORMAL 0x0 /* default page-in behavior */
+#define MADV_RANDOM 0x1 /* page-in minimum required */
+#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
+#define MADV_WILLNEED 0x3 /* pre-fault pages */
+#define MADV_DONTNEED 0x4 /* discard these pages */
+
+/* compatibility flags */
+#define MAP_ANON MAP_ANONYMOUS
+#define MAP_FILE 0
+
+#endif /* __I386_MMAN_H__ */
--- /dev/null
+
+#ifndef __i386_MMU_H
+#define __i386_MMU_H
+
+#include <linux/list.h>
+
+/* describes dirrectly mapped vma nodes */
+typedef struct {
+ struct list_head list;
+ unsigned long vm_start;
+ unsigned long vm_end;
+} direct_mmap_node_t;
+
+/*
+ * The i386 doesn't have a mmu context, but
+ * we put the segment information here.
+ */
+typedef struct {
+ void *segments;
+ unsigned long cpuvalid;
+ struct list_head direct_list;
+} mm_context_t;
+
+#endif
--- /dev/null
+
+#ifndef __I386_MMU_CONTEXT_H
+#define __I386_MMU_CONTEXT_H
+
+#include <linux/config.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+
+/*
+ * possibly do the LDT unload here?
+ */
+
+extern int init_new_context(struct task_struct *tsk, struct mm_struct *);
+extern void destroy_context(struct mm_struct *);
+
+//#define destroy_context(mm) do { } while(0)
+//#define init_new_context(tsk,mm) 0
+
+#ifdef CONFIG_SMP
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk, unsigned cpu)
+{
+ if(cpu_tlbstate[cpu].state == TLBSTATE_OK)
+ cpu_tlbstate[cpu].state = TLBSTATE_LAZY;
+}
+#else
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk, unsigned cpu)
+{
+}
+#endif
+
+extern pgd_t *cur_pgd;
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk, unsigned cpu)
+{
+ if (prev != next) {
+ /* stop flush ipis for the previous mm */
+ clear_bit(cpu, &prev->cpu_vm_mask);
+ /*
+ * Re-load LDT if necessary
+ */
+ if (prev->context.segments != next->context.segments)
+ load_LDT(next);
+#ifdef CONFIG_SMP
+ cpu_tlbstate[cpu].state = TLBSTATE_OK;
+ cpu_tlbstate[cpu].active_mm = next;
+#endif
+ set_bit(cpu, &next->cpu_vm_mask);
+ set_bit(cpu, &next->context.cpuvalid);
+ /* Re-load page tables */
+ cur_pgd = next->pgd;
+ queue_pt_switch(__pa(cur_pgd));
+ XENO_flush_page_update_queue();
+ }
+#ifdef CONFIG_SMP
+ else {
+ cpu_tlbstate[cpu].state = TLBSTATE_OK;
+ if(cpu_tlbstate[cpu].active_mm != next)
+ BUG();
+ if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) {
+ /* We were in lazy tlb mode and leave_mm disabled
+ * tlb flush IPI delivery. We must flush our tlb.
+ */
+ local_flush_tlb();
+ }
+ if (!test_and_set_bit(cpu, &next->context.cpuvalid))
+ load_LDT(next);
+ }
+#endif
+}
+
+#define activate_mm(prev, next) \
+ switch_mm((prev),(next),NULL,smp_processor_id())
+
+#endif
--- /dev/null
+#ifndef _ASM_MMX_H
+#define _ASM_MMX_H
+
+/*
+ * MMX 3Dnow! helper operations
+ */
+
+#include <linux/types.h>
+
+extern void *_mmx_memcpy(void *to, const void *from, size_t size);
+extern void mmx_clear_page(void *page);
+extern void mmx_copy_page(void *to, void *from);
+
+#endif
--- /dev/null
+#ifndef _ASM_I386_MODULE_H
+#define _ASM_I386_MODULE_H
+/*
+ * This file contains the i386 architecture specific module code.
+ */
+
+#define module_map(x) vmalloc(x)
+#define module_unmap(x) vfree(x)
+#define module_arch_init(x) (0)
+#define arch_init_modules(x) do { } while (0)
+
+#endif /* _ASM_I386_MODULE_H */
--- /dev/null
+#ifndef __ASM_MPSPEC_H
+#define __ASM_MPSPEC_H
+
+/*
+ * Structure definitions for SMP machines following the
+ * Intel Multiprocessing Specification 1.1 and 1.4.
+ */
+
+/*
+ * This tag identifies where the SMP configuration
+ * information is.
+ */
+
+#define SMP_MAGIC_IDENT (('_'<<24)|('P'<<16)|('M'<<8)|'_')
+
+/*
+ * a maximum of 16 APICs with the current APIC ID architecture.
+ */
+#ifdef CONFIG_MULTIQUAD
+#define MAX_APICS 256
+#else /* !CONFIG_MULTIQUAD */
+#define MAX_APICS 16
+#endif /* CONFIG_MULTIQUAD */
+
+#define MAX_MPC_ENTRY 1024
+
+struct intel_mp_floating
+{
+ char mpf_signature[4]; /* "_MP_" */
+ unsigned long mpf_physptr; /* Configuration table address */
+ unsigned char mpf_length; /* Our length (paragraphs) */
+ unsigned char mpf_specification;/* Specification version */
+ unsigned char mpf_checksum; /* Checksum (makes sum 0) */
+ unsigned char mpf_feature1; /* Standard or configuration ? */
+ unsigned char mpf_feature2; /* Bit7 set for IMCR|PIC */
+ unsigned char mpf_feature3; /* Unused (0) */
+ unsigned char mpf_feature4; /* Unused (0) */
+ unsigned char mpf_feature5; /* Unused (0) */
+};
+
+struct mp_config_table
+{
+ char mpc_signature[4];
+#define MPC_SIGNATURE "PCMP"
+ unsigned short mpc_length; /* Size of table */
+ char mpc_spec; /* 0x01 */
+ char mpc_checksum;
+ char mpc_oem[8];
+ char mpc_productid[12];
+ unsigned long mpc_oemptr; /* 0 if not present */
+ unsigned short mpc_oemsize; /* 0 if not present */
+ unsigned short mpc_oemcount;
+ unsigned long mpc_lapic; /* APIC address */
+ unsigned long reserved;
+};
+
+/* Followed by entries */
+
+#define MP_PROCESSOR 0
+#define MP_BUS 1
+#define MP_IOAPIC 2
+#define MP_INTSRC 3
+#define MP_LINTSRC 4
+#define MP_TRANSLATION 192 /* Used by IBM NUMA-Q to describe node locality */
+
+struct mpc_config_processor
+{
+ unsigned char mpc_type;
+ unsigned char mpc_apicid; /* Local APIC number */
+ unsigned char mpc_apicver; /* Its versions */
+ unsigned char mpc_cpuflag;
+#define CPU_ENABLED 1 /* Processor is available */
+#define CPU_BOOTPROCESSOR 2 /* Processor is the BP */
+ unsigned long mpc_cpufeature;
+#define CPU_STEPPING_MASK 0x0F
+#define CPU_MODEL_MASK 0xF0
+#define CPU_FAMILY_MASK 0xF00
+ unsigned long mpc_featureflag; /* CPUID feature value */
+ unsigned long mpc_reserved[2];
+};
+
+struct mpc_config_bus
+{
+ unsigned char mpc_type;
+ unsigned char mpc_busid;
+ unsigned char mpc_bustype[6] __attribute((packed));
+};
+
+/* List of Bus Type string values, Intel MP Spec. */
+#define BUSTYPE_EISA "EISA"
+#define BUSTYPE_ISA "ISA"
+#define BUSTYPE_INTERN "INTERN" /* Internal BUS */
+#define BUSTYPE_MCA "MCA"
+#define BUSTYPE_VL "VL" /* Local bus */
+#define BUSTYPE_PCI "PCI"
+#define BUSTYPE_PCMCIA "PCMCIA"
+#define BUSTYPE_CBUS "CBUS"
+#define BUSTYPE_CBUSII "CBUSII"
+#define BUSTYPE_FUTURE "FUTURE"
+#define BUSTYPE_MBI "MBI"
+#define BUSTYPE_MBII "MBII"
+#define BUSTYPE_MPI "MPI"
+#define BUSTYPE_MPSA "MPSA"
+#define BUSTYPE_NUBUS "NUBUS"
+#define BUSTYPE_TC "TC"
+#define BUSTYPE_VME "VME"
+#define BUSTYPE_XPRESS "XPRESS"
+
+struct mpc_config_ioapic
+{
+ unsigned char mpc_type;
+ unsigned char mpc_apicid;
+ unsigned char mpc_apicver;
+ unsigned char mpc_flags;
+#define MPC_APIC_USABLE 0x01
+ unsigned long mpc_apicaddr;
+};
+
+struct mpc_config_intsrc
+{
+ unsigned char mpc_type;
+ unsigned char mpc_irqtype;
+ unsigned short mpc_irqflag;
+ unsigned char mpc_srcbus;
+ unsigned char mpc_srcbusirq;
+ unsigned char mpc_dstapic;
+ unsigned char mpc_dstirq;
+};
+
+enum mp_irq_source_types {
+ mp_INT = 0,
+ mp_NMI = 1,
+ mp_SMI = 2,
+ mp_ExtINT = 3
+};
+
+#define MP_IRQDIR_DEFAULT 0
+#define MP_IRQDIR_HIGH 1
+#define MP_IRQDIR_LOW 3
+
+
+struct mpc_config_lintsrc
+{
+ unsigned char mpc_type;
+ unsigned char mpc_irqtype;
+ unsigned short mpc_irqflag;
+ unsigned char mpc_srcbusid;
+ unsigned char mpc_srcbusirq;
+ unsigned char mpc_destapic;
+#define MP_APIC_ALL 0xFF
+ unsigned char mpc_destapiclint;
+};
+
+struct mp_config_oemtable
+{
+ char oem_signature[4];
+#define MPC_OEM_SIGNATURE "_OEM"
+ unsigned short oem_length; /* Size of table */
+ char oem_rev; /* 0x01 */
+ char oem_checksum;
+ char mpc_oem[8];
+};
+
+struct mpc_config_translation
+{
+ unsigned char mpc_type;
+ unsigned char trans_len;
+ unsigned char trans_type;
+ unsigned char trans_quad;
+ unsigned char trans_global;
+ unsigned char trans_local;
+ unsigned short trans_reserved;
+};
+
+/*
+ * Default configurations
+ *
+ * 1 2 CPU ISA 82489DX
+ * 2 2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
+ * 3 2 CPU EISA 82489DX
+ * 4 2 CPU MCA 82489DX
+ * 5 2 CPU ISA+PCI
+ * 6 2 CPU EISA+PCI
+ * 7 2 CPU MCA+PCI
+ */
+
+#ifdef CONFIG_MULTIQUAD
+#define MAX_IRQ_SOURCES 512
+#else /* !CONFIG_MULTIQUAD */
+#define MAX_IRQ_SOURCES 256
+#endif /* CONFIG_MULTIQUAD */
+
+#define MAX_MP_BUSSES 32
+enum mp_bustype {
+ MP_BUS_ISA = 1,
+ MP_BUS_EISA,
+ MP_BUS_PCI,
+ MP_BUS_MCA
+};
+extern int mp_bus_id_to_type [MAX_MP_BUSSES];
+extern int mp_bus_id_to_pci_bus [MAX_MP_BUSSES];
+
+extern unsigned int boot_cpu_physical_apicid;
+extern unsigned long phys_cpu_present_map;
+extern int smp_found_config;
+extern void find_smp_config (void);
+extern void get_smp_config (void);
+extern int nr_ioapics;
+extern int apic_version [MAX_APICS];
+extern int mp_bus_id_to_type [MAX_MP_BUSSES];
+extern int mp_irq_entries;
+extern struct mpc_config_intsrc mp_irqs [MAX_IRQ_SOURCES];
+extern int mpc_default_type;
+extern int mp_bus_id_to_pci_bus [MAX_MP_BUSSES];
+extern int mp_current_pci_id;
+extern unsigned long mp_lapic_addr;
+extern int pic_mode;
+extern int using_apic_timer;
+
+#endif
+
--- /dev/null
+#ifndef _I386_MSGBUF_H
+#define _I386_MSGBUF_H
+
+/*
+ * The msqid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct msqid64_ds {
+ struct ipc64_perm msg_perm;
+ __kernel_time_t msg_stime; /* last msgsnd time */
+ unsigned long __unused1;
+ __kernel_time_t msg_rtime; /* last msgrcv time */
+ unsigned long __unused2;
+ __kernel_time_t msg_ctime; /* last change time */
+ unsigned long __unused3;
+ unsigned long msg_cbytes; /* current number of bytes on queue */
+ unsigned long msg_qnum; /* number of messages in queue */
+ unsigned long msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+
+#endif /* _I386_MSGBUF_H */
--- /dev/null
+#ifndef __ASM_MSR_H
+#define __ASM_MSR_H
+
+/*
+ * Access to machine-specific registers (available on 586 and better only)
+ * Note: the rd* operations modify the parameters directly (without using
+ * pointer indirection), this allows gcc to optimize better
+ */
+
+#define rdmsr(msr,val1,val2) \
+ __asm__ __volatile__("rdmsr" \
+ : "=a" (val1), "=d" (val2) \
+ : "c" (msr))
+
+#define wrmsr(msr,val1,val2) \
+ __asm__ __volatile__("wrmsr" \
+ : /* no outputs */ \
+ : "c" (msr), "a" (val1), "d" (val2))
+
+#define rdtsc(low,high) \
+ __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))
+
+#define rdtscl(low) \
+ __asm__ __volatile__("rdtsc" : "=a" (low) : : "edx")
+
+#define rdtscll(val) \
+ __asm__ __volatile__("rdtsc" : "=A" (val))
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+#define rdpmc(counter,low,high) \
+ __asm__ __volatile__("rdpmc" \
+ : "=a" (low), "=d" (high) \
+ : "c" (counter))
+
+/* symbolic names for some interesting MSRs */
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR 0
+#define MSR_IA32_P5_MC_TYPE 1
+#define MSR_IA32_PLATFORM_ID 0x17
+#define MSR_IA32_EBL_CR_POWERON 0x2a
+
+#define MSR_IA32_APICBASE 0x1b
+#define MSR_IA32_APICBASE_BSP (1<<8)
+#define MSR_IA32_APICBASE_ENABLE (1<<11)
+#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+
+#define MSR_IA32_UCODE_WRITE 0x79
+#define MSR_IA32_UCODE_REV 0x8b
+
+#define MSR_IA32_PERFCTR0 0xc1
+#define MSR_IA32_PERFCTR1 0xc2
+
+#define MSR_IA32_BBL_CR_CTL 0x119
+
+#define MSR_IA32_MCG_CAP 0x179
+#define MSR_IA32_MCG_STATUS 0x17a
+#define MSR_IA32_MCG_CTL 0x17b
+
+#define MSR_IA32_EVNTSEL0 0x186
+#define MSR_IA32_EVNTSEL1 0x187
+
+#define MSR_IA32_DEBUGCTLMSR 0x1d9
+#define MSR_IA32_LASTBRANCHFROMIP 0x1db
+#define MSR_IA32_LASTBRANCHTOIP 0x1dc
+#define MSR_IA32_LASTINTFROMIP 0x1dd
+#define MSR_IA32_LASTINTTOIP 0x1de
+
+#define MSR_IA32_MC0_CTL 0x400
+#define MSR_IA32_MC0_STATUS 0x401
+#define MSR_IA32_MC0_ADDR 0x402
+#define MSR_IA32_MC0_MISC 0x403
+
+/* AMD Defined MSRs */
+#define MSR_K6_EFER 0xC0000080
+#define MSR_K6_STAR 0xC0000081
+#define MSR_K6_WHCR 0xC0000082
+#define MSR_K6_UWCCR 0xC0000085
+#define MSR_K6_PSOR 0xC0000087
+#define MSR_K6_PFIR 0xC0000088
+
+#define MSR_K7_EVNTSEL0 0xC0010000
+#define MSR_K7_PERFCTR0 0xC0010004
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1 0x107
+#define MSR_IDT_FCR2 0x108
+#define MSR_IDT_FCR3 0x109
+#define MSR_IDT_FCR4 0x10a
+
+#define MSR_IDT_MCR0 0x110
+#define MSR_IDT_MCR1 0x111
+#define MSR_IDT_MCR2 0x112
+#define MSR_IDT_MCR3 0x113
+#define MSR_IDT_MCR4 0x114
+#define MSR_IDT_MCR5 0x115
+#define MSR_IDT_MCR6 0x116
+#define MSR_IDT_MCR7 0x117
+#define MSR_IDT_MCR_CTRL 0x120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR 0x1107
+
+#endif /* __ASM_MSR_H */
--- /dev/null
+/* Generic MTRR (Memory Type Range Register) ioctls.
+
+ Copyright (C) 1997-1999 Richard Gooch
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Library General Public
+ License as published by the Free Software Foundation; either
+ version 2 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Library General Public License for more details.
+
+ You should have received a copy of the GNU Library General Public
+ License along with this library; if not, write to the Free
+ Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ Richard Gooch may be reached by email at rgooch@atnf.csiro.au
+ The postal address is:
+ Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
+*/
+#ifndef _LINUX_MTRR_H
+#define _LINUX_MTRR_H
+
+#include <linux/config.h>
+#include <linux/ioctl.h>
+
+#define MTRR_IOCTL_BASE 'M'
+
+struct mtrr_sentry
+{
+ unsigned long base; /* Base address */
+ unsigned long size; /* Size of region */
+ unsigned int type; /* Type of region */
+};
+
+struct mtrr_gentry
+{
+ unsigned int regnum; /* Register number */
+ unsigned long base; /* Base address */
+ unsigned long size; /* Size of region */
+ unsigned int type; /* Type of region */
+};
+
+/* These are the various ioctls */
+#define MTRRIOC_ADD_ENTRY _IOW(MTRR_IOCTL_BASE, 0, struct mtrr_sentry)
+#define MTRRIOC_SET_ENTRY _IOW(MTRR_IOCTL_BASE, 1, struct mtrr_sentry)
+#define MTRRIOC_DEL_ENTRY _IOW(MTRR_IOCTL_BASE, 2, struct mtrr_sentry)
+#define MTRRIOC_GET_ENTRY _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
+#define MTRRIOC_KILL_ENTRY _IOW(MTRR_IOCTL_BASE, 4, struct mtrr_sentry)
+#define MTRRIOC_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 5, struct mtrr_sentry)
+#define MTRRIOC_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 6, struct mtrr_sentry)
+#define MTRRIOC_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 7, struct mtrr_sentry)
+#define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
+#define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry)
+
+/* These are the region types */
+#define MTRR_TYPE_UNCACHABLE 0
+#define MTRR_TYPE_WRCOMB 1
+/*#define MTRR_TYPE_ 2*/
+/*#define MTRR_TYPE_ 3*/
+#define MTRR_TYPE_WRTHROUGH 4
+#define MTRR_TYPE_WRPROT 5
+#define MTRR_TYPE_WRBACK 6
+#define MTRR_NUM_TYPES 7
+
+#ifdef MTRR_NEED_STRINGS
+static char *mtrr_strings[MTRR_NUM_TYPES] =
+{
+ "uncachable", /* 0 */
+ "write-combining", /* 1 */
+ "?", /* 2 */
+ "?", /* 3 */
+ "write-through", /* 4 */
+ "write-protect", /* 5 */
+ "write-back", /* 6 */
+};
+#endif
+
+#ifdef __KERNEL__
+
+/* The following functions are for use by other drivers */
+# ifdef CONFIG_MTRR
+extern int mtrr_add (unsigned long base, unsigned long size,
+ unsigned int type, char increment);
+extern int mtrr_add_page (unsigned long base, unsigned long size,
+ unsigned int type, char increment);
+extern int mtrr_del (int reg, unsigned long base, unsigned long size);
+extern int mtrr_del_page (int reg, unsigned long base, unsigned long size);
+extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
+# else
+static __inline__ int mtrr_add (unsigned long base, unsigned long size,
+ unsigned int type, char increment)
+{
+ return -ENODEV;
+}
+static __inline__ int mtrr_add_page (unsigned long base, unsigned long size,
+ unsigned int type, char increment)
+{
+ return -ENODEV;
+}
+static __inline__ int mtrr_del (int reg, unsigned long base,
+ unsigned long size)
+{
+ return -ENODEV;
+}
+static __inline__ int mtrr_del_page (int reg, unsigned long base,
+ unsigned long size)
+{
+ return -ENODEV;
+}
+
+static __inline__ void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) {;}
+
+# endif
+
+/* The following functions are for initialisation: don't use them! */
+extern int mtrr_init (void);
+# if defined(CONFIG_SMP) && defined(CONFIG_MTRR)
+extern void mtrr_init_boot_cpu (void);
+extern void mtrr_init_secondary_cpu (void);
+# endif
+
+#endif
+
+#endif /* _LINUX_MTRR_H */
--- /dev/null
+/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $
+ * linux/include/asm-i386/namei.h
+ *
+ * Included from linux/fs/namei.c
+ */
+
+#ifndef __I386_NAMEI_H
+#define __I386_NAMEI_H
+
+/* This dummy routine maybe changed to something useful
+ * for /usr/gnemul/ emulation stuff.
+ * Look at asm-sparc/namei.h for details.
+ */
+
+#define __emul_prefix() NULL
+
+#endif /* __I386_NAMEI_H */
--- /dev/null
+#ifndef _I386_PAGE_H
+#define _I386_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1UL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+#define clear_page(page) mmx_clear_page((void *)(page))
+#define copy_page(to,from) mmx_copy_page(to,from)
+
+#else
+
+/*
+ * On older X86 processors its not a win to use MMX here it seems.
+ * Maybe the K6-III ?
+ */
+
+#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE)
+
+#endif
+
+#define clear_user_page(page, vaddr) clear_page(page)
+#define copy_user_page(to, from, vaddr) copy_page(to, from)
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+extern unsigned long *phys_to_machine_mapping;
+#define pfn_to_mfn(_pfn) (phys_to_machine_mapping[(_pfn)])
+#define mfn_to_pfn(_mfn) (machine_to_phys_mapping[(_mfn)])
+static inline unsigned long phys_to_machine(unsigned long phys)
+{
+ unsigned long machine = pfn_to_mfn(phys >> PAGE_SHIFT);
+ machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK);
+ return machine;
+}
+static inline unsigned long machine_to_phys(unsigned long machine)
+{
+ unsigned long phys = mfn_to_pfn(machine >> PAGE_SHIFT);
+ phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK);
+ return phys;
+}
+
+/*
+ * These are used to make use of C type-checking..
+ */
+#if CONFIG_X86_PAE
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long long pmd; } pmd_t;
+typedef struct { unsigned long long pgd; } pgd_t;
+#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
+#else
+typedef struct { unsigned long pte_low; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pgd; } pgd_t;
+static inline unsigned long pte_val(pte_t x)
+{
+ unsigned long ret = x.pte_low;
+ if ( (ret & 1) ) ret = machine_to_phys(ret);
+ return ret;
+}
+#endif
+#define PTE_MASK PAGE_MASK
+
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+static inline unsigned long pmd_val(pmd_t x)
+{
+ unsigned long ret = x.pmd;
+ if ( (ret & 1) ) ret = machine_to_phys(ret);
+ return ret;
+}
+#define pgd_val(x) ({ BUG(); (unsigned long)0; })
+#define pgprot_val(x) ((x).pgprot)
+
+static inline pte_t __pte(unsigned long x)
+{
+ if ( (x & 1) ) x = phys_to_machine(x);
+ return ((pte_t) { (x) });
+}
+static inline pmd_t __pmd(unsigned long x)
+{
+ if ( (x & 1) ) x = phys_to_machine(x);
+ return ((pmd_t) { (x) });
+}
+#define __pgd(x) ({ BUG(); (pgprot_t) { 0 }; })
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#endif /* !__ASSEMBLY__ */
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/*
+ * This handles the memory map.. We could make this a config
+ * option, but too many people screw it up, and too few need
+ * it.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB.
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+
+#define __PAGE_OFFSET (0xC0000000)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Tell the user there is some problem. Beep too, so we can
+ * see^H^H^Hhear bugs in early bootup as well!
+ */
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+extern void do_BUG(const char *file, int line);
+#define BUG() do { \
+ do_BUG(__FILE__, __LINE__); \
+ __asm__ __volatile__("ud2"); \
+} while (0)
+#else
+#define BUG() __asm__ __volatile__(".byte 0x0f,0x0b")
+#endif
+
+#define PAGE_BUG(page) do { \
+ BUG(); \
+} while (0)
+
+/* Pure 2^n version of get_order */
+static __inline__ int get_order(unsigned long size)
+{
+ int order;
+
+ size = (size-1) >> (PAGE_SHIFT-1);
+ order = -1;
+ do {
+ size >>= 1;
+ order++;
+ } while (size);
+ return order;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET)
+#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET)
+#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
+#define virt_to_page(kaddr) (mem_map + (__pa(kaddr) >> PAGE_SHIFT))
+#define VALID_PAGE(page) ((page - mem_map) < max_mapnr)
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_PAGE_H */
--- /dev/null
+#ifndef _ASMi386_PARAM_H
+#define _ASMi386_PARAM_H
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE 4096
+
+#ifndef NGROUPS
+#define NGROUPS 32
+#endif
+
+#ifndef NOGROUP
+#define NOGROUP (-1)
+#endif
+
+#define MAXHOSTNAMELEN 64 /* max length of hostname */
+
+#ifdef __KERNEL__
+# define CLOCKS_PER_SEC 100 /* frequency at which times() counts */
+#endif
+
+#endif
--- /dev/null
+/*
+ * parport.h: ia32-specific parport initialisation
+ *
+ * Copyright (C) 1999, 2000 Tim Waugh <tim@cyberelk.demon.co.uk>
+ *
+ * This file should only be included by drivers/parport/parport_pc.c.
+ */
+
+#ifndef _ASM_I386_PARPORT_H
+#define _ASM_I386_PARPORT_H 1
+
+static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
+static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
+{
+ return parport_pc_find_isa_ports (autoirq, autodma);
+}
+
+#endif /* !(_ASM_I386_PARPORT_H) */
--- /dev/null
+#ifndef _I386_PGALLOC_H
+#define _I386_PGALLOC_H
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/hypervisor.h>
+#include <linux/threads.h>
+
+/*
+ * Quick lists are aligned so that least significant bits of array pointer
+ * are all zero when list is empty, and all one when list is full.
+ */
+#define QUICKLIST_ENTRIES 256
+#define QUICKLIST_EMPTY(_l) !((unsigned long)(_l) & ((QUICKLIST_ENTRIES*4)-1))
+#define QUICKLIST_FULL(_l) QUICKLIST_EMPTY((_l)+1)
+#define pgd_quicklist (current_cpu_data.pgd_quick)
+#define pmd_quicklist (current_cpu_data.pmd_quick)
+#define pte_quicklist (current_cpu_data.pte_quick)
+#define pgtable_cache_size (current_cpu_data.pgtable_cache_sz)
+
+#define pmd_populate(mm, pmd, pte) \
+ do { \
+ set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \
+ XENO_flush_page_update_queue(); \
+ } while ( 0 )
+
+static __inline__ pgd_t *get_pgd_slow(void)
+{
+ pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+
+ if (pgd) {
+ memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ kpgd = pgd_offset_k((unsigned long)pgd);
+ kpmd = pmd_offset(kpgd, (unsigned long)pgd);
+ kpte = pte_offset(kpmd, (unsigned long)pgd);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)&~_PAGE_RW);
+ queue_pgd_pin(__pa(pgd));
+ }
+
+ return pgd;
+}
+
+static __inline__ void free_pgd_slow(pgd_t *pgd)
+{
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+ queue_pgd_unpin(__pa(pgd));
+ kpgd = pgd_offset_k((unsigned long)pgd);
+ kpmd = pmd_offset(kpgd, (unsigned long)pgd);
+ kpte = pte_offset(kpmd, (unsigned long)pgd);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)|_PAGE_RW);
+ free_page((unsigned long)pgd);
+}
+
+static __inline__ pgd_t *get_pgd_fast(void)
+{
+ unsigned long ret;
+
+ if ( !QUICKLIST_EMPTY(pgd_quicklist) ) {
+ ret = *(--pgd_quicklist);
+ pgtable_cache_size--;
+ } else
+ ret = (unsigned long)get_pgd_slow();
+ return (pgd_t *)ret;
+}
+
+static __inline__ void free_pgd_fast(pgd_t *pgd)
+{
+ if ( !QUICKLIST_FULL(pgd_quicklist) ) {
+ *(pgd_quicklist++) = (unsigned long)pgd;
+ pgtable_cache_size++;
+ } else
+ free_pgd_slow(pgd);
+}
+
+static inline pte_t *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ pte_t *pte;
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+
+ pte = (pte_t *) __get_free_page(GFP_KERNEL);
+ if (pte)
+ {
+ clear_page(pte);
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)&~_PAGE_RW);
+ queue_pte_pin(__pa(pte));
+ }
+ return pte;
+}
+
+static __inline__ void pte_free_slow(pte_t *pte)
+{
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+ queue_pte_unpin(__pa(pte));
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)|_PAGE_RW);
+ free_page((unsigned long)pte);
+}
+
+static inline pte_t *pte_alloc_one_fast(struct mm_struct *mm, unsigned long address)
+{
+ unsigned long ret = 0;
+ if ( !QUICKLIST_EMPTY(pte_quicklist) ) {
+ ret = *(--pte_quicklist);
+ pgtable_cache_size--;
+ }
+ return (pte_t *)ret;
+}
+
+static __inline__ void pte_free_fast(pte_t *pte)
+{
+ if ( !QUICKLIST_FULL(pte_quicklist) ) {
+ *(pte_quicklist++) = (unsigned long)pte;
+ pgtable_cache_size++;
+ } else
+ pte_free_slow(pte);
+}
+
+#define pte_free(pte) pte_free_fast(pte)
+#define pgd_alloc(mm) get_pgd_fast()
+#define pgd_free(pgd) free_pgd_fast(pgd)
+
+#define pmd_alloc_one_fast(mm, addr) ({ BUG(); ((pmd_t *)1); })
+#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
+#define pmd_free_slow(x) do { } while (0)
+#define pmd_free_fast(x) do { } while (0)
+#define pmd_free(x) do { } while (0)
+#define pgd_populate(mm, pmd, pte) BUG()
+
+extern int do_check_pgt_cache(int, int);
+
+/*
+ * - flush_tlb() flushes the current mm struct TLBs
+ * - flush_tlb_all() flushes all processes TLBs
+ * - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ * - flush_tlb_page(vma, vmaddr) flushes one page
+ * - flush_tlb_range(mm, start, end) flushes a range of pages
+ * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ */
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ if ( mm == current->active_mm ) queue_tlb_flush();
+ XENO_flush_page_update_queue();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ if ( vma->vm_mm == current->active_mm ) queue_invlpg(addr);
+ XENO_flush_page_update_queue();
+}
+
+static inline void flush_tlb_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ if ( mm == current->active_mm ) queue_tlb_flush();
+ XENO_flush_page_update_queue();
+}
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ /* i386 does not keep any page table caches in TLB */
+ XENO_flush_page_update_queue();
+}
+
+#endif /* _I386_PGALLOC_H */
--- /dev/null
+#ifndef _I386_PGTABLE_2LEVEL_H
+#define _I386_PGTABLE_2LEVEL_H
+
+/*
+ * traditional i386 two-level paging structure:
+ */
+
+#define PGDIR_SHIFT 22
+#define PTRS_PER_PGD 1024
+
+/*
+ * the i386 is two-level, so we don't really have any
+ * PMD directory physically.
+ */
+#define PMD_SHIFT 22
+#define PTRS_PER_PMD 1
+
+#define PTRS_PER_PTE 1024
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pgd is never bad, and a pmd always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+#define pgd_clear(xp) do { } while (0)
+
+#define set_pte(pteptr, pteval) queue_l1_entry_update(__pa(pteptr), (pteval).pte_low)
+#define set_pmd(pmdptr, pmdval) queue_l2_entry_update(__pa(pmdptr), (pmdval).pmd)
+#define set_pgd(pgdptr, pgdval) ((void)0)
+
+#define pgd_page(pgd) \
+((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
+
+static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
+{
+ return (pmd_t *) dir;
+}
+
+/*
+ * A note on implementation of this atomic 'get-and-clear' operation.
+ * This is actually very simple because XenoLinux can only run on a single
+ * processor. Therefore, we cannot race other processors setting the 'accessed'
+ * or 'dirty' bits on a page-table entry.
+ * Even if pages are shared between domains, that is not a problem because
+ * each domain will have separate page tables, with their own versions of
+ * accessed & dirty state.
+ */
+static inline pte_t ptep_get_and_clear(pte_t *xp)
+{
+ pte_t pte = *xp;
+ queue_l1_entry_update(__pa(xp), 0);
+ return pte;
+}
+
+#define pte_same(a, b) ((a).pte_low == (b).pte_low)
+#define pte_page(x) (mem_map+((unsigned long)((pte_val(x) >> PAGE_SHIFT))))
+#define pte_none(x) (!(x).pte_low)
+#define __mk_pte(page_nr,pgprot) __pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+
+#endif /* _I386_PGTABLE_2LEVEL_H */
--- /dev/null
+#ifndef _I386_PGTABLE_3LEVEL_H
+#define _I386_PGTABLE_3LEVEL_H
+
+#error "PAE unsupported"
+
+/*
+ * Intel Physical Address Extension (PAE) Mode - three-level page
+ * tables on PPro+ CPUs.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT 30
+#define PTRS_PER_PGD 4
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT 21
+#define PTRS_PER_PMD 512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE 512
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
+
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+
+/* Rules for using set_pte: the pte being assigned *must* be
+ * either not present or in a state where the hardware will
+ * not attempt to update the pte. In places where this is
+ * not possible, use pte_get_and_clear to obtain the old pte
+ * value and then use set_pte to update it. -ben
+ */
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+ ptep->pte_high = pte.pte_high;
+ smp_wmb();
+ ptep->pte_low = pte.pte_low;
+}
+#define set_pmd(pmdptr,pmdval) \
+ set_64bit((unsigned long long *)(pmdptr),pmd_val(pmdval))
+#define set_pgd(pgdptr,pgdval) \
+ set_64bit((unsigned long long *)(pgdptr),pgd_val(pgdval))
+
+/*
+ * Pentium-II erratum A13: in PAE mode we explicitly have to flush
+ * the TLB via cr3 if the top-level pgd is changed...
+ * We do not let the generic code free and clear pgd entries due to
+ * this erratum.
+ */
+static inline void pgd_clear (pgd_t * pgd) { }
+
+#define pgd_page(pgd) \
+((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(dir, address) ((pmd_t *) pgd_page(*(dir)) + \
+ __pmd_offset(address))
+
+static inline pte_t ptep_get_and_clear(pte_t *ptep)
+{
+ pte_t res;
+
+ /* xchg acts as a barrier before the setting of the high bits */
+ res.pte_low = xchg(&ptep->pte_low, 0);
+ res.pte_high = ptep->pte_high;
+ ptep->pte_high = 0;
+
+ return res;
+}
+
+static inline int pte_same(pte_t a, pte_t b)
+{
+ return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
+}
+
+#define pte_page(x) (mem_map+(((x).pte_low >> PAGE_SHIFT) | ((x).pte_high << (32 - PAGE_SHIFT))))
+#define pte_none(x) (!(x).pte_low && !(x).pte_high)
+
+static inline pte_t __mk_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+ pte_t pte;
+
+ pte.pte_high = page_nr >> (32 - PAGE_SHIFT);
+ pte.pte_low = (page_nr << PAGE_SHIFT) | pgprot_val(pgprot);
+ return pte;
+}
+
+#endif /* _I386_PGTABLE_3LEVEL_H */
--- /dev/null
+#ifndef _I386_PGTABLE_H
+#define _I386_PGTABLE_H
+
+#include <linux/config.h>
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/hypervisor.h>
+#include <linux/threads.h>
+#include <asm/fixmap.h>
+
+#ifndef _I386_BITOPS_H
+#include <asm/bitops.h>
+#endif
+
+#define swapper_pg_dir 0
+extern void paging_init(void);
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all() do { } while (0)
+#define flush_cache_mm(mm) do { } while (0)
+#define flush_cache_range(mm, start, end) do { } while (0)
+#define flush_cache_page(vma, vmaddr) do { } while (0)
+#define flush_page_to_ram(page) do { } while (0)
+#define flush_dcache_page(page) do { } while (0)
+#define flush_icache_range(start, end) do { } while (0)
+#define flush_icache_page(vma,pg) do { } while (0)
+
+extern unsigned long pgkern_mask;
+
+#define __flush_tlb() ({ queue_tlb_flush(); XENO_flush_page_update_queue(); })
+#define __flush_tlb_global() __flush_tlb()
+#define __flush_tlb_all() __flush_tlb_global()
+#define __flush_tlb_one(addr) ({ queue_invlpg(addr); XENO_flush_page_update_queue(); })
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[1024];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifndef __ASSEMBLY__
+#if CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+
+/*
+ * Need to initialise the X86 PAE caches
+ */
+extern void pgtable_cache_init(void);
+
+#else
+# include <asm/pgtable-2level.h>
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init() do { } while (0)
+
+#endif
+#endif
+
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_PGD_NR 0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define TWOLEVEL_PGDIR_SHIFT 22
+#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
+#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
+
+
+#ifndef __ASSEMBLY__
+/* 4MB is just a nice "safety zone". Also, we align to a fresh pde. */
+#define VMALLOC_OFFSET (4*1024*1024)
+#define VMALLOC_START (((unsigned long) high_memory + 2*VMALLOC_OFFSET-1) & \
+ ~(VMALLOC_OFFSET-1))
+#define VMALLOC_VMADDR(x) ((unsigned long)(x))
+#define VMALLOC_END (FIXADDR_START - 2*PAGE_SIZE)
+
+#define _PAGE_BIT_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+
+#define _PAGE_PRESENT 0x001
+#define _PAGE_RW 0x002
+#define _PAGE_USER 0x004
+#define _PAGE_PWT 0x008
+#define _PAGE_PCD 0x010
+#define _PAGE_ACCESSED 0x020
+#define _PAGE_DIRTY 0x040
+#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
+
+#define _PAGE_PROTNONE 0x080 /* If not present */
+
+#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+
+#define __PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_NOCACHE \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_RO \
+ (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+#if 0
+#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
+#else
+#define MAKE_GLOBAL(x) __pgprot(x)
+#endif
+
+#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+
+/*
+ * The i386 can't do page protection for execute, and considers that
+ * the same are read. Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY
+#define __P101 PAGE_READONLY
+#define __P110 PAGE_COPY
+#define __P111 PAGE_COPY
+
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY
+#define __S101 PAGE_READONLY
+#define __S110 PAGE_SHARED
+#define __S111 PAGE_SHARED
+
+#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+#define pte_clear(xp) queue_l1_entry_update(__pa(xp), 0)
+
+#define pmd_none(x) (!(x).pmd)
+#define pmd_present(x) ((x).pmd & _PAGE_PRESENT)
+#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
+#define pmd_bad(x) (((x).pmd & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+
+/*
+ * Permanent address of a page. Obviously must never be
+ * called on a highmem page.
+ */
+#define page_address(page) ((page)->virtual)
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
+static inline int pte_exec(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
+static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; }
+
+static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; }
+static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; }
+
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ int ret = pteval & _PAGE_DIRTY;
+ if ( ret ) queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_DIRTY);
+ return ret;
+}
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ int ret = pteval & _PAGE_ACCESSED;
+ if ( ret ) queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_ACCESSED);
+ return ret;
+}
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ if ( (pteval & _PAGE_RW) )
+ queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_RW);
+}
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ if ( !(pteval & _PAGE_DIRTY) )
+ queue_l1_entry_update(__pa(ptep), pteval | _PAGE_DIRTY);
+}
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot) __mk_pte((page) - mem_map, (pgprot))
+
+/* This takes a physical page address that is used by the remapping functions */
+#define mk_pte_phys(physpage, pgprot) __mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ pte.pte_low &= _PAGE_CHG_MASK;
+ pte.pte_low |= pgprot_val(newprot);
+ return pte;
+}
+
+#define page_pte(page) page_pte_prot(page, __pgprot(0))
+
+#define pmd_page(pmd) \
+((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/* to find an entry in a page-table-directory. */
+#define pgd_index(address) ((address >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+
+#define __pgd_offset(address) pgd_index(address)
+
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+#define __pmd_offset(address) \
+ (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/* Find an entry in the third-level page table.. */
+#define __pte_offset(address) \
+ ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset(dir, address) ((pte_t *) pmd_page(*(dir)) + \
+ __pte_offset(address))
+
+/*
+ * The i386 doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ */
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+
+/* Encode and de-code a swap entry */
+#define SWP_TYPE(x) (((x).val >> 1) & 0x3f)
+#define SWP_OFFSET(x) ((x).val >> 8)
+#define SWP_ENTRY(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#define pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low })
+#define swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#endif /* !__ASSEMBLY__ */
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+#define PageSkip(page) (0)
+#define kern_addr_valid(addr) (1)
+
+#define io_remap_page_range remap_page_range
+
+#endif /* _I386_PGTABLE_H */
--- /dev/null
+#ifndef __i386_POLL_H
+#define __i386_POLL_H
+
+/* These are specified by iBCS2 */
+#define POLLIN 0x0001
+#define POLLPRI 0x0002
+#define POLLOUT 0x0004
+#define POLLERR 0x0008
+#define POLLHUP 0x0010
+#define POLLNVAL 0x0020
+
+/* The rest seem to be more-or-less nonstandard. Check them! */
+#define POLLRDNORM 0x0040
+#define POLLRDBAND 0x0080
+#define POLLWRNORM 0x0100
+#define POLLWRBAND 0x0200
+#define POLLMSG 0x0400
+
+struct pollfd {
+ int fd;
+ short events;
+ short revents;
+};
+
+#endif
--- /dev/null
+#ifndef __ARCH_I386_POSIX_TYPES_H
+#define __ARCH_I386_POSIX_TYPES_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc. Also, we cannot
+ * assume GCC is being used.
+ */
+
+typedef unsigned short __kernel_dev_t;
+typedef unsigned long __kernel_ino_t;
+typedef unsigned short __kernel_mode_t;
+typedef unsigned short __kernel_nlink_t;
+typedef long __kernel_off_t;
+typedef int __kernel_pid_t;
+typedef unsigned short __kernel_ipc_pid_t;
+typedef unsigned short __kernel_uid_t;
+typedef unsigned short __kernel_gid_t;
+typedef unsigned int __kernel_size_t;
+typedef int __kernel_ssize_t;
+typedef int __kernel_ptrdiff_t;
+typedef long __kernel_time_t;
+typedef long __kernel_suseconds_t;
+typedef long __kernel_clock_t;
+typedef int __kernel_daddr_t;
+typedef char * __kernel_caddr_t;
+typedef unsigned short __kernel_uid16_t;
+typedef unsigned short __kernel_gid16_t;
+typedef unsigned int __kernel_uid32_t;
+typedef unsigned int __kernel_gid32_t;
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+
+#ifdef __GNUC__
+typedef long long __kernel_loff_t;
+#endif
+
+typedef struct {
+#if defined(__KERNEL__) || defined(__USE_ALL)
+ int val[2];
+#else /* !defined(__KERNEL__) && !defined(__USE_ALL) */
+ int __val[2];
+#endif /* !defined(__KERNEL__) && !defined(__USE_ALL) */
+} __kernel_fsid_t;
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#undef __FD_SET
+#define __FD_SET(fd,fdsetp) \
+ __asm__ __volatile__("btsl %1,%0": \
+ "=m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
+
+#undef __FD_CLR
+#define __FD_CLR(fd,fdsetp) \
+ __asm__ __volatile__("btrl %1,%0": \
+ "=m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
+
+#undef __FD_ISSET
+#define __FD_ISSET(fd,fdsetp) (__extension__ ({ \
+ unsigned char __result; \
+ __asm__ __volatile__("btl %1,%2 ; setb %0" \
+ :"=q" (__result) :"r" ((int) (fd)), \
+ "m" (*(__kernel_fd_set *) (fdsetp))); \
+ __result; }))
+
+#undef __FD_ZERO
+#define __FD_ZERO(fdsetp) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__("cld ; rep ; stosl" \
+ :"=m" (*(__kernel_fd_set *) (fdsetp)), \
+ "=&c" (__d0), "=&D" (__d1) \
+ :"a" (0), "1" (__FDSET_LONGS), \
+ "2" ((__kernel_fd_set *) (fdsetp)) : "memory"); \
+} while (0)
+
+#endif /* defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) */
+
+#endif
--- /dev/null
+/*
+ * include/asm-i386/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_I386_PROCESSOR_H
+#define __ASM_I386_PROCESSOR_H
+
+#include <asm/math_emu.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <linux/cache.h>
+#include <linux/config.h>
+#include <linux/threads.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
+
+/*
+ * CPU type and hardware bug flags. Kept separately for each CPU.
+ * Members of this structure are referenced in head.S, so think twice
+ * before touching them. [mj]
+ */
+
+struct cpuinfo_x86 {
+ __u8 x86; /* CPU family */
+ __u8 x86_vendor; /* CPU vendor */
+ __u8 x86_model;
+ __u8 x86_mask;
+ char wp_works_ok; /* It doesn't on 386's */
+ char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */
+ char hard_math;
+ char rfu;
+ int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */
+ __u32 x86_capability[NCAPINTS];
+ char x86_vendor_id[16];
+ char x86_model_id[64];
+ int x86_cache_size; /* in KB - valid for CPUS which support this
+ call */
+ int fdiv_bug;
+ int f00f_bug;
+ int coma_bug;
+ unsigned long loops_per_jiffy;
+ unsigned long *pgd_quick;
+ unsigned long *pmd_quick;
+ unsigned long *pte_quick;
+ unsigned long pgtable_cache_sz;
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_RISE 6
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_UNKNOWN 0xff
+
+/*
+ * capabilities of CPUs
+ */
+
+extern struct cpuinfo_x86 boot_cpu_data;
+extern struct tss_struct init_tss[NR_CPUS];
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+#define cpu_has_pge (test_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability))
+#define cpu_has_pse (test_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability))
+#define cpu_has_pae (test_bit(X86_FEATURE_PAE, boot_cpu_data.x86_capability))
+#define cpu_has_tsc (test_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability))
+#define cpu_has_de (test_bit(X86_FEATURE_DE, boot_cpu_data.x86_capability))
+#define cpu_has_vme (test_bit(X86_FEATURE_VME, boot_cpu_data.x86_capability))
+#define cpu_has_fxsr (test_bit(X86_FEATURE_FXSR, boot_cpu_data.x86_capability))
+#define cpu_has_xmm (test_bit(X86_FEATURE_XMM, boot_cpu_data.x86_capability))
+#define cpu_has_fpu (test_bit(X86_FEATURE_FPU, boot_cpu_data.x86_capability))
+#define cpu_has_apic (test_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability))
+
+extern char ignore_irq13;
+
+extern void identify_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT 0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */
+
+/*
+ * Generic CPUID function
+ */
+static inline void cpuid(int op, int *eax, int *ebx, int *ecx, int *edx)
+{
+ __asm__("cpuid"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (op));
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+ unsigned int eax;
+
+ __asm__("cpuid"
+ : "=a" (eax)
+ : "0" (op)
+ : "bx", "cx", "dx");
+ return eax;
+}
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+ unsigned int eax, ebx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=b" (ebx)
+ : "0" (op)
+ : "cx", "dx" );
+ return ebx;
+}
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+ unsigned int eax, ecx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=c" (ecx)
+ : "0" (op)
+ : "bx", "dx" );
+ return ecx;
+}
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+ unsigned int eax, edx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=d" (edx)
+ : "0" (op)
+ : "bx", "cx");
+ return edx;
+}
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME 0x0001 /* enable vm86 extensions */
+#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE 0x0008 /* enable debugging extensions */
+#define X86_CR4_PSE 0x0010 /* enable page size extensions */
+#define X86_CR4_PAE 0x0020 /* enable physical address extensions */
+#define X86_CR4_MCE 0x0040 /* Machine check enable */
+#define X86_CR4_PGE 0x0080 /* enable global pages */
+#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */
+#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */
+
+extern unsigned long mmu_cr4_features;
+
+#include <asm/hypervisor.h>
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+ HYPERVISOR_console_write("No set_in_cr4", 13);
+}
+
+static inline void clear_in_cr4 (unsigned long mask)
+{
+ HYPERVISOR_console_write("No clear_in_cr4", 15);
+}
+
+/*
+ * Cyrix CPU configuration register indexes
+ */
+#define CX86_CCR0 0xc0
+#define CX86_CCR1 0xc1
+#define CX86_CCR2 0xc2
+#define CX86_CCR3 0xc3
+#define CX86_CCR4 0xe8
+#define CX86_CCR5 0xe9
+#define CX86_CCR6 0xea
+#define CX86_CCR7 0xeb
+#define CX86_DIR0 0xfe
+#define CX86_DIR1 0xff
+#define CX86_ARR_BASE 0xc4
+#define CX86_RCR_BASE 0xdc
+
+/*
+ * Cyrix CPU indexed register access macros
+ */
+
+#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86(reg, data) do { \
+ outb((reg), 0x22); \
+ outb((data), 0x23); \
+} while (0)
+
+/*
+ * Bus types (default is ISA, but people can check others with these..)
+ */
+#ifdef CONFIG_EISA
+extern int EISA_bus;
+#else
+#define EISA_bus (0)
+#endif
+extern int MCA_bus;
+
+/* from system description table in BIOS. Mostly for MCA use, but
+others may find it useful. */
+extern unsigned int machine_id;
+extern unsigned int machine_submodel_id;
+extern unsigned int BIOS_revision;
+extern unsigned int mca_pentium_flag;
+
+/*
+ * User space process size: 3GB (default).
+ */
+#define TASK_SIZE (PAGE_OFFSET)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE (TASK_SIZE / 3)
+
+/*
+ * Size of io_bitmap in longwords: 32 is ports 0-0x3ff.
+ */
+#define IO_BITMAP_SIZE 32
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+
+struct i387_fsave_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ long status; /* software status information */
+};
+
+struct i387_fxsave_struct {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long mxcsr;
+ long reserved;
+ long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+ long padding[56];
+} __attribute__ ((aligned (16)));
+
+struct i387_soft_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ unsigned char ftop, changed, lookahead, no_update, rm, alimit;
+ struct info *info;
+ unsigned long entry_eip;
+};
+
+union i387_union {
+ struct i387_fsave_struct fsave;
+ struct i387_fxsave_struct fxsave;
+ struct i387_soft_struct soft;
+};
+
+typedef struct {
+ unsigned long seg;
+} mm_segment_t;
+
+struct tss_struct {
+ unsigned short back_link,__blh;
+ unsigned long esp0;
+ unsigned short ss0,__ss0h;
+ unsigned long esp1;
+ unsigned short ss1,__ss1h;
+ unsigned long esp2;
+ unsigned short ss2,__ss2h;
+ unsigned long __cr3;
+ unsigned long eip;
+ unsigned long eflags;
+ unsigned long eax,ecx,edx,ebx;
+ unsigned long esp;
+ unsigned long ebp;
+ unsigned long esi;
+ unsigned long edi;
+ unsigned short es, __esh;
+ unsigned short cs, __csh;
+ unsigned short ss, __ssh;
+ unsigned short ds, __dsh;
+ unsigned short fs, __fsh;
+ unsigned short gs, __gsh;
+ unsigned short ldt, __ldth;
+ unsigned short trace, bitmap;
+ unsigned long io_bitmap[IO_BITMAP_SIZE+1];
+ /*
+ * pads the TSS to be cacheline-aligned (size is 0x100)
+ */
+ unsigned long __cacheline_filler[5];
+};
+
+struct thread_struct {
+ unsigned long esp0;
+ unsigned long eip;
+ unsigned long esp;
+ unsigned long fs;
+ unsigned long gs;
+/* Hardware debugging registers */
+ unsigned long debugreg[8]; /* %%db0-7 debug registers */
+/* fault info */
+ unsigned long cr2, trap_no, error_code;
+/* floating point info */
+ union i387_union i387;
+/* virtual 86 mode info */
+ struct vm86_struct * vm86_info;
+ unsigned long screen_bitmap;
+ unsigned long v86flags, v86mask, v86mode, saved_esp0;
+};
+
+#define INIT_THREAD { 0 }
+
+#define INIT_TSS { \
+ 0,0, /* back_link, __blh */ \
+ sizeof(init_stack) + (long) &init_stack, /* esp0 */ \
+ __KERNEL_DS, 0, /* ss0 */ \
+ 0,0,0,0,0,0, /* stack1, stack2 */ \
+ 0, /* cr3 */ \
+ 0,0, /* eip,eflags */ \
+ 0,0,0,0, /* eax,ecx,edx,ebx */ \
+ 0,0,0,0, /* esp,ebp,esi,edi */ \
+ 0,0,0,0,0,0, /* es,cs,ss */ \
+ 0,0,0,0,0,0, /* ds,fs,gs */ \
+ __LDT(0),0, /* ldt */ \
+ 0, INVALID_IO_BITMAP_OFFSET, /* tace, bitmap */ \
+ {~0, } /* ioperm */ \
+}
+
+#define start_thread(regs, new_eip, new_esp) do { \
+ __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \
+ set_fs(USER_DS); \
+ regs->xds = __USER_DS; \
+ regs->xes = __USER_DS; \
+ regs->xss = __USER_DS; \
+ regs->xcs = __USER_CS; \
+ regs->eip = new_eip; \
+ regs->esp = new_esp; \
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+/* Copy and release all segment info associated with a VM */
+extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
+extern void release_segments(struct mm_struct * mm);
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+static inline unsigned long thread_saved_pc(struct thread_struct *t)
+{
+ return ((unsigned long *)t->esp)[3];
+}
+
+unsigned long get_wchan(struct task_struct *p);
+#define KSTK_EIP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1019])
+#define KSTK_ESP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1022])
+
+#define THREAD_SIZE (2*PAGE_SIZE)
+#define alloc_task_struct() ((struct task_struct *) __get_free_pages(GFP_KERNEL,1))
+#define free_task_struct(p) free_pages((unsigned long) (p), 1)
+#define get_task_struct(tsk) atomic_inc(&virt_to_page(tsk)->count)
+
+#define init_task (init_task_union.task)
+#define init_stack (init_task_union.stack)
+
+struct microcode {
+ unsigned int hdrver;
+ unsigned int rev;
+ unsigned int date;
+ unsigned int sig;
+ unsigned int cksum;
+ unsigned int ldrver;
+ unsigned int pf;
+ unsigned int reserved[5];
+ unsigned int bits[500];
+};
+
+/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
+#define MICROCODE_IOCFREE _IO('6',0)
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+ __asm__ __volatile__("rep;nop");
+}
+
+#define cpu_relax() rep_nop()
+
+/* Prefetch instructions for Pentium III and AMD Athlon */
+#ifdef CONFIG_MPENTIUMIII
+
+#define ARCH_HAS_PREFETCH
+extern inline void prefetch(const void *x)
+{
+ __asm__ __volatile__ ("prefetchnta (%0)" : : "r"(x));
+}
+
+#elif CONFIG_X86_USE_3DNOW
+
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+extern inline void prefetch(const void *x)
+{
+ __asm__ __volatile__ ("prefetch (%0)" : : "r"(x));
+}
+
+extern inline void prefetchw(const void *x)
+{
+ __asm__ __volatile__ ("prefetchw (%0)" : : "r"(x));
+}
+#define spin_lock_prefetch(x) prefetchw(x)
+
+#endif
+
+#define TF_MASK 0x100
+
+#endif /* __ASM_I386_PROCESSOR_H */
--- /dev/null
+#ifndef _I386_PTRACE_H
+#define _I386_PTRACE_H
+
+#define EBX 0
+#define ECX 1
+#define EDX 2
+#define ESI 3
+#define EDI 4
+#define EBP 5
+#define EAX 6
+#define DS 7
+#define ES 8
+#define FS 9
+#define GS 10
+#define ORIG_EAX 11
+#define EIP 12
+#define CS 13
+#define EFL 14
+#define UESP 15
+#define SS 16
+#define FRAME_SIZE 17
+
+/* this struct defines the way the registers are stored on the
+ stack during a system call. */
+
+struct pt_regs {
+ long ebx;
+ long ecx;
+ long edx;
+ long esi;
+ long edi;
+ long ebp;
+ long eax;
+ int xds;
+ int xes;
+ long orig_eax;
+ long eip;
+ int xcs;
+ long eflags;
+ long esp;
+ int xss;
+};
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS 12
+#define PTRACE_SETREGS 13
+#define PTRACE_GETFPREGS 14
+#define PTRACE_SETFPREGS 15
+#define PTRACE_GETFPXREGS 18
+#define PTRACE_SETFPXREGS 19
+
+#define PTRACE_SETOPTIONS 21
+
+/* options set using PTRACE_SETOPTIONS */
+#define PTRACE_O_TRACESYSGOOD 0x00000001
+
+enum EFLAGS {
+ EF_CF = 0x00000001,
+ EF_PF = 0x00000004,
+ EF_AF = 0x00000010,
+ EF_ZF = 0x00000040,
+ EF_SF = 0x00000080,
+ EF_TF = 0x00000100,
+ EF_IE = 0x00000200,
+ EF_DF = 0x00000400,
+ EF_OF = 0x00000800,
+ EF_IOPL = 0x00003000,
+ EF_IOPL_RING0 = 0x00000000,
+ EF_IOPL_RING1 = 0x00001000,
+ EF_IOPL_RING2 = 0x00002000,
+ EF_NT = 0x00004000, /* nested task */
+ EF_RF = 0x00010000, /* resume */
+ EF_VM = 0x00020000, /* virtual mode */
+ EF_AC = 0x00040000, /* alignment */
+ EF_VIF = 0x00080000, /* virtual interrupt */
+ EF_VIP = 0x00100000, /* virtual interrupt pending */
+ EF_ID = 0x00200000, /* id */
+};
+
+#ifdef __KERNEL__
+#define user_mode(regs) ((regs) && (3 & (regs)->xcs))
+#define instruction_pointer(regs) ((regs) ? (regs)->eip : NULL)
+extern void show_regs(struct pt_regs *);
+#endif
+
+#endif
--- /dev/null
+#ifndef _I386_RESOURCE_H
+#define _I386_RESOURCE_H
+
+/*
+ * Resource limits
+ */
+
+#define RLIMIT_CPU 0 /* CPU time in ms */
+#define RLIMIT_FSIZE 1 /* Maximum filesize */
+#define RLIMIT_DATA 2 /* max data size */
+#define RLIMIT_STACK 3 /* max stack size */
+#define RLIMIT_CORE 4 /* max core file size */
+#define RLIMIT_RSS 5 /* max resident set size */
+#define RLIMIT_NPROC 6 /* max number of processes */
+#define RLIMIT_NOFILE 7 /* max number of open files */
+#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */
+#define RLIMIT_AS 9 /* address space limit */
+#define RLIMIT_LOCKS 10 /* maximum file locks held */
+
+#define RLIM_NLIMITS 11
+
+/*
+ * SuS says limits have to be unsigned.
+ * Which makes a ton more sense anyway.
+ */
+#define RLIM_INFINITY (~0UL)
+
+#ifdef __KERNEL__
+
+#define INIT_RLIMITS \
+{ \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { _STK_LIM, RLIM_INFINITY }, \
+ { 0, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { 0, 0 }, \
+ { INR_OPEN, INR_OPEN }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+}
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+/* include/asm-i386/rwlock.h
+ *
+ * Helpers used by both rw spinlocks and rw semaphores.
+ *
+ * Based in part on code from semaphore.h and
+ * spinlock.h Copyright 1996 Linus Torvalds.
+ *
+ * Copyright 1999 Red Hat, Inc.
+ *
+ * Written by Benjamin LaHaise.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_I386_RWLOCK_H
+#define _ASM_I386_RWLOCK_H
+
+#define RW_LOCK_BIAS 0x01000000
+#define RW_LOCK_BIAS_STR "0x01000000"
+
+#define __build_read_lock_ptr(rw, helper) \
+ asm volatile(LOCK "subl $1,(%0)\n\t" \
+ "js 2f\n" \
+ "1:\n" \
+ ".section .text.lock,\"ax\"\n" \
+ "2:\tcall " helper "\n\t" \
+ "jmp 1b\n" \
+ ".previous" \
+ ::"a" (rw) : "memory")
+
+#define __build_read_lock_const(rw, helper) \
+ asm volatile(LOCK "subl $1,%0\n\t" \
+ "js 2f\n" \
+ "1:\n" \
+ ".section .text.lock,\"ax\"\n" \
+ "2:\tpushl %%eax\n\t" \
+ "leal %0,%%eax\n\t" \
+ "call " helper "\n\t" \
+ "popl %%eax\n\t" \
+ "jmp 1b\n" \
+ ".previous" \
+ :"=m" (*(volatile int *)rw) : : "memory")
+
+#define __build_read_lock(rw, helper) do { \
+ if (__builtin_constant_p(rw)) \
+ __build_read_lock_const(rw, helper); \
+ else \
+ __build_read_lock_ptr(rw, helper); \
+ } while (0)
+
+#define __build_write_lock_ptr(rw, helper) \
+ asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+ "jnz 2f\n" \
+ "1:\n" \
+ ".section .text.lock,\"ax\"\n" \
+ "2:\tcall " helper "\n\t" \
+ "jmp 1b\n" \
+ ".previous" \
+ ::"a" (rw) : "memory")
+
+#define __build_write_lock_const(rw, helper) \
+ asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+ "jnz 2f\n" \
+ "1:\n" \
+ ".section .text.lock,\"ax\"\n" \
+ "2:\tpushl %%eax\n\t" \
+ "leal %0,%%eax\n\t" \
+ "call " helper "\n\t" \
+ "popl %%eax\n\t" \
+ "jmp 1b\n" \
+ ".previous" \
+ :"=m" (*(volatile int *)rw) : : "memory")
+
+#define __build_write_lock(rw, helper) do { \
+ if (__builtin_constant_p(rw)) \
+ __build_write_lock_const(rw, helper); \
+ else \
+ __build_write_lock_ptr(rw, helper); \
+ } while (0)
+
+#endif
--- /dev/null
+/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ *
+ * Derived from asm-i386/semaphore.h
+ *
+ *
+ * The MSW of the count is the negated number of active writers and waiting
+ * lockers, and the LSW is the total number of active locks
+ *
+ * The lock count is initialized to 0 (no active and no waiting lockers).
+ *
+ * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
+ * uncontended lock. This can be determined because XADD returns the old value.
+ * Readers increment by 1 and see a positive value when uncontended, negative
+ * if there are writers (and maybe) readers waiting (in which case it goes to
+ * sleep).
+ *
+ * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
+ * be extended to 65534 by manually checking the whole MSW rather than relying
+ * on the S flag.
+ *
+ * The value of ACTIVE_BIAS supports up to 65535 active processes.
+ *
+ * This should be totally fair - if anything is waiting, a process that wants a
+ * lock will go to the back of the queue. When the currently active lock is
+ * released, if there's a writer at the front of the queue, then that and only
+ * that will be woken up; if there's a bunch of consequtive readers at the
+ * front, then they'll all be woken up, but no other readers will be.
+ */
+
+#ifndef _I386_RWSEM_H
+#define _I386_RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error please dont include asm/rwsem.h directly, use linux/rwsem.h instead
+#endif
+
+#ifdef __KERNEL__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+struct rwsem_waiter;
+
+extern struct rw_semaphore *FASTCALL(rwsem_down_read_failed(struct rw_semaphore *sem));
+extern struct rw_semaphore *FASTCALL(rwsem_down_write_failed(struct rw_semaphore *sem));
+extern struct rw_semaphore *FASTCALL(rwsem_wake(struct rw_semaphore *));
+
+/*
+ * the semaphore definition
+ */
+struct rw_semaphore {
+ signed long count;
+#define RWSEM_UNLOCKED_VALUE 0x00000000
+#define RWSEM_ACTIVE_BIAS 0x00000001
+#define RWSEM_ACTIVE_MASK 0x0000ffff
+#define RWSEM_WAITING_BIAS (-0x00010000)
+#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+ spinlock_t wait_lock;
+ struct list_head wait_list;
+#if RWSEM_DEBUG
+ int debug;
+#endif
+};
+
+/*
+ * initialisation
+ */
+#if RWSEM_DEBUG
+#define __RWSEM_DEBUG_INIT , 0
+#else
+#define __RWSEM_DEBUG_INIT /* */
+#endif
+
+#define __RWSEM_INITIALIZER(name) \
+{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, LIST_HEAD_INIT((name).wait_list) \
+ __RWSEM_DEBUG_INIT }
+
+#define DECLARE_RWSEM(name) \
+ struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+static inline void init_rwsem(struct rw_semaphore *sem)
+{
+ sem->count = RWSEM_UNLOCKED_VALUE;
+ spin_lock_init(&sem->wait_lock);
+ INIT_LIST_HEAD(&sem->wait_list);
+#if RWSEM_DEBUG
+ sem->debug = 0;
+#endif
+}
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+ __asm__ __volatile__(
+ "# beginning down_read\n\t"
+LOCK_PREFIX " incl (%%eax)\n\t" /* adds 0x00000001, returns the old value */
+ " js 2f\n\t" /* jump if we weren't granted the lock */
+ "1:\n\t"
+ ".section .text.lock,\"ax\"\n"
+ "2:\n\t"
+ " pushl %%ecx\n\t"
+ " pushl %%edx\n\t"
+ " call rwsem_down_read_failed\n\t"
+ " popl %%edx\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ ".previous"
+ "# ending down_read\n\t"
+ : "+m"(sem->count)
+ : "a"(sem)
+ : "memory", "cc");
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+ int tmp;
+
+ tmp = RWSEM_ACTIVE_WRITE_BIAS;
+ __asm__ __volatile__(
+ "# beginning down_write\n\t"
+LOCK_PREFIX " xadd %0,(%%eax)\n\t" /* subtract 0x0000ffff, returns the old value */
+ " testl %0,%0\n\t" /* was the count 0 before? */
+ " jnz 2f\n\t" /* jump if we weren't granted the lock */
+ "1:\n\t"
+ ".section .text.lock,\"ax\"\n"
+ "2:\n\t"
+ " pushl %%ecx\n\t"
+ " call rwsem_down_write_failed\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ ".previous\n"
+ "# ending down_write"
+ : "+d"(tmp), "+m"(sem->count)
+ : "a"(sem)
+ : "memory", "cc");
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+ __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
+ __asm__ __volatile__(
+ "# beginning __up_read\n\t"
+LOCK_PREFIX " xadd %%edx,(%%eax)\n\t" /* subtracts 1, returns the old value */
+ " js 2f\n\t" /* jump if the lock is being waited upon */
+ "1:\n\t"
+ ".section .text.lock,\"ax\"\n"
+ "2:\n\t"
+ " decw %%dx\n\t" /* do nothing if still outstanding active readers */
+ " jnz 1b\n\t"
+ " pushl %%ecx\n\t"
+ " call rwsem_wake\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ ".previous\n"
+ "# ending __up_read\n"
+ : "+m"(sem->count), "+d"(tmp)
+ : "a"(sem)
+ : "memory", "cc");
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+ __asm__ __volatile__(
+ "# beginning __up_write\n\t"
+ " movl %2,%%edx\n\t"
+LOCK_PREFIX " xaddl %%edx,(%%eax)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */
+ " jnz 2f\n\t" /* jump if the lock is being waited upon */
+ "1:\n\t"
+ ".section .text.lock,\"ax\"\n"
+ "2:\n\t"
+ " decw %%dx\n\t" /* did the active count reduce to 0? */
+ " jnz 1b\n\t" /* jump back if not */
+ " pushl %%ecx\n\t"
+ " call rwsem_wake\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ ".previous\n"
+ "# ending __up_write\n"
+ : "+m"(sem->count)
+ : "a"(sem), "i"(-RWSEM_ACTIVE_WRITE_BIAS)
+ : "memory", "cc", "edx");
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+{
+ __asm__ __volatile__(
+LOCK_PREFIX "addl %1,%0"
+ :"=m"(sem->count)
+ :"ir"(delta), "m"(sem->count));
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+ int tmp = delta;
+
+ __asm__ __volatile__(
+LOCK_PREFIX "xadd %0,(%2)"
+ : "+r"(tmp), "=m"(sem->count)
+ : "r"(sem), "m"(sem->count)
+ : "memory");
+
+ return tmp+delta;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _I386_RWSEM_H */
--- /dev/null
+#ifndef _I386_SCATTERLIST_H
+#define _I386_SCATTERLIST_H
+
+struct scatterlist {
+ char * address; /* Location data is to be transferred to, NULL for
+ * highmem page */
+ struct page * page; /* Location for highmem page, if any */
+ unsigned int offset;/* for highmem, page offset */
+
+ dma_addr_t dma_address;
+ unsigned int length;
+};
+
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+
+#endif /* !(_I386_SCATTERLIST_H) */
--- /dev/null
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+#define __KERNEL_CS 0x11
+#define __KERNEL_DS 0x19
+
+#define __USER_CS 0x23
+#define __USER_DS 0x2B
+
+#endif
--- /dev/null
+#ifndef _I386_SEMAPHORE_H
+#define _I386_SEMAPHORE_H
+
+#include <linux/linkage.h>
+
+#ifdef __KERNEL__
+
+/*
+ * SMP- and interrupt-safe semaphores..
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ *
+ * Modified 1996-12-23 by Dave Grothe <dave@gcom.com> to fix bugs in
+ * the original code and to make semaphore waits
+ * interruptible so that processes waiting on
+ * semaphores can be killed.
+ * Modified 1999-02-14 by Andrea Arcangeli, split the sched.c helper
+ * functions in asm/sempahore-helper.h while fixing a
+ * potential and subtle race discovered by Ulrich Schmid
+ * in down_interruptible(). Since I started to play here I
+ * also implemented the `trylock' semaphore operation.
+ * 1999-07-02 Artur Skawina <skawina@geocities.com>
+ * Optimized "0(ecx)" -> "(ecx)" (the assembler does not
+ * do this). Changed calling sequences from push/jmp to
+ * traditional call/ret.
+ * Modified 2001-01-01 Andreas Franck <afranck@gmx.de>
+ * Some hacks to ensure compatibility with recent
+ * GCC snapshots, to avoid stack corruption when compiling
+ * with -fomit-frame-pointer. It's not sure if this will
+ * be fixed in GCC, as our previous implementation was a
+ * bit dubious.
+ *
+ * If you would like to see an analysis of this implementation, please
+ * ftp to gcom.com and download the file
+ * /pub/linux/src/semaphore/semaphore-2.0.24.tar.gz.
+ *
+ */
+
+#include <asm/system.h>
+#include <asm/atomic.h>
+#include <linux/wait.h>
+#include <linux/rwsem.h>
+
+struct semaphore {
+ atomic_t count;
+ int sleepers;
+ wait_queue_head_t wait;
+#if WAITQUEUE_DEBUG
+ long __magic;
+#endif
+};
+
+#if WAITQUEUE_DEBUG
+# define __SEM_DEBUG_INIT(name) \
+ , (int)&(name).__magic
+#else
+# define __SEM_DEBUG_INIT(name)
+#endif
+
+#define __SEMAPHORE_INITIALIZER(name,count) \
+{ ATOMIC_INIT(count), 0, __WAIT_QUEUE_HEAD_INITIALIZER((name).wait) \
+ __SEM_DEBUG_INIT(name) }
+
+#define __MUTEX_INITIALIZER(name) \
+ __SEMAPHORE_INITIALIZER(name,1)
+
+#define __DECLARE_SEMAPHORE_GENERIC(name,count) \
+ struct semaphore name = __SEMAPHORE_INITIALIZER(name,count)
+
+#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name,1)
+#define DECLARE_MUTEX_LOCKED(name) __DECLARE_SEMAPHORE_GENERIC(name,0)
+
+static inline void sema_init (struct semaphore *sem, int val)
+{
+/*
+ * *sem = (struct semaphore)__SEMAPHORE_INITIALIZER((*sem),val);
+ *
+ * i'd rather use the more flexible initialization above, but sadly
+ * GCC 2.7.2.3 emits a bogus warning. EGCS doesnt. Oh well.
+ */
+ atomic_set(&sem->count, val);
+ sem->sleepers = 0;
+ init_waitqueue_head(&sem->wait);
+#if WAITQUEUE_DEBUG
+ sem->__magic = (int)&sem->__magic;
+#endif
+}
+
+static inline void init_MUTEX (struct semaphore *sem)
+{
+ sema_init(sem, 1);
+}
+
+static inline void init_MUTEX_LOCKED (struct semaphore *sem)
+{
+ sema_init(sem, 0);
+}
+
+asmlinkage void __down_failed(void /* special register calling convention */);
+asmlinkage int __down_failed_interruptible(void /* params in registers */);
+asmlinkage int __down_failed_trylock(void /* params in registers */);
+asmlinkage void __up_wakeup(void /* special register calling convention */);
+
+asmlinkage void __down(struct semaphore * sem);
+asmlinkage int __down_interruptible(struct semaphore * sem);
+asmlinkage int __down_trylock(struct semaphore * sem);
+asmlinkage void __up(struct semaphore * sem);
+
+/*
+ * This is ugly, but we want the default case to fall through.
+ * "__down_failed" is a special asm handler that calls the C
+ * routine that actually waits. See arch/i386/kernel/semaphore.c
+ */
+static inline void down(struct semaphore * sem)
+{
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+
+ __asm__ __volatile__(
+ "# atomic down operation\n\t"
+ LOCK "decl %0\n\t" /* --sem->count */
+ "js 2f\n"
+ "1:\n"
+ ".section .text.lock,\"ax\"\n"
+ "2:\tcall __down_failed\n\t"
+ "jmp 1b\n"
+ ".previous"
+ :"=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+}
+
+/*
+ * Interruptible try to acquire a semaphore. If we obtained
+ * it, return zero. If we were interrupted, returns -EINTR
+ */
+static inline int down_interruptible(struct semaphore * sem)
+{
+ int result;
+
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+
+ __asm__ __volatile__(
+ "# atomic interruptible down operation\n\t"
+ LOCK "decl %1\n\t" /* --sem->count */
+ "js 2f\n\t"
+ "xorl %0,%0\n"
+ "1:\n"
+ ".section .text.lock,\"ax\"\n"
+ "2:\tcall __down_failed_interruptible\n\t"
+ "jmp 1b\n"
+ ".previous"
+ :"=a" (result), "=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+ return result;
+}
+
+/*
+ * Non-blockingly attempt to down() a semaphore.
+ * Returns zero if we acquired it
+ */
+static inline int down_trylock(struct semaphore * sem)
+{
+ int result;
+
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+
+ __asm__ __volatile__(
+ "# atomic interruptible down operation\n\t"
+ LOCK "decl %1\n\t" /* --sem->count */
+ "js 2f\n\t"
+ "xorl %0,%0\n"
+ "1:\n"
+ ".section .text.lock,\"ax\"\n"
+ "2:\tcall __down_failed_trylock\n\t"
+ "jmp 1b\n"
+ ".previous"
+ :"=a" (result), "=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+ return result;
+}
+
+/*
+ * Note! This is subtle. We jump to wake people up only if
+ * the semaphore was negative (== somebody was waiting on it).
+ * The default case (no contention) will result in NO
+ * jumps for both down() and up().
+ */
+static inline void up(struct semaphore * sem)
+{
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+ __asm__ __volatile__(
+ "# atomic up operation\n\t"
+ LOCK "incl %0\n\t" /* ++sem->count */
+ "jle 2f\n"
+ "1:\n"
+ ".section .text.lock,\"ax\"\n"
+ "2:\tcall __up_wakeup\n\t"
+ "jmp 1b\n"
+ ".previous"
+ :"=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+}
+
+#endif
+#endif
--- /dev/null
+#ifndef _I386_SEMBUF_H
+#define _I386_SEMBUF_H
+
+/*
+ * The semid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct semid64_ds {
+ struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
+ __kernel_time_t sem_otime; /* last semop time */
+ unsigned long __unused1;
+ __kernel_time_t sem_ctime; /* last change time */
+ unsigned long __unused2;
+ unsigned long sem_nsems; /* no. of semaphores in array */
+ unsigned long __unused3;
+ unsigned long __unused4;
+};
+
+#endif /* _I386_SEMBUF_H */
--- /dev/null
+/*
+ * include/asm-i386/serial.h
+ */
+
+#include <linux/config.h>
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ *
+ * It'd be nice if someone built a serial card with a 24.576 MHz
+ * clock, since the 16550A is capable of handling a top speed of 1.5
+ * megabits/second; but this requires the faster clock.
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+/* Standard COM flags (except for COM4, because of the 8514 problem) */
+#ifdef CONFIG_SERIAL_DETECT_IRQ
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+#else
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
+#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+#endif
+
+#ifdef CONFIG_SERIAL_MANY_PORTS
+#define FOURPORT_FLAGS ASYNC_FOURPORT
+#define ACCENT_FLAGS 0
+#define BOCA_FLAGS 0
+#define HUB6_FLAGS 0
+#define RS_TABLE_SIZE 64
+#else
+#define RS_TABLE_SIZE
+#endif
+
+#define MCA_COM_FLAGS (STD_COM_FLAGS|ASYNC_BOOT_ONLYMCA)
+
+/*
+ * The following define the access methods for the HUB6 card. All
+ * access is through two ports for all 24 possible chips. The card is
+ * selected through the high 2 bits, the port on that card with the
+ * "middle" 3 bits, and the register on that port with the bottom
+ * 3 bits.
+ *
+ * While the access port and interrupt is configurable, the default
+ * port locations are 0x302 for the port control register, and 0x303
+ * for the data read/write register. Normally, the interrupt is at irq3
+ * but can be anything from 3 to 7 inclusive. Note that using 3 will
+ * require disabling com2.
+ */
+
+#define C_P(card,port) (((card)<<6|(port)<<3) + 1)
+
+#define STD_SERIAL_PORT_DEFNS \
+ /* UART CLK PORT IRQ FLAGS */ \
+ { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS }, /* ttyS0 */ \
+ { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS }, /* ttyS1 */ \
+ { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS }, /* ttyS2 */ \
+ { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */
+
+
+#ifdef CONFIG_SERIAL_MANY_PORTS
+#define EXTRA_SERIAL_PORT_DEFNS \
+ { 0, BASE_BAUD, 0x1A0, 9, FOURPORT_FLAGS }, /* ttyS4 */ \
+ { 0, BASE_BAUD, 0x1A8, 9, FOURPORT_FLAGS }, /* ttyS5 */ \
+ { 0, BASE_BAUD, 0x1B0, 9, FOURPORT_FLAGS }, /* ttyS6 */ \
+ { 0, BASE_BAUD, 0x1B8, 9, FOURPORT_FLAGS }, /* ttyS7 */ \
+ { 0, BASE_BAUD, 0x2A0, 5, FOURPORT_FLAGS }, /* ttyS8 */ \
+ { 0, BASE_BAUD, 0x2A8, 5, FOURPORT_FLAGS }, /* ttyS9 */ \
+ { 0, BASE_BAUD, 0x2B0, 5, FOURPORT_FLAGS }, /* ttyS10 */ \
+ { 0, BASE_BAUD, 0x2B8, 5, FOURPORT_FLAGS }, /* ttyS11 */ \
+ { 0, BASE_BAUD, 0x330, 4, ACCENT_FLAGS }, /* ttyS12 */ \
+ { 0, BASE_BAUD, 0x338, 4, ACCENT_FLAGS }, /* ttyS13 */ \
+ { 0, BASE_BAUD, 0x000, 0, 0 }, /* ttyS14 (spare) */ \
+ { 0, BASE_BAUD, 0x000, 0, 0 }, /* ttyS15 (spare) */ \
+ { 0, BASE_BAUD, 0x100, 12, BOCA_FLAGS }, /* ttyS16 */ \
+ { 0, BASE_BAUD, 0x108, 12, BOCA_FLAGS }, /* ttyS17 */ \
+ { 0, BASE_BAUD, 0x110, 12, BOCA_FLAGS }, /* ttyS18 */ \
+ { 0, BASE_BAUD, 0x118, 12, BOCA_FLAGS }, /* ttyS19 */ \
+ { 0, BASE_BAUD, 0x120, 12, BOCA_FLAGS }, /* ttyS20 */ \
+ { 0, BASE_BAUD, 0x128, 12, BOCA_FLAGS }, /* ttyS21 */ \
+ { 0, BASE_BAUD, 0x130, 12, BOCA_FLAGS }, /* ttyS22 */ \
+ { 0, BASE_BAUD, 0x138, 12, BOCA_FLAGS }, /* ttyS23 */ \
+ { 0, BASE_BAUD, 0x140, 12, BOCA_FLAGS }, /* ttyS24 */ \
+ { 0, BASE_BAUD, 0x148, 12, BOCA_FLAGS }, /* ttyS25 */ \
+ { 0, BASE_BAUD, 0x150, 12, BOCA_FLAGS }, /* ttyS26 */ \
+ { 0, BASE_BAUD, 0x158, 12, BOCA_FLAGS }, /* ttyS27 */ \
+ { 0, BASE_BAUD, 0x160, 12, BOCA_FLAGS }, /* ttyS28 */ \
+ { 0, BASE_BAUD, 0x168, 12, BOCA_FLAGS }, /* ttyS29 */ \
+ { 0, BASE_BAUD, 0x170, 12, BOCA_FLAGS }, /* ttyS30 */ \
+ { 0, BASE_BAUD, 0x178, 12, BOCA_FLAGS }, /* ttyS31 */
+#else
+#define EXTRA_SERIAL_PORT_DEFNS
+#endif
+
+/* You can have up to four HUB6's in the system, but I've only
+ * included two cards here for a total of twelve ports.
+ */
+#if (defined(CONFIG_HUB6) && defined(CONFIG_SERIAL_MANY_PORTS))
+#define HUB6_SERIAL_PORT_DFNS \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,0) }, /* ttyS32 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,1) }, /* ttyS33 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,2) }, /* ttyS34 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,3) }, /* ttyS35 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,4) }, /* ttyS36 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,5) }, /* ttyS37 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,0) }, /* ttyS38 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,1) }, /* ttyS39 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,2) }, /* ttyS40 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,3) }, /* ttyS41 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,4) }, /* ttyS42 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,5) }, /* ttyS43 */
+#else
+#define HUB6_SERIAL_PORT_DFNS
+#endif
+
+#ifdef CONFIG_MCA
+#define MCA_SERIAL_PORT_DFNS \
+ { 0, BASE_BAUD, 0x3220, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x3228, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x4220, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x4228, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x5220, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x5228, 3, MCA_COM_FLAGS },
+#else
+#define MCA_SERIAL_PORT_DFNS
+#endif
+
+#define SERIAL_PORT_DFNS \
+ STD_SERIAL_PORT_DEFNS \
+ EXTRA_SERIAL_PORT_DEFNS \
+ HUB6_SERIAL_PORT_DFNS \
+ MCA_SERIAL_PORT_DFNS
+
--- /dev/null
+/*
+ * Just a place holder. We don't want to have to test x86 before
+ * we include stuff
+ */
+
+#ifndef _i386_SETUP_H
+#define _i386_SETUP_H
+
+
+#endif /* _i386_SETUP_H */
--- /dev/null
+#ifndef _I386_SHMBUF_H
+#define _I386_SHMBUF_H
+
+/*
+ * The shmid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct shmid64_ds {
+ struct ipc64_perm shm_perm; /* operation perms */
+ size_t shm_segsz; /* size of segment (bytes) */
+ __kernel_time_t shm_atime; /* last attach time */
+ unsigned long __unused1;
+ __kernel_time_t shm_dtime; /* last detach time */
+ unsigned long __unused2;
+ __kernel_time_t shm_ctime; /* last change time */
+ unsigned long __unused3;
+ __kernel_pid_t shm_cpid; /* pid of creator */
+ __kernel_pid_t shm_lpid; /* pid of last operator */
+ unsigned long shm_nattch; /* no. of current attaches */
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+
+struct shminfo64 {
+ unsigned long shmmax;
+ unsigned long shmmin;
+ unsigned long shmmni;
+ unsigned long shmseg;
+ unsigned long shmall;
+ unsigned long __unused1;
+ unsigned long __unused2;
+ unsigned long __unused3;
+ unsigned long __unused4;
+};
+
+#endif /* _I386_SHMBUF_H */
--- /dev/null
+#ifndef _ASMI386_SHMPARAM_H
+#define _ASMI386_SHMPARAM_H
+
+#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */
+
+#endif /* _ASMI386_SHMPARAM_H */
--- /dev/null
+#ifndef _ASMi386_SIGCONTEXT_H
+#define _ASMi386_SIGCONTEXT_H
+
+/*
+ * As documented in the iBCS2 standard..
+ *
+ * The first part of "struct _fpstate" is just the normal i387
+ * hardware setup, the extra "status" word is used to save the
+ * coprocessor status word before entering the handler.
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * The FPU state data structure has had to grow to accomodate the
+ * extended FPU state required by the Streaming SIMD Extensions.
+ * There is no documented standard to accomplish this at the moment.
+ */
+struct _fpreg {
+ unsigned short significand[4];
+ unsigned short exponent;
+};
+
+struct _fpxreg {
+ unsigned short significand[4];
+ unsigned short exponent;
+ unsigned short padding[3];
+};
+
+struct _xmmreg {
+ unsigned long element[4];
+};
+
+struct _fpstate {
+ /* Regular FPU environment */
+ unsigned long cw;
+ unsigned long sw;
+ unsigned long tag;
+ unsigned long ipoff;
+ unsigned long cssel;
+ unsigned long dataoff;
+ unsigned long datasel;
+ struct _fpreg _st[8];
+ unsigned short status;
+ unsigned short magic; /* 0xffff = regular FPU data only */
+
+ /* FXSR FPU environment */
+ unsigned long _fxsr_env[6]; /* FXSR FPU env is ignored */
+ unsigned long mxcsr;
+ unsigned long reserved;
+ struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */
+ struct _xmmreg _xmm[8];
+ unsigned long padding[56];
+};
+
+#define X86_FXSR_MAGIC 0x0000
+
+struct sigcontext {
+ unsigned short gs, __gsh;
+ unsigned short fs, __fsh;
+ unsigned short es, __esh;
+ unsigned short ds, __dsh;
+ unsigned long edi;
+ unsigned long esi;
+ unsigned long ebp;
+ unsigned long esp;
+ unsigned long ebx;
+ unsigned long edx;
+ unsigned long ecx;
+ unsigned long eax;
+ unsigned long trapno;
+ unsigned long err;
+ unsigned long eip;
+ unsigned short cs, __csh;
+ unsigned long eflags;
+ unsigned long esp_at_signal;
+ unsigned short ss, __ssh;
+ struct _fpstate * fpstate;
+ unsigned long oldmask;
+ unsigned long cr2;
+};
+
+
+#endif
--- /dev/null
+#ifndef _I386_SIGINFO_H
+#define _I386_SIGINFO_H
+
+#include <linux/types.h>
+
+/* XXX: This structure was copied from the Alpha; is there an iBCS version? */
+
+typedef union sigval {
+ int sival_int;
+ void *sival_ptr;
+} sigval_t;
+
+#define SI_MAX_SIZE 128
+#define SI_PAD_SIZE ((SI_MAX_SIZE/sizeof(int)) - 3)
+
+typedef struct siginfo {
+ int si_signo;
+ int si_errno;
+ int si_code;
+
+ union {
+ int _pad[SI_PAD_SIZE];
+
+ /* kill() */
+ struct {
+ pid_t _pid; /* sender's pid */
+ uid_t _uid; /* sender's uid */
+ } _kill;
+
+ /* POSIX.1b timers */
+ struct {
+ unsigned int _timer1;
+ unsigned int _timer2;
+ } _timer;
+
+ /* POSIX.1b signals */
+ struct {
+ pid_t _pid; /* sender's pid */
+ uid_t _uid; /* sender's uid */
+ sigval_t _sigval;
+ } _rt;
+
+ /* SIGCHLD */
+ struct {
+ pid_t _pid; /* which child */
+ uid_t _uid; /* sender's uid */
+ int _status; /* exit code */
+ clock_t _utime;
+ clock_t _stime;
+ } _sigchld;
+
+ /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+ struct {
+ void *_addr; /* faulting insn/memory ref. */
+ } _sigfault;
+
+ /* SIGPOLL */
+ struct {
+ int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
+ int _fd;
+ } _sigpoll;
+ } _sifields;
+} siginfo_t;
+
+/*
+ * How these fields are to be accessed.
+ */
+#define si_pid _sifields._kill._pid
+#define si_uid _sifields._kill._uid
+#define si_status _sifields._sigchld._status
+#define si_utime _sifields._sigchld._utime
+#define si_stime _sifields._sigchld._stime
+#define si_value _sifields._rt._sigval
+#define si_int _sifields._rt._sigval.sival_int
+#define si_ptr _sifields._rt._sigval.sival_ptr
+#define si_addr _sifields._sigfault._addr
+#define si_band _sifields._sigpoll._band
+#define si_fd _sifields._sigpoll._fd
+
+#ifdef __KERNEL__
+#define __SI_MASK 0xffff0000
+#define __SI_KILL (0 << 16)
+#define __SI_TIMER (1 << 16)
+#define __SI_POLL (2 << 16)
+#define __SI_FAULT (3 << 16)
+#define __SI_CHLD (4 << 16)
+#define __SI_RT (5 << 16)
+#define __SI_CODE(T,N) ((T) << 16 | ((N) & 0xffff))
+#else
+#define __SI_KILL 0
+#define __SI_TIMER 0
+#define __SI_POLL 0
+#define __SI_FAULT 0
+#define __SI_CHLD 0
+#define __SI_RT 0
+#define __SI_CODE(T,N) (N)
+#endif
+
+/*
+ * si_code values
+ * Digital reserves positive values for kernel-generated signals.
+ */
+#define SI_USER 0 /* sent by kill, sigsend, raise */
+#define SI_KERNEL 0x80 /* sent by the kernel from somewhere */
+#define SI_QUEUE -1 /* sent by sigqueue */
+#define SI_TIMER __SI_CODE(__SI_TIMER,-2) /* sent by timer expiration */
+#define SI_MESGQ -3 /* sent by real time mesq state change */
+#define SI_ASYNCIO -4 /* sent by AIO completion */
+#define SI_SIGIO -5 /* sent by queued SIGIO */
+
+#define SI_FROMUSER(siptr) ((siptr)->si_code <= 0)
+#define SI_FROMKERNEL(siptr) ((siptr)->si_code > 0)
+
+/*
+ * SIGILL si_codes
+ */
+#define ILL_ILLOPC (__SI_FAULT|1) /* illegal opcode */
+#define ILL_ILLOPN (__SI_FAULT|2) /* illegal operand */
+#define ILL_ILLADR (__SI_FAULT|3) /* illegal addressing mode */
+#define ILL_ILLTRP (__SI_FAULT|4) /* illegal trap */
+#define ILL_PRVOPC (__SI_FAULT|5) /* privileged opcode */
+#define ILL_PRVREG (__SI_FAULT|6) /* privileged register */
+#define ILL_COPROC (__SI_FAULT|7) /* coprocessor error */
+#define ILL_BADSTK (__SI_FAULT|8) /* internal stack error */
+#define NSIGILL 8
+
+/*
+ * SIGFPE si_codes
+ */
+#define FPE_INTDIV (__SI_FAULT|1) /* integer divide by zero */
+#define FPE_INTOVF (__SI_FAULT|2) /* integer overflow */
+#define FPE_FLTDIV (__SI_FAULT|3) /* floating point divide by zero */
+#define FPE_FLTOVF (__SI_FAULT|4) /* floating point overflow */
+#define FPE_FLTUND (__SI_FAULT|5) /* floating point underflow */
+#define FPE_FLTRES (__SI_FAULT|6) /* floating point inexact result */
+#define FPE_FLTINV (__SI_FAULT|7) /* floating point invalid operation */
+#define FPE_FLTSUB (__SI_FAULT|8) /* subscript out of range */
+#define NSIGFPE 8
+
+/*
+ * SIGSEGV si_codes
+ */
+#define SEGV_MAPERR (__SI_FAULT|1) /* address not mapped to object */
+#define SEGV_ACCERR (__SI_FAULT|2) /* invalid permissions for mapped object */
+#define NSIGSEGV 2
+
+/*
+ * SIGBUS si_codes
+ */
+#define BUS_ADRALN (__SI_FAULT|1) /* invalid address alignment */
+#define BUS_ADRERR (__SI_FAULT|2) /* non-existant physical address */
+#define BUS_OBJERR (__SI_FAULT|3) /* object specific hardware error */
+#define NSIGBUS 3
+
+/*
+ * SIGTRAP si_codes
+ */
+#define TRAP_BRKPT (__SI_FAULT|1) /* process breakpoint */
+#define TRAP_TRACE (__SI_FAULT|2) /* process trace trap */
+#define NSIGTRAP 2
+
+/*
+ * SIGCHLD si_codes
+ */
+#define CLD_EXITED (__SI_CHLD|1) /* child has exited */
+#define CLD_KILLED (__SI_CHLD|2) /* child was killed */
+#define CLD_DUMPED (__SI_CHLD|3) /* child terminated abnormally */
+#define CLD_TRAPPED (__SI_CHLD|4) /* traced child has trapped */
+#define CLD_STOPPED (__SI_CHLD|5) /* child has stopped */
+#define CLD_CONTINUED (__SI_CHLD|6) /* stopped child has continued */
+#define NSIGCHLD 6
+
+/*
+ * SIGPOLL si_codes
+ */
+#define POLL_IN (__SI_POLL|1) /* data input available */
+#define POLL_OUT (__SI_POLL|2) /* output buffers available */
+#define POLL_MSG (__SI_POLL|3) /* input message available */
+#define POLL_ERR (__SI_POLL|4) /* i/o error */
+#define POLL_PRI (__SI_POLL|5) /* high priority input available */
+#define POLL_HUP (__SI_POLL|6) /* device disconnected */
+#define NSIGPOLL 6
+
+/*
+ * sigevent definitions
+ *
+ * It seems likely that SIGEV_THREAD will have to be handled from
+ * userspace, libpthread transmuting it to SIGEV_SIGNAL, which the
+ * thread manager then catches and does the appropriate nonsense.
+ * However, everything is written out here so as to not get lost.
+ */
+#define SIGEV_SIGNAL 0 /* notify via signal */
+#define SIGEV_NONE 1 /* other notification: meaningless */
+#define SIGEV_THREAD 2 /* deliver via thread creation */
+
+#define SIGEV_MAX_SIZE 64
+#define SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3)
+
+typedef struct sigevent {
+ sigval_t sigev_value;
+ int sigev_signo;
+ int sigev_notify;
+ union {
+ int _pad[SIGEV_PAD_SIZE];
+
+ struct {
+ void (*_function)(sigval_t);
+ void *_attribute; /* really pthread_attr_t */
+ } _sigev_thread;
+ } _sigev_un;
+} sigevent_t;
+
+#define sigev_notify_function _sigev_un._sigev_thread._function
+#define sigev_notify_attributes _sigev_un._sigev_thread._attribute
+
+#ifdef __KERNEL__
+#include <linux/string.h>
+
+static inline void copy_siginfo(siginfo_t *to, siginfo_t *from)
+{
+ if (from->si_code < 0)
+ memcpy(to, from, sizeof(siginfo_t));
+ else
+ /* _sigchld is currently the largest know union member */
+ memcpy(to, from, 3*sizeof(int) + sizeof(from->_sifields._sigchld));
+}
+
+extern int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from);
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef _ASMi386_SIGNAL_H
+#define _ASMi386_SIGNAL_H
+
+#include <linux/types.h>
+
+/* Avoid too many header ordering problems. */
+struct siginfo;
+
+#ifdef __KERNEL__
+/* Most things should be clean enough to redefine this at will, if care
+ is taken to make libc match. */
+
+#define _NSIG 64
+#define _NSIG_BPW 32
+#define _NSIG_WORDS (_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t; /* at least 32 bits */
+
+typedef struct {
+ unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+#else
+/* Here we must cater to libcs that poke about in kernel headers. */
+
+#define NSIG 32
+typedef unsigned long sigset_t;
+
+#endif /* __KERNEL__ */
+
+#define SIGHUP 1
+#define SIGINT 2
+#define SIGQUIT 3
+#define SIGILL 4
+#define SIGTRAP 5
+#define SIGABRT 6
+#define SIGIOT 6
+#define SIGBUS 7
+#define SIGFPE 8
+#define SIGKILL 9
+#define SIGUSR1 10
+#define SIGSEGV 11
+#define SIGUSR2 12
+#define SIGPIPE 13
+#define SIGALRM 14
+#define SIGTERM 15
+#define SIGSTKFLT 16
+#define SIGCHLD 17
+#define SIGCONT 18
+#define SIGSTOP 19
+#define SIGTSTP 20
+#define SIGTTIN 21
+#define SIGTTOU 22
+#define SIGURG 23
+#define SIGXCPU 24
+#define SIGXFSZ 25
+#define SIGVTALRM 26
+#define SIGPROF 27
+#define SIGWINCH 28
+#define SIGIO 29
+#define SIGPOLL SIGIO
+/*
+#define SIGLOST 29
+*/
+#define SIGPWR 30
+#define SIGSYS 31
+#define SIGUNUSED 31
+
+/* These should not be considered constants from userland. */
+#define SIGRTMIN 32
+#define SIGRTMAX (_NSIG-1)
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_INTERRUPT is a no-op, but left due to historical reasons. Use the
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_NOCLDSTOP 0x00000001
+#define SA_NOCLDWAIT 0x00000002 /* not supported yet */
+#define SA_SIGINFO 0x00000004
+#define SA_ONSTACK 0x08000000
+#define SA_RESTART 0x10000000
+#define SA_NODEFER 0x40000000
+#define SA_RESETHAND 0x80000000
+
+#define SA_NOMASK SA_NODEFER
+#define SA_ONESHOT SA_RESETHAND
+#define SA_INTERRUPT 0x20000000 /* dummy -- ignored */
+
+#define SA_RESTORER 0x04000000
+
+/*
+ * sigaltstack controls
+ */
+#define SS_ONSTACK 1
+#define SS_DISABLE 2
+
+#define MINSIGSTKSZ 2048
+#define SIGSTKSZ 8192
+
+#ifdef __KERNEL__
+
+/*
+ * These values of sa_flags are used only by the kernel as part of the
+ * irq handling routines.
+ *
+ * SA_INTERRUPT is also used by the irq handling routines.
+ * SA_SHIRQ is for shared interrupt support on PCI and EISA.
+ */
+#define SA_PROBE SA_ONESHOT
+#define SA_SAMPLE_RANDOM SA_RESTART
+#define SA_SHIRQ 0x04000000
+#endif
+
+#define SIG_BLOCK 0 /* for blocking signals */
+#define SIG_UNBLOCK 1 /* for unblocking signals */
+#define SIG_SETMASK 2 /* for setting the signal mask */
+
+/* Type of a signal handler. */
+typedef void (*__sighandler_t)(int);
+
+#define SIG_DFL ((__sighandler_t)0) /* default signal handling */
+#define SIG_IGN ((__sighandler_t)1) /* ignore signal */
+#define SIG_ERR ((__sighandler_t)-1) /* error return from signal */
+
+#ifdef __KERNEL__
+struct old_sigaction {
+ __sighandler_t sa_handler;
+ old_sigset_t sa_mask;
+ unsigned long sa_flags;
+ void (*sa_restorer)(void);
+};
+
+struct sigaction {
+ __sighandler_t sa_handler;
+ unsigned long sa_flags;
+ void (*sa_restorer)(void);
+ sigset_t sa_mask; /* mask last for extensibility */
+};
+
+struct k_sigaction {
+ struct sigaction sa;
+};
+#else
+/* Here we must cater to libcs that poke about in kernel headers. */
+
+struct sigaction {
+ union {
+ __sighandler_t _sa_handler;
+ void (*_sa_sigaction)(int, struct siginfo *, void *);
+ } _u;
+ sigset_t sa_mask;
+ unsigned long sa_flags;
+ void (*sa_restorer)(void);
+};
+
+#define sa_handler _u._sa_handler
+#define sa_sigaction _u._sa_sigaction
+
+#endif /* __KERNEL__ */
+
+typedef struct sigaltstack {
+ void *ss_sp;
+ int ss_flags;
+ size_t ss_size;
+} stack_t;
+
+#ifdef __KERNEL__
+#include <asm/sigcontext.h>
+
+#define __HAVE_ARCH_SIG_BITOPS
+
+static __inline__ void sigaddset(sigset_t *set, int _sig)
+{
+ __asm__("btsl %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static __inline__ void sigdelset(sigset_t *set, int _sig)
+{
+ __asm__("btrl %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static __inline__ int __const_sigismember(sigset_t *set, int _sig)
+{
+ unsigned long sig = _sig - 1;
+ return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
+}
+
+static __inline__ int __gen_sigismember(sigset_t *set, int _sig)
+{
+ int ret;
+ __asm__("btl %2,%1\n\tsbbl %0,%0"
+ : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+ return ret;
+}
+
+#define sigismember(set,sig) \
+ (__builtin_constant_p(sig) ? \
+ __const_sigismember((set),(sig)) : \
+ __gen_sigismember((set),(sig)))
+
+#define sigmask(sig) (1UL << ((sig) - 1))
+
+static __inline__ int sigfindinword(unsigned long word)
+{
+ __asm__("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc");
+ return word;
+}
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifndef __ASSEMBLY__
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/ptrace.h>
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#ifndef __ASSEMBLY__
+#include <asm/bitops.h>
+#include <asm/mpspec.h>
+#ifdef CONFIG_X86_IO_APIC
+#include <asm/io_apic.h>
+#endif
+#include <asm/apic.h>
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+# define TARGET_CPUS cpu_online_map
+# define INT_DELIVERY_MODE 1 /* logical delivery broadcast to all procs */
+#else
+# define INT_DELIVERY_MODE 1 /* logical delivery */
+# define TARGET_CPUS 0x01
+#endif
+
+#ifndef clustered_apic_mode
+ #define clustered_apic_mode (0)
+ #define esr_disable (0)
+#endif
+
+#ifdef CONFIG_SMP
+#ifndef __ASSEMBLY__
+
+/*
+ * Private routines/data
+ */
+
+extern void smp_alloc_memory(void);
+extern unsigned long phys_cpu_present_map;
+extern unsigned long cpu_online_map;
+extern volatile unsigned long smp_invalidate_needed;
+extern int pic_mode;
+extern void smp_flush_tlb(void);
+extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs);
+extern void smp_send_reschedule(int cpu);
+extern void smp_invalidate_rcv(void); /* Process an NMI */
+extern void (*mtrr_hook) (void);
+extern void zap_low_mappings (void);
+
+/*
+ * On x86 all CPUs are mapped 1:1 to the APIC space.
+ * This simplifies scheduling and IPI sending and
+ * compresses data structures.
+ */
+static inline int cpu_logical_map(int cpu)
+{
+ return cpu;
+}
+static inline int cpu_number_map(int cpu)
+{
+ return cpu;
+}
+
+/*
+ * Some lowlevel functions might want to know about
+ * the real APIC ID <-> CPU # mapping.
+ */
+#define MAX_APICID 256
+extern volatile int cpu_to_physical_apicid[NR_CPUS];
+extern volatile int physical_apicid_to_cpu[MAX_APICID];
+extern volatile int cpu_to_logical_apicid[NR_CPUS];
+extern volatile int logical_apicid_to_cpu[MAX_APICID];
+
+/*
+ * General functions that each host system must provide.
+ */
+
+extern void smp_boot_cpus(void);
+extern void smp_store_cpu_info(int id); /* Store per CPU info (like the initial udelay numbers */
+
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+
+#define smp_processor_id() (current->processor)
+
+#endif /* !__ASSEMBLY__ */
+
+#define NO_PROC_ID 0xFF /* No processor magic marker */
+
+/*
+ * This magic constant controls our willingness to transfer
+ * a process across CPUs. Such a transfer incurs misses on the L1
+ * cache, and on a P6 or P5 with multiple L2 caches L2 hits. My
+ * gut feeling is this will vary by board in value. For a board
+ * with separate L2 cache it probably depends also on the RSS, and
+ * for a board with shared L2 cache it ought to decay fast as other
+ * processes are run.
+ */
+
+#define PROC_CHANGE_PENALTY 15 /* Schedule penalty */
+
+#endif
+#endif
--- /dev/null
+/*
+ * <asm/smplock.h>
+ *
+ * i386 SMP lock implementation
+ */
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <asm/current.h>
+
+extern spinlock_t kernel_flag;
+
+#define kernel_locked() spin_is_locked(&kernel_flag)
+
+/*
+ * Release global kernel lock and global interrupt lock
+ */
+#define release_kernel_lock(task, cpu) \
+do { \
+ if (task->lock_depth >= 0) \
+ spin_unlock(&kernel_flag); \
+ release_irqlock(cpu); \
+ __sti(); \
+} while (0)
+
+/*
+ * Re-acquire the kernel lock
+ */
+#define reacquire_kernel_lock(task) \
+do { \
+ if (task->lock_depth >= 0) \
+ spin_lock(&kernel_flag); \
+} while (0)
+
+
+/*
+ * Getting the big kernel lock.
+ *
+ * This cannot happen asynchronously,
+ * so we only need to worry about other
+ * CPU's.
+ */
+static __inline__ void lock_kernel(void)
+{
+#if 1
+ if (!++current->lock_depth)
+ spin_lock(&kernel_flag);
+#else
+ __asm__ __volatile__(
+ "incl %1\n\t"
+ "jne 9f"
+ spin_lock_string
+ "\n9:"
+ :"=m" (__dummy_lock(&kernel_flag)),
+ "=m" (current->lock_depth));
+#endif
+}
+
+static __inline__ void unlock_kernel(void)
+{
+ if (current->lock_depth < 0)
+ BUG();
+#if 1
+ if (--current->lock_depth < 0)
+ spin_unlock(&kernel_flag);
+#else
+ __asm__ __volatile__(
+ "decl %1\n\t"
+ "jns 9f\n\t"
+ spin_unlock_string
+ "\n9:"
+ :"=m" (__dummy_lock(&kernel_flag)),
+ "=m" (current->lock_depth));
+#endif
+}
--- /dev/null
+#ifndef _ASM_SOCKET_H
+#define _ASM_SOCKET_H
+
+#include <asm/sockios.h>
+
+/* For setsockoptions(2) */
+#define SOL_SOCKET 1
+
+#define SO_DEBUG 1
+#define SO_REUSEADDR 2
+#define SO_TYPE 3
+#define SO_ERROR 4
+#define SO_DONTROUTE 5
+#define SO_BROADCAST 6
+#define SO_SNDBUF 7
+#define SO_RCVBUF 8
+#define SO_KEEPALIVE 9
+#define SO_OOBINLINE 10
+#define SO_NO_CHECK 11
+#define SO_PRIORITY 12
+#define SO_LINGER 13
+#define SO_BSDCOMPAT 14
+/* To add :#define SO_REUSEPORT 15 */
+#define SO_PASSCRED 16
+#define SO_PEERCRED 17
+#define SO_RCVLOWAT 18
+#define SO_SNDLOWAT 19
+#define SO_RCVTIMEO 20
+#define SO_SNDTIMEO 21
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION 22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
+#define SO_SECURITY_ENCRYPTION_NETWORK 24
+
+#define SO_BINDTODEVICE 25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER 26
+#define SO_DETACH_FILTER 27
+
+#define SO_PEERNAME 28
+#define SO_TIMESTAMP 29
+#define SCM_TIMESTAMP SO_TIMESTAMP
+
+#define SO_ACCEPTCONN 30
+
+/* Nasty libc5 fixup - bletch */
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+/* Socket types. */
+#define SOCK_STREAM 1 /* stream (connection) socket */
+#define SOCK_DGRAM 2 /* datagram (conn.less) socket */
+#define SOCK_RAW 3 /* raw socket */
+#define SOCK_RDM 4 /* reliably-delivered message */
+#define SOCK_SEQPACKET 5 /* sequential packet socket */
+#define SOCK_PACKET 10 /* linux specific way of */
+ /* getting packets at the dev */
+ /* level. For writing rarp and */
+ /* other similar things on the */
+ /* user level. */
+#define SOCK_MAX (SOCK_PACKET+1)
+#endif
+
+#endif /* _ASM_SOCKET_H */
--- /dev/null
+#ifndef __ARCH_I386_SOCKIOS__
+#define __ARCH_I386_SOCKIOS__
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN 0x8901
+#define SIOCSPGRP 0x8902
+#define FIOGETOWN 0x8903
+#define SIOCGPGRP 0x8904
+#define SIOCATMARK 0x8905
+#define SIOCGSTAMP 0x8906 /* Get stamp */
+
+#endif
--- /dev/null
+#ifndef __ASM_SOFTIRQ_H
+#define __ASM_SOFTIRQ_H
+
+#include <asm/atomic.h>
+#include <asm/hardirq.h>
+
+#define __cpu_bh_enable(cpu) \
+ do { barrier(); local_bh_count(cpu)--; } while (0)
+#define cpu_bh_disable(cpu) \
+ do { local_bh_count(cpu)++; barrier(); } while (0)
+
+#define local_bh_disable() cpu_bh_disable(smp_processor_id())
+#define __local_bh_enable() __cpu_bh_enable(smp_processor_id())
+
+#define in_softirq() (local_bh_count(smp_processor_id()) != 0)
+
+/*
+ * NOTE: this assembly code assumes:
+ *
+ * (char *)&local_bh_count - 8 == (char *)&softirq_pending
+ *
+ * If you change the offsets in irq_stat then you have to
+ * update this code as well.
+ */
+#define local_bh_enable() \
+do { \
+ unsigned int *ptr = &local_bh_count(smp_processor_id()); \
+ \
+ barrier(); \
+ if (!--*ptr) \
+ __asm__ __volatile__ ( \
+ "cmpl $0, -8(%0);" \
+ "jnz 2f;" \
+ "1:;" \
+ \
+ ".section .text.lock,\"ax\";" \
+ "2: pushl %%eax; pushl %%ecx; pushl %%edx;" \
+ "call %c1;" \
+ "popl %%edx; popl %%ecx; popl %%eax;" \
+ "jmp 1b;" \
+ ".previous;" \
+ \
+ : /* no output */ \
+ : "r" (ptr), "i" (do_softirq) \
+ /* no registers clobbered */ ); \
+} while (0)
+
+#endif /* __ASM_SOFTIRQ_H */
--- /dev/null
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <linux/config.h>
+
+extern int printk(const char * fmt, ...)
+ __attribute__ ((format (printf, 1, 2)));
+
+/* It seems that people are forgetting to
+ * initialize their spinlocks properly, tsk tsk.
+ * Remember to turn this off in 2.4. -ben
+ */
+#if defined(CONFIG_DEBUG_SPINLOCK)
+#define SPINLOCK_DEBUG 1
+#else
+#define SPINLOCK_DEBUG 0
+#endif
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ */
+
+typedef struct {
+ volatile unsigned int lock;
+#if SPINLOCK_DEBUG
+ unsigned magic;
+#endif
+} spinlock_t;
+
+#define SPINLOCK_MAGIC 0xdead4ead
+
+#if SPINLOCK_DEBUG
+#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC
+#else
+#define SPINLOCK_MAGIC_INIT /* */
+#endif
+
+#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT }
+
+#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0)
+
+/*
+ * Simple spin lock operations. There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * We make no fairness assumptions. They have a cost.
+ */
+
+#define spin_is_locked(x) (*(volatile char *)(&(x)->lock) <= 0)
+#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x))
+
+#define spin_lock_string \
+ "\n1:\t" \
+ "lock ; decb %0\n\t" \
+ "js 2f\n" \
+ ".section .text.lock,\"ax\"\n" \
+ "2:\t" \
+ "cmpb $0,%0\n\t" \
+ "rep;nop\n\t" \
+ "jle 2b\n\t" \
+ "jmp 1b\n" \
+ ".previous"
+
+/*
+ * This works. Despite all the confusion.
+ * (except on PPro SMP or if we are using OOSTORE)
+ * (PPro errata 66, 92)
+ */
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define spin_unlock_string \
+ "movb $1,%0" \
+ :"=m" (lock->lock) : : "memory"
+
+
+static inline void spin_unlock(spinlock_t *lock)
+{
+#if SPINLOCK_DEBUG
+ if (lock->magic != SPINLOCK_MAGIC)
+ BUG();
+ if (!spin_is_locked(lock))
+ BUG();
+#endif
+ __asm__ __volatile__(
+ spin_unlock_string
+ );
+}
+
+#else
+
+#define spin_unlock_string \
+ "xchgb %b0, %1" \
+ :"=q" (oldval), "=m" (lock->lock) \
+ :"0" (oldval) : "memory"
+
+static inline void spin_unlock(spinlock_t *lock)
+{
+ char oldval = 1;
+#if SPINLOCK_DEBUG
+ if (lock->magic != SPINLOCK_MAGIC)
+ BUG();
+ if (!spin_is_locked(lock))
+ BUG();
+#endif
+ __asm__ __volatile__(
+ spin_unlock_string
+ );
+}
+
+#endif
+
+static inline int spin_trylock(spinlock_t *lock)
+{
+ char oldval;
+ __asm__ __volatile__(
+ "xchgb %b0,%1"
+ :"=q" (oldval), "=m" (lock->lock)
+ :"0" (0) : "memory");
+ return oldval > 0;
+}
+
+static inline void spin_lock(spinlock_t *lock)
+{
+#if SPINLOCK_DEBUG
+ __label__ here;
+here:
+ if (lock->magic != SPINLOCK_MAGIC) {
+printk("eip: %p\n", &&here);
+ BUG();
+ }
+#endif
+ __asm__ __volatile__(
+ spin_lock_string
+ :"=m" (lock->lock) : : "memory");
+}
+
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts
+ * but no interrupt writers. For those circumstances we
+ * can "mix" irq-safe locks - any writer needs to get a
+ * irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ */
+typedef struct {
+ volatile unsigned int lock;
+#if SPINLOCK_DEBUG
+ unsigned magic;
+#endif
+} rwlock_t;
+
+#define RWLOCK_MAGIC 0xdeaf1eed
+
+#if SPINLOCK_DEBUG
+#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC
+#else
+#define RWLOCK_MAGIC_INIT /* */
+#endif
+
+#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT }
+
+#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0)
+
+/*
+ * On x86, we implement read-write locks as a 32-bit counter
+ * with the high bit (sign) being the "contended" bit.
+ *
+ * The inline assembly is non-obvious. Think about it.
+ *
+ * Changed to use the same technique as rw semaphores. See
+ * semaphore.h for details. -ben
+ */
+/* the spinlock helpers are in arch/i386/kernel/semaphore.c */
+
+static inline void read_lock(rwlock_t *rw)
+{
+#if SPINLOCK_DEBUG
+ if (rw->magic != RWLOCK_MAGIC)
+ BUG();
+#endif
+ __build_read_lock(rw, "__read_lock_failed");
+}
+
+static inline void write_lock(rwlock_t *rw)
+{
+#if SPINLOCK_DEBUG
+ if (rw->magic != RWLOCK_MAGIC)
+ BUG();
+#endif
+ __build_write_lock(rw, "__write_lock_failed");
+}
+
+#define read_unlock(rw) asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory")
+#define write_unlock(rw) asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory")
+
+static inline int write_trylock(rwlock_t *lock)
+{
+ atomic_t *count = (atomic_t *)lock;
+ if (atomic_sub_and_test(RW_LOCK_BIAS, count))
+ return 1;
+ atomic_add(RW_LOCK_BIAS, count);
+ return 0;
+}
+
+#endif /* __ASM_SPINLOCK_H */
--- /dev/null
+#ifndef _I386_STAT_H
+#define _I386_STAT_H
+
+struct __old_kernel_stat {
+ unsigned short st_dev;
+ unsigned short st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+ unsigned short st_rdev;
+ unsigned long st_size;
+ unsigned long st_atime;
+ unsigned long st_mtime;
+ unsigned long st_ctime;
+};
+
+struct stat {
+ unsigned short st_dev;
+ unsigned short __pad1;
+ unsigned long st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+ unsigned short st_rdev;
+ unsigned short __pad2;
+ unsigned long st_size;
+ unsigned long st_blksize;
+ unsigned long st_blocks;
+ unsigned long st_atime;
+ unsigned long __unused1;
+ unsigned long st_mtime;
+ unsigned long __unused2;
+ unsigned long st_ctime;
+ unsigned long __unused3;
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+
+/* This matches struct stat64 in glibc2.1, hence the absolutely
+ * insane amounts of padding around dev_t's.
+ */
+struct stat64 {
+ unsigned short st_dev;
+ unsigned char __pad0[10];
+
+#define STAT64_HAS_BROKEN_ST_INO 1
+ unsigned long __st_ino;
+
+ unsigned int st_mode;
+ unsigned int st_nlink;
+
+ unsigned long st_uid;
+ unsigned long st_gid;
+
+ unsigned short st_rdev;
+ unsigned char __pad3[10];
+
+ long long st_size;
+ unsigned long st_blksize;
+
+ unsigned long st_blocks; /* Number 512-byte blocks allocated. */
+ unsigned long __pad4; /* future possible st_blocks high bits */
+
+ unsigned long st_atime;
+ unsigned long __pad5;
+
+ unsigned long st_mtime;
+ unsigned long __pad6;
+
+ unsigned long st_ctime;
+ unsigned long __pad7; /* will be high 32 bits of ctime someday */
+
+ unsigned long long st_ino;
+};
+
+#endif
--- /dev/null
+#ifndef _I386_STATFS_H
+#define _I386_STATFS_H
+
+#ifndef __KERNEL_STRICT_NAMES
+
+#include <linux/types.h>
+
+typedef __kernel_fsid_t fsid_t;
+
+#endif
+
+struct statfs {
+ long f_type;
+ long f_bsize;
+ long f_blocks;
+ long f_bfree;
+ long f_bavail;
+ long f_files;
+ long f_ffree;
+ __kernel_fsid_t f_fsid;
+ long f_namelen;
+ long f_spare[6];
+};
+
+#endif
--- /dev/null
+#ifndef _I386_STRING_I486_H_
+#define _I386_STRING_I486_H_
+
+/*
+ * This string-include defines all string functions as inline
+ * functions. Use gcc. It also assumes ds=es=data space, this should be
+ * normal. Most of the string-functions are rather heavily hand-optimized,
+ * see especially strtok,strstr,str[c]spn. They should work, but are not
+ * very easy to understand. Everything is done entirely within the register
+ * set, making the functions fast and clean.
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Revised and optimized for i486/pentium
+ * 1994/03/15 by Alberto Vignani/Davide Parodi @crf.it
+ *
+ * Split into 2 CPU specific files by Alan Cox to keep #ifdef noise down.
+ *
+ * 1999/10/5 Proper register args for newer GCCs and minor bugs
+ * fixed - Petko Manolov (petkan@spct.net)
+ * 1999/10/14 3DNow memscpy() added - Petkan
+ * 2000/05/09 extern changed to static in function definitions
+ * and a few cleanups - Petkan
+ */
+
+#define __HAVE_ARCH_STRCPY
+static inline char * strcpy(char * dest,const char *src)
+{
+register char *tmp= (char *)dest;
+register char dummy;
+__asm__ __volatile__(
+ "\n1:\t"
+ "movb (%0),%2\n\t"
+ "incl %0\n\t"
+ "movb %2,(%1)\n\t"
+ "incl %1\n\t"
+ "testb %2,%2\n\t"
+ "jne 1b"
+ :"=r" (src), "=r" (tmp), "=q" (dummy)
+ :"0" (src), "1" (tmp)
+ :"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCPY
+static inline char * strncpy(char * dest,const char *src,size_t count)
+{
+register char *tmp= (char *)dest;
+register char dummy;
+if (count) {
+__asm__ __volatile__(
+ "\n1:\t"
+ "movb (%0),%2\n\t"
+ "incl %0\n\t"
+ "movb %2,(%1)\n\t"
+ "incl %1\n\t"
+ "decl %3\n\t"
+ "je 3f\n\t"
+ "testb %2,%2\n\t"
+ "jne 1b\n\t"
+ "2:\tmovb %2,(%1)\n\t"
+ "incl %1\n\t"
+ "decl %3\n\t"
+ "jne 2b\n\t"
+ "3:"
+ :"=r" (src), "=r" (tmp), "=q" (dummy), "=r" (count)
+ :"0" (src), "1" (tmp), "3" (count)
+ :"memory");
+ } /* if (count) */
+return dest;
+}
+
+#define __HAVE_ARCH_STRCAT
+static inline char * strcat(char * dest,const char * src)
+{
+register char *tmp = (char *)(dest-1);
+register char dummy;
+__asm__ __volatile__(
+ "\n1:\tincl %1\n\t"
+ "cmpb $0,(%1)\n\t"
+ "jne 1b\n"
+ "2:\tmovb (%2),%b0\n\t"
+ "incl %2\n\t"
+ "movb %b0,(%1)\n\t"
+ "incl %1\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 2b\n"
+ :"=q" (dummy), "=r" (tmp), "=r" (src)
+ :"1" (tmp), "2" (src)
+ :"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCAT
+static inline char * strncat(char * dest,const char * src,size_t count)
+{
+register char *tmp = (char *)(dest-1);
+register char dummy;
+__asm__ __volatile__(
+ "\n1:\tincl %1\n\t"
+ "cmpb $0,(%1)\n\t"
+ "jne 1b\n"
+ "2:\tdecl %3\n\t"
+ "js 3f\n\t"
+ "movb (%2),%b0\n\t"
+ "incl %2\n\t"
+ "movb %b0,(%1)\n\t"
+ "incl %1\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 2b\n"
+ "3:\txorb %0,%0\n\t"
+ "movb %b0,(%1)\n\t"
+ :"=q" (dummy), "=r" (tmp), "=r" (src), "=r" (count)
+ :"1" (tmp), "2" (src), "3" (count)
+ :"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRCMP
+static inline int strcmp(const char * cs,const char * ct)
+{
+register int __res;
+__asm__ __volatile__(
+ "\n1:\tmovb (%1),%b0\n\t"
+ "incl %1\n\t"
+ "cmpb %b0,(%2)\n\t"
+ "jne 2f\n\t"
+ "incl %2\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 1b\n\t"
+ "xorl %0,%0\n\t"
+ "jmp 3f\n"
+ "2:\tmovl $1,%0\n\t"
+ "jb 3f\n\t"
+ "negl %0\n"
+ "3:"
+ :"=q" (__res), "=r" (cs), "=r" (ct)
+ :"1" (cs), "2" (ct)
+ : "memory" );
+return __res;
+}
+
+#define __HAVE_ARCH_STRNCMP
+static inline int strncmp(const char * cs,const char * ct,size_t count)
+{
+register int __res;
+__asm__ __volatile__(
+ "\n1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "movb (%1),%b0\n\t"
+ "incl %1\n\t"
+ "cmpb %b0,(%2)\n\t"
+ "jne 3f\n\t"
+ "incl %2\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 1b\n"
+ "2:\txorl %0,%0\n\t"
+ "jmp 4f\n"
+ "3:\tmovl $1,%0\n\t"
+ "jb 4f\n\t"
+ "negl %0\n"
+ "4:"
+ :"=q" (__res), "=r" (cs), "=r" (ct), "=r" (count)
+ :"1" (cs), "2" (ct), "3" (count));
+return __res;
+}
+
+#define __HAVE_ARCH_STRCHR
+static inline char * strchr(const char * s, int c)
+{
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tmovb (%1),%%al\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "je 2f\n\t"
+ "incl %1\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "xorl %1,%1\n"
+ "2:\tmovl %1,%0\n\t"
+ :"=a" (__res), "=r" (s)
+ :"0" (c), "1" (s));
+return __res;
+}
+
+#define __HAVE_ARCH_STRRCHR
+static inline char * strrchr(const char * s, int c)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "jne 2f\n\t"
+ "leal -1(%%esi),%0\n"
+ "2:\ttestb %%al,%%al\n\t"
+ "jne 1b"
+ :"=d" (__res), "=&S" (d0), "=&a" (d1)
+ :"0" (0), "1" (s), "2" (c));
+return __res;
+}
+
+
+#define __HAVE_ARCH_STRCSPN
+static inline size_t strcspn(const char * cs, const char * ct)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movl %6,%%edi\n\t"
+ "repne\n\t"
+ "scasb\n\t"
+ "notl %%ecx\n\t"
+ "decl %%ecx\n\t"
+ "movl %%ecx,%%edx\n"
+ "1:\tlodsb\n\t"
+ "testb %%al,%%al\n\t"
+ "je 2f\n\t"
+ "movl %6,%%edi\n\t"
+ "movl %%edx,%%ecx\n\t"
+ "repne\n\t"
+ "scasb\n\t"
+ "jne 1b\n"
+ "2:\tdecl %0"
+ :"=S" (__res), "=&a" (d0), "=&c" (d1)
+ :"0" (cs), "1" (0), "2" (0xffffffff), "g" (ct)
+ :"dx", "di");
+return __res-cs;
+}
+
+
+#define __HAVE_ARCH_STRLEN
+static inline size_t strlen(const char * s)
+{
+/*
+ * slightly slower on a 486, but with better chances of
+ * register allocation
+ */
+register char dummy, *tmp= (char *)s;
+__asm__ __volatile__(
+ "\n1:\t"
+ "movb\t(%0),%1\n\t"
+ "incl\t%0\n\t"
+ "testb\t%1,%1\n\t"
+ "jne\t1b"
+ :"=r" (tmp),"=q" (dummy)
+ :"0" (s)
+ : "memory" );
+return (tmp-s-1);
+}
+
+/* Added by Gertjan van Wingerde to make minix and sysv module work */
+#define __HAVE_ARCH_STRNLEN
+static inline size_t strnlen(const char * s, size_t count)
+{
+int d0;
+register int __res;
+__asm__ __volatile__(
+ "movl %3,%0\n\t"
+ "jmp 2f\n"
+ "1:\tcmpb $0,(%0)\n\t"
+ "je 3f\n\t"
+ "incl %0\n"
+ "2:\tdecl %2\n\t"
+ "cmpl $-1,%2\n\t"
+ "jne 1b\n"
+ "3:\tsubl %3,%0"
+ :"=a" (__res), "=&d" (d0)
+ :"1" (count), "c" (s));
+return __res;
+}
+/* end of additional stuff */
+
+
+/*
+ * These ought to get tweaked to do some cache priming.
+ */
+
+static inline void * __memcpy_by4(void * to, const void * from, size_t n)
+{
+register void *tmp = (void *)to;
+register int dummy1,dummy2;
+__asm__ __volatile__ (
+ "\n1:\tmovl (%2),%0\n\t"
+ "addl $4,%2\n\t"
+ "movl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %3\n\t"
+ "jnz 1b"
+ :"=r" (dummy1), "=r" (tmp), "=r" (from), "=r" (dummy2)
+ :"1" (tmp), "2" (from), "3" (n/4)
+ :"memory");
+return (to);
+}
+
+static inline void * __memcpy_by2(void * to, const void * from, size_t n)
+{
+register void *tmp = (void *)to;
+register int dummy1,dummy2;
+__asm__ __volatile__ (
+ "shrl $1,%3\n\t"
+ "jz 2f\n" /* only a word */
+ "1:\tmovl (%2),%0\n\t"
+ "addl $4,%2\n\t"
+ "movl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %3\n\t"
+ "jnz 1b\n"
+ "2:\tmovw (%2),%w0\n\t"
+ "movw %w0,(%1)"
+ :"=r" (dummy1), "=r" (tmp), "=r" (from), "=r" (dummy2)
+ :"1" (tmp), "2" (from), "3" (n/2)
+ :"memory");
+return (to);
+}
+
+static inline void * __memcpy_g(void * to, const void * from, size_t n)
+{
+int d0, d1, d2;
+register void *tmp = (void *)to;
+__asm__ __volatile__ (
+ "shrl $1,%%ecx\n\t"
+ "jnc 1f\n\t"
+ "movsb\n"
+ "1:\tshrl $1,%%ecx\n\t"
+ "jnc 2f\n\t"
+ "movsw\n"
+ "2:\trep\n\t"
+ "movsl"
+ :"=&c" (d0), "=&D" (d1), "=&S" (d2)
+ :"0" (n), "1" ((long) tmp), "2" ((long) from)
+ :"memory");
+return (to);
+}
+
+#define __memcpy_c(d,s,count) \
+((count%4==0) ? \
+ __memcpy_by4((d),(s),(count)) : \
+ ((count%2==0) ? \
+ __memcpy_by2((d),(s),(count)) : \
+ __memcpy_g((d),(s),(count))))
+
+#define __memcpy(d,s,count) \
+(__builtin_constant_p(count) ? \
+ __memcpy_c((d),(s),(count)) : \
+ __memcpy_g((d),(s),(count)))
+
+#define __HAVE_ARCH_MEMCPY
+
+#include <linux/config.h>
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+/*
+** This CPU favours 3DNow strongly (eg AMD K6-II, K6-III, Athlon)
+*/
+
+static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+{
+ if (len < 512)
+ return __memcpy_c(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+static inline void *__memcpy3d(void *to, const void *from, size_t len)
+{
+ if(len < 512)
+ return __memcpy_g(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+#define memcpy(d, s, count) \
+(__builtin_constant_p(count) ? \
+ __constant_memcpy3d((d),(s),(count)) : \
+ __memcpy3d((d),(s),(count)))
+
+#else /* CONFIG_X86_USE_3DNOW */
+
+/*
+** Generic routines
+*/
+
+
+#define memcpy(d, s, count) __memcpy(d, s, count)
+
+#endif /* CONFIG_X86_USE_3DNOW */
+
+
+extern void __struct_cpy_bug( void );
+
+#define struct_cpy(x,y) \
+({ \
+ if (sizeof(*(x)) != sizeof(*(y))) \
+ __struct_cpy_bug; \
+ memcpy(x, y, sizeof(*(x))); \
+})
+
+
+#define __HAVE_ARCH_MEMMOVE
+static inline void * memmove(void * dest,const void * src, size_t n)
+{
+int d0, d1, d2;
+register void *tmp = (void *)dest;
+if (dest<src)
+__asm__ __volatile__ (
+ "rep\n\t"
+ "movsb"
+ :"=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n), "1" (src), "2" (tmp)
+ :"memory");
+else
+__asm__ __volatile__ (
+ "std\n\t"
+ "rep\n\t"
+ "movsb\n\t"
+ "cld"
+ :"=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n), "1" (n-1+(const char *)src), "2" (n-1+(char *)tmp)
+ :"memory");
+return dest;
+}
+
+
+#define __HAVE_ARCH_MEMCMP
+static inline int memcmp(const void * cs,const void * ct,size_t count)
+{
+int d0, d1, d2;
+register int __res;
+__asm__ __volatile__(
+ "repe\n\t"
+ "cmpsb\n\t"
+ "je 1f\n\t"
+ "sbbl %0,%0\n\t"
+ "orb $1,%b0\n"
+ "1:"
+ :"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+ :"0" (0), "1" (cs), "2" (ct), "3" (count));
+return __res;
+}
+
+
+#define __HAVE_ARCH_MEMCHR
+static inline void * memchr(const void * cs,int c,size_t count)
+{
+int d0;
+register void * __res;
+if (!count)
+ return NULL;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "je 1f\n\t"
+ "movl $1,%0\n"
+ "1:\tdecl %0"
+ :"=D" (__res), "=&c" (d0)
+ :"a" (c), "0" (cs), "1" (count));
+return __res;
+}
+
+#define __memset_cc(s,c,count) \
+((count%4==0) ? \
+ __memset_cc_by4((s),(c),(count)) : \
+ ((count%2==0) ? \
+ __memset_cc_by2((s),(c),(count)) : \
+ __memset_cg((s),(c),(count))))
+
+#define __memset_gc(s,c,count) \
+((count%4==0) ? \
+ __memset_gc_by4((s),(c),(count)) : \
+ ((count%2==0) ? \
+ __memset_gc_by2((s),(c),(count)) : \
+ __memset_gg((s),(c),(count))))
+
+#define __HAVE_ARCH_MEMSET
+#define memset(s,c,count) \
+(__builtin_constant_p(c) ? \
+ (__builtin_constant_p(count) ? \
+ __memset_cc((s),(c),(count)) : \
+ __memset_cg((s),(c),(count))) : \
+ (__builtin_constant_p(count) ? \
+ __memset_gc((s),(c),(count)) : \
+ __memset_gg((s),(c),(count))))
+
+static inline void * __memset_cc_by4(void * s, char c, size_t count)
+{
+/*
+ * register char *tmp = s;
+ */
+register char *tmp = (char *)s;
+register int dummy;
+__asm__ __volatile__ (
+ "\n1:\tmovl %2,(%0)\n\t"
+ "addl $4,%0\n\t"
+ "decl %1\n\t"
+ "jnz 1b"
+ :"=r" (tmp), "=r" (dummy)
+ :"q" (0x01010101UL * (unsigned char) c), "0" (tmp), "1" (count/4)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_cc_by2(void * s, char c, size_t count)
+{
+register void *tmp = (void *)s;
+register int dummy;
+__asm__ __volatile__ (
+ "shrl $1,%1\n\t" /* may be divisible also by 4 */
+ "jz 2f\n"
+ "\n1:\tmovl %2,(%0)\n\t"
+ "addl $4,%0\n\t"
+ "decl %1\n\t"
+ "jnz 1b\n"
+ "2:\tmovw %w2,(%0)"
+ :"=r" (tmp), "=r" (dummy)
+ :"q" (0x01010101UL * (unsigned char) c), "0" (tmp), "1" (count/2)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_gc_by4(void * s, char c, size_t count)
+{
+register void *tmp = (void *)s;
+register int dummy;
+__asm__ __volatile__ (
+ "movb %b0,%h0\n"
+ "pushw %w0\n\t"
+ "shll $16,%0\n\t"
+ "popw %w0\n"
+ "1:\tmovl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %2\n\t"
+ "jnz 1b\n"
+ :"=q" (c), "=r" (tmp), "=r" (dummy)
+ :"0" ((unsigned) c), "1" (tmp), "2" (count/4)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_gc_by2(void * s, char c, size_t count)
+{
+register void *tmp = (void *)s;
+register int dummy1,dummy2;
+__asm__ __volatile__ (
+ "movb %b0,%h0\n\t"
+ "shrl $1,%2\n\t" /* may be divisible also by 4 */
+ "jz 2f\n\t"
+ "pushw %w0\n\t"
+ "shll $16,%0\n\t"
+ "popw %w0\n"
+ "1:\tmovl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %2\n\t"
+ "jnz 1b\n"
+ "2:\tmovw %w0,(%1)"
+ :"=q" (dummy1), "=r" (tmp), "=r" (dummy2)
+ :"0" ((unsigned) c), "1" (tmp), "2" (count/2)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_cg(void * s, char c, size_t count)
+{
+int d0, d1;
+register void *tmp = (void *)s;
+__asm__ __volatile__ (
+ "shrl $1,%%ecx\n\t"
+ "rep\n\t"
+ "stosw\n\t"
+ "jnc 1f\n\t"
+ "movb %%al,(%%edi)\n"
+ "1:"
+ :"=&c" (d0), "=&D" (d1)
+ :"a" (0x0101U * (unsigned char) c), "0" (count), "1" (tmp)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_gg(void * s,char c,size_t count)
+{
+int d0, d1, d2;
+register void *tmp = (void *)s;
+__asm__ __volatile__ (
+ "movb %%al,%%ah\n\t"
+ "shrl $1,%%ecx\n\t"
+ "rep\n\t"
+ "stosw\n\t"
+ "jnc 1f\n\t"
+ "movb %%al,(%%edi)\n"
+ "1:"
+ :"=&c" (d0), "=&D" (d1), "=&D" (d2)
+ :"0" (count), "1" (tmp), "2" (c)
+ :"memory");
+return s;
+}
+
+
+/*
+ * find the first occurrence of byte 'c', or 1 past the area if none
+ */
+#define __HAVE_ARCH_MEMSCAN
+static inline void * memscan(void * addr, int c, size_t size)
+{
+ if (!size)
+ return addr;
+ __asm__("repnz; scasb
+ jnz 1f
+ dec %%edi
+1: "
+ : "=D" (addr), "=c" (size)
+ : "0" (addr), "1" (size), "a" (c));
+ return addr;
+}
+
+#endif
--- /dev/null
+#ifndef _I386_STRING_H_
+#define _I386_STRING_H_
+
+#ifdef __KERNEL__
+#include <linux/config.h>
+/*
+ * On a 486 or Pentium, we are better off not using the
+ * byte string operations. But on a 386 or a PPro the
+ * byte string ops are faster than doing it by hand
+ * (MUCH faster on a Pentium).
+ *
+ * Also, the byte strings actually work correctly. Forget
+ * the i486 routines for now as they may be broken..
+ */
+#if FIXED_486_STRING && defined(CONFIG_X86_USE_STRING_486)
+#include <asm/string-486.h>
+#else
+
+/*
+ * This string-include defines all string functions as inline
+ * functions. Use gcc. It also assumes ds=es=data space, this should be
+ * normal. Most of the string-functions are rather heavily hand-optimized,
+ * see especially strtok,strstr,str[c]spn. They should work, but are not
+ * very easy to understand. Everything is done entirely within the register
+ * set, making the functions fast and clean. String instructions have been
+ * used through-out, making for "slightly" unclear code :-)
+ *
+ * NO Copyright (C) 1991, 1992 Linus Torvalds,
+ * consider these trivial functions to be PD.
+ */
+
+#define __HAVE_ARCH_STRCPY
+static inline char * strcpy(char * dest,const char *src)
+{
+int d0, d1, d2;
+__asm__ __volatile__(
+ "1:\tlodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2)
+ :"0" (src),"1" (dest) : "memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCPY
+static inline char * strncpy(char * dest,const char *src,size_t count)
+{
+int d0, d1, d2, d3;
+__asm__ __volatile__(
+ "1:\tdecl %2\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "rep\n\t"
+ "stosb\n"
+ "2:"
+ : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
+ :"0" (src),"1" (dest),"2" (count) : "memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRCAT
+static inline char * strcat(char * dest,const char * src)
+{
+int d0, d1, d2, d3;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "decl %1\n"
+ "1:\tlodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+ : "0" (src), "1" (dest), "2" (0), "3" (0xffffffff):"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCAT
+static inline char * strncat(char * dest,const char * src,size_t count)
+{
+int d0, d1, d2, d3;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "decl %1\n\t"
+ "movl %8,%3\n"
+ "1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n"
+ "2:\txorl %2,%2\n\t"
+ "stosb"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+ : "0" (src),"1" (dest),"2" (0),"3" (0xffffffff), "g" (count)
+ : "memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRCMP
+static inline int strcmp(const char * cs,const char * ct)
+{
+int d0, d1;
+register int __res;
+__asm__ __volatile__(
+ "1:\tlodsb\n\t"
+ "scasb\n\t"
+ "jne 2f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "xorl %%eax,%%eax\n\t"
+ "jmp 3f\n"
+ "2:\tsbbl %%eax,%%eax\n\t"
+ "orb $1,%%al\n"
+ "3:"
+ :"=a" (__res), "=&S" (d0), "=&D" (d1)
+ :"1" (cs),"2" (ct));
+return __res;
+}
+
+#define __HAVE_ARCH_STRNCMP
+static inline int strncmp(const char * cs,const char * ct,size_t count)
+{
+register int __res;
+int d0, d1, d2;
+__asm__ __volatile__(
+ "1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "scasb\n\t"
+ "jne 3f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n"
+ "2:\txorl %%eax,%%eax\n\t"
+ "jmp 4f\n"
+ "3:\tsbbl %%eax,%%eax\n\t"
+ "orb $1,%%al\n"
+ "4:"
+ :"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+ :"1" (cs),"2" (ct),"3" (count));
+return __res;
+}
+
+#define __HAVE_ARCH_STRCHR
+static inline char * strchr(const char * s, int c)
+{
+int d0;
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "je 2f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "movl $1,%1\n"
+ "2:\tmovl %1,%0\n\t"
+ "decl %0"
+ :"=a" (__res), "=&S" (d0) : "1" (s),"0" (c));
+return __res;
+}
+
+#define __HAVE_ARCH_STRRCHR
+static inline char * strrchr(const char * s, int c)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "jne 2f\n\t"
+ "leal -1(%%esi),%0\n"
+ "2:\ttestb %%al,%%al\n\t"
+ "jne 1b"
+ :"=g" (__res), "=&S" (d0), "=&a" (d1) :"0" (0),"1" (s),"2" (c));
+return __res;
+}
+
+#define __HAVE_ARCH_STRLEN
+static inline size_t strlen(const char * s)
+{
+int d0;
+register int __res;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "notl %0\n\t"
+ "decl %0"
+ :"=c" (__res), "=&D" (d0) :"1" (s),"a" (0), "0" (0xffffffff));
+return __res;
+}
+
+static inline void * __memcpy(void * to, const void * from, size_t n)
+{
+int d0, d1, d2;
+__asm__ __volatile__(
+ "rep ; movsl\n\t"
+ "testb $2,%b4\n\t"
+ "je 1f\n\t"
+ "movsw\n"
+ "1:\ttestb $1,%b4\n\t"
+ "je 2f\n\t"
+ "movsb\n"
+ "2:"
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+ :"0" (n/4), "q" (n),"1" ((long) to),"2" ((long) from)
+ : "memory");
+return (to);
+}
+
+/*
+ * This looks horribly ugly, but the compiler can optimize it totally,
+ * as the count is constant.
+ */
+static inline void * __constant_memcpy(void * to, const void * from, size_t n)
+{
+ switch (n) {
+ case 0:
+ return to;
+ case 1:
+ *(unsigned char *)to = *(const unsigned char *)from;
+ return to;
+ case 2:
+ *(unsigned short *)to = *(const unsigned short *)from;
+ return to;
+ case 3:
+ *(unsigned short *)to = *(const unsigned short *)from;
+ *(2+(unsigned char *)to) = *(2+(const unsigned char *)from);
+ return to;
+ case 4:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ return to;
+ case 6: /* for Ethernet addresses */
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(2+(unsigned short *)to) = *(2+(const unsigned short *)from);
+ return to;
+ case 8:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ return to;
+ case 12:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
+ return to;
+ case 16:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
+ *(3+(unsigned long *)to) = *(3+(const unsigned long *)from);
+ return to;
+ case 20:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
+ *(3+(unsigned long *)to) = *(3+(const unsigned long *)from);
+ *(4+(unsigned long *)to) = *(4+(const unsigned long *)from);
+ return to;
+ }
+#define COMMON(x) \
+__asm__ __volatile__( \
+ "rep ; movsl" \
+ x \
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2) \
+ : "0" (n/4),"1" ((long) to),"2" ((long) from) \
+ : "memory");
+{
+ int d0, d1, d2;
+ switch (n % 4) {
+ case 0: COMMON(""); return to;
+ case 1: COMMON("\n\tmovsb"); return to;
+ case 2: COMMON("\n\tmovsw"); return to;
+ default: COMMON("\n\tmovsw\n\tmovsb"); return to;
+ }
+}
+
+#undef COMMON
+}
+
+#define __HAVE_ARCH_MEMCPY
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+/*
+ * This CPU favours 3DNow strongly (eg AMD Athlon)
+ */
+
+static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+{
+ if (len < 512)
+ return __constant_memcpy(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
+{
+ if (len < 512)
+ return __memcpy(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+#define memcpy(t, f, n) \
+(__builtin_constant_p(n) ? \
+ __constant_memcpy3d((t),(f),(n)) : \
+ __memcpy3d((t),(f),(n)))
+
+#else
+
+/*
+ * No 3D Now!
+ */
+
+#define memcpy(t, f, n) \
+(__builtin_constant_p(n) ? \
+ __constant_memcpy((t),(f),(n)) : \
+ __memcpy((t),(f),(n)))
+
+#endif
+
+/*
+ * struct_cpy(x,y), copy structure *x into (matching structure) *y.
+ *
+ * We get link-time errors if the structure sizes do not match.
+ * There is no runtime overhead, it's all optimized away at
+ * compile time.
+ */
+extern void __struct_cpy_bug (void);
+
+#define struct_cpy(x,y) \
+({ \
+ if (sizeof(*(x)) != sizeof(*(y))) \
+ __struct_cpy_bug; \
+ memcpy(x, y, sizeof(*(x))); \
+})
+
+#define __HAVE_ARCH_MEMMOVE
+static inline void * memmove(void * dest,const void * src, size_t n)
+{
+int d0, d1, d2;
+if (dest<src)
+__asm__ __volatile__(
+ "rep\n\t"
+ "movsb"
+ : "=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n),"1" (src),"2" (dest)
+ : "memory");
+else
+__asm__ __volatile__(
+ "std\n\t"
+ "rep\n\t"
+ "movsb\n\t"
+ "cld"
+ : "=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n),
+ "1" (n-1+(const char *)src),
+ "2" (n-1+(char *)dest)
+ :"memory");
+return dest;
+}
+
+#define memcmp __builtin_memcmp
+
+#define __HAVE_ARCH_MEMCHR
+static inline void * memchr(const void * cs,int c,size_t count)
+{
+int d0;
+register void * __res;
+if (!count)
+ return NULL;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "je 1f\n\t"
+ "movl $1,%0\n"
+ "1:\tdecl %0"
+ :"=D" (__res), "=&c" (d0) : "a" (c),"0" (cs),"1" (count));
+return __res;
+}
+
+static inline void * __memset_generic(void * s, char c,size_t count)
+{
+int d0, d1;
+__asm__ __volatile__(
+ "rep\n\t"
+ "stosb"
+ : "=&c" (d0), "=&D" (d1)
+ :"a" (c),"1" (s),"0" (count)
+ :"memory");
+return s;
+}
+
+/* we might want to write optimized versions of these later */
+#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
+
+/*
+ * memset(x,0,y) is a reasonably common thing to do, so we want to fill
+ * things 32 bits at a time even when we don't know the size of the
+ * area at compile-time..
+ */
+static inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
+{
+int d0, d1;
+__asm__ __volatile__(
+ "rep ; stosl\n\t"
+ "testb $2,%b3\n\t"
+ "je 1f\n\t"
+ "stosw\n"
+ "1:\ttestb $1,%b3\n\t"
+ "je 2f\n\t"
+ "stosb\n"
+ "2:"
+ : "=&c" (d0), "=&D" (d1)
+ :"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
+ :"memory");
+return (s);
+}
+
+/* Added by Gertjan van Wingerde to make minix and sysv module work */
+#define __HAVE_ARCH_STRNLEN
+static inline size_t strnlen(const char * s, size_t count)
+{
+int d0;
+register int __res;
+__asm__ __volatile__(
+ "movl %2,%0\n\t"
+ "jmp 2f\n"
+ "1:\tcmpb $0,(%0)\n\t"
+ "je 3f\n\t"
+ "incl %0\n"
+ "2:\tdecl %1\n\t"
+ "cmpl $-1,%1\n\t"
+ "jne 1b\n"
+ "3:\tsubl %2,%0"
+ :"=a" (__res), "=&d" (d0)
+ :"c" (s),"1" (count));
+return __res;
+}
+/* end of additional stuff */
+
+#define __HAVE_ARCH_STRSTR
+
+extern char *strstr(const char *cs, const char *ct);
+
+/*
+ * This looks horribly ugly, but the compiler can optimize it totally,
+ * as we by now know that both pattern and count is constant..
+ */
+static inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
+{
+ switch (count) {
+ case 0:
+ return s;
+ case 1:
+ *(unsigned char *)s = pattern;
+ return s;
+ case 2:
+ *(unsigned short *)s = pattern;
+ return s;
+ case 3:
+ *(unsigned short *)s = pattern;
+ *(2+(unsigned char *)s) = pattern;
+ return s;
+ case 4:
+ *(unsigned long *)s = pattern;
+ return s;
+ }
+#define COMMON(x) \
+__asm__ __volatile__( \
+ "rep ; stosl" \
+ x \
+ : "=&c" (d0), "=&D" (d1) \
+ : "a" (pattern),"0" (count/4),"1" ((long) s) \
+ : "memory")
+{
+ int d0, d1;
+ switch (count % 4) {
+ case 0: COMMON(""); return s;
+ case 1: COMMON("\n\tstosb"); return s;
+ case 2: COMMON("\n\tstosw"); return s;
+ default: COMMON("\n\tstosw\n\tstosb"); return s;
+ }
+}
+
+#undef COMMON
+}
+
+#define __constant_c_x_memset(s, c, count) \
+(__builtin_constant_p(count) ? \
+ __constant_c_and_count_memset((s),(c),(count)) : \
+ __constant_c_memset((s),(c),(count)))
+
+#define __memset(s, c, count) \
+(__builtin_constant_p(count) ? \
+ __constant_count_memset((s),(c),(count)) : \
+ __memset_generic((s),(c),(count)))
+
+#define __HAVE_ARCH_MEMSET
+#define memset(s, c, count) \
+(__builtin_constant_p(c) ? \
+ __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
+ __memset((s),(c),(count)))
+
+/*
+ * find the first occurrence of byte 'c', or 1 past the area if none
+ */
+#define __HAVE_ARCH_MEMSCAN
+static inline void * memscan(void * addr, int c, size_t size)
+{
+ if (!size)
+ return addr;
+ __asm__("repnz; scasb\n\t"
+ "jnz 1f\n\t"
+ "dec %%edi\n"
+ "1:"
+ : "=D" (addr), "=c" (size)
+ : "0" (addr), "1" (size), "a" (c));
+ return addr;
+}
+
+#endif /* CONFIG_X86_USE_STRING_486 */
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/segment.h>
+#include <asm/hypervisor.h>
+#include <linux/bitops.h> /* for LOCK_PREFIX */
+
+#ifdef __KERNEL__
+
+struct task_struct; /* one of the stranger aspects of C forward declarations.. */
+extern void FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
+
+#define prepare_to_switch() do { } while(0)
+#define switch_to(prev,next,last) do { \
+ asm volatile("pushl %%esi\n\t" \
+ "pushl %%edi\n\t" \
+ "pushl %%ebp\n\t" \
+ "movl %%esp,%0\n\t" /* save ESP */ \
+ "movl %3,%%esp\n\t" /* restore ESP */ \
+ "movl $1f,%1\n\t" /* save EIP */ \
+ "pushl %4\n\t" /* restore EIP */ \
+ "jmp __switch_to\n" \
+ "1:\t" \
+ "popl %%ebp\n\t" \
+ "popl %%edi\n\t" \
+ "popl %%esi\n\t" \
+ :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \
+ "=b" (last) \
+ :"m" (next->thread.esp),"m" (next->thread.eip), \
+ "a" (prev), "d" (next), \
+ "b" (prev)); \
+} while (0)
+
+#define _set_base(addr,base) do { unsigned long __pr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %%dl,%2\n\t" \
+ "movb %%dh,%3" \
+ :"=&d" (__pr) \
+ :"m" (*((addr)+2)), \
+ "m" (*((addr)+4)), \
+ "m" (*((addr)+7)), \
+ "0" (base) \
+ ); } while(0)
+
+#define _set_limit(addr,limit) do { unsigned long __lr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %2,%%dh\n\t" \
+ "andb $0xf0,%%dh\n\t" \
+ "orb %%dh,%%dl\n\t" \
+ "movb %%dl,%2" \
+ :"=&d" (__lr) \
+ :"m" (*(addr)), \
+ "m" (*((addr)+6)), \
+ "0" (limit) \
+ ); } while(0)
+
+#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
+#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 )
+
+static inline unsigned long _get_base(char * addr)
+{
+ unsigned long __base;
+ __asm__("movb %3,%%dh\n\t"
+ "movb %2,%%dl\n\t"
+ "shll $16,%%edx\n\t"
+ "movw %1,%%dx"
+ :"=&d" (__base)
+ :"m" (*((addr)+2)),
+ "m" (*((addr)+4)),
+ "m" (*((addr)+7)));
+ return __base;
+}
+
+#define get_base(ldt) _get_base( ((char *)&(ldt)) )
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value) \
+ asm volatile("\n" \
+ "1:\t" \
+ "movl %0,%%" #seg "\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3:\t" \
+ "pushl $0\n\t" \
+ "popl %%" #seg "\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,3b\n" \
+ ".previous" \
+ : :"m" (*(unsigned int *)&(value)))
+
+#define clts() ((void)0)
+#define read_cr0() ({ \
+ unsigned int __dummy; \
+ __asm__( \
+ "movl %%cr0,%0\n\t" \
+ :"=r" (__dummy)); \
+ __dummy; \
+})
+#define write_cr0(x) \
+ __asm__("movl %0,%%cr0": :"r" (x));
+
+#define read_cr4() ({ \
+ unsigned int __dummy; \
+ __asm__( \
+ "movl %%cr4,%0\n\t" \
+ :"=r" (__dummy)); \
+ __dummy; \
+})
+#define write_cr4(x) \
+ __asm__("movl %0,%%cr4": :"r" (x));
+#define stts() (HYPERVISOR_fpu_taskswitch())
+
+#endif /* __KERNEL__ */
+
+#define wbinvd() \
+ __asm__ __volatile__ ("wbinvd": : :"memory");
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+ unsigned long __limit;
+ __asm__("lsll %1,%0"
+ :"=r" (__limit):"r" (segment));
+ return __limit+1;
+}
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+
+/*
+ * The semantics of XCHGCMP8B are a bit strange, this is why
+ * there is a loop and the loading of %%eax and %%edx has to
+ * be inside. This inlines well in most cases, the cached
+ * cost is around ~38 cycles. (in the future we might want
+ * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
+ * might have an implicit FPU-save as a cost, so it's not
+ * clear which path to go.)
+ */
+static inline void __set_64bit (unsigned long long * ptr,
+ unsigned int low, unsigned int high)
+{
+ __asm__ __volatile__ (
+ "\n1:\t"
+ "movl (%0), %%eax\n\t"
+ "movl 4(%0), %%edx\n\t"
+ "cmpxchg8b (%0)\n\t"
+ "jnz 1b"
+ : /* no outputs */
+ : "D"(ptr),
+ "b"(low),
+ "c"(high)
+ : "ax","dx","memory");
+}
+
+static inline void __set_64bit_constant (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
+}
+#define ll_low(x) *(((unsigned int*)&(x))+0)
+#define ll_high(x) *(((unsigned int*)&(x))+1)
+
+static inline void __set_64bit_var (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,ll_low(value), ll_high(value));
+}
+
+#define set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit_constant(ptr, value) : \
+ __set_64bit_var(ptr, value) )
+
+#define _set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
+ __set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ * but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("xchgb %b0,%1"
+ :"=q" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 2:
+ __asm__ __volatile__("xchgw %w0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 4:
+ __asm__ __volatile__("xchgl %0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ }
+ return x;
+}
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ unsigned long prev;
+ switch (size) {
+ case 1:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 2:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 4:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
+
+#else
+/* Compiling for a 386 proper. Is it worth implementing via cli/sti? */
+#endif
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * For now, "wmb()" doesn't actually do anything, as all
+ * Intel CPU's follow what Intel calls a *Processor Order*,
+ * in which all writes are seen in the program order even
+ * outside the CPU.
+ *
+ * I expect future Intel CPU's to have a weaker ordering,
+ * but I'd also expect them to finally get their act together
+ * and add some real memory barriers if so.
+ *
+ * Some non intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+
+#define mb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
+#define rmb() mb()
+
+#ifdef CONFIG_X86_OOSTORE
+#define wmb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
+#else
+#define wmb() __asm__ __volatile__ ("": : :"memory")
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#endif
+
+#define set_mb(var, value) do { xchg(&var, value); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+#define __save_flags(x) ((x) = HYPERVISOR_shared_info->events_enable); barrier()
+#define __restore_flags(x) \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ _shared->events_enable = (x); \
+ barrier(); \
+ if ( _shared->events && (x) ) do_hypervisor_callback(NULL); \
+} while (0)
+#define __cli() (HYPERVISOR_shared_info->events_enable = 0); barrier()
+#define __sti() \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ _shared->events_enable = 1; \
+ barrier(); \
+ if ( _shared->events ) do_hypervisor_callback(NULL); \
+} while (0)
+#define safe_halt() ((void)0)
+
+/* For spinlocks etc */
+#define local_irq_save(x) ((x) = HYPERVISOR_shared_info->events_enable); (HYPERVISOR_shared_info->events_enable = 0); barrier()
+#define local_irq_restore(x) __restore_flags(x)
+#define local_irq_disable() __cli()
+#define local_irq_enable() __sti()
+
+#ifdef CONFIG_SMP
+
+extern void __global_cli(void);
+extern void __global_sti(void);
+extern unsigned long __global_save_flags(void);
+extern void __global_restore_flags(unsigned long);
+#define cli() __global_cli()
+#define sti() __global_sti()
+#define save_flags(x) ((x)=__global_save_flags())
+#define restore_flags(x) __global_restore_flags(x)
+
+#else
+
+#define cli() __cli()
+#define sti() __sti()
+#define save_flags(x) __save_flags(x)
+#define restore_flags(x) __restore_flags(x)
+
+#endif
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+extern unsigned long dmi_broken;
+extern int is_sony_vaio_laptop;
+
+#define BROKEN_ACPI_Sx 0x0001
+#define BROKEN_INIT_AFTER_S1 0x0002
+
+#endif
--- /dev/null
+#ifndef __ARCH_I386_TERMBITS_H__
+#define __ARCH_I386_TERMBITS_H__
+
+#include <linux/posix_types.h>
+
+typedef unsigned char cc_t;
+typedef unsigned int speed_t;
+typedef unsigned int tcflag_t;
+
+#define NCCS 19
+struct termios {
+ tcflag_t c_iflag; /* input mode flags */
+ tcflag_t c_oflag; /* output mode flags */
+ tcflag_t c_cflag; /* control mode flags */
+ tcflag_t c_lflag; /* local mode flags */
+ cc_t c_line; /* line discipline */
+ cc_t c_cc[NCCS]; /* control characters */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+/* c_iflag bits */
+#define IGNBRK 0000001
+#define BRKINT 0000002
+#define IGNPAR 0000004
+#define PARMRK 0000010
+#define INPCK 0000020
+#define ISTRIP 0000040
+#define INLCR 0000100
+#define IGNCR 0000200
+#define ICRNL 0000400
+#define IUCLC 0001000
+#define IXON 0002000
+#define IXANY 0004000
+#define IXOFF 0010000
+#define IMAXBEL 0020000
+
+/* c_oflag bits */
+#define OPOST 0000001
+#define OLCUC 0000002
+#define ONLCR 0000004
+#define OCRNL 0000010
+#define ONOCR 0000020
+#define ONLRET 0000040
+#define OFILL 0000100
+#define OFDEL 0000200
+#define NLDLY 0000400
+#define NL0 0000000
+#define NL1 0000400
+#define CRDLY 0003000
+#define CR0 0000000
+#define CR1 0001000
+#define CR2 0002000
+#define CR3 0003000
+#define TABDLY 0014000
+#define TAB0 0000000
+#define TAB1 0004000
+#define TAB2 0010000
+#define TAB3 0014000
+#define XTABS 0014000
+#define BSDLY 0020000
+#define BS0 0000000
+#define BS1 0020000
+#define VTDLY 0040000
+#define VT0 0000000
+#define VT1 0040000
+#define FFDLY 0100000
+#define FF0 0000000
+#define FF1 0100000
+
+/* c_cflag bit meaning */
+#define CBAUD 0010017
+#define B0 0000000 /* hang up */
+#define B50 0000001
+#define B75 0000002
+#define B110 0000003
+#define B134 0000004
+#define B150 0000005
+#define B200 0000006
+#define B300 0000007
+#define B600 0000010
+#define B1200 0000011
+#define B1800 0000012
+#define B2400 0000013
+#define B4800 0000014
+#define B9600 0000015
+#define B19200 0000016
+#define B38400 0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE 0000060
+#define CS5 0000000
+#define CS6 0000020
+#define CS7 0000040
+#define CS8 0000060
+#define CSTOPB 0000100
+#define CREAD 0000200
+#define PARENB 0000400
+#define PARODD 0001000
+#define HUPCL 0002000
+#define CLOCAL 0004000
+#define CBAUDEX 0010000
+#define B57600 0010001
+#define B115200 0010002
+#define B230400 0010003
+#define B460800 0010004
+#define B500000 0010005
+#define B576000 0010006
+#define B921600 0010007
+#define B1000000 0010010
+#define B1152000 0010011
+#define B1500000 0010012
+#define B2000000 0010013
+#define B2500000 0010014
+#define B3000000 0010015
+#define B3500000 0010016
+#define B4000000 0010017
+#define CIBAUD 002003600000 /* input baud rate (not used) */
+#define CMSPAR 010000000000 /* mark or space (stick) parity */
+#define CRTSCTS 020000000000 /* flow control */
+
+/* c_lflag bits */
+#define ISIG 0000001
+#define ICANON 0000002
+#define XCASE 0000004
+#define ECHO 0000010
+#define ECHOE 0000020
+#define ECHOK 0000040
+#define ECHONL 0000100
+#define NOFLSH 0000200
+#define TOSTOP 0000400
+#define ECHOCTL 0001000
+#define ECHOPRT 0002000
+#define ECHOKE 0004000
+#define FLUSHO 0010000
+#define PENDIN 0040000
+#define IEXTEN 0100000
+
+/* tcflow() and TCXONC use these */
+#define TCOOFF 0
+#define TCOON 1
+#define TCIOFF 2
+#define TCION 3
+
+/* tcflush() and TCFLSH use these */
+#define TCIFLUSH 0
+#define TCOFLUSH 1
+#define TCIOFLUSH 2
+
+/* tcsetattr uses these */
+#define TCSANOW 0
+#define TCSADRAIN 1
+#define TCSAFLUSH 2
+
+#endif
--- /dev/null
+#ifndef _I386_TERMIOS_H
+#define _I386_TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+ unsigned short ws_row;
+ unsigned short ws_col;
+ unsigned short ws_xpixel;
+ unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+ unsigned short c_iflag; /* input mode flags */
+ unsigned short c_oflag; /* output mode flags */
+ unsigned short c_cflag; /* control mode flags */
+ unsigned short c_lflag; /* local mode flags */
+ unsigned char c_line; /* line discipline */
+ unsigned char c_cc[NCC]; /* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE 0x001
+#define TIOCM_DTR 0x002
+#define TIOCM_RTS 0x004
+#define TIOCM_ST 0x008
+#define TIOCM_SR 0x010
+#define TIOCM_CTS 0x020
+#define TIOCM_CAR 0x040
+#define TIOCM_RNG 0x080
+#define TIOCM_DSR 0x100
+#define TIOCM_CD TIOCM_CAR
+#define TIOCM_RI TIOCM_RNG
+#define TIOCM_OUT1 0x2000
+#define TIOCM_OUT2 0x4000
+#define TIOCM_LOOP 0x8000
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
+/* line disciplines */
+#define N_TTY 0
+#define N_SLIP 1
+#define N_MOUSE 2
+#define N_PPP 3
+#define N_STRIP 4
+#define N_AX25 5
+#define N_X25 6 /* X.25 async */
+#define N_6PACK 7
+#define N_MASC 8 /* Reserved for Mobitex module <kaz@cafe.net> */
+#define N_R3964 9 /* Reserved for Simatic R3964 module */
+#define N_PROFIBUS_FDL 10 /* Reserved for Profibus <Dave@mvhi.com> */
+#define N_IRDA 11 /* Linux IR - http://irda.sourceforge.net/ */
+#define N_SMSBLOCK 12 /* SMS block mode - for talking to GSM data cards about SMS messages */
+#define N_HDLC 13 /* synchronous HDLC */
+#define N_SYNC_PPP 14 /* synchronous PPP */
+#define N_HCI 15 /* Bluetooth HCI UART */
+
+#ifdef __KERNEL__
+
+/* intr=^C quit=^\ erase=del kill=^U
+ eof=^D vtime=\0 vmin=\1 sxtc=\0
+ start=^Q stop=^S susp=^Z eol=\0
+ reprint=^R discard=^U werase=^W lnext=^V
+ eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+ unsigned short __tmp; \
+ get_user(__tmp,&(termio)->x); \
+ *(unsigned short *) &(termios)->x = __tmp; \
+}
+
+#define user_termio_to_kernel_termios(termios, termio) \
+({ \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
+ copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
+})
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+#define kernel_termios_to_user_termio(termio, termios) \
+({ \
+ put_user((termios)->c_iflag, &(termio)->c_iflag); \
+ put_user((termios)->c_oflag, &(termio)->c_oflag); \
+ put_user((termios)->c_cflag, &(termio)->c_cflag); \
+ put_user((termios)->c_lflag, &(termio)->c_lflag); \
+ put_user((termios)->c_line, &(termio)->c_line); \
+ copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
+})
+
+#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios))
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_TERMIOS_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/timex.h
+ *
+ * i386 architecture timex specifications
+ */
+#ifndef _ASMi386_TIMEX_H
+#define _ASMi386_TIMEX_H
+
+#include <linux/config.h>
+#include <asm/msr.h>
+
+#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */
+#define CLOCK_TICK_FACTOR 20 /* Factor of both 1000000 and CLOCK_TICK_RATE */
+#define FINETUNE ((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \
+ (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \
+ << (SHIFT_SCALE-SHIFT_HZ)) / HZ)
+
+/*
+ * Standard way to access the cycle counter on i586+ CPUs.
+ * Currently only used on SMP.
+ *
+ * If you really have a SMP machine with i486 chips or older,
+ * compile for that, and this will just always return zero.
+ * That's ok, it just means that the nicer scheduling heuristics
+ * won't work for you.
+ *
+ * We only use the low 32 bits, and we'd simply better make sure
+ * that we reschedule before that wraps. Scheduling at least every
+ * four billion cycles just basically sounds like a good idea,
+ * regardless of how fast the machine is.
+ */
+typedef unsigned long long cycles_t;
+
+extern cycles_t cacheflush_time;
+
+static inline cycles_t get_cycles (void)
+{
+#ifndef CONFIG_X86_TSC
+ return 0;
+#else
+ unsigned long long ret;
+
+ rdtscll(ret);
+ return ret;
+#endif
+}
+
+extern unsigned long cpu_khz;
+
+#endif
--- /dev/null
+#include <asm-generic/tlb.h>
--- /dev/null
+#ifndef _I386_TYPES_H
+#define _I386_TYPES_H
+
+typedef unsigned short umode_t;
+
+/*
+ * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
+ * header files exported to user space
+ */
+
+typedef __signed__ char __s8;
+typedef unsigned char __u8;
+
+typedef __signed__ short __s16;
+typedef unsigned short __u16;
+
+typedef __signed__ int __s32;
+typedef unsigned int __u32;
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+typedef __signed__ long long __s64;
+typedef unsigned long long __u64;
+#endif
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+#define BITS_PER_LONG 32
+
+/* DMA addresses come in generic and 64-bit flavours. */
+
+#ifdef CONFIG_HIGHMEM
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+typedef u64 dma64_addr_t;
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef __i386_UACCESS_H
+#define __i386_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/prefetch.h>
+#include <asm/page.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not. If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) })
+
+
+#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF)
+#define USER_DS MAKE_MM_SEG(PAGE_OFFSET)
+
+#define get_ds() (KERNEL_DS)
+#define get_fs() (current->addr_limit)
+#define set_fs(x) (current->addr_limit = (x))
+
+#define segment_eq(a,b) ((a).seg == (b).seg)
+
+extern int __verify_write(const void *, unsigned long);
+
+#define __addr_ok(addr) ((unsigned long)(addr) < (current->addr_limit.seg))
+
+/*
+ * Uhhuh, this needs 33-bit arithmetic. We have a carry..
+ */
+#define __range_ok(addr,size) ({ \
+ unsigned long flag,sum; \
+ asm("addl %3,%1 ; sbbl %0,%0; cmpl %1,%4; sbbl $0,%0" \
+ :"=&r" (flag), "=r" (sum) \
+ :"1" (addr),"g" ((int)(size)),"g" (current->addr_limit.seg)); \
+ flag; })
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+#define access_ok(type,addr,size) (__range_ok(addr,size) == 0)
+
+#else
+
+#define access_ok(type,addr,size) ( (__range_ok(addr,size) == 0) && \
+ ((type) == VERIFY_READ || boot_cpu_data.wp_works_ok || \
+ segment_eq(get_fs(),KERNEL_DS) || \
+ __verify_write((void *)(addr),(size))))
+
+#endif
+
+static inline int verify_area(int type, const void * addr, unsigned long size)
+{
+ return access_ok(type,addr,size) ? 0 : -EFAULT;
+}
+
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+ unsigned long insn, fixup;
+};
+
+/* Returns 0 if exception not found and fixup otherwise. */
+extern unsigned long search_exception_table(unsigned long);
+
+
+/*
+ * These are the main single-value transfer routines. They automatically
+ * use the right size if we just have the right pointer type.
+ *
+ * This gets kind of ugly. We want to return _two_ values in "get_user()"
+ * and yet we don't want to do any pointers, because that is too much
+ * of a performance impact. Thus we have a few rather ugly macros here,
+ * and hide all the uglyness from the user.
+ *
+ * The "__xxx" versions of the user access functions are versions that
+ * do not verify the address space, that must have been done previously
+ * with a separate "access_ok()" call (this is used when we do multiple
+ * accesses to the same area of user memory).
+ */
+
+extern void __get_user_1(void);
+extern void __get_user_2(void);
+extern void __get_user_4(void);
+
+#define __get_user_x(size,ret,x,ptr) \
+ __asm__ __volatile__("call __get_user_" #size \
+ :"=a" (ret),"=d" (x) \
+ :"0" (ptr))
+
+/* Careful: we have to cast the result to the type of the pointer for sign reasons */
+#define get_user(x,ptr) \
+({ int __ret_gu,__val_gu; \
+ switch(sizeof (*(ptr))) { \
+ case 1: __get_user_x(1,__ret_gu,__val_gu,ptr); break; \
+ case 2: __get_user_x(2,__ret_gu,__val_gu,ptr); break; \
+ case 4: __get_user_x(4,__ret_gu,__val_gu,ptr); break; \
+ default: __get_user_x(X,__ret_gu,__val_gu,ptr); break; \
+ } \
+ (x) = (__typeof__(*(ptr)))__val_gu; \
+ __ret_gu; \
+})
+
+extern void __put_user_1(void);
+extern void __put_user_2(void);
+extern void __put_user_4(void);
+extern void __put_user_8(void);
+
+extern void __put_user_bad(void);
+
+#define put_user(x,ptr) \
+ __put_user_check((__typeof__(*(ptr)))(x),(ptr),sizeof(*(ptr)))
+
+#define __get_user(x,ptr) \
+ __get_user_nocheck((x),(ptr),sizeof(*(ptr)))
+#define __put_user(x,ptr) \
+ __put_user_nocheck((__typeof__(*(ptr)))(x),(ptr),sizeof(*(ptr)))
+
+#define __put_user_nocheck(x,ptr,size) \
+({ \
+ long __pu_err; \
+ __put_user_size((x),(ptr),(size),__pu_err); \
+ __pu_err; \
+})
+
+
+#define __put_user_check(x,ptr,size) \
+({ \
+ long __pu_err = -EFAULT; \
+ __typeof__(*(ptr)) *__pu_addr = (ptr); \
+ if (access_ok(VERIFY_WRITE,__pu_addr,size)) \
+ __put_user_size((x),__pu_addr,(size),__pu_err); \
+ __pu_err; \
+})
+
+#define __put_user_u64(x, addr, err) \
+ __asm__ __volatile__( \
+ "1: movl %%eax,0(%2)\n" \
+ "2: movl %%edx,4(%2)\n" \
+ "3:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "4: movl %3,%0\n" \
+ " jmp 3b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,4b\n" \
+ " .long 2b,4b\n" \
+ ".previous" \
+ : "=r"(err) \
+ : "A" (x), "r" (addr), "i"(-EFAULT), "0"(err))
+
+#define __put_user_size(x,ptr,size,retval) \
+do { \
+ retval = 0; \
+ switch (size) { \
+ case 1: __put_user_asm(x,ptr,retval,"b","b","iq"); break; \
+ case 2: __put_user_asm(x,ptr,retval,"w","w","ir"); break; \
+ case 4: __put_user_asm(x,ptr,retval,"l","","ir"); break; \
+ case 8: __put_user_u64(x,ptr,retval); break; \
+ default: __put_user_bad(); \
+ } \
+} while (0)
+
+struct __large_struct { unsigned long buf[100]; };
+#define __m(x) (*(struct __large_struct *)(x))
+
+/*
+ * Tell gcc we read from memory instead of writing: this is because
+ * we do not write to any memory gcc knows about, so there are no
+ * aliasing issues.
+ */
+#define __put_user_asm(x, addr, err, itype, rtype, ltype) \
+ __asm__ __volatile__( \
+ "1: mov"itype" %"rtype"1,%2\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl %3,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,3b\n" \
+ ".previous" \
+ : "=r"(err) \
+ : ltype (x), "m"(__m(addr)), "i"(-EFAULT), "0"(err))
+
+
+#define __get_user_nocheck(x,ptr,size) \
+({ \
+ long __gu_err, __gu_val; \
+ __get_user_size(__gu_val,(ptr),(size),__gu_err); \
+ (x) = (__typeof__(*(ptr)))__gu_val; \
+ __gu_err; \
+})
+
+extern long __get_user_bad(void);
+
+#define __get_user_size(x,ptr,size,retval) \
+do { \
+ retval = 0; \
+ switch (size) { \
+ case 1: __get_user_asm(x,ptr,retval,"b","b","=q"); break; \
+ case 2: __get_user_asm(x,ptr,retval,"w","w","=r"); break; \
+ case 4: __get_user_asm(x,ptr,retval,"l","","=r"); break; \
+ default: (x) = __get_user_bad(); \
+ } \
+} while (0)
+
+#define __get_user_asm(x, addr, err, itype, rtype, ltype) \
+ __asm__ __volatile__( \
+ "1: mov"itype" %2,%"rtype"1\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl %3,%0\n" \
+ " xor"itype" %"rtype"1,%"rtype"1\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,3b\n" \
+ ".previous" \
+ : "=r"(err), ltype (x) \
+ : "m"(__m(addr)), "i"(-EFAULT), "0"(err))
+
+
+/*
+ * Copy To/From Userspace
+ */
+
+/* Generic arbitrary sized copy. */
+#define __copy_user(to,from,size) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ " movl %3,%0\n" \
+ "1: rep; movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: lea 0(%3,%0,4),%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,2b\n" \
+ ".previous" \
+ : "=&c"(size), "=&D" (__d0), "=&S" (__d1) \
+ : "r"(size & 3), "0"(size / 4), "1"(to), "2"(from) \
+ : "memory"); \
+} while (0)
+
+#define __copy_user_zeroing(to,from,size) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ " movl %3,%0\n" \
+ "1: rep; movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: lea 0(%3,%0,4),%0\n" \
+ "4: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosb\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=&c"(size), "=&D" (__d0), "=&S" (__d1) \
+ : "r"(size & 3), "0"(size / 4), "1"(to), "2"(from) \
+ : "memory"); \
+} while (0)
+
+/* We let the __ versions of copy_from/to_user inline, because they're often
+ * used in fast paths and have only a small space overhead.
+ */
+static inline unsigned long
+__generic_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __copy_user_zeroing(to,from,n);
+ return n;
+}
+
+static inline unsigned long
+__generic_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __copy_user(to,from,n);
+ return n;
+}
+
+
+/* Optimize just a little bit when we know the size of the move. */
+#define __constant_copy_user(to, from, size) \
+do { \
+ int __d0, __d1; \
+ switch (size & 3) { \
+ default: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "2: shl $2,%0\n" \
+ " jmp 1b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,2b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 1: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: shl $2,%0\n" \
+ "4: incl %0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 2: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: shl $2,%0\n" \
+ "4: addl $2,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 3: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2: movsb\n" \
+ "3:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "4: shl $2,%0\n" \
+ "5: addl $2,%0\n" \
+ "6: incl %0\n" \
+ " jmp 3b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,4b\n" \
+ " .long 1b,5b\n" \
+ " .long 2b,6b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+/* Optimize just a little bit when we know the size of the move. */
+#define __constant_copy_user_zeroing(to, from, size) \
+do { \
+ int __d0, __d1; \
+ switch (size & 3) { \
+ default: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "2: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " jmp 1b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,2b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 1: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " incl %0\n" \
+ " jmp 2b\n" \
+ "4: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " incl %0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 2: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " stosw\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " addl $2,%0\n" \
+ " jmp 2b\n" \
+ "4: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosw\n" \
+ " popl %%eax\n" \
+ " addl $2,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 3: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2: movsb\n" \
+ "3:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "4: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " stosw\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " addl $3,%0\n" \
+ " jmp 2b\n" \
+ "5: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosw\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " addl $3,%0\n" \
+ " jmp 2b\n" \
+ "6: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " incl %0\n" \
+ " jmp 3b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,4b\n" \
+ " .long 1b,5b\n" \
+ " .long 2b,6b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+unsigned long __generic_copy_to_user(void *, const void *, unsigned long);
+unsigned long __generic_copy_from_user(void *, const void *, unsigned long);
+
+static inline unsigned long
+__constant_copy_to_user(void *to, const void *from, unsigned long n)
+{
+ prefetch(from);
+ if (access_ok(VERIFY_WRITE, to, n))
+ __constant_copy_user(to,from,n);
+ return n;
+}
+
+static inline unsigned long
+__constant_copy_from_user(void *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_READ, from, n))
+ __constant_copy_user_zeroing(to,from,n);
+ else
+ memset(to, 0, n);
+ return n;
+}
+
+static inline unsigned long
+__constant_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __constant_copy_user(to,from,n);
+ return n;
+}
+
+static inline unsigned long
+__constant_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __constant_copy_user_zeroing(to,from,n);
+ return n;
+}
+
+#define copy_to_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_to_user((to),(from),(n)) : \
+ __generic_copy_to_user((to),(from),(n)))
+
+#define copy_from_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_from_user((to),(from),(n)) : \
+ __generic_copy_from_user((to),(from),(n)))
+
+#define __copy_to_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_to_user_nocheck((to),(from),(n)) : \
+ __generic_copy_to_user_nocheck((to),(from),(n)))
+
+#define __copy_from_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_from_user_nocheck((to),(from),(n)) : \
+ __generic_copy_from_user_nocheck((to),(from),(n)))
+
+long strncpy_from_user(char *dst, const char *src, long count);
+long __strncpy_from_user(char *dst, const char *src, long count);
+#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
+long strnlen_user(const char *str, long n);
+unsigned long clear_user(void *mem, unsigned long len);
+unsigned long __clear_user(void *mem, unsigned long len);
+
+#endif /* __i386_UACCESS_H */
--- /dev/null
+#ifndef _ASMi386_UCONTEXT_H
+#define _ASMi386_UCONTEXT_H
+
+struct ucontext {
+ unsigned long uc_flags;
+ struct ucontext *uc_link;
+ stack_t uc_stack;
+ struct sigcontext uc_mcontext;
+ sigset_t uc_sigmask; /* mask last for extensibility */
+};
+
+#endif /* !_ASMi386_UCONTEXT_H */
--- /dev/null
+#ifndef __I386_UNALIGNED_H
+#define __I386_UNALIGNED_H
+
+/*
+ * The i386 can do unaligned accesses itself.
+ *
+ * The strange macros are there to make sure these can't
+ * be misused in a way that makes them not work on other
+ * architectures where unaligned accesses aren't as simple.
+ */
+
+/**
+ * get_unaligned - get value from possibly mis-aligned location
+ * @ptr: pointer to value
+ *
+ * This macro should be used for accessing values larger in size than
+ * single bytes at locations that are expected to be improperly aligned,
+ * e.g. retrieving a u16 value from a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define get_unaligned(ptr) (*(ptr))
+
+/**
+ * put_unaligned - put value to a possibly mis-aligned location
+ * @val: value to place
+ * @ptr: pointer to location
+ *
+ * This macro should be used for placing values larger in size than
+ * single bytes at locations that are expected to be improperly aligned,
+ * e.g. writing a u16 value to a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+
+#endif
--- /dev/null
+#ifndef _ASM_I386_UNISTD_H_
+#define _ASM_I386_UNISTD_H_
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_exit 1
+#define __NR_fork 2
+#define __NR_read 3
+#define __NR_write 4
+#define __NR_open 5
+#define __NR_close 6
+#define __NR_waitpid 7
+#define __NR_creat 8
+#define __NR_link 9
+#define __NR_unlink 10
+#define __NR_execve 11
+#define __NR_chdir 12
+#define __NR_time 13
+#define __NR_mknod 14
+#define __NR_chmod 15
+#define __NR_lchown 16
+#define __NR_break 17
+#define __NR_oldstat 18
+#define __NR_lseek 19
+#define __NR_getpid 20
+#define __NR_mount 21
+#define __NR_umount 22
+#define __NR_setuid 23
+#define __NR_getuid 24
+#define __NR_stime 25
+#define __NR_ptrace 26
+#define __NR_alarm 27
+#define __NR_oldfstat 28
+#define __NR_pause 29
+#define __NR_utime 30
+#define __NR_stty 31
+#define __NR_gtty 32
+#define __NR_access 33
+#define __NR_nice 34
+#define __NR_ftime 35
+#define __NR_sync 36
+#define __NR_kill 37
+#define __NR_rename 38
+#define __NR_mkdir 39
+#define __NR_rmdir 40
+#define __NR_dup 41
+#define __NR_pipe 42
+#define __NR_times 43
+#define __NR_prof 44
+#define __NR_brk 45
+#define __NR_setgid 46
+#define __NR_getgid 47
+#define __NR_signal 48
+#define __NR_geteuid 49
+#define __NR_getegid 50
+#define __NR_acct 51
+#define __NR_umount2 52
+#define __NR_lock 53
+#define __NR_ioctl 54
+#define __NR_fcntl 55
+#define __NR_mpx 56
+#define __NR_setpgid 57
+#define __NR_ulimit 58
+#define __NR_oldolduname 59
+#define __NR_umask 60
+#define __NR_chroot 61
+#define __NR_ustat 62
+#define __NR_dup2 63
+#define __NR_getppid 64
+#define __NR_getpgrp 65
+#define __NR_setsid 66
+#define __NR_sigaction 67
+#define __NR_sgetmask 68
+#define __NR_ssetmask 69
+#define __NR_setreuid 70
+#define __NR_setregid 71
+#define __NR_sigsuspend 72
+#define __NR_sigpending 73
+#define __NR_sethostname 74
+#define __NR_setrlimit 75
+#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */
+#define __NR_getrusage 77
+#define __NR_gettimeofday 78
+#define __NR_settimeofday 79
+#define __NR_getgroups 80
+#define __NR_setgroups 81
+#define __NR_select 82
+#define __NR_symlink 83
+#define __NR_oldlstat 84
+#define __NR_readlink 85
+#define __NR_uselib 86
+#define __NR_swapon 87
+#define __NR_reboot 88
+#define __NR_readdir 89
+#define __NR_mmap 90
+#define __NR_munmap 91
+#define __NR_truncate 92
+#define __NR_ftruncate 93
+#define __NR_fchmod 94
+#define __NR_fchown 95
+#define __NR_getpriority 96
+#define __NR_setpriority 97
+#define __NR_profil 98
+#define __NR_statfs 99
+#define __NR_fstatfs 100
+#define __NR_ioperm 101
+#define __NR_socketcall 102
+#define __NR_syslog 103
+#define __NR_setitimer 104
+#define __NR_getitimer 105
+#define __NR_stat 106
+#define __NR_lstat 107
+#define __NR_fstat 108
+#define __NR_olduname 109
+#define __NR_iopl 110
+#define __NR_vhangup 111
+#define __NR_idle 112
+#define __NR_vm86old 113
+#define __NR_wait4 114
+#define __NR_swapoff 115
+#define __NR_sysinfo 116
+#define __NR_ipc 117
+#define __NR_fsync 118
+#define __NR_sigreturn 119
+#define __NR_clone 120
+#define __NR_setdomainname 121
+#define __NR_uname 122
+#define __NR_modify_ldt 123
+#define __NR_adjtimex 124
+#define __NR_mprotect 125
+#define __NR_sigprocmask 126
+#define __NR_create_module 127
+#define __NR_init_module 128
+#define __NR_delete_module 129
+#define __NR_get_kernel_syms 130
+#define __NR_quotactl 131
+#define __NR_getpgid 132
+#define __NR_fchdir 133
+#define __NR_bdflush 134
+#define __NR_sysfs 135
+#define __NR_personality 136
+#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
+#define __NR_setfsuid 138
+#define __NR_setfsgid 139
+#define __NR__llseek 140
+#define __NR_getdents 141
+#define __NR__newselect 142
+#define __NR_flock 143
+#define __NR_msync 144
+#define __NR_readv 145
+#define __NR_writev 146
+#define __NR_getsid 147
+#define __NR_fdatasync 148
+#define __NR__sysctl 149
+#define __NR_mlock 150
+#define __NR_munlock 151
+#define __NR_mlockall 152
+#define __NR_munlockall 153
+#define __NR_sched_setparam 154
+#define __NR_sched_getparam 155
+#define __NR_sched_setscheduler 156
+#define __NR_sched_getscheduler 157
+#define __NR_sched_yield 158
+#define __NR_sched_get_priority_max 159
+#define __NR_sched_get_priority_min 160
+#define __NR_sched_rr_get_interval 161
+#define __NR_nanosleep 162
+#define __NR_mremap 163
+#define __NR_setresuid 164
+#define __NR_getresuid 165
+#define __NR_vm86 166
+#define __NR_query_module 167
+#define __NR_poll 168
+#define __NR_nfsservctl 169
+#define __NR_setresgid 170
+#define __NR_getresgid 171
+#define __NR_prctl 172
+#define __NR_rt_sigreturn 173
+#define __NR_rt_sigaction 174
+#define __NR_rt_sigprocmask 175
+#define __NR_rt_sigpending 176
+#define __NR_rt_sigtimedwait 177
+#define __NR_rt_sigqueueinfo 178
+#define __NR_rt_sigsuspend 179
+#define __NR_pread 180
+#define __NR_pwrite 181
+#define __NR_chown 182
+#define __NR_getcwd 183
+#define __NR_capget 184
+#define __NR_capset 185
+#define __NR_sigaltstack 186
+#define __NR_sendfile 187
+#define __NR_getpmsg 188 /* some people actually want streams */
+#define __NR_putpmsg 189 /* some people actually want streams */
+#define __NR_vfork 190
+#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
+#define __NR_mmap2 192
+#define __NR_truncate64 193
+#define __NR_ftruncate64 194
+#define __NR_stat64 195
+#define __NR_lstat64 196
+#define __NR_fstat64 197
+#define __NR_lchown32 198
+#define __NR_getuid32 199
+#define __NR_getgid32 200
+#define __NR_geteuid32 201
+#define __NR_getegid32 202
+#define __NR_setreuid32 203
+#define __NR_setregid32 204
+#define __NR_getgroups32 205
+#define __NR_setgroups32 206
+#define __NR_fchown32 207
+#define __NR_setresuid32 208
+#define __NR_getresuid32 209
+#define __NR_setresgid32 210
+#define __NR_getresgid32 211
+#define __NR_chown32 212
+#define __NR_setuid32 213
+#define __NR_setgid32 214
+#define __NR_setfsuid32 215
+#define __NR_setfsgid32 216
+#define __NR_pivot_root 217
+#define __NR_mincore 218
+#define __NR_madvise 219
+#define __NR_madvise1 219 /* delete when C lib stub is removed */
+#define __NR_getdents64 220
+#define __NR_fcntl64 221
+#define __NR_security 223 /* syscall for security modules */
+#define __NR_gettid 224
+#define __NR_readahead 225
+
+/* user-visible error numbers are in the range -1 - -124: see <asm-i386/errno.h> */
+
+#define __syscall_return(type, res) \
+do { \
+ if ((unsigned long)(res) >= (unsigned long)(-125)) { \
+ errno = -(res); \
+ res = -1; \
+ } \
+ return (type) (res); \
+} while (0)
+
+/* XXX - _foo needs to be __foo, while __NR_bar could be _NR_bar. */
+#define _syscall0(type,name) \
+type name(void) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name)); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall1(type,name,type1,arg1) \
+type name(type1 arg1) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall2(type,name,type1,arg1,type2,arg2) \
+type name(type1 arg1,type2 arg2) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \
+type name(type1 arg1,type2 arg2,type3 arg3) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
+type name (type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3)),"S" ((long)(arg4))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
+ type5,arg5) \
+type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
+ type5,arg5,type6,arg6) \
+type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5,type6 arg6) \
+{ \
+long __res; \
+__asm__ volatile ("push %%ebp ; movl %%eax,%%ebp ; movl %1,%%eax ; int $0x80 ; pop %%ebp" \
+ : "=a" (__res) \
+ : "i" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)), \
+ "0" ((long)(arg6))); \
+__syscall_return(type,__res); \
+}
+
+#ifdef __KERNEL_SYSCALLS__
+
+/*
+ * we need this inline - forking from kernel space will result
+ * in NO COPY ON WRITE (!!!), until an execve is executed. This
+ * is no problem, but for the stack. This is handled by not letting
+ * main() use the stack at all after fork(). Thus, no function
+ * calls - which means inline code for fork too, as otherwise we
+ * would use the stack upon exit from 'fork()'.
+ *
+ * Actually only pause and fork are needed inline, so that there
+ * won't be any messing with the stack from main(), but we define
+ * some others too.
+ */
+#define __NR__exit __NR_exit
+static inline _syscall0(int,pause)
+static inline _syscall0(int,sync)
+static inline _syscall0(pid_t,setsid)
+static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count)
+static inline _syscall3(int,read,int,fd,char *,buf,off_t,count)
+static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count)
+static inline _syscall1(int,dup,int,fd)
+static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp)
+static inline _syscall3(int,open,const char *,file,int,flag,int,mode)
+static inline _syscall1(int,close,int,fd)
+static inline _syscall1(int,_exit,int,exitcode)
+static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options)
+static inline _syscall1(int,delete_module,const char *,name)
+
+static inline pid_t wait(int * wait_stat)
+{
+ return waitpid(-1,wait_stat,0);
+}
+
+#endif
+
+#endif /* _ASM_I386_UNISTD_H_ */
--- /dev/null
+#ifndef _I386_USER_H
+#define _I386_USER_H
+
+#include <asm/page.h>
+#include <linux/ptrace.h>
+/* Core file format: The core file is written in such a way that gdb
+ can understand it and provide useful information to the user (under
+ linux we use the 'trad-core' bfd). There are quite a number of
+ obstacles to being able to view the contents of the floating point
+ registers, and until these are solved you will not be able to view the
+ contents of them. Actually, you can read in the core file and look at
+ the contents of the user struct to find out what the floating point
+ registers contain.
+ The actual file contents are as follows:
+ UPAGE: 1 page consisting of a user struct that tells gdb what is present
+ in the file. Directly after this is a copy of the task_struct, which
+ is currently not used by gdb, but it may come in useful at some point.
+ All of the registers are stored as part of the upage. The upage should
+ always be only one page.
+ DATA: The data area is stored. We use current->end_text to
+ current->brk to pick up all of the user variables, plus any memory
+ that may have been malloced. No attempt is made to determine if a page
+ is demand-zero or if a page is totally unused, we just cover the entire
+ range. All of the addresses are rounded in such a way that an integral
+ number of pages is written.
+ STACK: We need the stack information in order to get a meaningful
+ backtrace. We need to write the data from (esp) to
+ current->start_stack, so we round each of these off in order to be able
+ to write an integer number of pages.
+ The minimum core file size is 3 pages, or 12288 bytes.
+*/
+
+/*
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
+ * interacting with the FXSR-format floating point environment. Floating
+ * point data can be accessed in the regular format in the usual manner,
+ * and both the standard and SIMD floating point data can be accessed via
+ * the new ptrace requests. In either case, changes to the FPU environment
+ * will be reflected in the task's state as expected.
+ */
+
+struct user_i387_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+};
+
+struct user_fxsr_struct {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long mxcsr;
+ long reserved;
+ long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+ long padding[56];
+};
+
+/*
+ * This is the old layout of "struct pt_regs", and
+ * is still the layout used by user mode (the new
+ * pt_regs doesn't have all registers as the kernel
+ * doesn't use the extra segment registers)
+ */
+struct user_regs_struct {
+ long ebx, ecx, edx, esi, edi, ebp, eax;
+ unsigned short ds, __ds, es, __es;
+ unsigned short fs, __fs, gs, __gs;
+ long orig_eax, eip;
+ unsigned short cs, __cs;
+ long eflags, esp;
+ unsigned short ss, __ss;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+ this will be used by gdb to figure out where the data and stack segments
+ are within the file, and what virtual addresses to use. */
+struct user{
+/* We start with the registers, to mimic the way that "memory" is returned
+ from the ptrace(3,...) function. */
+ struct user_regs_struct regs; /* Where the registers are actually stored */
+/* ptrace does not yet supply these. Someday.... */
+ int u_fpvalid; /* True if math co-processor being used. */
+ /* for this mess. Not yet used. */
+ struct user_i387_struct i387; /* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+ unsigned long int u_tsize; /* Text segment size (pages). */
+ unsigned long int u_dsize; /* Data segment size (pages). */
+ unsigned long int u_ssize; /* Stack segment size (pages). */
+ unsigned long start_code; /* Starting virtual address of text. */
+ unsigned long start_stack; /* Starting virtual address of stack area.
+ This is actually the bottom of the stack,
+ the top of the stack is always found in the
+ esp register. */
+ long int signal; /* Signal that caused the core dump. */
+ int reserved; /* No longer used */
+ struct user_pt_regs * u_ar0; /* Used by gdb to help find the values for */
+ /* the registers. */
+ struct user_i387_struct* u_fpstate; /* Math Co-processor pointer. */
+ unsigned long magic; /* To uniquely identify a core file */
+ char u_comm[32]; /* User command that was responsible */
+ int u_debugreg[8];
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif /* _I386_USER_H */
--- /dev/null
+/*
+ * Access to VGA videoram
+ *
+ * (c) 1998 Martin Mares <mj@ucw.cz>
+ */
+
+#ifndef _LINUX_ASM_VGA_H_
+#define _LINUX_ASM_VGA_H_
+
+/*
+ * On the PC, we can just recalculate addresses and then
+ * access the videoram directly without any black magic.
+ */
+
+#define VGA_MAP_MEM(x) (unsigned long)phys_to_virt(x)
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x,y) (*(y) = (x))
+
+#endif
--- /dev/null
+/*
+ * include/asm-i386/xor.h
+ *
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * High-speed RAID5 checksumming functions utilizing MMX instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+#define FPU_SAVE \
+ do { \
+ if (!(current->flags & PF_USEDFPU)) \
+ __asm__ __volatile__ (" clts;\n"); \
+ __asm__ __volatile__ ("fsave %0; fwait": "=m"(fpu_save[0])); \
+ } while (0)
+
+#define FPU_RESTORE \
+ do { \
+ __asm__ __volatile__ ("frstor %0": : "m"(fpu_save[0])); \
+ if (!(current->flags & PF_USEDFPU)) \
+ stts(); \
+ } while (0)
+
+#define LD(x,y) " movq 8*("#x")(%1), %%mm"#y" ;\n"
+#define ST(x,y) " movq %%mm"#y", 8*("#x")(%1) ;\n"
+#define XO1(x,y) " pxor 8*("#x")(%2), %%mm"#y" ;\n"
+#define XO2(x,y) " pxor 8*("#x")(%3), %%mm"#y" ;\n"
+#define XO3(x,y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
+#define XO4(x,y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
+
+
+static void
+xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ ST(i,0) \
+ XO1(i+1,1) \
+ ST(i+1,1) \
+ XO1(i+2,2) \
+ ST(i+2,2) \
+ XO1(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ ST(i,0) \
+ XO2(i+1,1) \
+ ST(i+1,1) \
+ XO2(i+2,2) \
+ ST(i+2,2) \
+ XO2(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2), "r" (p3)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ ST(i,0) \
+ XO3(i+1,1) \
+ ST(i+1,1) \
+ XO3(i+2,2) \
+ ST(i+2,2) \
+ XO3(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " addl $128, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2), "r" (p3), "r" (p4)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ ST(i,0) \
+ XO4(i+1,1) \
+ ST(i+1,1) \
+ XO4(i+2,2) \
+ ST(i+2,2) \
+ XO4(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " addl $128, %4 ;\n"
+ " addl $128, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "g" (lines),
+ "r" (p1), "r" (p2), "r" (p3), "r" (p4), "r" (p5)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+#undef LD
+#undef XO1
+#undef XO2
+#undef XO3
+#undef XO4
+#undef ST
+#undef BLOCK
+
+static void
+xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2), "r" (p3)
+ : "memory" );
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor (%4), %%mm0 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " pxor 8(%4), %%mm1 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " pxor 16(%4), %%mm2 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 24(%4), %%mm3 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " pxor 32(%4), %%mm4 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " pxor 40(%4), %%mm5 ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%4), %%mm6 ;\n"
+ " pxor 56(%4), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " addl $64, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2), "r" (p3), "r" (p4)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " pxor (%4), %%mm0 ;\n"
+ " pxor 8(%4), %%mm1 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " pxor (%5), %%mm0 ;\n"
+ " pxor 8(%5), %%mm1 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 16(%4), %%mm2 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " pxor 16(%5), %%mm2 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 24(%4), %%mm3 ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 24(%5), %%mm3 ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%4), %%mm4 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " pxor 32(%5), %%mm4 ;\n"
+ " pxor 40(%4), %%mm5 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " pxor 40(%5), %%mm5 ;\n"
+ " pxor 48(%4), %%mm6 ;\n"
+ " pxor 56(%4), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%5), %%mm6 ;\n"
+ " pxor 56(%5), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " addl $64, %4 ;\n"
+ " addl $64, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "g" (lines),
+ "r" (p1), "r" (p2), "r" (p3), "r" (p4), "r" (p5)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static struct xor_block_template xor_block_pII_mmx = {
+ name: "pII_mmx",
+ do_2: xor_pII_mmx_2,
+ do_3: xor_pII_mmx_3,
+ do_4: xor_pII_mmx_4,
+ do_5: xor_pII_mmx_5,
+};
+
+static struct xor_block_template xor_block_p5_mmx = {
+ name: "p5_mmx",
+ do_2: xor_p5_mmx_2,
+ do_3: xor_p5_mmx_3,
+ do_4: xor_p5_mmx_4,
+ do_5: xor_p5_mmx_5,
+};
+
+#undef FPU_SAVE
+#undef FPU_RESTORE
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+#define XMMS_SAVE \
+ __asm__ __volatile__ ( \
+ "movl %%cr0,%0 ;\n\t" \
+ "clts ;\n\t" \
+ "movups %%xmm0,(%1) ;\n\t" \
+ "movups %%xmm1,0x10(%1) ;\n\t" \
+ "movups %%xmm2,0x20(%1) ;\n\t" \
+ "movups %%xmm3,0x30(%1) ;\n\t" \
+ : "=r" (cr0) \
+ : "r" (xmm_save) \
+ : "memory")
+
+#define XMMS_RESTORE \
+ __asm__ __volatile__ ( \
+ "sfence ;\n\t" \
+ "movups (%1),%%xmm0 ;\n\t" \
+ "movups 0x10(%1),%%xmm1 ;\n\t" \
+ "movups 0x20(%1),%%xmm2 ;\n\t" \
+ "movups 0x30(%1),%%xmm3 ;\n\t" \
+ "movl %0,%%cr0 ;\n\t" \
+ : \
+ : "r" (cr0), "r" (xmm_save) \
+ : "memory")
+
+#define OFFS(x) "16*("#x")"
+#define PF_OFFS(x) "256+16*("#x")"
+#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n"
+#define LD(x,y) " movaps "OFFS(x)"(%1), %%xmm"#y" ;\n"
+#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%1) ;\n"
+#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n"
+#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n"
+#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n"
+#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n"
+#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n"
+#define XO1(x,y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n"
+#define XO2(x,y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n"
+#define XO3(x,y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n"
+#define XO4(x,y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n"
+#define XO5(x,y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4];
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2)
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4];
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r"(p2), "r"(p3)
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4];
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " addl $256, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2), "r" (p3), "r" (p4)
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4];
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ PF4(i) \
+ PF4(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ XO4(i+1,1) \
+ XO4(i+2,2) \
+ XO4(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " addl $256, %4 ;\n"
+ " addl $256, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ :
+ : "r" (lines),
+ "r" (p1), "r" (p2), "r" (p3), "r" (p4), "r" (p5)
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_pIII_sse = {
+ name: "pIII_sse",
+ do_2: xor_sse_2,
+ do_3: xor_sse_3,
+ do_4: xor_sse_4,
+ do_5: xor_sse_5,
+};
+
+/* Also try the generic routines. */
+#include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES \
+ do { \
+ xor_speed(&xor_block_8regs); \
+ xor_speed(&xor_block_32regs); \
+ if (cpu_has_xmm) \
+ xor_speed(&xor_block_pIII_sse); \
+ if (md_cpu_has_mmx()) { \
+ xor_speed(&xor_block_pII_mmx); \
+ xor_speed(&xor_block_p5_mmx); \
+ } \
+ } while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+ We may also be able to load into the L1 only depending on how the cpu
+ deals with a load to a line that is being prefetched. */
+#define XOR_SELECT_TEMPLATE(FASTEST) \
+ (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
--- /dev/null
+#ifndef _BLK_H
+#define _BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/locks.h>
+#include <linux/config.h>
+#include <linux/spinlock.h>
+
+/*
+ * Spinlock for protecting the request queue which
+ * is mucked around with in interrupts on potentially
+ * multiple CPU's..
+ */
+extern spinlock_t io_request_lock;
+
+/*
+ * Initialization functions.
+ */
+extern int isp16_init(void);
+extern int cdu31a_init(void);
+extern int acsi_init(void);
+extern int mcd_init(void);
+extern int mcdx_init(void);
+extern int sbpcd_init(void);
+extern int aztcd_init(void);
+extern int sony535_init(void);
+extern int gscd_init(void);
+extern int cm206_init(void);
+extern int optcd_init(void);
+extern int sjcd_init(void);
+extern int cdi_init(void);
+extern int hd_init(void);
+extern int ide_init(void);
+extern int xd_init(void);
+extern int mfm_init(void);
+extern int loop_init(void);
+extern int md_init(void);
+extern int ap_init(void);
+extern int ddv_init(void);
+extern int z2_init(void);
+extern int swim3_init(void);
+extern int swimiop_init(void);
+extern int amiga_floppy_init(void);
+extern int atari_floppy_init(void);
+extern int ez_init(void);
+extern int bpcd_init(void);
+extern int ps2esdi_init(void);
+extern int jsfd_init(void);
+extern int viodasd_init(void);
+extern int viocd_init(void);
+extern int xlblk_init(void);
+
+#if defined(CONFIG_ARCH_S390)
+extern int dasd_init(void);
+extern int xpram_init(void);
+extern int tapeblock_init(void);
+#endif /* CONFIG_ARCH_S390 */
+
+extern void set_device_ro(kdev_t dev,int flag);
+void add_blkdev_randomness(int major);
+
+extern int floppy_init(void);
+extern void rd_load(void);
+extern int rd_init(void);
+extern int rd_doload; /* 1 = load ramdisk, 0 = don't load */
+extern int rd_prompt; /* 1 = prompt for ramdisk, 0 = don't prompt */
+extern int rd_image_start; /* starting block # of image */
+
+#ifdef CONFIG_BLK_DEV_INITRD
+
+#define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */
+
+extern unsigned long initrd_start,initrd_end;
+extern int mount_initrd; /* zero if initrd should not be mounted */
+extern int initrd_below_start_ok; /* 1 if it is not an error if initrd_start < memory_start */
+void initrd_init(void);
+
+#endif
+
+
+/*
+ * end_request() and friends. Must be called with the request queue spinlock
+ * acquired. All functions called within end_request() _must_be_ atomic.
+ *
+ * Several drivers define their own end_request and call
+ * end_that_request_first() and end_that_request_last()
+ * for parts of the original function. This prevents
+ * code duplication in drivers.
+ */
+
+static inline void blkdev_dequeue_request(struct request * req)
+{
+ list_del(&req->queue);
+}
+
+int end_that_request_first(struct request *req, int uptodate, char *name);
+void end_that_request_last(struct request *req);
+
+#if defined(MAJOR_NR) || defined(IDE_DRIVER)
+
+#undef DEVICE_ON
+#undef DEVICE_OFF
+
+/*
+ * Add entries as needed.
+ */
+
+#ifdef IDE_DRIVER
+
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+#define DEVICE_NAME "ide"
+
+#elif (MAJOR_NR == RAMDISK_MAJOR)
+
+/* ram disk */
+#define DEVICE_NAME "ramdisk"
+#define DEVICE_NR(device) (MINOR(device))
+#define DEVICE_NO_RANDOM
+
+#elif (MAJOR_NR == Z2RAM_MAJOR)
+
+/* Zorro II Ram */
+#define DEVICE_NAME "Z2RAM"
+#define DEVICE_REQUEST do_z2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == FLOPPY_MAJOR)
+
+static void floppy_off(unsigned int nr);
+
+#define DEVICE_NAME "floppy"
+#define DEVICE_INTR do_floppy
+#define DEVICE_REQUEST do_fd_request
+#define DEVICE_NR(device) ( (MINOR(device) & 3) | ((MINOR(device) & 0x80 ) >> 5 ))
+#define DEVICE_OFF(device) floppy_off(DEVICE_NR(device))
+
+#elif (MAJOR_NR == HD_MAJOR)
+
+/* Hard disk: timeout is 6 seconds. */
+#define DEVICE_NAME "hard disk"
+#define DEVICE_INTR do_hd
+#define TIMEOUT_VALUE (6*HZ)
+#define DEVICE_REQUEST do_hd_request
+#define DEVICE_NR(device) (MINOR(device)>>6)
+
+#elif (SCSI_DISK_MAJOR(MAJOR_NR))
+
+#define DEVICE_NAME "scsidisk"
+#define TIMEOUT_VALUE (2*HZ)
+#define DEVICE_NR(device) (((MAJOR(device) & SD_MAJOR_MASK) << (8 - 4)) + (MINOR(device) >> 4))
+
+/* Kludge to use the same number for both char and block major numbers */
+#elif (MAJOR_NR == MD_MAJOR) && defined(MD_DRIVER)
+
+#define DEVICE_NAME "Multiple devices driver"
+#define DEVICE_REQUEST do_md_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SCSI_TAPE_MAJOR)
+
+#define DEVICE_NAME "scsitape"
+#define DEVICE_INTR do_st
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+
+#elif (MAJOR_NR == OSST_MAJOR)
+
+#define DEVICE_NAME "onstream"
+#define DEVICE_INTR do_osst
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+#define DEVICE_ON(device)
+#define DEVICE_OFF(device)
+
+#elif (MAJOR_NR == SCSI_CDROM_MAJOR)
+
+#define DEVICE_NAME "CD-ROM"
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == XT_DISK_MAJOR)
+
+#define DEVICE_NAME "xt disk"
+#define DEVICE_REQUEST do_xd_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == PS2ESDI_MAJOR)
+
+#define DEVICE_NAME "PS/2 ESDI"
+#define DEVICE_REQUEST do_ps2esdi_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == CDU31A_CDROM_MAJOR)
+
+#define DEVICE_NAME "CDU31A"
+#define DEVICE_REQUEST do_cdu31a_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == ACSI_MAJOR) && (defined(CONFIG_ATARI_ACSI) || defined(CONFIG_ATARI_ACSI_MODULE))
+
+#define DEVICE_NAME "ACSI"
+#define DEVICE_INTR do_acsi
+#define DEVICE_REQUEST do_acsi_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#elif (MAJOR_NR == MITSUMI_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcd */
+#define DEVICE_REQUEST do_mcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MITSUMI_X_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcdx */
+#define DEVICE_REQUEST do_mcdx_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #1"
+#define DEVICE_REQUEST do_sbpcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM2_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #2"
+#define DEVICE_REQUEST do_sbpcd2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM3_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #3"
+#define DEVICE_REQUEST do_sbpcd3_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM4_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #4"
+#define DEVICE_REQUEST do_sbpcd4_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == AZTECH_CDROM_MAJOR)
+
+#define DEVICE_NAME "Aztech CD-ROM"
+#define DEVICE_REQUEST do_aztcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CDU535_CDROM_MAJOR)
+
+#define DEVICE_NAME "SONY-CDU535"
+#define DEVICE_INTR do_cdu535
+#define DEVICE_REQUEST do_cdu535_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == GOLDSTAR_CDROM_MAJOR)
+
+#define DEVICE_NAME "Goldstar R420"
+#define DEVICE_REQUEST do_gscd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CM206_CDROM_MAJOR)
+#define DEVICE_NAME "Philips/LMS CD-ROM cm206"
+#define DEVICE_REQUEST do_cm206_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == OPTICS_CDROM_MAJOR)
+
+#define DEVICE_NAME "DOLPHIN 8000AT CD-ROM"
+#define DEVICE_REQUEST do_optcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SANYO_CDROM_MAJOR)
+
+#define DEVICE_NAME "Sanyo H94A CD-ROM"
+#define DEVICE_REQUEST do_sjcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == APBLOCK_MAJOR)
+
+#define DEVICE_NAME "apblock"
+#define DEVICE_REQUEST ap_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DDV_MAJOR)
+
+#define DEVICE_NAME "ddv"
+#define DEVICE_REQUEST ddv_request
+#define DEVICE_NR(device) (MINOR(device)>>PARTN_BITS)
+
+#elif (MAJOR_NR == MFM_ACORN_MAJOR)
+
+#define DEVICE_NAME "mfm disk"
+#define DEVICE_INTR do_mfm
+#define DEVICE_REQUEST do_mfm_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == NBD_MAJOR)
+
+#define DEVICE_NAME "nbd"
+#define DEVICE_REQUEST do_nbd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MDISK_MAJOR)
+
+#define DEVICE_NAME "mdisk"
+#define DEVICE_REQUEST mdisk_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DASD_MAJOR)
+
+#define DEVICE_NAME "dasd"
+#define DEVICE_REQUEST do_dasd_request
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+
+#elif (MAJOR_NR == I2O_MAJOR)
+
+#define DEVICE_NAME "I2O block"
+#define DEVICE_REQUEST i2ob_request
+#define DEVICE_NR(device) (MINOR(device)>>4)
+
+#elif (MAJOR_NR == COMPAQ_SMART2_MAJOR)
+
+#define DEVICE_NAME "ida"
+#define TIMEOUT_VALUE (25*HZ)
+#define DEVICE_REQUEST do_ida_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#elif (MAJOR_NR == XLBLK_MAJOR)
+
+#define DEVICE_NAME "xeno disk"
+#define DEVICE_REQUEST do_xlblk_request
+/* #define DEVICE_INTR */
+#define DEVICE_NR(device) (MINOR(device))
+
+#endif /* MAJOR_NR == whatever */
+
+/* provide DEVICE_xxx defaults, if not explicitly defined
+ * above in the MAJOR_NR==xxx if-elif tree */
+#ifndef DEVICE_ON
+#define DEVICE_ON(device) do {} while (0)
+#endif
+#ifndef DEVICE_OFF
+#define DEVICE_OFF(device) do {} while (0)
+#endif
+
+#if (MAJOR_NR != SCSI_TAPE_MAJOR) && (MAJOR_NR != OSST_MAJOR)
+#if !defined(IDE_DRIVER)
+
+#ifndef CURRENT
+#define CURRENT blkdev_entry_next_request(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+#ifndef QUEUE_EMPTY
+#define QUEUE_EMPTY list_empty(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+
+#ifndef DEVICE_NAME
+#define DEVICE_NAME "unknown"
+#endif
+
+#define CURRENT_DEV DEVICE_NR(CURRENT->rq_dev)
+
+#ifdef DEVICE_INTR
+static void (*DEVICE_INTR)(void) = NULL;
+#endif
+
+#define SET_INTR(x) (DEVICE_INTR = (x))
+
+#ifdef DEVICE_REQUEST
+static void (DEVICE_REQUEST)(request_queue_t *);
+#endif
+
+#ifdef DEVICE_INTR
+#define CLEAR_INTR SET_INTR(NULL)
+#else
+#define CLEAR_INTR
+#endif
+
+#define INIT_REQUEST \
+ if (QUEUE_EMPTY) {\
+ CLEAR_INTR; \
+ return; \
+ } \
+ if (MAJOR(CURRENT->rq_dev) != MAJOR_NR) \
+ panic(DEVICE_NAME ": request list destroyed"); \
+ if (CURRENT->bh) { \
+ if (!buffer_locked(CURRENT->bh)) \
+ panic(DEVICE_NAME ": block not locked"); \
+ }
+
+#endif /* !defined(IDE_DRIVER) */
+
+
+#ifndef LOCAL_END_REQUEST /* If we have our own end_request, we do not want to include this mess */
+
+#if ! SCSI_BLK_MAJOR(MAJOR_NR) && (MAJOR_NR != COMPAQ_SMART2_MAJOR)
+
+static inline void end_request(int uptodate) {
+ struct request *req = CURRENT;
+
+ if (end_that_request_first(req, uptodate, DEVICE_NAME))
+ return;
+
+#ifndef DEVICE_NO_RANDOM
+ add_blkdev_randomness(MAJOR(req->rq_dev));
+#endif
+ DEVICE_OFF(req->rq_dev);
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+}
+
+#endif /* ! SCSI_BLK_MAJOR(MAJOR_NR) */
+#endif /* LOCAL_END_REQUEST */
+
+#endif /* (MAJOR_NR != SCSI_TAPE_MAJOR) */
+#endif /* defined(MAJOR_NR) || defined(IDE_DRIVER) */
+
+#endif /* _BLK_H */
--- /dev/null
+#ifndef _LINUX_MAJOR_H
+#define _LINUX_MAJOR_H
+
+/*
+ * This file has definitions for major device numbers.
+ * For the device number assignments, see Documentation/devices.txt.
+ */
+
+/* limits */
+
+/*
+ * Important: Don't change this to 256. Major number 255 is and must be
+ * reserved for future expansion into a larger dev_t space.
+ */
+#define MAX_CHRDEV 255
+#define MAX_BLKDEV 255
+
+#define UNNAMED_MAJOR 0
+#define MEM_MAJOR 1
+#define RAMDISK_MAJOR 1
+#define FLOPPY_MAJOR 2
+#define PTY_MASTER_MAJOR 2
+#define IDE0_MAJOR 3
+#define PTY_SLAVE_MAJOR 3
+#define HD_MAJOR IDE0_MAJOR
+#define TTY_MAJOR 4
+#define TTYAUX_MAJOR 5
+#define LP_MAJOR 6
+#define VCS_MAJOR 7
+#define LOOP_MAJOR 7
+#define SCSI_DISK0_MAJOR 8
+#define SCSI_TAPE_MAJOR 9
+#define MD_MAJOR 9
+#define MISC_MAJOR 10
+#define SCSI_CDROM_MAJOR 11
+#define QIC02_TAPE_MAJOR 12
+#define XT_DISK_MAJOR 13
+#define SOUND_MAJOR 14
+#define CDU31A_CDROM_MAJOR 15
+#define JOYSTICK_MAJOR 15
+#define GOLDSTAR_CDROM_MAJOR 16
+#define OPTICS_CDROM_MAJOR 17
+#define SANYO_CDROM_MAJOR 18
+#define CYCLADES_MAJOR 19
+#define CYCLADESAUX_MAJOR 20
+#define MITSUMI_X_CDROM_MAJOR 20
+#define MFM_ACORN_MAJOR 21 /* ARM Linux /dev/mfm */
+#define SCSI_GENERIC_MAJOR 21
+#define Z8530_MAJOR 34
+#define DIGI_MAJOR 23
+#define IDE1_MAJOR 22
+#define DIGICU_MAJOR 22
+#define MITSUMI_CDROM_MAJOR 23
+#define CDU535_CDROM_MAJOR 24
+#define STL_SERIALMAJOR 24
+#define MATSUSHITA_CDROM_MAJOR 25
+#define STL_CALLOUTMAJOR 25
+#define MATSUSHITA_CDROM2_MAJOR 26
+#define QIC117_TAPE_MAJOR 27
+#define MATSUSHITA_CDROM3_MAJOR 27
+#define MATSUSHITA_CDROM4_MAJOR 28
+#define STL_SIOMEMMAJOR 28
+#define ACSI_MAJOR 28
+#define AZTECH_CDROM_MAJOR 29
+#define GRAPHDEV_MAJOR 29 /* SparcLinux & Linux/68k /dev/fb */
+#define SHMIQ_MAJOR 85 /* Linux/mips, SGI /dev/shmiq */
+#define CM206_CDROM_MAJOR 32
+#define IDE2_MAJOR 33
+#define IDE3_MAJOR 34
+#define XPRAM_MAJOR 35 /* expanded storage on S/390 = "slow ram" */
+ /* proposed by Peter */
+#define NETLINK_MAJOR 36
+#define PS2ESDI_MAJOR 36
+#define IDETAPE_MAJOR 37
+#define Z2RAM_MAJOR 37
+#define APBLOCK_MAJOR 38 /* AP1000 Block device */
+#define DDV_MAJOR 39 /* AP1000 DDV block device */
+#define NBD_MAJOR 43 /* Network block device */
+#define RISCOM8_NORMAL_MAJOR 48
+#define DAC960_MAJOR 48 /* 48..55 */
+#define RISCOM8_CALLOUT_MAJOR 49
+#define MKISS_MAJOR 55
+#define DSP56K_MAJOR 55 /* DSP56001 processor device */
+
+#define IDE4_MAJOR 56
+#define IDE5_MAJOR 57
+
+#define LVM_BLK_MAJOR 58 /* Logical Volume Manager */
+
+#define SCSI_DISK1_MAJOR 65
+#define SCSI_DISK2_MAJOR 66
+#define SCSI_DISK3_MAJOR 67
+#define SCSI_DISK4_MAJOR 68
+#define SCSI_DISK5_MAJOR 69
+#define SCSI_DISK6_MAJOR 70
+#define SCSI_DISK7_MAJOR 71
+
+
+#define COMPAQ_SMART2_MAJOR 72
+#define COMPAQ_SMART2_MAJOR1 73
+#define COMPAQ_SMART2_MAJOR2 74
+#define COMPAQ_SMART2_MAJOR3 75
+#define COMPAQ_SMART2_MAJOR4 76
+#define COMPAQ_SMART2_MAJOR5 77
+#define COMPAQ_SMART2_MAJOR6 78
+#define COMPAQ_SMART2_MAJOR7 79
+
+#define SPECIALIX_NORMAL_MAJOR 75
+#define SPECIALIX_CALLOUT_MAJOR 76
+
+#define COMPAQ_CISS_MAJOR 104
+#define COMPAQ_CISS_MAJOR1 105
+#define COMPAQ_CISS_MAJOR2 106
+#define COMPAQ_CISS_MAJOR3 107
+#define COMPAQ_CISS_MAJOR4 108
+#define COMPAQ_CISS_MAJOR5 109
+#define COMPAQ_CISS_MAJOR6 110
+#define COMPAQ_CISS_MAJOR7 111
+
+#define ATARAID_MAJOR 114
+
+#define DASD_MAJOR 94 /* Official assignations from Peter */
+
+#define MDISK_MAJOR 95 /* Official assignations from Peter */
+
+#define I2O_MAJOR 80 /* 80->87 */
+
+#define IDE6_MAJOR 88
+#define IDE7_MAJOR 89
+#define IDE8_MAJOR 90
+#define IDE9_MAJOR 91
+
+#define UBD_MAJOR 98
+
+#define AURORA_MAJOR 79
+
+#define JSFD_MAJOR 99
+
+#define PHONE_MAJOR 100
+
+#define LVM_CHAR_MAJOR 109 /* Logical Volume Manager */
+
+#define UMEM_MAJOR 116 /* http://www.umem.com/ Battery Backed RAM */
+
+#define XLBLK_MAJOR 123 /* XenoLinux Block Device */
+
+#define RTF_MAJOR 150
+#define RAW_MAJOR 162
+
+#define USB_ACM_MAJOR 166
+#define USB_ACM_AUX_MAJOR 167
+#define USB_CHAR_MAJOR 180
+
+#define UNIX98_PTY_MASTER_MAJOR 128
+#define UNIX98_PTY_MAJOR_COUNT 8
+#define UNIX98_PTY_SLAVE_MAJOR (UNIX98_PTY_MASTER_MAJOR+UNIX98_PTY_MAJOR_COUNT)
+
+#define VXVM_MAJOR 199 /* VERITAS volume i/o driver */
+#define VXSPEC_MAJOR 200 /* VERITAS volume config driver */
+#define VXDMP_MAJOR 201 /* VERITAS volume multipath driver */
+
+#define MSR_MAJOR 202
+#define CPUID_MAJOR 203
+
+#define OSST_MAJOR 206 /* OnStream-SCx0 SCSI tape */
+
+#define IBM_TTY3270_MAJOR 227 /* Official allocations now */
+#define IBM_FS3270_MAJOR 228
+
+/*
+ * Tests for SCSI devices.
+ */
+
+#define SCSI_DISK_MAJOR(M) ((M) == SCSI_DISK0_MAJOR || \
+ ((M) >= SCSI_DISK1_MAJOR && (M) <= SCSI_DISK7_MAJOR))
+
+#define SCSI_BLK_MAJOR(M) \
+ (SCSI_DISK_MAJOR(M) \
+ || (M) == SCSI_CDROM_MAJOR)
+
+static __inline__ int scsi_blk_major(int m) {
+ return SCSI_BLK_MAJOR(m);
+}
+
+/*
+ * Tests for IDE devices
+ */
+#define IDE_DISK_MAJOR(M) ((M) == IDE0_MAJOR || (M) == IDE1_MAJOR || \
+ (M) == IDE2_MAJOR || (M) == IDE3_MAJOR || \
+ (M) == IDE4_MAJOR || (M) == IDE5_MAJOR || \
+ (M) == IDE6_MAJOR || (M) == IDE7_MAJOR || \
+ (M) == IDE8_MAJOR || (M) == IDE9_MAJOR)
+
+static __inline__ int ide_blk_major(int m)
+{
+ return IDE_DISK_MAJOR(m);
+}
+
+#endif
--- /dev/null
+/*
+ * linux/include/linux/sunrpc/debug.h
+ *
+ * Debugging support for sunrpc module
+ *
+ * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LINUX_SUNRPC_DEBUG_H_
+#define _LINUX_SUNRPC_DEBUG_H_
+
+#include <linux/config.h>
+
+#include <linux/timer.h>
+#include <linux/tqueue.h>
+
+/*
+ * Enable RPC debugging/profiling.
+ */
+/*#ifdef CONFIG_SYSCTL*/
+/*#define RPC_DEBUG*/
+/*#endif*/
+/* #define RPC_PROFILE */
+
+/*
+ * RPC debug facilities
+ */
+#define RPCDBG_XPRT 0x0001
+#define RPCDBG_CALL 0x0002
+#define RPCDBG_DEBUG 0x0004
+#define RPCDBG_NFS 0x0008
+#define RPCDBG_AUTH 0x0010
+#define RPCDBG_PMAP 0x0020
+#define RPCDBG_SCHED 0x0040
+#define RPCDBG_SVCSOCK 0x0100
+#define RPCDBG_SVCDSP 0x0200
+#define RPCDBG_MISC 0x0400
+#define RPCDBG_ALL 0x7fff
+
+#ifdef __KERNEL__
+
+/*
+ * Debugging macros etc
+ */
+#ifdef RPC_DEBUG
+extern unsigned int rpc_debug;
+extern unsigned int nfs_debug;
+extern unsigned int nfsd_debug;
+extern unsigned int nlm_debug;
+#endif
+
+#define dprintk(args...) dfprintk(FACILITY, ## args)
+
+#undef ifdebug
+#ifdef RPC_DEBUG
+# define ifdebug(fac) if (rpc_debug & RPCDBG_##fac)
+# define dfprintk(fac, args...) do { ifdebug(fac) printk(args); } while(0)
+# define RPC_IFDEBUG(x) x
+#else
+# define dfprintk(fac, args...) do ; while (0)
+# define RPC_IFDEBUG(x)
+#endif
+
+#ifdef RPC_PROFILE
+# define pprintk(args...) printk(## args)
+#else
+# define pprintk(args...) do ; while (0)
+#endif
+
+/*
+ * Sysctl interface for RPC debugging
+ */
+#ifdef RPC_DEBUG
+void rpc_register_sysctl(void);
+void rpc_unregister_sysctl(void);
+#endif
+
+#endif /* __KERNEL__ */
+
+/*
+ * Declarations for the sysctl debug interface, which allows to read or
+ * change the debug flags for rpc, nfs, nfsd, and lockd. Since the sunrpc
+ * module currently registers its sysctl table dynamically, the sysctl path
+ * for module FOO is <CTL_SUNRPC, CTL_FOODEBUG>.
+ */
+#define CTL_SUNRPC 7249 /* arbitrary and hopefully unused */
+
+enum {
+ CTL_RPCDEBUG = 1,
+ CTL_NFSDEBUG,
+ CTL_NFSDDEBUG,
+ CTL_NLMDEBUG,
+};
+
+#endif /* _LINUX_SUNRPC_DEBUG_H_ */
--- /dev/null
+/*
+ * linux/init/main.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * GK 2/5/95 - Changed to support mounting root fs via NFS
+ * Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96
+ * Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96
+ * Simplified starting of init: Michael A. Griffith <grif@acm.org>
+ */
+
+#define __KERNEL_SYSCALLS__
+
+#include <linux/config.h>
+#include <linux/proc_fs.h>
+#include <linux/devfs_fs_kernel.h>
+#include <linux/unistd.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/delay.h>
+#include <linux/utsname.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/smp_lock.h>
+#include <linux/blk.h>
+#include <linux/hdreg.h>
+#include <linux/iobuf.h>
+#include <linux/bootmem.h>
+#include <linux/tty.h>
+
+#include <asm/io.h>
+#include <asm/bugs.h>
+
+#if defined(CONFIG_ARCH_S390)
+#include <asm/s390mach.h>
+#include <asm/ccwcache.h>
+#endif
+
+#ifdef CONFIG_PCI
+#include <linux/pci.h>
+#endif
+
+#ifdef CONFIG_DIO
+#include <linux/dio.h>
+#endif
+
+#ifdef CONFIG_ZORRO
+#include <linux/zorro.h>
+#endif
+
+#ifdef CONFIG_MTRR
+# include <asm/mtrr.h>
+#endif
+
+#ifdef CONFIG_NUBUS
+#include <linux/nubus.h>
+#endif
+
+#ifdef CONFIG_ISAPNP
+#include <linux/isapnp.h>
+#endif
+
+#ifdef CONFIG_IRDA
+extern int irda_proto_init(void);
+extern int irda_device_init(void);
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/smp.h>
+#endif
+
+#if defined(CONFIG_KDB)
+#include <linux/kdb.h>
+#endif
+
+/*
+ * Versions of gcc older than that listed below may actually compile
+ * and link okay, but the end product can have subtle run time bugs.
+ * To avoid associated bogus bug reports, we flatly refuse to compile
+ * with a gcc that is known to be too old from the very beginning.
+ */
+#if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 91)
+#error Sorry, your GCC is too old. It builds incorrect kernels.
+#endif
+
+extern char _stext, _etext;
+extern char *linux_banner;
+
+static int init(void *);
+
+extern void init_IRQ(void);
+extern void init_modules(void);
+extern void sock_init(void);
+extern void fork_init(unsigned long);
+extern void mca_init(void);
+extern void sbus_init(void);
+extern void ppc_init(void);
+extern void sysctl_init(void);
+extern void signals_init(void);
+extern int init_pcmcia_ds(void);
+
+extern void free_initmem(void);
+
+#ifdef CONFIG_TC
+extern void tc_init(void);
+#endif
+
+extern void ecard_init(void);
+
+#if defined(CONFIG_SYSVIPC)
+extern void ipc_init(void);
+#endif
+
+/*
+ * Boot command-line arguments
+ */
+#define MAX_INIT_ARGS 8
+#define MAX_INIT_ENVS 8
+
+extern void time_init(void);
+extern void softirq_init(void);
+
+int rows, cols;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+unsigned int real_root_dev; /* do_proc_dointvec cannot handle kdev_t */
+#endif
+
+int root_mountflags = MS_RDONLY;
+char *execute_command;
+char root_device_name[64];
+
+
+static char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
+static char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
+
+static int __init profile_setup(char *str)
+{
+ int par;
+ if (get_option(&str,&par)) prof_shift = par;
+ return 1;
+}
+
+__setup("profile=", profile_setup);
+
+
+static struct dev_name_struct {
+ const char *name;
+ const int num;
+} root_dev_names[] __initdata = {
+ { "nfs", 0x00ff },
+ { "xhda", 0x7b00 },
+ { "hda", 0x0300 },
+ { "hdb", 0x0340 },
+ { "loop", 0x0700 },
+ { "hdc", 0x1600 },
+ { "hdd", 0x1640 },
+ { "hde", 0x2100 },
+ { "hdf", 0x2140 },
+ { "hdg", 0x2200 },
+ { "hdh", 0x2240 },
+ { "hdi", 0x3800 },
+ { "hdj", 0x3840 },
+ { "hdk", 0x3900 },
+ { "hdl", 0x3940 },
+ { "hdm", 0x5800 },
+ { "hdn", 0x5840 },
+ { "hdo", 0x5900 },
+ { "hdp", 0x5940 },
+ { "hdq", 0x5A00 },
+ { "hdr", 0x5A40 },
+ { "hds", 0x5B00 },
+ { "hdt", 0x5B40 },
+ { "sda", 0x0800 },
+ { "sdb", 0x0810 },
+ { "sdc", 0x0820 },
+ { "sdd", 0x0830 },
+ { "sde", 0x0840 },
+ { "sdf", 0x0850 },
+ { "sdg", 0x0860 },
+ { "sdh", 0x0870 },
+ { "sdi", 0x0880 },
+ { "sdj", 0x0890 },
+ { "sdk", 0x08a0 },
+ { "sdl", 0x08b0 },
+ { "sdm", 0x08c0 },
+ { "sdn", 0x08d0 },
+ { "sdo", 0x08e0 },
+ { "sdp", 0x08f0 },
+ { "ada", 0x1c00 },
+ { "adb", 0x1c10 },
+ { "adc", 0x1c20 },
+ { "add", 0x1c30 },
+ { "ade", 0x1c40 },
+ { "fd", 0x0200 },
+ { "md", 0x0900 },
+ { "xda", 0x0d00 },
+ { "xdb", 0x0d40 },
+ { "ram", 0x0100 },
+ { "scd", 0x0b00 },
+ { "mcd", 0x1700 },
+ { "cdu535", 0x1800 },
+ { "sonycd", 0x1800 },
+ { "aztcd", 0x1d00 },
+ { "cm206cd", 0x2000 },
+ { "gscd", 0x1000 },
+ { "sbpcd", 0x1900 },
+ { "eda", 0x2400 },
+ { "edb", 0x2440 },
+ { "pda", 0x2d00 },
+ { "pdb", 0x2d10 },
+ { "pdc", 0x2d20 },
+ { "pdd", 0x2d30 },
+ { "pcd", 0x2e00 },
+ { "pf", 0x2f00 },
+ { "apblock", APBLOCK_MAJOR << 8},
+ { "ddv", DDV_MAJOR << 8},
+ { "jsfd", JSFD_MAJOR << 8},
+#if defined(CONFIG_ARCH_S390)
+ { "dasda", (DASD_MAJOR << MINORBITS) },
+ { "dasdb", (DASD_MAJOR << MINORBITS) + (1 << 2) },
+ { "dasdc", (DASD_MAJOR << MINORBITS) + (2 << 2) },
+ { "dasdd", (DASD_MAJOR << MINORBITS) + (3 << 2) },
+ { "dasde", (DASD_MAJOR << MINORBITS) + (4 << 2) },
+ { "dasdf", (DASD_MAJOR << MINORBITS) + (5 << 2) },
+ { "dasdg", (DASD_MAJOR << MINORBITS) + (6 << 2) },
+ { "dasdh", (DASD_MAJOR << MINORBITS) + (7 << 2) },
+#endif
+#if defined(CONFIG_BLK_CPQ_DA) || defined(CONFIG_BLK_CPQ_DA_MODULE)
+ { "ida/c0d0p",0x4800 },
+ { "ida/c0d1p",0x4810 },
+ { "ida/c0d2p",0x4820 },
+ { "ida/c0d3p",0x4830 },
+ { "ida/c0d4p",0x4840 },
+ { "ida/c0d5p",0x4850 },
+ { "ida/c0d6p",0x4860 },
+ { "ida/c0d7p",0x4870 },
+ { "ida/c0d8p",0x4880 },
+ { "ida/c0d9p",0x4890 },
+ { "ida/c0d10p",0x48A0 },
+ { "ida/c0d11p",0x48B0 },
+ { "ida/c0d12p",0x48C0 },
+ { "ida/c0d13p",0x48D0 },
+ { "ida/c0d14p",0x48E0 },
+ { "ida/c0d15p",0x48F0 },
+#endif
+#if defined(CONFIG_BLK_CPQ_CISS_DA) || defined(CONFIG_BLK_CPQ_CISS_DA_MODULE)
+ { "cciss/c0d0p",0x6800 },
+ { "cciss/c0d1p",0x6810 },
+ { "cciss/c0d2p",0x6820 },
+ { "cciss/c0d3p",0x6830 },
+ { "cciss/c0d4p",0x6840 },
+ { "cciss/c0d5p",0x6850 },
+ { "cciss/c0d6p",0x6860 },
+ { "cciss/c0d7p",0x6870 },
+ { "cciss/c0d8p",0x6880 },
+ { "cciss/c0d9p",0x6890 },
+ { "cciss/c0d10p",0x68A0 },
+ { "cciss/c0d11p",0x68B0 },
+ { "cciss/c0d12p",0x68C0 },
+ { "cciss/c0d13p",0x68D0 },
+ { "cciss/c0d14p",0x68E0 },
+ { "cciss/c0d15p",0x68F0 },
+#endif
+ { "nftla", 0x5d00 },
+ { "nftlb", 0x5d10 },
+ { "nftlc", 0x5d20 },
+ { "nftld", 0x5d30 },
+ { "ftla", 0x2c00 },
+ { "ftlb", 0x2c08 },
+ { "ftlc", 0x2c10 },
+ { "ftld", 0x2c18 },
+ { "mtdblock", 0x1f00 },
+ { NULL, 0 }
+};
+
+kdev_t __init name_to_kdev_t(char *line)
+{
+ int base = 0;
+
+ if (strncmp(line,"/dev/",5) == 0) {
+ struct dev_name_struct *dev = root_dev_names;
+ line += 5;
+ do {
+ int len = strlen(dev->name);
+ if (strncmp(line,dev->name,len) == 0) {
+ line += len;
+ base = dev->num;
+ break;
+ }
+ dev++;
+ } while (dev->name);
+ }
+ return to_kdev_t(base + simple_strtoul(line,NULL,base?10:16));
+}
+
+static int __init root_dev_setup(char *line)
+{
+ int i;
+ char ch;
+
+ ROOT_DEV = name_to_kdev_t(line);
+ memset (root_device_name, 0, sizeof root_device_name);
+ if (strncmp (line, "/dev/", 5) == 0) line += 5;
+ for (i = 0; i < sizeof root_device_name - 1; ++i)
+ {
+ ch = line[i];
+ if ( isspace (ch) || (ch == ',') || (ch == '\0') ) break;
+ root_device_name[i] = ch;
+ }
+ return 1;
+}
+
+__setup("root=", root_dev_setup);
+
+static int __init checksetup(char *line)
+{
+ struct kernel_param *p;
+
+ p = &__setup_start;
+ do {
+ int n = strlen(p->str);
+ if (!strncmp(line,p->str,n)) {
+ if (p->setup_func(line+n))
+ return 1;
+ }
+ p++;
+ } while (p < &__setup_end);
+ return 0;
+}
+
+/* this should be approx 2 Bo*oMips to start (note initial shift), and will
+ still work even if initially too large, it will just take slightly longer */
+unsigned long loops_per_jiffy = (1<<12);
+
+/* This is the number of bits of precision for the loops_per_jiffy. Each
+ bit takes on average 1.5/HZ seconds. This (like the original) is a little
+ better than 1% */
+#define LPS_PREC 8
+
+void __init calibrate_delay(void)
+{
+ unsigned long ticks, loopbit;
+ int lps_precision = LPS_PREC;
+
+ loops_per_jiffy = (1<<12);
+
+ printk("Calibrating delay loop... ");
+ while (loops_per_jiffy <<= 1) {
+ /* wait for "start of" clock tick */
+ ticks = jiffies;
+ while (ticks == jiffies)
+ /* nothing */;
+ /* Go .. */
+ ticks = jiffies;
+ __delay(loops_per_jiffy);
+ ticks = jiffies - ticks;
+ if (ticks)
+ break;
+ }
+
+/* Do a binary approximation to get loops_per_jiffy set to equal one clock
+ (up to lps_precision bits) */
+ loops_per_jiffy >>= 1;
+ loopbit = loops_per_jiffy;
+ while ( lps_precision-- && (loopbit >>= 1) ) {
+ loops_per_jiffy |= loopbit;
+ ticks = jiffies;
+ while (ticks == jiffies);
+ ticks = jiffies;
+ __delay(loops_per_jiffy);
+ if (jiffies != ticks) /* longer than 1 tick */
+ loops_per_jiffy &= ~loopbit;
+ }
+
+/* Round the value and print it */
+ printk("%lu.%02lu BogoMIPS\n",
+ loops_per_jiffy/(500000/HZ),
+ (loops_per_jiffy/(5000/HZ)) % 100);
+}
+
+static int __init readonly(char *str)
+{
+ if (*str)
+ return 0;
+ root_mountflags |= MS_RDONLY;
+ return 1;
+}
+
+static int __init readwrite(char *str)
+{
+ if (*str)
+ return 0;
+ root_mountflags &= ~MS_RDONLY;
+ return 1;
+}
+
+static int __init debug_kernel(char *str)
+{
+ if (*str)
+ return 0;
+ console_loglevel = 10;
+ return 1;
+}
+
+static int __init quiet_kernel(char *str)
+{
+ if (*str)
+ return 0;
+ console_loglevel = 4;
+ return 1;
+}
+
+__setup("ro", readonly);
+__setup("rw", readwrite);
+__setup("debug", debug_kernel);
+__setup("quiet", quiet_kernel);
+
+/*
+ * This is a simple kernel command line parsing function: it parses
+ * the command line, and fills in the arguments/environment to init
+ * as appropriate. Any cmd-line option is taken to be an environment
+ * variable if it contains the character '='.
+ *
+ * This routine also checks for options meant for the kernel.
+ * These options are not given to init - they are for internal kernel use only.
+ */
+static void __init parse_options(char *line)
+{
+ char *next,*quote;
+ int args, envs;
+
+ if (!*line)
+ return;
+ args = 0;
+ envs = 1; /* TERM is set to 'linux' by default */
+ next = line;
+ while ((line = next) != NULL) {
+ quote = strchr(line,'"');
+ next = strchr(line, ' ');
+ while (next != NULL && quote != NULL && quote < next) {
+ /* we found a left quote before the next blank
+ * now we have to find the matching right quote
+ */
+ next = strchr(quote+1, '"');
+ if (next != NULL) {
+ quote = strchr(next+1, '"');
+ next = strchr(next+1, ' ');
+ }
+ }
+ if (next != NULL)
+ *next++ = 0;
+#if defined(CONFIG_KDB)
+ /* kdb, kdb=on, kdb=off, kdb=early */
+ if (strncmp(line, "kdb", 3) == 0) {
+ if (line[3] == '\0') {
+ /* Backward compatibility, kdb with no option means early activation */
+ printk("Boot flag kdb with no options is obsolete, use kdb=early\n");
+ kdb_on = 1;
+ kdb_flags |= KDB_FLAG_EARLYKDB;
+ continue;
+ }
+ if (line[3] == '=') {
+ if (strcmp(line+4, "on") == 0) {
+ kdb_on = 1;
+ continue;
+ }
+ if (strcmp(line+4, "off") == 0) {
+ kdb_on = 0;
+ continue;
+ }
+ if (strcmp(line+4, "early") == 0) {
+ kdb_on = 1;
+ kdb_flags |= KDB_FLAG_EARLYKDB;
+ continue;
+ }
+ printk("Boot flag %s not recognised, assumed to be environment variable\n", line);
+ }
+ }
+#endif
+ if (!strncmp(line,"init=",5)) {
+ line += 5;
+ execute_command = line;
+ /* In case LILO is going to boot us with default command line,
+ * it prepends "auto" before the whole cmdline which makes
+ * the shell think it should execute a script with such name.
+ * So we ignore all arguments entered _before_ init=... [MJ]
+ */
+ args = 0;
+ continue;
+ }
+ if (checksetup(line))
+ continue;
+
+ /*
+ * Then check if it's an environment variable or
+ * an option.
+ */
+ if (strchr(line,'=')) {
+ if (envs >= MAX_INIT_ENVS)
+ break;
+ envp_init[++envs] = line;
+ } else {
+ if (args >= MAX_INIT_ARGS)
+ break;
+ if (*line)
+ argv_init[++args] = line;
+ }
+ }
+ argv_init[args+1] = NULL;
+ envp_init[envs+1] = NULL;
+}
+
+
+extern void setup_arch(char **);
+extern void cpu_idle(void);
+
+unsigned long wait_init_idle;
+
+#ifndef CONFIG_SMP
+
+#ifdef CONFIG_X86_LOCAL_APIC
+static void __init smp_init(void)
+{
+ APIC_init_uniprocessor();
+}
+#else
+#define smp_init() do { } while (0)
+#endif
+
+#else
+
+
+/* Called by boot processor to activate the rest. */
+static void __init smp_init(void)
+{
+ /* Get other processors into their bootup holding patterns. */
+ smp_boot_cpus();
+ wait_init_idle = cpu_online_map;
+ clear_bit(current->processor, &wait_init_idle); /* Don't wait on me! */
+
+ smp_threads_ready=1;
+ smp_commence();
+
+ /* Wait for the other cpus to set up their idle processes */
+ printk("Waiting on wait_init_idle (map = 0x%lx)\n", wait_init_idle);
+ while (wait_init_idle) {
+ cpu_relax();
+ barrier();
+ }
+ printk("All processors have done init_idle\n");
+}
+
+#endif
+
+/*
+ * We need to finalize in a non-__init function or else race conditions
+ * between the root thread and the init thread may cause start_kernel to
+ * be reaped by free_initmem before the root thread has proceeded to
+ * cpu_idle.
+ */
+
+static void rest_init(void)
+{
+ kernel_thread(init, NULL, CLONE_FS | CLONE_FILES | CLONE_SIGNAL);
+ unlock_kernel();
+ current->need_resched = 1;
+ cpu_idle();
+}
+
+/*
+ * Activate the first processor.
+ */
+
+asmlinkage void __init start_kernel(void)
+{
+ char * command_line;
+ unsigned long mempages;
+ extern char saved_command_line[];
+/*
+ * Interrupts are still disabled. Do necessary setups, then
+ * enable them
+ */
+ lock_kernel();
+ printk(linux_banner);
+ setup_arch(&command_line);
+ printk("Kernel command line: %s\n", saved_command_line);
+ parse_options(command_line);
+ trap_init();
+ init_IRQ();
+ sched_init();
+ softirq_init();
+ time_init();
+
+ /*
+ * HACK ALERT! This is early. We're enabling the console before
+ * we've done PCI setups etc, and console_init() must be aware of
+ * this. But we do want output early, in case something goes wrong.
+ */
+ console_init();
+#ifdef CONFIG_MODULES
+ init_modules();
+#endif
+ if (prof_shift) {
+ unsigned int size;
+ /* only text is profiled */
+ prof_len = (unsigned long) &_etext - (unsigned long) &_stext;
+ prof_len >>= prof_shift;
+
+ size = prof_len * sizeof(unsigned int) + PAGE_SIZE-1;
+ prof_buffer = (unsigned int *) alloc_bootmem(size);
+ }
+
+ kmem_cache_init();
+ sti();
+ calibrate_delay();
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (initrd_start && !initrd_below_start_ok &&
+ initrd_start < min_low_pfn << PAGE_SHIFT) {
+ printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
+ "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);
+ initrd_start = 0;
+ }
+#endif
+ mem_init();
+ kmem_cache_sizes_init();
+#if defined(CONFIG_KDB)
+ kdb_init();
+ if (KDB_FLAG(EARLYKDB)) {
+ KDB_ENTER();
+ }
+#endif
+ mempages = num_physpages;
+
+ fork_init(mempages);
+ proc_caches_init();
+ vfs_caches_init(mempages);
+ buffer_init(mempages);
+ page_cache_init(mempages);
+#if defined(CONFIG_ARCH_S390)
+ ccwcache_init();
+#endif
+ signals_init();
+#ifdef CONFIG_PROC_FS
+ proc_root_init();
+#endif
+#if defined(CONFIG_SYSVIPC)
+ ipc_init();
+#endif
+ check_bugs();
+ printk("POSIX conformance testing by UNIFIX\n");
+
+ /*
+ * We count on the initial thread going ok
+ * Like idlers init is an unlocked kernel thread, which will
+ * make syscalls (and thus be locked).
+ */
+ smp_init();
+ rest_init();
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static int do_linuxrc(void * shell)
+{
+ static char *argv[] = { "linuxrc", NULL, };
+
+ close(0);close(1);close(2);
+ setsid();
+ (void) open("/dev/console",O_RDWR,0);
+ (void) dup(0);
+ (void) dup(0);
+ return execve(shell, argv, envp_init);
+}
+
+#endif
+
+struct task_struct *child_reaper = &init_task;
+
+static void __init do_initcalls(void)
+{
+ initcall_t *call;
+
+ call = &__initcall_start;
+ do {
+ (*call)();
+ call++;
+ } while (call < &__initcall_end);
+
+ /* Make sure there is no pending stuff from the initcall sequence */
+ flush_scheduled_tasks();
+}
+
+/*
+ * Ok, the machine is now initialized. None of the devices
+ * have been touched yet, but the CPU subsystem is up and
+ * running, and memory and process management works.
+ *
+ * Now we can finally start doing some real work..
+ */
+static void __init do_basic_setup(void)
+{
+
+ /*
+ * Tell the world that we're going to be the grim
+ * reaper of innocent orphaned children.
+ *
+ * We don't want people to have to make incorrect
+ * assumptions about where in the task array this
+ * can be found.
+ */
+ child_reaper = current;
+
+#if defined(CONFIG_MTRR) /* Do this after SMP initialization */
+/*
+ * We should probably create some architecture-dependent "fixup after
+ * everything is up" style function where this would belong better
+ * than in init/main.c..
+ */
+ mtrr_init();
+#endif
+
+#ifdef CONFIG_SYSCTL
+ sysctl_init();
+#endif
+
+ /*
+ * Ok, at this point all CPU's should be initialized, so
+ * we can start looking into devices..
+ */
+#if defined(CONFIG_ARCH_S390)
+ s390_init_machine_check();
+#endif
+
+#ifdef CONFIG_PCI
+ pci_init();
+#endif
+#ifdef CONFIG_SBUS
+ sbus_init();
+#endif
+#if defined(CONFIG_PPC)
+ ppc_init();
+#endif
+#ifdef CONFIG_MCA
+ mca_init();
+#endif
+#ifdef CONFIG_ARCH_ACORN
+ ecard_init();
+#endif
+#ifdef CONFIG_ZORRO
+ zorro_init();
+#endif
+#ifdef CONFIG_DIO
+ dio_init();
+#endif
+#ifdef CONFIG_NUBUS
+ nubus_init();
+#endif
+#ifdef CONFIG_ISAPNP
+ isapnp_init();
+#endif
+#ifdef CONFIG_TC
+ tc_init();
+#endif
+
+ /* Networking initialization needs a process context */
+ sock_init();
+
+ start_context_thread();
+ do_initcalls();
+
+#ifdef CONFIG_IRDA
+ irda_proto_init();
+ irda_device_init(); /* Must be done after protocol initialization */
+#endif
+#ifdef CONFIG_PCMCIA
+ init_pcmcia_ds(); /* Do this last */
+#endif
+}
+
+extern void rd_load(void);
+extern void initrd_load(void);
+
+/*
+ * Prepare the namespace - decide what/where to mount, load ramdisks, etc.
+ */
+static void prepare_namespace(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ int real_root_mountflags = root_mountflags;
+ if (!initrd_start)
+ mount_initrd = 0;
+ if (mount_initrd)
+ root_mountflags &= ~MS_RDONLY;
+ real_root_dev = ROOT_DEV;
+#endif
+
+#ifdef CONFIG_BLK_DEV_RAM
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (mount_initrd)
+ initrd_load();
+ else
+#endif
+ rd_load();
+#endif
+
+ /* Mount the root filesystem.. */
+ mount_root();
+
+ mount_devfs_fs ();
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ root_mountflags = real_root_mountflags;
+ if (mount_initrd && ROOT_DEV != real_root_dev
+ && MAJOR(ROOT_DEV) == RAMDISK_MAJOR && MINOR(ROOT_DEV) == 0) {
+ int error;
+ int i, pid;
+
+ pid = kernel_thread(do_linuxrc, "/linuxrc", SIGCHLD);
+ if (pid > 0) {
+ while (pid != wait(&i)) {
+ current->policy |= SCHED_YIELD;
+ schedule();
+ }
+ }
+ if (MAJOR(real_root_dev) != RAMDISK_MAJOR
+ || MINOR(real_root_dev) != 0) {
+ error = change_root(real_root_dev,"/initrd");
+ if (error)
+ printk(KERN_ERR "Change root to /initrd: "
+ "error %d\n",error);
+ }
+ }
+#endif
+}
+
+static int init(void * unused)
+{
+ lock_kernel();
+ do_basic_setup();
+
+ prepare_namespace();
+
+ /*
+ * Ok, we have completed the initial bootup, and
+ * we're essentially up and running. Get rid of the
+ * initmem segments and start the user-mode stuff..
+ */
+ free_initmem();
+ unlock_kernel();
+
+ if (open("/dev/console", O_RDWR, 0) < 0)
+ printk("Warning: unable to open an initial console.\n");
+
+ (void) dup(0);
+ (void) dup(0);
+
+ /*
+ * We try each of these until one succeeds.
+ *
+ * The Bourne shell can be used instead of init if we are
+ * trying to recover a really broken machine.
+ */
+
+ if (execute_command)
+ execve(execute_command,argv_init,envp_init);
+ execve("/sbin/init",argv_init,envp_init);
+ execve("/etc/init",argv_init,envp_init);
+ execve("/bin/init",argv_init,envp_init);
+ execve("/bin/sh",argv_init,envp_init);
+ panic("No init found. Try passing init= option to kernel.");
+}
--- /dev/null
+/*
+ * linux/kernel/panic.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * This function is used through-out the kernel (including mm and fs)
+ * to indicate a major problem.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/sysrq.h>
+#include <linux/interrupt.h>
+
+asmlinkage void sys_sync(void); /* it's really int */
+
+int panic_timeout;
+
+struct notifier_block *panic_notifier_list;
+
+static int __init panic_setup(char *str)
+{
+ panic_timeout = simple_strtoul(str, NULL, 0);
+ return 1;
+}
+
+__setup("panic=", panic_setup);
+
+/**
+ * panic - halt the system
+ * @fmt: The text string to print
+ *
+ * Display a message, then perform cleanups. Functions in the panic
+ * notifier list are called after the filesystem cache is flushed (when possible).
+ *
+ * This function never returns.
+ */
+
+NORET_TYPE void panic(const char * fmt, ...)
+{
+ static char buf[1024];
+ va_list args;
+#if defined(CONFIG_ARCH_S390)
+ unsigned long caller = (unsigned long) __builtin_return_address(0);
+#endif
+
+ bust_spinlocks(1);
+ va_start(args, fmt);
+ vsprintf(buf, fmt, args);
+ va_end(args);
+ printk(KERN_EMERG "Kernel panic: %s\n",buf);
+ if (in_interrupt())
+ printk(KERN_EMERG "In interrupt handler - not syncing\n");
+ else if (!current->pid)
+ printk(KERN_EMERG "In idle task - not syncing\n");
+ else
+ sys_sync();
+ bust_spinlocks(0);
+
+#ifdef CONFIG_SMP
+ smp_send_stop();
+#endif
+
+ notifier_call_chain(&panic_notifier_list, 0, NULL);
+
+ if (panic_timeout > 0)
+ {
+ /*
+ * Delay timeout seconds before rebooting the machine.
+ * We can't use the "normal" timers since we just panicked..
+ */
+ printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
+ mdelay(panic_timeout*1000);
+ /*
+ * Should we run the reboot notifier. For the moment Im
+ * choosing not too. It might crash, be corrupt or do
+ * more harm than good for other reasons.
+ */
+ machine_restart(NULL);
+ }
+#ifdef __sparc__
+ {
+ extern int stop_a_enabled;
+ /* Make sure the user can actually press L1-A */
+ stop_a_enabled = 1;
+ printk("Press L1-A to return to the boot prom\n");
+ }
+#endif
+#if defined(CONFIG_ARCH_S390)
+ disabled_wait(caller);
+#endif
+ sti();
+ for(;;) {
+ CHECK_EMERGENCY_SYNC
+#if defined(CONFIG_XENO)
+ HYPERVISOR_exit();
+#endif
+ }
+}
+
+/**
+ * print_tainted - return a string to represent the kernel taint state.
+ *
+ * The string is overwritten by the next call to print_taint().
+ */
+
+const char *print_tainted()
+{
+ static char buf[20];
+ if (tainted) {
+ snprintf(buf, sizeof(buf), "Tainted: %c%c",
+ tainted & 1 ? 'P' : 'G',
+ tainted & 2 ? 'F' : ' ');
+ }
+ else
+ snprintf(buf, sizeof(buf), "Not tainted");
+ return(buf);
+}
+
+int tainted = 0;
--- /dev/null
+export INSTALL_MOD_PATH=/local/scratch/kaf24/xeno/linux-install
+ARCH=xeno make -j 4 bzImage
+ARCH=xeno make -j 4 modules
+ARCH=xeno INSTALL_MOD_PATH=/anfs/nta3/xeno-roots/kaf24/root0 really make modules_install
+ARCH=xeno INSTALL_MOD_PATH=/anfs/nta3/xeno-roots/kaf24/root1 really make modules_install
+cp arch/xeno/boot/image.gz /usr/groups/pegasus/boot/kaf24/meteors/vmlinux.gz
--- /dev/null
+/*
+ * linux/mm/memory.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ */
+
+/*
+ * demand-loading started 01.12.91 - seems it is high on the list of
+ * things wanted, and it should be easy to implement. - Linus
+ */
+
+/*
+ * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
+ * pages started 02.12.91, seems to work. - Linus.
+ *
+ * Tested sharing by executing about 30 /bin/sh: under the old kernel it
+ * would have taken more than the 6M I have free, but it worked well as
+ * far as I could see.
+ *
+ * Also corrected some "invalidate()"s - I wasn't doing enough of them.
+ */
+
+/*
+ * Real VM (paging to/from disk) started 18.12.91. Much more work and
+ * thought has to go into this. Oh, well..
+ * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
+ * Found it. Everything seems to work now.
+ * 20.12.91 - Ok, making the swap-device changeable like the root.
+ */
+
+/*
+ * 05.04.94 - Multi-page memory management added for v1.1.
+ * Idea by Alex Bligh (alex@cconcepts.co.uk)
+ *
+ * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
+ * (Gerhard.Wichert@pdb.siemens.de)
+ */
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+
+unsigned long max_mapnr;
+unsigned long num_physpages;
+void * high_memory;
+struct page *highmem_start_page;
+
+/*
+ * We special-case the C-O-W ZERO_PAGE, because it's such
+ * a common occurrence (no need to read the page to know
+ * that it's zero - better for the cache and memory subsystem).
+ */
+static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address)
+{
+ if (from == ZERO_PAGE(address)) {
+ clear_user_highpage(to, address);
+ return;
+ }
+ copy_user_highpage(to, from, address);
+}
+
+mem_map_t * mem_map;
+
+/*
+ * Called by TLB shootdown
+ */
+void __free_pte(pte_t pte)
+{
+ struct page *page = pte_page(pte);
+ if ((!VALID_PAGE(page)) || PageReserved(page))
+ return;
+ if (pte_dirty(pte))
+ set_page_dirty(page);
+ free_page_and_swap_cache(page);
+}
+
+
+/*
+ * Note: this doesn't free the actual pages themselves. That
+ * has been handled earlier when unmapping all the memory regions.
+ */
+static inline void free_one_pmd(pmd_t * dir)
+{
+ pte_t * pte;
+
+ if (pmd_none(*dir))
+ return;
+ if (pmd_bad(*dir)) {
+ pmd_ERROR(*dir);
+ pmd_clear(dir);
+ return;
+ }
+ pte = pte_offset(dir, 0);
+ pmd_clear(dir);
+ pte_free(pte);
+}
+
+static inline void free_one_pgd(pgd_t * dir)
+{
+ int j;
+ pmd_t * pmd;
+
+ if (pgd_none(*dir))
+ return;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return;
+ }
+ pmd = pmd_offset(dir, 0);
+ pgd_clear(dir);
+ for (j = 0; j < PTRS_PER_PMD ; j++) {
+ prefetchw(pmd+j+(PREFETCH_STRIDE/16));
+ free_one_pmd(pmd+j);
+ }
+ pmd_free(pmd);
+}
+
+/* Low and high watermarks for page table cache.
+ The system should try to have pgt_water[0] <= cache elements <= pgt_water[1]
+ */
+int pgt_cache_water[2] = { 25, 50 };
+
+/* Returns the number of pages freed */
+int check_pgt_cache(void)
+{
+ return do_check_pgt_cache(pgt_cache_water[0], pgt_cache_water[1]);
+}
+
+
+/*
+ * This function clears all user-level page tables of a process - this
+ * is needed by execve(), so that old pages aren't in the way.
+ */
+void clear_page_tables(struct mm_struct *mm, unsigned long first, int nr)
+{
+ pgd_t * page_dir = mm->pgd;
+
+ spin_lock(&mm->page_table_lock);
+ page_dir += first;
+ do {
+ free_one_pgd(page_dir);
+ page_dir++;
+ } while (--nr);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+
+ /* keep the page table cache within bounds */
+ check_pgt_cache();
+}
+
+#define PTE_TABLE_MASK ((PTRS_PER_PTE-1) * sizeof(pte_t))
+#define PMD_TABLE_MASK ((PTRS_PER_PMD-1) * sizeof(pmd_t))
+
+/*
+ * copy one vm_area from one task to the other. Assumes the page tables
+ * already present in the new task to be cleared in the whole range
+ * covered by this vma.
+ *
+ * 08Jan98 Merged into one routine from several inline routines to reduce
+ * variable count and make things faster. -jj
+ *
+ * dst->page_table_lock is held on entry and exit,
+ * but may be dropped within pmd_alloc() and pte_alloc().
+ */
+int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
+ struct vm_area_struct *vma)
+{
+ pgd_t * src_pgd, * dst_pgd;
+ unsigned long address = vma->vm_start;
+ unsigned long end = vma->vm_end;
+ unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE;
+
+ src_pgd = pgd_offset(src, address)-1;
+ dst_pgd = pgd_offset(dst, address)-1;
+
+ for (;;) {
+ pmd_t * src_pmd, * dst_pmd;
+
+ src_pgd++; dst_pgd++;
+
+ /* copy_pmd_range */
+
+ if (pgd_none(*src_pgd))
+ goto skip_copy_pmd_range;
+ if (pgd_bad(*src_pgd)) {
+ pgd_ERROR(*src_pgd);
+ pgd_clear(src_pgd);
+skip_copy_pmd_range: address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ if (!address || (address >= end))
+ goto out;
+ continue;
+ }
+
+ src_pmd = pmd_offset(src_pgd, address);
+ dst_pmd = pmd_alloc(dst, dst_pgd, address);
+ if (!dst_pmd)
+ goto nomem;
+
+ do {
+ pte_t * src_pte, * dst_pte;
+
+ /* copy_pte_range */
+
+ if (pmd_none(*src_pmd))
+ goto skip_copy_pte_range;
+ if (pmd_bad(*src_pmd)) {
+ pmd_ERROR(*src_pmd);
+ pmd_clear(src_pmd);
+skip_copy_pte_range: address = (address + PMD_SIZE) & PMD_MASK;
+ if (address >= end)
+ goto out;
+ goto cont_copy_pmd_range;
+ }
+
+ src_pte = pte_offset(src_pmd, address);
+ dst_pte = pte_alloc(dst, dst_pmd, address);
+ if (!dst_pte)
+ goto nomem;
+
+ spin_lock(&src->page_table_lock);
+ do {
+ pte_t pte = *src_pte;
+ struct page *ptepage;
+
+ /* copy_one_pte */
+
+ if (pte_none(pte))
+ goto cont_copy_pte_range_noset;
+ if (!pte_present(pte)) {
+ swap_duplicate(pte_to_swp_entry(pte));
+ goto cont_copy_pte_range;
+ }
+ ptepage = pte_page(pte);
+ if ((!VALID_PAGE(ptepage)) ||
+ PageReserved(ptepage))
+ goto cont_copy_pte_range;
+
+ /* If it's a COW mapping, write protect it both in the parent and the child */
+ if (cow) {
+ /* XENO modification: modified ordering here to avoid RaW hazard. */
+ pte = *src_pte;
+ pte = pte_wrprotect(pte);
+ ptep_set_wrprotect(src_pte);
+ }
+
+ /* If it's a shared mapping, mark it clean in the child */
+ if (vma->vm_flags & VM_SHARED)
+ pte = pte_mkclean(pte);
+ pte = pte_mkold(pte);
+ get_page(ptepage);
+ dst->rss++;
+
+cont_copy_pte_range: set_pte(dst_pte, pte);
+cont_copy_pte_range_noset: address += PAGE_SIZE;
+ if (address >= end)
+ goto out_unlock;
+ src_pte++;
+ dst_pte++;
+ } while ((unsigned long)src_pte & PTE_TABLE_MASK);
+ spin_unlock(&src->page_table_lock);
+
+cont_copy_pmd_range: src_pmd++;
+ dst_pmd++;
+ } while ((unsigned long)src_pmd & PMD_TABLE_MASK);
+ }
+out_unlock:
+ spin_unlock(&src->page_table_lock);
+out:
+ return 0;
+nomem:
+ return -ENOMEM;
+}
+
+/*
+ * Return indicates whether a page was freed so caller can adjust rss
+ */
+static inline void forget_pte(pte_t page)
+{
+ if (!pte_none(page)) {
+ printk("forget_pte: old mapping existed!\n");
+ BUG();
+ }
+}
+
+static inline int zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address, unsigned long size)
+{
+ unsigned long offset;
+ pte_t * ptep;
+ int freed = 0;
+
+ if (pmd_none(*pmd))
+ return 0;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return 0;
+ }
+ ptep = pte_offset(pmd, address);
+ offset = address & ~PMD_MASK;
+ if (offset + size > PMD_SIZE)
+ size = PMD_SIZE - offset;
+ size &= PAGE_MASK;
+ for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
+ pte_t pte = *ptep;
+ if (pte_none(pte))
+ continue;
+ if (pte_present(pte)) {
+ struct page *page = pte_page(pte);
+ if (VALID_PAGE(page) && !PageReserved(page))
+ freed ++;
+ /* This will eventually call __free_pte on the pte. */
+ tlb_remove_page(tlb, ptep, address + offset);
+ } else {
+ free_swap_and_cache(pte_to_swp_entry(pte));
+ pte_clear(ptep);
+ }
+ }
+
+ return freed;
+}
+
+static inline int zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir, unsigned long address, unsigned long size)
+{
+ pmd_t * pmd;
+ unsigned long end;
+ int freed;
+
+ if (pgd_none(*dir))
+ return 0;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return 0;
+ }
+ pmd = pmd_offset(dir, address);
+ end = address + size;
+ if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
+ end = ((address + PGDIR_SIZE) & PGDIR_MASK);
+ freed = 0;
+ do {
+ freed += zap_pte_range(tlb, pmd, address, end - address);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address < end);
+ return freed;
+}
+
+/*
+ * remove user pages in a given range.
+ */
+void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
+{
+ mmu_gather_t *tlb;
+ pgd_t * dir;
+ unsigned long start = address, end = address + size;
+ int freed = 0;
+
+ dir = pgd_offset(mm, address);
+
+ /*
+ * This is a long-lived spinlock. That's fine.
+ * There's no contention, because the page table
+ * lock only protects against kswapd anyway, and
+ * even if kswapd happened to be looking at this
+ * process we _want_ it to get stuck.
+ */
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ flush_cache_range(mm, address, end);
+ tlb = tlb_gather_mmu(mm);
+
+ do {
+ freed += zap_pmd_range(tlb, dir, address, end - address);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+
+ /* this will flush any remaining tlb entries */
+ tlb_finish_mmu(tlb, start, end);
+
+ /*
+ * Update rss for the mm_struct (not necessarily current->mm)
+ * Notice that rss is an unsigned long.
+ */
+ if (mm->rss > freed)
+ mm->rss -= freed;
+ else
+ mm->rss = 0;
+ spin_unlock(&mm->page_table_lock);
+}
+
+
+/*
+ * Do a quick page-table lookup for a single page.
+ */
+static struct page * follow_page(unsigned long address, int write)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
+
+ pgd = pgd_offset(current->mm, address);
+ if (pgd_none(*pgd) || pgd_bad(*pgd))
+ goto out;
+
+ pmd = pmd_offset(pgd, address);
+ if (pmd_none(*pmd) || pmd_bad(*pmd))
+ goto out;
+
+ ptep = pte_offset(pmd, address);
+ if (!ptep)
+ goto out;
+
+ pte = *ptep;
+ if (pte_present(pte)) {
+ if (!write ||
+ (pte_write(pte) && pte_dirty(pte)))
+ return pte_page(pte);
+ }
+
+out:
+ return 0;
+}
+
+/*
+ * Given a physical address, is there a useful struct page pointing to
+ * it? This may become more complex in the future if we start dealing
+ * with IO-aperture pages in kiobufs.
+ */
+
+static inline struct page * get_page_map(struct page *page)
+{
+ if (!VALID_PAGE(page))
+ return 0;
+ return page;
+}
+
+/*
+ * Force in an entire range of pages from the current process's user VA,
+ * and pin them in physical memory.
+ */
+
+#define dprintk(x...)
+int map_user_kiobuf(int rw, struct kiobuf *iobuf, unsigned long va, size_t len)
+{
+ unsigned long ptr, end;
+ int err;
+ struct mm_struct * mm;
+ struct vm_area_struct * vma = 0;
+ struct page * map;
+ int i;
+ int datain = (rw == READ);
+
+ /* Make sure the iobuf is not already mapped somewhere. */
+ if (iobuf->nr_pages)
+ return -EINVAL;
+
+ mm = current->mm;
+ dprintk ("map_user_kiobuf: begin\n");
+
+ ptr = va & PAGE_MASK;
+ end = (va + len + PAGE_SIZE - 1) & PAGE_MASK;
+ err = expand_kiobuf(iobuf, (end - ptr) >> PAGE_SHIFT);
+ if (err)
+ return err;
+
+ down_read(&mm->mmap_sem);
+
+ err = -EFAULT;
+ iobuf->locked = 0;
+ iobuf->offset = va & ~PAGE_MASK;
+ iobuf->length = len;
+
+ i = 0;
+
+ /*
+ * First of all, try to fault in all of the necessary pages
+ */
+ while (ptr < end) {
+ if (!vma || ptr >= vma->vm_end) {
+ vma = find_vma(current->mm, ptr);
+ if (!vma)
+ goto out_unlock;
+ if (vma->vm_start > ptr) {
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto out_unlock;
+ if (expand_stack(vma, ptr))
+ goto out_unlock;
+ }
+ if (((datain) && (!(vma->vm_flags & VM_WRITE))) ||
+ (!(vma->vm_flags & VM_READ))) {
+ err = -EACCES;
+ goto out_unlock;
+ }
+ }
+ spin_lock(&mm->page_table_lock);
+ while (!(map = follow_page(ptr, datain))) {
+ int ret;
+
+ spin_unlock(&mm->page_table_lock);
+ ret = handle_mm_fault(current->mm, vma, ptr, datain);
+ if (ret <= 0) {
+ if (!ret)
+ goto out_unlock;
+ else {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+ }
+ spin_lock(&mm->page_table_lock);
+ }
+ map = get_page_map(map);
+ if (map) {
+ flush_dcache_page(map);
+ page_cache_get(map);
+ } else
+ printk (KERN_INFO "Mapped page missing [%d]\n", i);
+ spin_unlock(&mm->page_table_lock);
+ iobuf->maplist[i] = map;
+ iobuf->nr_pages = ++i;
+
+ ptr += PAGE_SIZE;
+ }
+
+ up_read(&mm->mmap_sem);
+ dprintk ("map_user_kiobuf: end OK\n");
+ return 0;
+
+ out_unlock:
+ up_read(&mm->mmap_sem);
+ unmap_kiobuf(iobuf);
+ dprintk ("map_user_kiobuf: end %d\n", err);
+ return err;
+}
+
+/*
+ * Mark all of the pages in a kiobuf as dirty
+ *
+ * We need to be able to deal with short reads from disk: if an IO error
+ * occurs, the number of bytes read into memory may be less than the
+ * size of the kiobuf, so we have to stop marking pages dirty once the
+ * requested byte count has been reached.
+ */
+
+void mark_dirty_kiobuf(struct kiobuf *iobuf, int bytes)
+{
+ int index, offset, remaining;
+ struct page *page;
+
+ index = iobuf->offset >> PAGE_SHIFT;
+ offset = iobuf->offset & ~PAGE_MASK;
+ remaining = bytes;
+ if (remaining > iobuf->length)
+ remaining = iobuf->length;
+
+ while (remaining > 0 && index < iobuf->nr_pages) {
+ page = iobuf->maplist[index];
+
+ if (!PageReserved(page))
+ SetPageDirty(page);
+
+ remaining -= (PAGE_SIZE - offset);
+ offset = 0;
+ index++;
+ }
+}
+
+/*
+ * Unmap all of the pages referenced by a kiobuf. We release the pages,
+ * and unlock them if they were locked.
+ */
+
+void unmap_kiobuf (struct kiobuf *iobuf)
+{
+ int i;
+ struct page *map;
+
+ for (i = 0; i < iobuf->nr_pages; i++) {
+ map = iobuf->maplist[i];
+ if (map) {
+ if (iobuf->locked)
+ UnlockPage(map);
+ page_cache_release(map);
+ }
+ }
+
+ iobuf->nr_pages = 0;
+ iobuf->locked = 0;
+}
+
+
+/*
+ * Lock down all of the pages of a kiovec for IO.
+ *
+ * If any page is mapped twice in the kiovec, we return the error -EINVAL.
+ *
+ * The optional wait parameter causes the lock call to block until all
+ * pages can be locked if set. If wait==0, the lock operation is
+ * aborted if any locked pages are found and -EAGAIN is returned.
+ */
+
+int lock_kiovec(int nr, struct kiobuf *iovec[], int wait)
+{
+ struct kiobuf *iobuf;
+ int i, j;
+ struct page *page, **ppage;
+ int doublepage = 0;
+ int repeat = 0;
+
+ repeat:
+
+ for (i = 0; i < nr; i++) {
+ iobuf = iovec[i];
+
+ if (iobuf->locked)
+ continue;
+
+ ppage = iobuf->maplist;
+ for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
+ page = *ppage;
+ if (!page)
+ continue;
+
+ if (TryLockPage(page)) {
+ while (j--) {
+ struct page *tmp = *--ppage;
+ if (tmp)
+ UnlockPage(tmp);
+ }
+ goto retry;
+ }
+ }
+ iobuf->locked = 1;
+ }
+
+ return 0;
+
+ retry:
+
+ /*
+ * We couldn't lock one of the pages. Undo the locking so far,
+ * wait on the page we got to, and try again.
+ */
+
+ unlock_kiovec(nr, iovec);
+ if (!wait)
+ return -EAGAIN;
+
+ /*
+ * Did the release also unlock the page we got stuck on?
+ */
+ if (!PageLocked(page)) {
+ /*
+ * If so, we may well have the page mapped twice
+ * in the IO address range. Bad news. Of
+ * course, it _might_ just be a coincidence,
+ * but if it happens more than once, chances
+ * are we have a double-mapped page.
+ */
+ if (++doublepage >= 3)
+ return -EINVAL;
+
+ /* Try again... */
+ wait_on_page(page);
+ }
+
+ if (++repeat < 16)
+ goto repeat;
+ return -EAGAIN;
+}
+
+/*
+ * Unlock all of the pages of a kiovec after IO.
+ */
+
+int unlock_kiovec(int nr, struct kiobuf *iovec[])
+{
+ struct kiobuf *iobuf;
+ int i, j;
+ struct page *page, **ppage;
+
+ for (i = 0; i < nr; i++) {
+ iobuf = iovec[i];
+
+ if (!iobuf->locked)
+ continue;
+ iobuf->locked = 0;
+
+ ppage = iobuf->maplist;
+ for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
+ page = *ppage;
+ if (!page)
+ continue;
+ UnlockPage(page);
+ }
+ }
+ return 0;
+}
+
+static inline void zeromap_pte_range(pte_t * pte, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address), prot));
+ pte_t oldpage = ptep_get_and_clear(pte);
+ set_pte(pte, zero_pte);
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ zeromap_pte_range(pte, address, end - address, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int zeromap_page_range(unsigned long address, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = address;
+ unsigned long end = address + size;
+ struct mm_struct *mm = current->mm;
+
+ dir = pgd_offset(mm, address);
+ flush_cache_range(mm, beg, end);
+ if (address >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, address);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = zeromap_pmd_range(mm, pmd, address, end - address, prot);
+ if (error)
+ break;
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * maps a range of physical memory into the requested pages. the old
+ * mappings are removed. any references to nonexistent pages results
+ * in null mappings (currently treated as "copy-on-access")
+ */
+static inline void remap_pte_range(pte_t * pte, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ struct page *page;
+ pte_t oldpage;
+ oldpage = ptep_get_and_clear(pte);
+
+ page = virt_to_page(__va(phys_addr));
+ if ((!VALID_PAGE(page)) || PageReserved(page))
+ set_pte(pte, mk_pte_phys(phys_addr, prot));
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ phys_addr += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ phys_addr -= address;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ remap_pte_range(pte, address, end - address, address + phys_addr, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+/* Note: this is only safe if the mm semaphore is held when called. */
+int remap_page_range(unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = from;
+ unsigned long end = from + size;
+ struct mm_struct *mm = current->mm;
+
+ phys_addr -= from;
+ dir = pgd_offset(mm, from);
+ flush_cache_range(mm, beg, end);
+ if (from >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, from);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = remap_pmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
+ if (error)
+ break;
+ from = (from + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (from && (from < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * Establish a new mapping:
+ * - flush the old one
+ * - update the page tables
+ * - inform the TLB about the new one
+ *
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void establish_pte(struct vm_area_struct * vma, unsigned long address, pte_t *page_table, pte_t entry)
+{
+ set_pte(page_table, entry);
+ flush_tlb_page(vma, address);
+ update_mmu_cache(vma, address, entry);
+}
+
+/*
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address,
+ pte_t *page_table)
+{
+ flush_page_to_ram(new_page);
+ flush_cache_page(vma, address);
+ establish_pte(vma, address, page_table, pte_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot))));
+}
+
+/*
+ * This routine handles present pages, when users try to write
+ * to a shared page. It is done by copying the page to a new address
+ * and decrementing the shared-page counter for the old page.
+ *
+ * Goto-purists beware: the only reason for goto's here is that it results
+ * in better assembly code.. The "default" path will see no jumps at all.
+ *
+ * Note that this routine assumes that the protection checks have been
+ * done by the caller (the low-level page fault routine in most cases).
+ * Thus we can safely just mark it writable once we've done any necessary
+ * COW.
+ *
+ * We also mark the page dirty at this point even though the page will
+ * change only once the write actually happens. This avoids a few races,
+ * and potentially makes it more efficient.
+ *
+ * We hold the mm semaphore and the page_table_lock on entry and exit
+ * with the page_table_lock released.
+ */
+static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, pte_t *page_table, pte_t pte)
+{
+ struct page *old_page, *new_page;
+
+ old_page = pte_page(pte);
+ if (!VALID_PAGE(old_page))
+ goto bad_wp_page;
+
+ if (!TryLockPage(old_page)) {
+ int reuse = can_share_swap_page(old_page);
+ unlock_page(old_page);
+ if (reuse) {
+ flush_cache_page(vma, address);
+ establish_pte(vma, address, page_table, pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
+ spin_unlock(&mm->page_table_lock);
+ return 1; /* Minor fault */
+ }
+ }
+
+ /*
+ * Ok, we need to copy. Oh, well..
+ */
+ page_cache_get(old_page);
+ spin_unlock(&mm->page_table_lock);
+
+ new_page = alloc_page(GFP_HIGHUSER);
+ if (!new_page)
+ goto no_mem;
+ copy_cow_page(old_page,new_page,address);
+
+ /*
+ * Re-check the pte - we dropped the lock
+ */
+ spin_lock(&mm->page_table_lock);
+ if (pte_same(*page_table, pte)) {
+ if (PageReserved(old_page))
+ ++mm->rss;
+ break_cow(vma, new_page, address, page_table);
+ lru_cache_add(new_page);
+
+ /* Free the old page.. */
+ new_page = old_page;
+ }
+ spin_unlock(&mm->page_table_lock);
+ page_cache_release(new_page);
+ page_cache_release(old_page);
+ return 1; /* Minor fault */
+
+bad_wp_page:
+ spin_unlock(&mm->page_table_lock);
+ printk("do_wp_page: bogus page at address %08lx (page 0x%lx)\n",address,(unsigned long)old_page);
+ return -1;
+no_mem:
+ page_cache_release(old_page);
+ return -1;
+}
+
+static void vmtruncate_list(struct vm_area_struct *mpnt, unsigned long pgoff)
+{
+ do {
+ struct mm_struct *mm = mpnt->vm_mm;
+ unsigned long start = mpnt->vm_start;
+ unsigned long end = mpnt->vm_end;
+ unsigned long len = end - start;
+ unsigned long diff;
+
+ /* mapping wholly truncated? */
+ if (mpnt->vm_pgoff >= pgoff) {
+ zap_page_range(mm, start, len);
+ continue;
+ }
+
+ /* mapping wholly unaffected? */
+ len = len >> PAGE_SHIFT;
+ diff = pgoff - mpnt->vm_pgoff;
+ if (diff >= len)
+ continue;
+
+ /* Ok, partially affected.. */
+ start += diff << PAGE_SHIFT;
+ len = (len - diff) << PAGE_SHIFT;
+ zap_page_range(mm, start, len);
+ } while ((mpnt = mpnt->vm_next_share) != NULL);
+}
+
+/*
+ * Handle all mappings that got truncated by a "truncate()"
+ * system call.
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page. Ugly, but necessary.
+ */
+int vmtruncate(struct inode * inode, loff_t offset)
+{
+ unsigned long pgoff;
+ struct address_space *mapping = inode->i_mapping;
+ unsigned long limit;
+
+ if (inode->i_size < offset)
+ goto do_expand;
+ inode->i_size = offset;
+ spin_lock(&mapping->i_shared_lock);
+ if (!mapping->i_mmap && !mapping->i_mmap_shared)
+ goto out_unlock;
+
+ pgoff = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ if (mapping->i_mmap != NULL)
+ vmtruncate_list(mapping->i_mmap, pgoff);
+ if (mapping->i_mmap_shared != NULL)
+ vmtruncate_list(mapping->i_mmap_shared, pgoff);
+
+out_unlock:
+ spin_unlock(&mapping->i_shared_lock);
+ truncate_inode_pages(mapping, offset);
+ goto out_truncate;
+
+do_expand:
+ limit = current->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY) {
+ if (inode->i_size >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ goto out;
+ }
+ if (offset > limit) {
+ send_sig(SIGXFSZ, current, 0);
+ offset = limit;
+ }
+ }
+ inode->i_size = offset;
+
+out_truncate:
+ if (inode->i_op && inode->i_op->truncate) {
+ lock_kernel();
+ inode->i_op->truncate(inode);
+ unlock_kernel();
+ }
+out:
+ return 0;
+}
+
+/*
+ * Primitive swap readahead code. We simply read an aligned block of
+ * (1 << page_cluster) entries in the swap area. This method is chosen
+ * because it doesn't cost us any seek time. We also make sure to queue
+ * the 'original' request together with the readahead ones...
+ */
+void swapin_readahead(swp_entry_t entry)
+{
+ int i, num;
+ struct page *new_page;
+ unsigned long offset;
+
+ /*
+ * Get the number of handles we should do readahead io to.
+ */
+ num = valid_swaphandles(entry, &offset);
+ for (i = 0; i < num; offset++, i++) {
+ /* Ok, do the async read-ahead now */
+ new_page = read_swap_cache_async(SWP_ENTRY(SWP_TYPE(entry), offset));
+ if (!new_page)
+ break;
+ page_cache_release(new_page);
+ }
+ return;
+}
+
+/*
+ * We hold the mm semaphore and the page_table_lock on entry and
+ * should release the pagetable lock on exit..
+ */
+static int do_swap_page(struct mm_struct * mm,
+ struct vm_area_struct * vma, unsigned long address,
+ pte_t * page_table, pte_t orig_pte, int write_access)
+{
+ struct page *page;
+ swp_entry_t entry = pte_to_swp_entry(orig_pte);
+ pte_t pte;
+ int ret = 1;
+
+ spin_unlock(&mm->page_table_lock);
+ page = lookup_swap_cache(entry);
+ if (!page) {
+ swapin_readahead(entry);
+ page = read_swap_cache_async(entry);
+ if (!page) {
+ /*
+ * Back out if somebody else faulted in this pte while
+ * we released the page table lock.
+ */
+ int retval;
+ spin_lock(&mm->page_table_lock);
+ retval = pte_same(*page_table, orig_pte) ? -1 : 1;
+ spin_unlock(&mm->page_table_lock);
+ return retval;
+ }
+
+ /* Had to read the page from swap area: Major fault */
+ ret = 2;
+ }
+
+ lock_page(page);
+
+ /*
+ * Back out if somebody else faulted in this pte while we
+ * released the page table lock.
+ */
+ spin_lock(&mm->page_table_lock);
+ if (!pte_same(*page_table, orig_pte)) {
+ spin_unlock(&mm->page_table_lock);
+ unlock_page(page);
+ page_cache_release(page);
+ return 1;
+ }
+
+ /* The page isn't present yet, go ahead with the fault. */
+
+ swap_free(entry);
+ if (vm_swap_full())
+ remove_exclusive_swap_page(page);
+
+ mm->rss++;
+ pte = mk_pte(page, vma->vm_page_prot);
+ if (write_access && can_share_swap_page(page))
+ pte = pte_mkdirty(pte_mkwrite(pte));
+ unlock_page(page);
+
+ flush_page_to_ram(page);
+ flush_icache_page(vma, page);
+ set_pte(page_table, pte);
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, address, pte);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return ret;
+}
+
+/*
+ * We are called with the MM semaphore and page_table_lock
+ * spinlock held to protect against concurrent faults in
+ * multithreaded programs.
+ */
+static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, int write_access, unsigned long addr)
+{
+ pte_t entry;
+
+ /* Read-only mapping of ZERO_PAGE. */
+ entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
+
+ /* ..except if it's a write access */
+ if (write_access) {
+ struct page *page;
+
+ /* Allocate our own private page. */
+ spin_unlock(&mm->page_table_lock);
+
+ page = alloc_page(GFP_HIGHUSER);
+ if (!page)
+ goto no_mem;
+ clear_user_highpage(page, addr);
+
+ spin_lock(&mm->page_table_lock);
+ if (!pte_none(*page_table)) {
+ page_cache_release(page);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+ }
+ mm->rss++;
+ flush_page_to_ram(page);
+ entry = pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
+ lru_cache_add(page);
+ }
+
+ set_pte(page_table, entry);
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, addr, entry);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return 1; /* Minor fault */
+
+no_mem:
+ return -1;
+}
+
+/*
+ * do_no_page() tries to create a new page mapping. It aggressively
+ * tries to share with existing pages, but makes a separate copy if
+ * the "write_access" parameter is true in order to avoid the next
+ * page fault.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * This is called with the MM semaphore held and the page table
+ * spinlock held. Exit with the spinlock released.
+ */
+static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access, pte_t *page_table)
+{
+ struct page * new_page;
+ pte_t entry;
+
+ if (!vma->vm_ops || !vma->vm_ops->nopage)
+ return do_anonymous_page(mm, vma, page_table, write_access, address);
+ spin_unlock(&mm->page_table_lock);
+
+ new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
+
+ if (new_page == NULL) /* no page was available -- SIGBUS */
+ return 0;
+ if (new_page == NOPAGE_OOM)
+ return -1;
+
+ /*
+ * Should we do an early C-O-W break?
+ */
+ if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ struct page * page = alloc_page(GFP_HIGHUSER);
+ if (!page)
+ return -1;
+ copy_highpage(page, new_page);
+ page_cache_release(new_page);
+ lru_cache_add(page);
+ new_page = page;
+ }
+
+ spin_lock(&mm->page_table_lock);
+ /*
+ * This silly early PAGE_DIRTY setting removes a race
+ * due to the bad i386 page protection. But it's valid
+ * for other architectures too.
+ *
+ * Note that if write_access is true, we either now have
+ * an exclusive copy of the page, or this is a shared mapping,
+ * so we can make it writable and dirty to avoid having to
+ * handle that later.
+ */
+ /* Only go through if we didn't race with anybody else... */
+ if (pte_none(*page_table)) {
+ ++mm->rss;
+ flush_page_to_ram(new_page);
+ flush_icache_page(vma, new_page);
+ entry = mk_pte(new_page, vma->vm_page_prot);
+ if (write_access)
+ entry = pte_mkwrite(pte_mkdirty(entry));
+ set_pte(page_table, entry);
+ } else {
+ /* One of our sibling threads was faster, back out. */
+ page_cache_release(new_page);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+ }
+
+ /* no need to invalidate: a not-present page shouldn't be cached */
+ update_mmu_cache(vma, address, entry);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return 2; /* Major fault */
+}
+
+/*
+ * These routines also need to handle stuff like marking pages dirty
+ * and/or accessed for architectures that don't do it in hardware (most
+ * RISC architectures). The early dirtying is also good on the i386.
+ *
+ * There is also a hook called "update_mmu_cache()" that architectures
+ * with external mmu caches can use to update those (ie the Sparc or
+ * PowerPC hashed page tables that act as extended TLBs).
+ *
+ * Note the "page_table_lock". It is to protect against kswapd removing
+ * pages from under us. Note that kswapd only ever _removes_ pages, never
+ * adds them. As such, once we have noticed that the page is not present,
+ * we can drop the lock early.
+ *
+ * The adding of pages is protected by the MM semaphore (which we hold),
+ * so we don't need to worry about a page being suddenly been added into
+ * our VM.
+ *
+ * We enter with the pagetable spinlock held, we are supposed to
+ * release it when done.
+ */
+static inline int handle_pte_fault(struct mm_struct *mm,
+ struct vm_area_struct * vma, unsigned long address,
+ int write_access, pte_t * pte)
+{
+ pte_t entry;
+
+ entry = *pte;
+ if (!pte_present(entry)) {
+ /*
+ * If it truly wasn't present, we know that kswapd
+ * and the PTE updates will not touch it later. So
+ * drop the lock.
+ */
+ if (pte_none(entry))
+ return do_no_page(mm, vma, address, write_access, pte);
+ return do_swap_page(mm, vma, address, pte, entry, write_access);
+ }
+
+ if (write_access) {
+ if (!pte_write(entry))
+ return do_wp_page(mm, vma, address, pte, entry);
+
+ entry = pte_mkdirty(entry);
+ }
+ entry = pte_mkyoung(entry);
+ establish_pte(vma, address, pte, entry);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+}
+
+/*
+ * By the time we get here, we already hold the mm semaphore
+ */
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+
+ current->state = TASK_RUNNING;
+ pgd = pgd_offset(mm, address);
+
+ /*
+ * We need the page table lock to synchronize with kswapd
+ * and the SMP-safe atomic PTE updates.
+ */
+ spin_lock(&mm->page_table_lock);
+ pmd = pmd_alloc(mm, pgd, address);
+
+ if (pmd) {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (pte)
+ return handle_pte_fault(mm, vma, address, write_access, pte);
+ }
+ spin_unlock(&mm->page_table_lock);
+ return -1;
+}
+
+/*
+ * Allocate page middle directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ *
+ * On a two-level page table, this ends up actually being entirely
+ * optimized away.
+ */
+pmd_t *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ pmd_t *new;
+
+ /* "fast" allocation can happen without dropping the lock.. */
+ new = pmd_alloc_one_fast(mm, address);
+ if (!new) {
+ spin_unlock(&mm->page_table_lock);
+ new = pmd_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (!pgd_none(*pgd)) {
+ pmd_free(new);
+ goto out;
+ }
+ }
+ pgd_populate(mm, pgd, new);
+out:
+ return pmd_offset(pgd, address);
+}
+
+/*
+ * Allocate the page table directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ */
+pte_t *pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+{
+ if (pmd_none(*pmd)) {
+ pte_t *new;
+
+ /* "fast" allocation can happen without dropping the lock.. */
+ new = pte_alloc_one_fast(mm, address);
+ if (!new) {
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ new = pte_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (!pmd_none(*pmd)) {
+ pte_free(new);
+ goto out;
+ }
+ }
+ pmd_populate(mm, pmd, new);
+ }
+out:
+ return pte_offset(pmd, address);
+}
+
+/*
+ * Simplistic page force-in..
+ */
+int make_pages_present(unsigned long addr, unsigned long end)
+{
+ int write;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct * vma;
+
+ vma = find_vma(mm, addr);
+ write = (vma->vm_flags & VM_WRITE) != 0;
+ if (addr >= end)
+ BUG();
+ do {
+ if (handle_mm_fault(mm, vma, addr, write) < 0)
+ return -1;
+ addr += PAGE_SIZE;
+ } while (addr < end);
+ return 0;
+}
--- /dev/null
+/*
+ * linux/mm/remap.c
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ */
+
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+
+extern int vm_enough_memory(long pages);
+
+static inline pte_t *get_one_pte(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t * pgd;
+ pmd_t * pmd;
+ pte_t * pte = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ if (pgd_none(*pgd))
+ goto end;
+ if (pgd_bad(*pgd)) {
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+ goto end;
+ }
+
+ pmd = pmd_offset(pgd, addr);
+ if (pmd_none(*pmd))
+ goto end;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ goto end;
+ }
+
+ pte = pte_offset(pmd, addr);
+ if (pte_none(*pte))
+ pte = NULL;
+end:
+ return pte;
+}
+
+static inline pte_t *alloc_one_pte(struct mm_struct *mm, unsigned long addr)
+{
+ pmd_t * pmd;
+ pte_t * pte = NULL;
+
+ pmd = pmd_alloc(mm, pgd_offset(mm, addr), addr);
+ if (pmd)
+ pte = pte_alloc(mm, pmd, addr);
+ return pte;
+}
+
+static inline int copy_one_pte(struct mm_struct *mm, pte_t * src, pte_t * dst)
+{
+ int error = 0;
+ pte_t pte;
+
+ if (!pte_none(*src)) {
+ pte = ptep_get_and_clear(src);
+ if (!dst) {
+ /* No dest? We must put it back. */
+ dst = src;
+ error++;
+ }
+ set_pte(dst, pte);
+ }
+ return error;
+}
+
+static int move_one_page(struct mm_struct *mm, unsigned long old_addr, unsigned long new_addr)
+{
+ int error = 0;
+ pte_t * src;
+
+ spin_lock(&mm->page_table_lock);
+ src = get_one_pte(mm, old_addr);
+ if (src)
+ error = copy_one_pte(mm, src, alloc_one_pte(mm, new_addr));
+ spin_unlock(&mm->page_table_lock);
+ return error;
+}
+
+static int move_page_tables(struct mm_struct * mm,
+ unsigned long new_addr, unsigned long old_addr, unsigned long len)
+{
+ unsigned long offset = len;
+
+ flush_cache_range(mm, old_addr, old_addr + len);
+
+ /*
+ * This is not the clever way to do this, but we're taking the
+ * easy way out on the assumption that most remappings will be
+ * only a few pages.. This also makes error recovery easier.
+ */
+ while (offset) {
+ offset -= PAGE_SIZE;
+ if (move_one_page(mm, old_addr + offset, new_addr + offset))
+ goto oops_we_failed;
+ }
+ flush_tlb_range(mm, old_addr, old_addr + len);
+ return 0;
+
+ /*
+ * Ok, the move failed because we didn't have enough pages for
+ * the new page table tree. This is unlikely, but we have to
+ * take the possibility into account. In that case we just move
+ * all the pages back (this will work, because we still have
+ * the old page tables)
+ */
+oops_we_failed:
+ XENO_flush_page_update_queue();
+ flush_cache_range(mm, new_addr, new_addr + len);
+ while ((offset += PAGE_SIZE) < len)
+ move_one_page(mm, new_addr + offset, old_addr + offset);
+ XENO_flush_page_update_queue();
+ zap_page_range(mm, new_addr, len);
+ return -1;
+}
+
+static inline unsigned long move_vma(struct vm_area_struct * vma,
+ unsigned long addr, unsigned long old_len, unsigned long new_len,
+ unsigned long new_addr)
+{
+ struct mm_struct * mm = vma->vm_mm;
+ struct vm_area_struct * new_vma, * next, * prev;
+ int allocated_vma;
+
+ new_vma = NULL;
+ next = find_vma_prev(mm, new_addr, &prev);
+ if (next) {
+ if (prev && prev->vm_end == new_addr &&
+ can_vma_merge(prev, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = new_addr + new_len;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = prev;
+ if (next != prev->vm_next)
+ BUG();
+ if (prev->vm_end == next->vm_start && can_vma_merge(next, prev->vm_flags)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = next->vm_end;
+ __vma_unlink(mm, next, prev);
+ spin_unlock(&mm->page_table_lock);
+
+ mm->map_count--;
+ kmem_cache_free(vm_area_cachep, next);
+ }
+ } else if (next->vm_start == new_addr + new_len &&
+ can_vma_merge(next, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ next->vm_start = new_addr;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = next;
+ }
+ } else {
+ prev = find_vma(mm, new_addr-1);
+ if (prev && prev->vm_end == new_addr &&
+ can_vma_merge(prev, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = new_addr + new_len;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = prev;
+ }
+ }
+
+ allocated_vma = 0;
+ if (!new_vma) {
+ new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!new_vma)
+ goto out;
+ allocated_vma = 1;
+ }
+
+ if (!move_page_tables(current->mm, new_addr, addr, old_len)) {
+ if (allocated_vma) {
+ *new_vma = *vma;
+ new_vma->vm_start = new_addr;
+ new_vma->vm_end = new_addr+new_len;
+ new_vma->vm_pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
+ new_vma->vm_raend = 0;
+ if (new_vma->vm_file)
+ get_file(new_vma->vm_file);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ insert_vm_struct(current->mm, new_vma);
+ }
+ do_munmap(current->mm, addr, old_len);
+ current->mm->total_vm += new_len >> PAGE_SHIFT;
+ if (new_vma->vm_flags & VM_LOCKED) {
+ current->mm->locked_vm += new_len >> PAGE_SHIFT;
+ make_pages_present(new_vma->vm_start,
+ new_vma->vm_end);
+ }
+ return new_addr;
+ }
+ if (allocated_vma)
+ kmem_cache_free(vm_area_cachep, new_vma);
+ out:
+ return -ENOMEM;
+}
+
+/*
+ * Expand (or shrink) an existing mapping, potentially moving it at the
+ * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
+ *
+ * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
+ * This option implies MREMAP_MAYMOVE.
+ */
+unsigned long do_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr)
+{
+ struct vm_area_struct *vma;
+ unsigned long ret = -EINVAL;
+
+ if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
+ goto out;
+
+ if (addr & ~PAGE_MASK)
+ goto out;
+
+ old_len = PAGE_ALIGN(old_len);
+ new_len = PAGE_ALIGN(new_len);
+
+ /* new_addr is only valid if MREMAP_FIXED is specified */
+ if (flags & MREMAP_FIXED) {
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+ if (!(flags & MREMAP_MAYMOVE))
+ goto out;
+
+ if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
+ goto out;
+
+ /* Check if the location we're moving into overlaps the
+ * old location at all, and fail if it does.
+ */
+ if ((new_addr <= addr) && (new_addr+new_len) > addr)
+ goto out;
+
+ if ((addr <= new_addr) && (addr+old_len) > new_addr)
+ goto out;
+
+ do_munmap(current->mm, new_addr, new_len);
+ }
+
+ /*
+ * Always allow a shrinking remap: that just unmaps
+ * the unnecessary pages..
+ */
+ ret = addr;
+ if (old_len >= new_len) {
+ do_munmap(current->mm, addr+new_len, old_len - new_len);
+ if (!(flags & MREMAP_FIXED) || (new_addr == addr))
+ goto out;
+ }
+
+ /*
+ * Ok, we need to grow.. or relocate.
+ */
+ ret = -EFAULT;
+ vma = find_vma(current->mm, addr);
+ if (!vma || vma->vm_start > addr)
+ goto out;
+ /* We can't remap across vm area boundaries */
+ if (old_len > vma->vm_end - addr)
+ goto out;
+ if (vma->vm_flags & VM_DONTEXPAND) {
+ if (new_len > old_len)
+ goto out;
+ }
+ if (vma->vm_flags & VM_LOCKED) {
+ unsigned long locked = current->mm->locked_vm << PAGE_SHIFT;
+ locked += new_len - old_len;
+ ret = -EAGAIN;
+ if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ goto out;
+ }
+ ret = -ENOMEM;
+ if ((current->mm->total_vm << PAGE_SHIFT) + (new_len - old_len)
+ > current->rlim[RLIMIT_AS].rlim_cur)
+ goto out;
+ /* Private writable mapping? Check memory availability.. */
+ if ((vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
+ !(flags & MAP_NORESERVE) &&
+ !vm_enough_memory((new_len - old_len) >> PAGE_SHIFT))
+ goto out;
+
+ /* old_len exactly to the end of the area..
+ * And we're not relocating the area.
+ */
+ if (old_len == vma->vm_end - addr &&
+ !((flags & MREMAP_FIXED) && (addr != new_addr)) &&
+ (old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
+ unsigned long max_addr = TASK_SIZE;
+ if (vma->vm_next)
+ max_addr = vma->vm_next->vm_start;
+ /* can we just expand the current mapping? */
+ if (max_addr - addr >= new_len) {
+ int pages = (new_len - old_len) >> PAGE_SHIFT;
+ spin_lock(&vma->vm_mm->page_table_lock);
+ vma->vm_end = addr + new_len;
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ current->mm->total_vm += pages;
+ if (vma->vm_flags & VM_LOCKED) {
+ current->mm->locked_vm += pages;
+ make_pages_present(addr + old_len,
+ addr + new_len);
+ }
+ ret = addr;
+ goto out;
+ }
+ }
+
+ /*
+ * We weren't able to just expand or shrink the area,
+ * we need to create a new one and move it..
+ */
+ ret = -ENOMEM;
+ if (flags & MREMAP_MAYMOVE) {
+ if (!(flags & MREMAP_FIXED)) {
+ unsigned long map_flags = 0;
+ if (vma->vm_flags & VM_SHARED)
+ map_flags |= MAP_SHARED;
+
+ new_addr = get_unmapped_area(vma->vm_file, 0, new_len, vma->vm_pgoff, map_flags);
+ ret = new_addr;
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+ }
+ ret = move_vma(vma, addr, old_len, new_len, new_addr);
+ }
+out:
+ return ret;
+}
+
+asmlinkage unsigned long sys_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr)
+{
+ unsigned long ret;
+
+ down_write(¤t->mm->mmap_sem);
+ ret = do_mremap(addr, old_len, new_len, flags, new_addr);
+ up_write(¤t->mm->mmap_sem);
+ return ret;
+}
--- /dev/null
+/*
+ * linux/mm/swapfile.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ * Swap reorganised 29.12.95, Stephen Tweedie
+ */
+
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel_stat.h>
+#include <linux/swap.h>
+#include <linux/swapctl.h>
+#include <linux/blkdev.h> /* for blk_size */
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <linux/shm.h>
+#include <linux/compiler.h>
+
+#include <asm/pgtable.h>
+
+spinlock_t swaplock = SPIN_LOCK_UNLOCKED;
+unsigned int nr_swapfiles;
+int total_swap_pages;
+static int swap_overflow;
+
+static const char Bad_file[] = "Bad swap file entry ";
+static const char Unused_file[] = "Unused swap file entry ";
+static const char Bad_offset[] = "Bad swap offset entry ";
+static const char Unused_offset[] = "Unused swap offset entry ";
+
+struct swap_list_t swap_list = {-1, -1};
+
+struct swap_info_struct swap_info[MAX_SWAPFILES];
+
+#define SWAPFILE_CLUSTER 256
+
+static inline int scan_swap_map(struct swap_info_struct *si)
+{
+ unsigned long offset;
+ /*
+ * We try to cluster swap pages by allocating them
+ * sequentially in swap. Once we've allocated
+ * SWAPFILE_CLUSTER pages this way, however, we resort to
+ * first-free allocation, starting a new cluster. This
+ * prevents us from scattering swap pages all over the entire
+ * swap partition, so that we reduce overall disk seek times
+ * between swap pages. -- sct */
+ if (si->cluster_nr) {
+ while (si->cluster_next <= si->highest_bit) {
+ offset = si->cluster_next++;
+ if (si->swap_map[offset])
+ continue;
+ si->cluster_nr--;
+ goto got_page;
+ }
+ }
+ si->cluster_nr = SWAPFILE_CLUSTER;
+
+ /* try to find an empty (even not aligned) cluster. */
+ offset = si->lowest_bit;
+ check_next_cluster:
+ if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
+ {
+ int nr;
+ for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
+ if (si->swap_map[nr])
+ {
+ offset = nr+1;
+ goto check_next_cluster;
+ }
+ /* We found a completly empty cluster, so start
+ * using it.
+ */
+ goto got_page;
+ }
+ /* No luck, so now go finegrined as usual. -Andrea */
+ for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) {
+ if (si->swap_map[offset])
+ continue;
+ si->lowest_bit = offset+1;
+ got_page:
+ if (offset == si->lowest_bit)
+ si->lowest_bit++;
+ if (offset == si->highest_bit)
+ si->highest_bit--;
+ if (si->lowest_bit > si->highest_bit) {
+ si->lowest_bit = si->max;
+ si->highest_bit = 0;
+ }
+ si->swap_map[offset] = 1;
+ nr_swap_pages--;
+ si->cluster_next = offset+1;
+ return offset;
+ }
+ si->lowest_bit = si->max;
+ si->highest_bit = 0;
+ return 0;
+}
+
+swp_entry_t get_swap_page(void)
+{
+ struct swap_info_struct * p;
+ unsigned long offset;
+ swp_entry_t entry;
+ int type, wrapped = 0;
+
+ entry.val = 0; /* Out of memory */
+ swap_list_lock();
+ type = swap_list.next;
+ if (type < 0)
+ goto out;
+ if (nr_swap_pages <= 0)
+ goto out;
+
+ while (1) {
+ p = &swap_info[type];
+ if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
+ swap_device_lock(p);
+ offset = scan_swap_map(p);
+ swap_device_unlock(p);
+ if (offset) {
+ entry = SWP_ENTRY(type,offset);
+ type = swap_info[type].next;
+ if (type < 0 ||
+ p->prio != swap_info[type].prio) {
+ swap_list.next = swap_list.head;
+ } else {
+ swap_list.next = type;
+ }
+ goto out;
+ }
+ }
+ type = p->next;
+ if (!wrapped) {
+ if (type < 0 || p->prio != swap_info[type].prio) {
+ type = swap_list.head;
+ wrapped = 1;
+ }
+ } else
+ if (type < 0)
+ goto out; /* out of swap space */
+ }
+out:
+ swap_list_unlock();
+ return entry;
+}
+
+static struct swap_info_struct * swap_info_get(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+ unsigned long offset, type;
+
+ if (!entry.val)
+ goto out;
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles)
+ goto bad_nofile;
+ p = & swap_info[type];
+ if (!(p->flags & SWP_USED))
+ goto bad_device;
+ offset = SWP_OFFSET(entry);
+ if (offset >= p->max)
+ goto bad_offset;
+ if (!p->swap_map[offset])
+ goto bad_free;
+ swap_list_lock();
+ if (p->prio > swap_info[swap_list.next].prio)
+ swap_list.next = type;
+ swap_device_lock(p);
+ return p;
+
+bad_free:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
+ goto out;
+bad_offset:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
+ goto out;
+bad_device:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
+ goto out;
+bad_nofile:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
+out:
+ return NULL;
+}
+
+static void swap_info_put(struct swap_info_struct * p)
+{
+ swap_device_unlock(p);
+ swap_list_unlock();
+}
+
+static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
+{
+ int count = p->swap_map[offset];
+
+ if (count < SWAP_MAP_MAX) {
+ count--;
+ p->swap_map[offset] = count;
+ if (!count) {
+ if (offset < p->lowest_bit)
+ p->lowest_bit = offset;
+ if (offset > p->highest_bit)
+ p->highest_bit = offset;
+ nr_swap_pages++;
+ }
+ }
+ return count;
+}
+
+/*
+ * Caller has made sure that the swapdevice corresponding to entry
+ * is still around or has not been recycled.
+ */
+void swap_free(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+
+ p = swap_info_get(entry);
+ if (p) {
+ swap_entry_free(p, SWP_OFFSET(entry));
+ swap_info_put(p);
+ }
+}
+
+/*
+ * Check if we're the only user of a swap page,
+ * when the page is locked.
+ */
+static int exclusive_swap_page(struct page *page)
+{
+ int retval = 0;
+ struct swap_info_struct * p;
+ swp_entry_t entry;
+
+ entry.val = page->index;
+ p = swap_info_get(entry);
+ if (p) {
+ /* Is the only swap cache user the cache itself? */
+ if (p->swap_map[SWP_OFFSET(entry)] == 1) {
+ /* Recheck the page count with the pagecache lock held.. */
+ spin_lock(&pagecache_lock);
+ if (page_count(page) - !!page->buffers == 2)
+ retval = 1;
+ spin_unlock(&pagecache_lock);
+ }
+ swap_info_put(p);
+ }
+ return retval;
+}
+
+/*
+ * We can use this swap cache entry directly
+ * if there are no other references to it.
+ *
+ * Here "exclusive_swap_page()" does the real
+ * work, but we opportunistically check whether
+ * we need to get all the locks first..
+ */
+int can_share_swap_page(struct page *page)
+{
+ int retval = 0;
+
+ if (!PageLocked(page))
+ BUG();
+ switch (page_count(page)) {
+ case 3:
+ if (!page->buffers)
+ break;
+ /* Fallthrough */
+ case 2:
+ if (!PageSwapCache(page))
+ break;
+ retval = exclusive_swap_page(page);
+ break;
+ case 1:
+ if (PageReserved(page))
+ break;
+ retval = 1;
+ }
+ return retval;
+}
+
+/*
+ * Work out if there are any other processes sharing this
+ * swap cache page. Free it if you can. Return success.
+ */
+int remove_exclusive_swap_page(struct page *page)
+{
+ int retval;
+ struct swap_info_struct * p;
+ swp_entry_t entry;
+
+ if (!PageLocked(page))
+ BUG();
+ if (!PageSwapCache(page))
+ return 0;
+ if (page_count(page) - !!page->buffers != 2) /* 2: us + cache */
+ return 0;
+
+ entry.val = page->index;
+ p = swap_info_get(entry);
+ if (!p)
+ return 0;
+
+ /* Is the only swap cache user the cache itself? */
+ retval = 0;
+ if (p->swap_map[SWP_OFFSET(entry)] == 1) {
+ /* Recheck the page count with the pagecache lock held.. */
+ spin_lock(&pagecache_lock);
+ if (page_count(page) - !!page->buffers == 2) {
+ __delete_from_swap_cache(page);
+ SetPageDirty(page);
+ retval = 1;
+ }
+ spin_unlock(&pagecache_lock);
+ }
+ swap_info_put(p);
+
+ if (retval) {
+ block_flushpage(page, 0);
+ swap_free(entry);
+ page_cache_release(page);
+ }
+
+ return retval;
+}
+
+/*
+ * Free the swap entry like above, but also try to
+ * free the page cache entry if it is the last user.
+ */
+void free_swap_and_cache(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+ struct page *page = NULL;
+
+ p = swap_info_get(entry);
+ if (p) {
+ if (swap_entry_free(p, SWP_OFFSET(entry)) == 1)
+ page = find_trylock_page(&swapper_space, entry.val);
+ swap_info_put(p);
+ }
+ if (page) {
+ page_cache_get(page);
+ /* Only cache user (+us), or swap space full? Free it! */
+ if (page_count(page) == 2 || vm_swap_full()) {
+ delete_from_swap_cache(page);
+ SetPageDirty(page);
+ }
+ UnlockPage(page);
+ page_cache_release(page);
+ }
+}
+
+/*
+ * The swap entry has been read in advance, and we return 1 to indicate
+ * that the page has been used or is no longer needed.
+ *
+ * Always set the resulting pte to be nowrite (the same as COW pages
+ * after one process has exited). We don't know just how many PTEs will
+ * share this swap entry, so be cautious and let do_wp_page work out
+ * what to do if a write is requested later.
+ */
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static inline void unuse_pte(struct vm_area_struct * vma, unsigned long address,
+ pte_t *dir, swp_entry_t entry, struct page* page)
+{
+ pte_t pte = *dir;
+
+ if (likely(pte_to_swp_entry(pte).val != entry.val))
+ return;
+ if (unlikely(pte_none(pte) || pte_present(pte)))
+ return;
+ get_page(page);
+ set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
+ swap_free(entry);
+ ++vma->vm_mm->rss;
+}
+
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static inline void unuse_pmd(struct vm_area_struct * vma, pmd_t *dir,
+ unsigned long address, unsigned long size, unsigned long offset,
+ swp_entry_t entry, struct page* page)
+{
+ pte_t * pte;
+ unsigned long end;
+
+ if (pmd_none(*dir))
+ return;
+ if (pmd_bad(*dir)) {
+ pmd_ERROR(*dir);
+ pmd_clear(dir);
+ return;
+ }
+ pte = pte_offset(dir, address);
+ offset += address & PMD_MASK;
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ unuse_pte(vma, offset+address-vma->vm_start, pte, entry, page);
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static inline void unuse_pgd(struct vm_area_struct * vma, pgd_t *dir,
+ unsigned long address, unsigned long size,
+ swp_entry_t entry, struct page* page)
+{
+ pmd_t * pmd;
+ unsigned long offset, end;
+
+ if (pgd_none(*dir))
+ return;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return;
+ }
+ pmd = pmd_offset(dir, address);
+ offset = address & PGDIR_MASK;
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ if (address >= end)
+ BUG();
+ do {
+ unuse_pmd(vma, pmd, address, end - address, offset, entry,
+ page);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+}
+
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static void unuse_vma(struct vm_area_struct * vma, pgd_t *pgdir,
+ swp_entry_t entry, struct page* page)
+{
+ unsigned long start = vma->vm_start, end = vma->vm_end;
+
+ if (start >= end)
+ BUG();
+ do {
+ unuse_pgd(vma, pgdir, start, end - start, entry, page);
+ start = (start + PGDIR_SIZE) & PGDIR_MASK;
+ pgdir++;
+ } while (start && (start < end));
+}
+
+static void unuse_process(struct mm_struct * mm,
+ swp_entry_t entry, struct page* page)
+{
+ struct vm_area_struct* vma;
+
+ /*
+ * Go through process' page directory.
+ */
+ spin_lock(&mm->page_table_lock);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ pgd_t * pgd = pgd_offset(mm, vma->vm_start);
+ unuse_vma(vma, pgd, entry, page);
+ }
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return;
+}
+
+/*
+ * Scan swap_map from current position to next entry still in use.
+ * Recycle to start on reaching the end, returning 0 when empty.
+ */
+static int find_next_to_unuse(struct swap_info_struct *si, int prev)
+{
+ int max = si->max;
+ int i = prev;
+ int count;
+
+ /*
+ * No need for swap_device_lock(si) here: we're just looking
+ * for whether an entry is in use, not modifying it; false
+ * hits are okay, and sys_swapoff() has already prevented new
+ * allocations from this area (while holding swap_list_lock()).
+ */
+ for (;;) {
+ if (++i >= max) {
+ if (!prev) {
+ i = 0;
+ break;
+ }
+ /*
+ * No entries in use at top of swap_map,
+ * loop back to start and recheck there.
+ */
+ max = prev + 1;
+ prev = 0;
+ i = 1;
+ }
+ count = si->swap_map[i];
+ if (count && count != SWAP_MAP_BAD)
+ break;
+ }
+ return i;
+}
+
+/*
+ * We completely avoid races by reading each swap page in advance,
+ * and then search for the process using it. All the necessary
+ * page table adjustments can then be made atomically.
+ */
+static int try_to_unuse(unsigned int type)
+{
+ struct swap_info_struct * si = &swap_info[type];
+ struct mm_struct *start_mm;
+ unsigned short *swap_map;
+ unsigned short swcount;
+ struct page *page;
+ swp_entry_t entry;
+ int i = 0;
+ int retval = 0;
+ int reset_overflow = 0;
+
+ /*
+ * When searching mms for an entry, a good strategy is to
+ * start at the first mm we freed the previous entry from
+ * (though actually we don't notice whether we or coincidence
+ * freed the entry). Initialize this start_mm with a hold.
+ *
+ * A simpler strategy would be to start at the last mm we
+ * freed the previous entry from; but that would take less
+ * advantage of mmlist ordering (now preserved by swap_out()),
+ * which clusters forked address spaces together, most recent
+ * child immediately after parent. If we race with dup_mmap(),
+ * we very much want to resolve parent before child, otherwise
+ * we may miss some entries: using last mm would invert that.
+ */
+ start_mm = &init_mm;
+ atomic_inc(&init_mm.mm_users);
+
+ /*
+ * Keep on scanning until all entries have gone. Usually,
+ * one pass through swap_map is enough, but not necessarily:
+ * mmput() removes mm from mmlist before exit_mmap() and its
+ * zap_page_range(). That's not too bad, those entries are
+ * on their way out, and handled faster there than here.
+ * do_munmap() behaves similarly, taking the range out of mm's
+ * vma list before zap_page_range(). But unfortunately, when
+ * unmapping a part of a vma, it takes the whole out first,
+ * then reinserts what's left after (might even reschedule if
+ * open() method called) - so swap entries may be invisible
+ * to swapoff for a while, then reappear - but that is rare.
+ */
+ while ((i = find_next_to_unuse(si, i))) {
+ /*
+ * Get a page for the entry, using the existing swap
+ * cache page if there is one. Otherwise, get a clean
+ * page and read the swap into it.
+ */
+ swap_map = &si->swap_map[i];
+ entry = SWP_ENTRY(type, i);
+ page = read_swap_cache_async(entry);
+ if (!page) {
+ /*
+ * Either swap_duplicate() failed because entry
+ * has been freed independently, and will not be
+ * reused since sys_swapoff() already disabled
+ * allocation from here, or alloc_page() failed.
+ */
+ if (!*swap_map)
+ continue;
+ retval = -ENOMEM;
+ break;
+ }
+
+ /*
+ * Don't hold on to start_mm if it looks like exiting.
+ */
+ if (atomic_read(&start_mm->mm_users) == 1) {
+ mmput(start_mm);
+ start_mm = &init_mm;
+ atomic_inc(&init_mm.mm_users);
+ }
+
+ /*
+ * Wait for and lock page. When do_swap_page races with
+ * try_to_unuse, do_swap_page can handle the fault much
+ * faster than try_to_unuse can locate the entry. This
+ * apparently redundant "wait_on_page" lets try_to_unuse
+ * defer to do_swap_page in such a case - in some tests,
+ * do_swap_page and try_to_unuse repeatedly compete.
+ */
+ wait_on_page(page);
+ lock_page(page);
+
+ /*
+ * Remove all references to entry, without blocking.
+ * Whenever we reach init_mm, there's no address space
+ * to search, but use it as a reminder to search shmem.
+ */
+ swcount = *swap_map;
+ if (swcount > 1) {
+ flush_page_to_ram(page);
+ if (start_mm == &init_mm)
+ shmem_unuse(entry, page);
+ else
+ unuse_process(start_mm, entry, page);
+ }
+ if (*swap_map > 1) {
+ int set_start_mm = (*swap_map >= swcount);
+ struct list_head *p = &start_mm->mmlist;
+ struct mm_struct *new_start_mm = start_mm;
+ struct mm_struct *mm;
+
+ spin_lock(&mmlist_lock);
+ while (*swap_map > 1 &&
+ (p = p->next) != &start_mm->mmlist) {
+ mm = list_entry(p, struct mm_struct, mmlist);
+ swcount = *swap_map;
+ if (mm == &init_mm) {
+ set_start_mm = 1;
+ shmem_unuse(entry, page);
+ } else
+ unuse_process(mm, entry, page);
+ if (set_start_mm && *swap_map < swcount) {
+ new_start_mm = mm;
+ set_start_mm = 0;
+ }
+ }
+ atomic_inc(&new_start_mm->mm_users);
+ spin_unlock(&mmlist_lock);
+ mmput(start_mm);
+ start_mm = new_start_mm;
+ }
+
+ /*
+ * How could swap count reach 0x7fff when the maximum
+ * pid is 0x7fff, and there's no way to repeat a swap
+ * page within an mm (except in shmem, where it's the
+ * shared object which takes the reference count)?
+ * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
+ *
+ * If that's wrong, then we should worry more about
+ * exit_mmap() and do_munmap() cases described above:
+ * we might be resetting SWAP_MAP_MAX too early here.
+ * We know "Undead"s can happen, they're okay, so don't
+ * report them; but do report if we reset SWAP_MAP_MAX.
+ */
+ if (*swap_map == SWAP_MAP_MAX) {
+ swap_list_lock();
+ swap_device_lock(si);
+ nr_swap_pages++;
+ *swap_map = 1;
+ swap_device_unlock(si);
+ swap_list_unlock();
+ reset_overflow = 1;
+ }
+
+ /*
+ * If a reference remains (rare), we would like to leave
+ * the page in the swap cache; but try_to_swap_out could
+ * then re-duplicate the entry once we drop page lock,
+ * so we might loop indefinitely; also, that page could
+ * not be swapped out to other storage meanwhile. So:
+ * delete from cache even if there's another reference,
+ * after ensuring that the data has been saved to disk -
+ * since if the reference remains (rarer), it will be
+ * read from disk into another page. Splitting into two
+ * pages would be incorrect if swap supported "shared
+ * private" pages, but they are handled by tmpfs files.
+ * Note shmem_unuse already deleted its from swap cache.
+ */
+ swcount = *swap_map;
+ if ((swcount > 0) != PageSwapCache(page))
+ BUG();
+ if ((swcount > 1) && PageDirty(page)) {
+ rw_swap_page(WRITE, page);
+ lock_page(page);
+ }
+ if (PageSwapCache(page))
+ delete_from_swap_cache(page);
+
+ /*
+ * So we could skip searching mms once swap count went
+ * to 1, we did not mark any present ptes as dirty: must
+ * mark page dirty so try_to_swap_out will preserve it.
+ */
+ SetPageDirty(page);
+ UnlockPage(page);
+ page_cache_release(page);
+
+ /*
+ * Make sure that we aren't completely killing
+ * interactive performance. Interruptible check on
+ * signal_pending() would be nice, but changes the spec?
+ */
+ if (current->need_resched)
+ schedule();
+ }
+
+ mmput(start_mm);
+ if (reset_overflow) {
+ printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
+ swap_overflow = 0;
+ }
+ return retval;
+}
+
+asmlinkage long sys_swapoff(const char * specialfile)
+{
+ struct swap_info_struct * p = NULL;
+ unsigned short *swap_map;
+ struct nameidata nd;
+ int i, type, prev;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = user_path_walk(specialfile, &nd);
+ if (err)
+ goto out;
+
+ lock_kernel();
+ prev = -1;
+ swap_list_lock();
+ for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
+ p = swap_info + type;
+ if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
+ if (p->swap_file == nd.dentry)
+ break;
+ }
+ prev = type;
+ }
+ err = -EINVAL;
+ if (type < 0) {
+ swap_list_unlock();
+ goto out_dput;
+ }
+
+ if (prev < 0) {
+ swap_list.head = p->next;
+ } else {
+ swap_info[prev].next = p->next;
+ }
+ if (type == swap_list.next) {
+ /* just pick something that's safe... */
+ swap_list.next = swap_list.head;
+ }
+ nr_swap_pages -= p->pages;
+ total_swap_pages -= p->pages;
+ p->flags = SWP_USED;
+ swap_list_unlock();
+ unlock_kernel();
+ err = try_to_unuse(type);
+ lock_kernel();
+ if (err) {
+ /* re-insert swap space back into swap_list */
+ swap_list_lock();
+ for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
+ if (p->prio >= swap_info[i].prio)
+ break;
+ p->next = i;
+ if (prev < 0)
+ swap_list.head = swap_list.next = p - swap_info;
+ else
+ swap_info[prev].next = p - swap_info;
+ nr_swap_pages += p->pages;
+ total_swap_pages += p->pages;
+ p->flags = SWP_WRITEOK;
+ swap_list_unlock();
+ goto out_dput;
+ }
+ if (p->swap_device)
+ blkdev_put(p->swap_file->d_inode->i_bdev, BDEV_SWAP);
+ path_release(&nd);
+
+ swap_list_lock();
+ swap_device_lock(p);
+ nd.mnt = p->swap_vfsmnt;
+ nd.dentry = p->swap_file;
+ p->swap_vfsmnt = NULL;
+ p->swap_file = NULL;
+ p->swap_device = 0;
+ p->max = 0;
+ swap_map = p->swap_map;
+ p->swap_map = NULL;
+ p->flags = 0;
+ swap_device_unlock(p);
+ swap_list_unlock();
+ vfree(swap_map);
+ err = 0;
+
+out_dput:
+ unlock_kernel();
+ path_release(&nd);
+out:
+ return err;
+}
+
+int get_swaparea_info(char *buf)
+{
+ char * page = (char *) __get_free_page(GFP_KERNEL);
+ struct swap_info_struct *ptr = swap_info;
+ int i, j, len = 0, usedswap;
+
+ if (!page)
+ return -ENOMEM;
+
+ len += sprintf(buf, "Filename\t\t\tType\t\tSize\tUsed\tPriority\n");
+ for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
+ if ((ptr->flags & SWP_USED) && ptr->swap_map) {
+ char * path = d_path(ptr->swap_file, ptr->swap_vfsmnt,
+ page, PAGE_SIZE);
+
+ len += sprintf(buf + len, "%-31s ", path);
+
+ if (!ptr->swap_device)
+ len += sprintf(buf + len, "file\t\t");
+ else
+ len += sprintf(buf + len, "partition\t");
+
+ usedswap = 0;
+ for (j = 0; j < ptr->max; ++j)
+ switch (ptr->swap_map[j]) {
+ case SWAP_MAP_BAD:
+ case 0:
+ continue;
+ default:
+ usedswap++;
+ }
+ len += sprintf(buf + len, "%d\t%d\t%d\n", ptr->pages << (PAGE_SHIFT - 10),
+ usedswap << (PAGE_SHIFT - 10), ptr->prio);
+ }
+ }
+ free_page((unsigned long) page);
+ return len;
+}
+
+int is_swap_partition(kdev_t dev) {
+ struct swap_info_struct *ptr = swap_info;
+ int i;
+
+ for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
+ if (ptr->flags & SWP_USED)
+ if (ptr->swap_device == dev)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
+ *
+ * The swapon system call
+ */
+asmlinkage long sys_swapon(const char * specialfile, int swap_flags)
+{
+ struct swap_info_struct * p;
+ struct nameidata nd;
+ struct inode * swap_inode;
+ unsigned int type;
+ int i, j, prev;
+ int error;
+ static int least_priority = 0;
+ union swap_header *swap_header = 0;
+ int swap_header_version;
+ int nr_good_pages = 0;
+ unsigned long maxpages = 1;
+ int swapfilesize;
+ struct block_device *bdev = NULL;
+ unsigned short *swap_map;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ lock_kernel();
+ swap_list_lock();
+ p = swap_info;
+ for (type = 0 ; type < nr_swapfiles ; type++,p++)
+ if (!(p->flags & SWP_USED))
+ break;
+ error = -EPERM;
+ if (type >= MAX_SWAPFILES) {
+ swap_list_unlock();
+ goto out;
+ }
+ if (type >= nr_swapfiles)
+ nr_swapfiles = type+1;
+ p->flags = SWP_USED;
+ p->swap_file = NULL;
+ p->swap_vfsmnt = NULL;
+ p->swap_device = 0;
+ p->swap_map = NULL;
+ p->lowest_bit = 0;
+ p->highest_bit = 0;
+ p->cluster_nr = 0;
+ p->sdev_lock = SPIN_LOCK_UNLOCKED;
+ p->next = -1;
+ if (swap_flags & SWAP_FLAG_PREFER) {
+ p->prio =
+ (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
+ } else {
+ p->prio = --least_priority;
+ }
+ swap_list_unlock();
+ error = user_path_walk(specialfile, &nd);
+ if (error)
+ goto bad_swap_2;
+
+ p->swap_file = nd.dentry;
+ p->swap_vfsmnt = nd.mnt;
+ swap_inode = nd.dentry->d_inode;
+ error = -EINVAL;
+
+ if (S_ISBLK(swap_inode->i_mode)) {
+ kdev_t dev = swap_inode->i_rdev;
+ struct block_device_operations *bdops;
+
+ p->swap_device = dev;
+ set_blocksize(dev, PAGE_SIZE);
+
+ bd_acquire(swap_inode);
+ bdev = swap_inode->i_bdev;
+ bdops = devfs_get_ops(devfs_get_handle_from_inode(swap_inode));
+ if (bdops) bdev->bd_op = bdops;
+
+ error = blkdev_get(bdev, FMODE_READ|FMODE_WRITE, 0, BDEV_SWAP);
+ if (error)
+ goto bad_swap_2;
+ set_blocksize(dev, PAGE_SIZE);
+ error = -ENODEV;
+ if (!dev || (blk_size[MAJOR(dev)] &&
+ !blk_size[MAJOR(dev)][MINOR(dev)]))
+ goto bad_swap;
+ swapfilesize = 0;
+ if (blk_size[MAJOR(dev)])
+ swapfilesize = blk_size[MAJOR(dev)][MINOR(dev)]
+ >> (PAGE_SHIFT - 10);
+ } else if (S_ISREG(swap_inode->i_mode))
+ swapfilesize = swap_inode->i_size >> PAGE_SHIFT;
+ else
+ goto bad_swap;
+
+ error = -EBUSY;
+ for (i = 0 ; i < nr_swapfiles ; i++) {
+ struct swap_info_struct *q = &swap_info[i];
+ if (i == type || !q->swap_file)
+ continue;
+ if (swap_inode->i_mapping == q->swap_file->d_inode->i_mapping)
+ goto bad_swap;
+ }
+
+ swap_header = (void *) __get_free_page(GFP_USER);
+ if (!swap_header) {
+ printk("Unable to start swapping: out of memory :-)\n");
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+
+ lock_page(virt_to_page(swap_header));
+ rw_swap_page_nolock(READ, SWP_ENTRY(type,0), (char *) swap_header);
+
+ if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
+ swap_header_version = 1;
+ else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
+ swap_header_version = 2;
+ else {
+ printk("Unable to find swap-space signature\n");
+ error = -EINVAL;
+ goto bad_swap;
+ }
+
+ switch (swap_header_version) {
+ case 1:
+ memset(((char *) swap_header)+PAGE_SIZE-10,0,10);
+ j = 0;
+ p->lowest_bit = 0;
+ p->highest_bit = 0;
+ for (i = 1 ; i < 8*PAGE_SIZE ; i++) {
+ if (test_bit(i,(char *) swap_header)) {
+ if (!p->lowest_bit)
+ p->lowest_bit = i;
+ p->highest_bit = i;
+ maxpages = i+1;
+ j++;
+ }
+ }
+ nr_good_pages = j;
+ p->swap_map = vmalloc(maxpages * sizeof(short));
+ if (!p->swap_map) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+ for (i = 1 ; i < maxpages ; i++) {
+ if (test_bit(i,(char *) swap_header))
+ p->swap_map[i] = 0;
+ else
+ p->swap_map[i] = SWAP_MAP_BAD;
+ }
+ break;
+
+ case 2:
+ /* Check the swap header's sub-version and the size of
+ the swap file and bad block lists */
+ if (swap_header->info.version != 1) {
+ printk(KERN_WARNING
+ "Unable to handle swap header version %d\n",
+ swap_header->info.version);
+ error = -EINVAL;
+ goto bad_swap;
+ }
+
+ p->lowest_bit = 1;
+ maxpages = SWP_OFFSET(SWP_ENTRY(0,~0UL)) - 1;
+ if (maxpages > swap_header->info.last_page)
+ maxpages = swap_header->info.last_page;
+ p->highest_bit = maxpages - 1;
+
+ error = -EINVAL;
+ if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+ goto bad_swap;
+
+ /* OK, set up the swap map and apply the bad block list */
+ if (!(p->swap_map = vmalloc(maxpages * sizeof(short)))) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+
+ error = 0;
+ memset(p->swap_map, 0, maxpages * sizeof(short));
+ for (i=0; i<swap_header->info.nr_badpages; i++) {
+ int page = swap_header->info.badpages[i];
+ if (page <= 0 || page >= swap_header->info.last_page)
+ error = -EINVAL;
+ else
+ p->swap_map[page] = SWAP_MAP_BAD;
+ }
+ nr_good_pages = swap_header->info.last_page -
+ swap_header->info.nr_badpages -
+ 1 /* header page */;
+ if (error)
+ goto bad_swap;
+ }
+
+ if (swapfilesize && maxpages > swapfilesize) {
+ printk(KERN_WARNING
+ "Swap area shorter than signature indicates\n");
+ error = -EINVAL;
+ goto bad_swap;
+ }
+ if (!nr_good_pages) {
+ printk(KERN_WARNING "Empty swap-file\n");
+ error = -EINVAL;
+ goto bad_swap;
+ }
+ p->swap_map[0] = SWAP_MAP_BAD;
+ swap_list_lock();
+ swap_device_lock(p);
+ p->max = maxpages;
+ p->flags = SWP_WRITEOK;
+ p->pages = nr_good_pages;
+ nr_swap_pages += nr_good_pages;
+ total_swap_pages += nr_good_pages;
+ printk(KERN_INFO "Adding Swap: %dk swap-space (priority %d)\n",
+ nr_good_pages<<(PAGE_SHIFT-10), p->prio);
+
+ /* insert swap space into swap_list: */
+ prev = -1;
+ for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
+ if (p->prio >= swap_info[i].prio) {
+ break;
+ }
+ prev = i;
+ }
+ p->next = i;
+ if (prev < 0) {
+ swap_list.head = swap_list.next = p - swap_info;
+ } else {
+ swap_info[prev].next = p - swap_info;
+ }
+ swap_device_unlock(p);
+ swap_list_unlock();
+ error = 0;
+ goto out;
+bad_swap:
+ if (bdev)
+ blkdev_put(bdev, BDEV_SWAP);
+bad_swap_2:
+ swap_list_lock();
+ swap_map = p->swap_map;
+ nd.mnt = p->swap_vfsmnt;
+ nd.dentry = p->swap_file;
+ p->swap_device = 0;
+ p->swap_file = NULL;
+ p->swap_vfsmnt = NULL;
+ p->swap_map = NULL;
+ p->flags = 0;
+ if (!(swap_flags & SWAP_FLAG_PREFER))
+ ++least_priority;
+ swap_list_unlock();
+ if (swap_map)
+ vfree(swap_map);
+ path_release(&nd);
+out:
+ if (swap_header)
+ free_page((long) swap_header);
+ unlock_kernel();
+ return error;
+}
+
+void si_swapinfo(struct sysinfo *val)
+{
+ unsigned int i;
+ unsigned long nr_to_be_unused = 0;
+
+ swap_list_lock();
+ for (i = 0; i < nr_swapfiles; i++) {
+ unsigned int j;
+ if (swap_info[i].flags != SWP_USED)
+ continue;
+ for (j = 0; j < swap_info[i].max; ++j) {
+ switch (swap_info[i].swap_map[j]) {
+ case 0:
+ case SWAP_MAP_BAD:
+ continue;
+ default:
+ nr_to_be_unused++;
+ }
+ }
+ }
+ val->freeswap = nr_swap_pages + nr_to_be_unused;
+ val->totalswap = total_swap_pages + nr_to_be_unused;
+ swap_list_unlock();
+}
+
+/*
+ * Verify that a swap entry is valid and increment its swap map count.
+ *
+ * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
+ * "permanent", but will be reclaimed by the next swapoff.
+ */
+int swap_duplicate(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+ unsigned long offset, type;
+ int result = 0;
+
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles)
+ goto bad_file;
+ p = type + swap_info;
+ offset = SWP_OFFSET(entry);
+
+ swap_device_lock(p);
+ if (offset < p->max && p->swap_map[offset]) {
+ if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
+ p->swap_map[offset]++;
+ result = 1;
+ } else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
+ if (swap_overflow++ < 5)
+ printk(KERN_WARNING "swap_dup: swap entry overflow\n");
+ p->swap_map[offset] = SWAP_MAP_MAX;
+ result = 1;
+ }
+ }
+ swap_device_unlock(p);
+out:
+ return result;
+
+bad_file:
+ printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
+ goto out;
+}
+
+/*
+ * Page lock needs to be held in all cases to prevent races with
+ * swap file deletion.
+ */
+int swap_count(struct page *page)
+{
+ struct swap_info_struct * p;
+ unsigned long offset, type;
+ swp_entry_t entry;
+ int retval = 0;
+
+ entry.val = page->index;
+ if (!entry.val)
+ goto bad_entry;
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles)
+ goto bad_file;
+ p = type + swap_info;
+ offset = SWP_OFFSET(entry);
+ if (offset >= p->max)
+ goto bad_offset;
+ if (!p->swap_map[offset])
+ goto bad_unused;
+ retval = p->swap_map[offset];
+out:
+ return retval;
+
+bad_entry:
+ printk(KERN_ERR "swap_count: null entry!\n");
+ goto out;
+bad_file:
+ printk(KERN_ERR "swap_count: %s%08lx\n", Bad_file, entry.val);
+ goto out;
+bad_offset:
+ printk(KERN_ERR "swap_count: %s%08lx\n", Bad_offset, entry.val);
+ goto out;
+bad_unused:
+ printk(KERN_ERR "swap_count: %s%08lx\n", Unused_offset, entry.val);
+ goto out;
+}
+
+/*
+ * Prior swap_duplicate protects against swap device deletion.
+ */
+void get_swaphandle_info(swp_entry_t entry, unsigned long *offset,
+ kdev_t *dev, struct inode **swapf)
+{
+ unsigned long type;
+ struct swap_info_struct *p;
+
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Bad_file, entry.val);
+ return;
+ }
+
+ p = &swap_info[type];
+ *offset = SWP_OFFSET(entry);
+ if (*offset >= p->max && *offset != 0) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Bad_offset, entry.val);
+ return;
+ }
+ if (p->swap_map && !p->swap_map[*offset]) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Unused_offset, entry.val);
+ return;
+ }
+ if (!(p->flags & SWP_USED)) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Unused_file, entry.val);
+ return;
+ }
+
+ if (p->swap_device) {
+ *dev = p->swap_device;
+ } else if (p->swap_file) {
+ *swapf = p->swap_file->d_inode;
+ } else {
+ printk(KERN_ERR "rw_swap_page: no swap file or device\n");
+ }
+ return;
+}
+
+/*
+ * swap_device_lock prevents swap_map being freed. Don't grab an extra
+ * reference on the swaphandle, it doesn't matter if it becomes unused.
+ */
+int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
+{
+ int ret = 0, i = 1 << page_cluster;
+ unsigned long toff;
+ struct swap_info_struct *swapdev = SWP_TYPE(entry) + swap_info;
+
+ if (!page_cluster) /* no readahead */
+ return 0;
+ toff = (SWP_OFFSET(entry) >> page_cluster) << page_cluster;
+ if (!toff) /* first page is swap header */
+ toff++, i--;
+ *offset = toff;
+
+ swap_device_lock(swapdev);
+ do {
+ /* Don't read-ahead past the end of the swap area */
+ if (toff >= swapdev->max)
+ break;
+ /* Don't read in free or bad pages */
+ if (!swapdev->swap_map[toff])
+ break;
+ if (swapdev->swap_map[toff] == SWAP_MAP_BAD)
+ break;
+ toff++;
+ ret++;
+ } while (--i);
+ swap_device_unlock(swapdev);
+ return ret;
+}
+++ /dev/null
-VERSION = 2
-PATCHLEVEL = 4
-SUBLEVEL = 16
-EXTRAVERSION = -kdb-xeno
-
-KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
-
-HW_ARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ -e s/arm.*/arm/ -e s/sa110/arm/)
-ifndef ARCH
-ARCH := $(HW_ARCH)
-endif
-
-ARCH=xeno
-
-KERNELPATH=kernel-$(shell echo $(KERNELRELEASE) | sed -e "s/-//")
-
-CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
- else if [ -x /bin/bash ]; then echo /bin/bash; \
- else echo sh; fi ; fi)
-TOPDIR := $(shell /bin/pwd)
-
-HPATH = $(TOPDIR)/include
-FINDHPATH = $(HPATH)/asm $(HPATH)/linux $(HPATH)/scsi $(HPATH)/net
-
-HOSTCC = gcc
-HOSTCFLAGS = -Wall -Wstrict-prototypes -O2 -fomit-frame-pointer
-
-CROSS_COMPILE =
-
-#
-# Include the make variables (CC, etc...)
-#
-
-AS = $(CROSS_COMPILE)as
-LD = $(CROSS_COMPILE)ld
-CC = $(CROSS_COMPILE)gcc
-CPP = $(CC) -E
-AR = $(CROSS_COMPILE)ar
-NM = $(CROSS_COMPILE)nm
-STRIP = $(CROSS_COMPILE)strip
-OBJCOPY = $(CROSS_COMPILE)objcopy
-OBJDUMP = $(CROSS_COMPILE)objdump
-MAKEFILES = $(TOPDIR)/.config
-GENKSYMS = /sbin/genksyms
-DEPMOD = /sbin/depmod
-KALLSYMS = /sbin/kallsyms
-MODFLAGS = -DMODULE
-CFLAGS_KERNEL =
-PERL = perl
-AWK = awk
-TMPPREFIX =
-
-export VERSION PATCHLEVEL SUBLEVEL EXTRAVERSION KERNELRELEASE ARCH \
- CONFIG_SHELL TOPDIR HPATH HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC \
- CPP AR NM STRIP OBJCOPY OBJDUMP MAKE MAKEFILES GENKSYMS MODFLAGS PERL AWK
-
-all: do-it-all
-
-#
-# Make "config" the default target if there is no configuration file or
-# "depend" the target if there is no top-level dependency information.
-#
-
-ifeq (.config,$(wildcard .config))
-include .config
-ifeq (.depend,$(wildcard .depend))
-include .depend
-do-it-all: Version vmlinux
-else
-CONFIGURATION = depend
-do-it-all: depend
-endif
-else
-CONFIGURATION = config
-do-it-all: config
-endif
-
-#
-# INSTALL_PATH specifies where to place the updated kernel and system map
-# images. Uncomment if you want to place them anywhere other than root.
-#
-
-#export INSTALL_PATH=/boot
-
-#
-# INSTALL_MOD_PATH specifies a prefix to MODLIB for module directory
-# relocations required by build roots. This is not defined in the
-# makefile but the arguement can be passed to make if needed.
-#
-
-MODLIB := $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
-export MODLIB
-
-#
-# standard CFLAGS
-#
-
-CPPFLAGS := -D__KERNEL__ -I$(HPATH)
-CPPFLAGS += $(patsubst %,-I%,$(CROSS_COMPILE_INC))
-
-CFLAGS := $(CPPFLAGS) -Wall -Wstrict-prototypes -Wno-trigraphs -O2 \
- -fno-strict-aliasing -fno-common
-ifndef CONFIG_FRAME_POINTER
-CFLAGS += -fomit-frame-pointer
-endif
-AFLAGS := -D__ASSEMBLY__ $(CPPFLAGS)
-
-#
-# ROOT_DEV specifies the default root-device when making the image.
-# This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case
-# the default of FLOPPY is used by 'build'.
-# This is i386 specific.
-#
-
-export ROOT_DEV = CURRENT
-
-#
-# If you want to preset the SVGA mode, uncomment the next line and
-# set SVGA_MODE to whatever number you want.
-# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
-# The number is the same as you would ordinarily press at bootup.
-# This is i386 specific.
-#
-
-export SVGA_MODE = -DSVGA_MODE=NORMAL_VGA
-
-#
-# If you want the RAM disk device, define this to be the size in blocks.
-# This is i386 specific.
-#
-
-#export RAMDISK = -DRAMDISK=512
-
-CORE_FILES =kernel/kernel.o mm/mm.o fs/fs.o ipc/ipc.o
-NETWORKS =net/network.o
-
-LIBS =$(TOPDIR)/lib/lib.a
-SUBDIRS =kernel drivers mm fs net ipc lib
-
-ifeq ($(CONFIG_KDB),y)
-CORE_FILES += kdb/kdb.o
-SUBDIRS += kdb
-endif
-
-DRIVERS-n :=
-DRIVERS-y :=
-DRIVERS-m :=
-DRIVERS- :=
-
-DRIVERS-$(CONFIG_ACPI) += drivers/acpi/acpi.o
-DRIVERS-$(CONFIG_PARPORT) += drivers/parport/driver.o
-DRIVERS-y += drivers/char/char.o \
- drivers/block/block.o \
- drivers/misc/misc.o \
- drivers/net/net.o \
- drivers/media/media.o
-DRIVERS-$(CONFIG_AGP) += drivers/char/agp/agp.o
-DRIVERS-$(CONFIG_DRM) += drivers/char/drm/drm.o
-DRIVERS-$(CONFIG_NUBUS) += drivers/nubus/nubus.a
-DRIVERS-$(CONFIG_ISDN) += drivers/isdn/isdn.a
-DRIVERS-$(CONFIG_NET_FC) += drivers/net/fc/fc.o
-DRIVERS-$(CONFIG_APPLETALK) += drivers/net/appletalk/appletalk.o
-DRIVERS-$(CONFIG_TR) += drivers/net/tokenring/tr.o
-DRIVERS-$(CONFIG_WAN) += drivers/net/wan/wan.o
-DRIVERS-$(CONFIG_ARCNET) += drivers/net/arcnet/arcnetdrv.o
-DRIVERS-$(CONFIG_ATM) += drivers/atm/atm.o
-DRIVERS-$(CONFIG_IDE) += drivers/ide/idedriver.o
-DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
-DRIVERS-$(CONFIG_SCSI) += drivers/scsi/scsidrv.o
-DRIVERS-$(CONFIG_FUSION_BOOT) += drivers/message/fusion/fusion.o
-DRIVERS-$(CONFIG_IEEE1394) += drivers/ieee1394/ieee1394drv.o
-
-ifneq ($(CONFIG_CD_NO_IDESCSI)$(CONFIG_BLK_DEV_IDECD)$(CONFIG_BLK_DEV_SR)$(CONFIG_PARIDE_PCD),)
-DRIVERS-y += drivers/cdrom/driver.o
-endif
-
-DRIVERS-$(CONFIG_SOUND) += drivers/sound/sounddrivers.o
-DRIVERS-$(CONFIG_PCI) += drivers/pci/driver.o
-DRIVERS-$(CONFIG_MTD) += drivers/mtd/mtdlink.o
-DRIVERS-$(CONFIG_PCMCIA) += drivers/pcmcia/pcmcia.o
-DRIVERS-$(CONFIG_NET_PCMCIA) += drivers/net/pcmcia/pcmcia_net.o
-DRIVERS-$(CONFIG_NET_WIRELESS) += drivers/net/wireless/wireless_net.o
-DRIVERS-$(CONFIG_PCMCIA_CHRDEV) += drivers/char/pcmcia/pcmcia_char.o
-DRIVERS-$(CONFIG_DIO) += drivers/dio/dio.a
-DRIVERS-$(CONFIG_SBUS) += drivers/sbus/sbus_all.o
-DRIVERS-$(CONFIG_ZORRO) += drivers/zorro/driver.o
-DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
-DRIVERS-$(CONFIG_ALL_PPC) += drivers/macintosh/macintosh.o
-DRIVERS-$(CONFIG_MAC) += drivers/macintosh/macintosh.o
-DRIVERS-$(CONFIG_ISAPNP) += drivers/pnp/pnp.o
-DRIVERS-$(CONFIG_SGI_IP22) += drivers/sgi/sgi.a
-DRIVERS-$(CONFIG_VT) += drivers/video/video.o
-DRIVERS-$(CONFIG_PARIDE) += drivers/block/paride/paride.a
-DRIVERS-$(CONFIG_HAMRADIO) += drivers/net/hamradio/hamradio.o
-DRIVERS-$(CONFIG_TC) += drivers/tc/tc.a
-DRIVERS-$(CONFIG_USB) += drivers/usb/usbdrv.o
-DRIVERS-$(CONFIG_INPUT) += drivers/input/inputdrv.o
-DRIVERS-$(CONFIG_I2O) += drivers/message/i2o/i2o.o
-DRIVERS-$(CONFIG_IRDA) += drivers/net/irda/irda.o
-DRIVERS-$(CONFIG_I2C) += drivers/i2c/i2c.o
-DRIVERS-$(CONFIG_PHONE) += drivers/telephony/telephony.o
-DRIVERS-$(CONFIG_MD) += drivers/md/mddev.o
-DRIVERS-$(CONFIG_BLUEZ) += drivers/bluetooth/bluetooth.o
-DRIVERS-$(CONFIG_HOTPLUG_PCI) += drivers/hotplug/vmlinux-obj.o
-
-DRIVERS := $(DRIVERS-y)
-
-
-# files removed with 'make clean'
-CLEAN_FILES = \
- kernel/ksyms.lst include/linux/compile.h \
- vmlinux System.map \
- $(TMPPREFIX).tmp* \
- drivers/char/consolemap_deftbl.c drivers/video/promcon_tbl.c \
- drivers/char/conmakehash \
- drivers/char/drm/*-mod.c \
- drivers/pci/devlist.h drivers/pci/classlist.h drivers/pci/gen-devlist \
- drivers/zorro/devlist.h drivers/zorro/gen-devlist \
- drivers/sound/bin2hex drivers/sound/hex2hex \
- drivers/atm/fore200e_mkfirm drivers/atm/{pca,sba}*{.bin,.bin1,.bin2} \
- drivers/scsi/aic7xxx/aicasm/aicasm_gram.c \
- drivers/scsi/aic7xxx/aicasm/aicasm_scan.c \
- drivers/scsi/aic7xxx/aicasm/y.tab.h \
- drivers/scsi/aic7xxx/aicasm/aicasm \
- drivers/scsi/53c700-mem.c \
- net/khttpd/make_times_h \
- net/khttpd/times.h \
- submenu*
-# directories removed with 'make clean'
-CLEAN_DIRS = \
- modules
-
-# files removed with 'make mrproper'
-MRPROPER_FILES = \
- include/linux/autoconf.h include/linux/version.h \
- drivers/net/hamradio/soundmodem/sm_tbl_{afsk1200,afsk2666,fsk9600}.h \
- drivers/net/hamradio/soundmodem/sm_tbl_{hapn4800,psk4800}.h \
- drivers/net/hamradio/soundmodem/sm_tbl_{afsk2400_7,afsk2400_8}.h \
- drivers/net/hamradio/soundmodem/gentbl \
- drivers/sound/*_boot.h drivers/sound/.*.boot \
- drivers/sound/msndinit.c \
- drivers/sound/msndperm.c \
- drivers/sound/pndsperm.c \
- drivers/sound/pndspini.c \
- drivers/atm/fore200e_*_fw.c drivers/atm/.fore200e_*.fw \
- .version .config* config.in config.old \
- scripts/tkparse scripts/kconfig.tk scripts/kconfig.tmp \
- scripts/lxdialog/*.o scripts/lxdialog/lxdialog \
- .menuconfig.log \
- include/asm \
- kdb/gen-kdb_cmds.c \
- .hdepend scripts/mkdep scripts/split-include scripts/docproc \
- $(TOPDIR)/include/linux/modversions.h \
- kernel.spec
-
-# directories removed with 'make mrproper'
-MRPROPER_DIRS = \
- include/config \
- $(TOPDIR)/include/linux/modules
-
-
-include arch/$(ARCH)/Makefile
-
-export CPPFLAGS CFLAGS CFLAGS_KERNEL AFLAGS AFLAGS_KERNEL
-
-export NETWORKS DRIVERS LIBS HEAD LDFLAGS LINKFLAGS MAKEBOOT ASFLAGS
-
-.S.s:
- $(CPP) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -o $*.s $<
-.S.o:
- $(CC) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -c -o $*.o $<
-
-Version: dummy
- @rm -f include/linux/compile.h
-
-boot: vmlinux
- @$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C arch/$(ARCH)/boot
-
-LD_VMLINUX := $(LD) $(LINKFLAGS) $(HEAD) init/main.o init/version.o \
- --start-group \
- $(CORE_FILES) \
- $(DRIVERS) \
- $(NETWORKS) \
- $(LIBS) \
- --end-group
-ifeq ($(CONFIG_KALLSYMS),y)
-LD_VMLINUX_KALLSYMS := $(TMPPREFIX).tmp_kallsyms3.o
-else
-LD_VMLINUX_KALLSYMS :=
-endif
-
-vmlinux: include/linux/version.h $(CONFIGURATION) init/main.o init/version.o linuxsubdirs
- @$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" kallsyms
-
-.PHONY: kallsyms
-
-kallsyms:
-ifeq ($(CONFIG_KALLSYMS),y)
- @echo kallsyms pass 1
- $(LD_VMLINUX) -o $(TMPPREFIX).tmp_vmlinux1
- @$(KALLSYMS) $(TMPPREFIX).tmp_vmlinux1 > $(TMPPREFIX).tmp_kallsyms1.o
- @echo kallsyms pass 2
- @$(LD_VMLINUX) $(TMPPREFIX).tmp_kallsyms1.o -o $(TMPPREFIX).tmp_vmlinux2
- @$(KALLSYMS) $(TMPPREFIX).tmp_vmlinux2 > $(TMPPREFIX).tmp_kallsyms2.o
- @echo kallsyms pass 3
- @$(LD_VMLINUX) $(TMPPREFIX).tmp_kallsyms2.o -o $(TMPPREFIX).tmp_vmlinux3
- @$(KALLSYMS) $(TMPPREFIX).tmp_vmlinux3 > $(TMPPREFIX).tmp_kallsyms3.o
-endif
- $(LD_VMLINUX) $(LD_VMLINUX_KALLSYMS) -o $(TMPPREFIX)vmlinux
-ifneq ($(TMPPREFIX),)
- mv $(TMPPREFIX)vmlinux vmlinux
-endif
- $(NM) vmlinux | grep -v '\(compiled\)\|\(\.o$$\)\|\( [aUw] \)\|\(\.\.ng$$\)\|\(LASH[RL]DI\)' | sort > System.map
- @rm -f $(TMPPREFIX).tmp_vmlinux* $(TMPPREFIX).tmp_kallsyms*
-
-symlinks:
- rm -f include/asm
- ( cd include ; ln -sf asm-$(ARCH) asm)
- @if [ ! -d include/linux/modules ]; then \
- mkdir include/linux/modules; \
- fi
-
-oldconfig: symlinks
- $(CONFIG_SHELL) scripts/Configure -d arch/$(ARCH)/config.in
-
-xconfig: symlinks
- $(MAKE) -C scripts kconfig.tk
- wish -f scripts/kconfig.tk
-
-menuconfig: include/linux/version.h symlinks
- $(MAKE) -C scripts/lxdialog all
- $(CONFIG_SHELL) scripts/Menuconfig arch/$(ARCH)/config.in
-
-config: symlinks
- $(CONFIG_SHELL) scripts/Configure arch/$(ARCH)/config.in
-
-include/config/MARKER: scripts/split-include include/linux/autoconf.h
- scripts/split-include include/linux/autoconf.h include/config
- @ touch include/config/MARKER
-
-linuxsubdirs: $(patsubst %, _dir_%, $(SUBDIRS))
-
-$(patsubst %, _dir_%, $(SUBDIRS)) : dummy include/linux/version.h include/config/MARKER
- $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C $(patsubst _dir_%, %, $@)
-
-$(TOPDIR)/include/linux/version.h: include/linux/version.h
-$(TOPDIR)/include/linux/compile.h: include/linux/compile.h
-
-newversion:
- . scripts/mkversion > .tmpversion
- @mv -f .tmpversion .version
-
-include/linux/compile.h: $(CONFIGURATION) include/linux/version.h newversion
- @echo -n \#define UTS_VERSION \"\#`cat .version` > .ver
- @if [ -n "$(CONFIG_SMP)" ] ; then echo -n " SMP" >> .ver; fi
- @if [ -f .name ]; then echo -n \-`cat .name` >> .ver; fi
- @echo ' '`date`'"' >> .ver
- @echo \#define LINUX_COMPILE_TIME \"`date +%T`\" >> .ver
- @echo \#define LINUX_COMPILE_BY \"`whoami`\" >> .ver
- @echo \#define LINUX_COMPILE_HOST \"`hostname`\" >> .ver
- @if [ -x /bin/dnsdomainname ]; then \
- echo \#define LINUX_COMPILE_DOMAIN \"`dnsdomainname`\"; \
- elif [ -x /bin/domainname ]; then \
- echo \#define LINUX_COMPILE_DOMAIN \"`domainname`\"; \
- else \
- echo \#define LINUX_COMPILE_DOMAIN ; \
- fi >> .ver
- @echo \#define LINUX_COMPILER \"`$(CC) $(CFLAGS) -v 2>&1 | tail -1`\" >> .ver
- @mv -f .ver $@
-
-include/linux/version.h: ./Makefile
- @echo \#define UTS_RELEASE \"$(KERNELRELEASE)\" > .ver
- @echo \#define LINUX_VERSION_CODE `expr $(VERSION) \\* 65536 + $(PATCHLEVEL) \\* 256 + $(SUBLEVEL)` >> .ver
- @echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))' >>.ver
- @mv -f .ver $@
-
-init/version.o: init/version.c include/linux/compile.h include/config/MARKER
- $(CC) $(CFLAGS) $(CFLAGS_KERNEL) -DUTS_MACHINE='"$(HW_ARCH)"' -c -o init/version.o init/version.c
-
-init/main.o: init/main.c include/config/MARKER
- $(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -c -o $*.o $<
-
-fs lib mm ipc kernel drivers net: dummy
- $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" $(subst $@, _dir_$@, $@)
-
-TAGS: dummy
- etags `find include/asm-$(ARCH) -name '*.h'`
- find include -type d \( -name "asm-*" -o -name config \) -prune -o -name '*.h' -print | xargs etags -a
- find $(SUBDIRS) init -name '*.[ch]' | xargs etags -a
-
-# Exuberant ctags works better with -I
-tags: dummy
- CTAGSF=`ctags --version | grep -i exuberant >/dev/null && echo "-I __initdata,__exitdata,EXPORT_SYMBOL,EXPORT_SYMBOL_NOVERS"`; \
- ctags $$CTAGSF `find include/asm-$(ARCH) -name '*.h'` && \
- find include -type d \( -name "asm-*" -o -name config \) -prune -o -name '*.h' -print | xargs ctags $$CTAGSF -a && \
- find $(SUBDIRS) init -name '*.[ch]' | xargs ctags $$CTAGSF -a
-
-ifdef CONFIG_MODULES
-ifdef CONFIG_MODVERSIONS
-MODFLAGS += -DMODVERSIONS -include $(HPATH)/linux/modversions.h
-endif
-
-.PHONY: modules
-modules: $(patsubst %, _mod_%, $(SUBDIRS))
-
-.PHONY: $(patsubst %, _mod_%, $(SUBDIRS))
-$(patsubst %, _mod_%, $(SUBDIRS)) : include/linux/version.h include/config/MARKER
- $(MAKE) -C $(patsubst _mod_%, %, $@) CFLAGS="$(CFLAGS) $(MODFLAGS)" MAKING_MODULES=1 modules
-
-.PHONY: modules_install
-modules_install: _modinst_ $(patsubst %, _modinst_%, $(SUBDIRS)) _modinst_post
-
-.PHONY: _modinst_
-_modinst_:
- @rm -rf $(MODLIB)/kernel
- @rm -f $(MODLIB)/build
- @mkdir -p $(MODLIB)/kernel
- @ln -s $(TOPDIR) $(MODLIB)/build
-
-# If System.map exists, run depmod. This deliberately does not have a
-# dependency on System.map since that would run the dependency tree on
-# vmlinux. This depmod is only for convenience to give the initial
-# boot a modules.dep even before / is mounted read-write. However the
-# boot script depmod is the master version.
-ifeq "$(strip $(INSTALL_MOD_PATH))" ""
-depmod_opts :=
-else
-depmod_opts := -b $(INSTALL_MOD_PATH) -r
-endif
-.PHONY: _modinst_post
-_modinst_post: _modinst_post_pcmcia
-# if [ -r System.map ]; then $(DEPMOD) -ae -F System.map $(depmod_opts) $(KERNELRELEASE); fi
-
-# Backwards compatibilty symlinks for people still using old versions
-# of pcmcia-cs with hard coded pathnames on insmod. Remove
-# _modinst_post_pcmcia for kernel 2.4.1.
-.PHONY: _modinst_post_pcmcia
-_modinst_post_pcmcia:
- cd $(MODLIB); \
- mkdir -p pcmcia; \
- find kernel -path '*/pcmcia/*' -name '*.o' | xargs -i -r ln -sf ../{} pcmcia
-
-.PHONY: $(patsubst %, _modinst_%, $(SUBDIRS))
-$(patsubst %, _modinst_%, $(SUBDIRS)) :
- $(MAKE) -C $(patsubst _modinst_%, %, $@) modules_install
-
-# modules disabled....
-
-else
-modules modules_install: dummy
- @echo
- @echo "The present kernel configuration has modules disabled."
- @echo "Type 'make config' and enable loadable module support."
- @echo "Then build a kernel with module support enabled."
- @echo
- @exit 1
-endif
-
-clean: archclean
- find . \( -name '*.[oas]' -o -name core -o -name '.*.flags' \) -type f -print \
- | grep -v lxdialog/ | xargs rm -f
- rm -f $(CLEAN_FILES)
- rm -rf $(CLEAN_DIRS)
- $(MAKE) -C Documentation/DocBook clean
-
-mrproper: clean archmrproper
- find . \( -size 0 -o -name .depend \) -type f -print | xargs rm -f
- rm -f $(MRPROPER_FILES)
- rm -rf $(MRPROPER_DIRS)
- $(MAKE) -C Documentation/DocBook mrproper
-
-distclean: mrproper
- rm -f core `find . \( -not -type d \) -and \
- \( -name '*.orig' -o -name '*.rej' -o -name '*~' \
- -o -name '*.bak' -o -name '#*#' -o -name '.*.orig' \
- -o -name '.*.rej' -o -name '.SUMS' -o -size 0 \) -type f -print` TAGS tags
-
-backup: mrproper
- cd .. && tar cf - linux/ | gzip -9 > backup.gz
- sync
-
-sgmldocs:
- chmod 755 $(TOPDIR)/scripts/docgen
- chmod 755 $(TOPDIR)/scripts/gen-all-syms
- chmod 755 $(TOPDIR)/scripts/kernel-doc
- $(MAKE) -C $(TOPDIR)/Documentation/DocBook books
-
-psdocs: sgmldocs
- $(MAKE) -C Documentation/DocBook ps
-
-pdfdocs: sgmldocs
- $(MAKE) -C Documentation/DocBook pdf
-
-htmldocs: sgmldocs
- $(MAKE) -C Documentation/DocBook html
-
-sums:
- find . -type f -print | sort | xargs sum > .SUMS
-
-dep-files: scripts/mkdep archdep include/linux/version.h
- scripts/mkdep -- init/*.c > .depend
- scripts/mkdep -- `find $(FINDHPATH) -name SCCS -prune -o -follow -name \*.h ! -name modversions.h -print` > .hdepend
- $(MAKE) $(patsubst %,_sfdep_%,$(SUBDIRS)) _FASTDEP_ALL_SUB_DIRS="$(SUBDIRS)"
-ifdef CONFIG_MODVERSIONS
- $(MAKE) update-modverfile
-endif
-
-ifdef CONFIG_MODVERSIONS
-MODVERFILE := $(TOPDIR)/include/linux/modversions.h
-else
-MODVERFILE :=
-endif
-export MODVERFILE
-
-depend dep: dep-files
-
-checkconfig:
- find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w scripts/checkconfig.pl
-
-checkhelp:
- find * -name [cC]onfig.in -print | sort | xargs $(PERL) -w scripts/checkhelp.pl
-
-checkincludes:
- find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w scripts/checkincludes.pl
-
-ifdef CONFIGURATION
-..$(CONFIGURATION):
- @echo
- @echo "You have a bad or nonexistent" .$(CONFIGURATION) ": running 'make" $(CONFIGURATION)"'"
- @echo
- $(MAKE) $(CONFIGURATION)
- @echo
- @echo "Successful. Try re-making (ignore the error that follows)"
- @echo
- exit 1
-
-#dummy: ..$(CONFIGURATION)
-dummy:
-
-else
-
-dummy:
-
-endif
-
-include Rules.make
-
-#
-# This generates dependencies for the .h files.
-#
-
-scripts/mkdep: scripts/mkdep.c
- $(HOSTCC) $(HOSTCFLAGS) -o scripts/mkdep scripts/mkdep.c
-
-scripts/split-include: scripts/split-include.c
- $(HOSTCC) $(HOSTCFLAGS) -o scripts/split-include scripts/split-include.c
-
-#
-# RPM target
-#
-# If you do a make spec before packing the tarball you can rpm -ta it
-#
-spec:
- . scripts/mkspec >kernel.spec
-
-#
-# Build a tar ball, generate an rpm from it and pack the result
-# There arw two bits of magic here
-# 1) The use of /. to avoid tar packing just the symlink
-# 2) Removing the .dep files as they have source paths in them that
-# will become invalid
-#
-rpm: clean spec
- find . \( -size 0 -o -name .depend -o -name .hdepend \) -type f -print | xargs rm -f
- set -e; \
- cd $(TOPDIR)/.. ; \
- ln -sf $(TOPDIR) $(KERNELPATH) ; \
- tar -cvz --exclude CVS -f $(KERNELPATH).tar.gz $(KERNELPATH)/. ; \
- rm $(KERNELPATH) ; \
- cd $(TOPDIR) ; \
- . scripts/mkversion > .version ; \
- rpm -ta $(TOPDIR)/../$(KERNELPATH).tar.gz ; \
- rm $(TOPDIR)/../$(KERNELPATH).tar.gz
+++ /dev/null
-#
-# xeno/Makefile
-#
-# This file is included by the global makefile so that you can add your own
-# architecture-specific flags and dependencies. Remember to do have actions
-# for "archclean" and "archdep" for cleaning up and making dependencies for
-# this architecture
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License. See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# Copyright (C) 1994 by Linus Torvalds
-#
-# 19990713 Artur Skawina <skawina@geocities.com>
-# Added '-march' and '-mpreferred-stack-boundary' support
-#
-
-LD=$(CROSS_COMPILE)ld -m elf_i386
-OBJCOPY=$(CROSS_COMPILE)objcopy -O binary -R .note -R .comment -S
-LDFLAGS=-e stext
-LINKFLAGS =-T $(TOPDIR)/arch/xeno/vmlinux.lds $(LDFLAGS)
-
-CFLAGS += -pipe
-
-# prevent gcc from keeping the stack 16 byte aligned
-CFLAGS += $(shell if $(CC) -mpreferred-stack-boundary=2 -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-mpreferred-stack-boundary=2"; fi)
-
-ifdef CONFIG_M686
-CFLAGS += -march=i686
-endif
-
-ifdef CONFIG_MPENTIUMIII
-CFLAGS += -march=i686
-endif
-
-ifdef CONFIG_MPENTIUM4
-CFLAGS += -march=i686
-endif
-
-ifdef CONFIG_MK7
-CFLAGS += $(shell if $(CC) -march=athlon -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-march=athlon"; else echo "-march=i686 -malign-functions=4"; fi)
-endif
-
-HEAD := arch/xeno/kernel/head.o arch/xeno/kernel/init_task.o
-
-SUBDIRS += arch/xeno/kernel arch/xeno/mm arch/xeno/lib
-SUBDIRS += arch/xeno/drivers/console arch/xeno/drivers/network
-SUBDIRS += arch/xeno/drivers/dom0 arch/xeno/drivers/block
-
-CORE_FILES += arch/xeno/kernel/kernel.o arch/xeno/mm/mm.o
-CORE_FILES += arch/xeno/drivers/console/con.o
-CORE_FILES += arch/xeno/drivers/block/blk.o
-CORE_FILES += arch/xeno/drivers/network/net.o
-CORE_FILES += arch/xeno/drivers/dom0/dom0.o
-LIBS := $(TOPDIR)/arch/xeno/lib/lib.a $(LIBS) $(TOPDIR)/arch/xeno/lib/lib.a
-
-arch/xeno/kernel: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/kernel
-
-arch/xeno/mm: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/mm
-
-arch/xeno/drivers/console: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/console
-
-arch/xeno/drivers/network: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/network
-
-arch/xeno/drivers/block: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/block
-
-arch/xeno/drivers/dom0: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/dom0
-
-ifdef CONFIG_KDB
-arch/xeno/kdb: dummy
- $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/kdb
-endif
-
-MAKEBOOT = $(MAKE) -C arch/$(ARCH)/boot
-
-vmlinux: arch/xeno/vmlinux.lds
-
-FORCE: ;
-
-.PHONY: bzImage compressed clean archclean archmrproper archdep
-
-bzImage: vmlinux
- @$(MAKEBOOT) image.gz
-
-archclean:
- @$(MAKEBOOT) clean
-
-archmrproper:
-
-archdep:
- @$(MAKEBOOT) dep
+++ /dev/null
-#
-# arch/xeno/boot/Makefile
-#
-
-image.gz: image
- gzip -f -9 < $< > $@
-
-image: $(TOPDIR)/vmlinux
- # Guest OS header -- first 8 bytes are identifier 'XenoGues'.
- echo -e -n 'XenoGues' >$@
- # Guest OS header -- next 4 bytes are load address (0xC0000000).
- echo -e -n '\000\000\000\300' >>$@
- $(OBJCOPY) $< image.body
- # Guest OS header is immediately followed by raw OS image.
- # Start address must be at byte 0.
- cat image.body >>$@
- rm -f image.body
-
-dep:
-
-clean:
- rm -f image image.gz
+++ /dev/null
-#
-# For a description of the syntax of this configuration file,
-# see Documentation/kbuild/config-language.txt.
-#
-mainmenu_name "Linux Kernel Configuration"
-
-define_bool CONFIG_XENO y
-
-define_bool CONFIG_X86 y
-define_bool CONFIG_ISA y
-define_bool CONFIG_SBUS n
-
-define_bool CONFIG_UID16 y
-
-mainmenu_option next_comment
-comment 'Code maturity level options'
-bool 'Prompt for development and/or incomplete code/drivers' CONFIG_EXPERIMENTAL
-endmenu
-
-mainmenu_option next_comment
-comment 'Loadable module support'
-bool 'Enable loadable module support' CONFIG_MODULES
-if [ "$CONFIG_MODULES" = "y" ]; then
- bool ' Set version information on all module symbols' CONFIG_MODVERSIONS
- bool ' Kernel module loader' CONFIG_KMOD
-fi
-endmenu
-
-mainmenu_option next_comment
-comment 'Processor type and features'
-choice 'Processor family' \
- "Pentium-Pro/Celeron/Pentium-II CONFIG_M686 \
- Pentium-III/Celeron(Coppermine) CONFIG_MPENTIUMIII \
- Pentium-4 CONFIG_MPENTIUM4 \
- Athlon/Duron/K7 CONFIG_MK7" Pentium-Pro
-
- define_bool CONFIG_X86_WP_WORKS_OK y
- define_bool CONFIG_X86_INVLPG y
- define_bool CONFIG_X86_CMPXCHG y
- define_bool CONFIG_X86_XADD y
- define_bool CONFIG_X86_BSWAP y
- define_bool CONFIG_X86_POPAD_OK y
- define_bool CONFIG_RWSEM_GENERIC_SPINLOCK n
- define_bool CONFIG_RWSEM_XCHGADD_ALGORITHM y
-
- define_bool CONFIG_X86_GOOD_APIC y
- define_bool CONFIG_X86_PGE y
- define_bool CONFIG_X86_USE_PPRO_CHECKSUM y
- define_bool CONFIG_X86_TSC y
-
-if [ "$CONFIG_M686" = "y" ]; then
- define_int CONFIG_X86_L1_CACHE_SHIFT 5
-fi
-if [ "$CONFIG_MPENTIUMIII" = "y" ]; then
- define_int CONFIG_X86_L1_CACHE_SHIFT 5
-fi
-if [ "$CONFIG_MPENTIUM4" = "y" ]; then
- define_int CONFIG_X86_L1_CACHE_SHIFT 7
-fi
-if [ "$CONFIG_MK7" = "y" ]; then
- define_int CONFIG_X86_L1_CACHE_SHIFT 6
- define_bool CONFIG_X86_USE_3DNOW y
-fi
-
-choice 'High Memory Support' \
- "off CONFIG_NOHIGHMEM \
- 4GB CONFIG_HIGHMEM4G \
- 64GB CONFIG_HIGHMEM64G" off
-if [ "$CONFIG_HIGHMEM4G" = "y" ]; then
- define_bool CONFIG_HIGHMEM y
-fi
-if [ "$CONFIG_HIGHMEM64G" = "y" ]; then
- define_bool CONFIG_HIGHMEM y
- define_bool CONFIG_X86_PAE y
-fi
-
-#bool 'Symmetric multi-processing support' CONFIG_SMP
-#if [ "$CONFIG_SMP" = "y" -a "$CONFIG_X86_CMPXCHG" = "y" ]; then
-# define_bool CONFIG_HAVE_DEC_LOCK y
-#fi
-endmenu
-
-mainmenu_option next_comment
-comment 'General setup'
-
-bool 'Networking support' CONFIG_NET
-
-bool 'System V IPC' CONFIG_SYSVIPC
-bool 'BSD Process Accounting' CONFIG_BSD_PROCESS_ACCT
-bool 'Sysctl support' CONFIG_SYSCTL
-if [ "$CONFIG_PROC_FS" = "y" ]; then
- choice 'Kernel core (/proc/kcore) format' \
- "ELF CONFIG_KCORE_ELF \
- A.OUT CONFIG_KCORE_AOUT" ELF
-fi
-tristate 'Kernel support for a.out binaries' CONFIG_BINFMT_AOUT
-tristate 'Kernel support for ELF binaries' CONFIG_BINFMT_ELF
-tristate 'Kernel support for MISC binaries' CONFIG_BINFMT_MISC
-
-endmenu
-
-if [ "$CONFIG_NET" = "y" ]; then
- source net/Config.in
-fi
-
-source drivers/block/Config.in
-define_bool CONFIG_BLK_DEV_IDE_MODES n
-define_bool CONFIG_BLK_DEV_HD n
-
-source fs/Config.in
-
-mainmenu_option next_comment
-comment 'Kernel hacking'
-
-bool 'Kernel debugging' CONFIG_DEBUG_KERNEL
-if [ "$CONFIG_DEBUG_KERNEL" != "n" ]; then
- bool ' Debug high memory support' CONFIG_DEBUG_HIGHMEM
- bool ' Debug memory allocations' CONFIG_DEBUG_SLAB
- bool ' Memory mapped I/O debugging' CONFIG_DEBUG_IOVIRT
- bool ' Magic SysRq key' CONFIG_MAGIC_SYSRQ
- bool ' Spinlock debugging' CONFIG_DEBUG_SPINLOCK
- bool ' Verbose BUG() reporting (adds 70K)' CONFIG_DEBUG_BUGVERBOSE
- bool ' Built-in Kernel Debugger support' CONFIG_KDB
- dep_tristate ' KDB modules' CONFIG_KDB_MODULES $CONFIG_KDB
- if [ "$CONFIG_KDB" = "y" ]; then
- bool ' KDB off by default' CONFIG_KDB_OFF
- comment ' Load all symbols for debugging is required for KDB'
- define_bool CONFIG_KALLSYMS y
- else
- bool ' Load all symbols for debugging' CONFIG_KALLSYMS
- fi
- bool ' Compile the kernel with frame pointers' CONFIG_FRAME_POINTER
-fi
-
-endmenu
+++ /dev/null
-#
-# Automatically generated make config: don't edit
-#
-CONFIG_X86=y
-CONFIG_ISA=y
-# CONFIG_SBUS is not set
-CONFIG_UID16=y
-
-#
-# Code maturity level options
-#
-# CONFIG_EXPERIMENTAL is not set
-
-#
-# Loadable module support
-#
-CONFIG_MODULES=y
-CONFIG_MODVERSIONS=y
-CONFIG_KMOD=y
-
-#
-# Processor type and features
-#
-# CONFIG_M386 is not set
-# CONFIG_M486 is not set
-# CONFIG_M586 is not set
-# CONFIG_M586TSC is not set
-# CONFIG_M586MMX is not set
-CONFIG_M686=y
-# CONFIG_MPENTIUMIII is not set
-# CONFIG_MPENTIUM4 is not set
-# CONFIG_MK6 is not set
-# CONFIG_MK7 is not set
-# CONFIG_MCRUSOE is not set
-# CONFIG_MWINCHIPC6 is not set
-# CONFIG_MWINCHIP2 is not set
-# CONFIG_MWINCHIP3D is not set
-# CONFIG_MCYRIXIII is not set
-CONFIG_X86_WP_WORKS_OK=y
-CONFIG_X86_INVLPG=y
-CONFIG_X86_CMPXCHG=y
-CONFIG_X86_XADD=y
-CONFIG_X86_BSWAP=y
-CONFIG_X86_POPAD_OK=y
-# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
-CONFIG_X86_L1_CACHE_SHIFT=5
-CONFIG_X86_TSC=y
-CONFIG_X86_GOOD_APIC=y
-CONFIG_X86_PGE=y
-CONFIG_X86_USE_PPRO_CHECKSUM=y
-# CONFIG_TOSHIBA is not set
-# CONFIG_I8K is not set
-# CONFIG_MICROCODE is not set
-# CONFIG_X86_MSR is not set
-# CONFIG_X86_CPUID is not set
-CONFIG_NOHIGHMEM=y
-# CONFIG_HIGHMEM4G is not set
-# CONFIG_HIGHMEM64G is not set
-# CONFIG_MATH_EMULATION is not set
-# CONFIG_MTRR is not set
-# CONFIG_SMP is not set
-# CONFIG_X86_UP_APIC is not set
-
-#
-# General setup
-#
-CONFIG_NET=y
-# CONFIG_PCI is not set
-# CONFIG_EISA is not set
-# CONFIG_MCA is not set
-# CONFIG_HOTPLUG is not set
-# CONFIG_PCMCIA is not set
-# CONFIG_HOTPLUG_PCI is not set
-CONFIG_SYSVIPC=y
-# CONFIG_BSD_PROCESS_ACCT is not set
-CONFIG_SYSCTL=y
-CONFIG_KCORE_ELF=y
-# CONFIG_KCORE_AOUT is not set
-CONFIG_BINFMT_AOUT=y
-CONFIG_BINFMT_ELF=y
-# CONFIG_BINFMT_MISC is not set
-# CONFIG_PM is not set
-# CONFIG_APM_IGNORE_USER_SUSPEND is not set
-# CONFIG_APM_DO_ENABLE is not set
-# CONFIG_APM_CPU_IDLE is not set
-# CONFIG_APM_DISPLAY_BLANK is not set
-# CONFIG_APM_RTC_IS_GMT is not set
-# CONFIG_APM_ALLOW_INTS is not set
-# CONFIG_APM_REAL_MODE_POWER_OFF is not set
-
-#
-# Memory Technology Devices (MTD)
-#
-# CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
-# CONFIG_PARPORT is not set
-
-#
-# Plug and Play configuration
-#
-# CONFIG_PNP is not set
-
-#
-# Block devices
-#
-# CONFIG_BLK_DEV_FD is not set
-# CONFIG_BLK_DEV_XD is not set
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=4096
-# CONFIG_BLK_DEV_INITRD is not set
-CONFIG_XENOLINUX_BLOCK=y
-
-#
-# Multi-device support (RAID and LVM)
-#
-# CONFIG_MD is not set
-
-#
-# Networking options
-#
-CONFIG_PACKET=y
-CONFIG_PACKET_MMAP=y
-CONFIG_NETLINK=y
-CONFIG_RTNETLINK=y
-# CONFIG_NETLINK_DEV is not set
-# CONFIG_NETFILTER is not set
-CONFIG_FILTER=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_IP_MULTICAST is not set
-# CONFIG_IP_ADVANCED_ROUTER is not set
-CONFIG_IP_PNP=y
-# CONFIG_IP_PNP_DHCP is not set
-# CONFIG_IP_PNP_BOOTP is not set
-# CONFIG_IP_PNP_RARP is not set
-# CONFIG_NET_IPIP is not set
-# CONFIG_NET_IPGRE is not set
-# CONFIG_INET_ECN is not set
-# CONFIG_SYN_COOKIES is not set
-
-#
-#
-#
-# CONFIG_IPX is not set
-# CONFIG_ATALK is not set
-# CONFIG_DECNET is not set
-# CONFIG_BRIDGE is not set
-
-#
-# QoS and/or fair queueing
-#
-# CONFIG_NET_SCHED is not set
-
-#
-# Telephony Support
-#
-# CONFIG_PHONE is not set
-
-#
-# ATA/IDE/MFM/RLL support
-#
-# CONFIG_IDE is not set
-# CONFIG_BLK_DEV_IDE_MODES is not set
-# CONFIG_BLK_DEV_HD is not set
-
-#
-# SCSI support
-#
-# CONFIG_SCSI is not set
-
-#
-# Fusion MPT device support
-#
-# CONFIG_FUSION_BOOT is not set
-# CONFIG_FUSION_ISENSE is not set
-# CONFIG_FUSION_CTL is not set
-# CONFIG_FUSION_LAN is not set
-
-#
-# I2O device support
-#
-# CONFIG_I2O is not set
-
-#
-# Network device support
-#
-# CONFIG_NETDEVICES is not set
-
-#
-# Amateur Radio support
-#
-# CONFIG_HAMRADIO is not set
-
-#
-# IrDA (infrared) support
-#
-# CONFIG_IRDA is not set
-
-#
-# ISDN subsystem
-#
-# CONFIG_ISDN is not set
-
-#
-# Old CD-ROM drivers (not SCSI, not IDE)
-#
-# CONFIG_CD_NO_IDESCSI is not set
-
-#
-# Input core support
-#
-# CONFIG_INPUT is not set
-CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
-CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
-
-#
-# Character devices
-#
-# CONFIG_VT is not set
-# CONFIG_SERIAL is not set
-# CONFIG_SERIAL_NONSTANDARD is not set
-# CONFIG_UNIX98_PTYS is not set
-
-#
-# I2C support
-#
-# CONFIG_I2C is not set
-
-#
-# Mice
-#
-# CONFIG_BUSMOUSE is not set
-# CONFIG_MOUSE is not set
-
-#
-# Joysticks
-#
-# CONFIG_INPUT_GAMEPORT is not set
-
-#
-# Input core support is needed for gameports
-#
-
-#
-# Input core support is needed for joysticks
-#
-# CONFIG_QIC02_TAPE is not set
-
-#
-# Watchdog Cards
-#
-# CONFIG_WATCHDOG is not set
-# CONFIG_NVRAM is not set
-# CONFIG_RTC is not set
-# CONFIG_DTLK is not set
-# CONFIG_R3964 is not set
-# CONFIG_APPLICOM is not set
-
-#
-# Ftape, the floppy tape device driver
-#
-# CONFIG_FTAPE is not set
-# CONFIG_AGP is not set
-# CONFIG_DRM is not set
-# CONFIG_MWAVE is not set
-
-#
-# Multimedia devices
-#
-# CONFIG_VIDEO_DEV is not set
-
-#
-# File systems
-#
-# CONFIG_QUOTA is not set
-CONFIG_AUTOFS_FS=y
-CONFIG_AUTOFS4_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_JBD=y
-# CONFIG_FAT_FS is not set
-# CONFIG_CRAMFS is not set
-# CONFIG_TMPFS is not set
-# CONFIG_RAMFS is not set
-# CONFIG_ISO9660_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_VXFS_FS is not set
-# CONFIG_NTFS_FS is not set
-# CONFIG_HPFS_FS is not set
-CONFIG_PROC_FS=y
-# CONFIG_ROMFS_FS is not set
-CONFIG_EXT2_FS=y
-# CONFIG_SYSV_FS is not set
-# CONFIG_UDF_FS is not set
-# CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
-# CONFIG_CODA_FS is not set
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NFSD_V3=y
-CONFIG_SUNRPC=y
-CONFIG_LOCKD=y
-CONFIG_LOCKD_V4=y
-# CONFIG_SMB_FS is not set
-# CONFIG_NCP_FS is not set
-# CONFIG_ZISOFS_FS is not set
-# CONFIG_ZLIB_FS_INFLATE is not set
-
-#
-# Partition Types
-#
-# CONFIG_PARTITION_ADVANCED is not set
-CONFIG_MSDOS_PARTITION=y
-# CONFIG_SMB_NLS is not set
-# CONFIG_NLS is not set
-
-#
-# Sound
-#
-# CONFIG_SOUND is not set
-
-#
-# USB support
-#
-
-#
-# USB Controllers
-#
-
-#
-# USB Device Class drivers
-#
-
-#
-# USB Human Interface Devices (HID)
-#
-
-#
-# Input core support is needed for USB HID
-#
-
-#
-# USB Imaging devices
-#
-
-#
-# USB Multimedia devices
-#
-
-#
-# Video4Linux support is needed for USB Multimedia device support
-#
-
-#
-# USB Network adaptors
-#
-
-#
-# USB port drivers
-#
-
-#
-# USB Serial Converter support
-#
-
-#
-# USB Miscellaneous drivers
-#
-
-#
-# Kernel hacking
-#
-CONFIG_DEBUG_KERNEL=y
-# CONFIG_DEBUG_HIGHMEM is not set
-# CONFIG_DEBUG_SLAB is not set
-# CONFIG_DEBUG_IOVIRT is not set
-# CONFIG_MAGIC_SYSRQ is not set
-# CONFIG_DEBUG_SPINLOCK is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_KDB is not set
-CONFIG_KALLSYMS=y
-# CONFIG_FRAME_POINTER is not set
+++ /dev/null
-O_TARGET := blk.o
-obj-y := xl_block.o xl_block_test.o
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/******************************************************************************
- * xl_block.c
- *
- * Xenolinux virtual block-device driver.
- *
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-
-#include <linux/fs.h>
-#include <linux/hdreg.h>
-#include <linux/blkdev.h>
-#include <linux/major.h>
-
-#include <asm/hypervisor-ifs/block.h>
-#include <asm/hypervisor-ifs/hypervisor-if.h>
-#include <asm/io.h>
-#include <asm/uaccess.h>
-
-#define MAJOR_NR XLBLK_MAJOR /* force defns in blk.h, must precede include */
-static int xlblk_major = XLBLK_MAJOR;
-#include <linux/blk.h>
-
-/* Copied from linux/ide.h */
-typedef unsigned char byte;
-
-void xlblk_ide_register_disk(int, unsigned long);
-
-#define XLBLK_MAX 32 /* Maximum minor devices we support */
-#define XLBLK_MAJOR_NAME "xhd"
-#define IDE_PARTN_BITS 6 /* from ide.h::PARTN_BITS */
-#define IDE_PARTN_MASK ((1<<IDE_PARTN_BITS)-1) /* from ide.h::PARTN_MASK */
-static int xlblk_blk_size[XLBLK_MAX];
-static int xlblk_blksize_size[XLBLK_MAX];
-static int xlblk_read_ahead;
-static int xlblk_hardsect_size[XLBLK_MAX];
-static int xlblk_max_sectors[XLBLK_MAX];
-
-#define XLBLK_RESPONSE_IRQ _EVENT_BLK_RESP
-
-#define DEBUG_IRQ _EVENT_DEBUG
-
-#if 0
-#define DPRINTK(_f, _a...) printk ( KERN_ALERT _f , ## _a )
-#define DPRINTK_IOCTL(_f, _a...) printk ( KERN_ALERT _f , ## _a )
-#else
-#define DPRINTK(_f, _a...) ((void)0)
-#define DPRINTK_IOCTL(_f, _a...) ((void)0)
-#endif
-
-static blk_ring_t *blk_ring;
-static unsigned int resp_cons; /* Response consumer for comms ring. */
-static xen_disk_info_t xen_disk_info;
-
-int hypervisor_request(void * id,
- int operation,
- char * buffer,
- unsigned long block_number,
- unsigned short block_size,
- kdev_t device);
-
-
-/* ------------------------------------------------------------------------
- */
-
-static int xenolinux_block_open(struct inode *inode, struct file *filep)
-{
- DPRINTK("xenolinux_block_open\n");
- return 0;
-}
-
-static int xenolinux_block_release(struct inode *inode, struct file *filep)
-{
- DPRINTK("xenolinux_block_release\n");
- return 0;
-}
-
-static int xenolinux_block_ioctl(struct inode *inode, struct file *filep,
- unsigned command, unsigned long argument)
-{
- int minor_dev;
- struct hd_geometry *geo = (struct hd_geometry *)argument;
-
- DPRINTK("xenolinux_block_ioctl\n");
-
- /* check permissions */
- if (!capable(CAP_SYS_ADMIN)) return -EPERM;
- if (!inode) return -EINVAL;
- minor_dev = MINOR(inode->i_rdev);
- if (minor_dev >= XLBLK_MAX) return -ENODEV;
-
- DPRINTK_IOCTL("command: 0x%x, argument: 0x%lx, minor: 0x%x\n",
- command, (long) argument, minor_dev);
-
- switch (command)
- {
- case BLKGETSIZE:
- DPRINTK_IOCTL(" BLKGETSIZE: %x %lx\n", BLKGETSIZE,
- (long) xen_disk_info.disks[0].capacity);
- return put_user(xen_disk_info.disks[0].capacity,
- (unsigned long *) argument);
-
- case BLKRRPART:
- DPRINTK_IOCTL(" BLKRRPART: %x\n", BLKRRPART);
- break;
-
- case BLKSSZGET:
- DPRINTK_IOCTL(" BLKSSZGET: %x 0x%x\n", BLKSSZGET,
- xlblk_hardsect_size[minor_dev]);
- return xlblk_hardsect_size[minor_dev];
-
- case HDIO_GETGEO:
- DPRINTK_IOCTL(" HDIO_GETGEO: %x\n", HDIO_GETGEO);
- if (!argument) return -EINVAL;
- if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
- if (put_user(0xff, (byte *)&geo->heads)) return -EFAULT;
- if (put_user(0x3f, (byte *)&geo->sectors)) return -EFAULT;
- if (put_user(0x106, (unsigned short *)&geo->cylinders)) return -EFAULT;
- return 0;
-
- case HDIO_GETGEO_BIG:
- DPRINTK_IOCTL(" HDIO_GETGEO_BIG: %x\n", HDIO_GETGEO_BIG);
- if (!argument) return -EINVAL;
- if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
- if (put_user(0xff, (byte *)&geo->heads)) return -EFAULT;
- if (put_user(0x3f, (byte *)&geo->sectors)) return -EFAULT;
- if (put_user(0x106, (unsigned int *) &geo->cylinders)) return -EFAULT;
-
- return 0;
-
- default:
- DPRINTK_IOCTL(" eh? unknown ioctl\n");
- break;
- }
-
- return 0;
-}
-
-static int xenolinux_block_check(kdev_t dev)
-{
- DPRINTK("xenolinux_block_check\n");
- return 0;
-}
-
-static int xenolinux_block_revalidate(kdev_t dev)
-{
- DPRINTK("xenolinux_block_revalidate\n");
- return 0;
-}
-
-/*
- * hypervisor_request
- *
- * request block io
- *
- * id: for guest use only.
- * operation: XEN_BLOCK_READ, XEN_BLOCK_WRITE or XEN_BLOCK_PROBE
- * buffer: buffer to read/write into. this should be a
- * virtual address in the guest os.
- * block_number: block to read
- * block_size: size of each block
- * device: ide/hda is 768 or 0x300
- */
-int hypervisor_request(void * id,
- int operation,
- char * buffer,
- unsigned long block_number,
- unsigned short block_size,
- kdev_t device)
-{
- int position;
- void *buffer_ma;
- kdev_t phys_device = (kdev_t) 0;
- unsigned long sector_number = 0;
- struct gendisk *gd;
-
- /*
- * Bail if there's no room in the request communication ring. This may be
- * because we have a whole bunch of outstanding responses to process. No
- * matter, as the response handler will kick the request queue.
- */
- if ( BLK_RING_INC(blk_ring->req_prod) == resp_cons )
- return 1;
-
- buffer_ma = (void *)phys_to_machine(virt_to_phys(buffer));
-
- switch ( operation )
- {
- case XEN_BLOCK_PROBE:
- phys_device = (kdev_t) 0;
- sector_number = 0;
- break;
-
- case XEN_BLOCK_READ:
- case XEN_BLOCK_WRITE:
- if ( MAJOR(device) != XLBLK_MAJOR )
- panic("error: xl_block::hypervisor_request: "
- "unknown device [0x%x]\n", device);
- phys_device = MKDEV(IDE0_MAJOR, 0);
- /* Compute real buffer location on disk */
- sector_number = block_number;
- if ( (gd = (struct gendisk *)xen_disk_info.disks[0].gendisk) != NULL )
- sector_number += gd->part[MINOR(device)&IDE_PARTN_MASK].start_sect;
- break;
-
- default:
- panic("unknown op %d\n", operation);
- }
-
- /* Fill out a communications ring structure & trap to the hypervisor */
- position = blk_ring->req_prod;
- blk_ring->ring[position].req.id = id;
- blk_ring->ring[position].req.operation = operation;
- blk_ring->ring[position].req.buffer = buffer_ma;
- blk_ring->ring[position].req.block_number = block_number;
- blk_ring->ring[position].req.block_size = block_size;
- blk_ring->ring[position].req.device = phys_device;
- blk_ring->ring[position].req.sector_number = sector_number;
-
- blk_ring->req_prod = BLK_RING_INC(position);
-
- return 0;
-}
-
-
-/*
- * do_xlblk_request
- * read a block; request is in a request queue
- */
-static void do_xlblk_request (request_queue_t *rq)
-{
- struct request *req;
- struct buffer_head *bh;
- int rw, nsect, full, queued = 0;
-
- DPRINTK("xlblk.c::do_xlblk_request for '%s'\n", DEVICE_NAME);
-
- while ( !rq->plugged && !QUEUE_EMPTY )
- {
- if ( (req = CURRENT) == NULL ) goto out;
-
- DPRINTK("do_xlblk_request %p: cmd %i, sec %lx, (%li/%li) bh:%p\n",
- req, req->cmd, req->sector,
- req->current_nr_sectors, req->nr_sectors, req->bh);
-
- rw = req->cmd;
- if ( rw == READA ) rw = READ;
- if ((rw != READ) && (rw != WRITE))
- panic("XenoLinux Virtual Block Device: bad cmd: %d\n", rw);
-
- req->errors = 0;
-
- bh = req->bh;
- while ( bh != NULL )
- {
- full = hypervisor_request(
- bh, (rw == READ) ? XEN_BLOCK_READ : XEN_BLOCK_WRITE,
- bh->b_data, bh->b_rsector, bh->b_size, bh->b_dev);
-
- if ( full ) goto out;
-
- queued++;
-
- /* Dequeue the buffer head from the request. */
- nsect = bh->b_size >> 9;
- req->bh = bh->b_reqnext;
- bh->b_reqnext = NULL;
- bh = req->bh;
-
- if ( bh != NULL )
- {
- /* There's another buffer head to do. Update the request. */
- req->hard_sector += nsect;
- req->hard_nr_sectors -= nsect;
- req->sector = req->hard_sector;
- req->nr_sectors = req->hard_nr_sectors;
- req->current_nr_sectors = bh->b_size >> 9;
- req->buffer = bh->b_data;
- }
- else
- {
- /* That was the last buffer head. Finalise the request. */
- if ( end_that_request_first(req, 1, "XenBlk") ) BUG();
- blkdev_dequeue_request(req);
- end_that_request_last(req);
- }
- }
- }
-
- out:
- if ( queued != 0 ) HYPERVISOR_block_io_op();
-}
-
-
-static struct block_device_operations xenolinux_block_fops =
-{
- open: xenolinux_block_open,
- release: xenolinux_block_release,
- ioctl: xenolinux_block_ioctl,
- check_media_change: xenolinux_block_check,
- revalidate: xenolinux_block_revalidate,
-};
-
-static void xlblk_response_int(int irq, void *dev_id, struct pt_regs *ptregs)
-{
- int i;
- unsigned long flags;
- struct buffer_head *bh;
-
- spin_lock_irqsave(&io_request_lock, flags);
-
- for ( i = resp_cons;
- i != blk_ring->resp_prod;
- i = BLK_RING_INC(i) )
- {
- blk_ring_resp_entry_t *bret = &blk_ring->ring[i].resp;
- if ( (bh = bret->id) != NULL ) bh->b_end_io(bh, 1);
- }
-
- resp_cons = i;
-
- /* KAF: We can push work down at this point. We have the lock. */
- do_xlblk_request(BLK_DEFAULT_QUEUE(MAJOR_NR));
-
- spin_unlock_irqrestore(&io_request_lock, flags);
-}
-
-
-int __init xlblk_init(void)
-{
- int i, error, result;
-
- /* This mapping was created early at boot time. */
- blk_ring = (blk_ring_t *)fix_to_virt(FIX_BLKRING_BASE);
- blk_ring->req_prod = blk_ring->resp_prod = resp_cons = 0;
-
- error = request_irq(XLBLK_RESPONSE_IRQ, xlblk_response_int, 0,
- "xlblk-response", NULL);
- if (error) {
- printk(KERN_ALERT "Could not allocate receive interrupt\n");
- goto fail;
- }
-
- memset (&xen_disk_info, 0, sizeof(xen_disk_info));
- xen_disk_info.count = 0;
-
- if ( hypervisor_request(NULL, XEN_BLOCK_PROBE, (char *) &xen_disk_info,
- 0, 0, (kdev_t) 0) )
- BUG();
- HYPERVISOR_block_io_op();
- while ( blk_ring->resp_prod != 1 ) barrier();
- for ( i = 0; i < xen_disk_info.count; i++ )
- {
- printk (KERN_ALERT " %2d: type: %d, capacity: %ld\n",
- i, xen_disk_info.disks[i].type,
- xen_disk_info.disks[i].capacity);
- }
-
- SET_MODULE_OWNER(&xenolinux_block_fops);
- result = register_blkdev(xlblk_major, "block", &xenolinux_block_fops);
- if (result < 0) {
- printk (KERN_ALERT "xenolinux block: can't get major %d\n",
- xlblk_major);
- return result;
- }
-
- /* initialize global arrays in drivers/block/ll_rw_block.c */
- for (i = 0; i < XLBLK_MAX; i++) {
- xlblk_blk_size[i] = xen_disk_info.disks[0].capacity;
- xlblk_blksize_size[i] = 512;
- xlblk_hardsect_size[i] = 512;
- xlblk_max_sectors[i] = 128;
- }
- xlblk_read_ahead = 8;
-
- blk_size[xlblk_major] = xlblk_blk_size;
- blksize_size[xlblk_major] = xlblk_blksize_size;
- hardsect_size[xlblk_major] = xlblk_hardsect_size;
- read_ahead[xlblk_major] = xlblk_read_ahead;
- max_sectors[xlblk_major] = xlblk_max_sectors;
-
- blk_init_queue(BLK_DEFAULT_QUEUE(xlblk_major), do_xlblk_request);
-
- /*
- * Turn off barking 'headactive' mode. We dequeue buffer heads as
- * soon as we pass them down to Xen.
- */
- blk_queue_headactive(BLK_DEFAULT_QUEUE(xlblk_major), 0);
-
- xlblk_ide_register_disk(0, xen_disk_info.disks[0].capacity);
-
- printk(KERN_ALERT
- "XenoLinux Virtual Block Device Driver installed [device: %d]\n",
- xlblk_major);
- return 0;
-
- fail:
- return error;
-}
-
-void xlblk_ide_register_disk(int idx, unsigned long capacity)
-{
- int units;
- int minors;
- struct gendisk *gd;
-
- /* plagarized from ide-probe.c::init_gendisk */
-
- units = 2; /* from ide.h::MAX_DRIVES */
-
- minors = units * (1<<IDE_PARTN_BITS);
- gd = kmalloc (sizeof(struct gendisk), GFP_KERNEL);
- gd->sizes = kmalloc (minors * sizeof(int), GFP_KERNEL);
- gd->part = kmalloc (minors * sizeof(struct hd_struct), GFP_KERNEL);
- memset(gd->part, 0, minors * sizeof(struct hd_struct));
-
- gd->major = xlblk_major;
- gd->major_name = XLBLK_MAJOR_NAME;
- gd->minor_shift = IDE_PARTN_BITS;
- gd->max_p = 1<<IDE_PARTN_BITS;
- gd->nr_real = units;
- gd->real_devices = NULL;
- gd->next = NULL;
- gd->fops = &xenolinux_block_fops;
- gd->de_arr = kmalloc (sizeof *gd->de_arr * units, GFP_KERNEL);
- gd->flags = kmalloc (sizeof *gd->flags * units, GFP_KERNEL);
-
- if (gd->de_arr)
- memset (gd->de_arr, 0, sizeof *gd->de_arr * units);
-
- if (gd->flags)
- memset (gd->flags, 0, sizeof *gd->flags * units);
-
- add_gendisk(gd);
-
- xen_disk_info.disks[idx].gendisk = gd;
-
- /* default disk size is just a big number. in the future, we
- need a message to probe the devices to determine the actual size */
- register_disk(gd, MKDEV(xlblk_major, 0), 1<<IDE_PARTN_BITS,
- &xenolinux_block_fops, capacity);
-
- return;
-}
-
-
-
-static void __exit xlblk_cleanup(void)
-{
- /* CHANGE FOR MULTIQUEUE */
- blk_cleanup_queue(BLK_DEFAULT_QUEUE(xlblk_major));
-
- /* clean up global arrays */
- read_ahead[xlblk_major] = 0;
-
- if (blk_size[xlblk_major])
- kfree(blk_size[xlblk_major]);
- blk_size[xlblk_major] = NULL;
-
- if (blksize_size[xlblk_major])
- kfree(blksize_size[xlblk_major]);
- blksize_size[xlblk_major] = NULL;
-
- if (hardsect_size[xlblk_major])
- kfree(hardsect_size[xlblk_major]);
- hardsect_size[xlblk_major] = NULL;
-
- /* XXX: free each gendisk */
- if (unregister_blkdev(xlblk_major, "block"))
- printk(KERN_ALERT
- "XenoLinux Virtual Block Device Driver uninstalled w/ errs\n");
- else
- printk(KERN_ALERT
- "XenoLinux Virtual Block Device Driver uninstalled\n");
-
- return;
-}
-
-
-#ifdef MODULE
-module_init(xlblk_init);
-module_exit(xlblk_cleanup);
-#endif
+++ /dev/null
-/******************************************************************************
- * xenolinux_block_test.c
- *
- */
-#define EXPORT_SYMTAB
-
-#include <linux/config.h>
-#include <linux/module.h>
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/sched.h>
-#include <asm/uaccess.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/delay.h>
-
-#include <asm/hypervisor-ifs/block.h>
-#include <asm/hypervisor-ifs/hypervisor-if.h>
-
-/******************************************************************/
-
-static struct proc_dir_entry *bdt;
-static blk_ring_req_entry_t meta;
-static char * data;
-
-static int proc_read_bdt(char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- switch (meta.operation)
- {
- case XEN_BLOCK_READ :
- case XEN_BLOCK_WRITE :
- {
- return proc_dump_block(page, start, off, count, eof, data);
- }
- case XEN_BLOCK_DEBUG :
- {
- return proc_dump_debug(page, start, off, count, eof, data);
- }
- default :
- {
- printk(KERN_ALERT
- "block device test error: unknown operation [%c]\n",
- meta.operation);
- return -EINVAL;
- }
- }
-}
-
-int proc_dump_debug(char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- char header[100];
- char dump[1024];
-
- sprintf (header, "Block Device Test: Debug Dump\n\n");
-
- sprintf (dump, "%s\n", meta.buffer);
-
- if (data)
- {
- kfree(data);
- }
-
- strncpy (page, dump, count);
- return strlen(page);
-}
-
-int proc_dump_block(char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- char header[100];
- char dump[1024];
- char temp[100];
- int loop;
-
- sprintf (header, "Block Device Test\n\n%s blk num: %ld 0x%lx; size: %d 0x%x; device: 0x%x\n",
- meta.operation == XEN_BLOCK_WRITE ? "write" : "read",
- meta.block_number, meta.block_number,
- meta.block_size, meta.block_size,
- meta.device);
-
- sprintf (dump, "%s", header);
-
- if (meta.buffer)
- {
- for (loop = 0; loop < 100; loop++)
- {
- int i = meta.buffer[loop];
-
- if (loop % 8 == 0)
- {
- sprintf (temp, "[%2d] ", loop);
- strcat(dump, temp);
- }
- else if (loop % 2 == 0)
- {
- strcat(dump, " ");
- }
-
- sprintf (temp, " 0x%02x", i & 255);
- strcat(dump, temp);
- if ((loop + 1) % 8 == 0)
- {
- strcat(dump, "\n");
- }
- }
- strcat(dump, "\n\n");
- }
-
- if (data)
- {
- kfree(data);
- }
-
- strncpy (page, dump, count);
- return strlen(page);
-}
-
-int proc_write_bdt(struct file *file, const char *buffer,
- unsigned long count, void *data)
-{
- char *local = kmalloc((count + 1) * sizeof(char), GFP_KERNEL);
- char opcode;
- int block_number = 0;
- int block_size = 0;
- int device = 0;
-
- if (copy_from_user(local, buffer, count))
- {
- return -EFAULT;
- }
- local[count] = '\0';
-
- sscanf(local, "%c %i %i %i",
- &opcode, &block_number, &block_size, &device);
-
- if (opcode == 'r' || opcode == 'R')
- {
- meta.operation = XEN_BLOCK_READ;
- }
- else if (opcode == 'w' || opcode == 'W')
- {
- meta.operation = XEN_BLOCK_WRITE;
- }
- else if (opcode == 'd' || opcode == 'D')
- {
- meta.operation = XEN_BLOCK_DEBUG;
- block_size = 10000;
- }
- else
- {
- printk(KERN_ALERT
- "block device test error: unknown opcode [%c]\n", opcode);
- return -EINVAL;
- }
-
- if (data)
- {
- kfree(data);
- }
- data = kmalloc(block_size * sizeof(char), GFP_KERNEL);
- if (data == NULL)
- {
- kfree(local);
- return -ENOMEM;
- }
-
- meta.block_number = block_number;
- meta.block_size = block_size;
- meta.device = device;
- meta.buffer = data;
-
- /* submit request */
- hypervisor_request(0, meta.operation, meta.buffer,
- meta.block_number, meta.block_size,
- meta.device);
- HYPERVISOR_block_io_op();
- mdelay(1000); /* should wait for a proper acknowledgement/response. */
-
- kfree(local);
- return count;
-}
-
-
-static int __init init_module(void)
-{
- int return_value = 0;
-
- /* create proc entry */
- bdt = create_proc_entry("bdt", 0644, NULL);
- if (bdt == NULL)
- {
- return_value = -ENOMEM;
- goto error;
- }
- bdt->data = NULL;
- bdt->read_proc = proc_read_bdt;
- bdt->write_proc = proc_write_bdt;
- bdt->owner = THIS_MODULE;
-
- memset(&meta, 0, sizeof(meta));
-
- /* success */
- printk(KERN_ALERT "XenoLinux Block Device Test installed\n");
- return 0;
-
- error:
- return return_value;
-}
-
-static void __exit cleanup_module(void)
-{
- if (data)
- {
- kfree(data);
- }
- printk(KERN_ALERT "XenoLinux Block Device Test uninstalled\n");
-}
-
-module_init(init_module);
-module_exit(cleanup_module);
+++ /dev/null
-O_TARGET := con.o
-obj-y := console.o
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/******************************************************************************
- * console.c
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/interrupt.h>
-#include <linux/tty.h>
-#include <linux/tty_flip.h>
-#include <linux/serial.h>
-#include <linux/major.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/console.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/uaccess.h>
-#include <asm/hypervisor.h>
-
-/******************** Kernel console driver ********************************/
-
-static void kconsole_write(struct console *co, const char *s, unsigned count)
-{
-#define STRLEN 256
- static char str[STRLEN];
- static int pos = 0;
- int len;
-
- /* We buffer output until we see a newline, or until the buffer is full. */
- while ( count != 0 )
- {
- len = ((STRLEN - pos) > count) ? count : STRLEN - pos;
- memcpy(str + pos, s, len);
- pos += len;
- s += len;
- count -= len;
- if ( (pos == STRLEN) || (str[pos-1] == '\n') )
- {
- (void)HYPERVISOR_console_write(str, pos);
- pos = 0;
- }
- }
-}
-
-static kdev_t kconsole_device(struct console *c)
-{
- /*
- * This is the magic that binds our "struct console" to our
- * "tty_struct", defined below.
- */
- return MKDEV(TTY_MAJOR, 0);
-}
-
-static struct console kconsole_info = {
- name: "xenocon",
- write: kconsole_write,
- device: kconsole_device,
- flags: CON_PRINTBUFFER,
- index: -1,
-};
-
-void xeno_console_init(void)
-{
- register_console(&kconsole_info);
-}
-
-
-/******************** Initial /dev/console *********************************/
-
-
-static struct tty_driver console_driver;
-static int console_refcount;
-static struct tty_struct *console_table[1];
-static struct termios *console_termios[1];
-static struct termios *console_termios_locked[1];
-
-static int console_write_room(struct tty_struct *tty)
-{
- return INT_MAX;
-}
-
-static int console_chars_in_buffer(struct tty_struct *tty)
-{
- return 0;
-}
-
-static inline int console_xmit(int ch)
-{
- char _ch = ch;
- kconsole_write(NULL, &_ch, 1);
- return 1;
-}
-
-static int console_write(struct tty_struct *tty, int from_user,
- const u_char * buf, int count)
-{
- int i;
-
- if ( from_user && verify_area(VERIFY_READ, buf, count) )
- {
- return -EINVAL;
- }
-
- for ( i = 0; i < count; i++ )
- {
- char ch;
- if ( from_user )
- {
- __get_user(ch, buf + i);
- }
- else
- {
- ch = buf[i];
- }
- console_xmit(ch);
- }
- return i;
-}
-
-static void console_put_char(struct tty_struct *tty, u_char ch)
-{
- console_xmit(ch);
-}
-
-static int console_open(struct tty_struct *tty, struct file *filp)
-{
- int line;
-
- MOD_INC_USE_COUNT;
- line = MINOR(tty->device) - tty->driver.minor_start;
- if ( line )
- {
- MOD_DEC_USE_COUNT;
- return -ENODEV;
- }
-
- tty->driver_data = NULL;
-
- return 0;
-}
-
-static void console_close(struct tty_struct *tty, struct file *filp)
-{
- MOD_DEC_USE_COUNT;
-}
-
-static int __init console_ini(void)
-{
- memset(&console_driver, 0, sizeof(struct tty_driver));
- console_driver.magic = TTY_DRIVER_MAGIC;
- console_driver.driver_name = "xeno_console";
- console_driver.name = "console";
- console_driver.major = TTY_MAJOR;
- console_driver.minor_start = 0;
- console_driver.num = 1;
- console_driver.type = TTY_DRIVER_TYPE_SERIAL;
- console_driver.subtype = SERIAL_TYPE_NORMAL;
- console_driver.init_termios = tty_std_termios;
- console_driver.flags = TTY_DRIVER_REAL_RAW;
- console_driver.refcount = &console_refcount;
- console_driver.table = console_table;
- console_driver.termios = console_termios;
- console_driver.termios_locked = console_termios_locked;
- /* Functions */
- console_driver.open = console_open;
- console_driver.close = console_close;
- console_driver.write = console_write;
- console_driver.write_room = console_write_room;
- console_driver.put_char = console_put_char;
- console_driver.chars_in_buffer = console_chars_in_buffer;
-
- if ( tty_register_driver(&console_driver) )
- {
- printk(KERN_ERR "Couldn't register Xeno console driver\n");
- }
- else
- {
- printk("Xeno console successfully installed\n");
- }
-
- return 0;
-}
-
-static void __exit console_fin(void)
-{
- int ret;
-
- ret = tty_unregister_driver(&console_driver);
- if ( ret != 0 )
- {
- printk(KERN_ERR "Unable to unregister Xeno console driver: %d\n", ret);
- }
-}
-
-module_init(console_ini);
-module_exit(console_fin);
-
+++ /dev/null
-O_TARGET := dom0.o
-obj-y := dom0_memory.o dom0_core.o vfr.o
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/*
- * domain 0 block driver interface
- *
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-
-static int __init init_module(void)
-{
- request_module("xl_block");
- printk("Successfully installed domain 0 block interface\n");
-
-
- return 0;
-}
-
-static void __exit cleanup_module(void)
-{
- printk("Successfully de-installed domain-0 block interface\n");
- return 0;
-}
-
-module_init(init_module);
-module_exit(cleanup_module);
+++ /dev/null
-/******************************************************************************
- * dom0_core.c
- *
- * Interface to privileged domain-0 commands.
- *
- * Copyright (c) 2002, K A Fraser, B Dragovic
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/proc_fs.h>
-
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/swap.h>
-#include <linux/smp_lock.h>
-#include <linux/swapctl.h>
-#include <linux/iobuf.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/tlb.h>
-
-#include "dom0_ops.h"
-
-/* Private proc-file data structures. */
-typedef struct proc_data {
- unsigned int domain;
- unsigned long map_size;
-} dom_procdata_t;
-
-typedef struct proc_mem_data {
- unsigned long pfn;
- int tot_pages;
-} proc_memdata_t;
-
-#define XENO_BASE "xeno"
-#define DOM0_CMD_INTF "dom0_cmd"
-#define DOM0_NEWDOM "new_dom_data"
-
-#define MAX_LEN 16
-#define DOM_DIR "dom"
-#define DOM_MEM "mem"
-#define DOM_VIF "vif"
-
-#define MAP_DISCONT 1
-
-static struct proc_dir_entry *xeno_base;
-static struct proc_dir_entry *dom0_cmd_intf;
-static struct proc_dir_entry *proc_ft;
-
-unsigned long direct_mmap(unsigned long, unsigned long, pgprot_t, int, int);
-int direct_unmap(unsigned long, unsigned long);
-int direct_disc_unmap(unsigned long, unsigned long, int);
-
-static unsigned char readbuf[1204];
-
-static int cmd_read_proc(char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- strcpy(page, readbuf);
- *readbuf = '\0';
- *eof = 1;
- *start = page;
- return strlen(page);
-}
-
-static ssize_t dom_vif_read(struct file * file, char * buff, size_t size, loff_t * off)
-{
- char hyp_buf[128]; // Hypervisor is going to write its reply here.
- network_op_t op;
- static int finished = 0;
-
- // This seems to be the only way to make the OS stop making read requests
- // to the file. When we use the fileoperations version of read, offset
- // seems to be ignored altogether.
-
- if (finished)
- {
- finished = 0;
- return 0;
- }
-
- op.cmd = NETWORK_OP_VIFQUERY;
- op.u.vif_query.domain = (unsigned int) ((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
- op.u.vif_query.buf = hyp_buf;
-
- strcpy(hyp_buf, "Error getting domain's vif list from hypervisor.\n"); // This will be replaced if everything works.
-
- (void)HYPERVISOR_network_op(&op);
-
- if (*off >= (strlen(hyp_buf)+1)) return 0;
-
- copy_to_user(buff, hyp_buf, strlen(hyp_buf));
-
- finished = 1;
-
- return strlen(hyp_buf)+1;
-}
-
-struct file_operations dom_vif_ops = {
- read: dom_vif_read
-};
-
-
-static void create_proc_dom_entries(int dom)
-{
- struct proc_dir_entry * dir;
- dom_procdata_t * dom_data;
- char dir_name[MAX_LEN];
- struct proc_dir_entry * file;
-
- snprintf(dir_name, MAX_LEN, "%s%d", DOM_DIR, dom);
-
- dom_data = (dom_procdata_t *)kmalloc(sizeof(dom_procdata_t), GFP_KERNEL);
- dom_data->domain = dom;
-
- dir = proc_mkdir(dir_name, xeno_base);
- dir->data = dom_data;
-
- file = create_proc_entry(DOM_VIF, 0600, dir);
- if (file != NULL)
- {
- file->owner = THIS_MODULE;
- file->nlink = 1;
- file->proc_fops = &dom_vif_ops;
- file->data = (void *) dom;
- }
-}
-
-static ssize_t dom_mem_write(struct file * file, const char * buff,
- size_t size , loff_t * off)
-{
- dom_mem_t mem_data;
-
- copy_from_user(&mem_data, (dom_mem_t *)buff, sizeof(dom_mem_t));
-
- if(direct_disc_unmap(mem_data.vaddr, mem_data.start_pfn,
- mem_data.tot_pages) == 0){
- return sizeof(sizeof(dom_mem_t));
- } else {
- return -1;
- }
-}
-
-static ssize_t dom_mem_read(struct file * file, char * buff, size_t size, loff_t * off)
-{
- unsigned long addr;
- pgprot_t prot;
-
- proc_memdata_t * mem_data = (proc_memdata_t *)((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
-
- prot = PAGE_SHARED;
-
- /* remap the range using xen specific routines */
-
- addr = direct_mmap(mem_data->pfn << PAGE_SHIFT, mem_data->tot_pages << PAGE_SHIFT, prot, MAP_DISCONT, mem_data->tot_pages);
-
- copy_to_user((unsigned long *)buff, &addr, sizeof(addr));
-
- return sizeof(addr);
-}
-
-struct file_operations dom_mem_ops = {
- read: dom_mem_read,
- write: dom_mem_write,
-};
-
-static int dom_map_mem(unsigned int dom, unsigned long pfn, int tot_pages)
-{
- int ret = -ENOENT;
- struct proc_dir_entry * pd = xeno_base->subdir;
- struct proc_dir_entry * file;
- proc_memdata_t * memdata;
-
- while(pd != NULL){
-
- if((pd->mode & S_IFDIR) && ((dom_procdata_t *)pd->data)->domain == dom){
-
- /* check if there is already an entry for mem and if so
- * remove it.
- */
- remove_proc_entry(DOM_MEM, pd);
-
- /* create new entry with parameters describing what to do
- * when it is mmaped.
- */
- file = create_proc_entry(DOM_MEM, 0600, pd);
- if(file != NULL)
- {
- file->owner = THIS_MODULE;
- file->nlink = 1;
- file->proc_fops = &dom_mem_ops;
-
- memdata = (proc_memdata_t *)kmalloc(sizeof(proc_memdata_t), GFP_KERNEL);
- memdata->pfn = pfn;
- memdata->tot_pages = tot_pages;
- file->data = memdata;
-
- ret = 0;
- break;
- }
-
- ret = -EAGAIN;
- break;
- }
- pd = pd->next;
- }
-
- return ret;
-}
-
-/* function used to retrieve data associated with new domain */
-static ssize_t dom_data_read(struct file * file, char * buff, size_t size, loff_t * off)
-{
- dom0_newdomain_t * dom_data = (dom0_newdomain_t *)
- ((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
-
- copy_to_user((dom0_newdomain_t *)buff, dom_data, sizeof(dom0_newdomain_t));
-
- remove_proc_entry(DOM0_NEWDOM, xeno_base);
-
- kfree(dom_data);
-
- return sizeof(dom0_newdomain_t);
-}
-
-struct file_operations newdom_data_fops = {
- read: dom_data_read,
-};
-
-static int cmd_write_proc(struct file *file, const char *buffer,
- u_long count, void *data)
-{
- dom0_op_t op;
- int ret = 0;
- struct proc_dir_entry * new_dom_id;
- dom0_newdomain_t * params;
- int i;
- unsigned long p;
-
- copy_from_user(&op, buffer, sizeof(dom0_op_t));
-
- /* do some sanity checks */
- if(op.cmd > MAX_CMD){
- ret = -ENOSYS;
- goto out;
- }
-
- if ( op.cmd == MAP_DOM_MEM )
- {
- ret = dom_map_mem(op.u.dommem.domain, op.u.dommem.start_pfn,
- op.u.dommem.tot_pages);
- }
- else if ( op.cmd == DO_PGUPDATES )
- {
- ret = HYPERVISOR_pt_update(op.u.pgupdate.pgt_update_arr,
- op.u.pgupdate.num_pgt_updates);
- }
- else
- {
- ret = HYPERVISOR_dom0_op(&op);
-
- /* if new domain created, create proc entries */
- if(op.cmd == DOM0_NEWDOMAIN){
- create_proc_dom_entries(ret);
-
- params = (dom0_newdomain_t *)kmalloc(sizeof(dom0_newdomain_t),
- GFP_KERNEL);
- params->memory_kb = op.u.newdomain.memory_kb;
- params->pg_head = op.u.newdomain.pg_head;
- params->num_vifs = op.u.newdomain.num_vifs;
- params->domain = op.u.newdomain.domain;
-
- /* now notify user space of the new domain's id */
- new_dom_id = create_proc_entry(DOM0_NEWDOM, 0600, xeno_base);
- if ( new_dom_id != NULL )
- {
- new_dom_id->owner = THIS_MODULE;
- new_dom_id->nlink = 1;
- new_dom_id->proc_fops = &newdom_data_fops;
- new_dom_id->data = (void *)params;
- }
-
- }
-
- }
-
-out:
- return ret;
-
-}
-
-static int __init init_module(void)
-{
- /* xeno proc root setup */
- xeno_base = proc_mkdir(XENO_BASE, &proc_root);
-
- /* xeno control interface */
- *readbuf = '\0';
- dom0_cmd_intf = create_proc_entry (DOM0_CMD_INTF, 0600, xeno_base);
- if ( dom0_cmd_intf != NULL )
- {
- dom0_cmd_intf->owner = THIS_MODULE;
- dom0_cmd_intf->nlink = 1;
- dom0_cmd_intf->read_proc = cmd_read_proc;
- dom0_cmd_intf->write_proc = cmd_write_proc;
- }
-
- /* set up /proc entries for dom 0 */
- create_proc_dom_entries(0);
-
- return 0;
-}
-
-
-static void __exit cleanup_module(void)
-{
- if ( dom0_cmd_intf == NULL ) return;
- remove_proc_entry("dom0", &proc_root);
- dom0_cmd_intf = NULL;
-}
-
-
-module_init(init_module);
-module_exit(cleanup_module);
+++ /dev/null
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/swap.h>
-#include <linux/smp_lock.h>
-#include <linux/swapctl.h>
-#include <linux/iobuf.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-#include <linux/list.h>
-
-#include <asm/pgalloc.h>
-#include <asm/uaccess.h>
-#include <asm/tlb.h>
-#include <asm/mmu.h>
-
-#include "dom0_ops.h"
-
-#define MAP_CONT 0
-#define MAP_DISCONT 1
-
-extern struct list_head * find_direct(struct list_head *, unsigned long);
-
-/*
- * bd240: functions below perform direct mapping to the real physical pages
- * needed for mapping various hypervisor specific structures needed in dom0
- * userspace by various management applications such as domain builder etc.
- */
-
-#define direct_set_pte(pteptr, pteval) queue_l1_entry_update(__pa(pteptr)|PGREQ_UNCHECKED_UPDATE, (pteval).pte_low)
-
-#define direct_pte_clear(pteptr) queue_l1_entry_update(__pa(pteptr)|PGREQ_UNCHECKED_UPDATE, 0)
-
-#define __direct_pte(x) ((pte_t) { (x) } )
-#define __direct_mk_pte(page_nr,pgprot) __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
-#define direct_mk_pte_phys(physpage, pgprot) __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot)
-
-static inline void forget_pte(pte_t page)
-{
- if (!pte_none(page)) {
- printk("forget_pte: old mapping existed!\n");
- BUG();
- }
-}
-
-static inline void direct_remappte_range(pte_t * pte, unsigned long address, unsigned long size,
- unsigned long phys_addr, pgprot_t prot)
-{
- unsigned long end;
-
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- pte_t oldpage;
- oldpage = ptep_get_and_clear(pte);
-
- direct_set_pte(pte, direct_mk_pte_phys(phys_addr, prot));
-
- forget_pte(oldpage);
- address += PAGE_SIZE;
- phys_addr += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
-
-}
-
-static inline int direct_remappmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long phys_addr, pgprot_t prot)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- phys_addr -= address;
- do {
- pte_t * pte = pte_alloc(mm, pmd, address);
- if (!pte)
- return -ENOMEM;
- direct_remappte_range(pte, address, end - address, address + phys_addr, prot);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
- return 0;
-}
-
-/* Note: this is only safe if the mm semaphore is held when called. */
-int direct_remap_page_range(unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
- struct mm_struct *mm = current->mm;
-
- phys_addr -= from;
- dir = pgd_offset(mm, from);
- flush_cache_range(mm, beg, end);
- if (from >= end)
- BUG();
-
- spin_lock(&mm->page_table_lock);
- do {
- pmd_t *pmd = pmd_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = direct_remappmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
- if (error)
- break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (from && (from < end));
- spin_unlock(&mm->page_table_lock);
- flush_tlb_range(mm, beg, end);
- return error;
-}
-
-/*
- * used for remapping discontiguous bits of domain's memory, pages to map are
- * found from frame table beginning at the given first_pg index
- */
-int direct_remap_disc_page_range(unsigned long from,
- unsigned long first_pg, int tot_pages, pgprot_t prot)
-{
- dom0_op_t dom0_op;
- unsigned long *pfns = get_free_page(GFP_KERNEL);
- unsigned long start = from;
- int pages, i;
-
- while ( tot_pages != 0 )
- {
- dom0_op.cmd = DOM0_GETMEMLIST;
- dom0_op.u.getmemlist.start_pfn = first_pg;
- pages = 1023;
- dom0_op.u.getmemlist.num_pfns = 1024;
- if ( tot_pages < 1024 )
- dom0_op.u.getmemlist.num_pfns = pages = tot_pages;
- dom0_op.u.getmemlist.buffer = pfns;
- (void)HYPERVISOR_dom0_op(&dom0_op);
- first_pg = pfns[1023];
-
- for ( i = 0; i < pages; i++ )
- {
- if(direct_remap_page_range(start, pfns[i] << PAGE_SHIFT,
- PAGE_SIZE, prot))
- goto out;
- start += PAGE_SIZE;
- tot_pages--;
- }
- }
-
-out:
- free_page(pfns);
- return tot_pages;
-}
-
-/* below functions replace standard sys_mmap and sys_munmap which are absolutely useless
- * for direct memory mapping. direct_zap* functions are minor ammendments to the
- * original versions in mm/memory.c. the changes are to enable unmapping of real physical
- * addresses.
- */
-
-unsigned long direct_mmap(unsigned long phys_addr, unsigned long size,
- pgprot_t prot, int flag, int tot_pages)
-{
- direct_mmap_node_t * dmmap;
- struct list_head * entry;
- unsigned long addr;
- int ret = 0;
-
- if(!capable(CAP_SYS_ADMIN)){
- ret = -EPERM;
- goto out;
- }
-
- /* get unmapped area invokes xen specific arch_get_unmapped_area */
- addr = get_unmapped_area(NULL, 0, size, 0, 0);
- if(addr & ~PAGE_MASK){
- ret = -ENOMEM;
- goto out;
- }
-
- /* add node on the list of directly mapped areas, make sure the
- * list remains sorted.
- */
- dmmap = (direct_mmap_node_t *)kmalloc(sizeof(direct_mmap_node_t), GFP_KERNEL);
- dmmap->vm_start = addr;
- dmmap->vm_end = addr + size;
- entry = find_direct(¤t->mm->context.direct_list, addr);
- if(entry != ¤t->mm->context.direct_list){
- list_add_tail(&dmmap->list, entry);
- } else {
- list_add_tail(&dmmap->list, ¤t->mm->context.direct_list);
- }
-
- /* and perform the mapping */
- if(flag == MAP_DISCONT){
- ret = direct_remap_disc_page_range(addr, phys_addr >> PAGE_SHIFT,
- tot_pages, prot);
- } else {
- ret = direct_remap_page_range(addr, phys_addr, size, prot);
- }
-
- if(ret == 0)
- ret = addr;
-
-out:
- return ret;
-}
-
-/* most of the checks, refcnt updates, cache stuff have been thrown out as they are not
- * needed
- */
-static inline int direct_zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address,
- unsigned long size)
-{
- unsigned long offset;
- pte_t * ptep;
- int freed = 0;
-
- if (pmd_none(*pmd))
- return 0;
- if (pmd_bad(*pmd)) {
- pmd_ERROR(*pmd);
- pmd_clear(pmd);
- return 0;
- }
- ptep = pte_offset(pmd, address);
- offset = address & ~PMD_MASK;
- if (offset + size > PMD_SIZE)
- size = PMD_SIZE - offset;
- size &= PAGE_MASK;
- for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
- pte_t pte = *ptep;
- if (pte_none(pte))
- continue;
- freed ++;
- direct_pte_clear(ptep);
- }
-
- return freed;
-}
-
-static inline int direct_zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir,
- unsigned long address, unsigned long size)
-{
- pmd_t * pmd;
- unsigned long end;
- int freed;
-
- if (pgd_none(*dir))
- return 0;
- if (pgd_bad(*dir)) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
- return 0;
- }
- pmd = pmd_offset(dir, address);
- end = address + size;
- if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
- end = ((address + PGDIR_SIZE) & PGDIR_MASK);
- freed = 0;
- do {
- freed += direct_zap_pte_range(tlb, pmd, address, end - address);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address < end);
- return freed;
-}
-
-/*
- * remove user pages in a given range.
- */
-void direct_zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
-{
- mmu_gather_t *tlb;
- pgd_t * dir;
- unsigned long start = address, end = address + size;
- int freed = 0;
-
- dir = pgd_offset(mm, address);
-
- /*
- * This is a long-lived spinlock. That's fine.
- * There's no contention, because the page table
- * lock only protects against kswapd anyway, and
- * even if kswapd happened to be looking at this
- * process we _want_ it to get stuck.
- */
- if (address >= end)
- BUG();
- spin_lock(&mm->page_table_lock);
- flush_cache_range(mm, address, end);
- tlb = tlb_gather_mmu(mm);
-
- do {
- freed += direct_zap_pmd_range(tlb, dir, address, end - address);
- address = (address + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (address && (address < end));
-
- /* this will flush any remaining tlb entries */
- tlb_finish_mmu(tlb, start, end);
-
- /* decrementing rss removed */
-
- spin_unlock(&mm->page_table_lock);
-}
-
-int direct_unmap(unsigned long addr, unsigned long size)
-{
- direct_mmap_node_t * node;
- struct list_head * curr;
- struct list_head * direct_list = ¤t->mm->context.direct_list;
-
- curr = direct_list->next;
- while(curr != direct_list){
- node = list_entry(curr, direct_mmap_node_t, list);
- if(node->vm_start == addr)
- break;
- curr = curr->next;
- }
-
- if(curr == direct_list)
- return -1;
-
- list_del(&node->list);
- kfree(node);
-
- direct_zap_page_range(current->mm, addr, size);
-
- return 0;
-}
-
-int direct_disc_unmap(unsigned long from, unsigned long first_pg, int tot_pages)
-{
- int count = 0;
- direct_mmap_node_t * node;
- struct list_head * curr;
- struct list_head * direct_list = ¤t->mm->context.direct_list;
-
- curr = direct_list->next;
- while(curr != direct_list){
- node = list_entry(curr, direct_mmap_node_t, list);
-
- if(node->vm_start == from)
- break;
- curr = curr->next;
- }
-
- if(curr == direct_list)
- return -1;
-
- list_del(&node->list);
- kfree(node);
-
- while(count < tot_pages){
- direct_zap_page_range(current->mm, from, PAGE_SIZE);
- from += PAGE_SIZE;
- count++;
- }
-
- return 0;
-}
+++ /dev/null
-/******************************************************************************
- * dom0_ops.h
- *
- * Process command requests from domain-0 guest OS.
- *
- * Copyright (c) 2002, K A Fraser, B Dragovic
- */
-
-#define DOM0_NEWDOMAIN 0
-#define DOM0_KILLDOMAIN 1
-#define DOM0_GETMEMLIST 2
-#define DOM0_STARTDOM 4
-#define MAP_DOM_MEM 6 /* Not passed down to Xen */
-#define DO_PGUPDATES 7 /* Not passed down to Xen */
-#define MAX_CMD 8
-
-#define MAX_CMD_LEN 256
-
-typedef struct dom0_newdomain_st
-{
- unsigned int domain;
- unsigned int memory_kb;
- unsigned int num_vifs; // temporary
- unsigned long pg_head; // return parameter
-} dom0_newdomain_t;
-
-typedef struct dom0_killdomain_st
-{
- unsigned int domain;
-} dom0_killdomain_t;
-
-typedef struct dom0_getmemlist_st
-{
- unsigned long start_pfn;
- unsigned long num_pfns;
- void *buffer;
-} dom0_getmemlist_t;
-
-/* This is entirely processed by XenoLinux */
-typedef struct dom_mem
-{
- unsigned int domain;
- unsigned long vaddr;
- unsigned long start_pfn;
- int tot_pages;
-} dom_mem_t;
-
-/* This is entirely processed by XenoLinux */
-typedef struct dom_pgupdate
-{
- unsigned long pgt_update_arr;
- unsigned long num_pgt_updates;
-} dom_pgupdate_t;
-
-typedef struct domain_launch
-{
- unsigned int domain;
- unsigned long l2_pgt_addr;
- unsigned long virt_load_addr;
- unsigned long virt_shinfo_addr;
- unsigned long virt_startinfo_addr;
- unsigned int num_vifs;
- char cmd_line[MAX_CMD_LEN];
-} dom_meminfo_t;
-
-typedef struct dom0_op_st
-{
- unsigned long cmd;
- union
- {
- dom0_newdomain_t newdomain;
- dom0_killdomain_t killdomain;
- dom0_getmemlist_t getmemlist;
- dom_mem_t dommem;
- dom_pgupdate_t pgupdate;
- dom_meminfo_t meminfo;
- }
- u;
-} dom0_op_t;
-
+++ /dev/null
-/******************************************************************************
- * vfr.c
- *
- * Interface to the virtual firewall/router.
- *
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/proc_fs.h>
-
-#include <asm/hypervisor-ifs/network.h>
-
-static struct proc_dir_entry *proc_vfr;
-
-static unsigned char readbuf[1024];
-
-/* Helpers, implemented at the bottom. */
-u32 getipaddr(const char *buff, unsigned int len);
-u16 antous(const char *buff, int len);
-int anton(const char *buff, int len);
-
-static int vfr_read_proc(char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- strcpy(page, readbuf);
- *readbuf = '\0';
- *eof = 1;
- *start = page;
- return strlen(page);
-}
-
-/* The format for the vfr interface is as follows:
- *
- * COMMAND <field>=<val> [<field>=<val> [...]]
- *
- * where:
- *
- * COMMAND = { ACCEPT | COUNT }
- *
- * field=val pairs are as follows:
- *
- * field = { srcaddr | dstaddr }
- * val is a dot seperated, numeric IP address.
- *
- * field = { srcport | dstport }
- * val is a (16-bit) unsigned int
- *
- * field = { proto }
- * val = { IP | TCP | UDP | ARP }
- *
- */
-
-#define isspace(_x) ( ((_x)==' ') || ((_x)=='\t') || ((_x)=='\v') || \
- ((_x)=='\f') || ((_x)=='\r') || ((_x)=='\n') )
-
-static int vfr_write_proc(struct file *file, const char *buffer,
- u_long count, void *data)
-{
- network_op_t op;
- int ret, len;
- int ts, te, tl; // token start, end, and length
- int fs, fe, fl; // field.
-
- len = count;
- ts = te = 0;
-
- memset(&op, 0, sizeof(network_op_t));
-
- // get the command:
- while ( count && isspace(buffer[ts]) ) { ts++; count--; } // skip spaces.
- te = ts;
- while ( count && !isspace(buffer[te]) ) { te++; count--; } // command end
- if ( te <= ts ) goto bad;
- tl = te - ts;
-
- if ( strncmp(&buffer[ts], "ADD", tl) == 0 )
- {
- op.cmd = NETWORK_OP_ADDRULE;
- }
- else if ( strncmp(&buffer[ts], "DELETE", tl) == 0 )
- {
- op.cmd = NETWORK_OP_DELETERULE;
- }
- else if ( strncmp(&buffer[ts], "PRINT", tl) == 0 )
- {
- op.cmd = NETWORK_OP_GETRULELIST;
- goto doneparsing;
- }
-
- ts = te;
-
- // get the action
- while ( count && (buffer[ts] == ' ') ) { ts++; count--; } // skip spaces.
- te = ts;
- while ( count && (buffer[te] != ' ') ) { te++; count--; } // command end
- if ( te <= ts ) goto bad;
- tl = te - ts;
-
- if ( strncmp(&buffer[ts], "ACCEPT", tl) == 0 )
- {
- op.u.net_rule.action = NETWORK_ACTION_ACCEPT;
- goto keyval;
- }
- if ( strncmp(&buffer[ts], "COUNT", tl) == 0 )
- {
- op.u.net_rule.action = NETWORK_ACTION_COUNT;
- goto keyval;
- }
-
- // default case;
- return (len);
-
-
- // get the key=val pairs.
- keyval:
- while (count)
- {
- //get field
- ts = te; while ( count && isspace(buffer[ts]) ) { ts++; count--; }
- te = ts;
- while ( count && !isspace(buffer[te]) && (buffer[te] != '=') )
- { te++; count--; }
- if ( te <= ts )
- goto doneparsing;
- tl = te - ts;
- fs = ts; fe = te; fl = tl; // save the field markers.
- // skip " = " (ignores extra equals.)
- while ( count && (isspace(buffer[te]) || (buffer[te] == '=')) )
- { te++; count--; }
- ts = te;
- while ( count && !isspace(buffer[te]) ) { te++; count--; }
- tl = te - ts;
-
- if ( (fl <= 0) || (tl <= 0) ) goto bad;
-
- if (strncmp(&buffer[fs], "srcaddr", fl) == 0)
- {
- op.u.net_rule.src_addr = getipaddr(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "dstaddr", fl) == 0)
- {
- op.u.net_rule.dst_addr = getipaddr(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "srcaddrmask", fl) == 0)
- {
- op.u.net_rule.src_addr_mask = getipaddr(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "dstaddrmask", fl) == 0)
- {
- op.u.net_rule.dst_addr_mask = getipaddr(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "srcport", fl) == 0)
- {
- op.u.net_rule.src_port = antous(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "dstport", fl) == 0)
- {
- op.u.net_rule.dst_port = antous(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "srcportmask", fl) == 0)
- {
- op.u.net_rule.src_port_mask = antous(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "dstportmask", fl) == 0)
- {
- op.u.net_rule.dst_port_mask = antous(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "srcint", fl) == 0)
- {
- op.u.net_rule.src_interface = anton(&buffer[ts], tl);
- }
- else if (strncmp(&buffer[fs], "dstint", fl) == 0)
- {
- op.u.net_rule.dst_interface = anton(&buffer[ts], tl);
- }
- else if ( (strncmp(&buffer[fs], "proto", fl) == 0))
- {
- if (strncmp(&buffer[ts], "any", tl) == 0)
- op.u.net_rule.proto = NETWORK_PROTO_ANY;
- if (strncmp(&buffer[ts], "ip", tl) == 0)
- op.u.net_rule.proto = NETWORK_PROTO_IP;
- if (strncmp(&buffer[ts], "tcp", tl) == 0)
- op.u.net_rule.proto = NETWORK_PROTO_TCP;
- if (strncmp(&buffer[ts], "udp", tl) == 0)
- op.u.net_rule.proto = NETWORK_PROTO_UDP;
- if (strncmp(&buffer[ts], "arp", tl) == 0)
- op.u.net_rule.proto = NETWORK_PROTO_ARP;
-
- }
- }
-
- doneparsing:
- ret = HYPERVISOR_network_op(&op);
- return(len);
-
- bad:
- return(len);
-
-
-}
-
-static int __init init_module(void)
-{
- *readbuf = '\0';
- proc_vfr = create_proc_entry ("vfr", 0600, &proc_root);
- if ( proc_vfr != NULL )
- {
- proc_vfr->owner = THIS_MODULE;
- proc_vfr->nlink = 1;
- proc_vfr->read_proc = vfr_read_proc;
- proc_vfr->write_proc = vfr_write_proc;
- printk("Successfully installed virtual firewall/router interface\n");
- }
- return 0;
-}
-
-static void __exit cleanup_module(void)
-{
- if ( proc_vfr == NULL ) return;
- remove_proc_entry("vfr", &proc_root);
- proc_vfr = NULL;
-}
-
-module_init(init_module);
-module_exit(cleanup_module);
-
-/* Helper functions start here: */
-
-int anton(const char *buff, int len)
-{
- int ret;
- char c;
- int sign = 1;
-
- ret = 0;
-
- if (len == 0) return 0;
- if (*buff == '-') { sign = -1; buff++; len--; }
-
- while ( (len) && ((c = *buff) >= '0') && (c <= '9') )
- {
- ret *= 10;
- ret += c - '0';
- buff++; len--;
- }
-
- ret *= sign;
- return ret;
-}
-
-u16 antous(const char *buff, int len)
-{
- u16 ret;
- char c;
-
- ret = 0;
-
- while ( (len) && ((c = *buff) >= '0') && (c <= '9') )
- {
- ret *= 10;
- ret += c - '0';
- buff++; len--;
- }
-
- return ret;
-}
-
-u32 getipaddr(const char *buff, unsigned int len)
-{
- int i;
- char c;
- u32 ret, val;
-
- ret = 0; val = 0;
-
- while ( len )
- {
- if (!((((c = *buff) >= '0') && ( c <= '9')) || ( c == '.' ) ) )
- {
- return(0); // malformed.
- }
-
- if ( c == '.' ) {
- if (val > 255) return (0); //malformed.
- ret = ret << 8;
- ret += val;
- val = 0;
- len--; buff++;
- continue;
- }
- val *= 10;
- val += c - '0';
- buff++; len--;
- }
- ret = ret << 8;
- ret += val;
-
- return (ret);
-}
-
+++ /dev/null
-O_TARGET := net.o
-obj-y := network.o
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/******************************************************************************
- * network.c
- *
- * Virtual network driver for XenoLinux.
- *
- * Copyright (c) 2002, K A Fraser
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-
-#include <linux/netdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/init.h>
-
-#include <asm/io.h>
-#include <net/sock.h>
-
-#define NET_TX_IRQ _EVENT_NET_TX
-#define NET_RX_IRQ _EVENT_NET_RX
-
-#define TX_MAX_ENTRIES (TX_RING_SIZE - 2)
-#define RX_MAX_ENTRIES (RX_RING_SIZE - 2)
-
-#define TX_RING_INC(_i) (((_i)+1) & (TX_RING_SIZE-1))
-#define RX_RING_INC(_i) (((_i)+1) & (RX_RING_SIZE-1))
-#define TX_RING_ADD(_i,_j) (((_i)+(_j)) & (TX_RING_SIZE-1))
-#define RX_RING_ADD(_i,_j) (((_i)+(_j)) & (RX_RING_SIZE-1))
-
-#define RX_BUF_SIZE ((PAGE_SIZE/2)+1) /* Fool the slab allocator :-) */
-
-static void network_rx_int(int irq, void *dev_id, struct pt_regs *ptregs);
-static void network_tx_int(int irq, void *dev_id, struct pt_regs *ptregs);
-static void network_tx_buf_gc(struct net_device *dev);
-static void network_alloc_rx_buffers(struct net_device *dev);
-static void network_free_rx_buffers(struct net_device *dev);
-static void cleanup_module(void);
-
-static struct list_head dev_list;
-
-/*
- * RX RING: RX_IDX <= rx_cons <= rx_prod
- * TX RING: TX_IDX <= tx_cons <= tx_prod
- * (*_IDX allocated privately here, *_cons & *_prod shared with hypervisor)
- */
-struct net_private
-{
- struct list_head list;
- struct net_device *dev;
-
- struct net_device_stats stats;
- struct sk_buff **tx_skb_ring;
- struct sk_buff **rx_skb_ring;
- atomic_t tx_entries;
- unsigned int rx_idx, tx_idx, tx_full;
- net_ring_t *net_ring;
- spinlock_t tx_lock;
-};
-
-
-static int network_open(struct net_device *dev)
-{
- struct net_private *np = dev->priv;
- int error = 0;
-
- np->rx_idx = np->tx_idx = np->tx_full = 0;
-
- memset(&np->stats, 0, sizeof(np->stats));
-
- spin_lock_init(&np->tx_lock);
-
- atomic_set(&np->tx_entries, 0);
-
- np->net_ring->tx_prod = np->net_ring->tx_cons = np->net_ring->tx_event = 0;
- np->net_ring->rx_prod = np->net_ring->rx_cons = np->net_ring->rx_event = 0;
- np->net_ring->tx_ring = NULL;
- np->net_ring->rx_ring = NULL;
-
- np->tx_skb_ring = kmalloc(TX_RING_SIZE * sizeof(struct sk_buff *),
- GFP_KERNEL);
- np->rx_skb_ring = kmalloc(RX_RING_SIZE * sizeof(struct sk_buff *),
- GFP_KERNEL);
- np->net_ring->tx_ring = kmalloc(TX_RING_SIZE * sizeof(tx_entry_t),
- GFP_KERNEL);
- np->net_ring->rx_ring = kmalloc(RX_RING_SIZE * sizeof(rx_entry_t),
- GFP_KERNEL);
- if ( (np->tx_skb_ring == NULL) || (np->rx_skb_ring == NULL) ||
- (np->net_ring->tx_ring == NULL) || (np->net_ring->rx_ring == NULL) )
- {
- printk(KERN_WARNING "%s; Could not allocate ring memory\n", dev->name);
- error = -ENOBUFS;
- goto fail;
- }
-
- network_alloc_rx_buffers(dev);
-
- error = request_irq(NET_RX_IRQ, network_rx_int, 0,
- "net-rx", dev);
- if ( error )
- {
- printk(KERN_WARNING "%s: Could not allocate receive interrupt\n",
- dev->name);
- network_free_rx_buffers(dev);
- goto fail;
- }
-
- error = request_irq(NET_TX_IRQ, network_tx_int, 0,
- "net-tx", dev);
- if ( error )
- {
- printk(KERN_WARNING "%s: Could not allocate transmit interrupt\n",
- dev->name);
- free_irq(NET_RX_IRQ, dev);
- network_free_rx_buffers(dev);
- goto fail;
- }
-
- printk("XenoLinux Virtual Network Driver installed as %s\n", dev->name);
-
- netif_start_queue(dev);
-
- MOD_INC_USE_COUNT;
-
- return 0;
-
- fail:
- if ( np->net_ring->rx_ring ) kfree(np->net_ring->rx_ring);
- if ( np->net_ring->tx_ring ) kfree(np->net_ring->tx_ring);
- if ( np->rx_skb_ring ) kfree(np->rx_skb_ring);
- if ( np->tx_skb_ring ) kfree(np->tx_skb_ring);
- kfree(np);
- return error;
-}
-
-
-static void network_tx_buf_gc(struct net_device *dev)
-{
- unsigned int i;
- struct net_private *np = dev->priv;
- struct sk_buff *skb;
- unsigned long flags;
-
- spin_lock_irqsave(&np->tx_lock, flags);
-
- for ( i = np->tx_idx; i != np->net_ring->tx_cons; i = TX_RING_INC(i) )
- {
- skb = np->tx_skb_ring[i];
- dev_kfree_skb_any(skb);
- atomic_dec(&np->tx_entries);
- }
-
- np->tx_idx = i;
-
- if ( np->tx_full && (atomic_read(&np->tx_entries) < TX_MAX_ENTRIES) )
- {
- np->tx_full = 0;
- netif_wake_queue(dev);
- }
-
- spin_unlock_irqrestore(&np->tx_lock, flags);
-}
-
-inline unsigned long get_ppte(unsigned long addr)
-{
- unsigned long ppte;
- pgd_t *pgd; pmd_t *pmd; pte_t *ptep;
- pgd = pgd_offset_k(addr);
-
- if ( pgd_none(*pgd) || pgd_bad(*pgd) ) BUG();
-
- pmd = pmd_offset(pgd, addr);
- if ( pmd_none(*pmd) || pmd_bad(*pmd) ) BUG();
-
- ptep = pte_offset(pmd, addr);
- ppte = (unsigned long)phys_to_machine(virt_to_phys(ptep));
-
- return ppte;
-}
-
-static void network_alloc_rx_buffers(struct net_device *dev)
-{
- unsigned int i;
- struct net_private *np = dev->priv;
- struct sk_buff *skb;
- unsigned int end = RX_RING_ADD(np->rx_idx, RX_MAX_ENTRIES);
-
- for ( i = np->net_ring->rx_prod; i != end; i = RX_RING_INC(i) )
- {
- skb = dev_alloc_skb(RX_BUF_SIZE);
- if ( skb == NULL ) break;
- skb->dev = dev;
- skb_reserve(skb, 2); /* word align the IP header */
- np->rx_skb_ring[i] = skb;
- np->net_ring->rx_ring[i].addr = get_ppte((unsigned long)skb->head);
- np->net_ring->rx_ring[i].size = RX_BUF_SIZE - 16; /* arbitrary */
- }
-
- np->net_ring->rx_prod = i;
-
- np->net_ring->rx_event = RX_RING_INC(np->rx_idx);
-
- HYPERVISOR_net_update();
-}
-
-
-static void network_free_rx_buffers(struct net_device *dev)
-{
- unsigned int i;
- struct net_private *np = dev->priv;
- struct sk_buff *skb;
-
- for ( i = np->rx_idx; i != np->net_ring->rx_prod; i = RX_RING_INC(i) )
- {
- skb = np->rx_skb_ring[i];
- dev_kfree_skb(skb);
- }
-}
-
-static int network_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- unsigned int i;
- struct net_private *np = (struct net_private *)dev->priv;
-
- if ( np->tx_full )
- {
- printk(KERN_WARNING "%s: full queue wasn't stopped!\n", dev->name);
- netif_stop_queue(dev);
- return -ENOBUFS;
- }
- i = np->net_ring->tx_prod;
-
- if ( (((unsigned long)skb->data & ~PAGE_MASK) + skb->len) >= PAGE_SIZE )
- {
- struct sk_buff *new_skb = alloc_skb(RX_BUF_SIZE, GFP_KERNEL);
- skb_put(new_skb, skb->len);
- memcpy(new_skb->data, skb->data, skb->len);
- kfree_skb(skb);
- skb = new_skb;
- }
-
- np->tx_skb_ring[i] = skb;
- np->net_ring->tx_ring[i].addr =
- (unsigned long)phys_to_machine(virt_to_phys(skb->data));
- np->net_ring->tx_ring[i].size = skb->len;
- np->net_ring->tx_prod = TX_RING_INC(i);
- atomic_inc(&np->tx_entries);
-
- np->stats.tx_bytes += skb->len;
- np->stats.tx_packets++;
-
- spin_lock_irq(&np->tx_lock);
- if ( atomic_read(&np->tx_entries) >= TX_MAX_ENTRIES )
- {
- np->tx_full = 1;
- netif_stop_queue(dev);
- np->net_ring->tx_event =
- TX_RING_ADD(np->tx_idx, atomic_read(&np->tx_entries) >> 1);
- }
- else
- {
- /* Avoid unnecessary tx interrupts. */
- np->net_ring->tx_event = TX_RING_INC(np->net_ring->tx_prod);
- }
- spin_unlock_irq(&np->tx_lock);
-
- /* Must do this after setting tx_event: race with updates of tx_cons. */
- network_tx_buf_gc(dev);
-
- HYPERVISOR_net_update();
-
- return 0;
-}
-
-
-static void network_rx_int(int irq, void *dev_id, struct pt_regs *ptregs)
-{
- unsigned int i;
- struct net_device *dev = (struct net_device *)dev_id;
- struct net_private *np = dev->priv;
- struct sk_buff *skb;
-
- again:
- for ( i = np->rx_idx; i != np->net_ring->rx_cons; i = RX_RING_INC(i) )
- {
- if (np->net_ring->rx_ring[i].status != RING_STATUS_OK)
- {
- printk("bad buffer on RX ring!(%d)\n",
- np->net_ring->rx_ring[i].status);
- continue;
- }
- skb = np->rx_skb_ring[i];
-
- phys_to_machine_mapping[virt_to_phys(skb->head) >> PAGE_SHIFT] =
- (*(unsigned long *)phys_to_virt(
- machine_to_phys(np->net_ring->rx_ring[i].addr))
- ) >> PAGE_SHIFT;
-
- skb_put(skb, np->net_ring->rx_ring[i].size);
- skb->protocol = eth_type_trans(skb, dev);
-
- /*
- * Set up shinfo -- from alloc_skb This was particularily nasty: the
- * shared info is hidden at the back of the data area (presumably so it
- * can be shared), but on page flip it gets very spunked.
- */
- atomic_set(&(skb_shinfo(skb)->dataref), 1);
- skb_shinfo(skb)->nr_frags = 0;
- skb_shinfo(skb)->frag_list = NULL;
-
- np->stats.rx_packets++;
-
- np->stats.rx_bytes += np->net_ring->rx_ring[i].size;
- netif_rx(skb);
- dev->last_rx = jiffies;
- }
-
- np->rx_idx = i;
-
- network_alloc_rx_buffers(dev);
-
- /* Deal with hypervisor racing our resetting of rx_event. */
- smp_mb();
- if ( np->net_ring->rx_cons != i ) goto again;
-}
-
-
-static void network_tx_int(int irq, void *dev_id, struct pt_regs *ptregs)
-{
- struct net_device *dev = (struct net_device *)dev_id;
- network_tx_buf_gc(dev);
-}
-
-
-int network_close(struct net_device *dev)
-{
- struct net_private *np = dev->priv;
-
- netif_stop_queue(dev);
-
- free_irq(NET_RX_IRQ, dev);
- free_irq(NET_TX_IRQ, dev);
-
- /*
- * XXXX This cannot be done safely until be have a proper interface
- * for setting up and tearing down virtual interfaces on the fly.
- * Currently the receive buffers are locked down by Xen and we have
- * no sensible way of retrieving them.
- */
-#if 0
- network_free_rx_buffers(dev);
- kfree(np->net_ring->rx_ring);
- kfree(np->net_ring->tx_ring);
-#endif
-
- kfree(np->rx_skb_ring);
- kfree(np->tx_skb_ring);
-
- MOD_DEC_USE_COUNT;
-
- return 0;
-}
-
-
-static struct net_device_stats *network_get_stats(struct net_device *dev)
-{
- struct net_private *np = (struct net_private *)dev->priv;
- return &np->stats;
-}
-
-
-int __init init_module(void)
-{
- int i, err;
- struct net_device *dev;
- struct net_private *np;
-
- INIT_LIST_HEAD(&dev_list);
-
- for ( i = 0; i < start_info.num_net_rings; i++ )
- {
- dev = alloc_etherdev(sizeof(struct net_private));
- if ( dev == NULL )
- {
- err = -ENOMEM;
- goto fail;
- }
-
- np = dev->priv;
- np->net_ring = start_info.net_rings + i;
-
- SET_MODULE_OWNER(dev);
- dev->open = network_open;
- dev->hard_start_xmit = network_start_xmit;
- dev->stop = network_close;
- dev->get_stats = network_get_stats;
-
- memset(dev->dev_addr, 0, ETH_ALEN);
- *(unsigned int *)(dev->dev_addr + 1) = i;
-
- if ( (err = register_netdev(dev)) != 0 )
- {
- kfree(dev);
- goto fail;
- }
-
- np->dev = dev;
- list_add(&np->list, &dev_list);
- }
-
- return 0;
-
- fail:
- cleanup_module();
- return err;
-}
-
-
-static void cleanup_module(void)
-{
- struct net_private *np;
- struct net_device *dev;
-
- while ( !list_empty(&dev_list) )
- {
- np = list_entry(dev_list.next, struct net_private, list);
- list_del(&np->list);
- dev = np->dev;
- unregister_netdev(dev);
- kfree(dev);
- }
-}
-
-
-module_init(init_module);
-module_exit(cleanup_module);
+++ /dev/null
-
-.S.o:
- $(CC) $(AFLAGS) -traditional -c $< -o $*.o
-
-all: kernel.o head.o init_task.o
-
-O_TARGET := kernel.o
-
-export-objs := i386_ksyms.o
-
-obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \
- ptrace.o ioport.o ldt.o setup.o time.o sys_i386.o \
- i386_ksyms.o i387.o hypervisor.o
-
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/*
- * linux/arch/i386/entry.S
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- * This also contains the timer-interrupt handler, as well as all interrupts
- * and faults that can result in a task-switch.
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after a timer-interrupt and after each system call.
- *
- * I changed all the .align's to 4 (16 byte alignment), as that's faster
- * on a 486.
- *
- * Stack layout in 'ret_from_system_call':
- * ptrace needs to have all regs on the stack.
- * if the order here is changed, it needs to be
- * updated in fork.c:copy_process, signal.c:do_signal,
- * ptrace.c and ptrace.h
- *
- * 0(%esp) - %ebx
- * 4(%esp) - %ecx
- * 8(%esp) - %edx
- * C(%esp) - %esi
- * 10(%esp) - %edi
- * 14(%esp) - %ebp
- * 18(%esp) - %eax
- * 1C(%esp) - %ds
- * 20(%esp) - %es
- * 24(%esp) - orig_eax
- * 28(%esp) - %eip
- * 2C(%esp) - %cs
- * 30(%esp) - %eflags
- * 34(%esp) - %oldesp
- * 38(%esp) - %oldss
- *
- * "current" is in register %ebx during any slow entries.
- */
-
-#include <linux/config.h>
-#include <linux/sys.h>
-#include <linux/linkage.h>
-#include <asm/segment.h>
-#include <asm/smp.h>
-
-EBX = 0x00
-ECX = 0x04
-EDX = 0x08
-ESI = 0x0C
-EDI = 0x10
-EBP = 0x14
-EAX = 0x18
-DS = 0x1C
-ES = 0x20
-ORIG_EAX = 0x24
-EIP = 0x28
-CS = 0x2C
-EFLAGS = 0x30
-OLDESP = 0x34
-OLDSS = 0x38
-
-CF_MASK = 0x00000001
-IF_MASK = 0x00000200
-NT_MASK = 0x00004000
-
-/*
- * these are offsets into the task-struct.
- */
-state = 0
-flags = 4
-sigpending = 8
-addr_limit = 12
-exec_domain = 16
-need_resched = 20
-tsk_ptrace = 24
-processor = 52
-
-ENOSYS = 38
-
-
-#define SAVE_ALL \
- cld; \
- pushl %es; \
- pushl %ds; \
- pushl %eax; \
- pushl %ebp; \
- pushl %edi; \
- pushl %esi; \
- pushl %edx; \
- pushl %ecx; \
- pushl %ebx; \
- movl $(__KERNEL_DS),%edx; \
- movl %edx,%ds; \
- movl %edx,%es;
-
-#define RESTORE_ALL \
- popl %ebx; \
- popl %ecx; \
- popl %edx; \
- popl %esi; \
- popl %edi; \
- popl %ebp; \
- popl %eax; \
-1: popl %ds; \
-2: popl %es; \
- addl $4,%esp; \
-3: iret; \
-.section .fixup,"ax"; \
-4: movl $0,(%esp); \
- jmp 1b; \
-5: movl $0,(%esp); \
- jmp 2b; \
-6: pushl %ss; \
- popl %ds; \
- pushl %ss; \
- popl %es; \
- pushl $11; \
- call do_exit; \
-.previous; \
-.section __ex_table,"a";\
- .align 4; \
- .long 1b,4b; \
- .long 2b,5b; \
- .long 3b,6b; \
-.previous
-
-#define GET_CURRENT(reg) \
- movl $-8192, reg; \
- andl %esp, reg
-
-
-ENTRY(ret_from_fork)
- pushl %ebx
- call SYMBOL_NAME(schedule_tail)
- addl $4, %esp
- GET_CURRENT(%ebx)
- testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
- jne tracesys_exit
- jmp ret_from_sys_call
-
-#if defined(CONFIG_KDB)
-ENTRY(kdb_call)
- pushl %eax # save orig EAX
- SAVE_ALL
- pushl %esp # struct pt_regs
- pushl $0 # error_code
- pushl $7 # KDB_REASON_ENTRY
- call SYMBOL_NAME(kdb)
- addl $12,%esp # remove args
- RESTORE_ALL
-#endif
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
-ENTRY(system_call)
- pushl %eax # save orig_eax
- SAVE_ALL
- GET_CURRENT(%ebx)
- testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
- jne tracesys
- cmpl $(NR_syscalls),%eax
- jae badsys
- call *SYMBOL_NAME(sys_call_table)(,%eax,4)
- movl %eax,EAX(%esp) # save the return value
-ENTRY(ret_from_sys_call)
- movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
- xorl %eax,%eax
- movl %eax,4(%esi) # need_resched and signals atomic test
-ret_syscall_tests:
- cmpl $0,need_resched(%ebx)
- jne reschedule
- cmpl $0,sigpending(%ebx)
- je safesti # ensure need_resched updates are seen
-signal_return:
- btsl %eax,4(%esi) # reenable event callbacks
- movl %esp,%eax
- xorl %edx,%edx
- call SYMBOL_NAME(do_signal)
- jmp ret_from_sys_call
-
- ALIGN
-restore_all:
- RESTORE_ALL
-
- ALIGN
-tracesys:
- movl $-ENOSYS,EAX(%esp)
- call SYMBOL_NAME(syscall_trace)
- movl ORIG_EAX(%esp),%eax
- cmpl $(NR_syscalls),%eax
- jae tracesys_exit
- call *SYMBOL_NAME(sys_call_table)(,%eax,4)
- movl %eax,EAX(%esp) # save the return value
-tracesys_exit:
- call SYMBOL_NAME(syscall_trace)
- jmp ret_from_sys_call
-badsys:
- movl $-ENOSYS,EAX(%esp)
- jmp ret_from_sys_call
-
- ALIGN
-ENTRY(ret_from_intr)
- GET_CURRENT(%ebx)
-ret_from_exception:
- movb CS(%esp),%al
- testl $2,%eax
- jne ret_from_sys_call
- jmp restore_all
-
- ALIGN
-reschedule:
- btsl %eax,4(%esi) # reenable event callbacks
- call SYMBOL_NAME(schedule) # test
- jmp ret_from_sys_call
-
-ENTRY(divide_error)
- pushl $0 # no error code
- pushl $ SYMBOL_NAME(do_divide_error)
- ALIGN
-error_code:
- pushl %ds
- pushl %eax
- xorl %eax,%eax
- pushl %ebp
- pushl %edi
- pushl %esi
- pushl %edx
- decl %eax # eax = -1
- pushl %ecx
- pushl %ebx
- GET_CURRENT(%ebx)
- cld
- movl %es,%ecx
- movl ORIG_EAX(%esp), %esi # get the error code
- movl ES(%esp), %edi # get the function address
- movl %eax, ORIG_EAX(%esp)
- movl %ecx, ES(%esp)
- movl %esp,%edx
- pushl %esi # push the error code
- pushl %edx # push the pt_regs pointer
- movl $(__KERNEL_DS),%edx
- movl %edx,%ds
- movl %edx,%es
- call *%edi
- addl $8,%esp
- jmp ret_from_exception
-
-# A note on the "critical region" in our callback handler.
-# We want to avoid stacking callback handlers due to events occurring
-# during handling of the last event. To do this, we keep events disabled
-# until we've done all processing. HOWEVER, we must enable events before
-# popping the stack frame (can't be done atomically) and so it would still
-# be possible to get enough handler activations to overflow the stack.
-# Although unlikely, bugs of that kind are hard to track down, so we'd
-# like to avoid the possibility.
-# So, on entry to the handler we detect whether we interrupted an
-# existing activation in its critical region -- if so, we pop the current
-# activation and restart the handler using the previous one.
-ENTRY(hypervisor_callback)
- pushl %eax
- SAVE_ALL
- GET_CURRENT(%ebx)
- movl EIP(%esp),%eax
- cmpl $scrit,%eax
- jb 11f
- cmpl $ecrit,%eax
- jb critical_region_fixup
-11: push %esp
- call do_hypervisor_callback
- add $4,%esp
- movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
- xorl %eax,%eax
- movb CS(%esp),%cl
- test $2,%cl # slow return to ring 2 or 3
- jne ret_syscall_tests
-safesti:btsl %eax,4(%esi) # reenable event callbacks
-scrit: /**** START OF CRITICAL REGION ****/
- cmpl %eax,(%esi)
- jne 14f # process more events if necessary...
- RESTORE_ALL
-14: btrl %eax,4(%esi)
- jmp 11b
-ecrit: /**** END OF CRITICAL REGION ****/
-# [How we do the fixup]. We want to merge the current stack frame with the
-# just-interrupted frame. How we do this depends on where in the critical
-# region the interrupted handler was executing, and so how many saved
-# registers are in each frame. We do this quickly using the lookup table
-# 'critical_fixup_table'. For each byte offset in the critical region, it
-# provides the number of bytes which have already been popped from the
-# interrupted stack frame.
-critical_region_fixup:
- addl $critical_fixup_table-scrit,%eax
- movzbl (%eax),%eax # %eax contains num bytes popped
- mov %esp,%esi
- add %eax,%esi # %esi points at end of src region
- mov %esp,%edi
- add $0x34,%edi # %edi points at end of dst region
- mov %eax,%ecx
- shr $2,%ecx # convert words to bytes
- je 16f # skip loop if nothing to copy
-15: subl $4,%esi # pre-decrementing copy loop
- subl $4,%edi
- movl (%esi),%eax
- movl %eax,(%edi)
- loop 15b
-16: movl %edi,%esp # final %edi is top of merged stack
- jmp 11b
-
-critical_fixup_table:
- .byte 0x00,0x00 # cmpl %eax,(%esi)
- .byte 0x00,0x00 # jne 14f
- .byte 0x00 # pop %ebx
- .byte 0x04 # pop %ecx
- .byte 0x08 # pop %edx
- .byte 0x0c # pop %esi
- .byte 0x10 # pop %edi
- .byte 0x14 # pop %ebp
- .byte 0x18 # pop %eax
- .byte 0x1c # pop %ds
- .byte 0x20 # pop %es
- .byte 0x24,0x24,0x24 # add $4,%esp
- .byte 0x28 # iret
- .byte 0x00,0x00,0x00,0x00 # btrl %eax,4(%esi)
- .byte 0x00,0x00 # jmp 11b
-
-# Hypervisor uses this for application faults while it executes.
-ENTRY(failsafe_callback)
-1: pop %ds
-2: pop %es
-3: iret
-.section .fixup,"ax"; \
-4: movl $0,(%esp); \
- jmp 1b; \
-5: movl $0,(%esp); \
- jmp 2b; \
-6: pushl %ss; \
- popl %ds; \
- pushl %ss; \
- popl %es; \
- pushl $11; \
- call do_exit; \
-.previous; \
-.section __ex_table,"a";\
- .align 4; \
- .long 1b,4b; \
- .long 2b,5b; \
- .long 3b,6b; \
-.previous
-
-ENTRY(coprocessor_error)
- pushl $0
- pushl $ SYMBOL_NAME(do_coprocessor_error)
- jmp error_code
-
-ENTRY(simd_coprocessor_error)
- pushl $0
- pushl $ SYMBOL_NAME(do_simd_coprocessor_error)
- jmp error_code
-
-ENTRY(device_not_available)
- pushl $-1 # mark this as an int
- SAVE_ALL
- GET_CURRENT(%ebx)
- call SYMBOL_NAME(math_state_restore)
- jmp ret_from_exception
-
-ENTRY(debug)
- pushl $0
- pushl $ SYMBOL_NAME(do_debug)
- jmp error_code
-
-ENTRY(int3)
- pushl $0
- pushl $ SYMBOL_NAME(do_int3)
- jmp error_code
-
-ENTRY(overflow)
- pushl $0
- pushl $ SYMBOL_NAME(do_overflow)
- jmp error_code
-
-ENTRY(bounds)
- pushl $0
- pushl $ SYMBOL_NAME(do_bounds)
- jmp error_code
-
-ENTRY(invalid_op)
- pushl $0
- pushl $ SYMBOL_NAME(do_invalid_op)
- jmp error_code
-
-ENTRY(coprocessor_segment_overrun)
- pushl $0
- pushl $ SYMBOL_NAME(do_coprocessor_segment_overrun)
- jmp error_code
-
-ENTRY(double_fault)
- pushl $ SYMBOL_NAME(do_double_fault)
- jmp error_code
-
-ENTRY(invalid_TSS)
- pushl $ SYMBOL_NAME(do_invalid_TSS)
- jmp error_code
-
-ENTRY(segment_not_present)
- pushl $ SYMBOL_NAME(do_segment_not_present)
- jmp error_code
-
-ENTRY(stack_segment)
- pushl $ SYMBOL_NAME(do_stack_segment)
- jmp error_code
-
-ENTRY(general_protection)
- pushl $ SYMBOL_NAME(do_general_protection)
- jmp error_code
-
-ENTRY(alignment_check)
- pushl $ SYMBOL_NAME(do_alignment_check)
- jmp error_code
-
-#if defined(CONFIG_KDB)
-ENTRY(page_fault_mca)
- pushl %ecx
- pushl %edx
- pushl %eax
- movl $473,%ecx
- rdmsr
- andl $0xfffffffe,%eax /* Disable last branch recording */
- wrmsr
- popl %eax
- popl %edx
- popl %ecx
- pushl $ SYMBOL_NAME(do_page_fault)
- jmp error_code
-#endif
-
-# This handler is special, because it gets an extra value on its stack,
-# which is the linear faulting address.
-ENTRY(page_fault)
- pushl %ds
- pushl %eax
- xorl %eax,%eax
- pushl %ebp
- pushl %edi
- pushl %esi
- pushl %edx
- decl %eax # eax = -1
- pushl %ecx
- pushl %ebx
- GET_CURRENT(%ebx)
- cld
- movl %es,%ecx
- movl ORIG_EAX(%esp), %esi # get the error code
- movl ES(%esp), %edi # get the faulting address
- movl %eax, ORIG_EAX(%esp)
- movl %ecx, ES(%esp)
- movl %esp,%edx
- pushl %edi # push the faulting address
- pushl %esi # push the error code
- pushl %edx # push the pt_regs pointer
- movl $(__KERNEL_DS),%edx
- movl %edx,%ds
- movl %edx,%es
- call SYMBOL_NAME(do_page_fault)
- addl $12,%esp
- jmp ret_from_exception
-
-ENTRY(machine_check)
- pushl $0
- pushl $ SYMBOL_NAME(do_machine_check)
- jmp error_code
-
-ENTRY(spurious_interrupt_bug)
- pushl $0
- pushl $ SYMBOL_NAME(do_spurious_interrupt_bug)
- jmp error_code
-
-.data
-ENTRY(sys_call_table)
- .long SYMBOL_NAME(sys_ni_syscall) /* 0 - old "setup()" system call*/
- .long SYMBOL_NAME(sys_exit)
- .long SYMBOL_NAME(sys_fork)
- .long SYMBOL_NAME(sys_read)
- .long SYMBOL_NAME(sys_write)
- .long SYMBOL_NAME(sys_open) /* 5 */
- .long SYMBOL_NAME(sys_close)
- .long SYMBOL_NAME(sys_waitpid)
- .long SYMBOL_NAME(sys_creat)
- .long SYMBOL_NAME(sys_link)
- .long SYMBOL_NAME(sys_unlink) /* 10 */
- .long SYMBOL_NAME(sys_execve)
- .long SYMBOL_NAME(sys_chdir)
- .long SYMBOL_NAME(sys_time)
- .long SYMBOL_NAME(sys_mknod)
- .long SYMBOL_NAME(sys_chmod) /* 15 */
- .long SYMBOL_NAME(sys_lchown16)
- .long SYMBOL_NAME(sys_ni_syscall) /* old break syscall holder */
- .long SYMBOL_NAME(sys_stat)
- .long SYMBOL_NAME(sys_lseek)
- .long SYMBOL_NAME(sys_getpid) /* 20 */
- .long SYMBOL_NAME(sys_mount)
- .long SYMBOL_NAME(sys_oldumount)
- .long SYMBOL_NAME(sys_setuid16)
- .long SYMBOL_NAME(sys_getuid16)
- .long SYMBOL_NAME(sys_stime) /* 25 */
- .long SYMBOL_NAME(sys_ptrace)
- .long SYMBOL_NAME(sys_alarm)
- .long SYMBOL_NAME(sys_fstat)
- .long SYMBOL_NAME(sys_pause)
- .long SYMBOL_NAME(sys_utime) /* 30 */
- .long SYMBOL_NAME(sys_ni_syscall) /* old stty syscall holder */
- .long SYMBOL_NAME(sys_ni_syscall) /* old gtty syscall holder */
- .long SYMBOL_NAME(sys_access)
- .long SYMBOL_NAME(sys_nice)
- .long SYMBOL_NAME(sys_ni_syscall) /* 35 */ /* old ftime syscall holder */
- .long SYMBOL_NAME(sys_sync)
- .long SYMBOL_NAME(sys_kill)
- .long SYMBOL_NAME(sys_rename)
- .long SYMBOL_NAME(sys_mkdir)
- .long SYMBOL_NAME(sys_rmdir) /* 40 */
- .long SYMBOL_NAME(sys_dup)
- .long SYMBOL_NAME(sys_pipe)
- .long SYMBOL_NAME(sys_times)
- .long SYMBOL_NAME(sys_ni_syscall) /* old prof syscall holder */
- .long SYMBOL_NAME(sys_brk) /* 45 */
- .long SYMBOL_NAME(sys_setgid16)
- .long SYMBOL_NAME(sys_getgid16)
- .long SYMBOL_NAME(sys_signal)
- .long SYMBOL_NAME(sys_geteuid16)
- .long SYMBOL_NAME(sys_getegid16) /* 50 */
- .long SYMBOL_NAME(sys_acct)
- .long SYMBOL_NAME(sys_umount) /* recycled never used phys() */
- .long SYMBOL_NAME(sys_ni_syscall) /* old lock syscall holder */
- .long SYMBOL_NAME(sys_ioctl)
- .long SYMBOL_NAME(sys_fcntl) /* 55 */
- .long SYMBOL_NAME(sys_ni_syscall) /* old mpx syscall holder */
- .long SYMBOL_NAME(sys_setpgid)
- .long SYMBOL_NAME(sys_ni_syscall) /* old ulimit syscall holder */
- .long SYMBOL_NAME(sys_olduname)
- .long SYMBOL_NAME(sys_umask) /* 60 */
- .long SYMBOL_NAME(sys_chroot)
- .long SYMBOL_NAME(sys_ustat)
- .long SYMBOL_NAME(sys_dup2)
- .long SYMBOL_NAME(sys_getppid)
- .long SYMBOL_NAME(sys_getpgrp) /* 65 */
- .long SYMBOL_NAME(sys_setsid)
- .long SYMBOL_NAME(sys_sigaction)
- .long SYMBOL_NAME(sys_sgetmask)
- .long SYMBOL_NAME(sys_ssetmask)
- .long SYMBOL_NAME(sys_setreuid16) /* 70 */
- .long SYMBOL_NAME(sys_setregid16)
- .long SYMBOL_NAME(sys_sigsuspend)
- .long SYMBOL_NAME(sys_sigpending)
- .long SYMBOL_NAME(sys_sethostname)
- .long SYMBOL_NAME(sys_setrlimit) /* 75 */
- .long SYMBOL_NAME(sys_old_getrlimit)
- .long SYMBOL_NAME(sys_getrusage)
- .long SYMBOL_NAME(sys_gettimeofday)
- .long SYMBOL_NAME(sys_settimeofday)
- .long SYMBOL_NAME(sys_getgroups16) /* 80 */
- .long SYMBOL_NAME(sys_setgroups16)
- .long SYMBOL_NAME(old_select)
- .long SYMBOL_NAME(sys_symlink)
- .long SYMBOL_NAME(sys_lstat)
- .long SYMBOL_NAME(sys_readlink) /* 85 */
- .long SYMBOL_NAME(sys_uselib)
- .long SYMBOL_NAME(sys_swapon)
- .long SYMBOL_NAME(sys_reboot)
- .long SYMBOL_NAME(old_readdir)
- .long SYMBOL_NAME(old_mmap) /* 90 */
- .long SYMBOL_NAME(sys_munmap)
- .long SYMBOL_NAME(sys_truncate)
- .long SYMBOL_NAME(sys_ftruncate)
- .long SYMBOL_NAME(sys_fchmod)
- .long SYMBOL_NAME(sys_fchown16) /* 95 */
- .long SYMBOL_NAME(sys_getpriority)
- .long SYMBOL_NAME(sys_setpriority)
- .long SYMBOL_NAME(sys_ni_syscall) /* old profil syscall holder */
- .long SYMBOL_NAME(sys_statfs)
- .long SYMBOL_NAME(sys_fstatfs) /* 100 */
- .long SYMBOL_NAME(sys_ioperm)
- .long SYMBOL_NAME(sys_socketcall)
- .long SYMBOL_NAME(sys_syslog)
- .long SYMBOL_NAME(sys_setitimer)
- .long SYMBOL_NAME(sys_getitimer) /* 105 */
- .long SYMBOL_NAME(sys_newstat)
- .long SYMBOL_NAME(sys_newlstat)
- .long SYMBOL_NAME(sys_newfstat)
- .long SYMBOL_NAME(sys_uname)
- .long SYMBOL_NAME(sys_iopl) /* 110 */
- .long SYMBOL_NAME(sys_vhangup)
- .long SYMBOL_NAME(sys_ni_syscall) /* old "idle" system call */
- .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
- .long SYMBOL_NAME(sys_wait4)
- .long SYMBOL_NAME(sys_swapoff) /* 115 */
- .long SYMBOL_NAME(sys_sysinfo)
- .long SYMBOL_NAME(sys_ipc)
- .long SYMBOL_NAME(sys_fsync)
- .long SYMBOL_NAME(sys_sigreturn)
- .long SYMBOL_NAME(sys_clone) /* 120 */
- .long SYMBOL_NAME(sys_setdomainname)
- .long SYMBOL_NAME(sys_newuname)
- .long SYMBOL_NAME(sys_modify_ldt)
- .long SYMBOL_NAME(sys_adjtimex)
- .long SYMBOL_NAME(sys_mprotect) /* 125 */
- .long SYMBOL_NAME(sys_sigprocmask)
- .long SYMBOL_NAME(sys_create_module)
- .long SYMBOL_NAME(sys_init_module)
- .long SYMBOL_NAME(sys_delete_module)
- .long SYMBOL_NAME(sys_get_kernel_syms) /* 130 */
- .long SYMBOL_NAME(sys_quotactl)
- .long SYMBOL_NAME(sys_getpgid)
- .long SYMBOL_NAME(sys_fchdir)
- .long SYMBOL_NAME(sys_bdflush)
- .long SYMBOL_NAME(sys_sysfs) /* 135 */
- .long SYMBOL_NAME(sys_personality)
- .long SYMBOL_NAME(sys_ni_syscall) /* for afs_syscall */
- .long SYMBOL_NAME(sys_setfsuid16)
- .long SYMBOL_NAME(sys_setfsgid16)
- .long SYMBOL_NAME(sys_llseek) /* 140 */
- .long SYMBOL_NAME(sys_getdents)
- .long SYMBOL_NAME(sys_select)
- .long SYMBOL_NAME(sys_flock)
- .long SYMBOL_NAME(sys_msync)
- .long SYMBOL_NAME(sys_readv) /* 145 */
- .long SYMBOL_NAME(sys_writev)
- .long SYMBOL_NAME(sys_getsid)
- .long SYMBOL_NAME(sys_fdatasync)
- .long SYMBOL_NAME(sys_sysctl)
- .long SYMBOL_NAME(sys_mlock) /* 150 */
- .long SYMBOL_NAME(sys_munlock)
- .long SYMBOL_NAME(sys_mlockall)
- .long SYMBOL_NAME(sys_munlockall)
- .long SYMBOL_NAME(sys_sched_setparam)
- .long SYMBOL_NAME(sys_sched_getparam) /* 155 */
- .long SYMBOL_NAME(sys_sched_setscheduler)
- .long SYMBOL_NAME(sys_sched_getscheduler)
- .long SYMBOL_NAME(sys_sched_yield)
- .long SYMBOL_NAME(sys_sched_get_priority_max)
- .long SYMBOL_NAME(sys_sched_get_priority_min) /* 160 */
- .long SYMBOL_NAME(sys_sched_rr_get_interval)
- .long SYMBOL_NAME(sys_nanosleep)
- .long SYMBOL_NAME(sys_mremap)
- .long SYMBOL_NAME(sys_setresuid16)
- .long SYMBOL_NAME(sys_getresuid16) /* 165 */
- .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
- .long SYMBOL_NAME(sys_query_module)
- .long SYMBOL_NAME(sys_poll)
- .long SYMBOL_NAME(sys_nfsservctl)
- .long SYMBOL_NAME(sys_setresgid16) /* 170 */
- .long SYMBOL_NAME(sys_getresgid16)
- .long SYMBOL_NAME(sys_prctl)
- .long SYMBOL_NAME(sys_rt_sigreturn)
- .long SYMBOL_NAME(sys_rt_sigaction)
- .long SYMBOL_NAME(sys_rt_sigprocmask) /* 175 */
- .long SYMBOL_NAME(sys_rt_sigpending)
- .long SYMBOL_NAME(sys_rt_sigtimedwait)
- .long SYMBOL_NAME(sys_rt_sigqueueinfo)
- .long SYMBOL_NAME(sys_rt_sigsuspend)
- .long SYMBOL_NAME(sys_pread) /* 180 */
- .long SYMBOL_NAME(sys_pwrite)
- .long SYMBOL_NAME(sys_chown16)
- .long SYMBOL_NAME(sys_getcwd)
- .long SYMBOL_NAME(sys_capget)
- .long SYMBOL_NAME(sys_capset) /* 185 */
- .long SYMBOL_NAME(sys_sigaltstack)
- .long SYMBOL_NAME(sys_sendfile)
- .long SYMBOL_NAME(sys_ni_syscall) /* streams1 */
- .long SYMBOL_NAME(sys_ni_syscall) /* streams2 */
- .long SYMBOL_NAME(sys_vfork) /* 190 */
- .long SYMBOL_NAME(sys_getrlimit)
- .long SYMBOL_NAME(sys_mmap2)
- .long SYMBOL_NAME(sys_truncate64)
- .long SYMBOL_NAME(sys_ftruncate64)
- .long SYMBOL_NAME(sys_stat64) /* 195 */
- .long SYMBOL_NAME(sys_lstat64)
- .long SYMBOL_NAME(sys_fstat64)
- .long SYMBOL_NAME(sys_lchown)
- .long SYMBOL_NAME(sys_getuid)
- .long SYMBOL_NAME(sys_getgid) /* 200 */
- .long SYMBOL_NAME(sys_geteuid)
- .long SYMBOL_NAME(sys_getegid)
- .long SYMBOL_NAME(sys_setreuid)
- .long SYMBOL_NAME(sys_setregid)
- .long SYMBOL_NAME(sys_getgroups) /* 205 */
- .long SYMBOL_NAME(sys_setgroups)
- .long SYMBOL_NAME(sys_fchown)
- .long SYMBOL_NAME(sys_setresuid)
- .long SYMBOL_NAME(sys_getresuid)
- .long SYMBOL_NAME(sys_setresgid) /* 210 */
- .long SYMBOL_NAME(sys_getresgid)
- .long SYMBOL_NAME(sys_chown)
- .long SYMBOL_NAME(sys_setuid)
- .long SYMBOL_NAME(sys_setgid)
- .long SYMBOL_NAME(sys_setfsuid) /* 215 */
- .long SYMBOL_NAME(sys_setfsgid)
- .long SYMBOL_NAME(sys_pivot_root)
- .long SYMBOL_NAME(sys_mincore)
- .long SYMBOL_NAME(sys_madvise)
- .long SYMBOL_NAME(sys_getdents64) /* 220 */
- .long SYMBOL_NAME(sys_fcntl64)
- .long SYMBOL_NAME(sys_ni_syscall) /* reserved for TUX */
- .long SYMBOL_NAME(sys_ni_syscall) /* Reserved for Security */
- .long SYMBOL_NAME(sys_gettid)
- .long SYMBOL_NAME(sys_readahead) /* 225 */
-
- .rept NR_syscalls-(.-sys_call_table)/4
- .long SYMBOL_NAME(sys_ni_syscall)
- .endr
+++ /dev/null
-
-.text
-#include <linux/config.h>
-#include <linux/threads.h>
-#include <linux/linkage.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-
-/* Offsets in start_info structure */
-#define SHARED_INFO 4
-#define MOD_START 12
-#define MOD_LEN 16
-
-startup_32:
- cld
-
- lss stack_start,%esp
-
- /* Copy initrd somewhere safe before it's clobbered by BSS. */
- mov MOD_LEN(%esi),%ecx
- shr $2,%ecx
- jz 2f /* bail from copy loop if no initrd */
- mov $SYMBOL_NAME(_end),%edi
- add MOD_LEN(%esi),%edi
- mov MOD_START(%esi),%eax
- add MOD_LEN(%esi),%eax
-1: sub $4,%eax
- sub $4,%edi
- mov (%eax),%ebx
- mov %ebx,(%edi)
- loop 1b
- mov %edi,MOD_START(%esi)
-
- /* Clear BSS first so that there are no surprises... */
-2: xorl %eax,%eax
- movl $SYMBOL_NAME(__bss_start),%edi
- movl $SYMBOL_NAME(_end),%ecx
- subl %edi,%ecx
- rep stosb
-
- /* Copy the necessary stuff from start_info structure. */
- /* We need to copy shared_info early, so that sti/cli work */
- mov SHARED_INFO(%esi),%eax
- mov %eax,SYMBOL_NAME(HYPERVISOR_shared_info)
- mov $SYMBOL_NAME(start_info_union),%edi
- mov $128,%ecx
- rep movsl
-
- jmp SYMBOL_NAME(start_kernel)
-
-ENTRY(stack_start)
- .long SYMBOL_NAME(init_task_union)+8192, __KERNEL_DS
-
-.org 0x1000
-ENTRY(empty_zero_page)
-
-.org 0x2000
-ENTRY(cpu0_pte_quicklist)
-
-.org 0x2400
-ENTRY(cpu0_pgd_quicklist)
-
-.org 0x2800
-ENTRY(stext)
-ENTRY(_stext)
+++ /dev/null
-/******************************************************************************
- * hypervisor.c
- *
- * Communication to/from hypervisor.
- *
- * Copyright (c) 2002, K A Fraser
- */
-
-#include <linux/config.h>
-#include <asm/atomic.h>
-#include <linux/irq.h>
-#include <asm/hypervisor.h>
-#include <asm/system.h>
-#include <asm/ptrace.h>
-
-static unsigned long event_mask = 0;
-
-void frobb(void) {}
-
-void do_hypervisor_callback(struct pt_regs *regs)
-{
- unsigned long events, flags;
- shared_info_t *shared = HYPERVISOR_shared_info;
-
- do {
- /* Specialised local_irq_save(). */
- flags = shared->events_enable;
- shared->events_enable = 0;
- barrier();
-
- events = xchg(&shared->events, 0);
- events &= event_mask;
-
- __asm__ __volatile__ (
- " push %1 ;"
- " sub $4,%%esp ;"
- " jmp 2f ;"
- "1: btrl %%eax,%0 ;" /* clear bit */
- " mov %%eax,(%%esp) ;"
- " call do_IRQ ;" /* do_IRQ(event) */
- "2: bsfl %0,%%eax ;" /* %eax == bit # */
- " jnz 1b ;"
- " add $8,%%esp ;"
- /* we use %ebx because it is callee-saved */
- : : "b" (events), "r" (regs)
- /* clobbered by callback function calls */
- : "eax", "ecx", "edx", "memory" );
-
- /* Specialised local_irq_restore(). */
- shared->events_enable = flags;
- barrier();
- }
- while ( shared->events );
-}
-
-
-
-/*
- * Define interface to generic handling in irq.c
- */
-
-static unsigned int startup_hypervisor_event(unsigned int irq)
-{
- set_bit(irq, &event_mask);
- return 0;
-}
-
-static void shutdown_hypervisor_event(unsigned int irq)
-{
- clear_bit(irq, &event_mask);
-}
-
-static void enable_hypervisor_event(unsigned int irq)
-{
- set_bit(irq, &event_mask);
-}
-
-static void disable_hypervisor_event(unsigned int irq)
-{
- clear_bit(irq, &event_mask);
-}
-
-static void ack_hypervisor_event(unsigned int irq)
-{
- if ( !(event_mask & (1<<irq)) )
- {
- printk("Unexpected hypervisor event %d\n", irq);
- atomic_inc(&irq_err_count);
- }
-}
-
-static void end_hypervisor_event(unsigned int irq)
-{
-}
-
-static struct hw_interrupt_type hypervisor_irq_type = {
- "Hypervisor-event",
- startup_hypervisor_event,
- shutdown_hypervisor_event,
- enable_hypervisor_event,
- disable_hypervisor_event,
- ack_hypervisor_event,
- end_hypervisor_event,
- NULL
-};
-
-void __init init_IRQ(void)
-{
- int i;
-
- for ( i = 0; i < NR_IRQS; i++ )
- {
- irq_desc[i].status = IRQ_DISABLED;
- irq_desc[i].action = 0;
- irq_desc[i].depth = 1;
- irq_desc[i].handler = &hypervisor_irq_type;
- }
-}
+++ /dev/null
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/smp.h>
-#include <linux/user.h>
-#include <linux/elfcore.h>
-#include <linux/mca.h>
-#include <linux/sched.h>
-#include <linux/in6.h>
-#include <linux/interrupt.h>
-#include <linux/smp_lock.h>
-#include <linux/pm.h>
-#include <linux/pci.h>
-#include <linux/apm_bios.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/tty.h>
-
-#include <asm/semaphore.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/uaccess.h>
-#include <asm/checksum.h>
-#include <asm/io.h>
-#include <asm/hardirq.h>
-#include <asm/delay.h>
-#include <asm/irq.h>
-#include <asm/mmx.h>
-#include <asm/desc.h>
-#include <asm/pgtable.h>
-#include <asm/pgalloc.h>
-
-extern void dump_thread(struct pt_regs *, struct user *);
-extern spinlock_t rtc_lock;
-
-#ifdef CONFIG_SMP
-extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
-extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
-#endif
-
-#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
-extern struct drive_info_struct drive_info;
-EXPORT_SYMBOL(drive_info);
-#endif
-
-//extern unsigned long get_cmos_time(void);
-
-/* platform dependent support */
-EXPORT_SYMBOL(boot_cpu_data);
-EXPORT_SYMBOL(MCA_bus);
-EXPORT_SYMBOL(__verify_write);
-EXPORT_SYMBOL(dump_thread);
-EXPORT_SYMBOL(dump_fpu);
-EXPORT_SYMBOL(dump_extended_fpu);
-EXPORT_SYMBOL(enable_irq);
-EXPORT_SYMBOL(disable_irq);
-EXPORT_SYMBOL(disable_irq_nosync);
-EXPORT_SYMBOL(probe_irq_mask);
-EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(pm_idle);
-EXPORT_SYMBOL(pm_power_off);
-//EXPORT_SYMBOL(get_cmos_time);
-EXPORT_SYMBOL(apm_info);
-
-#ifdef CONFIG_DEBUG_IOVIRT
-EXPORT_SYMBOL(__io_virt_debug);
-#endif
-
-EXPORT_SYMBOL_NOVERS(__down_failed);
-EXPORT_SYMBOL_NOVERS(__down_failed_interruptible);
-EXPORT_SYMBOL_NOVERS(__down_failed_trylock);
-EXPORT_SYMBOL_NOVERS(__up_wakeup);
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial_copy_generic);
-/* Delay loops */
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__delay);
-EXPORT_SYMBOL(__const_udelay);
-
-EXPORT_SYMBOL_NOVERS(__get_user_1);
-EXPORT_SYMBOL_NOVERS(__get_user_2);
-EXPORT_SYMBOL_NOVERS(__get_user_4);
-
-EXPORT_SYMBOL(strtok);
-EXPORT_SYMBOL(strpbrk);
-EXPORT_SYMBOL(simple_strtol);
-EXPORT_SYMBOL(strstr);
-
-EXPORT_SYMBOL(strncpy_from_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(clear_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__generic_copy_from_user);
-EXPORT_SYMBOL(__generic_copy_to_user);
-EXPORT_SYMBOL(strnlen_user);
-
-#ifdef CONFIG_X86_USE_3DNOW
-EXPORT_SYMBOL(_mmx_memcpy);
-EXPORT_SYMBOL(mmx_clear_page);
-EXPORT_SYMBOL(mmx_copy_page);
-#endif
-
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(cpu_data);
-EXPORT_SYMBOL(kernel_flag);
-EXPORT_SYMBOL(smp_num_cpus);
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL_NOVERS(__write_lock_failed);
-EXPORT_SYMBOL_NOVERS(__read_lock_failed);
-
-/* Global SMP irq stuff */
-EXPORT_SYMBOL(synchronize_irq);
-EXPORT_SYMBOL(global_irq_holder);
-EXPORT_SYMBOL(__global_cli);
-EXPORT_SYMBOL(__global_sti);
-EXPORT_SYMBOL(__global_save_flags);
-EXPORT_SYMBOL(__global_restore_flags);
-EXPORT_SYMBOL(smp_call_function);
-
-/* TLB flushing */
-EXPORT_SYMBOL(flush_tlb_page);
-#endif
-
-#ifdef CONFIG_VT
-EXPORT_SYMBOL(screen_info);
-#endif
-
-EXPORT_SYMBOL(get_wchan);
-
-EXPORT_SYMBOL(rtc_lock);
-
-#undef memcpy
-#undef memset
-extern void * memset(void *,int,__kernel_size_t);
-extern void * memcpy(void *,const void *,__kernel_size_t);
-EXPORT_SYMBOL_NOVERS(memcpy);
-EXPORT_SYMBOL_NOVERS(memset);
-
-#ifdef CONFIG_HAVE_DEC_LOCK
-EXPORT_SYMBOL(atomic_dec_and_lock);
-#endif
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-EXPORT_SYMBOL(do_BUG);
-#endif
+++ /dev/null
-/*
- * linux/arch/i386/kernel/i387.c
- *
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/math_emu.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/ptrace.h>
-#include <asm/uaccess.h>
-
-#define HAVE_HWFP 1
-
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remeber the current task has used the FPU.
- */
-void init_fpu(void)
-{
- __asm__("fninit");
- if ( cpu_has_xmm )
- load_mxcsr(0x1f80);
-
- current->used_math = 1;
-}
-
-/*
- * FPU lazy state save handling.
- */
-
-static inline void __save_init_fpu( struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- asm volatile( "fxsave %0 ; fnclex"
- : "=m" (tsk->thread.i387.fxsave) );
- } else {
- asm volatile( "fnsave %0 ; fwait"
- : "=m" (tsk->thread.i387.fsave) );
- }
- tsk->flags &= ~PF_USEDFPU;
-}
-
-void save_init_fpu( struct task_struct *tsk )
-{
- __save_init_fpu(tsk);
- stts();
-}
-
-void kernel_fpu_begin(void)
-{
- struct task_struct *tsk = current;
-
- if (tsk->flags & PF_USEDFPU) {
- __save_init_fpu(tsk);
- return;
- }
- clts();
-}
-
-void restore_fpu( struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- asm volatile( "fxrstor %0"
- : : "m" (tsk->thread.i387.fxsave) );
- } else {
- asm volatile( "frstor %0"
- : : "m" (tsk->thread.i387.fsave) );
- }
-}
-
-/*
- * FPU tag word conversions.
- */
-
-static inline unsigned short twd_i387_to_fxsr( unsigned short twd )
-{
- unsigned int tmp; /* to avoid 16 bit prefixes in the code */
-
- /* Transform each pair of bits into 01 (valid) or 00 (empty) */
- tmp = ~twd;
- tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
- /* and move the valid bits to the lower byte. */
- tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
- tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
- tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
- return tmp;
-}
-
-static inline unsigned long twd_fxsr_to_i387( struct i387_fxsave_struct *fxsave )
-{
- struct _fpxreg *st = NULL;
- unsigned long twd = (unsigned long) fxsave->twd;
- unsigned long tag;
- unsigned long ret = 0xffff0000;
- int i;
-
-#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16);
-
- for ( i = 0 ; i < 8 ; i++ ) {
- if ( twd & 0x1 ) {
- st = (struct _fpxreg *) FPREG_ADDR( fxsave, i );
-
- switch ( st->exponent & 0x7fff ) {
- case 0x7fff:
- tag = 2; /* Special */
- break;
- case 0x0000:
- if ( !st->significand[0] &&
- !st->significand[1] &&
- !st->significand[2] &&
- !st->significand[3] ) {
- tag = 1; /* Zero */
- } else {
- tag = 2; /* Special */
- }
- break;
- default:
- if ( st->significand[3] & 0x8000 ) {
- tag = 0; /* Valid */
- } else {
- tag = 2; /* Special */
- }
- break;
- }
- } else {
- tag = 3; /* Empty */
- }
- ret |= (tag << (2 * i));
- twd = twd >> 1;
- }
- return ret;
-}
-
-/*
- * FPU state interaction.
- */
-
-unsigned short get_fpu_cwd( struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- return tsk->thread.i387.fxsave.cwd;
- } else {
- return (unsigned short)tsk->thread.i387.fsave.cwd;
- }
-}
-
-unsigned short get_fpu_swd( struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- return tsk->thread.i387.fxsave.swd;
- } else {
- return (unsigned short)tsk->thread.i387.fsave.swd;
- }
-}
-
-unsigned short get_fpu_twd( struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- return tsk->thread.i387.fxsave.twd;
- } else {
- return (unsigned short)tsk->thread.i387.fsave.twd;
- }
-}
-
-unsigned short get_fpu_mxcsr( struct task_struct *tsk )
-{
- if ( cpu_has_xmm ) {
- return tsk->thread.i387.fxsave.mxcsr;
- } else {
- return 0x1f80;
- }
-}
-
-void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd )
-{
- if ( cpu_has_fxsr ) {
- tsk->thread.i387.fxsave.cwd = cwd;
- } else {
- tsk->thread.i387.fsave.cwd = ((long)cwd | 0xffff0000);
- }
-}
-
-void set_fpu_swd( struct task_struct *tsk, unsigned short swd )
-{
- if ( cpu_has_fxsr ) {
- tsk->thread.i387.fxsave.swd = swd;
- } else {
- tsk->thread.i387.fsave.swd = ((long)swd | 0xffff0000);
- }
-}
-
-void set_fpu_twd( struct task_struct *tsk, unsigned short twd )
-{
- if ( cpu_has_fxsr ) {
- tsk->thread.i387.fxsave.twd = twd_i387_to_fxsr(twd);
- } else {
- tsk->thread.i387.fsave.twd = ((long)twd | 0xffff0000);
- }
-}
-
-void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr )
-{
- if ( cpu_has_xmm ) {
- tsk->thread.i387.fxsave.mxcsr = (mxcsr & 0xffbf);
- }
-}
-
-/*
- * FXSR floating point environment conversions.
- */
-
-static inline int convert_fxsr_to_user( struct _fpstate *buf,
- struct i387_fxsave_struct *fxsave )
-{
- unsigned long env[7];
- struct _fpreg *to;
- struct _fpxreg *from;
- int i;
-
- env[0] = (unsigned long)fxsave->cwd | 0xffff0000;
- env[1] = (unsigned long)fxsave->swd | 0xffff0000;
- env[2] = twd_fxsr_to_i387(fxsave);
- env[3] = fxsave->fip;
- env[4] = fxsave->fcs | ((unsigned long)fxsave->fop << 16);
- env[5] = fxsave->foo;
- env[6] = fxsave->fos;
-
- if ( __copy_to_user( buf, env, 7 * sizeof(unsigned long) ) )
- return 1;
-
- to = &buf->_st[0];
- from = (struct _fpxreg *) &fxsave->st_space[0];
- for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
- if ( __copy_to_user( to, from, sizeof(*to) ) )
- return 1;
- }
- return 0;
-}
-
-static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave,
- struct _fpstate *buf )
-{
- unsigned long env[7];
- struct _fpxreg *to;
- struct _fpreg *from;
- int i;
-
- if ( __copy_from_user( env, buf, 7 * sizeof(long) ) )
- return 1;
-
- fxsave->cwd = (unsigned short)(env[0] & 0xffff);
- fxsave->swd = (unsigned short)(env[1] & 0xffff);
- fxsave->twd = twd_i387_to_fxsr((unsigned short)(env[2] & 0xffff));
- fxsave->fip = env[3];
- fxsave->fop = (unsigned short)((env[4] & 0xffff0000) >> 16);
- fxsave->fcs = (env[4] & 0xffff);
- fxsave->foo = env[5];
- fxsave->fos = env[6];
-
- to = (struct _fpxreg *) &fxsave->st_space[0];
- from = &buf->_st[0];
- for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
- if ( __copy_from_user( to, from, sizeof(*from) ) )
- return 1;
- }
- return 0;
-}
-
-/*
- * Signal frame handlers.
- */
-
-static inline int save_i387_fsave( struct _fpstate *buf )
-{
- struct task_struct *tsk = current;
-
- unlazy_fpu( tsk );
- tsk->thread.i387.fsave.status = tsk->thread.i387.fsave.swd;
- if ( __copy_to_user( buf, &tsk->thread.i387.fsave,
- sizeof(struct i387_fsave_struct) ) )
- return -1;
- return 1;
-}
-
-static inline int save_i387_fxsave( struct _fpstate *buf )
-{
- struct task_struct *tsk = current;
- int err = 0;
-
- unlazy_fpu( tsk );
-
- if ( convert_fxsr_to_user( buf, &tsk->thread.i387.fxsave ) )
- return -1;
-
- err |= __put_user( tsk->thread.i387.fxsave.swd, &buf->status );
- err |= __put_user( X86_FXSR_MAGIC, &buf->magic );
- if ( err )
- return -1;
-
- if ( __copy_to_user( &buf->_fxsr_env[0], &tsk->thread.i387.fxsave,
- sizeof(struct i387_fxsave_struct) ) )
- return -1;
- return 1;
-}
-
-int save_i387( struct _fpstate *buf )
-{
- if ( !current->used_math )
- return 0;
-
- /* This will cause a "finit" to be triggered by the next
- * attempted FPU operation by the 'current' process.
- */
- current->used_math = 0;
-
- if ( HAVE_HWFP ) {
- if ( cpu_has_fxsr ) {
- return save_i387_fxsave( buf );
- } else {
- return save_i387_fsave( buf );
- }
- } else {
- return save_i387_soft( ¤t->thread.i387.soft, buf );
- }
-}
-
-static inline int restore_i387_fsave( struct _fpstate *buf )
-{
- struct task_struct *tsk = current;
- clear_fpu( tsk );
- return __copy_from_user( &tsk->thread.i387.fsave, buf,
- sizeof(struct i387_fsave_struct) );
-}
-
-static inline int restore_i387_fxsave( struct _fpstate *buf )
-{
- struct task_struct *tsk = current;
- clear_fpu( tsk );
- if ( __copy_from_user( &tsk->thread.i387.fxsave, &buf->_fxsr_env[0],
- sizeof(struct i387_fxsave_struct) ) )
- return 1;
- /* mxcsr bit 6 and 31-16 must be zero for security reasons */
- tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
- return convert_fxsr_from_user( &tsk->thread.i387.fxsave, buf );
-}
-
-int restore_i387( struct _fpstate *buf )
-{
- int err;
-
- if ( HAVE_HWFP ) {
- if ( cpu_has_fxsr ) {
- err = restore_i387_fxsave( buf );
- } else {
- err = restore_i387_fsave( buf );
- }
- } else {
- err = restore_i387_soft( ¤t->thread.i387.soft, buf );
- }
- current->used_math = 1;
- return err;
-}
-
-/*
- * ptrace request handlers.
- */
-
-static inline int get_fpregs_fsave( struct user_i387_struct *buf,
- struct task_struct *tsk )
-{
- return __copy_to_user( buf, &tsk->thread.i387.fsave,
- sizeof(struct user_i387_struct) );
-}
-
-static inline int get_fpregs_fxsave( struct user_i387_struct *buf,
- struct task_struct *tsk )
-{
- return convert_fxsr_to_user( (struct _fpstate *)buf,
- &tsk->thread.i387.fxsave );
-}
-
-int get_fpregs( struct user_i387_struct *buf, struct task_struct *tsk )
-{
- if ( HAVE_HWFP ) {
- if ( cpu_has_fxsr ) {
- return get_fpregs_fxsave( buf, tsk );
- } else {
- return get_fpregs_fsave( buf, tsk );
- }
- } else {
- return save_i387_soft( &tsk->thread.i387.soft,
- (struct _fpstate *)buf );
- }
-}
-
-static inline int set_fpregs_fsave( struct task_struct *tsk,
- struct user_i387_struct *buf )
-{
- return __copy_from_user( &tsk->thread.i387.fsave, buf,
- sizeof(struct user_i387_struct) );
-}
-
-static inline int set_fpregs_fxsave( struct task_struct *tsk,
- struct user_i387_struct *buf )
-{
- return convert_fxsr_from_user( &tsk->thread.i387.fxsave,
- (struct _fpstate *)buf );
-}
-
-int set_fpregs( struct task_struct *tsk, struct user_i387_struct *buf )
-{
- if ( HAVE_HWFP ) {
- if ( cpu_has_fxsr ) {
- return set_fpregs_fxsave( tsk, buf );
- } else {
- return set_fpregs_fsave( tsk, buf );
- }
- } else {
- return restore_i387_soft( &tsk->thread.i387.soft,
- (struct _fpstate *)buf );
- }
-}
-
-int get_fpxregs( struct user_fxsr_struct *buf, struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- if (__copy_to_user( (void *)buf, &tsk->thread.i387.fxsave,
- sizeof(struct user_fxsr_struct) ))
- return -EFAULT;
- return 0;
- } else {
- return -EIO;
- }
-}
-
-int set_fpxregs( struct task_struct *tsk, struct user_fxsr_struct *buf )
-{
- if ( cpu_has_fxsr ) {
- __copy_from_user( &tsk->thread.i387.fxsave, (void *)buf,
- sizeof(struct user_fxsr_struct) );
- /* mxcsr bit 6 and 31-16 must be zero for security reasons */
- tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
- return 0;
- } else {
- return -EIO;
- }
-}
-
-/*
- * FPU state for core dumps.
- */
-
-static inline void copy_fpu_fsave( struct task_struct *tsk,
- struct user_i387_struct *fpu )
-{
- memcpy( fpu, &tsk->thread.i387.fsave,
- sizeof(struct user_i387_struct) );
-}
-
-static inline void copy_fpu_fxsave( struct task_struct *tsk,
- struct user_i387_struct *fpu )
-{
- unsigned short *to;
- unsigned short *from;
- int i;
-
- memcpy( fpu, &tsk->thread.i387.fxsave, 7 * sizeof(long) );
-
- to = (unsigned short *)&fpu->st_space[0];
- from = (unsigned short *)&tsk->thread.i387.fxsave.st_space[0];
- for ( i = 0 ; i < 8 ; i++, to += 5, from += 8 ) {
- memcpy( to, from, 5 * sizeof(unsigned short) );
- }
-}
-
-int dump_fpu( struct pt_regs *regs, struct user_i387_struct *fpu )
-{
- int fpvalid;
- struct task_struct *tsk = current;
-
- fpvalid = tsk->used_math;
- if ( fpvalid ) {
- unlazy_fpu( tsk );
- if ( cpu_has_fxsr ) {
- copy_fpu_fxsave( tsk, fpu );
- } else {
- copy_fpu_fsave( tsk, fpu );
- }
- }
-
- return fpvalid;
-}
-
-int dump_extended_fpu( struct pt_regs *regs, struct user_fxsr_struct *fpu )
-{
- int fpvalid;
- struct task_struct *tsk = current;
-
- fpvalid = tsk->used_math && cpu_has_fxsr;
- if ( fpvalid ) {
- unlazy_fpu( tsk );
- memcpy( fpu, &tsk->thread.i387.fxsave,
- sizeof(struct user_fxsr_struct) );
- }
-
- return fpvalid;
-}
+++ /dev/null
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-
-static struct fs_struct init_fs = INIT_FS;
-static struct files_struct init_files = INIT_FILES;
-static struct signal_struct init_signals = INIT_SIGNALS;
-struct mm_struct init_mm = INIT_MM(init_mm);
-
-/*
- * Initial task structure.
- *
- * We need to make sure that this is 8192-byte aligned due to the
- * way process stacks are handled. This is done by having a special
- * "init_task" linker map entry..
- */
-union task_union init_task_union
- __attribute__((__section__(".data.init_task"))) =
- { INIT_TASK(init_task_union.task) };
-
-/*
- * per-CPU TSS segments. Threads are completely 'soft' on Linux,
- * no more per-task TSS's. The TSS size is kept cacheline-aligned
- * so they are allowed to end up in the .data.cacheline_aligned
- * section. Since TSS's are completely CPU-local, we want them
- * on exact cacheline boundaries, to eliminate cacheline ping-pong.
- */
-struct tss_struct init_tss[NR_CPUS] __cacheline_aligned = { [0 ... NR_CPUS-1] = INIT_TSS };
-
+++ /dev/null
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/types.h>
-#include <linux/stddef.h>
-
-
-asmlinkage int sys_ioperm(unsigned long from, unsigned long num, int turn_on)
-{
- /* No IO permission! */
- return -EPERM;
-}
-
-
-asmlinkage int sys_iopl(unsigned long unused)
-{
- /* The hypervisor won't allow it! */
- return -EPERM;
-}
+++ /dev/null
-/*
- * linux/arch/i386/kernel/irq.c
- *
- * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
- *
- * This file contains the code used by various IRQ handling routines:
- * asking for different IRQ's should be done through these routines
- * instead of just grabbing them. Thus setups with different IRQ numbers
- * shouldn't result in any weird surprises, and installing new handlers
- * should be easier.
- */
-
-/*
- * (mostly architecture independent, will move to kernel/irq.c in 2.5.)
- *
- * IRQs are in fact implemented a bit like signal handlers for the kernel.
- * Naturally it's not a 1:1 relation, but there are similarities.
- */
-
-#include <linux/config.h>
-#include <linux/ptrace.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/smp_lock.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/irq.h>
-#include <linux/proc_fs.h>
-#include <linux/kdb.h>
-
-#include <asm/atomic.h>
-#include <asm/io.h>
-#include <asm/smp.h>
-#include <asm/system.h>
-#include <asm/bitops.h>
-#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
-#include <asm/delay.h>
-#include <asm/desc.h>
-#include <asm/irq.h>
-
-
-
-/*
- * Linux has a controller-independent x86 interrupt architecture.
- * every controller has a 'controller-template', that is used
- * by the main code to do the right thing. Each driver-visible
- * interrupt source is transparently wired to the apropriate
- * controller. Thus drivers need not be aware of the
- * interrupt-controller.
- *
- * Various interrupt controllers we handle: 8259 PIC, SMP IO-APIC,
- * PIIX4's internal 8259 PIC and SGI's Visual Workstation Cobalt (IO-)APIC.
- * (IO-APICs assumed to be messaging to Pentium local-APICs)
- *
- * the code is designed to be easily extended with new/different
- * interrupt controllers, without having to do assembly magic.
- */
-
-/*
- * Controller mappings for all interrupt sources:
- */
-irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned =
- { [0 ... NR_IRQS-1] = { 0, &no_irq_type, NULL, 0, SPIN_LOCK_UNLOCKED}};
-
-static void register_irq_proc (unsigned int irq);
-
-/*
- * Special irq handlers.
- */
-
-void no_action(int cpl, void *dev_id, struct pt_regs *regs) { }
-
-/*
- * Generic no controller code
- */
-
-static void enable_none(unsigned int irq) { }
-static unsigned int startup_none(unsigned int irq) { return 0; }
-static void disable_none(unsigned int irq) { }
-static void ack_none(unsigned int irq)
-{
- printk("unexpected IRQ trap at vector %02x\n", irq);
-}
-
-/* startup is the same as "enable", shutdown is same as "disable" */
-#define shutdown_none disable_none
-#define end_none enable_none
-
-struct hw_interrupt_type no_irq_type = {
- "none",
- startup_none,
- shutdown_none,
- enable_none,
- disable_none,
- ack_none,
- end_none
-};
-
-atomic_t irq_err_count;
-#ifdef CONFIG_X86_IO_APIC
-#ifdef APIC_MISMATCH_DEBUG
-atomic_t irq_mis_count;
-#endif
-#endif
-
-/*
- * Generic, controller-independent functions:
- */
-
-int get_irq_list(char *buf)
-{
- int i, j;
- struct irqaction * action;
- char *p = buf;
-
- p += sprintf(p, " ");
- for (j=0; j<smp_num_cpus; j++)
- p += sprintf(p, "CPU%d ",j);
- *p++ = '\n';
-
- for (i = 0 ; i < NR_IRQS ; i++) {
- action = irq_desc[i].action;
- if (!action)
- continue;
- p += sprintf(p, "%3d: ",i);
-#ifndef CONFIG_SMP
- p += sprintf(p, "%10u ", kstat_irqs(i));
-#else
- for (j = 0; j < smp_num_cpus; j++)
- p += sprintf(p, "%10u ",
- kstat.irqs[cpu_logical_map(j)][i]);
-#endif
- p += sprintf(p, " %14s", irq_desc[i].handler->typename);
- p += sprintf(p, " %s", action->name);
-
- for (action=action->next; action; action = action->next)
- p += sprintf(p, ", %s", action->name);
- *p++ = '\n';
- }
- p += sprintf(p, "NMI: ");
- for (j = 0; j < smp_num_cpus; j++)
- p += sprintf(p, "%10u ",
- nmi_count(cpu_logical_map(j)));
- p += sprintf(p, "\n");
-#if CONFIG_X86_LOCAL_APIC
- p += sprintf(p, "LOC: ");
- for (j = 0; j < smp_num_cpus; j++)
- p += sprintf(p, "%10u ",
- apic_timer_irqs[cpu_logical_map(j)]);
- p += sprintf(p, "\n");
-#endif
- p += sprintf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
-#ifdef CONFIG_X86_IO_APIC
-#ifdef APIC_MISMATCH_DEBUG
- p += sprintf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
-#endif
-#endif
- return p - buf;
-}
-
-
-/*
- * Global interrupt locks for SMP. Allow interrupts to come in on any
- * CPU, yet make cli/sti act globally to protect critical regions..
- */
-
-#ifdef CONFIG_SMP
-unsigned char global_irq_holder = NO_PROC_ID;
-unsigned volatile long global_irq_lock; /* pendantic: long for set_bit --RR */
-
-extern void show_stack(unsigned long* esp);
-
-static void show(char * str)
-{
- int i;
- int cpu = smp_processor_id();
-
- printk("\n%s, CPU %d:\n", str, cpu);
- printk("irq: %d [",irqs_running());
- for(i=0;i < smp_num_cpus;i++)
- printk(" %d",local_irq_count(i));
- printk(" ]\nbh: %d [",spin_is_locked(&global_bh_lock) ? 1 : 0);
- for(i=0;i < smp_num_cpus;i++)
- printk(" %d",local_bh_count(i));
-
- printk(" ]\nStack dumps:");
- for(i = 0; i < smp_num_cpus; i++) {
- unsigned long esp;
- if (i == cpu)
- continue;
- printk("\nCPU %d:",i);
- esp = init_tss[i].esp0;
- if (!esp) {
- /* tss->esp0 is set to NULL in cpu_init(),
- * it's initialized when the cpu returns to user
- * space. -- manfreds
- */
- printk(" <unknown> ");
- continue;
- }
- esp &= ~(THREAD_SIZE-1);
- esp += sizeof(struct task_struct);
- show_stack((void*)esp);
- }
- printk("\nCPU %d:",cpu);
- show_stack(NULL);
- printk("\n");
-}
-
-#define MAXCOUNT 100000000
-
-/*
- * I had a lockup scenario where a tight loop doing
- * spin_unlock()/spin_lock() on CPU#1 was racing with
- * spin_lock() on CPU#0. CPU#0 should have noticed spin_unlock(), but
- * apparently the spin_unlock() information did not make it
- * through to CPU#0 ... nasty, is this by design, do we have to limit
- * 'memory update oscillation frequency' artificially like here?
- *
- * Such 'high frequency update' races can be avoided by careful design, but
- * some of our major constructs like spinlocks use similar techniques,
- * it would be nice to clarify this issue. Set this define to 0 if you
- * want to check whether your system freezes. I suspect the delay done
- * by SYNC_OTHER_CORES() is in correlation with 'snooping latency', but
- * i thought that such things are guaranteed by design, since we use
- * the 'LOCK' prefix.
- */
-#define SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND 0
-
-#if SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND
-# define SYNC_OTHER_CORES(x) udelay(x+1)
-#else
-/*
- * We have to allow irqs to arrive between __sti and __cli
- */
-# define SYNC_OTHER_CORES(x) __asm__ __volatile__ ("nop")
-#endif
-
-static inline void wait_on_irq(int cpu)
-{
- int count = MAXCOUNT;
-
- for (;;) {
-
- /*
- * Wait until all interrupts are gone. Wait
- * for bottom half handlers unless we're
- * already executing in one..
- */
- if (!irqs_running())
- if (local_bh_count(cpu) || !spin_is_locked(&global_bh_lock))
- break;
-
- /* Duh, we have to loop. Release the lock to avoid deadlocks */
- clear_bit(0,&global_irq_lock);
-
- for (;;) {
- if (!--count) {
- show("wait_on_irq");
- count = ~0;
- }
- __sti();
- SYNC_OTHER_CORES(cpu);
- __cli();
- if (irqs_running())
- continue;
- if (global_irq_lock)
- continue;
- if (!local_bh_count(cpu) && spin_is_locked(&global_bh_lock))
- continue;
- if (!test_and_set_bit(0,&global_irq_lock))
- break;
- }
- }
-}
-
-/*
- * This is called when we want to synchronize with
- * interrupts. We may for example tell a device to
- * stop sending interrupts: but to make sure there
- * are no interrupts that are executing on another
- * CPU we need to call this function.
- */
-void synchronize_irq(void)
-{
- if (irqs_running()) {
- /* Stupid approach */
- cli();
- sti();
- }
-}
-
-static inline void get_irqlock(int cpu)
-{
-#ifdef CONFIG_KDB
- static int kdb_rate;
- if (KDB_IS_RUNNING() && kdb_rate++ < 10)
- kdb_printf("Warning: get_irqlock on cpu %d while kdb is running, may hang\n", smp_processor_id());
-#endif /* CONFIG_KDB */
- if (test_and_set_bit(0,&global_irq_lock)) {
- /* do we already hold the lock? */
- if ((unsigned char) cpu == global_irq_holder)
- return;
- /* Uhhuh.. Somebody else got it. Wait.. */
- do {
- do {
- rep_nop();
- } while (test_bit(0,&global_irq_lock));
- } while (test_and_set_bit(0,&global_irq_lock));
- }
- /*
- * We also to make sure that nobody else is running
- * in an interrupt context.
- */
- wait_on_irq(cpu);
-
- /*
- * Ok, finally..
- */
- global_irq_holder = cpu;
-}
-
-void __global_cli(void)
-{
- panic("__global_cli");
-}
-
-void __global_sti(void)
-{
- panic("__global_sti");
-}
-
-/*
- * SMP flags value to restore to:
- * 0 - global cli
- * 1 - global sti
- * 2 - local cli
- * 3 - local sti
- */
-unsigned long __global_save_flags(void)
-{
- panic("__global_save_flags");
-}
-
-void __global_restore_flags(unsigned long flags)
-{
- panic("__global_restore_flags");
-}
-
-#endif
-
-/*
- * This should really return information about whether
- * we should do bottom half handling etc. Right now we
- * end up _always_ checking the bottom half, which is a
- * waste of time and is not what some drivers would
- * prefer.
- */
-int handle_IRQ_event(unsigned int irq, struct pt_regs * regs, struct irqaction * action)
-{
- int status;
- int cpu = smp_processor_id();
-
- irq_enter(cpu, irq);
-
- status = 1; /* Force the "do bottom halves" bit */
-
- if (!(action->flags & SA_INTERRUPT))
- __sti();
-
- do {
- status |= action->flags;
- action->handler(irq, action->dev_id, regs);
- action = action->next;
- } while (action);
- if (status & SA_SAMPLE_RANDOM)
- add_interrupt_randomness(irq);
- __cli();
-
- irq_exit(cpu, irq);
-
- return status;
-}
-
-/*
- * Generic enable/disable code: this just calls
- * down into the PIC-specific version for the actual
- * hardware disable after having gotten the irq
- * controller lock.
- */
-
-/**
- * disable_irq_nosync - disable an irq without waiting
- * @irq: Interrupt to disable
- *
- * Disable the selected interrupt line. Disables and Enables are
- * nested.
- * Unlike disable_irq(), this function does not ensure existing
- * instances of the IRQ handler have completed before returning.
- *
- * This function may be called from IRQ context.
- */
-
-inline void disable_irq_nosync(unsigned int irq)
-{
- irq_desc_t *desc = irq_desc + irq;
- unsigned long flags;
-
- spin_lock_irqsave(&desc->lock, flags);
- if (!desc->depth++) {
- desc->status |= IRQ_DISABLED;
- desc->handler->disable(irq);
- }
- spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- * disable_irq - disable an irq and wait for completion
- * @irq: Interrupt to disable
- *
- * Disable the selected interrupt line. Enables and Disables are
- * nested.
- * This function waits for any pending IRQ handlers for this interrupt
- * to complete before returning. If you use this function while
- * holding a resource the IRQ handler may need you will deadlock.
- *
- * This function may be called - with care - from IRQ context.
- */
-
-void disable_irq(unsigned int irq)
-{
- disable_irq_nosync(irq);
-
- if (!local_irq_count(smp_processor_id())) {
- do {
- barrier();
- cpu_relax();
- } while (irq_desc[irq].status & IRQ_INPROGRESS);
- }
-}
-
-/**
- * enable_irq - enable handling of an irq
- * @irq: Interrupt to enable
- *
- * Undoes the effect of one call to disable_irq(). If this
- * matches the last disable, processing of interrupts on this
- * IRQ line is re-enabled.
- *
- * This function may be called from IRQ context.
- */
-
-void enable_irq(unsigned int irq)
-{
- irq_desc_t *desc = irq_desc + irq;
- unsigned long flags;
-
- spin_lock_irqsave(&desc->lock, flags);
- switch (desc->depth) {
- case 1: {
- unsigned int status = desc->status & ~IRQ_DISABLED;
- desc->status = status;
- if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
- desc->status = status | IRQ_REPLAY;
- hw_resend_irq(desc->handler,irq);
- }
- desc->handler->enable(irq);
- /* fall-through */
- }
- default:
- desc->depth--;
- break;
- case 0:
- printk("enable_irq(%u) unbalanced from %p\n", irq,
- __builtin_return_address(0));
- }
- spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-asmlinkage unsigned int do_IRQ(int irq, struct pt_regs *regs)
-{
- /*
- * We ack quickly, we don't want the irq controller
- * thinking we're snobs just because some other CPU has
- * disabled global interrupts (we have already done the
- * INT_ACK cycles, it's too late to try to pretend to the
- * controller that we aren't taking the interrupt).
- *
- * 0 return value means that this irq is already being
- * handled by some other CPU. (or is disabled)
- */
- int cpu = smp_processor_id();
- irq_desc_t *desc = irq_desc + irq;
- struct irqaction * action;
- unsigned int status;
-
- kstat.irqs[cpu][irq]++;
- spin_lock(&desc->lock);
- desc->handler->ack(irq);
- /*
- REPLAY is when Linux resends an IRQ that was dropped earlier
- WAITING is used by probe to mark irqs that are being tested
- */
- status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
- status |= IRQ_PENDING; /* we _want_ to handle it */
-
- /*
- * If the IRQ is disabled for whatever reason, we cannot
- * use the action we have.
- */
- action = NULL;
- if (!(status & (IRQ_DISABLED | IRQ_INPROGRESS))) {
- action = desc->action;
- status &= ~IRQ_PENDING; /* we commit to handling */
- status |= IRQ_INPROGRESS; /* we are handling it */
- }
- desc->status = status;
-
- /*
- * If there is no IRQ handler or it was disabled, exit early.
- Since we set PENDING, if another processor is handling
- a different instance of this same irq, the other processor
- will take care of it.
- */
- if (!action)
- goto out;
-
- /*
- * Edge triggered interrupts need to remember
- * pending events.
- * This applies to any hw interrupts that allow a second
- * instance of the same irq to arrive while we are in do_IRQ
- * or in the handler. But the code here only handles the _second_
- * instance of the irq, not the third or fourth. So it is mostly
- * useful for irq hardware that does not mask cleanly in an
- * SMP environment.
- */
- for (;;) {
- spin_unlock(&desc->lock);
- handle_IRQ_event(irq, regs, action);
- spin_lock(&desc->lock);
-
- if (!(desc->status & IRQ_PENDING))
- break;
- desc->status &= ~IRQ_PENDING;
- }
- desc->status &= ~IRQ_INPROGRESS;
-out:
- /*
- * The ->end() handler has to deal with interrupts which got
- * disabled while the handler was running.
- */
- desc->handler->end(irq);
- spin_unlock(&desc->lock);
-
- if (softirq_pending(cpu))
- do_softirq();
-
- return 1;
-}
-
-/**
- * request_irq - allocate an interrupt line
- * @irq: Interrupt line to allocate
- * @handler: Function to be called when the IRQ occurs
- * @irqflags: Interrupt type flags
- * @devname: An ascii name for the claiming device
- * @dev_id: A cookie passed back to the handler function
- *
- * This call allocates interrupt resources and enables the
- * interrupt line and IRQ handling. From the point this
- * call is made your handler function may be invoked. Since
- * your handler function must clear any interrupt the board
- * raises, you must take care both to initialise your hardware
- * and to set up the interrupt handler in the right order.
- *
- * Dev_id must be globally unique. Normally the address of the
- * device data structure is used as the cookie. Since the handler
- * receives this value it makes sense to use it.
- *
- * If your interrupt is shared you must pass a non NULL dev_id
- * as this is required when freeing the interrupt.
- *
- * Flags:
- *
- * SA_SHIRQ Interrupt is shared
- *
- * SA_INTERRUPT Disable local interrupts while processing
- *
- * SA_SAMPLE_RANDOM The interrupt can be used for entropy
- *
- */
-
-int request_irq(unsigned int irq,
- void (*handler)(int, void *, struct pt_regs *),
- unsigned long irqflags,
- const char * devname,
- void *dev_id)
-{
- int retval;
- struct irqaction * action;
-
-#if 1
- /*
- * Sanity-check: shared interrupts should REALLY pass in
- * a real dev-ID, otherwise we'll have trouble later trying
- * to figure out which interrupt is which (messes up the
- * interrupt freeing logic etc).
- */
- if (irqflags & SA_SHIRQ) {
- if (!dev_id)
- printk("Bad boy: %s (at 0x%x) called us without a dev_id!\n", devname, (&irq)[-1]);
- }
-#endif
-
- if (irq >= NR_IRQS)
- return -EINVAL;
- if (!handler)
- return -EINVAL;
-
- action = (struct irqaction *)
- kmalloc(sizeof(struct irqaction), GFP_KERNEL);
- if (!action)
- return -ENOMEM;
-
- action->handler = handler;
- action->flags = irqflags;
- action->mask = 0;
- action->name = devname;
- action->next = NULL;
- action->dev_id = dev_id;
-
- retval = setup_irq(irq, action);
- if (retval)
- kfree(action);
- return retval;
-}
-
-/**
- * free_irq - free an interrupt
- * @irq: Interrupt line to free
- * @dev_id: Device identity to free
- *
- * Remove an interrupt handler. The handler is removed and if the
- * interrupt line is no longer in use by any driver it is disabled.
- * On a shared IRQ the caller must ensure the interrupt is disabled
- * on the card it drives before calling this function. The function
- * does not return until any executing interrupts for this IRQ
- * have completed.
- *
- * This function may be called from interrupt context.
- *
- * Bugs: Attempting to free an irq in a handler for the same irq hangs
- * the machine.
- */
-
-void free_irq(unsigned int irq, void *dev_id)
-{
- irq_desc_t *desc;
- struct irqaction **p;
- unsigned long flags;
-
- if (irq >= NR_IRQS)
- return;
-
- desc = irq_desc + irq;
- spin_lock_irqsave(&desc->lock,flags);
- p = &desc->action;
- for (;;) {
- struct irqaction * action = *p;
- if (action) {
- struct irqaction **pp = p;
- p = &action->next;
- if (action->dev_id != dev_id)
- continue;
-
- /* Found it - now remove it from the list of entries */
- *pp = action->next;
- if (!desc->action) {
- desc->status |= IRQ_DISABLED;
- desc->handler->shutdown(irq);
- }
- spin_unlock_irqrestore(&desc->lock,flags);
-
-#ifdef CONFIG_SMP
- /* Wait to make sure it's not being used on another CPU */
- while (desc->status & IRQ_INPROGRESS) {
- barrier();
- cpu_relax();
- }
-#endif
- kfree(action);
- return;
- }
- printk("Trying to free free IRQ%d\n",irq);
- spin_unlock_irqrestore(&desc->lock,flags);
- return;
- }
-}
-
-/*
- * IRQ autodetection code..
- *
- * This depends on the fact that any interrupt that
- * comes in on to an unassigned handler will get stuck
- * with "IRQ_WAITING" cleared and the interrupt
- * disabled.
- */
-
-static DECLARE_MUTEX(probe_sem);
-
-/**
- * probe_irq_on - begin an interrupt autodetect
- *
- * Commence probing for an interrupt. The interrupts are scanned
- * and a mask of potential interrupt lines is returned.
- *
- */
-
-unsigned long probe_irq_on(void)
-{
- unsigned int i;
- irq_desc_t *desc;
- unsigned long val;
- unsigned long delay;
-
- down(&probe_sem);
- /*
- * something may have generated an irq long ago and we want to
- * flush such a longstanding irq before considering it as spurious.
- */
- for (i = NR_IRQS-1; i > 0; i--) {
- desc = irq_desc + i;
-
- spin_lock_irq(&desc->lock);
- if (!irq_desc[i].action)
- irq_desc[i].handler->startup(i);
- spin_unlock_irq(&desc->lock);
- }
-
- /* Wait for longstanding interrupts to trigger. */
- for (delay = jiffies + HZ/50; time_after(delay, jiffies); )
- /* about 20ms delay */ synchronize_irq();
-
- /*
- * enable any unassigned irqs
- * (we must startup again here because if a longstanding irq
- * happened in the previous stage, it may have masked itself)
- */
- for (i = NR_IRQS-1; i > 0; i--) {
- desc = irq_desc + i;
-
- spin_lock_irq(&desc->lock);
- if (!desc->action) {
- desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
- if (desc->handler->startup(i))
- desc->status |= IRQ_PENDING;
- }
- spin_unlock_irq(&desc->lock);
- }
-
- /*
- * Wait for spurious interrupts to trigger
- */
- for (delay = jiffies + HZ/10; time_after(delay, jiffies); )
- /* about 100ms delay */ synchronize_irq();
-
- /*
- * Now filter out any obviously spurious interrupts
- */
- val = 0;
- for (i = 0; i < NR_IRQS; i++) {
- irq_desc_t *desc = irq_desc + i;
- unsigned int status;
-
- spin_lock_irq(&desc->lock);
- status = desc->status;
-
- if (status & IRQ_AUTODETECT) {
- /* It triggered already - consider it spurious. */
- if (!(status & IRQ_WAITING)) {
- desc->status = status & ~IRQ_AUTODETECT;
- desc->handler->shutdown(i);
- } else
- if (i < 32)
- val |= 1 << i;
- }
- spin_unlock_irq(&desc->lock);
- }
-
- return val;
-}
-
-/*
- * Return a mask of triggered interrupts (this
- * can handle only legacy ISA interrupts).
- */
-
-/**
- * probe_irq_mask - scan a bitmap of interrupt lines
- * @val: mask of interrupts to consider
- *
- * Scan the ISA bus interrupt lines and return a bitmap of
- * active interrupts. The interrupt probe logic state is then
- * returned to its previous value.
- *
- * Note: we need to scan all the irq's even though we will
- * only return ISA irq numbers - just so that we reset them
- * all to a known state.
- */
-unsigned int probe_irq_mask(unsigned long val)
-{
- int i;
- unsigned int mask;
-
- mask = 0;
- for (i = 0; i < NR_IRQS; i++) {
- irq_desc_t *desc = irq_desc + i;
- unsigned int status;
-
- spin_lock_irq(&desc->lock);
- status = desc->status;
-
- if (status & IRQ_AUTODETECT) {
- if (i < 16 && !(status & IRQ_WAITING))
- mask |= 1 << i;
-
- desc->status = status & ~IRQ_AUTODETECT;
- desc->handler->shutdown(i);
- }
- spin_unlock_irq(&desc->lock);
- }
- up(&probe_sem);
-
- return mask & val;
-}
-
-/*
- * Return the one interrupt that triggered (this can
- * handle any interrupt source).
- */
-
-/**
- * probe_irq_off - end an interrupt autodetect
- * @val: mask of potential interrupts (unused)
- *
- * Scans the unused interrupt lines and returns the line which
- * appears to have triggered the interrupt. If no interrupt was
- * found then zero is returned. If more than one interrupt is
- * found then minus the first candidate is returned to indicate
- * their is doubt.
- *
- * The interrupt probe logic state is returned to its previous
- * value.
- *
- * BUGS: When used in a module (which arguably shouldnt happen)
- * nothing prevents two IRQ probe callers from overlapping. The
- * results of this are non-optimal.
- */
-
-int probe_irq_off(unsigned long val)
-{
- int i, irq_found, nr_irqs;
-
- nr_irqs = 0;
- irq_found = 0;
- for (i = 0; i < NR_IRQS; i++) {
- irq_desc_t *desc = irq_desc + i;
- unsigned int status;
-
- spin_lock_irq(&desc->lock);
- status = desc->status;
-
- if (status & IRQ_AUTODETECT) {
- if (!(status & IRQ_WAITING)) {
- if (!nr_irqs)
- irq_found = i;
- nr_irqs++;
- }
- desc->status = status & ~IRQ_AUTODETECT;
- desc->handler->shutdown(i);
- }
- spin_unlock_irq(&desc->lock);
- }
- up(&probe_sem);
-
- if (nr_irqs > 1)
- irq_found = -irq_found;
- return irq_found;
-}
-
-/* this was setup_x86_irq but it seems pretty generic */
-int setup_irq(unsigned int irq, struct irqaction * new)
-{
- int shared = 0;
- unsigned long flags;
- struct irqaction *old, **p;
- irq_desc_t *desc = irq_desc + irq;
-
- /*
- * Some drivers like serial.c use request_irq() heavily,
- * so we have to be careful not to interfere with a
- * running system.
- */
- if (new->flags & SA_SAMPLE_RANDOM) {
- /*
- * This function might sleep, we want to call it first,
- * outside of the atomic block.
- * Yes, this might clear the entropy pool if the wrong
- * driver is attempted to be loaded, without actually
- * installing a new handler, but is this really a problem,
- * only the sysadmin is able to do this.
- */
- rand_initialize_irq(irq);
- }
-
- /*
- * The following block of code has to be executed atomically
- */
- spin_lock_irqsave(&desc->lock,flags);
- p = &desc->action;
- if ((old = *p) != NULL) {
- /* Can't share interrupts unless both agree to */
- if (!(old->flags & new->flags & SA_SHIRQ)) {
- spin_unlock_irqrestore(&desc->lock,flags);
- return -EBUSY;
- }
-
- /* add new interrupt at end of irq queue */
- do {
- p = &old->next;
- old = *p;
- } while (old);
- shared = 1;
- }
-
- *p = new;
-
- if (!shared) {
- desc->depth = 0;
- desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | IRQ_WAITING);
- desc->handler->startup(irq);
- }
- spin_unlock_irqrestore(&desc->lock,flags);
-
- register_irq_proc(irq);
- return 0;
-}
-
-static struct proc_dir_entry * root_irq_dir;
-static struct proc_dir_entry * irq_dir [NR_IRQS];
-
-#define HEX_DIGITS 8
-
-static unsigned int parse_hex_value (const char *buffer,
- unsigned long count, unsigned long *ret)
-{
- unsigned char hexnum [HEX_DIGITS];
- unsigned long value;
- int i;
-
- if (!count)
- return -EINVAL;
- if (count > HEX_DIGITS)
- count = HEX_DIGITS;
- if (copy_from_user(hexnum, buffer, count))
- return -EFAULT;
-
- /*
- * Parse the first 8 characters as a hex string, any non-hex char
- * is end-of-string. '00e1', 'e1', '00E1', 'E1' are all the same.
- */
- value = 0;
-
- for (i = 0; i < count; i++) {
- unsigned int c = hexnum[i];
-
- switch (c) {
- case '0' ... '9': c -= '0'; break;
- case 'a' ... 'f': c -= 'a'-10; break;
- case 'A' ... 'F': c -= 'A'-10; break;
- default:
- goto out;
- }
- value = (value << 4) | c;
- }
-out:
- *ret = value;
- return 0;
-}
-
-#if CONFIG_SMP
-
-static struct proc_dir_entry * smp_affinity_entry [NR_IRQS];
-
-static unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL };
-static int irq_affinity_read_proc (char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- if (count < HEX_DIGITS+1)
- return -EINVAL;
- return sprintf (page, "%08lx\n", irq_affinity[(long)data]);
-}
-
-static int irq_affinity_write_proc (struct file *file, const char *buffer,
- unsigned long count, void *data)
-{
- int irq = (long) data, full_count = count, err;
- unsigned long new_value;
-
- if (!irq_desc[irq].handler->set_affinity)
- return -EIO;
-
- err = parse_hex_value(buffer, count, &new_value);
-
- /*
- * Do not allow disabling IRQs completely - it's a too easy
- * way to make the system unusable accidentally :-) At least
- * one online CPU still has to be targeted.
- */
- if (!(new_value & cpu_online_map))
- return -EINVAL;
-
- irq_affinity[irq] = new_value;
- irq_desc[irq].handler->set_affinity(irq, new_value);
-
- return full_count;
-}
-
-#endif
-
-static int prof_cpu_mask_read_proc (char *page, char **start, off_t off,
- int count, int *eof, void *data)
-{
- unsigned long *mask = (unsigned long *) data;
- if (count < HEX_DIGITS+1)
- return -EINVAL;
- return sprintf (page, "%08lx\n", *mask);
-}
-
-static int prof_cpu_mask_write_proc (struct file *file, const char *buffer,
- unsigned long count, void *data)
-{
- unsigned long *mask = (unsigned long *) data, full_count = count, err;
- unsigned long new_value;
-
- err = parse_hex_value(buffer, count, &new_value);
- if (err)
- return err;
-
- *mask = new_value;
- return full_count;
-}
-
-#define MAX_NAMELEN 10
-
-static void register_irq_proc (unsigned int irq)
-{
- char name [MAX_NAMELEN];
-
- if (!root_irq_dir || (irq_desc[irq].handler == &no_irq_type) ||
- irq_dir[irq])
- return;
-
- memset(name, 0, MAX_NAMELEN);
- sprintf(name, "%d", irq);
-
- /* create /proc/irq/1234 */
- irq_dir[irq] = proc_mkdir(name, root_irq_dir);
-
-#if CONFIG_SMP
- {
- struct proc_dir_entry *entry;
-
- /* create /proc/irq/1234/smp_affinity */
- entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]);
-
- if (entry) {
- entry->nlink = 1;
- entry->data = (void *)(long)irq;
- entry->read_proc = irq_affinity_read_proc;
- entry->write_proc = irq_affinity_write_proc;
- }
-
- smp_affinity_entry[irq] = entry;
- }
-#endif
-}
-
-unsigned long prof_cpu_mask = -1;
-
-void init_irq_proc (void)
-{
- struct proc_dir_entry *entry;
- int i;
-
- /* create /proc/irq */
- root_irq_dir = proc_mkdir("irq", 0);
-
- /* create /proc/irq/prof_cpu_mask */
- entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
-
- if (!entry)
- return;
-
- entry->nlink = 1;
- entry->data = (void *)&prof_cpu_mask;
- entry->read_proc = prof_cpu_mask_read_proc;
- entry->write_proc = prof_cpu_mask_write_proc;
-
- /*
- * Create entries for all existing IRQs.
- */
- for (i = 0; i < NR_IRQS; i++)
- register_irq_proc(i);
-}
-
+++ /dev/null
-/*
- * linux/kernel/ldt.c
- *
- * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
- * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-
-/*
- * XXX KAF (28/7/02): This stuff is only used for DOS emulation, and is
- * the default way of finding current TCB in linuxthreads. Supporting
- * table update svia the hypervisor is feasible, but a hassle: for now,
- * recompiling linuxthreads is the most sensible option.
- *
- * Oh, this may become an issue depending on what JVM we use for
- * running the xeno-daemon.
- */
-
-asmlinkage int sys_modify_ldt(int func, void *ptr, unsigned long bytecount)
-{
- return -ENOSYS;
-}
+++ /dev/null
-/*
- * linux/arch/i386/kernel/process.c
- *
- * Copyright (C) 1995 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-
-/*
- * This file handles the architecture-dependent parts of process handling..
- */
-
-#define __KERNEL_SYSCALLS__
-#include <stdarg.h>
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-#include <linux/user.h>
-#include <linux/a.out.h>
-#include <linux/interrupt.h>
-#include <linux/config.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/mc146818rtc.h>
-#include <linux/kdb.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/ldt.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/desc.h>
-#include <asm/mmu_context.h>
-
-#include <linux/irq.h>
-
-asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-
-int hlt_counter;
-
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-
-/*
- * Power off function, if any
- */
-void (*pm_power_off)(void);
-
-void disable_hlt(void)
-{
- hlt_counter++;
-}
-
-void enable_hlt(void)
-{
- hlt_counter--;
-}
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle (void)
-{
- /* endless idle loop with no priority at all */
- init_idle();
- current->nice = 20;
- current->counter = -100;
-
- while (1) {
- while (!current->need_resched)
- HYPERVISOR_do_sched_op(NULL);
- schedule();
- check_pgt_cache();
- }
-}
-
-void machine_restart(char * __unused)
-{
- HYPERVISOR_exit();
-}
-
-void machine_halt(void)
-{
- HYPERVISOR_exit();
-}
-
-void machine_power_off(void)
-{
- HYPERVISOR_exit();
-}
-
-extern void show_trace(unsigned long* esp);
-
-void show_regs(struct pt_regs * regs)
-{
- printk("\n");
- printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
- printk("EIP: %04x:[<%08lx>] CPU: %d",0xffff & regs->xcs,regs->eip, smp_processor_id());
- if (regs->xcs & 2)
- printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
- printk(" EFLAGS: %08lx %s\n",regs->eflags, print_tainted());
- printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
- regs->eax,regs->ebx,regs->ecx,regs->edx);
- printk("ESI: %08lx EDI: %08lx EBP: %08lx",
- regs->esi, regs->edi, regs->ebp);
- printk(" DS: %04x ES: %04x\n",
- 0xffff & regs->xds,0xffff & regs->xes);
-
- show_trace(®s->esp);
-}
-
-/*
- * No need to lock the MM as we are the last user
- */
-void release_segments(struct mm_struct *mm)
-{
- void * ldt = mm->context.segments;
-
- /*
- * free the LDT
- */
- if (ldt) {
- mm->context.segments = NULL;
- clear_LDT();
- vfree(ldt);
- }
-}
-
-/*
- * Create a kernel thread
- */
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
- long retval, d0;
-
- __asm__ __volatile__(
- "movl %%esp,%%esi\n\t"
- "int $0x80\n\t" /* Linux/i386 system call */
- "cmpl %%esp,%%esi\n\t" /* child or parent? */
- "je 1f\n\t" /* parent - jump */
- /* Load the argument into eax, and push it. That way, it does
- * not matter whether the called function is compiled with
- * -mregparm or not. */
- "movl %4,%%eax\n\t"
- "pushl %%eax\n\t"
- "call *%5\n\t" /* call fn */
- "movl %3,%0\n\t" /* exit */
- "int $0x80\n"
- "1:\t"
- :"=&a" (retval), "=&S" (d0)
- :"0" (__NR_clone), "i" (__NR_exit),
- "r" (arg), "r" (fn),
- "b" (flags | CLONE_VM)
- : "memory");
-
- return retval;
-}
-
-/*
- * Free current thread data structures etc..
- */
-void exit_thread(void)
-{
- /* nothing to do ... */
-}
-
-void flush_thread(void)
-{
- struct task_struct *tsk = current;
-
- memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
-
- /*
- * Forget coprocessor state..
- */
- clear_fpu(tsk);
- tsk->used_math = 0;
-}
-
-void release_thread(struct task_struct *dead_task)
-{
- if (dead_task->mm) {
- void * ldt = dead_task->mm->context.segments;
-
- // temporary debugging check
- if (ldt) {
- printk("WARNING: dead process %8s still has LDT? <%p>\n",
- dead_task->comm, ldt);
- BUG();
- }
- }
-}
-
-/*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
- */
-void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
-{
- struct mm_struct * old_mm;
- void *old_ldt, *ldt;
-
- ldt = NULL;
- old_mm = current->mm;
- if (old_mm && (old_ldt = old_mm->context.segments) != NULL) {
- /*
- * Completely new LDT, we initialize it from the parent:
- */
- ldt = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE);
- if (!ldt)
- printk(KERN_WARNING "ldt allocation failed\n");
- else
- memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_SIZE);
- }
- new_mm->context.segments = ldt;
- new_mm->context.cpuvalid = ~0UL; /* valid on all CPU's - they can't have stale data */
-}
-
-/*
- * Save a segment.
- */
-#define savesegment(seg,value) \
- asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))
-
-int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
- unsigned long unused,
- struct task_struct * p, struct pt_regs * regs)
-{
- struct pt_regs * childregs;
-
- childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;
- struct_cpy(childregs, regs);
- childregs->eax = 0;
- childregs->esp = esp;
-
- p->thread.esp = (unsigned long) childregs;
- p->thread.esp0 = (unsigned long) (childregs+1);
-
- p->thread.eip = (unsigned long) ret_from_fork;
-
- savesegment(fs,p->thread.fs);
- savesegment(gs,p->thread.gs);
-
- unlazy_fpu(current);
- struct_cpy(&p->thread.i387, ¤t->thread.i387);
-
- return 0;
-}
-
-/*
- * fill in the user structure for a core dump..
- */
-void dump_thread(struct pt_regs * regs, struct user * dump)
-{
- int i;
-
-/* changed the size calculations - should hopefully work better. lbt */
- dump->magic = CMAGIC;
- dump->start_code = 0;
- dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
- dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
- dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
- dump->u_dsize -= dump->u_tsize;
- dump->u_ssize = 0;
- for (i = 0; i < 8; i++)
- dump->u_debugreg[i] = current->thread.debugreg[i];
-
- if (dump->start_stack < TASK_SIZE)
- dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;
-
- dump->regs.ebx = regs->ebx;
- dump->regs.ecx = regs->ecx;
- dump->regs.edx = regs->edx;
- dump->regs.esi = regs->esi;
- dump->regs.edi = regs->edi;
- dump->regs.ebp = regs->ebp;
- dump->regs.eax = regs->eax;
- dump->regs.ds = regs->xds;
- dump->regs.es = regs->xes;
- savesegment(fs,dump->regs.fs);
- savesegment(gs,dump->regs.gs);
- dump->regs.orig_eax = regs->orig_eax;
- dump->regs.eip = regs->eip;
- dump->regs.cs = regs->xcs;
- dump->regs.eflags = regs->eflags;
- dump->regs.esp = regs->esp;
- dump->regs.ss = regs->xss;
-
- dump->u_fpvalid = dump_fpu (regs, &dump->i387);
-}
-
-/*
- * switch_to(x,yn) should switch tasks from x to y.
- *
- * We fsave/fwait so that an exception goes off at the right time
- * (as a call from the fsave or fwait in effect) rather than to
- * the wrong process. Lazy FP saving no longer makes any sense
- * with modern CPU's, and this simplifies a lot of things (SMP
- * and UP become the same).
- *
- * NOTE! We used to use the x86 hardware context switching. The
- * reason for not using it any more becomes apparent when you
- * try to recover gracefully from saved state that is no longer
- * valid (stale segment register values in particular). With the
- * hardware task-switch, there is no way to fix up bad state in
- * a reasonable manner.
- *
- * The fact that Intel documents the hardware task-switching to
- * be slow is a fairly red herring - this code is not noticeably
- * faster. However, there _is_ some room for improvement here,
- * so the performance issues may eventually be a valid point.
- * More important, however, is the fact that this allows us much
- * more flexibility.
- */
-void __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
-{
- struct thread_struct *prev = &prev_p->thread,
- *next = &next_p->thread;
-
- unlazy_fpu(prev_p);
-
- HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, next->esp0, 0);
-
- /*
- * Save away %fs and %gs. No need to save %es and %ds, as
- * those are always kernel segments while inside the kernel.
- */
- asm volatile("movl %%fs,%0":"=m" (*(int *)&prev->fs));
- asm volatile("movl %%gs,%0":"=m" (*(int *)&prev->gs));
-
- /*
- * Restore %fs and %gs.
- */
- loadsegment(fs, next->fs);
- loadsegment(gs, next->gs);
-
- /*
- * Now maybe reload the debug registers
- */
- if ( next->debugreg[7] != 0 )
- {
- HYPERVISOR_set_debugreg(0, next->debugreg[0]);
- HYPERVISOR_set_debugreg(1, next->debugreg[1]);
- HYPERVISOR_set_debugreg(2, next->debugreg[2]);
- HYPERVISOR_set_debugreg(3, next->debugreg[3]);
- /* no 4 and 5 */
- HYPERVISOR_set_debugreg(6, next->debugreg[6]);
- HYPERVISOR_set_debugreg(7, next->debugreg[7]);
- }
-}
-
-asmlinkage int sys_fork(struct pt_regs regs)
-{
- return do_fork(SIGCHLD, regs.esp, ®s, 0);
-}
-
-asmlinkage int sys_clone(struct pt_regs regs)
-{
- unsigned long clone_flags;
- unsigned long newsp;
-
- clone_flags = regs.ebx;
- newsp = regs.ecx;
- if (!newsp)
- newsp = regs.esp;
- return do_fork(clone_flags, newsp, ®s, 0);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage int sys_vfork(struct pt_regs regs)
-{
- return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys_execve(struct pt_regs regs)
-{
- int error;
- char * filename;
-
- filename = getname((char *) regs.ebx);
- error = PTR_ERR(filename);
- if (IS_ERR(filename))
- goto out;
- error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, ®s);
- if (error == 0)
- current->ptrace &= ~PT_DTRACE;
- putname(filename);
- out:
- return error;
-}
-
-/*
- * These bracket the sleeping functions..
- */
-extern void scheduling_functions_start_here(void);
-extern void scheduling_functions_end_here(void);
-#define first_sched ((unsigned long) scheduling_functions_start_here)
-#define last_sched ((unsigned long) scheduling_functions_end_here)
-
-unsigned long get_wchan(struct task_struct *p)
-{
- unsigned long ebp, esp, eip;
- unsigned long stack_page;
- int count = 0;
- if (!p || p == current || p->state == TASK_RUNNING)
- return 0;
- stack_page = (unsigned long)p;
- esp = p->thread.esp;
- if (!stack_page || esp < stack_page || esp > 8188+stack_page)
- return 0;
- /* include/asm-i386/system.h:switch_to() pushes ebp last. */
- ebp = *(unsigned long *) esp;
- do {
- if (ebp < stack_page || ebp > 8184+stack_page)
- return 0;
- eip = *(unsigned long *) (ebp+4);
- if (eip < first_sched || eip >= last_sched)
- return eip;
- ebp = *(unsigned long *) ebp;
- } while (count++ < 16);
- return 0;
-}
-#undef last_sched
-#undef first_sched
+++ /dev/null
-/* ptrace.c */
-/* By Ross Biro 1/23/92 */
-/*
- * Pentium III FXSR, SSE support
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/debugreg.h>
-
-/*
- * does not yet catch signals sent when the child dies.
- * in exit.c or in signal.c.
- */
-
-/* determines which flags the user has access to. */
-/* 1 = access 0 = no access */
-#define FLAG_MASK 0x00044dd5
-
-/* set's the trap flag. */
-#define TRAP_FLAG 0x100
-
-/*
- * Offset of eflags on child stack..
- */
-#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))
-
-/*
- * this routine will get a word off of the processes privileged stack.
- * the offset is how far from the base addr as stored in the TSS.
- * this routine assumes that all the privileged stacks are in our
- * data space.
- */
-static inline int get_stack_long(struct task_struct *task, int offset)
-{
- unsigned char *stack;
-
- stack = (unsigned char *)task->thread.esp0;
- stack += offset;
- return (*((int *)stack));
-}
-
-/*
- * this routine will put a word on the processes privileged stack.
- * the offset is how far from the base addr as stored in the TSS.
- * this routine assumes that all the privileged stacks are in our
- * data space.
- */
-static inline int put_stack_long(struct task_struct *task, int offset,
- unsigned long data)
-{
- unsigned char * stack;
-
- stack = (unsigned char *) task->thread.esp0;
- stack += offset;
- *(unsigned long *) stack = data;
- return 0;
-}
-
-static int putreg(struct task_struct *child,
- unsigned long regno, unsigned long value)
-{
- switch (regno >> 2) {
- case FS:
- if (value && (value & 3) != 3)
- return -EIO;
- child->thread.fs = value;
- return 0;
- case GS:
- if (value && (value & 3) != 3)
- return -EIO;
- child->thread.gs = value;
- return 0;
- case DS:
- case ES:
- if (value && (value & 3) != 3)
- return -EIO;
- value &= 0xffff;
- break;
- case SS:
- case CS:
- if ((value & 3) != 3)
- return -EIO;
- value &= 0xffff;
- break;
- case EFL:
- value &= FLAG_MASK;
- value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
- break;
- }
- if (regno > GS*4)
- regno -= 2*4;
- put_stack_long(child, regno - sizeof(struct pt_regs), value);
- return 0;
-}
-
-static unsigned long getreg(struct task_struct *child,
- unsigned long regno)
-{
- unsigned long retval = ~0UL;
-
- switch (regno >> 2) {
- case FS:
- retval = child->thread.fs;
- break;
- case GS:
- retval = child->thread.gs;
- break;
- case DS:
- case ES:
- case SS:
- case CS:
- retval = 0xffff;
- /* fall through */
- default:
- if (regno > GS*4)
- regno -= 2*4;
- regno = regno - sizeof(struct pt_regs);
- retval &= get_stack_long(child, regno);
- }
- return retval;
-}
-
-/*
- * Called by kernel/ptrace.c when detaching..
- *
- * Make sure the single step bit is not set.
- */
-void ptrace_disable(struct task_struct *child)
-{
- long tmp;
-
- tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
- put_stack_long(child, EFL_OFFSET, tmp);
-}
-
-asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
-{
- struct task_struct *child;
- struct user * dummy = NULL;
- int i, ret;
-
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
- switch (request) {
- /* when I and D space are separate, these will need to be fixed. */
- case PTRACE_PEEKTEXT: /* read word at location addr. */
- case PTRACE_PEEKDATA: {
- unsigned long tmp;
- int copied;
-
- copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
- ret = -EIO;
- if (copied != sizeof(tmp))
- break;
- ret = put_user(tmp,(unsigned long *) data);
- break;
- }
-
- /* read the word at location addr in the USER area. */
- case PTRACE_PEEKUSR: {
- unsigned long tmp;
-
- ret = -EIO;
- if ((addr & 3) || addr < 0 ||
- addr > sizeof(struct user) - 3)
- break;
-
- tmp = 0; /* Default return condition */
- if(addr < FRAME_SIZE*sizeof(long))
- tmp = getreg(child, addr);
- if(addr >= (long) &dummy->u_debugreg[0] &&
- addr <= (long) &dummy->u_debugreg[7]){
- addr -= (long) &dummy->u_debugreg[0];
- addr = addr >> 2;
- tmp = child->thread.debugreg[addr];
- }
- ret = put_user(tmp,(unsigned long *) data);
- break;
- }
-
- /* when I and D space are separate, this will have to be fixed. */
- case PTRACE_POKETEXT: /* write the word at location addr. */
- case PTRACE_POKEDATA:
- ret = 0;
- if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
- break;
- ret = -EIO;
- break;
-
- case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
- ret = -EIO;
- if ((addr & 3) || addr < 0 ||
- addr > sizeof(struct user) - 3)
- break;
-
- if (addr < FRAME_SIZE*sizeof(long)) {
- ret = putreg(child, addr, data);
- break;
- }
- /* We need to be very careful here. We implicitly
- want to modify a portion of the task_struct, and we
- have to be selective about what portions we allow someone
- to modify. */
-
- ret = -EIO;
- if(addr >= (long) &dummy->u_debugreg[0] &&
- addr <= (long) &dummy->u_debugreg[7]){
-
- if(addr == (long) &dummy->u_debugreg[4]) break;
- if(addr == (long) &dummy->u_debugreg[5]) break;
- if(addr < (long) &dummy->u_debugreg[4] &&
- ((unsigned long) data) >= TASK_SIZE-3) break;
-
- if(addr == (long) &dummy->u_debugreg[7]) {
- data &= ~DR_CONTROL_RESERVED;
- for(i=0; i<4; i++)
- if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
- goto out_tsk;
- }
-
- addr -= (long) &dummy->u_debugreg;
- addr = addr >> 2;
- child->thread.debugreg[addr] = data;
- ret = 0;
- }
- break;
-
- case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
- case PTRACE_CONT: { /* restart after signal. */
- long tmp;
-
- ret = -EIO;
- if ((unsigned long) data > _NSIG)
- break;
- if (request == PTRACE_SYSCALL)
- child->ptrace |= PT_TRACESYS;
- else
- child->ptrace &= ~PT_TRACESYS;
- child->exit_code = data;
- /* make sure the single step bit is not set. */
- tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
- put_stack_long(child, EFL_OFFSET,tmp);
- wake_up_process(child);
- ret = 0;
- break;
- }
-
-/*
- * make the child exit. Best I can do is send it a sigkill.
- * perhaps it should be put in the status that it wants to
- * exit.
- */
- case PTRACE_KILL: {
- long tmp;
-
- ret = 0;
- if (child->state == TASK_ZOMBIE) /* already dead */
- break;
- child->exit_code = SIGKILL;
- /* make sure the single step bit is not set. */
- tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
- put_stack_long(child, EFL_OFFSET, tmp);
- wake_up_process(child);
- break;
- }
-
- case PTRACE_SINGLESTEP: { /* set the trap flag. */
- long tmp;
-
- ret = -EIO;
- if ((unsigned long) data > _NSIG)
- break;
- child->ptrace &= ~PT_TRACESYS;
- if ((child->ptrace & PT_DTRACE) == 0) {
- /* Spurious delayed TF traps may occur */
- child->ptrace |= PT_DTRACE;
- }
- tmp = get_stack_long(child, EFL_OFFSET) | TRAP_FLAG;
- put_stack_long(child, EFL_OFFSET, tmp);
- child->exit_code = data;
- /* give it a chance to run. */
- wake_up_process(child);
- ret = 0;
- break;
- }
-
- case PTRACE_DETACH:
- /* detach a process that was attached. */
- ret = ptrace_detach(child, data);
- break;
-
- case PTRACE_GETREGS: { /* Get all gp regs from the child. */
- if (!access_ok(VERIFY_WRITE, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
- ret = -EIO;
- break;
- }
- for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
- __put_user(getreg(child, i),(unsigned long *) data);
- data += sizeof(long);
- }
- ret = 0;
- break;
- }
-
- case PTRACE_SETREGS: { /* Set all gp regs in the child. */
- unsigned long tmp;
- if (!access_ok(VERIFY_READ, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
- ret = -EIO;
- break;
- }
- for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
- __get_user(tmp, (unsigned long *) data);
- putreg(child, i, tmp);
- data += sizeof(long);
- }
- ret = 0;
- break;
- }
-
- case PTRACE_GETFPREGS: { /* Get the child FPU state. */
- if (!access_ok(VERIFY_WRITE, (unsigned *)data,
- sizeof(struct user_i387_struct))) {
- ret = -EIO;
- break;
- }
- ret = 0;
- if ( !child->used_math ) {
- /* Simulate an empty FPU. */
- set_fpu_cwd(child, 0x037f);
- set_fpu_swd(child, 0x0000);
- set_fpu_twd(child, 0xffff);
- }
- get_fpregs((struct user_i387_struct *)data, child);
- break;
- }
-
- case PTRACE_SETFPREGS: { /* Set the child FPU state. */
- if (!access_ok(VERIFY_READ, (unsigned *)data,
- sizeof(struct user_i387_struct))) {
- ret = -EIO;
- break;
- }
- child->used_math = 1;
- set_fpregs(child, (struct user_i387_struct *)data);
- ret = 0;
- break;
- }
-
- case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
- if (!access_ok(VERIFY_WRITE, (unsigned *)data,
- sizeof(struct user_fxsr_struct))) {
- ret = -EIO;
- break;
- }
- if ( !child->used_math ) {
- /* Simulate an empty FPU. */
- set_fpu_cwd(child, 0x037f);
- set_fpu_swd(child, 0x0000);
- set_fpu_twd(child, 0xffff);
- set_fpu_mxcsr(child, 0x1f80);
- }
- ret = get_fpxregs((struct user_fxsr_struct *)data, child);
- break;
- }
-
- case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
- if (!access_ok(VERIFY_READ, (unsigned *)data,
- sizeof(struct user_fxsr_struct))) {
- ret = -EIO;
- break;
- }
- child->used_math = 1;
- ret = set_fpxregs(child, (struct user_fxsr_struct *)data);
- break;
- }
-
- case PTRACE_SETOPTIONS: {
- if (data & PTRACE_O_TRACESYSGOOD)
- child->ptrace |= PT_TRACESYSGOOD;
- else
- child->ptrace &= ~PT_TRACESYSGOOD;
- ret = 0;
- break;
- }
-
- default:
- ret = -EIO;
- break;
- }
-out_tsk:
- free_task_struct(child);
-out:
- unlock_kernel();
- return ret;
-}
-
-asmlinkage void syscall_trace(void)
-{
- if ((current->ptrace & (PT_PTRACED|PT_TRACESYS)) !=
- (PT_PTRACED|PT_TRACESYS))
- return;
- /* the 0x80 provides a way for the tracing parent to distinguish
- between a syscall stop and SIGTRAP delivery */
- current->exit_code = SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
- ? 0x80 : 0);
- current->state = TASK_STOPPED;
- notify_parent(current, SIGCHLD);
- schedule();
- /*
- * this isn't the same as continuing with a signal, but it will do
- * for normal use. strace only continues with a signal if the
- * stopping signal is not SIGTRAP. -brl
- */
- if (current->exit_code) {
- send_sig(current->exit_code, current, 1);
- current->exit_code = 0;
- }
-}
+++ /dev/null
-/*
- * i386 semaphore implementation.
- *
- * (C) Copyright 1999 Linus Torvalds
- *
- * Portions Copyright 1999 Red Hat, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@redhat.com>
- */
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <asm/semaphore.h>
-
-/*
- * Semaphores are implemented using a two-way counter:
- * The "count" variable is decremented for each process
- * that tries to acquire the semaphore, while the "sleeping"
- * variable is a count of such acquires.
- *
- * Notably, the inline "up()" and "down()" functions can
- * efficiently test if they need to do any extra work (up
- * needs to do something only if count was negative before
- * the increment operation.
- *
- * "sleeping" and the contention routine ordering is
- * protected by the semaphore spinlock.
- *
- * Note that these functions are only called when there is
- * contention on the lock, and as such all this is the
- * "non-critical" part of the whole semaphore business. The
- * critical part is the inline stuff in <asm/semaphore.h>
- * where we want to avoid any extra jumps and calls.
- */
-
-/*
- * Logic:
- * - only on a boundary condition do we need to care. When we go
- * from a negative count to a non-negative, we wake people up.
- * - when we go from a non-negative count to a negative do we
- * (a) synchronize with the "sleeper" count and (b) make sure
- * that we're on the wakeup list before we synchronize so that
- * we cannot lose wakeup events.
- */
-
-void __up(struct semaphore *sem)
-{
- wake_up(&sem->wait);
-}
-
-static spinlock_t semaphore_lock = SPIN_LOCK_UNLOCKED;
-
-void __down(struct semaphore * sem)
-{
- struct task_struct *tsk = current;
- DECLARE_WAITQUEUE(wait, tsk);
- tsk->state = TASK_UNINTERRUPTIBLE;
- add_wait_queue_exclusive(&sem->wait, &wait);
-
- spin_lock_irq(&semaphore_lock);
- sem->sleepers++;
- for (;;) {
- int sleepers = sem->sleepers;
-
- /*
- * Add "everybody else" into it. They aren't
- * playing, because we own the spinlock.
- */
- if (!atomic_add_negative(sleepers - 1, &sem->count)) {
- sem->sleepers = 0;
- break;
- }
- sem->sleepers = 1; /* us - see -1 above */
- spin_unlock_irq(&semaphore_lock);
-
- schedule();
- tsk->state = TASK_UNINTERRUPTIBLE;
- spin_lock_irq(&semaphore_lock);
- }
- spin_unlock_irq(&semaphore_lock);
- remove_wait_queue(&sem->wait, &wait);
- tsk->state = TASK_RUNNING;
- wake_up(&sem->wait);
-}
-
-int __down_interruptible(struct semaphore * sem)
-{
- int retval = 0;
- struct task_struct *tsk = current;
- DECLARE_WAITQUEUE(wait, tsk);
- tsk->state = TASK_INTERRUPTIBLE;
- add_wait_queue_exclusive(&sem->wait, &wait);
-
- spin_lock_irq(&semaphore_lock);
- sem->sleepers ++;
- for (;;) {
- int sleepers = sem->sleepers;
-
- /*
- * With signals pending, this turns into
- * the trylock failure case - we won't be
- * sleeping, and we* can't get the lock as
- * it has contention. Just correct the count
- * and exit.
- */
- if (signal_pending(current)) {
- retval = -EINTR;
- sem->sleepers = 0;
- atomic_add(sleepers, &sem->count);
- break;
- }
-
- /*
- * Add "everybody else" into it. They aren't
- * playing, because we own the spinlock. The
- * "-1" is because we're still hoping to get
- * the lock.
- */
- if (!atomic_add_negative(sleepers - 1, &sem->count)) {
- sem->sleepers = 0;
- break;
- }
- sem->sleepers = 1; /* us - see -1 above */
- spin_unlock_irq(&semaphore_lock);
-
- schedule();
- tsk->state = TASK_INTERRUPTIBLE;
- spin_lock_irq(&semaphore_lock);
- }
- spin_unlock_irq(&semaphore_lock);
- tsk->state = TASK_RUNNING;
- remove_wait_queue(&sem->wait, &wait);
- wake_up(&sem->wait);
- return retval;
-}
-
-/*
- * Trylock failed - make sure we correct for
- * having decremented the count.
- *
- * We could have done the trylock with a
- * single "cmpxchg" without failure cases,
- * but then it wouldn't work on a 386.
- */
-int __down_trylock(struct semaphore * sem)
-{
- int sleepers;
- unsigned long flags;
-
- spin_lock_irqsave(&semaphore_lock, flags);
- sleepers = sem->sleepers + 1;
- sem->sleepers = 0;
-
- /*
- * Add "everybody else" and us into it. They aren't
- * playing, because we own the spinlock.
- */
- if (!atomic_add_negative(sleepers, &sem->count))
- wake_up(&sem->wait);
-
- spin_unlock_irqrestore(&semaphore_lock, flags);
- return 1;
-}
-
-
-/*
- * The semaphore operations have a special calling sequence that
- * allow us to do a simpler in-line version of them. These routines
- * need to convert that sequence back into the C sequence when
- * there is contention on the semaphore.
- *
- * %ecx contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax when used as a return
- * value..
- */
-asm(
-".text\n"
-".align 4\n"
-".globl __down_failed\n"
-"__down_failed:\n\t"
-#if defined(CONFIG_FRAME_POINTER)
- "pushl %ebp\n\t"
- "movl %esp,%ebp\n\t"
-#endif
- "pushl %eax\n\t"
- "pushl %edx\n\t"
- "pushl %ecx\n\t"
- "call __down\n\t"
- "popl %ecx\n\t"
- "popl %edx\n\t"
- "popl %eax\n\t"
-#if defined(CONFIG_FRAME_POINTER)
- "movl %ebp,%esp\n\t"
- "popl %ebp\n\t"
-#endif
- "ret"
-);
-
-asm(
-".text\n"
-".align 4\n"
-".globl __down_failed_interruptible\n"
-"__down_failed_interruptible:\n\t"
-#if defined(CONFIG_FRAME_POINTER)
- "pushl %ebp\n\t"
- "movl %esp,%ebp\n\t"
-#endif
- "pushl %edx\n\t"
- "pushl %ecx\n\t"
- "call __down_interruptible\n\t"
- "popl %ecx\n\t"
- "popl %edx\n\t"
-#if defined(CONFIG_FRAME_POINTER)
- "movl %ebp,%esp\n\t"
- "popl %ebp\n\t"
-#endif
- "ret"
-);
-
-asm(
-".text\n"
-".align 4\n"
-".globl __down_failed_trylock\n"
-"__down_failed_trylock:\n\t"
-#if defined(CONFIG_FRAME_POINTER)
- "pushl %ebp\n\t"
- "movl %esp,%ebp\n\t"
-#endif
- "pushl %edx\n\t"
- "pushl %ecx\n\t"
- "call __down_trylock\n\t"
- "popl %ecx\n\t"
- "popl %edx\n\t"
-#if defined(CONFIG_FRAME_POINTER)
- "movl %ebp,%esp\n\t"
- "popl %ebp\n\t"
-#endif
- "ret"
-);
-
-asm(
-".text\n"
-".align 4\n"
-".globl __up_wakeup\n"
-"__up_wakeup:\n\t"
- "pushl %eax\n\t"
- "pushl %edx\n\t"
- "pushl %ecx\n\t"
- "call __up\n\t"
- "popl %ecx\n\t"
- "popl %edx\n\t"
- "popl %eax\n\t"
- "ret"
-);
-
-/*
- * rw spinlock fallbacks
- */
-#if defined(CONFIG_SMP)
-asm(
-"
-.align 4
-.globl __write_lock_failed
-__write_lock_failed:
- " LOCK "addl $" RW_LOCK_BIAS_STR ",(%eax)
-1: rep; nop
- cmpl $" RW_LOCK_BIAS_STR ",(%eax)
- jne 1b
-
- " LOCK "subl $" RW_LOCK_BIAS_STR ",(%eax)
- jnz __write_lock_failed
- ret
-
-
-.align 4
-.globl __read_lock_failed
-__read_lock_failed:
- lock ; incl (%eax)
-1: rep; nop
- cmpl $1,(%eax)
- js 1b
-
- lock ; decl (%eax)
- js __read_lock_failed
- ret
-"
-);
-#endif
+++ /dev/null
-/*
- * linux/arch/i386/kernel/setup.c
- *
- * Copyright (C) 1995 Linus Torvalds
- */
-
-/*
- * This file handles the architecture-dependent parts of initialization
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/user.h>
-#include <linux/a.out.h>
-#include <linux/tty.h>
-#include <linux/ioport.h>
-#include <linux/delay.h>
-#include <linux/config.h>
-#include <linux/init.h>
-#include <linux/apm_bios.h>
-#ifdef CONFIG_BLK_DEV_RAM
-#include <linux/blk.h>
-#endif
-#include <linux/highmem.h>
-#include <linux/bootmem.h>
-#include <linux/seq_file.h>
-#include <asm/processor.h>
-#include <linux/console.h>
-#include <asm/mtrr.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/smp.h>
-#include <asm/msr.h>
-#include <asm/desc.h>
-#include <asm/dma.h>
-#include <asm/mpspec.h>
-#include <asm/mmu_context.h>
-#include <asm/hypervisor.h>
-
-shared_info_t *HYPERVISOR_shared_info;
-
-unsigned long *phys_to_machine_mapping;
-
-/*
- * Machine setup..
- */
-
-char ignore_irq13; /* set if exception 16 works */
-struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
-
-unsigned long mmu_cr4_features;
-
-/*
- * Bus types ..
- */
-#ifdef CONFIG_EISA
-int EISA_bus;
-#endif
-int MCA_bus;
-
-/* for MCA, but anyone else can use it if they want */
-unsigned int machine_id;
-unsigned int machine_submodel_id;
-unsigned int BIOS_revision;
-unsigned int mca_pentium_flag;
-
-/* For PCI or other memory-mapped resources */
-unsigned long pci_mem_start = 0x10000000;
-
-/*
- * Setup options
- */
-struct drive_info_struct { char dummy[32]; } drive_info;
-struct screen_info screen_info;
-struct apm_info apm_info;
-struct sys_desc_table_struct {
- unsigned short length;
- unsigned char table[0];
-};
-
-unsigned char aux_device_present;
-
-extern int root_mountflags;
-extern char _text, _etext, _edata, _end;
-
-int enable_acpi_smp_table;
-
-/* Raw start-of-day parameters from the hypervisor. */
-union start_info_union start_info_union;
-
-#define COMMAND_LINE_SIZE 256
-static char command_line[COMMAND_LINE_SIZE];
-char saved_command_line[COMMAND_LINE_SIZE];
-
-static void __init parse_mem_cmdline (char ** cmdline_p)
-{
- char c = ' ', *to = command_line, *from = saved_command_line;
- int len = 0;
-
- /* Save unparsed command line copy for /proc/cmdline */
- memcpy(saved_command_line, start_info.cmd_line, COMMAND_LINE_SIZE);
- saved_command_line[COMMAND_LINE_SIZE-1] = '\0';
-
- for (;;) {
- /*
- * "mem=nopentium" disables the 4MB page tables.
- * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
- * to <mem>, overriding the bios size.
- * "mem=XXX[KkmM]@XXX[KkmM]" defines a memory region from
- * <start> to <start>+<mem>, overriding the bios size.
- */
- if (c == ' ' && !memcmp(from, "mem=", 4)) {
- if (to != command_line)
- to--;
- if (!memcmp(from+4, "nopentium", 9)) {
- from += 9+4;
- } else if (!memcmp(from+4, "exactmap", 8)) {
- from += 8+4;
- } else {
- (void)memparse(from+4, &from);
- if (*from == '@')
- (void)memparse(from+1, &from);
- }
- }
-
- c = *(from++);
- if (!c)
- break;
- if (COMMAND_LINE_SIZE <= ++len)
- break;
- *(to++) = c;
- }
- *to = '\0';
- *cmdline_p = command_line;
-}
-
-void __init setup_arch(char **cmdline_p)
-{
- unsigned long start_pfn, max_pfn, max_low_pfn;
- unsigned long bootmap_size;
- unsigned long i;
-
- extern void hypervisor_callback(void);
- extern void failsafe_callback(void);
-
- extern unsigned long cpu0_pte_quicklist[];
- extern unsigned long cpu0_pgd_quicklist[];
-
- HYPERVISOR_shared_info->event_address =
- (unsigned long)hypervisor_callback;
- HYPERVISOR_shared_info->failsafe_address =
- (unsigned long)failsafe_callback;
-
- boot_cpu_data.pgd_quick = cpu0_pgd_quicklist;
- boot_cpu_data.pte_quick = cpu0_pte_quicklist;
-
- ROOT_DEV = MKDEV(RAMDISK_MAJOR,0);
- memset(&drive_info, 0, sizeof(drive_info));
- memset(&screen_info, 0, sizeof(screen_info));
- memset(&apm_info.bios, 0, sizeof(apm_info.bios));
- aux_device_present = 0;
-
-#ifdef CONFIG_BLK_DEV_RAM
- rd_image_start = 0;
- rd_prompt = 0;
- rd_doload = 0;
-#endif
-
- root_mountflags &= ~MS_RDONLY;
- init_mm.start_code = (unsigned long) &_text;
- init_mm.end_code = (unsigned long) &_etext;
- init_mm.end_data = (unsigned long) &_edata;
- init_mm.brk = (unsigned long) &_end;
-
- parse_mem_cmdline(cmdline_p);
-
-#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
-#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
-#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
-
-/*
- * 128MB for vmalloc and initrd
- */
-#define VMALLOC_RESERVE (unsigned long)(128 << 20)
-#define MAXMEM (unsigned long)(HYPERVISOR_VIRT_START-PAGE_OFFSET-VMALLOC_RESERVE)
-#define MAXMEM_PFN PFN_DOWN(MAXMEM)
-#define MAX_NONPAE_PFN (1 << 20)
-
- /*
- * partially used pages are not usable - thus
- * we are rounding upwards:
- */
-#ifdef CONFIG_BLK_DEV_INITRD
- if ( start_info.mod_start )
- start_pfn = PFN_UP(__pa(start_info.mod_start + start_info.mod_len));
- else
-#endif
- start_pfn = PFN_UP(__pa(&_end));
- max_pfn = start_info.nr_pages;
-
- /*
- * Determine low and high memory ranges:
- */
- max_low_pfn = max_pfn;
- if (max_low_pfn > MAXMEM_PFN) {
- max_low_pfn = MAXMEM_PFN;
-#ifndef CONFIG_HIGHMEM
- /* Maximum memory usable is what is directly addressable */
- printk(KERN_WARNING "Warning only %ldMB will be used.\n",
- MAXMEM>>20);
- if (max_pfn > MAX_NONPAE_PFN)
- printk(KERN_WARNING "Use a PAE enabled kernel.\n");
- else
- printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
-#else /* !CONFIG_HIGHMEM */
-#ifndef CONFIG_X86_PAE
- if (max_pfn > MAX_NONPAE_PFN) {
- max_pfn = MAX_NONPAE_PFN;
- printk(KERN_WARNING "Warning only 4GB will be used.\n");
- printk(KERN_WARNING "Use a PAE enabled kernel.\n");
- }
-#endif /* !CONFIG_X86_PAE */
-#endif /* !CONFIG_HIGHMEM */
- }
-
-#ifdef CONFIG_HIGHMEM
- highstart_pfn = highend_pfn = max_pfn;
- if (max_pfn > MAXMEM_PFN) {
- highstart_pfn = MAXMEM_PFN;
- printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
- pages_to_mb(highend_pfn - highstart_pfn));
- }
-#endif
-
- /*
- * Initialize the boot-time allocator, and free up all RAM.
- * Then reserve space for OS image, and the bootmem bitmap.
- */
- bootmap_size = init_bootmem(start_pfn, max_low_pfn);
- free_bootmem(0, PFN_PHYS(max_low_pfn));
- reserve_bootmem(0, PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1);
-
- /* Now reserve space for the hypervisor-provided page tables. */
- {
- unsigned long *pgd = (unsigned long *)start_info.pt_base;
- unsigned long pte;
- int i;
- reserve_bootmem(__pa(pgd), PAGE_SIZE);
- for ( i = 0; i < (HYPERVISOR_VIRT_START>>22); i++ )
- {
- unsigned long pgde = *pgd++;
- if ( !(pgde & 1) ) continue;
- pte = machine_to_phys(pgde & PAGE_MASK);
- reserve_bootmem(pte, PAGE_SIZE);
- }
- }
- cur_pgd = init_mm.pgd = (pgd_t *)start_info.pt_base;
-
- /* Now initialise the physical->machine mapping table. */
- phys_to_machine_mapping = alloc_bootmem(max_pfn * sizeof(unsigned long));
- for ( i = 0; i < max_pfn; i++ )
- {
- unsigned long pgde, *ppte;
- unsigned long pfn = i + (PAGE_OFFSET >> PAGE_SHIFT);
- pgde = *((unsigned long *)start_info.pt_base + (pfn >> 10));
- ppte = (unsigned long *)machine_to_phys(pgde & PAGE_MASK) + (pfn&1023);
- phys_to_machine_mapping[i] =
- (*(unsigned long *)__va(ppte)) >> PAGE_SHIFT;
- }
-
-#ifdef CONFIG_BLK_DEV_INITRD
- if (start_info.mod_start) {
- if ((__pa(start_info.mod_start) + start_info.mod_len) <=
- (max_low_pfn << PAGE_SHIFT)) {
- initrd_start = start_info.mod_start;
- initrd_end = initrd_start + start_info.mod_len;
- initrd_below_start_ok = 1;
- }
- else {
- printk(KERN_ERR "initrd extends beyond end of memory "
- "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
- __pa(start_info.mod_start) + start_info.mod_len,
- max_low_pfn << PAGE_SHIFT);
- initrd_start = 0;
- }
- }
-#endif
-
- paging_init();
-}
-
-static int cachesize_override __initdata = -1;
-static int __init cachesize_setup(char *str)
-{
- get_option (&str, &cachesize_override);
- return 1;
-}
-__setup("cachesize=", cachesize_setup);
-
-
-static int __init get_model_name(struct cpuinfo_x86 *c)
-{
- unsigned int *v;
- char *p, *q;
-
- if (cpuid_eax(0x80000000) < 0x80000004)
- return 0;
-
- v = (unsigned int *) c->x86_model_id;
- cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
- cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
- cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
- c->x86_model_id[48] = 0;
-
- /* Intel chips right-justify this string for some dumb reason;
- undo that brain damage */
- p = q = &c->x86_model_id[0];
- while ( *p == ' ' )
- p++;
- if ( p != q ) {
- while ( *p )
- *q++ = *p++;
- while ( q <= &c->x86_model_id[48] )
- *q++ = '\0'; /* Zero-pad the rest */
- }
-
- return 1;
-}
-
-
-static void __init display_cacheinfo(struct cpuinfo_x86 *c)
-{
- unsigned int n, dummy, ecx, edx, l2size;
-
- n = cpuid_eax(0x80000000);
-
- if (n >= 0x80000005) {
- cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
- printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
- edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
- c->x86_cache_size=(ecx>>24)+(edx>>24);
- }
-
- if (n < 0x80000006) /* Some chips just has a large L1. */
- return;
-
- ecx = cpuid_ecx(0x80000006);
- l2size = ecx >> 16;
-
- /* AMD errata T13 (order #21922) */
- if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) {
- if (c->x86_model == 3 && c->x86_mask == 0) /* Duron Rev A0 */
- l2size = 64;
- if (c->x86_model == 4 &&
- (c->x86_mask==0 || c->x86_mask==1)) /* Tbird rev A1/A2 */
- l2size = 256;
- }
-
- /* Intel PIII Tualatin. This comes in two flavours.
- * One has 256kb of cache, the other 512. We have no way
- * to determine which, so we use a boottime override
- * for the 512kb model, and assume 256 otherwise.
- */
- if ((c->x86_vendor == X86_VENDOR_INTEL) && (c->x86 == 6) &&
- (c->x86_model == 11) && (l2size == 0))
- l2size = 256;
-
- /* VIA C3 CPUs (670-68F) need further shifting. */
- if (c->x86_vendor == X86_VENDOR_CENTAUR && (c->x86 == 6) &&
- ((c->x86_model == 7) || (c->x86_model == 8))) {
- l2size = l2size >> 8;
- }
-
- /* Allow user to override all this if necessary. */
- if (cachesize_override != -1)
- l2size = cachesize_override;
-
- if ( l2size == 0 )
- return; /* Again, no L2 cache is possible */
-
- c->x86_cache_size = l2size;
-
- printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
- l2size, ecx & 0xFF);
-}
-
-
-static int __init init_amd(struct cpuinfo_x86 *c)
-{
- int r;
-
- /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
- 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
- clear_bit(0*32+31, &c->x86_capability);
-
- r = get_model_name(c);
-
- switch(c->x86)
- {
- case 6: /* An Athlon/Duron. We can trust the BIOS probably */
- break;
- default:
- panic("Unsupported AMD processor\n");
- }
-
- display_cacheinfo(c);
- return r;
-}
-
-
-static void __init init_intel(struct cpuinfo_x86 *c)
-{
- char *p = NULL;
- unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */
-
- if (c->cpuid_level > 1) {
- /* supports eax=2 call */
- int i, j, n;
- int regs[4];
- unsigned char *dp = (unsigned char *)regs;
-
- /* Number of times to iterate */
- n = cpuid_eax(2) & 0xFF;
-
- for ( i = 0 ; i < n ; i++ ) {
- cpuid(2, ®s[0], ®s[1], ®s[2], ®s[3]);
-
- /* If bit 31 is set, this is an unknown format */
- for ( j = 0 ; j < 3 ; j++ ) {
- if ( regs[j] < 0 ) regs[j] = 0;
- }
-
- /* Byte 0 is level count, not a descriptor */
- for ( j = 1 ; j < 16 ; j++ ) {
- unsigned char des = dp[j];
- unsigned char dl, dh;
- unsigned int cs;
-
- dh = des >> 4;
- dl = des & 0x0F;
-
- /* Black magic... */
-
- switch ( dh )
- {
- case 0:
- switch ( dl ) {
- case 6:
- /* L1 I cache */
- l1i += 8;
- break;
- case 8:
- /* L1 I cache */
- l1i += 16;
- break;
- case 10:
- /* L1 D cache */
- l1d += 8;
- break;
- case 12:
- /* L1 D cache */
- l1d += 16;
- break;
- default:;
- /* TLB, or unknown */
- }
- break;
- case 2:
- if ( dl ) {
- /* L3 cache */
- cs = (dl-1) << 9;
- l3 += cs;
- }
- break;
- case 4:
- if ( c->x86 > 6 && dl ) {
- /* P4 family */
- /* L3 cache */
- cs = 128 << (dl-1);
- l3 += cs;
- break;
- }
- /* else same as 8 - fall through */
- case 8:
- if ( dl ) {
- /* L2 cache */
- cs = 128 << (dl-1);
- l2 += cs;
- }
- break;
- case 6:
- if (dl > 5) {
- /* L1 D cache */
- cs = 8<<(dl-6);
- l1d += cs;
- }
- break;
- case 7:
- if ( dl >= 8 )
- {
- /* L2 cache */
- cs = 64<<(dl-8);
- l2 += cs;
- } else {
- /* L0 I cache, count as L1 */
- cs = dl ? (16 << (dl-1)) : 12;
- l1i += cs;
- }
- break;
- default:
- /* TLB, or something else we don't know about */
- break;
- }
- }
- }
- if ( l1i || l1d )
- printk(KERN_INFO "CPU: L1 I cache: %dK, L1 D cache: %dK\n",
- l1i, l1d);
- if ( l2 )
- printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);
- if ( l3 )
- printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);
-
- /*
- * This assumes the L3 cache is shared; it typically lives in
- * the northbridge. The L1 caches are included by the L2
- * cache, and so should not be included for the purpose of
- * SMP switching weights.
- */
- c->x86_cache_size = l2 ? l2 : (l1i+l1d);
- }
-
- /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it */
- if ( c->x86 == 6 && c->x86_model < 3 && c->x86_mask < 3 )
- clear_bit(X86_FEATURE_SEP, &c->x86_capability);
-
- /* Names for the Pentium II/Celeron processors
- detectable only by also checking the cache size.
- Dixon is NOT a Celeron. */
- if (c->x86 == 6) {
- switch (c->x86_model) {
- case 5:
- if (l2 == 0)
- p = "Celeron (Covington)";
- if (l2 == 256)
- p = "Mobile Pentium II (Dixon)";
- break;
-
- case 6:
- if (l2 == 128)
- p = "Celeron (Mendocino)";
- break;
-
- case 8:
- if (l2 == 128)
- p = "Celeron (Coppermine)";
- break;
- }
- }
-
- if ( p )
- strcpy(c->x86_model_id, p);
-}
-
-void __init get_cpu_vendor(struct cpuinfo_x86 *c)
-{
- char *v = c->x86_vendor_id;
-
- if (!strcmp(v, "GenuineIntel"))
- c->x86_vendor = X86_VENDOR_INTEL;
- else if (!strcmp(v, "AuthenticAMD"))
- c->x86_vendor = X86_VENDOR_AMD;
- else
- c->x86_vendor = X86_VENDOR_UNKNOWN;
-}
-
-struct cpu_model_info {
- int vendor;
- int family;
- char *model_names[16];
-};
-
-/* Naming convention should be: <Name> [(<Codename>)] */
-/* This table only is used unless init_<vendor>() below doesn't set it; */
-/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */
-static struct cpu_model_info cpu_models[] __initdata = {
- { X86_VENDOR_INTEL, 6,
- { "Pentium Pro A-step", "Pentium Pro", NULL, "Pentium II (Klamath)",
- NULL, "Pentium II (Deschutes)", "Mobile Pentium II",
- "Pentium III (Katmai)", "Pentium III (Coppermine)", NULL,
- "Pentium III (Cascades)", NULL, NULL, NULL, NULL }},
- { X86_VENDOR_AMD, 6, /* Is this this really necessary?? */
- { "Athlon", "Athlon",
- "Athlon", NULL, "Athlon", NULL,
- NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL }}
-};
-
-/* Look up CPU names by table lookup. */
-static char __init *table_lookup_model(struct cpuinfo_x86 *c)
-{
- struct cpu_model_info *info = cpu_models;
- int i;
-
- if ( c->x86_model >= 16 )
- return NULL; /* Range check */
-
- for ( i = 0 ; i < sizeof(cpu_models)/sizeof(struct cpu_model_info) ; i++ ) {
- if ( info->vendor == c->x86_vendor &&
- info->family == c->x86 ) {
- return info->model_names[c->x86_model];
- }
- info++;
- }
- return NULL; /* Not found */
-}
-
-
-
-/* Standard macro to see if a specific flag is changeable */
-static inline int flag_is_changeable_p(u32 flag)
-{
- u32 f1, f2;
-
- asm("pushfl\n\t"
- "pushfl\n\t"
- "popl %0\n\t"
- "movl %0,%1\n\t"
- "xorl %2,%0\n\t"
- "pushl %0\n\t"
- "popfl\n\t"
- "pushfl\n\t"
- "popl %0\n\t"
- "popfl\n\t"
- : "=&r" (f1), "=&r" (f2)
- : "ir" (flag));
-
- return ((f1^f2) & flag) != 0;
-}
-
-
-/* Probe for the CPUID instruction */
-static int __init have_cpuid_p(void)
-{
- return flag_is_changeable_p(X86_EFLAGS_ID);
-}
-
-
-
-/*
- * This does the hard work of actually picking apart the CPU stuff...
- */
-void __init identify_cpu(struct cpuinfo_x86 *c)
-{
- int junk, i;
- u32 xlvl, tfms;
-
- c->loops_per_jiffy = loops_per_jiffy;
- c->x86_cache_size = -1;
- c->x86_vendor = X86_VENDOR_UNKNOWN;
- c->cpuid_level = -1; /* CPUID not detected */
- c->x86_model = c->x86_mask = 0; /* So far unknown... */
- c->x86_vendor_id[0] = '\0'; /* Unset */
- c->x86_model_id[0] = '\0'; /* Unset */
- memset(&c->x86_capability, 0, sizeof c->x86_capability);
- c->hard_math = 1;
-
- if ( !have_cpuid_p() ) {
- panic("Processor must support CPUID\n");
- } else {
- /* CPU does have CPUID */
-
- /* Get vendor name */
- cpuid(0x00000000, &c->cpuid_level,
- (int *)&c->x86_vendor_id[0],
- (int *)&c->x86_vendor_id[8],
- (int *)&c->x86_vendor_id[4]);
-
- get_cpu_vendor(c);
- /* Initialize the standard set of capabilities */
- /* Note that the vendor-specific code below might override */
-
- /* Intel-defined flags: level 0x00000001 */
- if ( c->cpuid_level >= 0x00000001 ) {
- cpuid(0x00000001, &tfms, &junk, &junk,
- &c->x86_capability[0]);
- c->x86 = (tfms >> 8) & 15;
- c->x86_model = (tfms >> 4) & 15;
- c->x86_mask = tfms & 15;
- } else {
- /* Have CPUID level 0 only - unheard of */
- c->x86 = 4;
- }
-
- /* AMD-defined flags: level 0x80000001 */
- xlvl = cpuid_eax(0x80000000);
- if ( (xlvl & 0xffff0000) == 0x80000000 ) {
- if ( xlvl >= 0x80000001 )
- c->x86_capability[1] = cpuid_edx(0x80000001);
- if ( xlvl >= 0x80000004 )
- get_model_name(c); /* Default name */
- }
-
- /* Transmeta-defined flags: level 0x80860001 */
- xlvl = cpuid_eax(0x80860000);
- if ( (xlvl & 0xffff0000) == 0x80860000 ) {
- if ( xlvl >= 0x80860001 )
- c->x86_capability[2] = cpuid_edx(0x80860001);
- }
- }
-
- printk(KERN_DEBUG "CPU: Before vendor init, caps: %08x %08x %08x, vendor = %d\n",
- c->x86_capability[0],
- c->x86_capability[1],
- c->x86_capability[2],
- c->x86_vendor);
-
- /*
- * Vendor-specific initialization. In this section we
- * canonicalize the feature flags, meaning if there are
- * features a certain CPU supports which CPUID doesn't
- * tell us, CPUID claiming incorrect flags, or other bugs,
- * we handle them here.
- *
- * At the end of this section, c->x86_capability better
- * indicate the features this CPU genuinely supports!
- */
- switch ( c->x86_vendor ) {
- case X86_VENDOR_AMD:
- init_amd(c);
- break;
-
- case X86_VENDOR_INTEL:
- init_intel(c);
- break;
-
- default:
- panic("Unsupported CPU vendor\n");
- }
-
- printk(KERN_DEBUG "CPU: After vendor init, caps: %08x %08x %08x %08x\n",
- c->x86_capability[0],
- c->x86_capability[1],
- c->x86_capability[2],
- c->x86_capability[3]);
-
-
- /* If the model name is still unset, do table lookup. */
- if ( !c->x86_model_id[0] ) {
- char *p;
- p = table_lookup_model(c);
- if ( p )
- strcpy(c->x86_model_id, p);
- else
- /* Last resort... */
- sprintf(c->x86_model_id, "%02x/%02x",
- c->x86_vendor, c->x86_model);
- }
-
- /* Now the feature flags better reflect actual CPU features! */
-
- printk(KERN_DEBUG "CPU: After generic, caps: %08x %08x %08x %08x\n",
- c->x86_capability[0],
- c->x86_capability[1],
- c->x86_capability[2],
- c->x86_capability[3]);
-
- /*
- * On SMP, boot_cpu_data holds the common feature set between
- * all CPUs; so make sure that we indicate which features are
- * common between the CPUs. The first time this routine gets
- * executed, c == &boot_cpu_data.
- */
- if ( c != &boot_cpu_data ) {
- /* AND the already accumulated flags with these */
- for ( i = 0 ; i < NCAPINTS ; i++ )
- boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
- }
-
- printk(KERN_DEBUG "CPU: Common caps: %08x %08x %08x %08x\n",
- boot_cpu_data.x86_capability[0],
- boot_cpu_data.x86_capability[1],
- boot_cpu_data.x86_capability[2],
- boot_cpu_data.x86_capability[3]);
-}
-
-
-/* These need to match <asm/processor.h> */
-static char *cpu_vendor_names[] __initdata = {
- "Intel", "Cyrix", "AMD", "UMC", "NexGen", "Centaur", "Rise", "Transmeta" };
-
-
-void __init print_cpu_info(struct cpuinfo_x86 *c)
-{
- char *vendor = NULL;
-
- if (c->x86_vendor < sizeof(cpu_vendor_names)/sizeof(char *))
- vendor = cpu_vendor_names[c->x86_vendor];
- else if (c->cpuid_level >= 0)
- vendor = c->x86_vendor_id;
-
- if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
- printk("%s ", vendor);
-
- if (!c->x86_model_id[0])
- printk("%d86", c->x86);
- else
- printk("%s", c->x86_model_id);
-
- if (c->x86_mask || c->cpuid_level >= 0)
- printk(" stepping %02x\n", c->x86_mask);
- else
- printk("\n");
-}
-
-/*
- * Get CPU information for use by the procfs.
- */
-static int show_cpuinfo(struct seq_file *m, void *v)
-{
- /*
- * These flag bits must match the definitions in <asm/cpufeature.h>.
- * NULL means this bit is undefined or reserved; either way it doesn't
- * have meaning as far as Linux is concerned. Note that it's important
- * to realize there is a difference between this table and CPUID -- if
- * applications want to get the raw CPUID data, they should access
- * /dev/cpu/<cpu_nr>/cpuid instead.
- */
- static char *x86_cap_flags[] = {
- /* Intel-defined */
- "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
- "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
- "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
- "fxsr", "sse", "sse2", "ss", NULL, "tm", "ia64", NULL,
-
- /* AMD-defined */
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, "mmxext", NULL,
- NULL, NULL, NULL, NULL, NULL, "lm", "3dnowext", "3dnow",
-
- /* Transmeta-defined */
- "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-
- /* Other (Linux-defined) */
- "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
- };
- struct cpuinfo_x86 *c = v;
- int i, n = c - cpu_data;
- int fpu_exception;
-
-#ifdef CONFIG_SMP
- if (!(cpu_online_map & (1<<n)))
- return 0;
-#endif
- seq_printf(m, "processor\t: %d\n"
- "vendor_id\t: %s\n"
- "cpu family\t: %d\n"
- "model\t\t: %d\n"
- "model name\t: %s\n",
- n,
- c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown",
- c->x86,
- c->x86_model,
- c->x86_model_id[0] ? c->x86_model_id : "unknown");
-
- if (c->x86_mask || c->cpuid_level >= 0)
- seq_printf(m, "stepping\t: %d\n", c->x86_mask);
- else
- seq_printf(m, "stepping\t: unknown\n");
-
- if ( test_bit(X86_FEATURE_TSC, &c->x86_capability) ) {
- seq_printf(m, "cpu MHz\t\t: %lu.%03lu\n",
- cpu_khz / 1000, (cpu_khz % 1000));
- }
-
- /* Cache size */
- if (c->x86_cache_size >= 0)
- seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
-
- /* We use exception 16 if we have hardware math and we've either seen it or the CPU claims it is internal */
- fpu_exception = c->hard_math && (ignore_irq13 || cpu_has_fpu);
- seq_printf(m, "fdiv_bug\t: %s\n"
- "hlt_bug\t\t: %s\n"
- "f00f_bug\t: %s\n"
- "coma_bug\t: %s\n"
- "fpu\t\t: %s\n"
- "fpu_exception\t: %s\n"
- "cpuid level\t: %d\n"
- "wp\t\t: %s\n"
- "flags\t\t:",
- c->fdiv_bug ? "yes" : "no",
- c->hlt_works_ok ? "no" : "yes",
- c->f00f_bug ? "yes" : "no",
- c->coma_bug ? "yes" : "no",
- c->hard_math ? "yes" : "no",
- fpu_exception ? "yes" : "no",
- c->cpuid_level,
- c->wp_works_ok ? "yes" : "no");
-
- for ( i = 0 ; i < 32*NCAPINTS ; i++ )
- if ( test_bit(i, &c->x86_capability) &&
- x86_cap_flags[i] != NULL )
- seq_printf(m, " %s", x86_cap_flags[i]);
-
- seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n",
- c->loops_per_jiffy/(500000/HZ),
- (c->loops_per_jiffy/(5000/HZ)) % 100);
- return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
- return *pos < NR_CPUS ? cpu_data + *pos : NULL;
-}
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
- ++*pos;
- return c_start(m, pos);
-}
-static void c_stop(struct seq_file *m, void *v)
-{
-}
-struct seq_operations cpuinfo_op = {
- start: c_start,
- next: c_next,
- stop: c_stop,
- show: show_cpuinfo,
-};
-
-unsigned long cpu_initialized __initdata = 0;
-
-/*
- * cpu_init() initializes state that is per-CPU. Some data is already
- * initialized (naturally) in the bootstrap process, such as the GDT
- * and IDT. We reload them nevertheless, this function acts as a
- * 'CPU state barrier', nothing should get across.
- */
-void __init cpu_init (void)
-{
- int nr = smp_processor_id();
-
- if (test_and_set_bit(nr, &cpu_initialized)) {
- printk(KERN_WARNING "CPU#%d already initialized!\n", nr);
- for (;;) __sti();
- }
- printk(KERN_INFO "Initializing CPU#%d\n", nr);
-
- /*
- * set up and load the per-CPU TSS and LDT
- */
- atomic_inc(&init_mm.mm_count);
- current->active_mm = &init_mm;
- if(current->mm)
- BUG();
- enter_lazy_tlb(&init_mm, current, nr);
-
- HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, current->thread.esp0, 0);
-
- /* Force FPU initialization. */
- current->flags &= ~PF_USEDFPU;
- current->used_math = 0;
- stts();
-}
-
-
-/******************************************************************************
- * Time-to-die callback handling.
- */
-
-static void time_to_die(int irq, void *unused, struct pt_regs *regs)
-{
- extern void ctrl_alt_del(void);
- ctrl_alt_del();
-}
-
-static int __init setup_death_event(void)
-{
- (void)request_irq(_EVENT_DIE, time_to_die, 0, "die", NULL);
- return 0;
-}
-
-__initcall(setup_death_event);
+++ /dev/null
-/*
- * linux/arch/i386/kernel/signal.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
- * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/errno.h>
-#include <linux/wait.h>
-#include <linux/ptrace.h>
-#include <linux/unistd.h>
-#include <linux/stddef.h>
-#include <linux/tty.h>
-#include <linux/personality.h>
-#include <asm/ucontext.h>
-#include <asm/uaccess.h>
-#include <asm/i387.h>
-
-#define DEBUG_SIG 0
-
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-int FASTCALL(do_signal(struct pt_regs *regs, sigset_t *oldset));
-
-int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from)
-{
- if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
- return -EFAULT;
- if (from->si_code < 0)
- return __copy_to_user(to, from, sizeof(siginfo_t));
- else {
- int err;
-
- /* If you change siginfo_t structure, please be sure
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user((short)from->si_code, &to->si_code);
- /* First 32bits of unions are always present. */
- err |= __put_user(from->si_pid, &to->si_pid);
- switch (from->si_code >> 16) {
- case __SI_FAULT >> 16:
- break;
- case __SI_CHLD >> 16:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- default:
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- /* case __SI_RT: This is not generated by the kernel as of now. */
- }
- return err;
- }
-}
-
-/*
- * Atomically swap in the new signal mask, and wait for a signal.
- */
-asmlinkage int
-sys_sigsuspend(int history0, int history1, old_sigset_t mask)
-{
- struct pt_regs * regs = (struct pt_regs *) &history0;
- sigset_t saveset;
-
- mask &= _BLOCKABLE;
- spin_lock_irq(¤t->sigmask_lock);
- saveset = current->blocked;
- siginitset(¤t->blocked, mask);
- recalc_sigpending(current);
- spin_unlock_irq(¤t->sigmask_lock);
-
- regs->eax = -EINTR;
- while (1) {
- current->state = TASK_INTERRUPTIBLE;
- schedule();
- if (do_signal(regs, &saveset))
- return -EINTR;
- }
-}
-
-asmlinkage int
-sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize)
-{
- struct pt_regs * regs = (struct pt_regs *) &unewset;
- sigset_t saveset, newset;
-
- /* XXX: Don't preclude handling different sized sigset_t's. */
- if (sigsetsize != sizeof(sigset_t))
- return -EINVAL;
-
- if (copy_from_user(&newset, unewset, sizeof(newset)))
- return -EFAULT;
- sigdelsetmask(&newset, ~_BLOCKABLE);
-
- spin_lock_irq(¤t->sigmask_lock);
- saveset = current->blocked;
- current->blocked = newset;
- recalc_sigpending(current);
- spin_unlock_irq(¤t->sigmask_lock);
-
- regs->eax = -EINTR;
- while (1) {
- current->state = TASK_INTERRUPTIBLE;
- schedule();
- if (do_signal(regs, &saveset))
- return -EINTR;
- }
-}
-
-asmlinkage int
-sys_sigaction(int sig, const struct old_sigaction *act,
- struct old_sigaction *oact)
-{
- struct k_sigaction new_ka, old_ka;
- int ret;
-
- if (act) {
- old_sigset_t mask;
- if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
- __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
- __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
- return -EFAULT;
- __get_user(new_ka.sa.sa_flags, &act->sa_flags);
- __get_user(mask, &act->sa_mask);
- siginitset(&new_ka.sa.sa_mask, mask);
- }
-
- ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
-
- if (!ret && oact) {
- if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
- __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
- __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
- return -EFAULT;
- __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
- __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
- }
-
- return ret;
-}
-
-asmlinkage int
-sys_sigaltstack(const stack_t *uss, stack_t *uoss)
-{
- struct pt_regs *regs = (struct pt_regs *) &uss;
- return do_sigaltstack(uss, uoss, regs->esp);
-}
-
-
-/*
- * Do a signal return; undo the signal stack.
- */
-
-struct sigframe
-{
- char *pretcode;
- int sig;
- struct sigcontext sc;
- struct _fpstate fpstate;
- unsigned long extramask[_NSIG_WORDS-1];
- char retcode[8];
-};
-
-struct rt_sigframe
-{
- char *pretcode;
- int sig;
- struct siginfo *pinfo;
- void *puc;
- struct siginfo info;
- struct ucontext uc;
- struct _fpstate fpstate;
- char retcode[8];
-};
-
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc, int *peax)
-{
- unsigned int err = 0;
-
-#define COPY(x) err |= __get_user(regs->x, &sc->x)
-
-#define COPY_SEG(seg) \
- { unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
- regs->x##seg = tmp; }
-
-#define COPY_SEG_STRICT(seg) \
- { unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
- regs->x##seg = tmp|3; }
-
-#define GET_SEG(seg) \
- { unsigned short tmp; \
- err |= __get_user(tmp, &sc->seg); \
- loadsegment(seg,tmp); }
-
- GET_SEG(gs);
- GET_SEG(fs);
- COPY_SEG(es);
- COPY_SEG(ds);
- COPY(edi);
- COPY(esi);
- COPY(ebp);
- COPY(esp);
- COPY(ebx);
- COPY(edx);
- COPY(ecx);
- COPY(eip);
- COPY_SEG_STRICT(cs);
- COPY_SEG_STRICT(ss);
-
- {
- unsigned int tmpflags;
- err |= __get_user(tmpflags, &sc->eflags);
- regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5);
- regs->orig_eax = -1; /* disable syscall checks */
- }
-
- {
- struct _fpstate * buf;
- err |= __get_user(buf, &sc->fpstate);
- if (buf) {
- if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
- goto badframe;
- err |= restore_i387(buf);
- }
- }
-
- err |= __get_user(*peax, &sc->eax);
- return err;
-
-badframe:
- return 1;
-}
-
-asmlinkage int sys_sigreturn(unsigned long __unused)
-{
- struct pt_regs *regs = (struct pt_regs *) &__unused;
- struct sigframe *frame = (struct sigframe *)(regs->esp - 8);
- sigset_t set;
- int eax;
-
- if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
- goto badframe;
- if (__get_user(set.sig[0], &frame->sc.oldmask)
- || (_NSIG_WORDS > 1
- && __copy_from_user(&set.sig[1], &frame->extramask,
- sizeof(frame->extramask))))
- goto badframe;
-
- sigdelsetmask(&set, ~_BLOCKABLE);
- spin_lock_irq(¤t->sigmask_lock);
- current->blocked = set;
- recalc_sigpending(current);
- spin_unlock_irq(¤t->sigmask_lock);
-
- if (restore_sigcontext(regs, &frame->sc, &eax))
- goto badframe;
- return eax;
-
-badframe:
- force_sig(SIGSEGV, current);
- return 0;
-}
-
-asmlinkage int sys_rt_sigreturn(unsigned long __unused)
-{
- struct pt_regs *regs = (struct pt_regs *) &__unused;
- struct rt_sigframe *frame = (struct rt_sigframe *)(regs->esp - 4);
- sigset_t set;
- stack_t st;
- int eax;
-
- if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
- goto badframe;
- if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
- goto badframe;
-
- sigdelsetmask(&set, ~_BLOCKABLE);
- spin_lock_irq(¤t->sigmask_lock);
- current->blocked = set;
- recalc_sigpending(current);
- spin_unlock_irq(¤t->sigmask_lock);
-
- if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax))
- goto badframe;
-
- if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
- goto badframe;
- /* It is more difficult to avoid calling this function than to
- call it and ignore errors. */
- do_sigaltstack(&st, NULL, regs->esp);
-
- return eax;
-
-badframe:
- force_sig(SIGSEGV, current);
- return 0;
-}
-
-/*
- * Set up a signal frame.
- */
-
-static int
-setup_sigcontext(struct sigcontext *sc, struct _fpstate *fpstate,
- struct pt_regs *regs, unsigned long mask)
-{
- int tmp, err = 0;
-
- tmp = 0;
- __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
- err |= __put_user(tmp, (unsigned int *)&sc->gs);
- __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
- err |= __put_user(tmp, (unsigned int *)&sc->fs);
-
- err |= __put_user(regs->xes, (unsigned int *)&sc->es);
- err |= __put_user(regs->xds, (unsigned int *)&sc->ds);
- err |= __put_user(regs->edi, &sc->edi);
- err |= __put_user(regs->esi, &sc->esi);
- err |= __put_user(regs->ebp, &sc->ebp);
- err |= __put_user(regs->esp, &sc->esp);
- err |= __put_user(regs->ebx, &sc->ebx);
- err |= __put_user(regs->edx, &sc->edx);
- err |= __put_user(regs->ecx, &sc->ecx);
- err |= __put_user(regs->eax, &sc->eax);
- err |= __put_user(current->thread.trap_no, &sc->trapno);
- err |= __put_user(current->thread.error_code, &sc->err);
- err |= __put_user(regs->eip, &sc->eip);
- err |= __put_user(regs->xcs, (unsigned int *)&sc->cs);
- err |= __put_user(regs->eflags, &sc->eflags);
- err |= __put_user(regs->esp, &sc->esp_at_signal);
- err |= __put_user(regs->xss, (unsigned int *)&sc->ss);
-
- tmp = save_i387(fpstate);
- if (tmp < 0)
- err = 1;
- else
- err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
-
- /* non-iBCS2 extensions.. */
- err |= __put_user(mask, &sc->oldmask);
- err |= __put_user(current->thread.cr2, &sc->cr2);
-
- return err;
-}
-
-/*
- * Determine which stack to use..
- */
-static inline void *
-get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
-{
- unsigned long esp;
-
- /* Default to using normal stack */
- esp = regs->esp;
-
- /* This is the X/Open sanctioned signal stack switching. */
- if (ka->sa.sa_flags & SA_ONSTACK) {
- if (sas_ss_flags(esp) == 0)
- esp = current->sas_ss_sp + current->sas_ss_size;
- }
-
- /* This is the legacy signal stack switching. */
- else if ((regs->xss & 0xffff) != __USER_DS &&
- !(ka->sa.sa_flags & SA_RESTORER) &&
- ka->sa.sa_restorer) {
- esp = (unsigned long) ka->sa.sa_restorer;
- }
-
- return (void *)((esp - frame_size) & -8ul);
-}
-
-static void setup_frame(int sig, struct k_sigaction *ka,
- sigset_t *set, struct pt_regs * regs)
-{
- struct sigframe *frame;
- int err = 0;
-
- frame = get_sigframe(ka, regs, sizeof(*frame));
-
- if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
- goto give_sigsegv;
-
- err |= __put_user((current->exec_domain
- && current->exec_domain->signal_invmap
- && sig < 32
- ? current->exec_domain->signal_invmap[sig]
- : sig),
- &frame->sig);
- if (err)
- goto give_sigsegv;
-
- err |= setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
- if (err)
- goto give_sigsegv;
-
- if (_NSIG_WORDS > 1) {
- err |= __copy_to_user(frame->extramask, &set->sig[1],
- sizeof(frame->extramask));
- }
- if (err)
- goto give_sigsegv;
-
- /* Set up to return from userspace. If provided, use a stub
- already in userspace. */
- if (ka->sa.sa_flags & SA_RESTORER) {
- err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
- } else {
- err |= __put_user(frame->retcode, &frame->pretcode);
- /* This is popl %eax ; movl $,%eax ; int $0x80 */
- err |= __put_user(0xb858, (short *)(frame->retcode+0));
- err |= __put_user(__NR_sigreturn, (int *)(frame->retcode+2));
- err |= __put_user(0x80cd, (short *)(frame->retcode+6));
- }
-
- if (err)
- goto give_sigsegv;
-
- /* Set up registers for signal handler */
- regs->esp = (unsigned long) frame;
- regs->eip = (unsigned long) ka->sa.sa_handler;
-
- set_fs(USER_DS);
- regs->xds = __USER_DS;
- regs->xes = __USER_DS;
- regs->xss = __USER_DS;
- regs->xcs = __USER_CS;
- regs->eflags &= ~TF_MASK;
-
-#if DEBUG_SIG
- printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
- current->comm, current->pid, frame, regs->eip, frame->pretcode);
-#endif
-
- return;
-
-give_sigsegv:
- if (sig == SIGSEGV)
- ka->sa.sa_handler = SIG_DFL;
- force_sig(SIGSEGV, current);
-}
-
-static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- sigset_t *set, struct pt_regs * regs)
-{
- struct rt_sigframe *frame;
- int err = 0;
-
- frame = get_sigframe(ka, regs, sizeof(*frame));
-
- if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
- goto give_sigsegv;
-
- err |= __put_user((current->exec_domain
- && current->exec_domain->signal_invmap
- && sig < 32
- ? current->exec_domain->signal_invmap[sig]
- : sig),
- &frame->sig);
- err |= __put_user(&frame->info, &frame->pinfo);
- err |= __put_user(&frame->uc, &frame->puc);
- err |= copy_siginfo_to_user(&frame->info, info);
- if (err)
- goto give_sigsegv;
-
- /* Create the ucontext. */
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->esp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
- if (err)
- goto give_sigsegv;
-
- /* Set up to return from userspace. If provided, use a stub
- already in userspace. */
- if (ka->sa.sa_flags & SA_RESTORER) {
- err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
- } else {
- err |= __put_user(frame->retcode, &frame->pretcode);
- /* This is movl $,%eax ; int $0x80 */
- err |= __put_user(0xb8, (char *)(frame->retcode+0));
- err |= __put_user(__NR_rt_sigreturn, (int *)(frame->retcode+1));
- err |= __put_user(0x80cd, (short *)(frame->retcode+5));
- }
-
- if (err)
- goto give_sigsegv;
-
- /* Set up registers for signal handler */
- regs->esp = (unsigned long) frame;
- regs->eip = (unsigned long) ka->sa.sa_handler;
-
- set_fs(USER_DS);
- regs->xds = __USER_DS;
- regs->xes = __USER_DS;
- regs->xss = __USER_DS;
- regs->xcs = __USER_CS;
- regs->eflags &= ~TF_MASK;
-
-#if DEBUG_SIG
- printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
- current->comm, current->pid, frame, regs->eip, frame->pretcode);
-#endif
-
- return;
-
-give_sigsegv:
- if (sig == SIGSEGV)
- ka->sa.sa_handler = SIG_DFL;
- force_sig(SIGSEGV, current);
-}
-
-/*
- * OK, we're invoking a handler
- */
-
-static void
-handle_signal(unsigned long sig, struct k_sigaction *ka,
- siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
-{
- /* Are we from a system call? */
- if (regs->orig_eax >= 0) {
- /* If so, check system call restarting.. */
- switch (regs->eax) {
- case -ERESTARTNOHAND:
- regs->eax = -EINTR;
- break;
-
- case -ERESTARTSYS:
- if (!(ka->sa.sa_flags & SA_RESTART)) {
- regs->eax = -EINTR;
- break;
- }
- /* fallthrough */
- case -ERESTARTNOINTR:
- regs->eax = regs->orig_eax;
- regs->eip -= 2;
- }
- }
-
- /* Set up the stack frame */
- if (ka->sa.sa_flags & SA_SIGINFO)
- setup_rt_frame(sig, ka, info, oldset, regs);
- else
- setup_frame(sig, ka, oldset, regs);
-
- if (ka->sa.sa_flags & SA_ONESHOT)
- ka->sa.sa_handler = SIG_DFL;
-
- if (!(ka->sa.sa_flags & SA_NODEFER)) {
- spin_lock_irq(¤t->sigmask_lock);
- sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
- sigaddset(¤t->blocked,sig);
- recalc_sigpending(current);
- spin_unlock_irq(¤t->sigmask_lock);
- }
-}
-
-/*
- * Note that 'init' is a special process: it doesn't get signals it doesn't
- * want to handle. Thus you cannot kill init even with a SIGKILL even by
- * mistake.
- */
-int do_signal(struct pt_regs *regs, sigset_t *oldset)
-{
- siginfo_t info;
- struct k_sigaction *ka;
-
- /*
- * We want the common case to go fast, which
- * is why we may in certain cases get here from
- * kernel mode. Just return without doing anything
- * if so.
- */
- if ((regs->xcs & 2) != 2)
- return 1;
-
- if (!oldset)
- oldset = ¤t->blocked;
-
- for (;;) {
- unsigned long signr;
-
- spin_lock_irq(¤t->sigmask_lock);
- signr = dequeue_signal(¤t->blocked, &info);
- spin_unlock_irq(¤t->sigmask_lock);
-
- if (!signr)
- break;
-
- if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
- /* Let the debugger run. */
- current->exit_code = signr;
- current->state = TASK_STOPPED;
- notify_parent(current, SIGCHLD);
- schedule();
-
- /* We're back. Did the debugger cancel the sig? */
- if (!(signr = current->exit_code))
- continue;
- current->exit_code = 0;
-
- /* The debugger continued. Ignore SIGSTOP. */
- if (signr == SIGSTOP)
- continue;
-
- /* Update the siginfo structure. Is this good? */
- if (signr != info.si_signo) {
- info.si_signo = signr;
- info.si_errno = 0;
- info.si_code = SI_USER;
- info.si_pid = current->p_pptr->pid;
- info.si_uid = current->p_pptr->uid;
- }
-
- /* If the (new) signal is now blocked, requeue it. */
- if (sigismember(¤t->blocked, signr)) {
- send_sig_info(signr, &info, current);
- continue;
- }
- }
-
- ka = ¤t->sig->action[signr-1];
- if (ka->sa.sa_handler == SIG_IGN) {
- if (signr != SIGCHLD)
- continue;
- /* Check for SIGCHLD: it's special. */
- while (sys_wait4(-1, NULL, WNOHANG, NULL) > 0)
- /* nothing */;
- continue;
- }
-
- if (ka->sa.sa_handler == SIG_DFL) {
- int exit_code = signr;
-
- /* Init gets no signals it doesn't want. */
- if (current->pid == 1)
- continue;
-
- switch (signr) {
- case SIGCONT: case SIGCHLD: case SIGWINCH:
- continue;
-
- case SIGTSTP: case SIGTTIN: case SIGTTOU:
- if (is_orphaned_pgrp(current->pgrp))
- continue;
- /* FALLTHRU */
-
- case SIGSTOP: {
- struct signal_struct *sig;
- current->state = TASK_STOPPED;
- current->exit_code = signr;
- sig = current->p_pptr->sig;
- if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
- notify_parent(current, SIGCHLD);
- schedule();
- continue;
- }
-
- case SIGQUIT: case SIGILL: case SIGTRAP:
- case SIGABRT: case SIGFPE: case SIGSEGV:
- case SIGBUS: case SIGSYS: case SIGXCPU: case SIGXFSZ:
- if (do_coredump(signr, regs))
- exit_code |= 0x80;
- /* FALLTHRU */
-
- default:
- sigaddset(¤t->pending.signal, signr);
- recalc_sigpending(current);
- current->flags |= PF_SIGNALED;
- do_exit(exit_code);
- /* NOTREACHED */
- }
- }
-
- /* Reenable any watchpoints before delivering the
- * signal to user space. The processor register will
- * have been cleared if the watchpoint triggered
- * inside the kernel.
- */
- if ( current->thread.debugreg[7] != 0 )
- HYPERVISOR_set_debugreg(7, current->thread.debugreg[7]);
-
- /* Whee! Actually deliver the signal. */
- handle_signal(signr, ka, &info, oldset, regs);
- return 1;
- }
-
- /* Did we come from a system call? */
- if (regs->orig_eax >= 0) {
- /* Restart the system call - no handlers present */
- if (regs->eax == -ERESTARTNOHAND ||
- regs->eax == -ERESTARTSYS ||
- regs->eax == -ERESTARTNOINTR) {
- regs->eax = regs->orig_eax;
- regs->eip -= 2;
- }
- }
- return 0;
-}
+++ /dev/null
-/*
- * linux/arch/i386/kernel/sys_i386.c
- *
- * This file contains various random system calls that
- * have a non-standard calling sequence on the Linux/i386
- * platform.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/utsname.h>
-
-#include <asm/uaccess.h>
-#include <asm/ipc.h>
-
-/*
- * sys_pipe() is the normal C calling standard for creating
- * a pipe. It's not the way Unix traditionally does this, though.
- */
-asmlinkage int sys_pipe(unsigned long * fildes)
-{
- int fd[2];
- int error;
-
- error = do_pipe(fd);
- if (!error) {
- if (copy_to_user(fildes, fd, 2*sizeof(int)))
- error = -EFAULT;
- }
- return error;
-}
-
-/* common code for old and new mmaps */
-static inline long do_mmap2(
- unsigned long addr, unsigned long len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, unsigned long pgoff)
-{
- int error = -EBADF;
- struct file * file = NULL;
-
- flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- if (!(flags & MAP_ANONYMOUS)) {
- file = fget(fd);
- if (!file)
- goto out;
- }
-
- down_write(¤t->mm->mmap_sem);
- error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
- up_write(¤t->mm->mmap_sem);
-
- if (file)
- fput(file);
-out:
- return error;
-}
-
-asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, unsigned long pgoff)
-{
- return do_mmap2(addr, len, prot, flags, fd, pgoff);
-}
-
-/*
- * Perform the select(nd, in, out, ex, tv) and mmap() system
- * calls. Linux/i386 didn't use to be able to handle more than
- * 4 system call parameters, so these system calls used a memory
- * block for parameter passing..
- */
-
-struct mmap_arg_struct {
- unsigned long addr;
- unsigned long len;
- unsigned long prot;
- unsigned long flags;
- unsigned long fd;
- unsigned long offset;
-};
-
-asmlinkage int old_mmap(struct mmap_arg_struct *arg)
-{
- struct mmap_arg_struct a;
- int err = -EFAULT;
-
- if (copy_from_user(&a, arg, sizeof(a)))
- goto out;
-
- err = -EINVAL;
- if (a.offset & ~PAGE_MASK)
- goto out;
-
- err = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT);
-out:
- return err;
-}
-
-
-extern asmlinkage int sys_select(int, fd_set *, fd_set *, fd_set *, struct timeval *);
-
-struct sel_arg_struct {
- unsigned long n;
- fd_set *inp, *outp, *exp;
- struct timeval *tvp;
-};
-
-asmlinkage int old_select(struct sel_arg_struct *arg)
-{
- struct sel_arg_struct a;
-
- if (copy_from_user(&a, arg, sizeof(a)))
- return -EFAULT;
- /* sys_select() does the appropriate kernel locking */
- return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
-}
-
-/*
- * sys_ipc() is the de-multiplexer for the SysV IPC calls..
- *
- * This is really horribly ugly.
- */
-asmlinkage int sys_ipc (uint call, int first, int second,
- int third, void *ptr, long fifth)
-{
- int version, ret;
-
- version = call >> 16; /* hack for backward compatibility */
- call &= 0xffff;
-
- switch (call) {
- case SEMOP:
- return sys_semop (first, (struct sembuf *)ptr, second);
- case SEMGET:
- return sys_semget (first, second, third);
- case SEMCTL: {
- union semun fourth;
- if (!ptr)
- return -EINVAL;
- if (get_user(fourth.__pad, (void **) ptr))
- return -EFAULT;
- return sys_semctl (first, second, third, fourth);
- }
-
- case MSGSND:
- return sys_msgsnd (first, (struct msgbuf *) ptr,
- second, third);
- case MSGRCV:
- switch (version) {
- case 0: {
- struct ipc_kludge tmp;
- if (!ptr)
- return -EINVAL;
-
- if (copy_from_user(&tmp,
- (struct ipc_kludge *) ptr,
- sizeof (tmp)))
- return -EFAULT;
- return sys_msgrcv (first, tmp.msgp, second,
- tmp.msgtyp, third);
- }
- default:
- return sys_msgrcv (first,
- (struct msgbuf *) ptr,
- second, fifth, third);
- }
- case MSGGET:
- return sys_msgget ((key_t) first, second);
- case MSGCTL:
- return sys_msgctl (first, second, (struct msqid_ds *) ptr);
-
- case SHMAT:
- switch (version) {
- default: {
- ulong raddr;
- ret = sys_shmat (first, (char *) ptr, second, &raddr);
- if (ret)
- return ret;
- return put_user (raddr, (ulong *) third);
- }
- case 1: /* iBCS2 emulator entry point */
- if (!segment_eq(get_fs(), get_ds()))
- return -EINVAL;
- return sys_shmat (first, (char *) ptr, second, (ulong *) third);
- }
- case SHMDT:
- return sys_shmdt ((char *)ptr);
- case SHMGET:
- return sys_shmget (first, second, third);
- case SHMCTL:
- return sys_shmctl (first, second,
- (struct shmid_ds *) ptr);
- default:
- return -EINVAL;
- }
-}
-
-/*
- * Old cruft
- */
-asmlinkage int sys_uname(struct old_utsname * name)
-{
- int err;
- if (!name)
- return -EFAULT;
- down_read(&uts_sem);
- err=copy_to_user(name, &system_utsname, sizeof (*name));
- up_read(&uts_sem);
- return err?-EFAULT:0;
-}
-
-asmlinkage int sys_olduname(struct oldold_utsname * name)
-{
- int error;
-
- if (!name)
- return -EFAULT;
- if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
- return -EFAULT;
-
- down_read(&uts_sem);
-
- error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN);
- error |= __put_user(0,name->sysname+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN);
- error |= __put_user(0,name->nodename+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN);
- error |= __put_user(0,name->release+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN);
- error |= __put_user(0,name->version+__OLD_UTS_LEN);
- error |= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN);
- error |= __put_user(0,name->machine+__OLD_UTS_LEN);
-
- up_read(&uts_sem);
-
- error = error ? -EFAULT : 0;
-
- return error;
-}
-
-asmlinkage int sys_pause(void)
-{
- current->state = TASK_INTERRUPTIBLE;
- schedule();
- return -ERESTARTNOHAND;
-}
-
+++ /dev/null
-/* -*- Mode:C; c-basic-offset:4; tab-width:4 -*-
- ****************************************************************************
- * (C) 2002 - Rolf Neugebauer - Intel Research Cambridge
- ****************************************************************************
- *
- * File: arch.xeno/time.c
- * Author: Rolf Neugebauer
- * Changes:
- *
- * Date: Nov 2002
- *
- * Environment: XenoLinux
- * Description: Interface with Hypervisor to get correct notion of time
- * Currently supports Systemtime and WallClock time.
- *
- * (This has hardly any resemblence with the Linux code but left the
- * copyright notice anyway. Ignore the comments in the copyright notice.)
- ****************************************************************************
- * $Id: c-insert.c,v 1.7 2002/11/08 16:04:34 rn Exp $
- ****************************************************************************
- */
-
-/*
- * linux/arch/i386/kernel/time.c
- *
- * Copyright (C) 1991, 1992, 1995 Linus Torvalds
- *
- * This file contains the PC-specific time handling details:
- * reading the RTC at bootup, etc..
- * 1994-07-02 Alan Modra
- * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
- * 1995-03-26 Markus Kuhn
- * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
- * precision CMOS clock update
- * 1996-05-03 Ingo Molnar
- * fixed time warps in do_[slow|fast]_gettimeoffset()
- * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
- * "A Kernel Model for Precision Timekeeping" by Dave Mills
- * 1998-09-05 (Various)
- * More robust do_fast_gettimeoffset() algorithm implemented
- * (works with APM, Cyrix 6x86MX and Centaur C6),
- * monotonic gettimeofday() with fast_get_timeoffset(),
- * drift-proof precision TSC calibration on boot
- * (C. Scott Ananian <cananian@alumni.princeton.edu>, Andrew D.
- * Balsa <andrebalsa@altern.org>, Philip Gladstone <philip@raptor.com>;
- * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@tu-harburg.de>).
- * 1998-12-16 Andrea Arcangeli
- * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
- * because was not accounting lost_ticks.
- * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli
- * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
- * serialize accesses to xtime/lost_ticks).
- */
-
-#include <asm/smp.h>
-#include <asm/irq.h>
-#include <asm/msr.h>
-#include <asm/delay.h>
-#include <asm/mpspec.h>
-#include <asm/uaccess.h>
-#include <asm/processor.h>
-
-#include <asm/div64.h>
-#include <asm/hypervisor.h>
-
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/irq.h>
-
-#undef XENO_TIME_DEBUG /* adds sanity checks and periodic printouts */
-
-spinlock_t rtc_lock = SPIN_LOCK_UNLOCKED;
-extern rwlock_t xtime_lock;
-
-unsigned long cpu_khz; /* get this from Xen, used elsewhere */
-static spinlock_t hyp_stime_lock = SPIN_LOCK_UNLOCKED;
-static spinlock_t hyp_wctime_lock = SPIN_LOCK_UNLOCKED;
-
-static u32 st_scale_f;
-static u32 st_scale_i;
-static u32 shadow_st_pcc;
-static s64 shadow_st;
-
-/*
- * System time.
- * Although the rest of the Linux kernel doesn't know about this, we
- * we use it to extrapolate passage of wallclock time.
- * We need to read the values from the shared info page "atomically"
- * and use the cycle counter value as the "version" number. Clashes
- * should be very rare.
- */
-static inline long long get_s_time(void)
-{
- unsigned long flags;
- u32 delta_tsc, low, pcc;
- u64 delta;
- s64 now;
-
- spin_lock_irqsave(&hyp_stime_lock, flags);
-
- while ((pcc = HYPERVISOR_shared_info->st_timestamp) != shadow_st_pcc)
- {
- barrier();
- shadow_st_pcc = pcc;
- shadow_st = HYPERVISOR_shared_info->system_time;
- barrier();
- }
-
- now = shadow_st;
- /* only use bottom 32bits of TSC. This should be sufficient */
- rdtscl(low);
- delta_tsc = low - pcc;
- delta = ((u64)delta_tsc * st_scale_f);
- delta >>= 32;
- delta += ((u64)delta_tsc * st_scale_i);
-
- spin_unlock_irqrestore(&hyp_time_lock, flags);
-
- return now + delta;
-
-}
-#define NOW() ((long long)get_s_time())
-
-/*
- * Wallclock time.
- * Based on what the hypervisor tells us, extrapolated using system time.
- * Again need to read a number of values from the shared page "atomically".
- * this time using a version number.
- */
-static u32 shadow_wc_version=0;
-static long shadow_tv_sec;
-static long shadow_tv_usec;
-static long long shadow_wc_timestamp;
-void do_gettimeofday(struct timeval *tv)
-{
- unsigned long flags;
- long usec, sec;
- u32 version;
- u64 now;
-
- spin_lock_irqsave(&hyp_wctime_lock, flags);
-
- while ((version = HYPERVISOR_shared_info->wc_version)!= shadow_wc_version)
- {
- barrier();
- shadow_wc_version = version;
- shadow_tv_sec = HYPERVISOR_shared_info->tv_sec;
- shadow_tv_usec = HYPERVISOR_shared_info->tv_usec;
- shadow_wc_timestamp = HYPERVISOR_shared_info->wc_timestamp;
- barrier();
- }
-
- now = NOW();
- usec = ((unsigned long)(now-shadow_wc_timestamp))/1000;
- sec = shadow_tv_sec;
- usec += shadow_tv_usec;
-
- while ( usec >= 1000000 )
- {
- usec -= 1000000;
- sec++;
- }
-
- tv->tv_sec = sec;
- tv->tv_usec = usec;
-
- spin_unlock_irqrestore(&hyp_time_lock, flags);
-
-#ifdef XENO_TIME_DEBUG
- {
- static long long old_now=0;
- static long long wct=0, old_wct=0;
-
- /* This debug code checks if time increase over two subsequent calls */
- wct=(((long long)sec) * 1000000) + usec;
- /* wall clock time going backwards */
- if ((wct < old_wct) ) {
- printk("Urgh1: wc diff=%6ld, usec = %ld (0x%lX)\n",
- (long)(wct-old_wct), usec, usec);
- printk(" st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
- now-old_now, now, old_now);
- }
-
- /* system time going backwards */
- if (now<=old_now) {
- printk("Urgh2: st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
- now-old_now, now, old_now);
- }
- old_wct = wct;
- old_now = now;
- }
-#endif
-
-}
-
-void do_settimeofday(struct timeval *tv)
-{
-/* XXX RN: should do something special here for dom0 */
-#if 0
- write_lock_irq(&xtime_lock);
- /*
- * This is revolting. We need to set "xtime" correctly. However, the
- * value in this location is the value at the most recent update of
- * wall time. Discover what correction gettimeofday() would have
- * made, and then undo it!
- */
- tv->tv_usec -= do_gettimeoffset();
- tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ);
-
- while ( tv->tv_usec < 0 )
- {
- tv->tv_usec += 1000000;
- tv->tv_sec--;
- }
-
- xtime = *tv;
- time_adjust = 0; /* stop active adjtime() */
- time_status |= STA_UNSYNC;
- time_maxerror = NTP_PHASE_LIMIT;
- time_esterror = NTP_PHASE_LIMIT;
- write_unlock_irq(&xtime_lock);
-#endif
-}
-
-
-/*
- * Timer ISR.
- * Unlike normal Linux these don't come in at a fixed rate of HZ.
- * In here we wrok out how often it should have been called and then call
- * the architecture independent part (do_timer()) the appropriate number of
- * times. A bit of a nasty hack, to keep the "other" notion of wallclock time
- * happy.
- */
-static long long us_per_tick=1000000/HZ;
-static long long last_irq;
-static inline void do_timer_interrupt(int irq, void *dev_id,
- struct pt_regs *regs)
-{
- struct timeval tv;
- long long time, delta;
-
-#ifdef XENO_TIME_DEBUG
- static u32 foo_count = 0;
- foo_count++;
- if (foo_count>= 1000) {
- s64 n = NOW();
- struct timeval tv;
- do_gettimeofday(&tv);
- printk("0x%08X%08X %ld:%ld\n",
- (u32)(n>>32), (u32)n, tv.tv_sec, tv.tv_usec);
- foo_count = 0;
- }
-#endif
- /*
- * The next bit really sucks:
- * Linux not only uses do_gettimeofday() to keep a notion of
- * wallclock time, but also maintains the xtime struct and jiffies.
- * (Even worse some userland code accesses this via the sys_time()
- * system call)
- * Unfortunately, xtime is maintain in the architecture independent
- * part of the timer ISR (./kernel/timer.c sic!). So, although we have
- * perfectly valid notion of wallclock time from the hypervisor we here
- * fake missed timer interrupts so that the arch independent part of
- * the Timer ISR updates jiffies for us *and* once the bh gets run
- * updates xtime accordingly. Yuck!
- */
-
- /* work out the number of jiffies past and update them */
- do_gettimeofday(&tv);
- time = (((long long)tv.tv_sec) * 1000000) + tv.tv_usec;
- delta = time - last_irq;
- if (delta <= 0) {
- printk ("Timer ISR: Time went backwards: %lld\n", delta);
- return;
- }
- while (delta >= us_per_tick) {
- do_timer(regs);
- delta -= us_per_tick;
- last_irq += us_per_tick;
- }
-
-#if 0
- if (!user_mode(regs))
- x86_do_profile(regs->eip);
-#endif
-}
-
-static void timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
-{
- write_lock(&xtime_lock);
- do_timer_interrupt(irq, NULL, regs);
- write_unlock(&xtime_lock);
-}
-
-static struct irqaction irq_timer = {
- timer_interrupt,
- SA_INTERRUPT,
- 0,
- "timer",
- NULL,
- NULL
-};
-
-void __init time_init(void)
-{
- unsigned long long alarm;
- u64 cpu_freq = HYPERVISOR_shared_info->cpu_freq;
- u64 scale;
-
- do_get_fast_time = do_gettimeofday;
-
- cpu_khz = (u32)cpu_freq/1000;
- printk("Xen reported: %lu.%03lu MHz processor.\n",
- cpu_khz / 1000, cpu_khz % 1000);
-
- /*
- * calculate systemtime scaling factor
- * XXX RN: have to cast cpu_freq to u32 limits it to 4.29 GHz.
- * Get a better do_div!
- */
- scale = 1000000000LL << 32;
- do_div(scale,(u32)cpu_freq);
- st_scale_f = scale & 0xffffffff;
- st_scale_i = scale >> 32;
- printk("System Time scale: %X %X\n",st_scale_i, st_scale_f);
-
- do_gettimeofday(&xtime);
- last_irq = (((long long)xtime.tv_sec) * 1000000) + xtime.tv_usec;
-
- setup_irq(TIMER_IRQ, &irq_timer);
-
- /*
- * Start ticker. Note that timing runs of wall clock, not virtual
- * 'domain' time. This means that clock sshould run at the correct
- * rate. For things like scheduling, it's not clear whether it
- * matters which sort of time we use.
- * XXX RN: unimplemented.
- */
-
- rdtscll(alarm);
-#if 0
- alarm += (1000/HZ)*HYPERVISOR_shared_info->ticks_per_ms;
- HYPERVISOR_shared_info->wall_timeout = alarm;
- HYPERVISOR_shared_info->domain_timeout = ~0ULL;
-#endif
- clear_bit(_EVENT_TIMER, &HYPERVISOR_shared_info->events);
-}
+++ /dev/null
-/*
- * linux/arch/i386/traps.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-
-/*
- * 'Traps.c' handles hardware traps and faults after we have saved some
- * state in 'asm.s'.
- */
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/timer.h>
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/spinlock.h>
-#include <linux/interrupt.h>
-#include <linux/highmem.h>
-
-#include <linux/kdb.h>
-
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/atomic.h>
-#include <asm/debugreg.h>
-#include <asm/desc.h>
-#include <asm/i387.h>
-
-#include <asm/smp.h>
-#include <asm/pgalloc.h>
-
-#include <asm/hypervisor.h>
-
-#include <linux/irq.h>
-#include <linux/module.h>
-
-asmlinkage int system_call(void);
-
-asmlinkage void divide_error(void);
-asmlinkage void debug(void);
-asmlinkage void int3(void);
-asmlinkage void overflow(void);
-asmlinkage void bounds(void);
-asmlinkage void invalid_op(void);
-asmlinkage void device_not_available(void);
-asmlinkage void double_fault(void);
-asmlinkage void coprocessor_segment_overrun(void);
-asmlinkage void invalid_TSS(void);
-asmlinkage void segment_not_present(void);
-asmlinkage void stack_segment(void);
-asmlinkage void general_protection(void);
-asmlinkage void page_fault(void);
-asmlinkage void coprocessor_error(void);
-asmlinkage void simd_coprocessor_error(void);
-asmlinkage void alignment_check(void);
-asmlinkage void spurious_interrupt_bug(void);
-asmlinkage void machine_check(void);
-
-int kstack_depth_to_print = 24;
-
-
-/*
- * If the address is either in the .text section of the
- * kernel, or in the vmalloc'ed module regions, it *may*
- * be the address of a calling routine
- */
-
-#ifdef CONFIG_MODULES
-
-extern struct module *module_list;
-extern struct module kernel_module;
-
-static inline int kernel_text_address(unsigned long addr)
-{
- int retval = 0;
- struct module *mod;
-
- if (addr >= (unsigned long) &_stext &&
- addr <= (unsigned long) &_etext)
- return 1;
-
- for (mod = module_list; mod != &kernel_module; mod = mod->next) {
- /* mod_bound tests for addr being inside the vmalloc'ed
- * module area. Of course it'd be better to test only
- * for the .text subset... */
- if (mod_bound(addr, 0, mod)) {
- retval = 1;
- break;
- }
- }
-
- return retval;
-}
-
-#else
-
-static inline int kernel_text_address(unsigned long addr)
-{
- return (addr >= (unsigned long) &_stext &&
- addr <= (unsigned long) &_etext);
-}
-
-#endif
-
-void show_trace(unsigned long * stack)
-{
- int i;
- unsigned long addr;
-
- if (!stack)
- stack = (unsigned long*)&stack;
-
- printk("Call Trace: ");
- i = 1;
- while (((long) stack & (THREAD_SIZE-1)) != 0) {
- addr = *stack++;
- if (kernel_text_address(addr)) {
- if (i && ((i % 6) == 0))
- printk("\n ");
- printk("[<%08lx>] ", addr);
- i++;
- }
- }
- printk("\n");
-}
-
-void show_trace_task(struct task_struct *tsk)
-{
- unsigned long esp = tsk->thread.esp;
-
- /* User space on another CPU? */
- if ((esp ^ (unsigned long)tsk) & (PAGE_MASK<<1))
- return;
- show_trace((unsigned long *)esp);
-}
-
-void show_stack(unsigned long * esp)
-{
- unsigned long *stack;
- int i;
-
- // debugging aid: "show_stack(NULL);" prints the
- // back trace for this cpu.
-
- if(esp==NULL)
- esp=(unsigned long*)&esp;
-
- stack = esp;
- for(i=0; i < kstack_depth_to_print; i++) {
- if (((long) stack & (THREAD_SIZE-1)) == 0)
- break;
- if (i && ((i % 8) == 0))
- printk("\n ");
- printk("%08lx ", *stack++);
- }
- printk("\n");
- show_trace(esp);
-}
-
-void show_registers(struct pt_regs *regs)
-{
- int i;
- int in_kernel = 1;
- unsigned long esp;
- unsigned short ss;
-
- esp = (unsigned long) (®s->esp);
- ss = __KERNEL_DS;
- if (regs->xcs & 2) {
- in_kernel = 0;
- esp = regs->esp;
- ss = regs->xss & 0xffff;
- }
- printk("CPU: %d\nEIP: %04x:[<%08lx>] %s\nEFLAGS: %08lx\n",
- smp_processor_id(), 0xffff & regs->xcs, regs->eip, print_tainted(), regs->eflags);
- printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n",
- regs->eax, regs->ebx, regs->ecx, regs->edx);
- printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n",
- regs->esi, regs->edi, regs->ebp, esp);
- printk("ds: %04x es: %04x ss: %04x\n",
- regs->xds & 0xffff, regs->xes & 0xffff, ss);
- printk("Process %s (pid: %d, stackpage=%08lx)",
- current->comm, current->pid, 4096+(unsigned long)current);
- /*
- * When in-kernel, we also print out the stack and code at the
- * time of the fault..
- */
- if (in_kernel) {
-
- printk("\nStack: ");
- show_stack((unsigned long*)esp);
-
-#if 0
- printk("\nCode: ");
- if(regs->eip < PAGE_OFFSET)
- goto bad;
-
- for(i=0;i<20;i++)
- {
- unsigned char c;
- if(__get_user(c, &((unsigned char*)regs->eip)[i])) {
-bad:
- printk(" Bad EIP value.");
- break;
- }
- printk("%02x ", c);
- }
-#endif
- }
- printk("\n");
-}
-
-spinlock_t die_lock = SPIN_LOCK_UNLOCKED;
-
-void die(const char * str, struct pt_regs * regs, long err)
-{
- console_verbose();
- spin_lock_irq(&die_lock);
- bust_spinlocks(1);
- printk("%s: %04lx\n", str, err & 0xffff);
- show_registers(regs);
- bust_spinlocks(0);
- spin_unlock_irq(&die_lock);
- do_exit(SIGSEGV);
-}
-
-static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
-{
- if (!(2 & regs->xcs))
- die(str, regs, err);
-}
-
-
-static void inline do_trap(int trapnr, int signr, char *str,
- struct pt_regs * regs, long error_code,
- siginfo_t *info)
-{
- if (!(regs->xcs & 2))
- goto kernel_trap;
-
- /*trap_signal:*/ {
- struct task_struct *tsk = current;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = trapnr;
- if (info)
- force_sig_info(signr, info, tsk);
- else
- force_sig(signr, tsk);
- return;
- }
-
- kernel_trap: {
- unsigned long fixup = search_exception_table(regs->eip);
- if (fixup)
- regs->eip = fixup;
- else
- die(str, regs, error_code);
- return;
- }
-}
-
-#define DO_ERROR(trapnr, signr, str, name) \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
-{ \
- do_trap(trapnr, signr, str, regs, error_code, NULL); \
-}
-
-#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
-asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
-{ \
- siginfo_t info; \
- info.si_signo = signr; \
- info.si_errno = 0; \
- info.si_code = sicode; \
- info.si_addr = (void *)siaddr; \
- do_trap(trapnr, signr, str, regs, error_code, &info); \
-}
-
-DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip)
-DO_ERROR( 3, SIGTRAP, "int3", int3)
-DO_ERROR( 4, SIGSEGV, "overflow", overflow)
-DO_ERROR( 5, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip)
-DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
-DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
-DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
-DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
-DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
-DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
-DO_ERROR(18, SIGBUS, "machine check", machine_check)
-
-asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
-{
- if (!(regs->xcs & 2))
- goto gp_in_kernel;
-
- current->thread.error_code = error_code;
- current->thread.trap_no = 13;
- force_sig(SIGSEGV, current);
- return;
-
-gp_in_kernel:
- {
- unsigned long fixup;
- fixup = search_exception_table(regs->eip);
- if (fixup) {
- regs->eip = fixup;
- return;
- }
- die("general protection fault", regs, error_code);
- }
-}
-
-
-asmlinkage void do_debug(struct pt_regs * regs, long error_code)
-{
- unsigned int condition;
- struct task_struct *tsk = current;
- siginfo_t info;
-
- condition = HYPERVISOR_get_debugreg(6);
-
- /* Mask out spurious debug traps due to lazy DR7 setting */
- if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
- if (!tsk->thread.debugreg[7])
- goto clear_dr7;
- }
-
- /* Save debug status register where ptrace can see it */
- tsk->thread.debugreg[6] = condition;
-
- /* Mask out spurious TF errors due to lazy TF clearing */
- if (condition & DR_STEP) {
- /*
- * The TF error should be masked out only if the current
- * process is not traced and if the TRAP flag has been set
- * previously by a tracing process (condition detected by
- * the PT_DTRACE flag); remember that the i386 TRAP flag
- * can be modified by the process itself in user mode,
- * allowing programs to debug themselves without the ptrace()
- * interface.
- */
- if ((tsk->ptrace & (PT_DTRACE|PT_PTRACED)) == PT_DTRACE)
- goto clear_TF;
- }
-
- /* Ok, finally something we can handle */
- tsk->thread.trap_no = 1;
- tsk->thread.error_code = error_code;
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
-
- /* If this is a kernel mode trap, save the user PC on entry to
- * the kernel, that's what the debugger can make sense of.
- */
- info.si_addr = ((regs->xcs & 3) == 0) ? (void *)tsk->thread.eip :
- (void *)regs->eip;
- force_sig_info(SIGTRAP, &info, tsk);
-
- /* Disable additional traps. They'll be re-enabled when
- * the signal is delivered.
- */
- clear_dr7:
- HYPERVISOR_set_debugreg(7, 0);
- return;
-
- clear_TF:
- regs->eflags &= ~TF_MASK;
- return;
-}
-
-
-/*
- * Note that we play around with the 'TS' bit in an attempt to get
- * the correct behaviour even in the presence of the asynchronous
- * IRQ13 behaviour
- */
-void math_error(void *eip)
-{
- struct task_struct * task;
- siginfo_t info;
- unsigned short cwd, swd;
-
- /*
- * Save the info for the exception handler and clear the error.
- */
- task = current;
- save_init_fpu(task);
- task->thread.trap_no = 16;
- task->thread.error_code = 0;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = __SI_FAULT;
- info.si_addr = eip;
- /*
- * (~cwd & swd) will mask out exceptions that are not set to unmasked
- * status. 0x3f is the exception bits in these regs, 0x200 is the
- * C1 reg you need in case of a stack fault, 0x040 is the stack
- * fault bit. We should only be taking one exception at a time,
- * so if this combination doesn't produce any single exception,
- * then we have a bad program that isn't syncronizing its FPU usage
- * and it will suffer the consequences since we won't be able to
- * fully reproduce the context of the exception
- */
- cwd = get_fpu_cwd(task);
- swd = get_fpu_swd(task);
- switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) {
- case 0x000:
- default:
- break;
- case 0x001: /* Invalid Op */
- case 0x040: /* Stack Fault */
- case 0x240: /* Stack Fault | Direction */
- info.si_code = FPE_FLTINV;
- break;
- case 0x002: /* Denormalize */
- case 0x010: /* Underflow */
- info.si_code = FPE_FLTUND;
- break;
- case 0x004: /* Zero Divide */
- info.si_code = FPE_FLTDIV;
- break;
- case 0x008: /* Overflow */
- info.si_code = FPE_FLTOVF;
- break;
- case 0x020: /* Precision */
- info.si_code = FPE_FLTRES;
- break;
- }
- force_sig_info(SIGFPE, &info, task);
-}
-
-asmlinkage void do_coprocessor_error(struct pt_regs * regs, long error_code)
-{
- ignore_irq13 = 1;
- math_error((void *)regs->eip);
-}
-
-void simd_math_error(void *eip)
-{
- struct task_struct * task;
- siginfo_t info;
- unsigned short mxcsr;
-
- /*
- * Save the info for the exception handler and clear the error.
- */
- task = current;
- save_init_fpu(task);
- task->thread.trap_no = 19;
- task->thread.error_code = 0;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = __SI_FAULT;
- info.si_addr = eip;
- /*
- * The SIMD FPU exceptions are handled a little differently, as there
- * is only a single status/control register. Thus, to determine which
- * unmasked exception was caught we must mask the exception mask bits
- * at 0x1f80, and then use these to mask the exception bits at 0x3f.
- */
- mxcsr = get_fpu_mxcsr(task);
- switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
- case 0x000:
- default:
- break;
- case 0x001: /* Invalid Op */
- info.si_code = FPE_FLTINV;
- break;
- case 0x002: /* Denormalize */
- case 0x010: /* Underflow */
- info.si_code = FPE_FLTUND;
- break;
- case 0x004: /* Zero Divide */
- info.si_code = FPE_FLTDIV;
- break;
- case 0x008: /* Overflow */
- info.si_code = FPE_FLTOVF;
- break;
- case 0x020: /* Precision */
- info.si_code = FPE_FLTRES;
- break;
- }
- force_sig_info(SIGFPE, &info, task);
-}
-
-asmlinkage void do_simd_coprocessor_error(struct pt_regs * regs,
- long error_code)
-{
- if (cpu_has_xmm) {
- /* Handle SIMD FPU exceptions on PIII+ processors. */
- ignore_irq13 = 1;
- simd_math_error((void *)regs->eip);
- } else {
- die_if_kernel("cache flush denied", regs, error_code);
- current->thread.trap_no = 19;
- current->thread.error_code = error_code;
- force_sig(SIGSEGV, current);
- }
-}
-
-asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs,
- long error_code)
-{
-}
-
-/*
- * 'math_state_restore()' saves the current math information in the
- * old math state array, and gets the new ones from the current task
- *
- * Careful.. There are problems with IBM-designed IRQ13 behaviour.
- * Don't touch unless you *really* know how it works.
- */
-asmlinkage void math_state_restore(struct pt_regs regs)
-{
- if (current->used_math) {
- restore_fpu(current);
- } else {
- init_fpu();
- }
- current->flags |= PF_USEDFPU; /* So we fnsave on switch_to() */
-}
-
-static trap_info_t trap_table[] = {
- { 0, 0, __KERNEL_CS, (unsigned long)divide_error },
- { 1, 0, __KERNEL_CS, (unsigned long)debug },
- { 3, 3, __KERNEL_CS, (unsigned long)int3 },
- { 4, 3, __KERNEL_CS, (unsigned long)overflow },
- { 5, 3, __KERNEL_CS, (unsigned long)bounds },
- { 6, 0, __KERNEL_CS, (unsigned long)invalid_op },
- { 7, 0, __KERNEL_CS, (unsigned long)device_not_available },
- { 8, 0, __KERNEL_CS, (unsigned long)double_fault },
- { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun },
- { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS },
- { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present },
- { 12, 0, __KERNEL_CS, (unsigned long)stack_segment },
- { 13, 0, __KERNEL_CS, (unsigned long)general_protection },
- { 14, 0, __KERNEL_CS, (unsigned long)page_fault },
- { 15, 0, __KERNEL_CS, (unsigned long)spurious_interrupt_bug },
- { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error },
- { 17, 0, __KERNEL_CS, (unsigned long)alignment_check },
- { 18, 0, __KERNEL_CS, (unsigned long)machine_check },
- { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error },
- { SYSCALL_VECTOR,
- 3, __KERNEL_CS, (unsigned long)system_call },
- { 0, 0, 0, 0 }
-};
-
-
-
-void __init trap_init(void)
-{
- HYPERVISOR_set_trap_table(trap_table);
- HYPERVISOR_set_fast_trap(SYSCALL_VECTOR);
- cpu_init();
-}
+++ /dev/null
-
-.S.o:
- $(CC) $(AFLAGS) -c $< -o $*.o
-
-L_TARGET = lib.a
-
-obj-y = checksum.o old-checksum.o delay.o \
- usercopy.o getuser.o \
- memcpy.o strstr.o
-
-obj-$(CONFIG_X86_USE_3DNOW) += mmx.o
-obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
-obj-$(CONFIG_DEBUG_IOVIRT) += iodebug.o
-
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/*
- * INET An implementation of the TCP/IP protocol suite for the LINUX
- * operating system. INET is implemented using the BSD Socket
- * interface as the means of communication with the user level.
- *
- * IP/TCP/UDP checksumming routines
- *
- * Authors: Jorge Cwik, <jorge@laser.satlink.net>
- * Arnt Gulbrandsen, <agulbra@nvg.unit.no>
- * Tom May, <ftom@netcom.com>
- * Pentium Pro/II routines:
- * Alexander Kjeldaas <astor@guardian.no>
- * Finn Arne Gangstad <finnag@guardian.no>
- * Lots of code moved from tcp.c and ip.c; see those files
- * for more names.
- *
- * Changes: Ingo Molnar, converted csum_partial_copy() to 2.1 exception
- * handling.
- * Andi Kleen, add zeroing on error
- * converted to pure assembler
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/config.h>
-#include <asm/errno.h>
-
-/*
- * computes a partial checksum, e.g. for TCP/UDP fragments
- */
-
-/*
-unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
- */
-
-.text
-.align 4
-.globl csum_partial
-
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
- /*
- * Experiments with Ethernet and SLIP connections show that buff
- * is aligned on either a 2-byte or 4-byte boundary. We get at
- * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
- * Fortunately, it is easy to convert 2-byte alignment to 4-byte
- * alignment for the unrolled loop.
- */
-csum_partial:
- pushl %esi
- pushl %ebx
- movl 20(%esp),%eax # Function arg: unsigned int sum
- movl 16(%esp),%ecx # Function arg: int len
- movl 12(%esp),%esi # Function arg: unsigned char *buff
- testl $2, %esi # Check alignment.
- jz 2f # Jump if alignment is ok.
- subl $2, %ecx # Alignment uses up two bytes.
- jae 1f # Jump if we had at least two bytes.
- addl $2, %ecx # ecx was < 2. Deal with it.
- jmp 4f
-1: movw (%esi), %bx
- addl $2, %esi
- addw %bx, %ax
- adcl $0, %eax
-2:
- movl %ecx, %edx
- shrl $5, %ecx
- jz 2f
- testl %esi, %esi
-1: movl (%esi), %ebx
- adcl %ebx, %eax
- movl 4(%esi), %ebx
- adcl %ebx, %eax
- movl 8(%esi), %ebx
- adcl %ebx, %eax
- movl 12(%esi), %ebx
- adcl %ebx, %eax
- movl 16(%esi), %ebx
- adcl %ebx, %eax
- movl 20(%esi), %ebx
- adcl %ebx, %eax
- movl 24(%esi), %ebx
- adcl %ebx, %eax
- movl 28(%esi), %ebx
- adcl %ebx, %eax
- lea 32(%esi), %esi
- dec %ecx
- jne 1b
- adcl $0, %eax
-2: movl %edx, %ecx
- andl $0x1c, %edx
- je 4f
- shrl $2, %edx # This clears CF
-3: adcl (%esi), %eax
- lea 4(%esi), %esi
- dec %edx
- jne 3b
- adcl $0, %eax
-4: andl $3, %ecx
- jz 7f
- cmpl $2, %ecx
- jb 5f
- movw (%esi),%cx
- leal 2(%esi),%esi
- je 6f
- shll $16,%ecx
-5: movb (%esi),%cl
-6: addl %ecx,%eax
- adcl $0, %eax
-7:
- popl %ebx
- popl %esi
- ret
-
-#else
-
-/* Version for PentiumII/PPro */
-
-csum_partial:
- pushl %esi
- pushl %ebx
- movl 20(%esp),%eax # Function arg: unsigned int sum
- movl 16(%esp),%ecx # Function arg: int len
- movl 12(%esp),%esi # Function arg: const unsigned char *buf
-
- testl $2, %esi
- jnz 30f
-10:
- movl %ecx, %edx
- movl %ecx, %ebx
- andl $0x7c, %ebx
- shrl $7, %ecx
- addl %ebx,%esi
- shrl $2, %ebx
- negl %ebx
- lea 45f(%ebx,%ebx,2), %ebx
- testl %esi, %esi
- jmp *%ebx
-
- # Handle 2-byte-aligned regions
-20: addw (%esi), %ax
- lea 2(%esi), %esi
- adcl $0, %eax
- jmp 10b
-
-30: subl $2, %ecx
- ja 20b
- je 32f
- movzbl (%esi),%ebx # csumming 1 byte, 2-aligned
- addl %ebx, %eax
- adcl $0, %eax
- jmp 80f
-32:
- addw (%esi), %ax # csumming 2 bytes, 2-aligned
- adcl $0, %eax
- jmp 80f
-
-40:
- addl -128(%esi), %eax
- adcl -124(%esi), %eax
- adcl -120(%esi), %eax
- adcl -116(%esi), %eax
- adcl -112(%esi), %eax
- adcl -108(%esi), %eax
- adcl -104(%esi), %eax
- adcl -100(%esi), %eax
- adcl -96(%esi), %eax
- adcl -92(%esi), %eax
- adcl -88(%esi), %eax
- adcl -84(%esi), %eax
- adcl -80(%esi), %eax
- adcl -76(%esi), %eax
- adcl -72(%esi), %eax
- adcl -68(%esi), %eax
- adcl -64(%esi), %eax
- adcl -60(%esi), %eax
- adcl -56(%esi), %eax
- adcl -52(%esi), %eax
- adcl -48(%esi), %eax
- adcl -44(%esi), %eax
- adcl -40(%esi), %eax
- adcl -36(%esi), %eax
- adcl -32(%esi), %eax
- adcl -28(%esi), %eax
- adcl -24(%esi), %eax
- adcl -20(%esi), %eax
- adcl -16(%esi), %eax
- adcl -12(%esi), %eax
- adcl -8(%esi), %eax
- adcl -4(%esi), %eax
-45:
- lea 128(%esi), %esi
- adcl $0, %eax
- dec %ecx
- jge 40b
- movl %edx, %ecx
-50: andl $3, %ecx
- jz 80f
-
- # Handle the last 1-3 bytes without jumping
- notl %ecx # 1->2, 2->1, 3->0, higher bits are masked
- movl $0xffffff,%ebx # by the shll and shrl instructions
- shll $3,%ecx
- shrl %cl,%ebx
- andl -128(%esi),%ebx # esi is 4-aligned so should be ok
- addl %ebx,%eax
- adcl $0,%eax
-80:
- popl %ebx
- popl %esi
- ret
-
-#endif
-
-/*
-unsigned int csum_partial_copy_generic (const char *src, char *dst,
- int len, int sum, int *src_err_ptr, int *dst_err_ptr)
- */
-
-/*
- * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- * DST definitions? It's damn hard to trigger all cases. I hope I got
- * them all but there's no guarantee.
- */
-
-#define SRC(y...) \
- 9999: y; \
- .section __ex_table, "a"; \
- .long 9999b, 6001f ; \
- .previous
-
-#define DST(y...) \
- 9999: y; \
- .section __ex_table, "a"; \
- .long 9999b, 6002f ; \
- .previous
-
-.align 4
-.globl csum_partial_copy_generic
-
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
-#define ARGBASE 16
-#define FP 12
-
-csum_partial_copy_generic:
- subl $4,%esp
- pushl %edi
- pushl %esi
- pushl %ebx
- movl ARGBASE+16(%esp),%eax # sum
- movl ARGBASE+12(%esp),%ecx # len
- movl ARGBASE+4(%esp),%esi # src
- movl ARGBASE+8(%esp),%edi # dst
-
- testl $2, %edi # Check alignment.
- jz 2f # Jump if alignment is ok.
- subl $2, %ecx # Alignment uses up two bytes.
- jae 1f # Jump if we had at least two bytes.
- addl $2, %ecx # ecx was < 2. Deal with it.
- jmp 4f
-SRC(1: movw (%esi), %bx )
- addl $2, %esi
-DST( movw %bx, (%edi) )
- addl $2, %edi
- addw %bx, %ax
- adcl $0, %eax
-2:
- movl %ecx, FP(%esp)
- shrl $5, %ecx
- jz 2f
- testl %esi, %esi
-SRC(1: movl (%esi), %ebx )
-SRC( movl 4(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, (%edi) )
- adcl %edx, %eax
-DST( movl %edx, 4(%edi) )
-
-SRC( movl 8(%esi), %ebx )
-SRC( movl 12(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, 8(%edi) )
- adcl %edx, %eax
-DST( movl %edx, 12(%edi) )
-
-SRC( movl 16(%esi), %ebx )
-SRC( movl 20(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, 16(%edi) )
- adcl %edx, %eax
-DST( movl %edx, 20(%edi) )
-
-SRC( movl 24(%esi), %ebx )
-SRC( movl 28(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, 24(%edi) )
- adcl %edx, %eax
-DST( movl %edx, 28(%edi) )
-
- lea 32(%esi), %esi
- lea 32(%edi), %edi
- dec %ecx
- jne 1b
- adcl $0, %eax
-2: movl FP(%esp), %edx
- movl %edx, %ecx
- andl $0x1c, %edx
- je 4f
- shrl $2, %edx # This clears CF
-SRC(3: movl (%esi), %ebx )
- adcl %ebx, %eax
-DST( movl %ebx, (%edi) )
- lea 4(%esi), %esi
- lea 4(%edi), %edi
- dec %edx
- jne 3b
- adcl $0, %eax
-4: andl $3, %ecx
- jz 7f
- cmpl $2, %ecx
- jb 5f
-SRC( movw (%esi), %cx )
- leal 2(%esi), %esi
-DST( movw %cx, (%edi) )
- leal 2(%edi), %edi
- je 6f
- shll $16,%ecx
-SRC(5: movb (%esi), %cl )
-DST( movb %cl, (%edi) )
-6: addl %ecx, %eax
- adcl $0, %eax
-7:
-5000:
-
-# Exception handler:
-.section .fixup, "ax"
-
-6001:
- movl ARGBASE+20(%esp), %ebx # src_err_ptr
- movl $-EFAULT, (%ebx)
-
- # zero the complete destination - computing the rest
- # is too much work
- movl ARGBASE+8(%esp), %edi # dst
- movl ARGBASE+12(%esp), %ecx # len
- xorl %eax,%eax
- rep ; stosb
-
- jmp 5000b
-
-6002:
- movl ARGBASE+24(%esp), %ebx # dst_err_ptr
- movl $-EFAULT,(%ebx)
- jmp 5000b
-
-.previous
-
- popl %ebx
- popl %esi
- popl %edi
- popl %ecx # equivalent to addl $4,%esp
- ret
-
-#else
-
-/* Version for PentiumII/PPro */
-
-#define ROUND1(x) \
- SRC(movl x(%esi), %ebx ) ; \
- addl %ebx, %eax ; \
- DST(movl %ebx, x(%edi) ) ;
-
-#define ROUND(x) \
- SRC(movl x(%esi), %ebx ) ; \
- adcl %ebx, %eax ; \
- DST(movl %ebx, x(%edi) ) ;
-
-#define ARGBASE 12
-
-csum_partial_copy_generic:
- pushl %ebx
- pushl %edi
- pushl %esi
- movl ARGBASE+4(%esp),%esi #src
- movl ARGBASE+8(%esp),%edi #dst
- movl ARGBASE+12(%esp),%ecx #len
- movl ARGBASE+16(%esp),%eax #sum
-# movl %ecx, %edx
- movl %ecx, %ebx
- movl %esi, %edx
- shrl $6, %ecx
- andl $0x3c, %ebx
- negl %ebx
- subl %ebx, %esi
- subl %ebx, %edi
- lea -1(%esi),%edx
- andl $-32,%edx
- lea 3f(%ebx,%ebx), %ebx
- testl %esi, %esi
- jmp *%ebx
-1: addl $64,%esi
- addl $64,%edi
- SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
- ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)
- ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)
- ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)
- ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4)
-3: adcl $0,%eax
- addl $64, %edx
- dec %ecx
- jge 1b
-4: movl ARGBASE+12(%esp),%edx #len
- andl $3, %edx
- jz 7f
- cmpl $2, %edx
- jb 5f
-SRC( movw (%esi), %dx )
- leal 2(%esi), %esi
-DST( movw %dx, (%edi) )
- leal 2(%edi), %edi
- je 6f
- shll $16,%edx
-5:
-SRC( movb (%esi), %dl )
-DST( movb %dl, (%edi) )
-6: addl %edx, %eax
- adcl $0, %eax
-7:
-.section .fixup, "ax"
-6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr
- movl $-EFAULT, (%ebx)
- # zero the complete destination (computing the rest is too much work)
- movl ARGBASE+8(%esp),%edi # dst
- movl ARGBASE+12(%esp),%ecx # len
- xorl %eax,%eax
- rep; stosb
- jmp 7b
-6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr
- movl $-EFAULT, (%ebx)
- jmp 7b
-.previous
-
- popl %esi
- popl %edi
- popl %ebx
- ret
-
-#undef ROUND
-#undef ROUND1
-
-#endif
+++ /dev/null
-/*
- * x86 version of "atomic_dec_and_lock()" using
- * the atomic "cmpxchg" instruction.
- *
- * (For CPU's lacking cmpxchg, we use the slow
- * generic version, and this one never even gets
- * compiled).
- */
-
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-
-int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
-{
- int counter;
- int newcount;
-
-repeat:
- counter = atomic_read(atomic);
- newcount = counter-1;
-
- if (!newcount)
- goto slow_path;
-
- asm volatile("lock; cmpxchgl %1,%2"
- :"=a" (newcount)
- :"r" (newcount), "m" (atomic->counter), "0" (counter));
-
- /* If the above failed, "eax" will have changed */
- if (newcount != counter)
- goto repeat;
- return 0;
-
-slow_path:
- spin_lock(lock);
- if (atomic_dec_and_test(atomic))
- return 1;
- spin_unlock(lock);
- return 0;
-}
+++ /dev/null
-/*
- * Precise Delay Loops for i386
- *
- * Copyright (C) 1993 Linus Torvalds
- * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
- *
- * The __delay function must _NOT_ be inlined as its execution time
- * depends wildly on alignment on many x86 processors. The additional
- * jump magic is needed to get the timing stable on all the CPU's
- * we have to worry about.
- */
-
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <linux/delay.h>
-#include <asm/processor.h>
-#include <asm/delay.h>
-
-#ifdef CONFIG_SMP
-#include <asm/smp.h>
-#endif
-
-void __delay(unsigned long loops)
-{
- unsigned long bclock, now;
-
- rdtscl(bclock);
- do
- {
- rep_nop();
- rdtscl(now);
- } while ((now-bclock) < loops);
-}
-
-inline void __const_udelay(unsigned long xloops)
-{
- int d0;
- __asm__("mull %0"
- :"=d" (xloops), "=&a" (d0)
- :"1" (xloops),"0" (current_cpu_data.loops_per_jiffy));
- __delay(xloops * HZ);
-}
-
-void __udelay(unsigned long usecs)
-{
- __const_udelay(usecs * 0x000010c6); /* 2**32 / 1000000 */
-}
+++ /dev/null
-/*
- * __get_user functions.
- *
- * (C) Copyright 1998 Linus Torvalds
- *
- * These functions have a non-standard call interface
- * to make them more efficient, especially as they
- * return an error value in addition to the "real"
- * return value.
- */
-
-/*
- * __get_user_X
- *
- * Inputs: %eax contains the address
- *
- * Outputs: %eax is error code (0 or -EFAULT)
- * %edx contains zero-extended value
- *
- * These functions should not modify any other registers,
- * as they get called from within inline assembly.
- */
-
-addr_limit = 12
-
-.text
-.align 4
-.globl __get_user_1
-__get_user_1:
- movl %esp,%edx
- andl $0xffffe000,%edx
- cmpl addr_limit(%edx),%eax
- jae bad_get_user
-1: movzbl (%eax),%edx
- xorl %eax,%eax
- ret
-
-.align 4
-.globl __get_user_2
-__get_user_2:
- addl $1,%eax
- movl %esp,%edx
- jc bad_get_user
- andl $0xffffe000,%edx
- cmpl addr_limit(%edx),%eax
- jae bad_get_user
-2: movzwl -1(%eax),%edx
- xorl %eax,%eax
- ret
-
-.align 4
-.globl __get_user_4
-__get_user_4:
- addl $3,%eax
- movl %esp,%edx
- jc bad_get_user
- andl $0xffffe000,%edx
- cmpl addr_limit(%edx),%eax
- jae bad_get_user
-3: movl -3(%eax),%edx
- xorl %eax,%eax
- ret
-
-bad_get_user:
- xorl %edx,%edx
- movl $-14,%eax
- ret
-
-.section __ex_table,"a"
- .long 1b,bad_get_user
- .long 2b,bad_get_user
- .long 3b,bad_get_user
-.previous
+++ /dev/null
-#include <asm/io.h>
-
-void * __io_virt_debug(unsigned long x, const char *file, int line)
-{
- if (x < PAGE_OFFSET) {
- printk("io mapaddr 0x%05lx not valid at %s:%d!\n", x, file, line);
- return __va(x);
- }
- return (void *)x;
-}
-
-unsigned long __io_phys_debug(unsigned long x, const char *file, int line)
-{
- if (x < PAGE_OFFSET) {
- printk("io mapaddr 0x%05lx not valid at %s:%d!\n", x, file, line);
- return x;
- }
- return __pa(x);
-}
+++ /dev/null
-#include <linux/config.h>
-#include <linux/string.h>
-
-#undef memcpy
-#undef memset
-
-void * memcpy(void * to, const void * from, size_t n)
-{
-#ifdef CONFIG_X86_USE_3DNOW
- return __memcpy3d(to, from, n);
-#else
- return __memcpy(to, from, n);
-#endif
-}
-
-void * memset(void * s, int c, size_t count)
-{
- return __memset(s, c, count);
-}
+++ /dev/null
-#include <linux/config.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/sched.h>
-
-#include <asm/i387.h>
-#include <asm/hardirq.h>
-
-
-/*
- * MMX 3DNow! library helper functions
- *
- * To do:
- * We can use MMX just for prefetch in IRQ's. This may be a win.
- * (reported so on K6-III)
- * We should use a better code neutral filler for the short jump
- * leal ebx. [ebx] is apparently best for K6-2, but Cyrix ??
- * We also want to clobber the filler register so we dont get any
- * register forwarding stalls on the filler.
- *
- * Add *user handling. Checksums are not a win with MMX on any CPU
- * tested so far for any MMX solution figured.
- *
- * 22/09/2000 - Arjan van de Ven
- * Improved for non-egineering-sample Athlons
- *
- */
-
-void *_mmx_memcpy(void *to, const void *from, size_t len)
-{
- void *p;
- int i;
-
- if (in_interrupt())
- return __memcpy(to, from, len);
-
- p = to;
- i = len >> 6; /* len/64 */
-
- kernel_fpu_begin();
-
- __asm__ __volatile__ (
- "1: prefetch (%0)\n" /* This set is 28 bytes */
- " prefetch 64(%0)\n"
- " prefetch 128(%0)\n"
- " prefetch 192(%0)\n"
- " prefetch 256(%0)\n"
- "2: \n"
- ".section .fixup, \"ax\"\n"
- "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
- " jmp 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b, 3b\n"
- ".previous"
- : : "r" (from) );
-
-
- for(; i>0; i--)
- {
- __asm__ __volatile__ (
- "1: prefetch 320(%0)\n"
- "2: movq (%0), %%mm0\n"
- " movq 8(%0), %%mm1\n"
- " movq 16(%0), %%mm2\n"
- " movq 24(%0), %%mm3\n"
- " movq %%mm0, (%1)\n"
- " movq %%mm1, 8(%1)\n"
- " movq %%mm2, 16(%1)\n"
- " movq %%mm3, 24(%1)\n"
- " movq 32(%0), %%mm0\n"
- " movq 40(%0), %%mm1\n"
- " movq 48(%0), %%mm2\n"
- " movq 56(%0), %%mm3\n"
- " movq %%mm0, 32(%1)\n"
- " movq %%mm1, 40(%1)\n"
- " movq %%mm2, 48(%1)\n"
- " movq %%mm3, 56(%1)\n"
- ".section .fixup, \"ax\"\n"
- "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
- " jmp 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b, 3b\n"
- ".previous"
- : : "r" (from), "r" (to) : "memory");
- from+=64;
- to+=64;
- }
- /*
- * Now do the tail of the block
- */
- __memcpy(to, from, len&63);
- kernel_fpu_end();
- return p;
-}
-
-#ifdef CONFIG_MK7
-
-/*
- * The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
- * other MMX using processors do not.
- */
-
-static void fast_clear_page(void *page)
-{
- int i;
-
- kernel_fpu_begin();
-
- __asm__ __volatile__ (
- " pxor %%mm0, %%mm0\n" : :
- );
-
- for(i=0;i<4096/64;i++)
- {
- __asm__ __volatile__ (
- " movntq %%mm0, (%0)\n"
- " movntq %%mm0, 8(%0)\n"
- " movntq %%mm0, 16(%0)\n"
- " movntq %%mm0, 24(%0)\n"
- " movntq %%mm0, 32(%0)\n"
- " movntq %%mm0, 40(%0)\n"
- " movntq %%mm0, 48(%0)\n"
- " movntq %%mm0, 56(%0)\n"
- : : "r" (page) : "memory");
- page+=64;
- }
- /* since movntq is weakly-ordered, a "sfence" is needed to become
- * ordered again.
- */
- __asm__ __volatile__ (
- " sfence \n" : :
- );
- kernel_fpu_end();
-}
-
-static void fast_copy_page(void *to, void *from)
-{
- int i;
-
- kernel_fpu_begin();
-
- /* maybe the prefetch stuff can go before the expensive fnsave...
- * but that is for later. -AV
- */
- __asm__ __volatile__ (
- "1: prefetch (%0)\n"
- " prefetch 64(%0)\n"
- " prefetch 128(%0)\n"
- " prefetch 192(%0)\n"
- " prefetch 256(%0)\n"
- "2: \n"
- ".section .fixup, \"ax\"\n"
- "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
- " jmp 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b, 3b\n"
- ".previous"
- : : "r" (from) );
-
- for(i=0; i<(4096-320)/64; i++)
- {
- __asm__ __volatile__ (
- "1: prefetch 320(%0)\n"
- "2: movq (%0), %%mm0\n"
- " movntq %%mm0, (%1)\n"
- " movq 8(%0), %%mm1\n"
- " movntq %%mm1, 8(%1)\n"
- " movq 16(%0), %%mm2\n"
- " movntq %%mm2, 16(%1)\n"
- " movq 24(%0), %%mm3\n"
- " movntq %%mm3, 24(%1)\n"
- " movq 32(%0), %%mm4\n"
- " movntq %%mm4, 32(%1)\n"
- " movq 40(%0), %%mm5\n"
- " movntq %%mm5, 40(%1)\n"
- " movq 48(%0), %%mm6\n"
- " movntq %%mm6, 48(%1)\n"
- " movq 56(%0), %%mm7\n"
- " movntq %%mm7, 56(%1)\n"
- ".section .fixup, \"ax\"\n"
- "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
- " jmp 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b, 3b\n"
- ".previous"
- : : "r" (from), "r" (to) : "memory");
- from+=64;
- to+=64;
- }
- for(i=(4096-320)/64; i<4096/64; i++)
- {
- __asm__ __volatile__ (
- "2: movq (%0), %%mm0\n"
- " movntq %%mm0, (%1)\n"
- " movq 8(%0), %%mm1\n"
- " movntq %%mm1, 8(%1)\n"
- " movq 16(%0), %%mm2\n"
- " movntq %%mm2, 16(%1)\n"
- " movq 24(%0), %%mm3\n"
- " movntq %%mm3, 24(%1)\n"
- " movq 32(%0), %%mm4\n"
- " movntq %%mm4, 32(%1)\n"
- " movq 40(%0), %%mm5\n"
- " movntq %%mm5, 40(%1)\n"
- " movq 48(%0), %%mm6\n"
- " movntq %%mm6, 48(%1)\n"
- " movq 56(%0), %%mm7\n"
- " movntq %%mm7, 56(%1)\n"
- : : "r" (from), "r" (to) : "memory");
- from+=64;
- to+=64;
- }
- /* since movntq is weakly-ordered, a "sfence" is needed to become
- * ordered again.
- */
- __asm__ __volatile__ (
- " sfence \n" : :
- );
- kernel_fpu_end();
-}
-
-#else
-
-/*
- * Generic MMX implementation without K7 specific streaming
- */
-
-static void fast_clear_page(void *page)
-{
- int i;
-
- kernel_fpu_begin();
-
- __asm__ __volatile__ (
- " pxor %%mm0, %%mm0\n" : :
- );
-
- for(i=0;i<4096/128;i++)
- {
- __asm__ __volatile__ (
- " movq %%mm0, (%0)\n"
- " movq %%mm0, 8(%0)\n"
- " movq %%mm0, 16(%0)\n"
- " movq %%mm0, 24(%0)\n"
- " movq %%mm0, 32(%0)\n"
- " movq %%mm0, 40(%0)\n"
- " movq %%mm0, 48(%0)\n"
- " movq %%mm0, 56(%0)\n"
- " movq %%mm0, 64(%0)\n"
- " movq %%mm0, 72(%0)\n"
- " movq %%mm0, 80(%0)\n"
- " movq %%mm0, 88(%0)\n"
- " movq %%mm0, 96(%0)\n"
- " movq %%mm0, 104(%0)\n"
- " movq %%mm0, 112(%0)\n"
- " movq %%mm0, 120(%0)\n"
- : : "r" (page) : "memory");
- page+=128;
- }
-
- kernel_fpu_end();
-}
-
-static void fast_copy_page(void *to, void *from)
-{
- int i;
-
-
- kernel_fpu_begin();
-
- __asm__ __volatile__ (
- "1: prefetch (%0)\n"
- " prefetch 64(%0)\n"
- " prefetch 128(%0)\n"
- " prefetch 192(%0)\n"
- " prefetch 256(%0)\n"
- "2: \n"
- ".section .fixup, \"ax\"\n"
- "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
- " jmp 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b, 3b\n"
- ".previous"
- : : "r" (from) );
-
- for(i=0; i<4096/64; i++)
- {
- __asm__ __volatile__ (
- "1: prefetch 320(%0)\n"
- "2: movq (%0), %%mm0\n"
- " movq 8(%0), %%mm1\n"
- " movq 16(%0), %%mm2\n"
- " movq 24(%0), %%mm3\n"
- " movq %%mm0, (%1)\n"
- " movq %%mm1, 8(%1)\n"
- " movq %%mm2, 16(%1)\n"
- " movq %%mm3, 24(%1)\n"
- " movq 32(%0), %%mm0\n"
- " movq 40(%0), %%mm1\n"
- " movq 48(%0), %%mm2\n"
- " movq 56(%0), %%mm3\n"
- " movq %%mm0, 32(%1)\n"
- " movq %%mm1, 40(%1)\n"
- " movq %%mm2, 48(%1)\n"
- " movq %%mm3, 56(%1)\n"
- ".section .fixup, \"ax\"\n"
- "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
- " jmp 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b, 3b\n"
- ".previous"
- : : "r" (from), "r" (to) : "memory");
- from+=64;
- to+=64;
- }
- kernel_fpu_end();
-}
-
-
-#endif
-
-/*
- * Favour MMX for page clear and copy.
- */
-
-static void slow_zero_page(void * page)
-{
- int d0, d1;
- __asm__ __volatile__( \
- "cld\n\t" \
- "rep ; stosl" \
- : "=&c" (d0), "=&D" (d1)
- :"a" (0),"1" (page),"0" (1024)
- :"memory");
-}
-
-void mmx_clear_page(void * page)
-{
- if(in_interrupt())
- slow_zero_page(page);
- else
- fast_clear_page(page);
-}
-
-static void slow_copy_page(void *to, void *from)
-{
- int d0, d1, d2;
- __asm__ __volatile__( \
- "cld\n\t" \
- "rep ; movsl" \
- : "=&c" (d0), "=&D" (d1), "=&S" (d2) \
- : "0" (1024),"1" ((long) to),"2" ((long) from) \
- : "memory");
-}
-
-
-void mmx_copy_page(void *to, void *from)
-{
- if(in_interrupt())
- slow_copy_page(to, from);
- else
- fast_copy_page(to, from);
-}
+++ /dev/null
-/*
- * FIXME: old compatibility stuff, will be removed soon.
- */
-
-#include <net/checksum.h>
-
-unsigned int csum_partial_copy( const char *src, char *dst, int len, int sum)
-{
- int src_err=0, dst_err=0;
-
- sum = csum_partial_copy_generic ( src, dst, len, sum, &src_err, &dst_err);
-
- if (src_err || dst_err)
- printk("old csum_partial_copy_fromuser(), tell mingo to convert me.\n");
-
- return sum;
-}
-
-
+++ /dev/null
-#include <linux/string.h>
-
-char * strstr(const char * cs,const char * ct)
-{
-int d0, d1;
-register char * __res;
-__asm__ __volatile__(
- "movl %6,%%edi\n\t"
- "repne\n\t"
- "scasb\n\t"
- "notl %%ecx\n\t"
- "decl %%ecx\n\t" /* NOTE! This also sets Z if searchstring='' */
- "movl %%ecx,%%edx\n"
- "1:\tmovl %6,%%edi\n\t"
- "movl %%esi,%%eax\n\t"
- "movl %%edx,%%ecx\n\t"
- "repe\n\t"
- "cmpsb\n\t"
- "je 2f\n\t" /* also works for empty string, see above */
- "xchgl %%eax,%%esi\n\t"
- "incl %%esi\n\t"
- "cmpb $0,-1(%%eax)\n\t"
- "jne 1b\n\t"
- "xorl %%eax,%%eax\n\t"
- "2:"
- :"=a" (__res), "=&c" (d0), "=&S" (d1)
- :"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
- :"dx", "di");
-return __res;
-}
-
+++ /dev/null
-/*
- * User address space access functions.
- * The non inlined parts of asm-i386/uaccess.h are here.
- *
- * Copyright 1997 Andi Kleen <ak@muc.de>
- * Copyright 1997 Linus Torvalds
- */
-#include <linux/config.h>
-#include <asm/uaccess.h>
-#include <asm/mmx.h>
-
-#ifdef CONFIG_X86_USE_3DNOW_AND_WORKS
-
-unsigned long
-__generic_copy_to_user(void *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- {
- if(n<512)
- __copy_user(to,from,n);
- else
- mmx_copy_user(to,from,n);
- }
- return n;
-}
-
-unsigned long
-__generic_copy_from_user(void *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- {
- if(n<512)
- __copy_user_zeroing(to,from,n);
- else
- mmx_copy_user_zeroing(to, from, n);
- }
- else
- memset(to, 0, n);
- return n;
-}
-
-#else
-
-unsigned long
-__generic_copy_to_user(void *to, const void *from, unsigned long n)
-{
- prefetch(from);
- if (access_ok(VERIFY_WRITE, to, n))
- __copy_user(to,from,n);
- return n;
-}
-
-unsigned long
-__generic_copy_from_user(void *to, const void *from, unsigned long n)
-{
- prefetchw(to);
- if (access_ok(VERIFY_READ, from, n))
- __copy_user_zeroing(to,from,n);
- else
- memset(to, 0, n);
- return n;
-}
-
-#endif
-
-/*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst,src,count,res) \
-do { \
- int __d0, __d1, __d2; \
- __asm__ __volatile__( \
- " testl %1,%1\n" \
- " jz 2f\n" \
- "0: lodsb\n" \
- " stosb\n" \
- " testb %%al,%%al\n" \
- " jz 1f\n" \
- " decl %1\n" \
- " jnz 0b\n" \
- "1: subl %1,%0\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl %5,%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- ".previous" \
- : "=d"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1), \
- "=&D" (__d2) \
- : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
- : "memory"); \
-} while (0)
-
-long
-__strncpy_from_user(char *dst, const char *src, long count)
-{
- long res;
- __do_strncpy_from_user(dst, src, count, res);
- return res;
-}
-
-long
-strncpy_from_user(char *dst, const char *src, long count)
-{
- long res = -EFAULT;
- if (access_ok(VERIFY_READ, src, 1))
- __do_strncpy_from_user(dst, src, count, res);
- return res;
-}
-
-
-/*
- * Zero Userspace
- */
-
-#define __do_clear_user(addr,size) \
-do { \
- int __d0; \
- __asm__ __volatile__( \
- "0: rep; stosl\n" \
- " movl %2,%0\n" \
- "1: rep; stosb\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: lea 0(%2,%0,4),%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,2b\n" \
- ".previous" \
- : "=&c"(size), "=&D" (__d0) \
- : "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
-} while (0)
-
-unsigned long
-clear_user(void *to, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- __do_clear_user(to, n);
- return n;
-}
-
-unsigned long
-__clear_user(void *to, unsigned long n)
-{
- __do_clear_user(to, n);
- return n;
-}
-
-/*
- * Return the size of a string (including the ending 0)
- *
- * Return 0 on exception, a value greater than N if too long
- */
-
-long strnlen_user(const char *s, long n)
-{
- unsigned long mask = -__addr_ok(s);
- unsigned long res, tmp;
-
- __asm__ __volatile__(
- " testl %0, %0\n"
- " jz 3f\n"
- " andl %0,%%ecx\n"
- "0: repne; scasb\n"
- " setne %%al\n"
- " subl %%ecx,%0\n"
- " addl %0,%%eax\n"
- "1:\n"
- ".section .fixup,\"ax\"\n"
- "2: xorl %%eax,%%eax\n"
- " jmp 1b\n"
- "3: movb $1,%%al\n"
- " jmp 1b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 0b,2b\n"
- ".previous"
- :"=r" (n), "=D" (s), "=a" (res), "=c" (tmp)
- :"0" (n), "1" (s), "2" (0), "3" (mask)
- :"cc");
- return res & mask;
-}
+++ /dev/null
-
-
-O_TARGET := mm.o
-
-obj-y := init.o fault.o extable.o hypervisor.o get_unmapped_area.o mmu_context.o
-
-include $(TOPDIR)/Rules.make
+++ /dev/null
-/*
- * linux/arch/i386/mm/extable.c
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <asm/uaccess.h>
-
-extern const struct exception_table_entry __start___ex_table[];
-extern const struct exception_table_entry __stop___ex_table[];
-
-static inline unsigned long
-search_one_table(const struct exception_table_entry *first,
- const struct exception_table_entry *last,
- unsigned long value)
-{
- while (first <= last) {
- const struct exception_table_entry *mid;
- long diff;
-
- mid = (last - first) / 2 + first;
- diff = mid->insn - value;
- if (diff == 0)
- return mid->fixup;
- else if (diff < 0)
- first = mid+1;
- else
- last = mid-1;
- }
- return 0;
-}
-
-extern spinlock_t modlist_lock;
-
-unsigned long
-search_exception_table(unsigned long addr)
-{
- unsigned long ret = 0;
-
-#ifndef CONFIG_MODULES
- /* There is only the kernel to search. */
- ret = search_one_table(__start___ex_table, __stop___ex_table-1, addr);
- return ret;
-#else
- unsigned long flags;
- /* The kernel is the last "module" -- no need to treat it special. */
- struct module *mp;
-
- spin_lock_irqsave(&modlist_lock, flags);
- for (mp = module_list; mp != NULL; mp = mp->next) {
- if (mp->ex_table_start == NULL || !(mp->flags&(MOD_RUNNING|MOD_INITIALIZING)))
- continue;
- ret = search_one_table(mp->ex_table_start,
- mp->ex_table_end - 1, addr);
- if (ret)
- break;
- }
- spin_unlock_irqrestore(&modlist_lock, flags);
- return ret;
-#endif
-}
+++ /dev/null
-/*
- * linux/arch/i386/mm/fault.c
- *
- * Copyright (C) 1995 Linus Torvalds
- */
-
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/tty.h>
-#include <linux/vt_kern.h> /* For unblank_screen() */
-
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
-#include <asm/hardirq.h>
-
-extern void die(const char *,struct pt_regs *,long);
-
-extern int console_loglevel;
-
-pgd_t *cur_pgd;
-
-/*
- * Ugly, ugly, but the goto's result in better assembly..
- */
-int __verify_write(const void * addr, unsigned long size)
-{
- struct vm_area_struct * vma;
- unsigned long start = (unsigned long) addr;
-
- if (!size)
- return 1;
-
- vma = find_vma(current->mm, start);
- if (!vma)
- goto bad_area;
- if (vma->vm_start > start)
- goto check_stack;
-
-good_area:
- if (!(vma->vm_flags & VM_WRITE))
- goto bad_area;
- size--;
- size += start & ~PAGE_MASK;
- size >>= PAGE_SHIFT;
- start &= PAGE_MASK;
-
- for (;;) {
- survive:
- {
- int fault = handle_mm_fault(current->mm, vma, start, 1);
- if (!fault)
- goto bad_area;
- if (fault < 0)
- goto out_of_memory;
- }
- if (!size)
- break;
- size--;
- start += PAGE_SIZE;
- if (start < vma->vm_end)
- continue;
- vma = vma->vm_next;
- if (!vma || vma->vm_start != start)
- goto bad_area;
- if (!(vma->vm_flags & VM_WRITE))
- goto bad_area;;
- }
- return 1;
-
-check_stack:
- if (!(vma->vm_flags & VM_GROWSDOWN))
- goto bad_area;
- if (expand_stack(vma, start) == 0)
- goto good_area;
-
-bad_area:
- return 0;
-
-out_of_memory:
- if (current->pid == 1) {
- current->policy |= SCHED_YIELD;
- schedule();
- goto survive;
- }
- goto bad_area;
-}
-
-extern spinlock_t timerlist_lock;
-
-/*
- * Unlock any spinlocks which will prevent us from getting the
- * message out (timerlist_lock is acquired through the
- * console unblank code)
- */
-void bust_spinlocks(int yes)
-{
- spin_lock_init(&timerlist_lock);
- if (yes) {
- oops_in_progress = 1;
- } else {
- int loglevel_save = console_loglevel;
-#ifdef CONFIG_VT
- unblank_screen();
-#endif
- oops_in_progress = 0;
- /*
- * OK, the message is on the console. Now we call printk()
- * without oops_in_progress set so that printk will give klogd
- * a poke. Hold onto your hats...
- */
- console_loglevel = 15; /* NMI oopser may have shut the console up */
- printk(" ");
- console_loglevel = loglevel_save;
- }
-}
-
-void do_BUG(const char *file, int line)
-{
- bust_spinlocks(1);
- printk("kernel BUG at %s:%d!\n", file, line);
-}
-
-/*
- * This routine handles page faults. It determines the address,
- * and the problem, and then passes it off to one of the appropriate
- * routines.
- *
- * error_code:
- * bit 0 == 0 means no page found, 1 means protection fault
- * bit 1 == 0 means read, 1 means write
- * bit 2 == 0 means kernel, 1 means user-mode
- */
-asmlinkage void do_page_fault(struct pt_regs *regs,
- unsigned long error_code,
- unsigned long address)
-{
- struct task_struct *tsk = current;
- struct mm_struct *mm;
- struct vm_area_struct * vma;
- unsigned long page;
- unsigned long fixup;
- int write;
- siginfo_t info;
-
- /* Set the "privileged fault" bit to something sane. */
- error_code &= 3;
- error_code |= (regs->xcs & 2) << 1;
-
-#if PT_UPDATE_DEBUG > 0
- if ( (error_code == 0) && (address >= TASK_SIZE) )
- {
- unsigned long paddr = __pa(address);
- int i;
- for ( i = 0; i < pt_update_queue_idx; i++ )
- {
- if ( update_debug_queue[i].ptr == paddr )
- {
- printk("XXX now(EIP=%08lx:ptr=%08lx) "
- "then(%s/%d:p/v=%08lx/%08lx)\n",
- regs->eip, address,
- update_debug_queue[i].file,
- update_debug_queue[i].line,
- update_debug_queue[i].ptr,
- update_debug_queue[i].val);
- }
- }
- }
-#endif
-
- if ( flush_page_update_queue() != 0 ) return;
-
- /*
- * We fault-in kernel-space virtual memory on-demand. The
- * 'reference' page table is init_mm.pgd.
- *
- * NOTE! We MUST NOT take any locks for this case. We may
- * be in an interrupt or a critical region, and should
- * only copy the information from the master page table,
- * nothing more.
- *
- * This verifies that the fault happens in kernel space
- * (error_code & 4) == 0, and that the fault was not a
- * protection error (error_code & 1) == 0.
- */
- if (address >= TASK_SIZE && !(error_code & 5))
- goto vmalloc_fault;
-
- mm = tsk->mm;
- info.si_code = SEGV_MAPERR;
-
- /*
- * If we're in an interrupt or have no user
- * context, we must not take the fault..
- */
- if (in_interrupt() || !mm)
- goto no_context;
-
- down_read(&mm->mmap_sem);
-
- vma = find_vma(mm, address);
- if (!vma)
- goto bad_area;
- if (vma->vm_start <= address)
- goto good_area;
- if (!(vma->vm_flags & VM_GROWSDOWN))
- goto bad_area;
- if (error_code & 4) {
- /*
- * accessing the stack below %esp is always a bug.
- * The "+ 32" is there due to some instructions (like
- * pusha) doing post-decrement on the stack and that
- * doesn't show up until later..
- */
- if (address + 32 < regs->esp)
- goto bad_area;
- }
- if (expand_stack(vma, address))
- goto bad_area;
-/*
- * Ok, we have a good vm_area for this memory access, so
- * we can handle it..
- */
-good_area:
- info.si_code = SEGV_ACCERR;
- write = 0;
- switch (error_code & 3) {
- default: /* 3: write, present */
- /* fall through */
- case 2: /* write, not present */
- if (!(vma->vm_flags & VM_WRITE))
- goto bad_area;
- write++;
- break;
- case 1: /* read, present */
- goto bad_area;
- case 0: /* read, not present */
- if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
- goto bad_area;
- }
-
- survive:
- /*
- * If for any reason at all we couldn't handle the fault,
- * make sure we exit gracefully rather than endlessly redo
- * the fault.
- */
- switch (handle_mm_fault(mm, vma, address, write)) {
- case 1:
- tsk->min_flt++;
- break;
- case 2:
- tsk->maj_flt++;
- break;
- case 0:
- goto do_sigbus;
- default:
- goto out_of_memory;
- }
-
- up_read(&mm->mmap_sem);
- return;
-
-/*
- * Something tried to access memory that isn't in our memory map..
- * Fix it, but check if it's kernel or user first..
- */
-bad_area:
- up_read(&mm->mmap_sem);
-
- /* User mode accesses just cause a SIGSEGV */
- if (error_code & 4) {
- tsk->thread.cr2 = address;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 14;
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- /* info.si_code has been set above */
- info.si_addr = (void *)address;
- force_sig_info(SIGSEGV, &info, tsk);
- return;
- }
-
-no_context:
- /* Are we prepared to handle this kernel fault? */
- if ((fixup = search_exception_table(regs->eip)) != 0) {
- regs->eip = fixup;
- return;
- }
-
-/*
- * Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
- */
-
- bust_spinlocks(1);
-
- if (address < PAGE_SIZE)
- printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
- else
- printk(KERN_ALERT "Unable to handle kernel paging request");
- printk(" at virtual address %08lx\n",address);
- printk(" printing eip:\n");
- printk("%08lx\n", regs->eip);
- page = ((unsigned long *) cur_pgd)[address >> 22];
- printk(KERN_ALERT "*pde=%08lx(%08lx)\n", page, machine_to_phys(page));
- if (page & 1) {
- page &= PAGE_MASK;
- address &= 0x003ff000;
- page = machine_to_phys(page);
- page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
- printk(KERN_ALERT "*pte=%08lx(%08lx)\n", page,
- machine_to_phys(page));
- }
- die("Oops", regs, error_code);
- bust_spinlocks(0);
- do_exit(SIGKILL);
-
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
-out_of_memory:
- up_read(&mm->mmap_sem);
- if (tsk->pid == 1) {
- tsk->policy |= SCHED_YIELD;
- schedule();
- down_read(&mm->mmap_sem);
- goto survive;
- }
- printk("VM: killing process %s\n", tsk->comm);
- if (error_code & 4)
- do_exit(SIGKILL);
- goto no_context;
-
-do_sigbus:
- up_read(&mm->mmap_sem);
-
- /*
- * Send a sigbus, regardless of whether we were in kernel
- * or user mode.
- */
- tsk->thread.cr2 = address;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 14;
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void *)address;
- force_sig_info(SIGBUS, &info, tsk);
-
- /* Kernel mode? Handle exceptions or die */
- if (!(error_code & 4))
- goto no_context;
- return;
-
-vmalloc_fault:
- {
- /*
- * Synchronize this task's top level page-table
- * with the 'reference' page table.
- *
- * Do _not_ use "tsk" here. We might be inside
- * an interrupt in the middle of a task switch..
- */
- int offset = __pgd_offset(address);
- pgd_t *pgd, *pgd_k;
- pmd_t *pmd, *pmd_k;
- pte_t *pte_k;
-
- pgd = offset + cur_pgd;
- pgd_k = init_mm.pgd + offset;
-
- if (!pgd_present(*pgd_k))
- goto no_context;
- set_pgd(pgd, *pgd_k);
-
- pmd = pmd_offset(pgd, address);
- pmd_k = pmd_offset(pgd_k, address);
- if (!pmd_present(*pmd_k))
- goto no_context;
- set_pmd(pmd, *pmd_k);
- XENO_flush_page_update_queue(); /* flush PMD update */
-
- pte_k = pte_offset(pmd_k, address);
- if (!pte_present(*pte_k))
- goto no_context;
- return;
- }
-}
+++ /dev/null
-
-#include <linux/slab.h>
-#include <linux/shm.h>
-#include <linux/mman.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <linux/swapctl.h>
-#include <linux/smp_lock.h>
-#include <linux/init.h>
-#include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/personality.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
-
-/*
-static int direct_mapped(unsigned long addr)
-{
- direct_mmap_node_t * node;
- struct list_head * curr;
- struct list_head * direct_list = ¤t->mm->context.direct_list;
-
- curr = direct_list->next;
- while(curr != direct_list){
- node = list_entry(curr, direct_mmap_node_t, list);
- if(node->addr == addr)
- break;
- curr = curr->next;
- }
-
- if(curr == direct_list)
- return 0;
-
- return 1;
-}
-*/
-/*
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
-{
- struct vm_area_struct *vma;
-
- if (len > TASK_SIZE)
- return -ENOMEM;
-
- if (addr) {
- addr = PAGE_ALIGN(addr);
- vma = find_vma(current->mm, addr);
- if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
- return addr;
- }
- addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);
-
- for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
- if (TASK_SIZE - len < addr)
- return -ENOMEM;
-
- if ((!vma || addr + len <= vma->vm_start) && !direct_mapped(addr))
- return addr;
-
- addr = vma->vm_end;
- }
-}
-*/
-struct list_head *find_direct(struct list_head *list, unsigned long addr)
-{
- struct list_head * curr;
- struct list_head * direct_list = ¤t->mm->context.direct_list;
- direct_mmap_node_t * node;
-
- for ( curr = direct_list->next; curr != direct_list; curr = curr->next )
- {
- node = list_entry(curr, direct_mmap_node_t, list);
- if ( node->vm_start >= addr ) break;
- }
-
- return curr;
-}
-
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long
-addr, unsigned long len, unsigned long pgoff, unsigned long flags)
-{
- struct vm_area_struct *vma;
- direct_mmap_node_t * node;
- struct list_head * curr;
- struct list_head * direct_list = ¤t->mm->context.direct_list;
-
- if (len > TASK_SIZE)
- return -ENOMEM;
-
- if ( addr )
- {
- addr = PAGE_ALIGN(addr);
- vma = find_vma(current->mm, addr);
- curr = find_direct(direct_list, addr);
- node = list_entry(curr, direct_mmap_node_t, list);
- if ( (TASK_SIZE - len >= addr) &&
- (!vma || addr + len <= vma->vm_start) &&
- ((curr == direct_list) || addr + len <= node->vm_start) )
- return addr;
- }
-
- addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);
-
-
- /* Find first VMA and direct_map nodes with vm_start > addr */
- vma = find_vma(current->mm, addr);
- curr = find_direct(direct_list, addr);
- node = list_entry(curr, direct_mmap_node_t, list);
-
- for ( ; ; )
- {
- if ( TASK_SIZE - len < addr ) return -ENOMEM;
-
- if ( vma && ((curr == direct_list) || (vma->vm_start < node->vm_start)))
- {
- /* Do we fit before VMA node? */
- if ( addr + len <= vma->vm_start ) return addr;
- addr = vma->vm_end;
- vma = vma->vm_next;
- }
- else if ( curr != direct_list )
- {
- /* Do we fit before direct_map node? */
- if ( addr + len <= node->vm_start) return addr;
- addr = node->vm_end;
- curr = curr->next;
- node = list_entry(curr, direct_mmap_node_t, list);
- }
- else
- {
- /* !vma && curr == direct_list */
- return addr;
- }
- }
-}
+++ /dev/null
-/******************************************************************************
- * xeno/mm/hypervisor.c
- *
- * Update page tables via the hypervisor.
- *
- * Copyright (c) 2002, K A Fraser
- */
-
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <asm/hypervisor.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-
-#define QUEUE_SIZE 2048
-static page_update_request_t update_queue[QUEUE_SIZE];
-unsigned int pt_update_queue_idx = 0;
-#define idx pt_update_queue_idx
-
-#if PT_UPDATE_DEBUG > 0
-page_update_debug_t update_debug_queue[QUEUE_SIZE] = {{0}};
-#undef queue_l1_entry_update
-#undef queue_l2_entry_update
-static void DEBUG_allow_pt_reads(void)
-{
- pte_t *pte;
- page_update_request_t update;
- int i;
- for ( i = idx-1; i >= 0; i-- )
- {
- pte = update_debug_queue[i].ptep;
- if ( pte == NULL ) continue;
- update_debug_queue[i].ptep = NULL;
- update.ptr = phys_to_machine(__pa(pte));
- update.val = update_debug_queue[i].pteval;
- HYPERVISOR_pt_update(&update, 1);
- }
-}
-static void DEBUG_disallow_pt_read(unsigned long pa)
-{
- pte_t *pte;
- pmd_t *pmd;
- pgd_t *pgd;
- unsigned long pteval;
- /*
- * We may fault because of an already outstanding update.
- * That's okay -- it'll get fixed up in the fault handler.
- */
- page_update_request_t update;
- unsigned long va = (unsigned long)__va(pa);
- pgd = pgd_offset_k(va);
- pmd = pmd_offset(pgd, va);
- pte = pte_offset(pmd, va);
- update.ptr = phys_to_machine(__pa(pte));
- pteval = *(unsigned long *)pte;
- update.val = pteval & ~_PAGE_PRESENT;
- HYPERVISOR_pt_update(&update, 1);
- update_debug_queue[idx].ptep = pte;
- update_debug_queue[idx].pteval = pteval;
-}
-#endif
-
-#if PT_UPDATE_DEBUG > 1
-#undef queue_pt_switch
-#undef queue_tlb_flush
-#undef queue_invlpg
-#undef queue_pgd_pin
-#undef queue_pgd_unpin
-#undef queue_pte_pin
-#undef queue_pte_unpin
-#endif
-
-
-/*
- * This is the current pagetable base pointer, which is updated
- * on context switch.
- */
-unsigned long pt_baseptr;
-
-void _flush_page_update_queue(void)
-{
- if ( idx == 0 ) return;
-#if PT_UPDATE_DEBUG > 1
- printk("Flushing %d entries from pt update queue\n", idx);
-#endif
-#if PT_UPDATE_DEBUG > 0
- DEBUG_allow_pt_reads();
-#endif
- HYPERVISOR_pt_update(update_queue, idx);
- idx = 0;
-}
-
-static void increment_index(void)
-{
- if ( ++idx == QUEUE_SIZE ) _flush_page_update_queue();
-}
-
-void queue_l1_entry_update(unsigned long ptr, unsigned long val)
-{
-#if PT_UPDATE_DEBUG > 0
- DEBUG_disallow_pt_read(ptr);
-#endif
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].val = val;
- increment_index();
-}
-
-void queue_l2_entry_update(unsigned long ptr, unsigned long val)
-{
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].val = val;
- increment_index();
-}
-
-void queue_pt_switch(unsigned long ptr)
-{
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = PGEXT_NEW_BASEPTR;
- increment_index();
-}
-
-void queue_tlb_flush(void)
-{
- update_queue[idx].ptr = PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = PGEXT_TLB_FLUSH;
- increment_index();
-}
-
-void queue_invlpg(unsigned long ptr)
-{
- update_queue[idx].ptr = PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = ptr & PAGE_MASK;
- update_queue[idx].val |= PGEXT_INVLPG;
- increment_index();
-}
-
-void queue_pgd_pin(unsigned long ptr)
-{
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = PGEXT_PIN_L2_TABLE;
- increment_index();
-}
-
-void queue_pgd_unpin(unsigned long ptr)
-{
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = PGEXT_UNPIN_TABLE;
- increment_index();
-}
-
-void queue_pte_pin(unsigned long ptr)
-{
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = PGEXT_PIN_L1_TABLE;
- increment_index();
-}
-
-void queue_pte_unpin(unsigned long ptr)
-{
- update_queue[idx].ptr = phys_to_machine(ptr);
- update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
- update_queue[idx].val = PGEXT_UNPIN_TABLE;
- increment_index();
-}
+++ /dev/null
-/*
- * linux/arch/i386/mm/init.c
- *
- * Copyright (C) 1995 Linus Torvalds
- *
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- */
-
-#include <linux/config.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/smp.h>
-#include <linux/init.h>
-#ifdef CONFIG_BLK_DEV_INITRD
-#include <linux/blk.h>
-#endif
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-#include <linux/bootmem.h>
-
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/pgalloc.h>
-#include <asm/dma.h>
-#include <asm/apic.h>
-#include <asm/tlb.h>
-
-mmu_gather_t mmu_gathers[NR_CPUS];
-unsigned long highstart_pfn, highend_pfn;
-static unsigned long totalram_pages;
-static unsigned long totalhigh_pages;
-
-int do_check_pgt_cache(int low, int high)
-{
- int freed = 0;
- if(pgtable_cache_size > high) {
- do {
- if (!QUICKLIST_EMPTY(pgd_quicklist)) {
- free_pgd_slow(get_pgd_fast());
- freed++;
- }
- if (!QUICKLIST_EMPTY(pte_quicklist)) {
- pte_free_slow(pte_alloc_one_fast(NULL, 0));
- freed++;
- }
- } while(pgtable_cache_size > low);
- }
- return freed;
-}
-
-void show_mem(void)
-{
- int i, total = 0, reserved = 0;
- int shared = 0, cached = 0;
- int highmem = 0;
-
- printk("Mem-info:\n");
- show_free_areas();
- printk("Free swap: %6dkB\n",nr_swap_pages<<(PAGE_SHIFT-10));
- i = max_mapnr;
- while (i-- > 0) {
- total++;
- if (PageHighMem(mem_map+i))
- highmem++;
- if (PageReserved(mem_map+i))
- reserved++;
- else if (PageSwapCache(mem_map+i))
- cached++;
- else if (page_count(mem_map+i))
- shared += page_count(mem_map+i) - 1;
- }
- printk("%d pages of RAM\n", total);
- printk("%d pages of HIGHMEM\n",highmem);
- printk("%d reserved pages\n",reserved);
- printk("%d pages shared\n",shared);
- printk("%d pages swap cached\n",cached);
- printk("%ld pages in page table cache\n",pgtable_cache_size);
- show_buffers();
-}
-
-/* References to section boundaries */
-
-extern char _text, _etext, _edata, __bss_start, _end;
-extern char __init_begin, __init_end;
-
-static inline void set_pte_phys (unsigned long vaddr,
- unsigned long phys, pgprot_t flags)
-{
- pgprot_t prot;
- pgd_t *pgd;
- pmd_t *pmd;
- pte_t *pte;
-
- pgd = init_mm.pgd + __pgd_offset(vaddr);
- if (pgd_none(*pgd)) {
- printk("PAE BUG #00!\n");
- return;
- }
- pmd = pmd_offset(pgd, vaddr);
- if (pmd_none(*pmd)) {
- printk("PAE BUG #01!\n");
- return;
- }
- pte = pte_offset(pmd, vaddr);
- if (pte_val(*pte))
- pte_ERROR(*pte);
- pgprot_val(prot) = pgprot_val(PAGE_KERNEL) | pgprot_val(flags);
-
- /* We queue directly, avoiding hidden phys->machine translation. */
- queue_l1_entry_update(__pa(pte), phys | pgprot_val(prot));
-
- /*
- * It's enough to flush this one mapping.
- * (PGE mappings get flushed as well)
- */
- __flush_tlb_one(vaddr);
-}
-
-void __set_fixmap (enum fixed_addresses idx, unsigned long phys,
- pgprot_t flags)
-{
- unsigned long address = __fix_to_virt(idx);
-
- if (idx >= __end_of_fixed_addresses) {
- printk("Invalid __set_fixmap\n");
- return;
- }
- set_pte_phys(address, phys, flags);
-}
-
-static void __init fixrange_init (unsigned long start,
- unsigned long end, pgd_t *pgd_base)
-{
- pgd_t *pgd, *kpgd;
- pmd_t *pmd, *kpmd;
- pte_t *pte, *kpte;
- int i, j;
- unsigned long vaddr;
-
- vaddr = start;
- i = __pgd_offset(vaddr);
- j = __pmd_offset(vaddr);
- pgd = pgd_base + i;
-
- for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
- pmd = (pmd_t *)pgd;
- for (; (j < PTRS_PER_PMD) && (vaddr != end); pmd++, j++) {
- if (pmd_none(*pmd)) {
- pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
- clear_page(pte);
- kpgd = pgd_offset_k((unsigned long)pte);
- kpmd = pmd_offset(kpgd, (unsigned long)pte);
- kpte = pte_offset(kpmd, (unsigned long)pte);
- queue_l1_entry_update(__pa(kpte),
- (*(unsigned long *)kpte)&~_PAGE_RW);
- set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
- }
- vaddr += PMD_SIZE;
- }
- j = 0;
- }
-
- XENO_flush_page_update_queue();
-}
-
-void __init paging_init(void)
-{
- unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
- unsigned int max_dma, high, low;
- unsigned long vaddr;
-
- max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
- low = max_low_pfn;
- high = highend_pfn;
-
- if (low < max_dma)
- {
- zones_size[ZONE_DMA] = low;
- }
- else
- {
- zones_size[ZONE_DMA] = max_dma;
- zones_size[ZONE_NORMAL] = low - max_dma;
- }
- free_area_init(zones_size);
-
- /*
- * Fixed mappings, only the page table structure has to be created -
- * mappings will be set by set_fixmap():
- */
- vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
- fixrange_init(vaddr, HYPERVISOR_VIRT_START, init_mm.pgd);
-
- /*
- * XXX We do this conversion early, so that all other page tables
- * will automatically get this mapping.
- */
- set_fixmap(FIX_BLKRING_BASE, start_info.blk_ring);
-}
-
-
-static inline int page_is_ram (unsigned long pagenr)
-{
- return 1;
-}
-
-void __init mem_init(void)
-{
- int codesize, reservedpages, datasize, initsize;
- int tmp;
-
- max_mapnr = num_physpages = max_low_pfn;
- high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-
- /* clear the zero-page */
- memset(empty_zero_page, 0, PAGE_SIZE);
-
- /* this will put all low memory onto the freelists */
- totalram_pages += free_all_bootmem();
-
- reservedpages = 0;
- for (tmp = 0; tmp < max_low_pfn; tmp++)
- /*
- * Only count reserved RAM pages
- */
- if (page_is_ram(tmp) && PageReserved(mem_map+tmp))
- reservedpages++;
- codesize = (unsigned long) &_etext - (unsigned long) &_text;
- datasize = (unsigned long) &_edata - (unsigned long) &_etext;
- initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
-
- printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n",
- (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
- max_mapnr << (PAGE_SHIFT-10),
- codesize >> 10,
- reservedpages << (PAGE_SHIFT-10),
- datasize >> 10,
- initsize >> 10,
- (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
- );
-
- boot_cpu_data.wp_works_ok = 1;
-}
-
-void free_initmem(void)
-{
- unsigned long addr;
-
- addr = (unsigned long)(&__init_begin);
- for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
- ClearPageReserved(virt_to_page(addr));
- set_page_count(virt_to_page(addr), 1);
- free_page(addr);
- totalram_pages++;
- }
- printk ("Freeing unused kernel memory: %dk freed\n", (&__init_end - &__init_begin) >> 10);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
- if (start < end)
- printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
- for (; start < end; start += PAGE_SIZE) {
- ClearPageReserved(virt_to_page(start));
- set_page_count(virt_to_page(start), 1);
- free_page(start);
- totalram_pages++;
- }
-}
-#endif
-
-void si_meminfo(struct sysinfo *val)
-{
- val->totalram = totalram_pages;
- val->sharedram = 0;
- val->freeram = nr_free_pages();
- val->bufferram = atomic_read(&buffermem_pages);
- val->totalhigh = totalhigh_pages;
- val->freehigh = nr_free_highpages();
- val->mem_unit = PAGE_SIZE;
- return;
-}
+++ /dev/null
-
-#include <linux/slab.h>
-#include <linux/list.h>
-
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
- INIT_LIST_HEAD(&mm->context.direct_list);
- return 0;
-}
-
-/* just free all elements of list identifying directly mapped areas */
-void destroy_context(struct mm_struct *mm)
-{
- direct_mmap_node_t * node;
- struct list_head * curr;
- struct list_head * direct_list = &mm->context.direct_list;
-
- curr = direct_list->next;
- while(curr != direct_list){
- node = list_entry(curr, direct_mmap_node_t, list);
- curr = curr->next;
- list_del(&node->list);
- kfree(node);
- }
-
-}
+++ /dev/null
-/* ld script to make i386 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- */
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(_start)
-SECTIONS
-{
- . = 0xC0000000 + 0x000000;
- _text = .; /* Text and read-only data */
- .text : {
- *(.text)
- *(.fixup)
- *(.gnu.warning)
- } = 0x9090
- .text.lock : { *(.text.lock) } /* out-of-line lock text */
-
- _etext = .; /* End of text section */
-
- .rodata : { *(.rodata) *(.rodata.*) }
- .kstrtab : { *(.kstrtab) }
-
- . = ALIGN(16); /* Exception table */
- __start___ex_table = .;
- __ex_table : { *(__ex_table) }
- __stop___ex_table = .;
-
- __start___ksymtab = .; /* Kernel symbol table */
- __ksymtab : { *(__ksymtab) }
- __stop___ksymtab = .;
-
- __start___kallsyms = .; /* All kernel symbols */
- __kallsyms : { *(__kallsyms) }
- __stop___kallsyms = .;
-
- .data : { /* Data */
- *(.data)
- CONSTRUCTORS
- }
-
- _edata = .; /* End of data section */
-
- . = ALIGN(8192); /* init_task */
- .data.init_task : { *(.data.init_task) }
-
- . = ALIGN(4096); /* Init code and data */
- __init_begin = .;
- .text.init : { *(.text.init) }
- .data.init : { *(.data.init) }
- . = ALIGN(16);
- __setup_start = .;
- .setup.init : { *(.setup.init) }
- __setup_end = .;
- __initcall_start = .;
- .initcall.init : { *(.initcall.init) }
- __initcall_end = .;
- . = ALIGN(4096);
- __init_end = .;
-
- . = ALIGN(4096);
- .data.page_aligned : { *(.data.idt) }
-
- . = ALIGN(32);
- .data.cacheline_aligned : { *(.data.cacheline_aligned) }
-
- __bss_start = .; /* BSS */
- .bss : {
- *(.bss)
- }
- _end = . ;
-
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.text.exit)
- *(.data.exit)
- *(.exitcall.exit)
- }
-
- /* Stabs debugging sections. */
- .stab 0 : { *(.stab) }
- .stabstr 0 : { *(.stabstr) }
- .stab.excl 0 : { *(.stab.excl) }
- .stab.exclstr 0 : { *(.stab.exclstr) }
- .stab.index 0 : { *(.stab.index) }
- .stab.indexstr 0 : { *(.stab.indexstr) }
- .comment 0 : { *(.comment) }
-}
+++ /dev/null
-#
-# Block device driver configuration
-#
-mainmenu_option next_comment
-comment 'Block devices'
-
-tristate 'Normal PC floppy disk support' CONFIG_BLK_DEV_FD
-if [ "$CONFIG_AMIGA" = "y" ]; then
- tristate 'Amiga floppy support' CONFIG_AMIGA_FLOPPY
-fi
-if [ "$CONFIG_ATARI" = "y" ]; then
- tristate 'Atari floppy support' CONFIG_ATARI_FLOPPY
-fi
-if [ "$CONFIG_MAC" = "y" ]; then
- dep_bool 'Macintosh IIfx/Quadra 900/Quadra 950 floppy support (EXPERIMENTAL)' CONFIG_BLK_DEV_SWIM_IOP $CONFIG_EXPERIMENTAL
-fi
-if [ "$CONFIG_MCA" = "y" ]; then
- tristate 'PS/2 ESDI hard disk support' CONFIG_BLK_DEV_PS2
-fi
-if [ "$CONFIG_ZORRO" = "y" ]; then
- tristate 'Amiga Zorro II ramdisk support' CONFIG_AMIGA_Z2RAM
-fi
-if [ "$CONFIG_ATARI" = "y" ]; then
- tristate 'Atari ACSI support' CONFIG_ATARI_ACSI
- if [ "$CONFIG_ATARI_ACSI" != "n" ]; then
- comment 'Some devices (e.g. CD jukebox) support multiple LUNs'
- bool ' Probe all LUNs on each ACSI device' CONFIG_ACSI_MULTI_LUN
- tristate ' Atari SLM laser printer support' CONFIG_ATARI_SLM
- fi
-fi
-dep_tristate 'XT hard disk support' CONFIG_BLK_DEV_XD $CONFIG_ISA
-dep_tristate 'Parallel port IDE device support' CONFIG_PARIDE $CONFIG_PARPORT
-if [ "$CONFIG_PARIDE" = "y" -o "$CONFIG_PARIDE" = "m" ]; then
- source drivers/block/paride/Config.in
-fi
-dep_tristate 'Compaq SMART2 support' CONFIG_BLK_CPQ_DA $CONFIG_PCI
-dep_tristate 'Compaq Smart Array 5xxx support' CONFIG_BLK_CPQ_CISS_DA $CONFIG_PCI
-dep_tristate 'Mylex DAC960/DAC1100 PCI RAID Controller support' CONFIG_BLK_DEV_DAC960 $CONFIG_PCI
-
-tristate 'Loopback device support' CONFIG_BLK_DEV_LOOP
-dep_tristate 'Network block device support' CONFIG_BLK_DEV_NBD $CONFIG_NET
-
-tristate 'RAM disk support' CONFIG_BLK_DEV_RAM
-if [ "$CONFIG_BLK_DEV_RAM" = "y" -o "$CONFIG_BLK_DEV_RAM" = "m" ]; then
- int ' Default RAM disk size' CONFIG_BLK_DEV_RAM_SIZE 4096
-fi
-dep_bool ' Initial RAM disk (initrd) support' CONFIG_BLK_DEV_INITRD $CONFIG_BLK_DEV_RAM
-
-bool 'XenoLinux virtual block device support' CONFIG_XENOLINUX_BLOCK
-
-endmenu
+++ /dev/null
-/*
- * linux/drivers/block/ll_rw_blk.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- * Copyright (C) 1994, Karl Keyte: Added support for disk statistics
- * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
- * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
- * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> - July2000
- */
-
-/*
- * This handles all read/write requests to block devices
- */
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/config.h>
-#include <linux/locks.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/init.h>
-#include <linux/smp_lock.h>
-#include <linux/completion.h>
-
-#include <asm/system.h>
-#include <asm/io.h>
-#include <linux/blk.h>
-#include <linux/highmem.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-
-/*
- * MAC Floppy IWM hooks
- */
-
-#ifdef CONFIG_MAC_FLOPPY_IWM
-extern int mac_floppy_init(void);
-#endif
-
-/*
- * For the allocated request tables
- */
-static kmem_cache_t *request_cachep;
-
-/*
- * The "disk" task queue is used to start the actual requests
- * after a plug
- */
-DECLARE_TASK_QUEUE(tq_disk);
-
-/*
- * Protect the request list against multiple users..
- *
- * With this spinlock the Linux block IO subsystem is 100% SMP threaded
- * from the IRQ event side, and almost 100% SMP threaded from the syscall
- * side (we still have protect against block device array operations, and
- * the do_request() side is casually still unsafe. The kernel lock protects
- * this part currently.).
- *
- * there is a fair chance that things will work just OK if these functions
- * are called with no global kernel lock held ...
- */
-spinlock_t io_request_lock = SPIN_LOCK_UNLOCKED;
-
-/* This specifies how many sectors to read ahead on the disk. */
-
-int read_ahead[MAX_BLKDEV];
-
-/* blk_dev_struct is:
- * *request_fn
- * *current_request
- */
-struct blk_dev_struct blk_dev[MAX_BLKDEV]; /* initialized by blk_dev_init() */
-
-/*
- * blk_size contains the size of all block-devices in units of 1024 byte
- * sectors:
- *
- * blk_size[MAJOR][MINOR]
- *
- * if (!blk_size[MAJOR]) then no minor size checking is done.
- */
-int * blk_size[MAX_BLKDEV];
-
-/*
- * blksize_size contains the size of all block-devices:
- *
- * blksize_size[MAJOR][MINOR]
- *
- * if (!blksize_size[MAJOR]) then 1024 bytes is assumed.
- */
-int * blksize_size[MAX_BLKDEV];
-
-/*
- * hardsect_size contains the size of the hardware sector of a device.
- *
- * hardsect_size[MAJOR][MINOR]
- *
- * if (!hardsect_size[MAJOR])
- * then 512 bytes is assumed.
- * else
- * sector_size is hardsect_size[MAJOR][MINOR]
- * This is currently set by some scsi devices and read by the msdos fs driver.
- * Other uses may appear later.
- */
-int * hardsect_size[MAX_BLKDEV];
-
-/*
- * The following tunes the read-ahead algorithm in mm/filemap.c
- */
-int * max_readahead[MAX_BLKDEV];
-
-/*
- * Max number of sectors per request
- */
-int * max_sectors[MAX_BLKDEV];
-
-/*
- * How many reqeusts do we allocate per queue,
- * and how many do we "batch" on freeing them?
- */
-static int queue_nr_requests, batch_requests;
-
-static inline int get_max_sectors(kdev_t dev)
-{
- if (!max_sectors[MAJOR(dev)])
- return MAX_SECTORS;
- return max_sectors[MAJOR(dev)][MINOR(dev)];
-}
-
-inline request_queue_t *blk_get_queue(kdev_t dev)
-{
- struct blk_dev_struct *bdev = blk_dev + MAJOR(dev);
-
- if (bdev->queue)
- return bdev->queue(dev);
- else
- return &blk_dev[MAJOR(dev)].request_queue;
-}
-
-static int __blk_cleanup_queue(struct request_list *list)
-{
- struct list_head *head = &list->free;
- struct request *rq;
- int i = 0;
-
- while (!list_empty(head)) {
- rq = list_entry(head->next, struct request, queue);
- list_del(&rq->queue);
- kmem_cache_free(request_cachep, rq);
- i++;
- };
-
- if (i != list->count)
- printk("request list leak!\n");
-
- list->count = 0;
- return i;
-}
-
-/**
- * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
- * @q: the request queue to be released
- *
- * Description:
- * blk_cleanup_queue is the pair to blk_init_queue(). It should
- * be called when a request queue is being released; typically
- * when a block device is being de-registered. Currently, its
- * primary task it to free all the &struct request structures that
- * were allocated to the queue.
- * Caveat:
- * Hopefully the low level driver will have finished any
- * outstanding requests first...
- **/
-void blk_cleanup_queue(request_queue_t * q)
-{
- int count = queue_nr_requests;
-
- count -= __blk_cleanup_queue(&q->rq[READ]);
- count -= __blk_cleanup_queue(&q->rq[WRITE]);
-
- if (count)
- printk("blk_cleanup_queue: leaked requests (%d)\n", count);
-
- memset(q, 0, sizeof(*q));
-}
-
-/**
- * blk_queue_headactive - indicate whether head of request queue may be active
- * @q: The queue which this applies to.
- * @active: A flag indication where the head of the queue is active.
- *
- * Description:
- * The driver for a block device may choose to leave the currently active
- * request on the request queue, removing it only when it has completed.
- * The queue handling routines assume this by default for safety reasons
- * and will not involve the head of the request queue in any merging or
- * reordering of requests when the queue is unplugged (and thus may be
- * working on this particular request).
- *
- * If a driver removes requests from the queue before processing them, then
- * it may indicate that it does so, there by allowing the head of the queue
- * to be involved in merging and reordering. This is done be calling
- * blk_queue_headactive() with an @active flag of %0.
- *
- * If a driver processes several requests at once, it must remove them (or
- * at least all but one of them) from the request queue.
- *
- * When a queue is plugged the head will be assumed to be inactive.
- **/
-
-void blk_queue_headactive(request_queue_t * q, int active)
-{
- q->head_active = active;
-}
-
-/**
- * blk_queue_make_request - define an alternate make_request function for a device
- * @q: the request queue for the device to be affected
- * @mfn: the alternate make_request function
- *
- * Description:
- * The normal way for &struct buffer_heads to be passed to a device
- * driver is for them to be collected into requests on a request
- * queue, and then to allow the device driver to select requests
- * off that queue when it is ready. This works well for many block
- * devices. However some block devices (typically virtual devices
- * such as md or lvm) do not benefit from the processing on the
- * request queue, and are served best by having the requests passed
- * directly to them. This can be achieved by providing a function
- * to blk_queue_make_request().
- *
- * Caveat:
- * The driver that does this *must* be able to deal appropriately
- * with buffers in "highmemory", either by calling bh_kmap() to get
- * a kernel mapping, to by calling create_bounce() to create a
- * buffer in normal memory.
- **/
-
-void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
-{
- q->make_request_fn = mfn;
-}
-
-static inline int ll_new_segment(request_queue_t *q, struct request *req, int max_segments)
-{
- if (req->nr_segments < max_segments) {
- req->nr_segments++;
- return 1;
- }
- return 0;
-}
-
-static int ll_back_merge_fn(request_queue_t *q, struct request *req,
- struct buffer_head *bh, int max_segments)
-{
- if (req->bhtail->b_data + req->bhtail->b_size == bh->b_data)
- return 1;
- return ll_new_segment(q, req, max_segments);
-}
-
-static int ll_front_merge_fn(request_queue_t *q, struct request *req,
- struct buffer_head *bh, int max_segments)
-{
- if (bh->b_data + bh->b_size == req->bh->b_data)
- return 1;
- return ll_new_segment(q, req, max_segments);
-}
-
-static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
- struct request *next, int max_segments)
-{
- int total_segments = req->nr_segments + next->nr_segments;
-
- if (req->bhtail->b_data + req->bhtail->b_size == next->bh->b_data)
- total_segments--;
-
- if (total_segments > max_segments)
- return 0;
-
- req->nr_segments = total_segments;
- return 1;
-}
-
-/*
- * "plug" the device if there are no outstanding requests: this will
- * force the transfer to start only after we have put all the requests
- * on the list.
- *
- * This is called with interrupts off and no requests on the queue.
- * (and with the request spinlock acquired)
- */
-static void generic_plug_device(request_queue_t *q, kdev_t dev)
-{
- /*
- * no need to replug device
- */
- if (!list_empty(&q->queue_head) || q->plugged)
- return;
-
- q->plugged = 1;
- queue_task(&q->plug_tq, &tq_disk);
-}
-
-/*
- * remove the plug and let it rip..
- */
-static inline void __generic_unplug_device(request_queue_t *q)
-{
- if (q->plugged) {
- q->plugged = 0;
- if (!list_empty(&q->queue_head))
- q->request_fn(q);
- }
-}
-
-void generic_unplug_device(void *data)
-{
- request_queue_t *q = (request_queue_t *) data;
- unsigned long flags;
-
- spin_lock_irqsave(&io_request_lock, flags);
- __generic_unplug_device(q);
- spin_unlock_irqrestore(&io_request_lock, flags);
-}
-
-static void blk_init_free_list(request_queue_t *q)
-{
- struct request *rq;
- int i;
-
- INIT_LIST_HEAD(&q->rq[READ].free);
- INIT_LIST_HEAD(&q->rq[WRITE].free);
- q->rq[READ].count = 0;
- q->rq[WRITE].count = 0;
-
- /*
- * Divide requests in half between read and write
- */
- for (i = 0; i < queue_nr_requests; i++) {
- rq = kmem_cache_alloc(request_cachep, SLAB_KERNEL);
- if (rq == NULL) {
- /* We'll get a `leaked requests' message from blk_cleanup_queue */
- printk(KERN_EMERG "blk_init_free_list: error allocating requests\n");
- break;
- }
- memset(rq, 0, sizeof(struct request));
- rq->rq_status = RQ_INACTIVE;
- list_add(&rq->queue, &q->rq[i&1].free);
- q->rq[i&1].count++;
- }
-
- init_waitqueue_head(&q->wait_for_request);
- spin_lock_init(&q->queue_lock);
-}
-
-static int __make_request(request_queue_t * q, int rw, struct buffer_head * bh);
-
-/**
- * blk_init_queue - prepare a request queue for use with a block device
- * @q: The &request_queue_t to be initialised
- * @rfn: The function to be called to process requests that have been
- * placed on the queue.
- *
- * Description:
- * If a block device wishes to use the standard request handling procedures,
- * which sorts requests and coalesces adjacent requests, then it must
- * call blk_init_queue(). The function @rfn will be called when there
- * are requests on the queue that need to be processed. If the device
- * supports plugging, then @rfn may not be called immediately when requests
- * are available on the queue, but may be called at some time later instead.
- * Plugged queues are generally unplugged when a buffer belonging to one
- * of the requests on the queue is needed, or due to memory pressure.
- *
- * @rfn is not required, or even expected, to remove all requests off the
- * queue, but only as many as it can handle at a time. If it does leave
- * requests on the queue, it is responsible for arranging that the requests
- * get dealt with eventually.
- *
- * A global spin lock $io_request_lock must be held while manipulating the
- * requests on the request queue.
- *
- * The request on the head of the queue is by default assumed to be
- * potentially active, and it is not considered for re-ordering or merging
- * whenever the given queue is unplugged. This behaviour can be changed with
- * blk_queue_headactive().
- *
- * Note:
- * blk_init_queue() must be paired with a blk_cleanup_queue() call
- * when the block device is deactivated (such as at module unload).
- **/
-void blk_init_queue(request_queue_t * q, request_fn_proc * rfn)
-{
- INIT_LIST_HEAD(&q->queue_head);
- elevator_init(&q->elevator, ELEVATOR_LINUS);
- blk_init_free_list(q);
- q->request_fn = rfn;
- q->back_merge_fn = ll_back_merge_fn;
- q->front_merge_fn = ll_front_merge_fn;
- q->merge_requests_fn = ll_merge_requests_fn;
- q->make_request_fn = __make_request;
- q->plug_tq.sync = 0;
- q->plug_tq.routine = &generic_unplug_device;
- q->plug_tq.data = q;
- q->plugged = 0;
- /*
- * These booleans describe the queue properties. We set the
- * default (and most common) values here. Other drivers can
- * use the appropriate functions to alter the queue properties.
- * as appropriate.
- */
- q->plug_device_fn = generic_plug_device;
- q->head_active = 1;
-}
-
-#define blkdev_free_rq(list) list_entry((list)->next, struct request, queue);
-/*
- * Get a free request. io_request_lock must be held and interrupts
- * disabled on the way in.
- */
-static inline struct request *get_request(request_queue_t *q, int rw)
-{
- struct request *rq = NULL;
- struct request_list *rl = q->rq + rw;
-
- if (!list_empty(&rl->free)) {
- rq = blkdev_free_rq(&rl->free);
- list_del(&rq->queue);
- rl->count--;
- rq->rq_status = RQ_ACTIVE;
- rq->special = NULL;
- rq->q = q;
- }
-
- return rq;
-}
-
-/*
- * No available requests for this queue, unplug the device.
- */
-static struct request *__get_request_wait(request_queue_t *q, int rw)
-{
- register struct request *rq;
- DECLARE_WAITQUEUE(wait, current);
-
- generic_unplug_device(q);
- add_wait_queue(&q->wait_for_request, &wait);
- do {
- set_current_state(TASK_UNINTERRUPTIBLE);
- if (q->rq[rw].count < batch_requests)
- schedule();
- spin_lock_irq(&io_request_lock);
- rq = get_request(q,rw);
- spin_unlock_irq(&io_request_lock);
- } while (rq == NULL);
- remove_wait_queue(&q->wait_for_request, &wait);
- current->state = TASK_RUNNING;
- return rq;
-}
-
-static inline struct request *get_request_wait(request_queue_t *q, int rw)
-{
- register struct request *rq;
-
- spin_lock_irq(&io_request_lock);
- rq = get_request(q, rw);
- spin_unlock_irq(&io_request_lock);
- if (rq)
- return rq;
- return __get_request_wait(q, rw);
-}
-
-/* RO fail safe mechanism */
-
-static long ro_bits[MAX_BLKDEV][8];
-
-int is_read_only(kdev_t dev)
-{
- int minor,major;
-
- major = MAJOR(dev);
- minor = MINOR(dev);
- if (major < 0 || major >= MAX_BLKDEV) return 0;
- return ro_bits[major][minor >> 5] & (1 << (minor & 31));
-}
-
-void set_device_ro(kdev_t dev,int flag)
-{
- int minor,major;
-
- major = MAJOR(dev);
- minor = MINOR(dev);
- if (major < 0 || major >= MAX_BLKDEV) return;
- if (flag) ro_bits[major][minor >> 5] |= 1 << (minor & 31);
- else ro_bits[major][minor >> 5] &= ~(1 << (minor & 31));
-}
-
-inline void drive_stat_acct (kdev_t dev, int rw,
- unsigned long nr_sectors, int new_io)
-{
- unsigned int major = MAJOR(dev);
- unsigned int index;
-
- index = disk_index(dev);
- if ((index >= DK_MAX_DISK) || (major >= DK_MAX_MAJOR))
- return;
-
- kstat.dk_drive[major][index] += new_io;
- if (rw == READ) {
- kstat.dk_drive_rio[major][index] += new_io;
- kstat.dk_drive_rblk[major][index] += nr_sectors;
- } else if (rw == WRITE) {
- kstat.dk_drive_wio[major][index] += new_io;
- kstat.dk_drive_wblk[major][index] += nr_sectors;
- } else
- printk(KERN_ERR "drive_stat_acct: cmd not R/W?\n");
-}
-
-/*
- * add-request adds a request to the linked list.
- * io_request_lock is held and interrupts disabled, as we muck with the
- * request queue list.
- *
- * By this point, req->cmd is always either READ/WRITE, never READA,
- * which is important for drive_stat_acct() above.
- */
-static inline void add_request(request_queue_t * q, struct request * req,
- struct list_head *insert_here)
-{
- drive_stat_acct(req->rq_dev, req->cmd, req->nr_sectors, 1);
-
- if (!q->plugged && q->head_active && insert_here == &q->queue_head) {
- spin_unlock_irq(&io_request_lock);
- printk("list_empty(&q->queue_head) is %d\n",
- list_empty(&q->queue_head));
- BUG();
- }
-
- /*
- * elevator indicated where it wants this request to be
- * inserted at elevator_merge time
- */
- list_add(&req->queue, insert_here);
-}
-
-/*
- * Must be called with io_request_lock held and interrupts disabled
- */
-inline void blkdev_release_request(struct request *req)
-{
- request_queue_t *q = req->q;
- int rw = req->cmd;
-
- req->rq_status = RQ_INACTIVE;
- req->q = NULL;
-
- /*
- * Request may not have originated from ll_rw_blk. if not,
- * assume it has free buffers and check waiters
- */
- if (q) {
- list_add(&req->queue, &q->rq[rw].free);
- if (++q->rq[rw].count >= batch_requests && waitqueue_active(&q->wait_for_request))
- wake_up(&q->wait_for_request);
- }
-}
-
-/*
- * Has to be called with the request spinlock acquired
- */
-static void attempt_merge(request_queue_t * q,
- struct request *req,
- int max_sectors,
- int max_segments)
-{
- struct request *next;
-
- next = blkdev_next_request(req);
- if (req->sector + req->nr_sectors != next->sector)
- return;
- if (req->cmd != next->cmd
- || req->rq_dev != next->rq_dev
- || req->nr_sectors + next->nr_sectors > max_sectors
- || next->waiting)
- return;
- /*
- * If we are not allowed to merge these requests, then
- * return. If we are allowed to merge, then the count
- * will have been updated to the appropriate number,
- * and we shouldn't do it here too.
- */
- if (!q->merge_requests_fn(q, req, next, max_segments))
- return;
-
- q->elevator.elevator_merge_req_fn(req, next);
- req->bhtail->b_reqnext = next->bh;
- req->bhtail = next->bhtail;
- req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
- list_del(&next->queue);
- blkdev_release_request(next);
-}
-
-static inline void attempt_back_merge(request_queue_t * q,
- struct request *req,
- int max_sectors,
- int max_segments)
-{
- if (&req->queue == q->queue_head.prev)
- return;
- attempt_merge(q, req, max_sectors, max_segments);
-}
-
-static inline void attempt_front_merge(request_queue_t * q,
- struct list_head * head,
- struct request *req,
- int max_sectors,
- int max_segments)
-{
- struct list_head * prev;
-
- prev = req->queue.prev;
- if (head == prev)
- return;
- attempt_merge(q, blkdev_entry_to_request(prev), max_sectors, max_segments);
-}
-
-static int __make_request(request_queue_t * q, int rw,
- struct buffer_head * bh)
-{
- unsigned int sector, count;
- int max_segments = MAX_SEGMENTS;
- struct request * req, *freereq = NULL;
- int rw_ahead, max_sectors, el_ret;
- struct list_head *head, *insert_here;
- int latency;
- elevator_t *elevator = &q->elevator;
-
- count = bh->b_size >> 9;
- sector = bh->b_rsector;
-
- rw_ahead = 0; /* normal case; gets changed below for READA */
- switch (rw) {
- case READA:
- rw_ahead = 1;
- rw = READ; /* drop into READ */
- case READ:
- case WRITE:
- latency = elevator_request_latency(elevator, rw);
- break;
- default:
- BUG();
- goto end_io;
- }
-
- /* We'd better have a real physical mapping!
- Check this bit only if the buffer was dirty and just locked
- down by us so at this point flushpage will block and
- won't clear the mapped bit under us. */
- if (!buffer_mapped(bh))
- BUG();
-
- /*
- * Temporary solution - in 2.5 this will be done by the lowlevel
- * driver. Create a bounce buffer if the buffer data points into
- * high memory - keep the original buffer otherwise.
- */
-#if CONFIG_HIGHMEM
- bh = create_bounce(rw, bh);
-#endif
-
-/* look for a free request. */
- /*
- * Try to coalesce the new request with old requests
- */
- max_sectors = get_max_sectors(bh->b_rdev);
-
-again:
- req = NULL;
- head = &q->queue_head;
- /*
- * Now we acquire the request spinlock, we have to be mega careful
- * not to schedule or do something nonatomic
- */
- spin_lock_irq(&io_request_lock);
-
- insert_here = head->prev;
- if (list_empty(head)) {
- q->plug_device_fn(q, bh->b_rdev); /* is atomic */
- goto get_rq;
- } else if (q->head_active && !q->plugged)
- head = head->next;
-
- el_ret = elevator->elevator_merge_fn(q, &req, head, bh, rw,max_sectors);
- switch (el_ret) {
-
- case ELEVATOR_BACK_MERGE:
- if (!q->back_merge_fn(q, req, bh, max_segments))
- break;
- elevator->elevator_merge_cleanup_fn(q, req, count);
- req->bhtail->b_reqnext = bh;
- req->bhtail = bh;
- req->nr_sectors = req->hard_nr_sectors += count;
- blk_started_io(count);
- drive_stat_acct(req->rq_dev, req->cmd, count, 0);
- attempt_back_merge(q, req, max_sectors, max_segments);
- goto out;
-
- case ELEVATOR_FRONT_MERGE:
- if (!q->front_merge_fn(q, req, bh, max_segments))
- break;
- elevator->elevator_merge_cleanup_fn(q, req, count);
- bh->b_reqnext = req->bh;
- req->bh = bh;
- req->buffer = bh->b_data;
- req->current_nr_sectors = count;
- req->sector = req->hard_sector = sector;
- req->nr_sectors = req->hard_nr_sectors += count;
- blk_started_io(count);
- drive_stat_acct(req->rq_dev, req->cmd, count, 0);
- attempt_front_merge(q, head, req, max_sectors, max_segments);
- goto out;
-
- /*
- * elevator says don't/can't merge. get new request
- */
- case ELEVATOR_NO_MERGE:
- /*
- * use elevator hints as to where to insert the
- * request. if no hints, just add it to the back
- * of the queue
- */
- if (req)
- insert_here = &req->queue;
- break;
-
- default:
- printk("elevator returned crap (%d)\n", el_ret);
- BUG();
- }
-
- /*
- * Grab a free request from the freelist - if that is empty, check
- * if we are doing read ahead and abort instead of blocking for
- * a free slot.
- */
-get_rq:
- if (freereq) {
- req = freereq;
- freereq = NULL;
- } else if ((req = get_request(q, rw)) == NULL) {
- spin_unlock_irq(&io_request_lock);
- if (rw_ahead)
- goto end_io;
-
- freereq = __get_request_wait(q, rw);
- goto again;
- }
-
-/* fill up the request-info, and add it to the queue */
- req->elevator_sequence = latency;
- req->cmd = rw;
- req->errors = 0;
- req->hard_sector = req->sector = sector;
- req->hard_nr_sectors = req->nr_sectors = count;
- req->current_nr_sectors = count;
- req->nr_segments = 1; /* Always 1 for a new request. */
- req->nr_hw_segments = 1; /* Always 1 for a new request. */
- req->buffer = bh->b_data;
- req->waiting = NULL;
- req->bh = bh;
- req->bhtail = bh;
- req->rq_dev = bh->b_rdev;
- blk_started_io(count);
-
- add_request(q, req, insert_here);
-out:
- if (freereq)
- blkdev_release_request(freereq);
- spin_unlock_irq(&io_request_lock);
- return 0;
-end_io:
- bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
- return 0;
-}
-
-/**
- * generic_make_request: hand a buffer head to it's device driver for I/O
- * @rw: READ, WRITE, or READA - what sort of I/O is desired.
- * @bh: The buffer head describing the location in memory and on the device.
- *
- * generic_make_request() is used to make I/O requests of block
- * devices. It is passed a &struct buffer_head and a &rw value. The
- * %READ and %WRITE options are (hopefully) obvious in meaning. The
- * %READA value means that a read is required, but that the driver is
- * free to fail the request if, for example, it cannot get needed
- * resources immediately.
- *
- * generic_make_request() does not return any status. The
- * success/failure status of the request, along with notification of
- * completion, is delivered asynchronously through the bh->b_end_io
- * function described (one day) else where.
- *
- * The caller of generic_make_request must make sure that b_page,
- * b_addr, b_size are set to describe the memory buffer, that b_rdev
- * and b_rsector are set to describe the device address, and the
- * b_end_io and optionally b_private are set to describe how
- * completion notification should be signaled. BH_Mapped should also
- * be set (to confirm that b_dev and b_blocknr are valid).
- *
- * generic_make_request and the drivers it calls may use b_reqnext,
- * and may change b_rdev and b_rsector. So the values of these fields
- * should NOT be depended on after the call to generic_make_request.
- * Because of this, the caller should record the device address
- * information in b_dev and b_blocknr.
- *
- * Apart from those fields mentioned above, no other fields, and in
- * particular, no other flags, are changed by generic_make_request or
- * any lower level drivers.
- * */
-void generic_make_request (int rw, struct buffer_head * bh)
-{
- int major = MAJOR(bh->b_rdev);
- int minorsize = 0;
- request_queue_t *q;
-
- if (!bh->b_end_io)
- BUG();
-
- /* Test device size, when known. */
- if (blk_size[major])
- minorsize = blk_size[major][MINOR(bh->b_rdev)];
- if (minorsize) {
- unsigned long maxsector = (minorsize << 1) + 1;
- unsigned long sector = bh->b_rsector;
- unsigned int count = bh->b_size >> 9;
-
- if (maxsector < count || maxsector - count < sector) {
- /* Yecch */
- bh->b_state &= (1 << BH_Lock) | (1 << BH_Mapped);
-
- /* This may well happen - the kernel calls bread()
- without checking the size of the device, e.g.,
- when mounting a device. */
- printk(KERN_INFO
- "attempt to access beyond end of device\n");
- printk(KERN_INFO "%s: rw=%d, want=%ld, limit=%d\n",
- kdevname(bh->b_rdev), rw,
- (sector + count)>>1, minorsize);
-
- /* Yecch again */
- bh->b_end_io(bh, 0);
- return;
- }
- }
-
- /*
- * Resolve the mapping until finished. (drivers are
- * still free to implement/resolve their own stacking
- * by explicitly returning 0)
- */
- /* NOTE: we don't repeat the blk_size check for each new device.
- * Stacking drivers are expected to know what they are doing.
- */
- do {
- q = blk_get_queue(bh->b_rdev);
- if (!q) {
- printk(KERN_ERR
- "generic_make_request: Trying to access "
- "nonexistent block-device %s (%ld)\n",
- kdevname(bh->b_rdev), bh->b_rsector);
- buffer_IO_error(bh);
- break;
- }
- } while (q->make_request_fn(q, rw, bh));
-}
-
-
-/**
- * submit_bh: submit a buffer_head to the block device later for I/O
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
- * @bh: The &struct buffer_head which describes the I/O
- *
- * submit_bh() is very similar in purpose to generic_make_request(), and
- * uses that function to do most of the work.
- *
- * The extra functionality provided by submit_bh is to determine
- * b_rsector from b_blocknr and b_size, and to set b_rdev from b_dev.
- * This is is appropriate for IO requests that come from the buffer
- * cache and page cache which (currently) always use aligned blocks.
- */
-void submit_bh(int rw, struct buffer_head * bh)
-{
- int count = bh->b_size >> 9;
-
- if (!test_bit(BH_Lock, &bh->b_state))
- BUG();
-
- set_bit(BH_Req, &bh->b_state);
-
- /*
- * First step, 'identity mapping' - RAID or LVM might
- * further remap this.
- */
- bh->b_rdev = bh->b_dev;
- bh->b_rsector = bh->b_blocknr * count;
-
- generic_make_request(rw, bh);
-
- switch (rw) {
- case WRITE:
- kstat.pgpgout += count;
- break;
- default:
- kstat.pgpgin += count;
- break;
- }
-}
-
-/**
- * ll_rw_block: low-level access to block devices
- * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
- * @nr: number of &struct buffer_heads in the array
- * @bhs: array of pointers to &struct buffer_head
- *
- * ll_rw_block() takes an array of pointers to &struct buffer_heads,
- * and requests an I/O operation on them, either a %READ or a %WRITE.
- * The third %READA option is described in the documentation for
- * generic_make_request() which ll_rw_block() calls.
- *
- * This function provides extra functionality that is not in
- * generic_make_request() that is relevant to buffers in the buffer
- * cache or page cache. In particular it drops any buffer that it
- * cannot get a lock on (with the BH_Lock state bit), any buffer that
- * appears to be clean when doing a write request, and any buffer that
- * appears to be up-to-date when doing read request. Further it marks
- * as clean buffers that are processed for writing (the buffer cache
- * wont assume that they are actually clean until the buffer gets
- * unlocked).
- *
- * ll_rw_block sets b_end_io to simple completion handler that marks
- * the buffer up-to-date (if approriate), unlocks the buffer and wakes
- * any waiters. As client that needs a more interesting completion
- * routine should call submit_bh() (or generic_make_request())
- * directly.
- *
- * Caveat:
- * All of the buffers must be for the same device, and must also be
- * of the current approved size for the device. */
-
-void ll_rw_block(int rw, int nr, struct buffer_head * bhs[])
-{
- unsigned int major;
- int correct_size;
- int i;
-
- if (!nr)
- return;
-
- major = MAJOR(bhs[0]->b_dev);
-
- /* Determine correct block size for this device. */
- correct_size = get_hardsect_size(bhs[0]->b_dev);
-
- /* Verify requested block sizes. */
- for (i = 0; i < nr; i++) {
- struct buffer_head *bh = bhs[i];
- if (bh->b_size % correct_size) {
- printk(KERN_NOTICE "ll_rw_block: device %s: "
- "only %d-char blocks implemented (%u)\n",
- kdevname(bhs[0]->b_dev),
- correct_size, bh->b_size);
- goto sorry;
- }
- }
-
- if ((rw & WRITE) && is_read_only(bhs[0]->b_dev)) {
- printk(KERN_NOTICE "Can't write to read-only device %s\n",
- kdevname(bhs[0]->b_dev));
- goto sorry;
- }
-
- for (i = 0; i < nr; i++) {
- struct buffer_head *bh = bhs[i];
-
- /* Only one thread can actually submit the I/O. */
- if (test_and_set_bit(BH_Lock, &bh->b_state))
- continue;
-
- /* We have the buffer lock */
- atomic_inc(&bh->b_count);
- bh->b_end_io = end_buffer_io_sync;
-
- switch(rw) {
- case WRITE:
- if (!atomic_set_buffer_clean(bh))
- /* Hmmph! Nothing to write */
- goto end_io;
- __mark_buffer_clean(bh);
- break;
-
- case READA:
- case READ:
- if (buffer_uptodate(bh))
- /* Hmmph! Already have it */
- goto end_io;
- break;
- default:
- BUG();
- end_io:
- bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
- continue;
- }
-
- submit_bh(rw, bh);
- }
- return;
-
-sorry:
- /* Make sure we don't get infinite dirty retries.. */
- for (i = 0; i < nr; i++)
- mark_buffer_clean(bhs[i]);
-}
-
-#ifdef CONFIG_STRAM_SWAP
-extern int stram_device_init (void);
-#endif
-
-
-/**
- * end_that_request_first - end I/O on one buffer.
- * @req: the request being processed
- * @uptodate: 0 for I/O error
- * @name: the name printed for an I/O error
- *
- * Description:
- * Ends I/O on the first buffer attached to @req, and sets it up
- * for the next buffer_head (if any) in the cluster.
- *
- * Return:
- * 0 - we are done with this request, call end_that_request_last()
- * 1 - still buffers pending for this request
- *
- * Caveat:
- * Drivers implementing their own end_request handling must call
- * blk_finished_io() appropriately.
- **/
-
-int end_that_request_first (struct request *req, int uptodate, char *name)
-{
- struct buffer_head * bh;
- int nsect;
-
- req->errors = 0;
- if (!uptodate)
- printk("end_request: I/O error, dev %s (%s), sector %lu\n",
- kdevname(req->rq_dev), name, req->sector);
-
- if ((bh = req->bh) != NULL) {
- nsect = bh->b_size >> 9;
- blk_finished_io(nsect);
- req->bh = bh->b_reqnext;
- bh->b_reqnext = NULL;
- bh->b_end_io(bh, uptodate);
- if ((bh = req->bh) != NULL) {
- req->hard_sector += nsect;
- req->hard_nr_sectors -= nsect;
- req->sector = req->hard_sector;
- req->nr_sectors = req->hard_nr_sectors;
-
- req->current_nr_sectors = bh->b_size >> 9;
- if (req->nr_sectors < req->current_nr_sectors) {
- req->nr_sectors = req->current_nr_sectors;
- printk("end_request: buffer-list destroyed\n");
- }
- req->buffer = bh->b_data;
- return 1;
- }
- }
- return 0;
-}
-
-void end_that_request_last(struct request *req)
-{
- if (req->waiting != NULL)
- complete(req->waiting);
-
- blkdev_release_request(req);
-}
-
-#define MB(kb) ((kb) << 10)
-
-int __init blk_dev_init(void)
-{
- struct blk_dev_struct *dev;
- int total_ram;
-
- request_cachep = kmem_cache_create("blkdev_requests",
- sizeof(struct request),
- 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
-
- if (!request_cachep)
- panic("Can't create request pool slab cache\n");
-
- for (dev = blk_dev + MAX_BLKDEV; dev-- != blk_dev;)
- dev->queue = NULL;
-
- memset(ro_bits,0,sizeof(ro_bits));
- memset(max_readahead, 0, sizeof(max_readahead));
- memset(max_sectors, 0, sizeof(max_sectors));
-
- total_ram = nr_free_pages() << (PAGE_SHIFT - 10);
-
- /*
- * Free request slots per queue.
- * (Half for reads, half for writes)
- */
- queue_nr_requests = 64;
- if (total_ram > MB(32))
- queue_nr_requests = 128;
-
- /*
- * Batch frees according to queue length
- */
- batch_requests = queue_nr_requests/4;
- printk("block: %d slots per queue, batch=%d\n", queue_nr_requests, batch_requests);
-
-#ifdef CONFIG_AMIGA_Z2RAM
- z2_init();
-#endif
-#ifdef CONFIG_STRAM_SWAP
- stram_device_init();
-#endif
-#ifdef CONFIG_BLK_DEV_RAM
- rd_init();
-#endif
-#ifdef CONFIG_ISP16_CDI
- isp16_init();
-#endif
-#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_IDE)
- ide_init(); /* this MUST precede hd_init */
-#endif
-#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_HD)
- hd_init();
-#endif
-#ifdef CONFIG_BLK_DEV_PS2
- ps2esdi_init();
-#endif
-#ifdef CONFIG_BLK_DEV_XD
- xd_init();
-#endif
-#ifdef CONFIG_BLK_DEV_MFM
- mfm_init();
-#endif
-#ifdef CONFIG_PARIDE
- { extern void paride_init(void); paride_init(); };
-#endif
-#ifdef CONFIG_MAC_FLOPPY
- swim3_init();
-#endif
-#ifdef CONFIG_BLK_DEV_SWIM_IOP
- swimiop_init();
-#endif
-#ifdef CONFIG_AMIGA_FLOPPY
- amiga_floppy_init();
-#endif
-#ifdef CONFIG_ATARI_FLOPPY
- atari_floppy_init();
-#endif
-#ifdef CONFIG_BLK_DEV_FD
- floppy_init();
-#else
-#if defined(__i386__) && !defined(CONFIG_XENO) /* Do we even need this? */
- outb_p(0xc, 0x3f2);
-#endif
-#endif
-#ifdef CONFIG_CDU31A
- cdu31a_init();
-#endif
-#ifdef CONFIG_ATARI_ACSI
- acsi_init();
-#endif
-#ifdef CONFIG_MCD
- mcd_init();
-#endif
-#ifdef CONFIG_MCDX
- mcdx_init();
-#endif
-#ifdef CONFIG_SBPCD
- sbpcd_init();
-#endif
-#ifdef CONFIG_AZTCD
- aztcd_init();
-#endif
-#ifdef CONFIG_CDU535
- sony535_init();
-#endif
-#ifdef CONFIG_GSCD
- gscd_init();
-#endif
-#ifdef CONFIG_CM206
- cm206_init();
-#endif
-#ifdef CONFIG_OPTCD
- optcd_init();
-#endif
-#ifdef CONFIG_SJCD
- sjcd_init();
-#endif
-#ifdef CONFIG_APBLOCK
- ap_init();
-#endif
-#ifdef CONFIG_DDV
- ddv_init();
-#endif
-#ifdef CONFIG_MDISK
- mdisk_init();
-#endif
-#ifdef CONFIG_DASD
- dasd_init();
-#endif
-#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_BLOCK)
- tapeblock_init();
-#endif
-#ifdef CONFIG_BLK_DEV_XPRAM
- xpram_init();
-#endif
-
-#ifdef CONFIG_SUN_JSFLASH
- jsfd_init();
-#endif
-
-#ifdef CONFIG_XENOLINUX_BLOCK
- xlblk_init();
-#endif
-
- return 0;
-};
-
-EXPORT_SYMBOL(io_request_lock);
-EXPORT_SYMBOL(end_that_request_first);
-EXPORT_SYMBOL(end_that_request_last);
-EXPORT_SYMBOL(blk_init_queue);
-EXPORT_SYMBOL(blk_get_queue);
-EXPORT_SYMBOL(blk_cleanup_queue);
-EXPORT_SYMBOL(blk_queue_headactive);
-EXPORT_SYMBOL(blk_queue_make_request);
-EXPORT_SYMBOL(generic_make_request);
-EXPORT_SYMBOL(blkdev_release_request);
-EXPORT_SYMBOL(generic_unplug_device);
+++ /dev/null
-/*
- * ramdisk.c - Multiple RAM disk driver - gzip-loading version - v. 0.8 beta.
- *
- * (C) Chad Page, Theodore Ts'o, et. al, 1995.
- *
- * This RAM disk is designed to have filesystems created on it and mounted
- * just like a regular floppy disk.
- *
- * It also does something suggested by Linus: use the buffer cache as the
- * RAM disk data. This makes it possible to dynamically allocate the RAM disk
- * buffer - with some consequences I have to deal with as I write this.
- *
- * This code is based on the original ramdisk.c, written mostly by
- * Theodore Ts'o (TYT) in 1991. The code was largely rewritten by
- * Chad Page to use the buffer cache to store the RAM disk data in
- * 1995; Theodore then took over the driver again, and cleaned it up
- * for inclusion in the mainline kernel.
- *
- * The original CRAMDISK code was written by Richard Lyons, and
- * adapted by Chad Page to use the new RAM disk interface. Theodore
- * Ts'o rewrote it so that both the compressed RAM disk loader and the
- * kernel decompressor uses the same inflate.c codebase. The RAM disk
- * loader now also loads into a dynamic (buffer cache based) RAM disk,
- * not the old static RAM disk. Support for the old static RAM disk has
- * been completely removed.
- *
- * Loadable module support added by Tom Dyas.
- *
- * Further cleanups by Chad Page (page0588@sundance.sjsu.edu):
- * Cosmetic changes in #ifdef MODULE, code movement, etc.
- * When the RAM disk module is removed, free the protected buffers
- * Default RAM disk size changed to 2.88 MB
- *
- * Added initrd: Werner Almesberger & Hans Lermen, Feb '96
- *
- * 4/25/96 : Made RAM disk size a parameter (default is now 4 MB)
- * - Chad Page
- *
- * Add support for fs images split across >1 disk, Paul Gortmaker, Mar '98
- *
- * Make block size and block size shift for RAM disks a global macro
- * and set blk_size for -ENOSPC, Werner Fink <werner@suse.de>, Apr '99
- */
-
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <linux/minix_fs.h>
-#include <linux/ext2_fs.h>
-#include <linux/romfs_fs.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/hdreg.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/slab.h>
-#include <linux/ioctl.h>
-#include <linux/fd.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/devfs_fs_kernel.h>
-#include <linux/smp_lock.h>
-
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/byteorder.h>
-
-extern void wait_for_keypress(void);
-
-/*
- * 35 has been officially registered as the RAMDISK major number, but
- * so is the original MAJOR number of 1. We're using 1 in
- * include/linux/major.h for now
- */
-#define MAJOR_NR RAMDISK_MAJOR
-#include <linux/blk.h>
-#include <linux/blkpg.h>
-
-/* The RAM disk size is now a parameter */
-#define NUM_RAMDISKS 16 /* This cannot be overridden (yet) */
-
-#ifndef MODULE
-/* We don't have to load RAM disks or gunzip them in a module. */
-#define RD_LOADER
-#define BUILD_CRAMDISK
-
-void rd_load(void);
-static int crd_load(struct file *fp, struct file *outfp);
-
-#ifdef CONFIG_BLK_DEV_INITRD
-static int initrd_users;
-#endif
-#endif
-
-/* Various static variables go here. Most are used only in the RAM disk code.
- */
-
-static unsigned long rd_length[NUM_RAMDISKS]; /* Size of RAM disks in bytes */
-static int rd_hardsec[NUM_RAMDISKS]; /* Size of real blocks in bytes */
-static int rd_blocksizes[NUM_RAMDISKS]; /* Size of 1024 byte blocks :) */
-static int rd_kbsize[NUM_RAMDISKS]; /* Size in blocks of 1024 bytes */
-static devfs_handle_t devfs_handle;
-static struct block_device *rd_bdev[NUM_RAMDISKS];/* Protected device data */
-
-/*
- * Parameters for the boot-loading of the RAM disk. These are set by
- * init/main.c (from arguments to the kernel command line) or from the
- * architecture-specific setup routine (from the stored boot sector
- * information).
- */
-int rd_size = CONFIG_BLK_DEV_RAM_SIZE; /* Size of the RAM disks */
-/*
- * It would be very desiderable to have a soft-blocksize (that in the case
- * of the ramdisk driver is also the hardblocksize ;) of PAGE_SIZE because
- * doing that we'll achieve a far better MM footprint. Using a rd_blocksize of
- * BLOCK_SIZE in the worst case we'll make PAGE_SIZE/BLOCK_SIZE buffer-pages
- * unfreeable. With a rd_blocksize of PAGE_SIZE instead we are sure that only
- * 1 page will be protected. Depending on the size of the ramdisk you
- * may want to change the ramdisk blocksize to achieve a better or worse MM
- * behaviour. The default is still BLOCK_SIZE (needed by rd_load_image that
- * supposes the filesystem in the image uses a BLOCK_SIZE blocksize).
- */
-int rd_blocksize = BLOCK_SIZE; /* blocksize of the RAM disks */
-
-#ifndef MODULE
-
-int rd_doload; /* 1 = load RAM disk, 0 = don't load */
-int rd_prompt = 1; /* 1 = prompt for RAM disk, 0 = don't prompt */
-int rd_image_start; /* starting block # of image */
-#ifdef CONFIG_BLK_DEV_INITRD
-unsigned long initrd_start, initrd_end;
-int mount_initrd = 1; /* zero if initrd should not be mounted */
-int initrd_below_start_ok;
-
-static int __init no_initrd(char *str)
-{
- mount_initrd = 0;
- return 1;
-}
-
-__setup("noinitrd", no_initrd);
-
-#endif
-
-static int __init ramdisk_start_setup(char *str)
-{
- rd_image_start = simple_strtol(str,NULL,0);
- return 1;
-}
-
-static int __init load_ramdisk(char *str)
-{
- rd_doload = simple_strtol(str,NULL,0) & 3;
- return 1;
-}
-
-static int __init prompt_ramdisk(char *str)
-{
- rd_prompt = simple_strtol(str,NULL,0) & 1;
- return 1;
-}
-
-static int __init ramdisk_size(char *str)
-{
- rd_size = simple_strtol(str,NULL,0);
- return 1;
-}
-
-static int __init ramdisk_size2(char *str)
-{
- return ramdisk_size(str);
-}
-
-static int __init ramdisk_blocksize(char *str)
-{
- rd_blocksize = simple_strtol(str,NULL,0);
- return 1;
-}
-
-__setup("ramdisk_start=", ramdisk_start_setup);
-__setup("load_ramdisk=", load_ramdisk);
-__setup("prompt_ramdisk=", prompt_ramdisk);
-__setup("ramdisk=", ramdisk_size);
-__setup("ramdisk_size=", ramdisk_size2);
-__setup("ramdisk_blocksize=", ramdisk_blocksize);
-
-#endif
-
-/*
- * Copyright (C) 2000 Linus Torvalds.
- * 2000 Transmeta Corp.
- * aops copied from ramfs.
- */
-static int ramdisk_readpage(struct file *file, struct page * page)
-{
- if (!Page_Uptodate(page)) {
- memset(kmap(page), 0, PAGE_CACHE_SIZE);
- kunmap(page);
- flush_dcache_page(page);
- SetPageUptodate(page);
- }
- UnlockPage(page);
- return 0;
-}
-
-static int ramdisk_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
-{
- if (!Page_Uptodate(page)) {
- void *addr = page_address(page);
- memset(addr, 0, PAGE_CACHE_SIZE);
- flush_dcache_page(page);
- SetPageUptodate(page);
- }
- SetPageDirty(page);
- return 0;
-}
-
-static int ramdisk_commit_write(struct file *file, struct page *page, unsigned offset, unsigned to)
-{
- return 0;
-}
-
-static struct address_space_operations ramdisk_aops = {
- readpage: ramdisk_readpage,
- writepage: fail_writepage,
- prepare_write: ramdisk_prepare_write,
- commit_write: ramdisk_commit_write,
-};
-
-static int rd_blkdev_pagecache_IO(int rw, struct buffer_head * sbh, int minor)
-{
- struct address_space * mapping;
- unsigned long index;
- int offset, size, err;
-
- err = -EIO;
- err = 0;
- mapping = rd_bdev[minor]->bd_inode->i_mapping;
-
- index = sbh->b_rsector >> (PAGE_CACHE_SHIFT - 9);
- offset = (sbh->b_rsector << 9) & ~PAGE_CACHE_MASK;
- size = sbh->b_size;
-
- do {
- int count;
- struct page ** hash;
- struct page * page;
- char * src, * dst;
- int unlock = 0;
-
- count = PAGE_CACHE_SIZE - offset;
- if (count > size)
- count = size;
- size -= count;
-
- hash = page_hash(mapping, index);
- page = __find_get_page(mapping, index, hash);
- if (!page) {
- page = grab_cache_page(mapping, index);
- err = -ENOMEM;
- if (!page)
- goto out;
- err = 0;
-
- if (!Page_Uptodate(page)) {
- memset(kmap(page), 0, PAGE_CACHE_SIZE);
- kunmap(page);
- SetPageUptodate(page);
- }
-
- unlock = 1;
- }
-
- index++;
-
- if (rw == READ) {
- src = kmap(page);
- src += offset;
- dst = bh_kmap(sbh);
- } else {
- dst = kmap(page);
- dst += offset;
- src = bh_kmap(sbh);
- }
- offset = 0;
-
- memcpy(dst, src, count);
-
- kunmap(page);
- bh_kunmap(sbh);
-
- if (rw == READ) {
- flush_dcache_page(page);
- } else {
- SetPageDirty(page);
- }
- if (unlock)
- UnlockPage(page);
- __free_page(page);
- } while (size);
-
- out:
- return err;
-}
-
-/*
- * Basically, my strategy here is to set up a buffer-head which can't be
- * deleted, and make that my Ramdisk. If the request is outside of the
- * allocated size, we must get rid of it...
- *
- * 19-JAN-1998 Richard Gooch <rgooch@atnf.csiro.au> Added devfs support
- *
- */
-static int rd_make_request(request_queue_t * q, int rw, struct buffer_head *sbh)
-{
- unsigned int minor;
- unsigned long offset, len;
-
- minor = MINOR(sbh->b_rdev);
-
- if (minor >= NUM_RAMDISKS)
- goto fail;
-
-
- offset = sbh->b_rsector << 9;
- len = sbh->b_size;
-
- if ((offset + len) > rd_length[minor])
- goto fail;
-
- if (rw==READA)
- rw=READ;
- if ((rw != READ) && (rw != WRITE)) {
- printk(KERN_INFO "RAMDISK: bad command: %d\n", rw);
- goto fail;
- }
-
- if (rd_blkdev_pagecache_IO(rw, sbh, minor))
- goto fail;
-
- sbh->b_end_io(sbh,1);
- return 0;
- fail:
- sbh->b_end_io(sbh,0);
- return 0;
-}
-
-static int rd_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg)
-{
- int error = -EINVAL;
- unsigned int minor;
-
- if (!inode || !inode->i_rdev)
- goto out;
-
- minor = MINOR(inode->i_rdev);
-
- switch (cmd) {
- case BLKFLSBUF:
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- /* special: we want to release the ramdisk memory,
- it's not like with the other blockdevices where
- this ioctl only flushes away the buffer cache. */
- error = -EBUSY;
- down(&inode->i_bdev->bd_sem);
- if (inode->i_bdev->bd_openers <= 2) {
- truncate_inode_pages(inode->i_mapping, 0);
- error = 0;
- }
- up(&inode->i_bdev->bd_sem);
- break;
- case BLKGETSIZE: /* Return device size */
- if (!arg)
- break;
- error = put_user(rd_kbsize[minor] << 1, (unsigned long *) arg);
- break;
- case BLKGETSIZE64:
- error = put_user((u64)rd_kbsize[minor]<<10, (u64*)arg);
- break;
- case BLKROSET:
- case BLKROGET:
- case BLKSSZGET:
- error = blk_ioctl(inode->i_rdev, cmd, arg);
- };
-out:
- return error;
-}
-
-
-#ifdef CONFIG_BLK_DEV_INITRD
-
-static ssize_t initrd_read(struct file *file, char *buf,
- size_t count, loff_t *ppos)
-{
- int left;
-
- left = initrd_end - initrd_start - *ppos;
- if (count > left) count = left;
- if (count == 0) return 0;
- copy_to_user(buf, (char *)initrd_start + *ppos, count);
- *ppos += count;
- return count;
-}
-
-
-static int initrd_release(struct inode *inode,struct file *file)
-{
- extern void free_initrd_mem(unsigned long, unsigned long);
-
- lock_kernel();
- if (!--initrd_users) {
- free_initrd_mem(initrd_start, initrd_end);
- initrd_start = 0;
- }
- unlock_kernel();
- blkdev_put(inode->i_bdev, BDEV_FILE);
- return 0;
-}
-
-
-static struct file_operations initrd_fops = {
- read: initrd_read,
- release: initrd_release,
-};
-
-#endif
-
-
-static int rd_open(struct inode * inode, struct file * filp)
-{
- int unit = DEVICE_NR(inode->i_rdev);
-
-#ifdef CONFIG_BLK_DEV_INITRD
- if (unit == INITRD_MINOR) {
- if (!initrd_start) return -ENODEV;
- initrd_users++;
- filp->f_op = &initrd_fops;
- return 0;
- }
-#endif
-
- if (unit >= NUM_RAMDISKS)
- return -ENXIO;
-
- /*
- * Immunize device against invalidate_buffers() and prune_icache().
- */
- if (rd_bdev[unit] == NULL) {
- rd_bdev[unit] = bdget(kdev_t_to_nr(inode->i_rdev));
- rd_bdev[unit]->bd_openers++;
- rd_bdev[unit]->bd_inode->i_mapping->a_ops = &ramdisk_aops;
- }
-
- return 0;
-}
-
-static struct block_device_operations rd_bd_op = {
- owner: THIS_MODULE,
- open: rd_open,
- ioctl: rd_ioctl,
-};
-
-#ifdef MODULE
-/* Before freeing the module, invalidate all of the protected buffers! */
-static void __exit rd_cleanup (void)
-{
- int i;
-
- for (i = 0 ; i < NUM_RAMDISKS; i++) {
- struct block_device *bdev = rd_bdev[i];
- rd_bdev[i] = NULL;
- if (bdev)
- blkdev_put(bdev, BDEV_FILE);
- destroy_buffers(MKDEV(MAJOR_NR, i));
- }
-
- devfs_unregister (devfs_handle);
- unregister_blkdev( MAJOR_NR, "ramdisk" );
- hardsect_size[MAJOR_NR] = NULL;
- blksize_size[MAJOR_NR] = NULL;
- blk_size[MAJOR_NR] = NULL;
-}
-#endif
-
-/* This is the registration and initialization section of the RAM disk driver */
-int __init rd_init (void)
-{
- int i;
-
- if (rd_blocksize > PAGE_SIZE || rd_blocksize < 512 ||
- (rd_blocksize & (rd_blocksize-1)))
- {
- printk("RAMDISK: wrong blocksize %d, reverting to defaults\n",
- rd_blocksize);
- rd_blocksize = BLOCK_SIZE;
- }
-
- if (register_blkdev(MAJOR_NR, "ramdisk", &rd_bd_op)) {
- printk("RAMDISK: Could not get major %d", MAJOR_NR);
- return -EIO;
- }
-
- blk_queue_make_request(BLK_DEFAULT_QUEUE(MAJOR_NR), &rd_make_request);
-
- for (i = 0; i < NUM_RAMDISKS; i++) {
- /* rd_size is given in kB */
- rd_length[i] = rd_size << 10;
- rd_hardsec[i] = rd_blocksize;
- rd_blocksizes[i] = rd_blocksize;
- rd_kbsize[i] = rd_size;
- }
- devfs_handle = devfs_mk_dir (NULL, "rd", NULL);
- devfs_register_series (devfs_handle, "%u", NUM_RAMDISKS,
- DEVFS_FL_DEFAULT, MAJOR_NR, 0,
- S_IFBLK | S_IRUSR | S_IWUSR,
- &rd_bd_op, NULL);
-
- for (i = 0; i < NUM_RAMDISKS; i++)
- register_disk(NULL, MKDEV(MAJOR_NR,i), 1, &rd_bd_op, rd_size<<1);
-
-#ifdef CONFIG_BLK_DEV_INITRD
- /* We ought to separate initrd operations here */
- register_disk(NULL, MKDEV(MAJOR_NR,INITRD_MINOR), 1, &rd_bd_op, rd_size<<1);
-#endif
-
- hardsect_size[MAJOR_NR] = rd_hardsec; /* Size of the RAM disk blocks */
- blksize_size[MAJOR_NR] = rd_blocksizes; /* Avoid set_blocksize() check */
- blk_size[MAJOR_NR] = rd_kbsize; /* Size of the RAM disk in kB */
-
- /* rd_size is given in kB */
- printk("RAMDISK driver initialized: "
- "%d RAM disks of %dK size %d blocksize\n",
- NUM_RAMDISKS, rd_size, rd_blocksize);
-
- return 0;
-}
-
-#ifdef MODULE
-module_init(rd_init);
-module_exit(rd_cleanup);
-#endif
-
-/* loadable module support */
-MODULE_PARM (rd_size, "1i");
-MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
-MODULE_PARM (rd_blocksize, "i");
-MODULE_PARM_DESC(rd_blocksize, "Blocksize of each RAM disk in bytes.");
-
-MODULE_LICENSE("GPL");
-
-/* End of non-loading portions of the RAM disk driver */
-
-#ifdef RD_LOADER
-/*
- * This routine tries to find a RAM disk image to load, and returns the
- * number of blocks to read for a non-compressed image, 0 if the image
- * is a compressed image, and -1 if an image with the right magic
- * numbers could not be found.
- *
- * We currently check for the following magic numbers:
- * minix
- * ext2
- * romfs
- * gzip
- */
-static int __init
-identify_ramdisk_image(kdev_t device, struct file *fp, int start_block)
-{
- const int size = 512;
- struct minix_super_block *minixsb;
- struct ext2_super_block *ext2sb;
- struct romfs_super_block *romfsb;
- int nblocks = -1;
- unsigned char *buf;
-
- buf = kmalloc(size, GFP_KERNEL);
- if (buf == 0)
- return -1;
-
- minixsb = (struct minix_super_block *) buf;
- ext2sb = (struct ext2_super_block *) buf;
- romfsb = (struct romfs_super_block *) buf;
- memset(buf, 0xe5, size);
-
- /*
- * Read block 0 to test for gzipped kernel
- */
- if (fp->f_op->llseek)
- fp->f_op->llseek(fp, start_block * BLOCK_SIZE, 0);
- fp->f_pos = start_block * BLOCK_SIZE;
-
- fp->f_op->read(fp, buf, size, &fp->f_pos);
-
- /*
- * If it matches the gzip magic numbers, return -1
- */
- if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) {
- printk(KERN_NOTICE
- "RAMDISK: Compressed image found at block %d\n",
- start_block);
- nblocks = 0;
- goto done;
- }
-
- /* romfs is at block zero too */
- if (romfsb->word0 == ROMSB_WORD0 &&
- romfsb->word1 == ROMSB_WORD1) {
- printk(KERN_NOTICE
- "RAMDISK: romfs filesystem found at block %d\n",
- start_block);
- nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS;
- goto done;
- }
-
- /*
- * Read block 1 to test for minix and ext2 superblock
- */
- if (fp->f_op->llseek)
- fp->f_op->llseek(fp, (start_block+1) * BLOCK_SIZE, 0);
- fp->f_pos = (start_block+1) * BLOCK_SIZE;
-
- fp->f_op->read(fp, buf, size, &fp->f_pos);
-
- /* Try minix */
- if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
- minixsb->s_magic == MINIX_SUPER_MAGIC2) {
- printk(KERN_NOTICE
- "RAMDISK: Minix filesystem found at block %d\n",
- start_block);
- nblocks = minixsb->s_nzones << minixsb->s_log_zone_size;
- goto done;
- }
-
- /* Try ext2 */
- if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) {
- printk(KERN_NOTICE
- "RAMDISK: ext2 filesystem found at block %d\n",
- start_block);
- nblocks = le32_to_cpu(ext2sb->s_blocks_count);
- goto done;
- }
-
- printk(KERN_NOTICE
- "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
- start_block);
-
-done:
- if (fp->f_op->llseek)
- fp->f_op->llseek(fp, start_block * BLOCK_SIZE, 0);
- fp->f_pos = start_block * BLOCK_SIZE;
-
- kfree(buf);
- return nblocks;
-}
-
-/*
- * This routine loads in the RAM disk image.
- */
-static void __init rd_load_image(kdev_t device, int offset, int unit)
-{
- struct inode *inode, *out_inode;
- struct file infile, outfile;
- struct dentry in_dentry, out_dentry;
- mm_segment_t fs;
- kdev_t ram_device;
- int nblocks, i;
- char *buf;
- unsigned short rotate = 0;
- unsigned short devblocks = 0;
-#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES) && !defined(CONFIG_XENO)
- char rotator[4] = { '|' , '/' , '-' , '\\' };
-#endif
- ram_device = MKDEV(MAJOR_NR, unit);
-
- if ((inode = get_empty_inode()) == NULL)
- return;
- memset(&infile, 0, sizeof(infile));
- memset(&in_dentry, 0, sizeof(in_dentry));
- infile.f_mode = 1; /* read only */
- infile.f_dentry = &in_dentry;
- in_dentry.d_inode = inode;
- infile.f_op = &def_blk_fops;
- init_special_inode(inode, S_IFBLK | S_IRUSR, kdev_t_to_nr(device));
-
- if ((out_inode = get_empty_inode()) == NULL)
- goto free_inode;
- memset(&outfile, 0, sizeof(outfile));
- memset(&out_dentry, 0, sizeof(out_dentry));
- outfile.f_mode = 3; /* read/write */
- outfile.f_dentry = &out_dentry;
- out_dentry.d_inode = out_inode;
- outfile.f_op = &def_blk_fops;
- init_special_inode(out_inode, S_IFBLK | S_IRUSR | S_IWUSR, kdev_t_to_nr(ram_device));
-
- if (blkdev_open(inode, &infile) != 0) {
- iput(out_inode);
- goto free_inode;
- }
- if (blkdev_open(out_inode, &outfile) != 0)
- goto free_inodes;
-
- fs = get_fs();
- set_fs(KERNEL_DS);
-
- nblocks = identify_ramdisk_image(device, &infile, offset);
- if (nblocks < 0)
- goto done;
-
- if (nblocks == 0) {
-#ifdef BUILD_CRAMDISK
- if (crd_load(&infile, &outfile) == 0)
- goto successful_load;
-#else
- printk(KERN_NOTICE
- "RAMDISK: Kernel does not support compressed "
- "RAM disk images\n");
-#endif
- goto done;
- }
-
- /*
- * NOTE NOTE: nblocks suppose that the blocksize is BLOCK_SIZE, so
- * rd_load_image will work only with filesystem BLOCK_SIZE wide!
- * So make sure to use 1k blocksize while generating ext2fs
- * ramdisk-images.
- */
- if (nblocks > (rd_length[unit] >> BLOCK_SIZE_BITS)) {
- printk("RAMDISK: image too big! (%d/%ld blocks)\n",
- nblocks, rd_length[unit] >> BLOCK_SIZE_BITS);
- goto done;
- }
-
- /*
- * OK, time to copy in the data
- */
- buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
- if (buf == 0) {
- printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
- goto done;
- }
-
- if (blk_size[MAJOR(device)])
- devblocks = blk_size[MAJOR(device)][MINOR(device)];
-
-#ifdef CONFIG_BLK_DEV_INITRD
- if (MAJOR(device) == MAJOR_NR && MINOR(device) == INITRD_MINOR)
- devblocks = nblocks;
-#endif
-
- if (devblocks == 0) {
- printk(KERN_ERR "RAMDISK: could not determine device size\n");
- goto done;
- }
-
- printk(KERN_NOTICE "RAMDISK: Loading %d blocks [%d disk%s] into ram disk... ",
- nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
- for (i=0; i < nblocks; i++) {
- if (i && (i % devblocks == 0)) {
- printk("done disk #%d.\n", i/devblocks);
- rotate = 0;
- if (infile.f_op->release(inode, &infile) != 0) {
- printk("Error closing the disk.\n");
- goto noclose_input;
- }
- printk("Please insert disk #%d and press ENTER\n", i/devblocks+1);
- wait_for_keypress();
- if (blkdev_open(inode, &infile) != 0) {
- printk("Error opening disk.\n");
- goto noclose_input;
- }
- infile.f_pos = 0;
- printk("Loading disk #%d... ", i/devblocks+1);
- }
- infile.f_op->read(&infile, buf, BLOCK_SIZE, &infile.f_pos);
- outfile.f_op->write(&outfile, buf, BLOCK_SIZE, &outfile.f_pos);
-#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES) && !defined(CONFIG_XENO)
- if (!(i % 16)) {
- printk("%c\b", rotator[rotate & 0x3]);
- rotate++;
- }
-#endif
- }
- printk("done.\n");
- kfree(buf);
-
-successful_load:
- ROOT_DEV = MKDEV(MAJOR_NR, unit);
- if (ROOT_DEVICE_NAME != NULL) strcpy (ROOT_DEVICE_NAME, "rd/0");
-
-done:
- infile.f_op->release(inode, &infile);
-noclose_input:
- blkdev_close(out_inode, &outfile);
- iput(inode);
- iput(out_inode);
- set_fs(fs);
- return;
-free_inodes: /* free inodes on error */
- iput(out_inode);
- infile.f_op->release(inode, &infile);
-free_inode:
- iput(inode);
-}
-
-#ifdef CONFIG_MAC_FLOPPY
-int swim3_fd_eject(int devnum);
-#endif
-
-static void __init rd_load_disk(int n)
-{
-
- if (rd_doload == 0)
- return;
-
- if (MAJOR(ROOT_DEV) != FLOPPY_MAJOR
-#ifdef CONFIG_BLK_DEV_INITRD
- && MAJOR(real_root_dev) != FLOPPY_MAJOR
-#endif
- )
- return;
-
- if (rd_prompt) {
-#ifdef CONFIG_BLK_DEV_FD
- floppy_eject();
-#endif
-#ifdef CONFIG_MAC_FLOPPY
- if(MAJOR(ROOT_DEV) == FLOPPY_MAJOR)
- swim3_fd_eject(MINOR(ROOT_DEV));
- else if(MAJOR(real_root_dev) == FLOPPY_MAJOR)
- swim3_fd_eject(MINOR(real_root_dev));
-#endif
- printk(KERN_NOTICE
- "VFS: Insert root floppy disk to be loaded into RAM disk and press ENTER\n");
- wait_for_keypress();
- }
-
- rd_load_image(ROOT_DEV,rd_image_start, n);
-
-}
-
-void __init rd_load(void)
-{
- rd_load_disk(0);
-}
-
-void __init rd_load_secondary(void)
-{
- rd_load_disk(1);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init initrd_load(void)
-{
- rd_load_image(MKDEV(MAJOR_NR, INITRD_MINOR),rd_image_start,0);
-}
-#endif
-
-#endif /* RD_LOADER */
-
-#ifdef BUILD_CRAMDISK
-
-/*
- * gzip declarations
- */
-
-#define OF(args) args
-
-#ifndef memzero
-#define memzero(s, n) memset ((s), 0, (n))
-#endif
-
-typedef unsigned char uch;
-typedef unsigned short ush;
-typedef unsigned long ulg;
-
-#define INBUFSIZ 4096
-#define WSIZE 0x8000 /* window size--must be a power of two, and */
- /* at least 32K for zip's deflate method */
-
-static uch *inbuf;
-static uch *window;
-
-static unsigned insize; /* valid bytes in inbuf */
-static unsigned inptr; /* index of next byte to be processed in inbuf */
-static unsigned outcnt; /* bytes in output buffer */
-static int exit_code;
-static long bytes_out;
-static struct file *crd_infp, *crd_outfp;
-
-#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
-
-/* Diagnostic functions (stubbed out) */
-#define Assert(cond,msg)
-#define Trace(x)
-#define Tracev(x)
-#define Tracevv(x)
-#define Tracec(c,x)
-#define Tracecv(c,x)
-
-#define STATIC static
-
-static int fill_inbuf(void);
-static void flush_window(void);
-static void *malloc(int size);
-static void free(void *where);
-static void error(char *m);
-static void gzip_mark(void **);
-static void gzip_release(void **);
-
-#include "../../lib/inflate.c"
-
-static void __init *malloc(int size)
-{
- return kmalloc(size, GFP_KERNEL);
-}
-
-static void __init free(void *where)
-{
- kfree(where);
-}
-
-static void __init gzip_mark(void **ptr)
-{
-}
-
-static void __init gzip_release(void **ptr)
-{
-}
-
-
-/* ===========================================================================
- * Fill the input buffer. This is called only when the buffer is empty
- * and at least one byte is really needed.
- */
-static int __init fill_inbuf(void)
-{
- if (exit_code) return -1;
-
- insize = crd_infp->f_op->read(crd_infp, inbuf, INBUFSIZ,
- &crd_infp->f_pos);
- if (insize == 0) return -1;
-
- inptr = 1;
-
- return inbuf[0];
-}
-
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-static void __init flush_window(void)
-{
- ulg c = crc; /* temporary variable */
- unsigned n;
- uch *in, ch;
-
- crd_outfp->f_op->write(crd_outfp, window, outcnt, &crd_outfp->f_pos);
- in = window;
- for (n = 0; n < outcnt; n++) {
- ch = *in++;
- c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
- }
- crc = c;
- bytes_out += (ulg)outcnt;
- outcnt = 0;
-}
-
-static void __init error(char *x)
-{
- printk(KERN_ERR "%s", x);
- exit_code = 1;
-}
-
-static int __init
-crd_load(struct file * fp, struct file *outfp)
-{
- int result;
-
- insize = 0; /* valid bytes in inbuf */
- inptr = 0; /* index of next byte to be processed in inbuf */
- outcnt = 0; /* bytes in output buffer */
- exit_code = 0;
- bytes_out = 0;
- crc = (ulg)0xffffffffL; /* shift register contents */
-
- crd_infp = fp;
- crd_outfp = outfp;
- inbuf = kmalloc(INBUFSIZ, GFP_KERNEL);
- if (inbuf == 0) {
- printk(KERN_ERR "RAMDISK: Couldn't allocate gzip buffer\n");
- return -1;
- }
- window = kmalloc(WSIZE, GFP_KERNEL);
- if (window == 0) {
- printk(KERN_ERR "RAMDISK: Couldn't allocate gzip window\n");
- kfree(inbuf);
- return -1;
- }
- makecrc();
- result = gunzip();
- kfree(inbuf);
- kfree(window);
- return result;
-}
-
-#endif /* BUILD_CRAMDISK */
-
+++ /dev/null
-/*
- * linux/drivers/char/tty_io.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles
- * or rs-channels. It also implements echoing, cooked mode etc.
- *
- * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0.
- *
- * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the
- * tty_struct and tty_queue structures. Previously there was an array
- * of 256 tty_struct's which was statically allocated, and the
- * tty_queue structures were allocated at boot time. Both are now
- * dynamically allocated only when the tty is open.
- *
- * Also restructured routines so that there is more of a separation
- * between the high-level tty routines (tty_io.c and tty_ioctl.c) and
- * the low-level tty routines (serial.c, pty.c, console.c). This
- * makes for cleaner and more compact code. -TYT, 9/17/92
- *
- * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines
- * which can be dynamically activated and de-activated by the line
- * discipline handling modules (like SLIP).
- *
- * NOTE: pay no attention to the line discipline code (yet); its
- * interface is still subject to change in this version...
- * -- TYT, 1/31/92
- *
- * Added functionality to the OPOST tty handling. No delays, but all
- * other bits should be there.
- * -- Nick Holloway <alfie@dcs.warwick.ac.uk>, 27th May 1993.
- *
- * Rewrote canonical mode and added more termios flags.
- * -- julian@uhunix.uhcc.hawaii.edu (J. Cowley), 13Jan94
- *
- * Reorganized FASYNC support so mouse code can share it.
- * -- ctm@ardi.com, 9Sep95
- *
- * New TIOCLINUX variants added.
- * -- mj@k332.feld.cvut.cz, 19-Nov-95
- *
- * Restrict vt switching via ioctl()
- * -- grif@cs.ucr.edu, 5-Dec-95
- *
- * Move console and virtual terminal code to more appropriate files,
- * implement CONFIG_VT and generalize console device interface.
- * -- Marko Kohtala <Marko.Kohtala@hut.fi>, March 97
- *
- * Rewrote init_dev and release_dev to eliminate races.
- * -- Bill Hawes <whawes@star.net>, June 97
- *
- * Added devfs support.
- * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 13-Jan-1998
- *
- * Added support for a Unix98-style ptmx device.
- * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998
- *
- * Reduced memory usage for older ARM systems
- * -- Russell King <rmk@arm.linux.org.uk>
- *
- * Move do_SAK() into process context. Less stack use in devfs functions.
- * alloc_tty_struct() always uses kmalloc() -- Andrew Morton <andrewm@uow.edu.eu> 17Mar01
- */
-
-#include <linux/config.h>
-#include <linux/types.h>
-#include <linux/major.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/fcntl.h>
-#include <linux/sched.h>
-#include <linux/interrupt.h>
-#include <linux/tty.h>
-#include <linux/tty_driver.h>
-#include <linux/tty_flip.h>
-#include <linux/devpts_fs.h>
-#include <linux/file.h>
-#include <linux/console.h>
-#include <linux/timer.h>
-#include <linux/ctype.h>
-#include <linux/kd.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/poll.h>
-#include <linux/proc_fs.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/smp_lock.h>
-
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/bitops.h>
-
-#include <linux/kbd_kern.h>
-#include <linux/vt_kern.h>
-#include <linux/selection.h>
-#include <linux/devfs_fs_kernel.h>
-
-#include <linux/kmod.h>
-
-#ifdef CONFIG_XENO
-extern void xeno_console_init(void);
-#endif
-
-#ifdef CONFIG_VT
-extern void con_init_devfs (void);
-#endif
-
-#define CONSOLE_DEV MKDEV(TTY_MAJOR,0)
-#define TTY_DEV MKDEV(TTYAUX_MAJOR,0)
-#define SYSCONS_DEV MKDEV(TTYAUX_MAJOR,1)
-#define PTMX_DEV MKDEV(TTYAUX_MAJOR,2)
-
-#undef TTY_DEBUG_HANGUP
-
-#define TTY_PARANOIA_CHECK 1
-#define CHECK_TTY_COUNT 1
-
-struct termios tty_std_termios; /* for the benefit of tty drivers */
-struct tty_driver *tty_drivers; /* linked list of tty drivers */
-struct tty_ldisc ldiscs[NR_LDISCS]; /* line disc dispatch table */
-
-#ifdef CONFIG_UNIX98_PTYS
-extern struct tty_driver ptm_driver[]; /* Unix98 pty masters; for /dev/ptmx */
-extern struct tty_driver pts_driver[]; /* Unix98 pty slaves; for /dev/ptmx */
-#endif
-
-/*
- * redirect is the pseudo-tty that console output
- * is redirected to if asked by TIOCCONS.
- */
-struct tty_struct * redirect;
-
-static void initialize_tty_struct(struct tty_struct *tty);
-
-static ssize_t tty_read(struct file *, char *, size_t, loff_t *);
-static ssize_t tty_write(struct file *, const char *, size_t, loff_t *);
-static unsigned int tty_poll(struct file *, poll_table *);
-static int tty_open(struct inode *, struct file *);
-static int tty_release(struct inode *, struct file *);
-int tty_ioctl(struct inode * inode, struct file * file,
- unsigned int cmd, unsigned long arg);
-static int tty_fasync(int fd, struct file * filp, int on);
-extern int vme_scc_init (void);
-extern long vme_scc_console_init(void);
-extern int serial167_init(void);
-extern long serial167_console_init(void);
-extern void console_8xx_init(void);
-extern int rs_8xx_init(void);
-extern void mac_scc_console_init(void);
-extern void hwc_console_init(void);
-extern void hwc_tty_init(void);
-extern void con3215_init(void);
-extern void tty3215_init(void);
-extern void tub3270_con_init(void);
-extern void tub3270_init(void);
-extern void rs285_console_init(void);
-extern void sa1100_rs_console_init(void);
-extern void sgi_serial_console_init(void);
-extern void sci_console_init(void);
-extern void tx3912_console_init(void);
-extern void tx3912_rs_init(void);
-
-#ifndef MIN
-#define MIN(a,b) ((a) < (b) ? (a) : (b))
-#endif
-#ifndef MAX
-#define MAX(a,b) ((a) < (b) ? (b) : (a))
-#endif
-
-static struct tty_struct *alloc_tty_struct(void)
-{
- struct tty_struct *tty;
-
- tty = kmalloc(sizeof(struct tty_struct), GFP_KERNEL);
- if (tty)
- memset(tty, 0, sizeof(struct tty_struct));
- return tty;
-}
-
-static inline void free_tty_struct(struct tty_struct *tty)
-{
- kfree(tty);
-}
-
-/*
- * This routine returns the name of tty.
- */
-static char *
-_tty_make_name(struct tty_struct *tty, const char *name, char *buf)
-{
- int idx = (tty)?MINOR(tty->device) - tty->driver.minor_start:0;
-
- if (!tty) /* Hmm. NULL pointer. That's fun. */
- strcpy(buf, "NULL tty");
- else
- sprintf(buf, name,
- idx + tty->driver.name_base);
-
- return buf;
-}
-
-#define TTY_NUMBER(tty) (MINOR((tty)->device) - (tty)->driver.minor_start + \
- (tty)->driver.name_base)
-
-char *tty_name(struct tty_struct *tty, char *buf)
-{
- return _tty_make_name(tty, (tty)?tty->driver.name:NULL, buf);
-}
-
-inline int tty_paranoia_check(struct tty_struct *tty, kdev_t device,
- const char *routine)
-{
-#ifdef TTY_PARANOIA_CHECK
- static const char badmagic[] = KERN_WARNING
- "Warning: bad magic number for tty struct (%s) in %s\n";
- static const char badtty[] = KERN_WARNING
- "Warning: null TTY for (%s) in %s\n";
-
- if (!tty) {
- printk(badtty, kdevname(device), routine);
- return 1;
- }
- if (tty->magic != TTY_MAGIC) {
- printk(badmagic, kdevname(device), routine);
- return 1;
- }
-#endif
- return 0;
-}
-
-static int check_tty_count(struct tty_struct *tty, const char *routine)
-{
-#ifdef CHECK_TTY_COUNT
- struct list_head *p;
- int count = 0;
-
- file_list_lock();
- for(p = tty->tty_files.next; p != &tty->tty_files; p = p->next) {
- if(list_entry(p, struct file, f_list)->private_data == tty)
- count++;
- }
- file_list_unlock();
- if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
- tty->driver.subtype == PTY_TYPE_SLAVE &&
- tty->link && tty->link->count)
- count++;
- if (tty->count != count) {
- printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) "
- "!= #fd's(%d) in %s\n",
- kdevname(tty->device), tty->count, count, routine);
- return count;
- }
-#endif
- return 0;
-}
-
-int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc)
-{
- if (disc < N_TTY || disc >= NR_LDISCS)
- return -EINVAL;
-
- if (new_ldisc) {
- ldiscs[disc] = *new_ldisc;
- ldiscs[disc].flags |= LDISC_FLAG_DEFINED;
- ldiscs[disc].num = disc;
- } else
- memset(&ldiscs[disc], 0, sizeof(struct tty_ldisc));
-
- return 0;
-}
-
-EXPORT_SYMBOL(tty_register_ldisc);
-
-/* Set the discipline of a tty line. */
-static int tty_set_ldisc(struct tty_struct *tty, int ldisc)
-{
- int retval = 0;
- struct tty_ldisc o_ldisc;
- char buf[64];
-
- if ((ldisc < N_TTY) || (ldisc >= NR_LDISCS))
- return -EINVAL;
- /* Eduardo Blanco <ejbs@cs.cs.com.uy> */
- /* Cyrus Durgin <cider@speakeasy.org> */
- if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED)) {
- char modname [20];
- sprintf(modname, "tty-ldisc-%d", ldisc);
- request_module (modname);
- }
- if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED))
- return -EINVAL;
-
- if (tty->ldisc.num == ldisc)
- return 0; /* We are already in the desired discipline */
- o_ldisc = tty->ldisc;
-
- tty_wait_until_sent(tty, 0);
-
- /* Shutdown the current discipline. */
- if (tty->ldisc.close)
- (tty->ldisc.close)(tty);
-
- /* Now set up the new line discipline. */
- tty->ldisc = ldiscs[ldisc];
- tty->termios->c_line = ldisc;
- if (tty->ldisc.open)
- retval = (tty->ldisc.open)(tty);
- if (retval < 0) {
- tty->ldisc = o_ldisc;
- tty->termios->c_line = tty->ldisc.num;
- if (tty->ldisc.open && (tty->ldisc.open(tty) < 0)) {
- tty->ldisc = ldiscs[N_TTY];
- tty->termios->c_line = N_TTY;
- if (tty->ldisc.open) {
- int r = tty->ldisc.open(tty);
-
- if (r < 0)
- panic("Couldn't open N_TTY ldisc for "
- "%s --- error %d.",
- tty_name(tty, buf), r);
- }
- }
- }
- if (tty->ldisc.num != o_ldisc.num && tty->driver.set_ldisc)
- tty->driver.set_ldisc(tty);
- return retval;
-}
-
-/*
- * This routine returns a tty driver structure, given a device number
- */
-struct tty_driver *get_tty_driver(kdev_t device)
-{
- int major, minor;
- struct tty_driver *p;
-
- minor = MINOR(device);
- major = MAJOR(device);
-
- for (p = tty_drivers; p; p = p->next) {
- if (p->major != major)
- continue;
- if (minor < p->minor_start)
- continue;
- if (minor >= p->minor_start + p->num)
- continue;
- return p;
- }
- return NULL;
-}
-
-/*
- * If we try to write to, or set the state of, a terminal and we're
- * not in the foreground, send a SIGTTOU. If the signal is blocked or
- * ignored, go ahead and perform the operation. (POSIX 7.2)
- */
-int tty_check_change(struct tty_struct * tty)
-{
- if (current->tty != tty)
- return 0;
- if (tty->pgrp <= 0) {
- printk(KERN_WARNING "tty_check_change: tty->pgrp <= 0!\n");
- return 0;
- }
- if (current->pgrp == tty->pgrp)
- return 0;
- if (is_ignored(SIGTTOU))
- return 0;
- if (is_orphaned_pgrp(current->pgrp))
- return -EIO;
- (void) kill_pg(current->pgrp,SIGTTOU,1);
- return -ERESTARTSYS;
-}
-
-static ssize_t hung_up_tty_read(struct file * file, char * buf,
- size_t count, loff_t *ppos)
-{
- /* Can't seek (pread) on ttys. */
- if (ppos != &file->f_pos)
- return -ESPIPE;
- return 0;
-}
-
-static ssize_t hung_up_tty_write(struct file * file, const char * buf,
- size_t count, loff_t *ppos)
-{
- /* Can't seek (pwrite) on ttys. */
- if (ppos != &file->f_pos)
- return -ESPIPE;
- return -EIO;
-}
-
-/* No kernel lock held - none needed ;) */
-static unsigned int hung_up_tty_poll(struct file * filp, poll_table * wait)
-{
- return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM;
-}
-
-static int hung_up_tty_ioctl(struct inode * inode, struct file * file,
- unsigned int cmd, unsigned long arg)
-{
- return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
-}
-
-static struct file_operations tty_fops = {
- llseek: no_llseek,
- read: tty_read,
- write: tty_write,
- poll: tty_poll,
- ioctl: tty_ioctl,
- open: tty_open,
- release: tty_release,
- fasync: tty_fasync,
-};
-
-static struct file_operations hung_up_tty_fops = {
- llseek: no_llseek,
- read: hung_up_tty_read,
- write: hung_up_tty_write,
- poll: hung_up_tty_poll,
- ioctl: hung_up_tty_ioctl,
- release: tty_release,
-};
-
-/*
- * This can be called by the "eventd" kernel thread. That is process synchronous,
- * but doesn't hold any locks, so we need to make sure we have the appropriate
- * locks for what we're doing..
- */
-void do_tty_hangup(void *data)
-{
- struct tty_struct *tty = (struct tty_struct *) data;
- struct file * cons_filp = NULL;
- struct task_struct *p;
- struct list_head *l;
- int closecount = 0, n;
-
- if (!tty)
- return;
-
- /* inuse_filps is protected by the single kernel lock */
- lock_kernel();
-
- check_tty_count(tty, "do_tty_hangup");
- file_list_lock();
- for (l = tty->tty_files.next; l != &tty->tty_files; l = l->next) {
- struct file * filp = list_entry(l, struct file, f_list);
- if (filp->f_dentry->d_inode->i_rdev == CONSOLE_DEV ||
- filp->f_dentry->d_inode->i_rdev == SYSCONS_DEV) {
- cons_filp = filp;
- continue;
- }
- if (filp->f_op != &tty_fops)
- continue;
- closecount++;
- tty_fasync(-1, filp, 0); /* can't block */
- filp->f_op = &hung_up_tty_fops;
- }
- file_list_unlock();
-
- /* FIXME! What are the locking issues here? This may me overdoing things.. */
- {
- unsigned long flags;
-
- save_flags(flags); cli();
- if (tty->ldisc.flush_buffer)
- tty->ldisc.flush_buffer(tty);
- if (tty->driver.flush_buffer)
- tty->driver.flush_buffer(tty);
- if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
- tty->ldisc.write_wakeup)
- (tty->ldisc.write_wakeup)(tty);
- restore_flags(flags);
- }
-
- wake_up_interruptible(&tty->write_wait);
- wake_up_interruptible(&tty->read_wait);
-
- /*
- * Shutdown the current line discipline, and reset it to
- * N_TTY.
- */
- if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS)
- *tty->termios = tty->driver.init_termios;
- if (tty->ldisc.num != ldiscs[N_TTY].num) {
- if (tty->ldisc.close)
- (tty->ldisc.close)(tty);
- tty->ldisc = ldiscs[N_TTY];
- tty->termios->c_line = N_TTY;
- if (tty->ldisc.open) {
- int i = (tty->ldisc.open)(tty);
- if (i < 0)
- printk(KERN_ERR "do_tty_hangup: N_TTY open: "
- "error %d\n", -i);
- }
- }
-
- read_lock(&tasklist_lock);
- for_each_task(p) {
- if ((tty->session > 0) && (p->session == tty->session) &&
- p->leader) {
- send_sig(SIGHUP,p,1);
- send_sig(SIGCONT,p,1);
- if (tty->pgrp > 0)
- p->tty_old_pgrp = tty->pgrp;
- }
- if (p->tty == tty)
- p->tty = NULL;
- }
- read_unlock(&tasklist_lock);
-
- tty->flags = 0;
- tty->session = 0;
- tty->pgrp = -1;
- tty->ctrl_status = 0;
- /*
- * If one of the devices matches a console pointer, we
- * cannot just call hangup() because that will cause
- * tty->count and state->count to go out of sync.
- * So we just call close() the right number of times.
- */
- if (cons_filp) {
- if (tty->driver.close)
- for (n = 0; n < closecount; n++)
- tty->driver.close(tty, cons_filp);
- } else if (tty->driver.hangup)
- (tty->driver.hangup)(tty);
- unlock_kernel();
-}
-
-void tty_hangup(struct tty_struct * tty)
-{
-#ifdef TTY_DEBUG_HANGUP
- char buf[64];
-
- printk(KERN_DEBUG "%s hangup...\n", tty_name(tty, buf));
-#endif
- schedule_task(&tty->tq_hangup);
-}
-
-void tty_vhangup(struct tty_struct * tty)
-{
-#ifdef TTY_DEBUG_HANGUP
- char buf[64];
-
- printk(KERN_DEBUG "%s vhangup...\n", tty_name(tty, buf));
-#endif
- do_tty_hangup((void *) tty);
-}
-
-int tty_hung_up_p(struct file * filp)
-{
- return (filp->f_op == &hung_up_tty_fops);
-}
-
-/*
- * This function is typically called only by the session leader, when
- * it wants to disassociate itself from its controlling tty.
- *
- * It performs the following functions:
- * (1) Sends a SIGHUP and SIGCONT to the foreground process group
- * (2) Clears the tty from being controlling the session
- * (3) Clears the controlling tty for all processes in the
- * session group.
- *
- * The argument on_exit is set to 1 if called when a process is
- * exiting; it is 0 if called by the ioctl TIOCNOTTY.
- */
-void disassociate_ctty(int on_exit)
-{
- struct tty_struct *tty = current->tty;
- struct task_struct *p;
- int tty_pgrp = -1;
-
- if (tty) {
- tty_pgrp = tty->pgrp;
- if (on_exit && tty->driver.type != TTY_DRIVER_TYPE_PTY)
- tty_vhangup(tty);
- } else {
- if (current->tty_old_pgrp) {
- kill_pg(current->tty_old_pgrp, SIGHUP, on_exit);
- kill_pg(current->tty_old_pgrp, SIGCONT, on_exit);
- }
- return;
- }
- if (tty_pgrp > 0) {
- kill_pg(tty_pgrp, SIGHUP, on_exit);
- if (!on_exit)
- kill_pg(tty_pgrp, SIGCONT, on_exit);
- }
-
- current->tty_old_pgrp = 0;
- tty->session = 0;
- tty->pgrp = -1;
-
- read_lock(&tasklist_lock);
- for_each_task(p)
- if (p->session == current->session)
- p->tty = NULL;
- read_unlock(&tasklist_lock);
-}
-
-void wait_for_keypress(void)
-{
- struct console *c = console_drivers;
- if (c) c->wait_key(c);
-}
-
-void stop_tty(struct tty_struct *tty)
-{
- if (tty->stopped)
- return;
- tty->stopped = 1;
- if (tty->link && tty->link->packet) {
- tty->ctrl_status &= ~TIOCPKT_START;
- tty->ctrl_status |= TIOCPKT_STOP;
- wake_up_interruptible(&tty->link->read_wait);
- }
- if (tty->driver.stop)
- (tty->driver.stop)(tty);
-}
-
-void start_tty(struct tty_struct *tty)
-{
- if (!tty->stopped || tty->flow_stopped)
- return;
- tty->stopped = 0;
- if (tty->link && tty->link->packet) {
- tty->ctrl_status &= ~TIOCPKT_STOP;
- tty->ctrl_status |= TIOCPKT_START;
- wake_up_interruptible(&tty->link->read_wait);
- }
- if (tty->driver.start)
- (tty->driver.start)(tty);
- if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
- tty->ldisc.write_wakeup)
- (tty->ldisc.write_wakeup)(tty);
- wake_up_interruptible(&tty->write_wait);
-}
-
-static ssize_t tty_read(struct file * file, char * buf, size_t count,
- loff_t *ppos)
-{
- int i;
- struct tty_struct * tty;
- struct inode *inode;
-
- /* Can't seek (pread) on ttys. */
- if (ppos != &file->f_pos)
- return -ESPIPE;
-
- tty = (struct tty_struct *)file->private_data;
- inode = file->f_dentry->d_inode;
- if (tty_paranoia_check(tty, inode->i_rdev, "tty_read"))
- return -EIO;
- if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
- return -EIO;
-
- /* This check not only needs to be done before reading, but also
- whenever read_chan() gets woken up after sleeping, so I've
- moved it to there. This should only be done for the N_TTY
- line discipline, anyway. Same goes for write_chan(). -- jlc. */
-#if 0
- if ((inode->i_rdev != CONSOLE_DEV) && /* don't stop on /dev/console */
- (tty->pgrp > 0) &&
- (current->tty == tty) &&
- (tty->pgrp != current->pgrp))
- if (is_ignored(SIGTTIN) || is_orphaned_pgrp(current->pgrp))
- return -EIO;
- else {
- (void) kill_pg(current->pgrp, SIGTTIN, 1);
- return -ERESTARTSYS;
- }
-#endif
- lock_kernel();
- if (tty->ldisc.read)
- i = (tty->ldisc.read)(tty,file,buf,count);
- else
- i = -EIO;
- unlock_kernel();
- if (i > 0)
- inode->i_atime = CURRENT_TIME;
- return i;
-}
-
-/*
- * Split writes up in sane blocksizes to avoid
- * denial-of-service type attacks
- */
-static inline ssize_t do_tty_write(
- ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t),
- struct tty_struct *tty,
- struct file *file,
- const unsigned char *buf,
- size_t count)
-{
- ssize_t ret = 0, written = 0;
-
- if (down_interruptible(&tty->atomic_write)) {
- return -ERESTARTSYS;
- }
- if ( test_bit(TTY_NO_WRITE_SPLIT, &tty->flags) ) {
- lock_kernel();
- written = write(tty, file, buf, count);
- unlock_kernel();
- } else {
- for (;;) {
- unsigned long size = MAX(PAGE_SIZE*2,16384);
- if (size > count)
- size = count;
- lock_kernel();
- ret = write(tty, file, buf, size);
- unlock_kernel();
- if (ret <= 0)
- break;
- written += ret;
- buf += ret;
- count -= ret;
- if (!count)
- break;
- ret = -ERESTARTSYS;
- if (signal_pending(current))
- break;
- if (current->need_resched)
- schedule();
- }
- }
- if (written) {
- file->f_dentry->d_inode->i_mtime = CURRENT_TIME;
- ret = written;
- }
- up(&tty->atomic_write);
- return ret;
-}
-
-
-static ssize_t tty_write(struct file * file, const char * buf, size_t count,
- loff_t *ppos)
-{
- int is_console;
- struct tty_struct * tty;
- struct inode *inode;
-
- /* Can't seek (pwrite) on ttys. */
- if (ppos != &file->f_pos)
- return -ESPIPE;
-
- /*
- * For now, we redirect writes from /dev/console as
- * well as /dev/tty0.
- */
- inode = file->f_dentry->d_inode;
- is_console = (inode->i_rdev == SYSCONS_DEV ||
- inode->i_rdev == CONSOLE_DEV);
-
- if (is_console && redirect)
- tty = redirect;
- else
- tty = (struct tty_struct *)file->private_data;
- if (tty_paranoia_check(tty, inode->i_rdev, "tty_write"))
- return -EIO;
- if (!tty || !tty->driver.write || (test_bit(TTY_IO_ERROR, &tty->flags)))
- return -EIO;
-#if 0
- if (!is_console && L_TOSTOP(tty) && (tty->pgrp > 0) &&
- (current->tty == tty) && (tty->pgrp != current->pgrp)) {
- if (is_orphaned_pgrp(current->pgrp))
- return -EIO;
- if (!is_ignored(SIGTTOU)) {
- (void) kill_pg(current->pgrp, SIGTTOU, 1);
- return -ERESTARTSYS;
- }
- }
-#endif
- if (!tty->ldisc.write)
- return -EIO;
- return do_tty_write(tty->ldisc.write, tty, file,
- (const unsigned char *)buf, count);
-}
-
-/* Semaphore to protect creating and releasing a tty */
-static DECLARE_MUTEX(tty_sem);
-
-static void down_tty_sem(int index)
-{
- down(&tty_sem);
-}
-
-static void up_tty_sem(int index)
-{
- up(&tty_sem);
-}
-
-static void release_mem(struct tty_struct *tty, int idx);
-
-/*
- * WSH 06/09/97: Rewritten to remove races and properly clean up after a
- * failed open. The new code protects the open with a semaphore, so it's
- * really quite straightforward. The semaphore locking can probably be
- * relaxed for the (most common) case of reopening a tty.
- */
-static int init_dev(kdev_t device, struct tty_struct **ret_tty)
-{
- struct tty_struct *tty, *o_tty;
- struct termios *tp, **tp_loc, *o_tp, **o_tp_loc;
- struct termios *ltp, **ltp_loc, *o_ltp, **o_ltp_loc;
- struct tty_driver *driver;
- int retval=0;
- int idx;
-
- driver = get_tty_driver(device);
- if (!driver)
- return -ENODEV;
-
- idx = MINOR(device) - driver->minor_start;
-
- /*
- * Check whether we need to acquire the tty semaphore to avoid
- * race conditions. For now, play it safe.
- */
- down_tty_sem(idx);
-
- /* check whether we're reopening an existing tty */
- tty = driver->table[idx];
- if (tty) goto fast_track;
-
- /*
- * First time open is complex, especially for PTY devices.
- * This code guarantees that either everything succeeds and the
- * TTY is ready for operation, or else the table slots are vacated
- * and the allocated memory released. (Except that the termios
- * and locked termios may be retained.)
- */
-
- o_tty = NULL;
- tp = o_tp = NULL;
- ltp = o_ltp = NULL;
-
- tty = alloc_tty_struct();
- if(!tty)
- goto fail_no_mem;
- initialize_tty_struct(tty);
- tty->device = device;
- tty->driver = *driver;
-
- tp_loc = &driver->termios[idx];
- if (!*tp_loc) {
- tp = (struct termios *) kmalloc(sizeof(struct termios),
- GFP_KERNEL);
- if (!tp)
- goto free_mem_out;
- *tp = driver->init_termios;
- }
-
- ltp_loc = &driver->termios_locked[idx];
- if (!*ltp_loc) {
- ltp = (struct termios *) kmalloc(sizeof(struct termios),
- GFP_KERNEL);
- if (!ltp)
- goto free_mem_out;
- memset(ltp, 0, sizeof(struct termios));
- }
-
- if (driver->type == TTY_DRIVER_TYPE_PTY) {
- o_tty = alloc_tty_struct();
- if (!o_tty)
- goto free_mem_out;
- initialize_tty_struct(o_tty);
- o_tty->device = (kdev_t) MKDEV(driver->other->major,
- driver->other->minor_start + idx);
- o_tty->driver = *driver->other;
-
- o_tp_loc = &driver->other->termios[idx];
- if (!*o_tp_loc) {
- o_tp = (struct termios *)
- kmalloc(sizeof(struct termios), GFP_KERNEL);
- if (!o_tp)
- goto free_mem_out;
- *o_tp = driver->other->init_termios;
- }
-
- o_ltp_loc = &driver->other->termios_locked[idx];
- if (!*o_ltp_loc) {
- o_ltp = (struct termios *)
- kmalloc(sizeof(struct termios), GFP_KERNEL);
- if (!o_ltp)
- goto free_mem_out;
- memset(o_ltp, 0, sizeof(struct termios));
- }
-
- /*
- * Everything allocated ... set up the o_tty structure.
- */
- driver->other->table[idx] = o_tty;
- if (!*o_tp_loc)
- *o_tp_loc = o_tp;
- if (!*o_ltp_loc)
- *o_ltp_loc = o_ltp;
- o_tty->termios = *o_tp_loc;
- o_tty->termios_locked = *o_ltp_loc;
- (*driver->other->refcount)++;
- if (driver->subtype == PTY_TYPE_MASTER)
- o_tty->count++;
-
- /* Establish the links in both directions */
- tty->link = o_tty;
- o_tty->link = tty;
- }
-
- /*
- * All structures have been allocated, so now we install them.
- * Failures after this point use release_mem to clean up, so
- * there's no need to null out the local pointers.
- */
- driver->table[idx] = tty;
-
- if (!*tp_loc)
- *tp_loc = tp;
- if (!*ltp_loc)
- *ltp_loc = ltp;
- tty->termios = *tp_loc;
- tty->termios_locked = *ltp_loc;
- (*driver->refcount)++;
- tty->count++;
-
- /*
- * Structures all installed ... call the ldisc open routines.
- * If we fail here just call release_mem to clean up. No need
- * to decrement the use counts, as release_mem doesn't care.
- */
- if (tty->ldisc.open) {
- retval = (tty->ldisc.open)(tty);
- if (retval)
- goto release_mem_out;
- }
- if (o_tty && o_tty->ldisc.open) {
- retval = (o_tty->ldisc.open)(o_tty);
- if (retval) {
- if (tty->ldisc.close)
- (tty->ldisc.close)(tty);
- goto release_mem_out;
- }
- }
- goto success;
-
- /*
- * This fast open can be used if the tty is already open.
- * No memory is allocated, and the only failures are from
- * attempting to open a closing tty or attempting multiple
- * opens on a pty master.
- */
-fast_track:
- if (test_bit(TTY_CLOSING, &tty->flags)) {
- retval = -EIO;
- goto end_init;
- }
- if (driver->type == TTY_DRIVER_TYPE_PTY &&
- driver->subtype == PTY_TYPE_MASTER) {
- /*
- * special case for PTY masters: only one open permitted,
- * and the slave side open count is incremented as well.
- */
- if (tty->count) {
- retval = -EIO;
- goto end_init;
- }
- tty->link->count++;
- }
- tty->count++;
- tty->driver = *driver; /* N.B. why do this every time?? */
-
-success:
- *ret_tty = tty;
-
- /* All paths come through here to release the semaphore */
-end_init:
- up_tty_sem(idx);
- return retval;
-
- /* Release locally allocated memory ... nothing placed in slots */
-free_mem_out:
- if (o_tp)
- kfree(o_tp);
- if (o_tty)
- free_tty_struct(o_tty);
- if (ltp)
- kfree(ltp);
- if (tp)
- kfree(tp);
- free_tty_struct(tty);
-
-fail_no_mem:
- retval = -ENOMEM;
- goto end_init;
-
- /* call the tty release_mem routine to clean out this slot */
-release_mem_out:
- printk(KERN_INFO "init_dev: ldisc open failed, "
- "clearing slot %d\n", idx);
- release_mem(tty, idx);
- goto end_init;
-}
-
-/*
- * Releases memory associated with a tty structure, and clears out the
- * driver table slots.
- */
-static void release_mem(struct tty_struct *tty, int idx)
-{
- struct tty_struct *o_tty;
- struct termios *tp;
-
- if ((o_tty = tty->link) != NULL) {
- o_tty->driver.table[idx] = NULL;
- if (o_tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
- tp = o_tty->driver.termios[idx];
- o_tty->driver.termios[idx] = NULL;
- kfree(tp);
- }
- o_tty->magic = 0;
- (*o_tty->driver.refcount)--;
- list_del(&o_tty->tty_files);
- free_tty_struct(o_tty);
- }
-
- tty->driver.table[idx] = NULL;
- if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
- tp = tty->driver.termios[idx];
- tty->driver.termios[idx] = NULL;
- kfree(tp);
- }
- tty->magic = 0;
- (*tty->driver.refcount)--;
- list_del(&tty->tty_files);
- free_tty_struct(tty);
-}
-
-/*
- * Even releasing the tty structures is a tricky business.. We have
- * to be very careful that the structures are all released at the
- * same time, as interrupts might otherwise get the wrong pointers.
- *
- * WSH 09/09/97: rewritten to avoid some nasty race conditions that could
- * lead to double frees or releasing memory still in use.
- */
-static void release_dev(struct file * filp)
-{
- struct tty_struct *tty, *o_tty;
- int pty_master, tty_closing, o_tty_closing, do_sleep;
- int idx;
- char buf[64];
-
- tty = (struct tty_struct *)filp->private_data;
- if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "release_dev"))
- return;
-
- check_tty_count(tty, "release_dev");
-
- tty_fasync(-1, filp, 0);
-
- idx = MINOR(tty->device) - tty->driver.minor_start;
- pty_master = (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
- tty->driver.subtype == PTY_TYPE_MASTER);
- o_tty = tty->link;
-
-#ifdef TTY_PARANOIA_CHECK
- if (idx < 0 || idx >= tty->driver.num) {
- printk(KERN_DEBUG "release_dev: bad idx when trying to "
- "free (%s)\n", kdevname(tty->device));
- return;
- }
- if (tty != tty->driver.table[idx]) {
- printk(KERN_DEBUG "release_dev: driver.table[%d] not tty "
- "for (%s)\n", idx, kdevname(tty->device));
- return;
- }
- if (tty->termios != tty->driver.termios[idx]) {
- printk(KERN_DEBUG "release_dev: driver.termios[%d] not termios "
- "for (%s)\n",
- idx, kdevname(tty->device));
- return;
- }
- if (tty->termios_locked != tty->driver.termios_locked[idx]) {
- printk(KERN_DEBUG "release_dev: driver.termios_locked[%d] not "
- "termios_locked for (%s)\n",
- idx, kdevname(tty->device));
- return;
- }
-#endif
-
-#ifdef TTY_DEBUG_HANGUP
- printk(KERN_DEBUG "release_dev of %s (tty count=%d)...",
- tty_name(tty, buf), tty->count);
-#endif
-
-#ifdef TTY_PARANOIA_CHECK
- if (tty->driver.other) {
- if (o_tty != tty->driver.other->table[idx]) {
- printk(KERN_DEBUG "release_dev: other->table[%d] "
- "not o_tty for (%s)\n",
- idx, kdevname(tty->device));
- return;
- }
- if (o_tty->termios != tty->driver.other->termios[idx]) {
- printk(KERN_DEBUG "release_dev: other->termios[%d] "
- "not o_termios for (%s)\n",
- idx, kdevname(tty->device));
- return;
- }
- if (o_tty->termios_locked !=
- tty->driver.other->termios_locked[idx]) {
- printk(KERN_DEBUG "release_dev: other->termios_locked["
- "%d] not o_termios_locked for (%s)\n",
- idx, kdevname(tty->device));
- return;
- }
- if (o_tty->link != tty) {
- printk(KERN_DEBUG "release_dev: bad pty pointers\n");
- return;
- }
- }
-#endif
-
- if (tty->driver.close)
- tty->driver.close(tty, filp);
-
- /*
- * Sanity check: if tty->count is going to zero, there shouldn't be
- * any waiters on tty->read_wait or tty->write_wait. We test the
- * wait queues and kick everyone out _before_ actually starting to
- * close. This ensures that we won't block while releasing the tty
- * structure.
- *
- * The test for the o_tty closing is necessary, since the master and
- * slave sides may close in any order. If the slave side closes out
- * first, its count will be one, since the master side holds an open.
- * Thus this test wouldn't be triggered at the time the slave closes,
- * so we do it now.
- *
- * Note that it's possible for the tty to be opened again while we're
- * flushing out waiters. By recalculating the closing flags before
- * each iteration we avoid any problems.
- */
- while (1) {
- tty_closing = tty->count <= 1;
- o_tty_closing = o_tty &&
- (o_tty->count <= (pty_master ? 1 : 0));
- do_sleep = 0;
-
- if (tty_closing) {
- if (waitqueue_active(&tty->read_wait)) {
- wake_up(&tty->read_wait);
- do_sleep++;
- }
- if (waitqueue_active(&tty->write_wait)) {
- wake_up(&tty->write_wait);
- do_sleep++;
- }
- }
- if (o_tty_closing) {
- if (waitqueue_active(&o_tty->read_wait)) {
- wake_up(&o_tty->read_wait);
- do_sleep++;
- }
- if (waitqueue_active(&o_tty->write_wait)) {
- wake_up(&o_tty->write_wait);
- do_sleep++;
- }
- }
- if (!do_sleep)
- break;
-
- printk(KERN_WARNING "release_dev: %s: read/write wait queue "
- "active!\n", tty_name(tty, buf));
- schedule();
- }
-
- /*
- * The closing flags are now consistent with the open counts on
- * both sides, and we've completed the last operation that could
- * block, so it's safe to proceed with closing.
- */
- if (pty_master) {
- if (--o_tty->count < 0) {
- printk(KERN_WARNING "release_dev: bad pty slave count "
- "(%d) for %s\n",
- o_tty->count, tty_name(o_tty, buf));
- o_tty->count = 0;
- }
- }
- if (--tty->count < 0) {
- printk(KERN_WARNING "release_dev: bad tty->count (%d) for %s\n",
- tty->count, tty_name(tty, buf));
- tty->count = 0;
- }
-
- /*
- * We've decremented tty->count, so we should zero out
- * filp->private_data, to break the link between the tty and
- * the file descriptor. Otherwise if filp_close() blocks before
- * the file descriptor is removed from the inuse_filp
- * list, check_tty_count() could observe a discrepancy and
- * printk a warning message to the user.
- */
- filp->private_data = 0;
-
- /*
- * Perform some housekeeping before deciding whether to return.
- *
- * Set the TTY_CLOSING flag if this was the last open. In the
- * case of a pty we may have to wait around for the other side
- * to close, and TTY_CLOSING makes sure we can't be reopened.
- */
- if(tty_closing)
- set_bit(TTY_CLOSING, &tty->flags);
- if(o_tty_closing)
- set_bit(TTY_CLOSING, &o_tty->flags);
-
- /*
- * If _either_ side is closing, make sure there aren't any
- * processes that still think tty or o_tty is their controlling
- * tty. Also, clear redirect if it points to either tty.
- */
- if (tty_closing || o_tty_closing) {
- struct task_struct *p;
-
- read_lock(&tasklist_lock);
- for_each_task(p) {
- if (p->tty == tty || (o_tty && p->tty == o_tty))
- p->tty = NULL;
- }
- read_unlock(&tasklist_lock);
-
- if (redirect == tty || (o_tty && redirect == o_tty))
- redirect = NULL;
- }
-
- /* check whether both sides are closing ... */
- if (!tty_closing || (o_tty && !o_tty_closing))
- return;
-
-#ifdef TTY_DEBUG_HANGUP
- printk(KERN_DEBUG "freeing tty structure...");
-#endif
-
- /*
- * Shutdown the current line discipline, and reset it to N_TTY.
- * N.B. why reset ldisc when we're releasing the memory??
- */
- if (tty->ldisc.close)
- (tty->ldisc.close)(tty);
- tty->ldisc = ldiscs[N_TTY];
- tty->termios->c_line = N_TTY;
- if (o_tty) {
- if (o_tty->ldisc.close)
- (o_tty->ldisc.close)(o_tty);
- o_tty->ldisc = ldiscs[N_TTY];
- }
-
- /*
- * Make sure that the tty's task queue isn't activated.
- */
- run_task_queue(&tq_timer);
- flush_scheduled_tasks();
-
- /*
- * The release_mem function takes care of the details of clearing
- * the slots and preserving the termios structure.
- */
- release_mem(tty, idx);
-}
-
-/*
- * tty_open and tty_release keep up the tty count that contains the
- * number of opens done on a tty. We cannot use the inode-count, as
- * different inodes might point to the same tty.
- *
- * Open-counting is needed for pty masters, as well as for keeping
- * track of serial lines: DTR is dropped when the last close happens.
- * (This is not done solely through tty->count, now. - Ted 1/27/92)
- *
- * The termios state of a pty is reset on first open so that
- * settings don't persist across reuse.
- */
-static int tty_open(struct inode * inode, struct file * filp)
-{
- struct tty_struct *tty;
- int noctty, retval;
- kdev_t device;
- unsigned short saved_flags;
- char buf[64];
-
- saved_flags = filp->f_flags;
-retry_open:
- noctty = filp->f_flags & O_NOCTTY;
- device = inode->i_rdev;
- if (device == TTY_DEV) {
- if (!current->tty)
- return -ENXIO;
- device = current->tty->device;
- filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */
- /* noctty = 1; */
- }
-#ifdef CONFIG_VT
- if (device == CONSOLE_DEV) {
- extern int fg_console;
- device = MKDEV(TTY_MAJOR, fg_console + 1);
- noctty = 1;
- }
-#endif
- if (device == SYSCONS_DEV) {
- struct console *c = console_drivers;
- while(c && !c->device)
- c = c->next;
- if (!c)
- return -ENODEV;
- device = c->device(c);
- filp->f_flags |= O_NONBLOCK; /* Don't let /dev/console block */
- noctty = 1;
- }
-
- if (device == PTMX_DEV) {
-#ifdef CONFIG_UNIX98_PTYS
-
- /* find a free pty. */
- int major, minor;
- struct tty_driver *driver;
-
- /* find a device that is not in use. */
- retval = -1;
- for ( major = 0 ; major < UNIX98_NR_MAJORS ; major++ ) {
- driver = &ptm_driver[major];
- for (minor = driver->minor_start ;
- minor < driver->minor_start + driver->num ;
- minor++) {
- device = MKDEV(driver->major, minor);
- if (!init_dev(device, &tty)) goto ptmx_found; /* ok! */
- }
- }
- return -EIO; /* no free ptys */
- ptmx_found:
- set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
- minor -= driver->minor_start;
- devpts_pty_new(driver->other->name_base + minor, MKDEV(driver->other->major, minor + driver->other->minor_start));
- tty_register_devfs(&pts_driver[major], DEVFS_FL_NO_PERSISTENCE,
- pts_driver[major].minor_start + minor);
- noctty = 1;
- goto init_dev_done;
-
-#else /* CONFIG_UNIX_98_PTYS */
-
- return -ENODEV;
-
-#endif /* CONFIG_UNIX_98_PTYS */
- }
-
- retval = init_dev(device, &tty);
- if (retval)
- return retval;
-
-#ifdef CONFIG_UNIX98_PTYS
-init_dev_done:
-#endif
- filp->private_data = tty;
- file_move(filp, &tty->tty_files);
- check_tty_count(tty, "tty_open");
- if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
- tty->driver.subtype == PTY_TYPE_MASTER)
- noctty = 1;
-#ifdef TTY_DEBUG_HANGUP
- printk(KERN_DEBUG "opening %s...", tty_name(tty, buf));
-#endif
- if (tty->driver.open)
- retval = tty->driver.open(tty, filp);
- else
- retval = -ENODEV;
- filp->f_flags = saved_flags;
-
- if (!retval && test_bit(TTY_EXCLUSIVE, &tty->flags) && !suser())
- retval = -EBUSY;
-
- if (retval) {
-#ifdef TTY_DEBUG_HANGUP
- printk(KERN_DEBUG "error %d in opening %s...", retval,
- tty_name(tty, buf));
-#endif
-
- release_dev(filp);
- if (retval != -ERESTARTSYS)
- return retval;
- if (signal_pending(current))
- return retval;
- schedule();
- /*
- * Need to reset f_op in case a hangup happened.
- */
- filp->f_op = &tty_fops;
- goto retry_open;
- }
- if (!noctty &&
- current->leader &&
- !current->tty &&
- tty->session == 0) {
- task_lock(current);
- current->tty = tty;
- task_unlock(current);
- current->tty_old_pgrp = 0;
- tty->session = current->session;
- tty->pgrp = current->pgrp;
- }
- if ((tty->driver.type == TTY_DRIVER_TYPE_SERIAL) &&
- (tty->driver.subtype == SERIAL_TYPE_CALLOUT) &&
- (tty->count == 1)) {
- static int nr_warns;
- if (nr_warns < 5) {
- printk(KERN_WARNING "tty_io.c: "
- "process %d (%s) used obsolete /dev/%s - "
- "update software to use /dev/ttyS%d\n",
- current->pid, current->comm,
- tty_name(tty, buf), TTY_NUMBER(tty));
- nr_warns++;
- }
- }
- return 0;
-}
-
-static int tty_release(struct inode * inode, struct file * filp)
-{
- lock_kernel();
- release_dev(filp);
- unlock_kernel();
- return 0;
-}
-
-/* No kernel lock held - fine */
-static unsigned int tty_poll(struct file * filp, poll_table * wait)
-{
- struct tty_struct * tty;
-
- tty = (struct tty_struct *)filp->private_data;
- if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_poll"))
- return 0;
-
- if (tty->ldisc.poll)
- return (tty->ldisc.poll)(tty, filp, wait);
- return 0;
-}
-
-static int tty_fasync(int fd, struct file * filp, int on)
-{
- struct tty_struct * tty;
- int retval;
-
- tty = (struct tty_struct *)filp->private_data;
- if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_fasync"))
- return 0;
-
- retval = fasync_helper(fd, filp, on, &tty->fasync);
- if (retval <= 0)
- return retval;
-
- if (on) {
- if (!waitqueue_active(&tty->read_wait))
- tty->minimum_to_wake = 1;
- if (filp->f_owner.pid == 0) {
- filp->f_owner.pid = (-tty->pgrp) ? : current->pid;
- filp->f_owner.uid = current->uid;
- filp->f_owner.euid = current->euid;
- }
- } else {
- if (!tty->fasync && !waitqueue_active(&tty->read_wait))
- tty->minimum_to_wake = N_TTY_BUF_SIZE;
- }
- return 0;
-}
-
-static int tiocsti(struct tty_struct *tty, char * arg)
-{
- char ch, mbz = 0;
-
- if ((current->tty != tty) && !suser())
- return -EPERM;
- if (get_user(ch, arg))
- return -EFAULT;
- tty->ldisc.receive_buf(tty, &ch, &mbz, 1);
- return 0;
-}
-
-static int tiocgwinsz(struct tty_struct *tty, struct winsize * arg)
-{
- if (copy_to_user(arg, &tty->winsize, sizeof(*arg)))
- return -EFAULT;
- return 0;
-}
-
-static int tiocswinsz(struct tty_struct *tty, struct tty_struct *real_tty,
- struct winsize * arg)
-{
- struct winsize tmp_ws;
-
- if (copy_from_user(&tmp_ws, arg, sizeof(*arg)))
- return -EFAULT;
- if (!memcmp(&tmp_ws, &tty->winsize, sizeof(*arg)))
- return 0;
- if (tty->pgrp > 0)
- kill_pg(tty->pgrp, SIGWINCH, 1);
- if ((real_tty->pgrp != tty->pgrp) && (real_tty->pgrp > 0))
- kill_pg(real_tty->pgrp, SIGWINCH, 1);
- tty->winsize = tmp_ws;
- real_tty->winsize = tmp_ws;
- return 0;
-}
-
-static int tioccons(struct inode *inode,
- struct tty_struct *tty, struct tty_struct *real_tty)
-{
- if (inode->i_rdev == SYSCONS_DEV ||
- inode->i_rdev == CONSOLE_DEV) {
- if (!suser())
- return -EPERM;
- redirect = NULL;
- return 0;
- }
- if (redirect)
- return -EBUSY;
- redirect = real_tty;
- return 0;
-}
-
-
-static int fionbio(struct file *file, int *arg)
-{
- int nonblock;
-
- if (get_user(nonblock, arg))
- return -EFAULT;
-
- if (nonblock)
- file->f_flags |= O_NONBLOCK;
- else
- file->f_flags &= ~O_NONBLOCK;
- return 0;
-}
-
-static int tiocsctty(struct tty_struct *tty, int arg)
-{
- if (current->leader &&
- (current->session == tty->session))
- return 0;
- /*
- * The process must be a session leader and
- * not have a controlling tty already.
- */
- if (!current->leader || current->tty)
- return -EPERM;
- if (tty->session > 0) {
- /*
- * This tty is already the controlling
- * tty for another session group!
- */
- if ((arg == 1) && suser()) {
- /*
- * Steal it away
- */
- struct task_struct *p;
-
- read_lock(&tasklist_lock);
- for_each_task(p)
- if (p->tty == tty)
- p->tty = NULL;
- read_unlock(&tasklist_lock);
- } else
- return -EPERM;
- }
- task_lock(current);
- current->tty = tty;
- task_unlock(current);
- current->tty_old_pgrp = 0;
- tty->session = current->session;
- tty->pgrp = current->pgrp;
- return 0;
-}
-
-static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
-{
- /*
- * (tty == real_tty) is a cheap way of
- * testing if the tty is NOT a master pty.
- */
- if (tty == real_tty && current->tty != real_tty)
- return -ENOTTY;
- return put_user(real_tty->pgrp, arg);
-}
-
-static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
-{
- pid_t pgrp;
- int retval = tty_check_change(real_tty);
-
- if (retval == -EIO)
- return -ENOTTY;
- if (retval)
- return retval;
- if (!current->tty ||
- (current->tty != real_tty) ||
- (real_tty->session != current->session))
- return -ENOTTY;
- if (get_user(pgrp, (pid_t *) arg))
- return -EFAULT;
- if (pgrp < 0)
- return -EINVAL;
- if (session_of_pgrp(pgrp) != current->session)
- return -EPERM;
- real_tty->pgrp = pgrp;
- return 0;
-}
-
-static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
-{
- /*
- * (tty == real_tty) is a cheap way of
- * testing if the tty is NOT a master pty.
- */
- if (tty == real_tty && current->tty != real_tty)
- return -ENOTTY;
- if (real_tty->session <= 0)
- return -ENOTTY;
- return put_user(real_tty->session, arg);
-}
-
-static int tiocttygstruct(struct tty_struct *tty, struct tty_struct *arg)
-{
- if (copy_to_user(arg, tty, sizeof(*arg)))
- return -EFAULT;
- return 0;
-}
-
-static int tiocsetd(struct tty_struct *tty, int *arg)
-{
- int ldisc;
-
- if (get_user(ldisc, arg))
- return -EFAULT;
- return tty_set_ldisc(tty, ldisc);
-}
-
-static int send_break(struct tty_struct *tty, int duration)
-{
- set_current_state(TASK_INTERRUPTIBLE);
-
- tty->driver.break_ctl(tty, -1);
- if (!signal_pending(current))
- schedule_timeout(duration);
- tty->driver.break_ctl(tty, 0);
- if (signal_pending(current))
- return -EINTR;
- return 0;
-}
-
-/*
- * Split this up, as gcc can choke on it otherwise..
- */
-int tty_ioctl(struct inode * inode, struct file * file,
- unsigned int cmd, unsigned long arg)
-{
- struct tty_struct *tty, *real_tty;
- int retval;
-
- tty = (struct tty_struct *)file->private_data;
- if (tty_paranoia_check(tty, inode->i_rdev, "tty_ioctl"))
- return -EINVAL;
-
- real_tty = tty;
- if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
- tty->driver.subtype == PTY_TYPE_MASTER)
- real_tty = tty->link;
-
- /*
- * Break handling by driver
- */
- if (!tty->driver.break_ctl) {
- switch(cmd) {
- case TIOCSBRK:
- case TIOCCBRK:
- if (tty->driver.ioctl)
- return tty->driver.ioctl(tty, file, cmd, arg);
- return -EINVAL;
-
- /* These two ioctl's always return success; even if */
- /* the driver doesn't support them. */
- case TCSBRK:
- case TCSBRKP:
- if (!tty->driver.ioctl)
- return 0;
- retval = tty->driver.ioctl(tty, file, cmd, arg);
- if (retval == -ENOIOCTLCMD)
- retval = 0;
- return retval;
- }
- }
-
- /*
- * Factor out some common prep work
- */
- switch (cmd) {
- case TIOCSETD:
- case TIOCSBRK:
- case TIOCCBRK:
- case TCSBRK:
- case TCSBRKP:
- retval = tty_check_change(tty);
- if (retval)
- return retval;
- if (cmd != TIOCCBRK) {
- tty_wait_until_sent(tty, 0);
- if (signal_pending(current))
- return -EINTR;
- }
- break;
- }
-
- switch (cmd) {
- case TIOCSTI:
- return tiocsti(tty, (char *)arg);
- case TIOCGWINSZ:
- return tiocgwinsz(tty, (struct winsize *) arg);
- case TIOCSWINSZ:
- return tiocswinsz(tty, real_tty, (struct winsize *) arg);
- case TIOCCONS:
- return tioccons(inode, tty, real_tty);
- case FIONBIO:
- return fionbio(file, (int *) arg);
- case TIOCEXCL:
- set_bit(TTY_EXCLUSIVE, &tty->flags);
- return 0;
- case TIOCNXCL:
- clear_bit(TTY_EXCLUSIVE, &tty->flags);
- return 0;
- case TIOCNOTTY:
- if (current->tty != tty)
- return -ENOTTY;
- if (current->leader)
- disassociate_ctty(0);
- task_lock(current);
- current->tty = NULL;
- task_unlock(current);
- return 0;
- case TIOCSCTTY:
- return tiocsctty(tty, arg);
- case TIOCGPGRP:
- return tiocgpgrp(tty, real_tty, (pid_t *) arg);
- case TIOCSPGRP:
- return tiocspgrp(tty, real_tty, (pid_t *) arg);
- case TIOCGSID:
- return tiocgsid(tty, real_tty, (pid_t *) arg);
- case TIOCGETD:
- return put_user(tty->ldisc.num, (int *) arg);
- case TIOCSETD:
- return tiocsetd(tty, (int *) arg);
-#ifdef CONFIG_VT
- case TIOCLINUX:
- return tioclinux(tty, arg);
-#endif
- case TIOCTTYGSTRUCT:
- return tiocttygstruct(tty, (struct tty_struct *) arg);
-
- /*
- * Break handling
- */
- case TIOCSBRK: /* Turn break on, unconditionally */
- tty->driver.break_ctl(tty, -1);
- return 0;
-
- case TIOCCBRK: /* Turn break off, unconditionally */
- tty->driver.break_ctl(tty, 0);
- return 0;
- case TCSBRK: /* SVID version: non-zero arg --> no break */
- /*
- * XXX is the above comment correct, or the
- * code below correct? Is this ioctl used at
- * all by anyone?
- */
- if (!arg)
- return send_break(tty, HZ/4);
- return 0;
- case TCSBRKP: /* support for POSIX tcsendbreak() */
- return send_break(tty, arg ? arg*(HZ/10) : HZ/4);
- }
- if (tty->driver.ioctl) {
- int retval = (tty->driver.ioctl)(tty, file, cmd, arg);
- if (retval != -ENOIOCTLCMD)
- return retval;
- }
- if (tty->ldisc.ioctl) {
- int retval = (tty->ldisc.ioctl)(tty, file, cmd, arg);
- if (retval != -ENOIOCTLCMD)
- return retval;
- }
- return -EINVAL;
-}
-
-
-/*
- * This implements the "Secure Attention Key" --- the idea is to
- * prevent trojan horses by killing all processes associated with this
- * tty when the user hits the "Secure Attention Key". Required for
- * super-paranoid applications --- see the Orange Book for more details.
- *
- * This code could be nicer; ideally it should send a HUP, wait a few
- * seconds, then send a INT, and then a KILL signal. But you then
- * have to coordinate with the init process, since all processes associated
- * with the current tty must be dead before the new getty is allowed
- * to spawn.
- *
- * Now, if it would be correct ;-/ The current code has a nasty hole -
- * it doesn't catch files in flight. We may send the descriptor to ourselves
- * via AF_UNIX socket, close it and later fetch from socket. FIXME.
- *
- * Nasty bug: do_SAK is being called in interrupt context. This can
- * deadlock. We punt it up to process context. AKPM - 16Mar2001
- */
-static void __do_SAK(void *arg)
-{
-#ifdef TTY_SOFT_SAK
- tty_hangup(tty);
-#else
- struct tty_struct *tty = arg;
- struct task_struct *p;
- int session;
- int i;
- struct file *filp;
-
- if (!tty)
- return;
- session = tty->session;
- if (tty->ldisc.flush_buffer)
- tty->ldisc.flush_buffer(tty);
- if (tty->driver.flush_buffer)
- tty->driver.flush_buffer(tty);
- read_lock(&tasklist_lock);
- for_each_task(p) {
- if ((p->tty == tty) ||
- ((session > 0) && (p->session == session))) {
- send_sig(SIGKILL, p, 1);
- continue;
- }
- task_lock(p);
- if (p->files) {
- read_lock(&p->files->file_lock);
- for (i=0; i < p->files->max_fds; i++) {
- filp = fcheck_files(p->files, i);
- if (filp && (filp->f_op == &tty_fops) &&
- (filp->private_data == tty)) {
- send_sig(SIGKILL, p, 1);
- break;
- }
- }
- read_unlock(&p->files->file_lock);
- }
- task_unlock(p);
- }
- read_unlock(&tasklist_lock);
-#endif
-}
-
-/*
- * The tq handling here is a little racy - tty->SAK_tq may already be queued.
- * But there's no mechanism to fix that without futzing with tqueue_lock.
- * Fortunately we don't need to worry, because if ->SAK_tq is already queued,
- * the values which we write to it will be identical to the values which it
- * already has. --akpm
- */
-void do_SAK(struct tty_struct *tty)
-{
- if (!tty)
- return;
- PREPARE_TQUEUE(&tty->SAK_tq, __do_SAK, tty);
- schedule_task(&tty->SAK_tq);
-}
-
-/*
- * This routine is called out of the software interrupt to flush data
- * from the flip buffer to the line discipline.
- */
-static void flush_to_ldisc(void *private_)
-{
- struct tty_struct *tty = (struct tty_struct *) private_;
- unsigned char *cp;
- char *fp;
- int count;
- unsigned long flags;
-
- if (test_bit(TTY_DONT_FLIP, &tty->flags)) {
- queue_task(&tty->flip.tqueue, &tq_timer);
- return;
- }
- if (tty->flip.buf_num) {
- cp = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
- fp = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
- tty->flip.buf_num = 0;
-
- save_flags(flags); cli();
- tty->flip.char_buf_ptr = tty->flip.char_buf;
- tty->flip.flag_buf_ptr = tty->flip.flag_buf;
- } else {
- cp = tty->flip.char_buf;
- fp = tty->flip.flag_buf;
- tty->flip.buf_num = 1;
-
- save_flags(flags); cli();
- tty->flip.char_buf_ptr = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
- tty->flip.flag_buf_ptr = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
- }
- count = tty->flip.count;
- tty->flip.count = 0;
- restore_flags(flags);
-
- tty->ldisc.receive_buf(tty, cp, fp, count);
-}
-
-/*
- * Routine which returns the baud rate of the tty
- *
- * Note that the baud_table needs to be kept in sync with the
- * include/asm/termbits.h file.
- */
-static int baud_table[] = {
- 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800,
- 9600, 19200, 38400, 57600, 115200, 230400, 460800,
-#ifdef __sparc__
- 76800, 153600, 307200, 614400, 921600
-#else
- 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000,
- 2500000, 3000000, 3500000, 4000000
-#endif
-};
-
-static int n_baud_table = sizeof(baud_table)/sizeof(int);
-
-int tty_get_baud_rate(struct tty_struct *tty)
-{
- unsigned int cflag, i;
-
- cflag = tty->termios->c_cflag;
-
- i = cflag & CBAUD;
- if (i & CBAUDEX) {
- i &= ~CBAUDEX;
- if (i < 1 || i+15 >= n_baud_table)
- tty->termios->c_cflag &= ~CBAUDEX;
- else
- i += 15;
- }
- if (i==15 && tty->alt_speed) {
- if (!tty->warned) {
- printk(KERN_WARNING "Use of setserial/setrocket to "
- "set SPD_* flags is deprecated\n");
- tty->warned = 1;
- }
- return(tty->alt_speed);
- }
-
- return baud_table[i];
-}
-
-void tty_flip_buffer_push(struct tty_struct *tty)
-{
- if (tty->low_latency)
- flush_to_ldisc((void *) tty);
- else
- queue_task(&tty->flip.tqueue, &tq_timer);
-}
-
-/*
- * This subroutine initializes a tty structure.
- */
-static void initialize_tty_struct(struct tty_struct *tty)
-{
- memset(tty, 0, sizeof(struct tty_struct));
- tty->magic = TTY_MAGIC;
- tty->ldisc = ldiscs[N_TTY];
- tty->pgrp = -1;
- tty->flip.char_buf_ptr = tty->flip.char_buf;
- tty->flip.flag_buf_ptr = tty->flip.flag_buf;
- tty->flip.tqueue.routine = flush_to_ldisc;
- tty->flip.tqueue.data = tty;
- init_MUTEX(&tty->flip.pty_sem);
- init_waitqueue_head(&tty->write_wait);
- init_waitqueue_head(&tty->read_wait);
- tty->tq_hangup.routine = do_tty_hangup;
- tty->tq_hangup.data = tty;
- sema_init(&tty->atomic_read, 1);
- sema_init(&tty->atomic_write, 1);
- spin_lock_init(&tty->read_lock);
- INIT_LIST_HEAD(&tty->tty_files);
- INIT_TQUEUE(&tty->SAK_tq, 0, 0);
-}
-
-/*
- * The default put_char routine if the driver did not define one.
- */
-void tty_default_put_char(struct tty_struct *tty, unsigned char ch)
-{
- tty->driver.write(tty, 0, &ch, 1);
-}
-
-/*
- * Register a tty device described by <driver>, with minor number <minor>.
- */
-void tty_register_devfs (struct tty_driver *driver, unsigned int flags, unsigned minor)
-{
-#ifdef CONFIG_DEVFS_FS
- umode_t mode = S_IFCHR | S_IRUSR | S_IWUSR;
- kdev_t device = MKDEV (driver->major, minor);
- int idx = minor - driver->minor_start;
- char buf[32];
-
- switch (device) {
- case TTY_DEV:
- case PTMX_DEV:
- mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
- break;
- default:
- if (driver->major == PTY_MASTER_MAJOR)
- mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
- break;
- }
- if ( (minor < driver->minor_start) ||
- (minor >= driver->minor_start + driver->num) ) {
- printk(KERN_ERR "Attempt to register invalid minor number "
- "with devfs (%d:%d).\n", (int)driver->major,(int)minor);
- return;
- }
-# ifdef CONFIG_UNIX98_PTYS
- if ( (driver->major >= UNIX98_PTY_SLAVE_MAJOR) &&
- (driver->major < UNIX98_PTY_SLAVE_MAJOR + UNIX98_NR_MAJORS) )
- flags |= DEVFS_FL_CURRENT_OWNER;
-# endif
- sprintf(buf, driver->name, idx + driver->name_base);
- devfs_register (NULL, buf, flags | DEVFS_FL_DEFAULT,
- driver->major, minor, mode, &tty_fops, NULL);
-#endif /* CONFIG_DEVFS_FS */
-}
-
-void tty_unregister_devfs (struct tty_driver *driver, unsigned minor)
-{
-#ifdef CONFIG_DEVFS_FS
- void * handle;
- int idx = minor - driver->minor_start;
- char buf[32];
-
- sprintf(buf, driver->name, idx + driver->name_base);
- handle = devfs_find_handle (NULL, buf, driver->major, minor,
- DEVFS_SPECIAL_CHR, 0);
- devfs_unregister (handle);
-#endif /* CONFIG_DEVFS_FS */
-}
-
-EXPORT_SYMBOL(tty_register_devfs);
-EXPORT_SYMBOL(tty_unregister_devfs);
-
-/*
- * Called by a tty driver to register itself.
- */
-int tty_register_driver(struct tty_driver *driver)
-{
- int error;
- int i;
-
- if (driver->flags & TTY_DRIVER_INSTALLED)
- return 0;
-
- error = devfs_register_chrdev(driver->major, driver->name, &tty_fops);
- if (error < 0)
- return error;
- else if(driver->major == 0)
- driver->major = error;
-
- if (!driver->put_char)
- driver->put_char = tty_default_put_char;
-
- driver->prev = 0;
- driver->next = tty_drivers;
- if (tty_drivers) tty_drivers->prev = driver;
- tty_drivers = driver;
-
- if ( !(driver->flags & TTY_DRIVER_NO_DEVFS) ) {
- for(i = 0; i < driver->num; i++)
- tty_register_devfs(driver, 0, driver->minor_start + i);
- }
- proc_tty_register_driver(driver);
- return error;
-}
-
-/*
- * Called by a tty driver to unregister itself.
- */
-int tty_unregister_driver(struct tty_driver *driver)
-{
- int retval;
- struct tty_driver *p;
- int i, found = 0;
- struct termios *tp;
- const char *othername = NULL;
-
- if (*driver->refcount)
- return -EBUSY;
-
- for (p = tty_drivers; p; p = p->next) {
- if (p == driver)
- found++;
- else if (p->major == driver->major)
- othername = p->name;
- }
-
- if (!found)
- return -ENOENT;
-
- if (othername == NULL) {
- retval = devfs_unregister_chrdev(driver->major, driver->name);
- if (retval)
- return retval;
- } else
- devfs_register_chrdev(driver->major, othername, &tty_fops);
-
- if (driver->prev)
- driver->prev->next = driver->next;
- else
- tty_drivers = driver->next;
-
- if (driver->next)
- driver->next->prev = driver->prev;
-
- /*
- * Free the termios and termios_locked structures because
- * we don't want to get memory leaks when modular tty
- * drivers are removed from the kernel.
- */
- for (i = 0; i < driver->num; i++) {
- tp = driver->termios[i];
- if (tp) {
- driver->termios[i] = NULL;
- kfree(tp);
- }
- tp = driver->termios_locked[i];
- if (tp) {
- driver->termios_locked[i] = NULL;
- kfree(tp);
- }
- tty_unregister_devfs(driver, driver->minor_start + i);
- }
- proc_tty_unregister_driver(driver);
- return 0;
-}
-
-
-/*
- * Initialize the console device. This is called *early*, so
- * we can't necessarily depend on lots of kernel help here.
- * Just do some early initializations, and do the complex setup
- * later.
- */
-void __init console_init(void)
-{
- /* Setup the default TTY line discipline. */
- memset(ldiscs, 0, sizeof(ldiscs));
- (void) tty_register_ldisc(N_TTY, &tty_ldisc_N_TTY);
-
- /*
- * Set up the standard termios. Individual tty drivers may
- * deviate from this; this is used as a template.
- */
- memset(&tty_std_termios, 0, sizeof(struct termios));
- memcpy(tty_std_termios.c_cc, INIT_C_CC, NCCS);
- tty_std_termios.c_iflag = ICRNL | IXON;
- tty_std_termios.c_oflag = OPOST | ONLCR;
- tty_std_termios.c_cflag = B38400 | CS8 | CREAD | HUPCL;
- tty_std_termios.c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK |
- ECHOCTL | ECHOKE | IEXTEN;
-
- /*
- * set up the console device so that later boot sequences can
- * inform about problems etc..
- */
-#ifdef CONFIG_XENO
- xeno_console_init();
-#endif
-#ifdef CONFIG_VT
- con_init();
-#endif
-#ifdef CONFIG_AU1000_SERIAL_CONSOLE
- au1000_serial_console_init();
-#endif
-#ifdef CONFIG_SERIAL_CONSOLE
-#if (defined(CONFIG_8xx) || defined(CONFIG_8260))
- console_8xx_init();
-#elif defined(CONFIG_MAC_SERIAL)
- mac_scc_console_init();
-#elif defined(CONFIG_PARISC)
- pdc_console_init();
-#elif defined(CONFIG_SERIAL)
- serial_console_init();
-#endif /* CONFIG_8xx */
-#ifdef CONFIG_SGI_SERIAL
- sgi_serial_console_init();
-#endif
-#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC)
- vme_scc_console_init();
-#endif
-#if defined(CONFIG_SERIAL167)
- serial167_console_init();
-#endif
-#if defined(CONFIG_SH_SCI)
- sci_console_init();
-#endif
-#endif
-#ifdef CONFIG_TN3270_CONSOLE
- tub3270_con_init();
-#endif
-#ifdef CONFIG_TN3215
- con3215_init();
-#endif
-#ifdef CONFIG_HWC
- hwc_console_init();
-#endif
-#ifdef CONFIG_STDIO_CONSOLE
- stdio_console_init();
-#endif
-#ifdef CONFIG_SERIAL_21285_CONSOLE
- rs285_console_init();
-#endif
-#ifdef CONFIG_SERIAL_SA1100_CONSOLE
- sa1100_rs_console_init();
-#endif
-#ifdef CONFIG_ARC_CONSOLE
- arc_console_init();
-#endif
-#ifdef CONFIG_SERIAL_AMBA_CONSOLE
- ambauart_console_init();
-#endif
-#ifdef CONFIG_SERIAL_TX3912_CONSOLE
- tx3912_console_init();
-#endif
-}
-
-static struct tty_driver dev_tty_driver, dev_syscons_driver;
-#ifdef CONFIG_UNIX98_PTYS
-static struct tty_driver dev_ptmx_driver;
-#endif
-#ifdef CONFIG_VT
-static struct tty_driver dev_console_driver;
-#endif
-
-/*
- * Ok, now we can initialize the rest of the tty devices and can count
- * on memory allocations, interrupts etc..
- */
-void __init tty_init(void)
-{
- /*
- * dev_tty_driver and dev_console_driver are actually magic
- * devices which get redirected at open time. Nevertheless,
- * we register them so that register_chrdev is called
- * appropriately.
- */
- memset(&dev_tty_driver, 0, sizeof(struct tty_driver));
- dev_tty_driver.magic = TTY_DRIVER_MAGIC;
- dev_tty_driver.driver_name = "/dev/tty";
- dev_tty_driver.name = dev_tty_driver.driver_name + 5;
- dev_tty_driver.name_base = 0;
- dev_tty_driver.major = TTYAUX_MAJOR;
- dev_tty_driver.minor_start = 0;
- dev_tty_driver.num = 1;
- dev_tty_driver.type = TTY_DRIVER_TYPE_SYSTEM;
- dev_tty_driver.subtype = SYSTEM_TYPE_TTY;
-
- if (tty_register_driver(&dev_tty_driver))
- panic("Couldn't register /dev/tty driver\n");
-
- dev_syscons_driver = dev_tty_driver;
- dev_syscons_driver.driver_name = "/dev/console";
- dev_syscons_driver.name = dev_syscons_driver.driver_name + 5;
- dev_syscons_driver.major = TTYAUX_MAJOR;
- dev_syscons_driver.minor_start = 1;
- dev_syscons_driver.type = TTY_DRIVER_TYPE_SYSTEM;
- dev_syscons_driver.subtype = SYSTEM_TYPE_SYSCONS;
-
- if (tty_register_driver(&dev_syscons_driver))
- panic("Couldn't register /dev/console driver\n");
-
- /* console calls tty_register_driver() before kmalloc() works.
- * Thus, we can't devfs_register() then. Do so now, instead.
- */
-#ifdef CONFIG_VT
- con_init_devfs();
-#endif
-
-#ifdef CONFIG_UNIX98_PTYS
- dev_ptmx_driver = dev_tty_driver;
- dev_ptmx_driver.driver_name = "/dev/ptmx";
- dev_ptmx_driver.name = dev_ptmx_driver.driver_name + 5;
- dev_ptmx_driver.major= MAJOR(PTMX_DEV);
- dev_ptmx_driver.minor_start = MINOR(PTMX_DEV);
- dev_ptmx_driver.type = TTY_DRIVER_TYPE_SYSTEM;
- dev_ptmx_driver.subtype = SYSTEM_TYPE_SYSPTMX;
-
- if (tty_register_driver(&dev_ptmx_driver))
- panic("Couldn't register /dev/ptmx driver\n");
-#endif
-
-#ifdef CONFIG_VT
- dev_console_driver = dev_tty_driver;
- dev_console_driver.driver_name = "/dev/vc/0";
- dev_console_driver.name = dev_console_driver.driver_name + 5;
- dev_console_driver.major = TTY_MAJOR;
- dev_console_driver.type = TTY_DRIVER_TYPE_SYSTEM;
- dev_console_driver.subtype = SYSTEM_TYPE_CONSOLE;
-
- if (tty_register_driver(&dev_console_driver))
- panic("Couldn't register /dev/tty0 driver\n");
-
- kbd_init();
-#endif
-
-#ifdef CONFIG_ESPSERIAL /* init ESP before rs, so rs doesn't see the port */
- espserial_init();
-#endif
-#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC)
- vme_scc_init();
-#endif
-#ifdef CONFIG_SERIAL_TX3912
- tx3912_rs_init();
-#endif
-#ifdef CONFIG_ROCKETPORT
- rp_init();
-#endif
-#ifdef CONFIG_SERIAL167
- serial167_init();
-#endif
-#ifdef CONFIG_CYCLADES
- cy_init();
-#endif
-#ifdef CONFIG_STALLION
- stl_init();
-#endif
-#ifdef CONFIG_ISTALLION
- stli_init();
-#endif
-#ifdef CONFIG_DIGI
- pcxe_init();
-#endif
-#ifdef CONFIG_DIGIEPCA
- pc_init();
-#endif
-#ifdef CONFIG_SPECIALIX
- specialix_init();
-#endif
-#if (defined(CONFIG_8xx) || defined(CONFIG_8260))
- rs_8xx_init();
-#endif /* CONFIG_8xx */
- pty_init();
-#ifdef CONFIG_MOXA_SMARTIO
- mxser_init();
-#endif
-#ifdef CONFIG_MOXA_INTELLIO
- moxa_init();
-#endif
-#ifdef CONFIG_VT
- vcs_init();
-#endif
-#ifdef CONFIG_TN3270
- tub3270_init();
-#endif
-#ifdef CONFIG_TN3215
- tty3215_init();
-#endif
-#ifdef CONFIG_HWC
- hwc_tty_init();
-#endif
-#ifdef CONFIG_A2232
- a2232board_init();
-#endif
-}
+++ /dev/null
-/*
- * linux/fs/exec.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * #!-checking implemented by tytso.
- */
-/*
- * Demand-loading implemented 01.12.91 - no need to read anything but
- * the header into memory. The inode of the executable is put into
- * "current->executable", and page faults do the actual loading. Clean.
- *
- * Once more I can proudly say that linux stood up to being changed: it
- * was less than 2 hours work to get demand-loading completely implemented.
- *
- * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead,
- * current->executable is only used by the procfs. This allows a dispatch
- * table to check for several different types of binary formats. We keep
- * trying until we recognize the file or we run out of supported binary
- * formats.
- */
-
-#include <linux/config.h>
-#include <linux/slab.h>
-#include <linux/file.h>
-#include <linux/mman.h>
-#include <linux/a.out.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/smp_lock.h>
-#include <linux/init.h>
-#include <linux/pagemap.h>
-#include <linux/highmem.h>
-#include <linux/spinlock.h>
-#include <linux/personality.h>
-#define __NO_VERSION__
-#include <linux/module.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
-#include <asm/mmu_context.h>
-
-#ifdef CONFIG_KMOD
-#include <linux/kmod.h>
-#endif
-
-int core_uses_pid;
-
-static struct linux_binfmt *formats;
-static rwlock_t binfmt_lock = RW_LOCK_UNLOCKED;
-
-int register_binfmt(struct linux_binfmt * fmt)
-{
- struct linux_binfmt ** tmp = &formats;
-
- if (!fmt)
- return -EINVAL;
- if (fmt->next)
- return -EBUSY;
- write_lock(&binfmt_lock);
- while (*tmp) {
- if (fmt == *tmp) {
- write_unlock(&binfmt_lock);
- return -EBUSY;
- }
- tmp = &(*tmp)->next;
- }
- fmt->next = formats;
- formats = fmt;
- write_unlock(&binfmt_lock);
- return 0;
-}
-
-int unregister_binfmt(struct linux_binfmt * fmt)
-{
- struct linux_binfmt ** tmp = &formats;
-
- write_lock(&binfmt_lock);
- while (*tmp) {
- if (fmt == *tmp) {
- *tmp = fmt->next;
- write_unlock(&binfmt_lock);
- return 0;
- }
- tmp = &(*tmp)->next;
- }
- write_unlock(&binfmt_lock);
- return -EINVAL;
-}
-
-static inline void put_binfmt(struct linux_binfmt * fmt)
-{
- if (fmt->module)
- __MOD_DEC_USE_COUNT(fmt->module);
-}
-
-/*
- * Note that a shared library must be both readable and executable due to
- * security reasons.
- *
- * Also note that we take the address to load from from the file itself.
- */
-asmlinkage long sys_uselib(const char * library)
-{
- struct file * file;
- struct nameidata nd;
- int error;
-
- error = user_path_walk(library, &nd);
- if (error)
- goto out;
-
- error = -EINVAL;
- if (!S_ISREG(nd.dentry->d_inode->i_mode))
- goto exit;
-
- error = permission(nd.dentry->d_inode, MAY_READ | MAY_EXEC);
- if (error)
- goto exit;
-
- file = dentry_open(nd.dentry, nd.mnt, O_RDONLY);
- error = PTR_ERR(file);
- if (IS_ERR(file))
- goto out;
-
- error = -ENOEXEC;
- if(file->f_op && file->f_op->read) {
- struct linux_binfmt * fmt;
-
- read_lock(&binfmt_lock);
- for (fmt = formats ; fmt ; fmt = fmt->next) {
- if (!fmt->load_shlib)
- continue;
- if (!try_inc_mod_count(fmt->module))
- continue;
- read_unlock(&binfmt_lock);
- error = fmt->load_shlib(file);
- read_lock(&binfmt_lock);
- put_binfmt(fmt);
- if (error != -ENOEXEC)
- break;
- }
- read_unlock(&binfmt_lock);
- }
- fput(file);
-out:
- return error;
-exit:
- path_release(&nd);
- goto out;
-}
-
-/*
- * count() counts the number of arguments/envelopes
- */
-static int count(char ** argv, int max)
-{
- int i = 0;
-
- if (argv != NULL) {
- for (;;) {
- char * p;
-
- if (get_user(p, argv))
- return -EFAULT;
- if (!p)
- break;
- argv++;
- if(++i > max)
- return -E2BIG;
- }
- }
- return i;
-}
-
-/*
- * 'copy_strings()' copies argument/envelope strings from user
- * memory to free pages in kernel mem. These are in a format ready
- * to be put directly into the top of new user memory.
- */
-int copy_strings(int argc,char ** argv, struct linux_binprm *bprm)
-{
- while (argc-- > 0) {
- char *str;
- int len;
- unsigned long pos;
-
- if (get_user(str, argv+argc) || !(len = strnlen_user(str, bprm->p)))
- return -EFAULT;
- if (bprm->p < len)
- return -E2BIG;
-
- bprm->p -= len;
- /* XXX: add architecture specific overflow check here. */
-
- pos = bprm->p;
- while (len > 0) {
- char *kaddr;
- int i, new, err;
- struct page *page;
- int offset, bytes_to_copy;
-
- offset = pos % PAGE_SIZE;
- i = pos/PAGE_SIZE;
- page = bprm->page[i];
- new = 0;
- if (!page) {
- page = alloc_page(GFP_HIGHUSER);
- bprm->page[i] = page;
- if (!page)
- return -ENOMEM;
- new = 1;
- }
- kaddr = kmap(page);
-
- if (new && offset)
- memset(kaddr, 0, offset);
- bytes_to_copy = PAGE_SIZE - offset;
- if (bytes_to_copy > len) {
- bytes_to_copy = len;
- if (new)
- memset(kaddr+offset+len, 0, PAGE_SIZE-offset-len);
- }
- err = copy_from_user(kaddr + offset, str, bytes_to_copy);
- kunmap(page);
-
- if (err)
- return -EFAULT;
-
- pos += bytes_to_copy;
- str += bytes_to_copy;
- len -= bytes_to_copy;
- }
- }
- return 0;
-}
-
-/*
- * Like copy_strings, but get argv and its values from kernel memory.
- */
-int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm)
-{
- int r;
- mm_segment_t oldfs = get_fs();
- set_fs(KERNEL_DS);
- r = copy_strings(argc, argv, bprm);
- set_fs(oldfs);
- return r;
-}
-
-/*
- * This routine is used to map in a page into an address space: needed by
- * execve() for the initial stack and environment pages.
- *
- * tsk->mmap_sem is held for writing.
- */
-void put_dirty_page(struct task_struct * tsk, struct page *page, unsigned long address)
-{
- pgd_t * pgd;
- pmd_t * pmd;
- pte_t * pte;
-
- if (page_count(page) != 1)
- printk(KERN_ERR "mem_map disagrees with %p at %08lx\n", page, address);
- pgd = pgd_offset(tsk->mm, address);
-
- spin_lock(&tsk->mm->page_table_lock);
- pmd = pmd_alloc(tsk->mm, pgd, address);
- if (!pmd)
- goto out;
- pte = pte_alloc(tsk->mm, pmd, address);
- if (!pte)
- goto out;
- if (!pte_none(*pte))
- goto out;
- lru_cache_add(page);
- flush_dcache_page(page);
- flush_page_to_ram(page);
- set_pte(pte, pte_mkdirty(pte_mkwrite(mk_pte(page, PAGE_COPY))));
- XENO_flush_page_update_queue();
- tsk->mm->rss++;
- spin_unlock(&tsk->mm->page_table_lock);
-
- /* no need for flush_tlb */
- return;
-out:
- spin_unlock(&tsk->mm->page_table_lock);
- __free_page(page);
- force_sig(SIGKILL, tsk);
- return;
-}
-
-int setup_arg_pages(struct linux_binprm *bprm)
-{
- unsigned long stack_base;
- struct vm_area_struct *mpnt;
- int i;
-
- stack_base = STACK_TOP - MAX_ARG_PAGES*PAGE_SIZE;
-
- bprm->p += stack_base;
- if (bprm->loader)
- bprm->loader += stack_base;
- bprm->exec += stack_base;
-
- mpnt = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
- if (!mpnt)
- return -ENOMEM;
-
- down_write(¤t->mm->mmap_sem);
- {
- mpnt->vm_mm = current->mm;
- mpnt->vm_start = PAGE_MASK & (unsigned long) bprm->p;
- mpnt->vm_end = STACK_TOP;
- mpnt->vm_page_prot = PAGE_COPY;
- mpnt->vm_flags = VM_STACK_FLAGS;
- mpnt->vm_ops = NULL;
- mpnt->vm_pgoff = 0;
- mpnt->vm_file = NULL;
- mpnt->vm_private_data = (void *) 0;
- insert_vm_struct(current->mm, mpnt);
- current->mm->total_vm = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
- }
-
- for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
- struct page *page = bprm->page[i];
- if (page) {
- bprm->page[i] = NULL;
- put_dirty_page(current,page,stack_base);
- }
- stack_base += PAGE_SIZE;
- }
- up_write(¤t->mm->mmap_sem);
-
- return 0;
-}
-
-struct file *open_exec(const char *name)
-{
- struct nameidata nd;
- struct inode *inode;
- struct file *file;
- int err = 0;
-
- if (path_init(name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, &nd))
- err = path_walk(name, &nd);
- file = ERR_PTR(err);
- if (!err) {
- inode = nd.dentry->d_inode;
- file = ERR_PTR(-EACCES);
- if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
- S_ISREG(inode->i_mode)) {
- int err = permission(inode, MAY_EXEC);
- if (!err && !(inode->i_mode & 0111))
- err = -EACCES;
- file = ERR_PTR(err);
- if (!err) {
- file = dentry_open(nd.dentry, nd.mnt, O_RDONLY);
- if (!IS_ERR(file)) {
- err = deny_write_access(file);
- if (err) {
- fput(file);
- file = ERR_PTR(err);
- }
- }
-out:
- return file;
- }
- }
- path_release(&nd);
- }
- goto out;
-}
-
-int kernel_read(struct file *file, unsigned long offset,
- char * addr, unsigned long count)
-{
- mm_segment_t old_fs;
- loff_t pos = offset;
- int result = -ENOSYS;
-
- if (!file->f_op->read)
- goto fail;
- old_fs = get_fs();
- set_fs(get_ds());
- result = file->f_op->read(file, addr, count, &pos);
- set_fs(old_fs);
-fail:
- return result;
-}
-
-static int exec_mmap(void)
-{
- struct mm_struct * mm, * old_mm;
-
- old_mm = current->mm;
- if (old_mm && atomic_read(&old_mm->mm_users) == 1) {
- mm_release();
- exit_mmap(old_mm);
- return 0;
- }
-
- mm = mm_alloc();
- if (mm) {
- struct mm_struct *active_mm;
-
- if (init_new_context(current, mm)) {
- mmdrop(mm);
- return -ENOMEM;
- }
-
- /* Add it to the list of mm's */
- spin_lock(&mmlist_lock);
- list_add(&mm->mmlist, &init_mm.mmlist);
- mmlist_nr++;
- spin_unlock(&mmlist_lock);
-
- task_lock(current);
- active_mm = current->active_mm;
- current->mm = mm;
- current->active_mm = mm;
- task_unlock(current);
- activate_mm(active_mm, mm);
- mm_release();
- if (old_mm) {
- if (active_mm != old_mm) BUG();
- mmput(old_mm);
- return 0;
- }
- mmdrop(active_mm);
- return 0;
- }
- return -ENOMEM;
-}
-
-/*
- * This function makes sure the current process has its own signal table,
- * so that flush_signal_handlers can later reset the handlers without
- * disturbing other processes. (Other processes might share the signal
- * table via the CLONE_SIGNAL option to clone().)
- */
-
-static inline int make_private_signals(void)
-{
- struct signal_struct * newsig;
-
- if (atomic_read(¤t->sig->count) <= 1)
- return 0;
- newsig = kmem_cache_alloc(sigact_cachep, GFP_KERNEL);
- if (newsig == NULL)
- return -ENOMEM;
- spin_lock_init(&newsig->siglock);
- atomic_set(&newsig->count, 1);
- memcpy(newsig->action, current->sig->action, sizeof(newsig->action));
- spin_lock_irq(¤t->sigmask_lock);
- current->sig = newsig;
- spin_unlock_irq(¤t->sigmask_lock);
- return 0;
-}
-
-/*
- * If make_private_signals() made a copy of the signal table, decrement the
- * refcount of the original table, and free it if necessary.
- * We don't do that in make_private_signals() so that we can back off
- * in flush_old_exec() if an error occurs after calling make_private_signals().
- */
-
-static inline void release_old_signals(struct signal_struct * oldsig)
-{
- if (current->sig == oldsig)
- return;
- if (atomic_dec_and_test(&oldsig->count))
- kmem_cache_free(sigact_cachep, oldsig);
-}
-
-/*
- * These functions flushes out all traces of the currently running executable
- * so that a new one can be started
- */
-
-static inline void flush_old_files(struct files_struct * files)
-{
- long j = -1;
-
- write_lock(&files->file_lock);
- for (;;) {
- unsigned long set, i;
-
- j++;
- i = j * __NFDBITS;
- if (i >= files->max_fds || i >= files->max_fdset)
- break;
- set = files->close_on_exec->fds_bits[j];
- if (!set)
- continue;
- files->close_on_exec->fds_bits[j] = 0;
- write_unlock(&files->file_lock);
- for ( ; set ; i++,set >>= 1) {
- if (set & 1) {
- sys_close(i);
- }
- }
- write_lock(&files->file_lock);
-
- }
- write_unlock(&files->file_lock);
-}
-
-/*
- * An execve() will automatically "de-thread" the process.
- * Note: we don't have to hold the tasklist_lock to test
- * whether we migth need to do this. If we're not part of
- * a thread group, there is no way we can become one
- * dynamically. And if we are, we only need to protect the
- * unlink - even if we race with the last other thread exit,
- * at worst the list_del_init() might end up being a no-op.
- */
-static inline void de_thread(struct task_struct *tsk)
-{
- if (!list_empty(&tsk->thread_group)) {
- write_lock_irq(&tasklist_lock);
- list_del_init(&tsk->thread_group);
- write_unlock_irq(&tasklist_lock);
- }
-
- /* Minor oddity: this might stay the same. */
- tsk->tgid = tsk->pid;
-}
-
-int flush_old_exec(struct linux_binprm * bprm)
-{
- char * name;
- int i, ch, retval;
- struct signal_struct * oldsig;
-
- /*
- * Make sure we have a private signal table
- */
- oldsig = current->sig;
- retval = make_private_signals();
- if (retval) goto flush_failed;
-
- /*
- * Release all of the old mmap stuff
- */
- retval = exec_mmap();
- if (retval) goto mmap_failed;
-
- /* This is the point of no return */
- release_old_signals(oldsig);
-
- current->sas_ss_sp = current->sas_ss_size = 0;
-
- if (current->euid == current->uid && current->egid == current->gid)
- current->mm->dumpable = 1;
- name = bprm->filename;
- for (i=0; (ch = *(name++)) != '\0';) {
- if (ch == '/')
- i = 0;
- else
- if (i < 15)
- current->comm[i++] = ch;
- }
- current->comm[i] = '\0';
-
- flush_thread();
-
- de_thread(current);
-
- if (bprm->e_uid != current->euid || bprm->e_gid != current->egid ||
- permission(bprm->file->f_dentry->d_inode,MAY_READ))
- current->mm->dumpable = 0;
-
- /* An exec changes our domain. We are no longer part of the thread
- group */
-
- current->self_exec_id++;
-
- flush_signal_handlers(current);
- flush_old_files(current->files);
-
- return 0;
-
-mmap_failed:
-flush_failed:
- spin_lock_irq(¤t->sigmask_lock);
- if (current->sig != oldsig) {
- kfree(current->sig);
- current->sig = oldsig;
- }
- spin_unlock_irq(¤t->sigmask_lock);
- return retval;
-}
-
-/*
- * We mustn't allow tracing of suid binaries, unless
- * the tracer has the capability to trace anything..
- */
-static inline int must_not_trace_exec(struct task_struct * p)
-{
- return (p->ptrace & PT_PTRACED) && !(p->ptrace & PT_PTRACE_CAP);
-}
-
-/*
- * Fill the binprm structure from the inode.
- * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
- */
-int prepare_binprm(struct linux_binprm *bprm)
-{
- int mode;
- struct inode * inode = bprm->file->f_dentry->d_inode;
-
- mode = inode->i_mode;
- /*
- * Check execute perms again - if the caller has CAP_DAC_OVERRIDE,
- * vfs_permission lets a non-executable through
- */
- if (!(mode & 0111)) /* with at least _one_ execute bit set */
- return -EACCES;
- if (bprm->file->f_op == NULL)
- return -EACCES;
-
- bprm->e_uid = current->euid;
- bprm->e_gid = current->egid;
-
- if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
- /* Set-uid? */
- if (mode & S_ISUID)
- bprm->e_uid = inode->i_uid;
-
- /* Set-gid? */
- /*
- * If setgid is set but no group execute bit then this
- * is a candidate for mandatory locking, not a setgid
- * executable.
- */
- if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
- bprm->e_gid = inode->i_gid;
- }
-
- /* We don't have VFS support for capabilities yet */
- cap_clear(bprm->cap_inheritable);
- cap_clear(bprm->cap_permitted);
- cap_clear(bprm->cap_effective);
-
- /* To support inheritance of root-permissions and suid-root
- * executables under compatibility mode, we raise all three
- * capability sets for the file.
- *
- * If only the real uid is 0, we only raise the inheritable
- * and permitted sets of the executable file.
- */
-
- if (!issecure(SECURE_NOROOT)) {
- if (bprm->e_uid == 0 || current->uid == 0) {
- cap_set_full(bprm->cap_inheritable);
- cap_set_full(bprm->cap_permitted);
- }
- if (bprm->e_uid == 0)
- cap_set_full(bprm->cap_effective);
- }
-
- memset(bprm->buf,0,BINPRM_BUF_SIZE);
- return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
-}
-
-/*
- * This function is used to produce the new IDs and capabilities
- * from the old ones and the file's capabilities.
- *
- * The formula used for evolving capabilities is:
- *
- * pI' = pI
- * (***) pP' = (fP & X) | (fI & pI)
- * pE' = pP' & fE [NB. fE is 0 or ~0]
- *
- * I=Inheritable, P=Permitted, E=Effective // p=process, f=file
- * ' indicates post-exec(), and X is the global 'cap_bset'.
- *
- */
-
-void compute_creds(struct linux_binprm *bprm)
-{
- kernel_cap_t new_permitted, working;
- int do_unlock = 0;
-
- new_permitted = cap_intersect(bprm->cap_permitted, cap_bset);
- working = cap_intersect(bprm->cap_inheritable,
- current->cap_inheritable);
- new_permitted = cap_combine(new_permitted, working);
-
- if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
- !cap_issubset(new_permitted, current->cap_permitted)) {
- current->mm->dumpable = 0;
-
- lock_kernel();
- if (must_not_trace_exec(current)
- || atomic_read(¤t->fs->count) > 1
- || atomic_read(¤t->files->count) > 1
- || atomic_read(¤t->sig->count) > 1) {
- if(!capable(CAP_SETUID)) {
- bprm->e_uid = current->uid;
- bprm->e_gid = current->gid;
- }
- if(!capable(CAP_SETPCAP)) {
- new_permitted = cap_intersect(new_permitted,
- current->cap_permitted);
- }
- }
- do_unlock = 1;
- }
-
-
- /* For init, we want to retain the capabilities set
- * in the init_task struct. Thus we skip the usual
- * capability rules */
- if (current->pid != 1) {
- current->cap_permitted = new_permitted;
- current->cap_effective =
- cap_intersect(new_permitted, bprm->cap_effective);
- }
-
- /* AUD: Audit candidate if current->cap_effective is set */
-
- current->suid = current->euid = current->fsuid = bprm->e_uid;
- current->sgid = current->egid = current->fsgid = bprm->e_gid;
-
- if(do_unlock)
- unlock_kernel();
- current->keep_capabilities = 0;
-}
-
-
-void remove_arg_zero(struct linux_binprm *bprm)
-{
- if (bprm->argc) {
- unsigned long offset;
- char * kaddr;
- struct page *page;
-
- offset = bprm->p % PAGE_SIZE;
- goto inside;
-
- while (bprm->p++, *(kaddr+offset++)) {
- if (offset != PAGE_SIZE)
- continue;
- offset = 0;
- kunmap(page);
-inside:
- page = bprm->page[bprm->p/PAGE_SIZE];
- kaddr = kmap(page);
- }
- kunmap(page);
- bprm->argc--;
- }
-}
-
-/*
- * cycle the list of binary formats handler, until one recognizes the image
- */
-int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
-{
- int try,retval=0;
- struct linux_binfmt *fmt;
-#ifdef __alpha__
- /* handle /sbin/loader.. */
- {
- struct exec * eh = (struct exec *) bprm->buf;
-
- if (!bprm->loader && eh->fh.f_magic == 0x183 &&
- (eh->fh.f_flags & 0x3000) == 0x3000)
- {
- struct file * file;
- unsigned long loader;
-
- allow_write_access(bprm->file);
- fput(bprm->file);
- bprm->file = NULL;
-
- loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
-
- file = open_exec("/sbin/loader");
- retval = PTR_ERR(file);
- if (IS_ERR(file))
- return retval;
-
- /* Remember if the application is TASO. */
- bprm->sh_bang = eh->ah.entry < 0x100000000;
-
- bprm->file = file;
- bprm->loader = loader;
- retval = prepare_binprm(bprm);
- if (retval<0)
- return retval;
- /* should call search_binary_handler recursively here,
- but it does not matter */
- }
- }
-#endif
- /* kernel module loader fixup */
- /* so we don't try to load run modprobe in kernel space. */
- set_fs(USER_DS);
- for (try=0; try<2; try++) {
- read_lock(&binfmt_lock);
- for (fmt = formats ; fmt ; fmt = fmt->next) {
- int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
- if (!fn)
- continue;
- if (!try_inc_mod_count(fmt->module))
- continue;
- read_unlock(&binfmt_lock);
- retval = fn(bprm, regs);
- if (retval >= 0) {
- put_binfmt(fmt);
- allow_write_access(bprm->file);
- if (bprm->file)
- fput(bprm->file);
- bprm->file = NULL;
- current->did_exec = 1;
- return retval;
- }
- read_lock(&binfmt_lock);
- put_binfmt(fmt);
- if (retval != -ENOEXEC)
- break;
- if (!bprm->file) {
- read_unlock(&binfmt_lock);
- return retval;
- }
- }
- read_unlock(&binfmt_lock);
- if (retval != -ENOEXEC) {
- break;
-#ifdef CONFIG_KMOD
- }else{
-#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
- char modname[20];
- if (printable(bprm->buf[0]) &&
- printable(bprm->buf[1]) &&
- printable(bprm->buf[2]) &&
- printable(bprm->buf[3]))
- break; /* -ENOEXEC */
- sprintf(modname, "binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
- request_module(modname);
-#endif
- }
- }
- return retval;
-}
-
-
-/*
- * sys_execve() executes a new program.
- */
-int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs)
-{
- struct linux_binprm bprm;
- struct file *file;
- int retval;
- int i;
-
- file = open_exec(filename);
-
- retval = PTR_ERR(file);
- if (IS_ERR(file))
- return retval;
-
- bprm.p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
- memset(bprm.page, 0, MAX_ARG_PAGES*sizeof(bprm.page[0]));
-
- bprm.file = file;
- bprm.filename = filename;
- bprm.sh_bang = 0;
- bprm.loader = 0;
- bprm.exec = 0;
- if ((bprm.argc = count(argv, bprm.p / sizeof(void *))) < 0) {
- allow_write_access(file);
- fput(file);
- return bprm.argc;
- }
-
- if ((bprm.envc = count(envp, bprm.p / sizeof(void *))) < 0) {
- allow_write_access(file);
- fput(file);
- return bprm.envc;
- }
-
- retval = prepare_binprm(&bprm);
- if (retval < 0)
- goto out;
-
- retval = copy_strings_kernel(1, &bprm.filename, &bprm);
- if (retval < 0)
- goto out;
-
- bprm.exec = bprm.p;
- retval = copy_strings(bprm.envc, envp, &bprm);
- if (retval < 0)
- goto out;
-
- retval = copy_strings(bprm.argc, argv, &bprm);
- if (retval < 0)
- goto out;
-
- retval = search_binary_handler(&bprm,regs);
- if (retval >= 0)
- /* execve success */
- return retval;
-
-out:
- /* Something went wrong, return the inode and free the argument pages*/
- allow_write_access(bprm.file);
- if (bprm.file)
- fput(bprm.file);
-
- for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
- struct page * page = bprm.page[i];
- if (page)
- __free_page(page);
- }
-
- return retval;
-}
-
-void set_binfmt(struct linux_binfmt *new)
-{
- struct linux_binfmt *old = current->binfmt;
- if (new && new->module)
- __MOD_INC_USE_COUNT(new->module);
- current->binfmt = new;
- if (old && old->module)
- __MOD_DEC_USE_COUNT(old->module);
-}
-
-int do_coredump(long signr, struct pt_regs * regs)
-{
- struct linux_binfmt * binfmt;
- char corename[6+sizeof(current->comm)+10];
- struct file * file;
- struct inode * inode;
- int retval = 0;
-
- lock_kernel();
- binfmt = current->binfmt;
- if (!binfmt || !binfmt->core_dump)
- goto fail;
- if (!current->mm->dumpable)
- goto fail;
- current->mm->dumpable = 0;
- if (current->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump)
- goto fail;
-
- memcpy(corename,"core.", 5);
- corename[4] = '\0';
- if (core_uses_pid || atomic_read(¤t->mm->mm_users) != 1)
- sprintf(&corename[4], ".%d", current->pid);
- file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW, 0600);
- if (IS_ERR(file))
- goto fail;
- inode = file->f_dentry->d_inode;
- if (inode->i_nlink > 1)
- goto close_fail; /* multiple links - don't dump */
- if (d_unhashed(file->f_dentry))
- goto close_fail;
-
- if (!S_ISREG(inode->i_mode))
- goto close_fail;
- if (!file->f_op)
- goto close_fail;
- if (!file->f_op->write)
- goto close_fail;
- if (do_truncate(file->f_dentry, 0) != 0)
- goto close_fail;
-
- down_read(¤t->mm->mmap_sem);
- retval = binfmt->core_dump(signr, regs, file);
- up_read(¤t->mm->mmap_sem);
-
-close_fail:
- filp_close(file, NULL);
-fail:
- unlock_kernel();
- return retval;
-}
+++ /dev/null
-#ifndef __I386_A_OUT_H__
-#define __I386_A_OUT_H__
-
-struct exec
-{
- unsigned long a_info; /* Use macros N_MAGIC, etc for access */
- unsigned a_text; /* length of text, in bytes */
- unsigned a_data; /* length of data, in bytes */
- unsigned a_bss; /* length of uninitialized data area for file, in bytes */
- unsigned a_syms; /* length of symbol table data in file, in bytes */
- unsigned a_entry; /* start address */
- unsigned a_trsize; /* length of relocation info for text, in bytes */
- unsigned a_drsize; /* length of relocation info for data, in bytes */
-};
-
-#define N_TRSIZE(a) ((a).a_trsize)
-#define N_DRSIZE(a) ((a).a_drsize)
-#define N_SYMSIZE(a) ((a).a_syms)
-
-#ifdef __KERNEL__
-
-#define STACK_TOP TASK_SIZE
-
-#endif
-
-#endif /* __A_OUT_GNU_H__ */
+++ /dev/null
-#ifndef __ASM_APIC_H
-#define __ASM_APIC_H
-
-#include <linux/config.h>
-#include <linux/pm.h>
-#include <asm/apicdef.h>
-#include <asm/system.h>
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-#define APIC_DEBUG 0
-
-#if APIC_DEBUG
-#define Dprintk(x...) printk(x)
-#else
-#define Dprintk(x...)
-#endif
-
-/*
- * Basic functions accessing APICs.
- */
-
-static __inline void apic_write(unsigned long reg, unsigned long v)
-{
- *((volatile unsigned long *)(APIC_BASE+reg)) = v;
-}
-
-static __inline void apic_write_atomic(unsigned long reg, unsigned long v)
-{
- xchg((volatile unsigned long *)(APIC_BASE+reg), v);
-}
-
-static __inline unsigned long apic_read(unsigned long reg)
-{
- return *((volatile unsigned long *)(APIC_BASE+reg));
-}
-
-static __inline__ void apic_wait_icr_idle(void)
-{
- do { } while ( apic_read( APIC_ICR ) & APIC_ICR_BUSY );
-}
-
-#ifdef CONFIG_X86_GOOD_APIC
-# define FORCE_READ_AROUND_WRITE 0
-# define apic_read_around(x)
-# define apic_write_around(x,y) apic_write((x),(y))
-#else
-# define FORCE_READ_AROUND_WRITE 1
-# define apic_read_around(x) apic_read(x)
-# define apic_write_around(x,y) apic_write_atomic((x),(y))
-#endif
-
-static inline void ack_APIC_irq(void)
-{
- /*
- * ack_APIC_irq() actually gets compiled as a single instruction:
- * - a single rmw on Pentium/82489DX
- * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
- * ... yummie.
- */
-
- /* Docs say use 0 for future compatibility */
- apic_write_around(APIC_EOI, 0);
-}
-
-extern int get_maxlvt(void);
-extern void clear_local_APIC(void);
-extern void connect_bsp_APIC (void);
-extern void disconnect_bsp_APIC (void);
-extern void disable_local_APIC (void);
-extern int verify_local_APIC (void);
-extern void cache_APIC_registers (void);
-extern void sync_Arb_IDs (void);
-extern void init_bsp_APIC (void);
-extern void setup_local_APIC (void);
-extern void init_apic_mappings (void);
-extern void smp_local_timer_interrupt (struct pt_regs * regs);
-extern void setup_APIC_clocks (void);
-extern void setup_apic_nmi_watchdog (void);
-extern inline void nmi_watchdog_tick (struct pt_regs * regs);
-extern int APIC_init_uniprocessor (void);
-
-extern struct pm_dev *apic_pm_register(pm_dev_t, unsigned long, pm_callback);
-extern void apic_pm_unregister(struct pm_dev*);
-
-extern unsigned int apic_timer_irqs [NR_CPUS];
-extern int check_nmi_watchdog (void);
-
-extern unsigned int nmi_watchdog;
-#define NMI_NONE 0
-#define NMI_IO_APIC 1
-#define NMI_LOCAL_APIC 2
-#define NMI_INVALID 3
-
-#endif /* CONFIG_X86_LOCAL_APIC */
-
-#endif /* __ASM_APIC_H */
+++ /dev/null
-#ifndef __ASM_APICDEF_H
-#define __ASM_APICDEF_H
-
-/*
- * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
- *
- * Alan Cox <Alan.Cox@linux.org>, 1995.
- * Ingo Molnar <mingo@redhat.com>, 1999, 2000
- */
-
-#define APIC_DEFAULT_PHYS_BASE 0xfee00000
-
-#define APIC_ID 0x20
-#define APIC_ID_MASK (0x0F<<24)
-#define GET_APIC_ID(x) (((x)>>24)&0x0F)
-#define APIC_LVR 0x30
-#define APIC_LVR_MASK 0xFF00FF
-#define GET_APIC_VERSION(x) ((x)&0xFF)
-#define GET_APIC_MAXLVT(x) (((x)>>16)&0xFF)
-#define APIC_INTEGRATED(x) ((x)&0xF0)
-#define APIC_TASKPRI 0x80
-#define APIC_TPRI_MASK 0xFF
-#define APIC_ARBPRI 0x90
-#define APIC_ARBPRI_MASK 0xFF
-#define APIC_PROCPRI 0xA0
-#define APIC_EOI 0xB0
-#define APIC_EIO_ACK 0x0 /* Write this to the EOI register */
-#define APIC_RRR 0xC0
-#define APIC_LDR 0xD0
-#define APIC_LDR_MASK (0xFF<<24)
-#define GET_APIC_LOGICAL_ID(x) (((x)>>24)&0xFF)
-#define SET_APIC_LOGICAL_ID(x) (((x)<<24))
-#define APIC_ALL_CPUS 0xFF
-#define APIC_DFR 0xE0
-#define APIC_SPIV 0xF0
-#define APIC_SPIV_FOCUS_DISABLED (1<<9)
-#define APIC_SPIV_APIC_ENABLED (1<<8)
-#define APIC_ISR 0x100
-#define APIC_TMR 0x180
-#define APIC_IRR 0x200
-#define APIC_ESR 0x280
-#define APIC_ESR_SEND_CS 0x00001
-#define APIC_ESR_RECV_CS 0x00002
-#define APIC_ESR_SEND_ACC 0x00004
-#define APIC_ESR_RECV_ACC 0x00008
-#define APIC_ESR_SENDILL 0x00020
-#define APIC_ESR_RECVILL 0x00040
-#define APIC_ESR_ILLREGA 0x00080
-#define APIC_ICR 0x300
-#define APIC_DEST_SELF 0x40000
-#define APIC_DEST_ALLINC 0x80000
-#define APIC_DEST_ALLBUT 0xC0000
-#define APIC_ICR_RR_MASK 0x30000
-#define APIC_ICR_RR_INVALID 0x00000
-#define APIC_ICR_RR_INPROG 0x10000
-#define APIC_ICR_RR_VALID 0x20000
-#define APIC_INT_LEVELTRIG 0x08000
-#define APIC_INT_ASSERT 0x04000
-#define APIC_ICR_BUSY 0x01000
-#define APIC_DEST_LOGICAL 0x00800
-#define APIC_DM_FIXED 0x00000
-#define APIC_DM_LOWEST 0x00100
-#define APIC_DM_SMI 0x00200
-#define APIC_DM_REMRD 0x00300
-#define APIC_DM_NMI 0x00400
-#define APIC_DM_INIT 0x00500
-#define APIC_DM_STARTUP 0x00600
-#define APIC_DM_EXTINT 0x00700
-#define APIC_VECTOR_MASK 0x000FF
-#define APIC_ICR2 0x310
-#define GET_APIC_DEST_FIELD(x) (((x)>>24)&0xFF)
-#define SET_APIC_DEST_FIELD(x) ((x)<<24)
-#define APIC_LVTT 0x320
-#define APIC_LVTPC 0x340
-#define APIC_LVT0 0x350
-#define APIC_LVT_TIMER_BASE_MASK (0x3<<18)
-#define GET_APIC_TIMER_BASE(x) (((x)>>18)&0x3)
-#define SET_APIC_TIMER_BASE(x) (((x)<<18))
-#define APIC_TIMER_BASE_CLKIN 0x0
-#define APIC_TIMER_BASE_TMBASE 0x1
-#define APIC_TIMER_BASE_DIV 0x2
-#define APIC_LVT_TIMER_PERIODIC (1<<17)
-#define APIC_LVT_MASKED (1<<16)
-#define APIC_LVT_LEVEL_TRIGGER (1<<15)
-#define APIC_LVT_REMOTE_IRR (1<<14)
-#define APIC_INPUT_POLARITY (1<<13)
-#define APIC_SEND_PENDING (1<<12)
-#define GET_APIC_DELIVERY_MODE(x) (((x)>>8)&0x7)
-#define SET_APIC_DELIVERY_MODE(x,y) (((x)&~0x700)|((y)<<8))
-#define APIC_MODE_FIXED 0x0
-#define APIC_MODE_NMI 0x4
-#define APIC_MODE_EXINT 0x7
-#define APIC_LVT1 0x360
-#define APIC_LVTERR 0x370
-#define APIC_TMICT 0x380
-#define APIC_TMCCT 0x390
-#define APIC_TDCR 0x3E0
-#define APIC_TDR_DIV_TMBASE (1<<2)
-#define APIC_TDR_DIV_1 0xB
-#define APIC_TDR_DIV_2 0x0
-#define APIC_TDR_DIV_4 0x1
-#define APIC_TDR_DIV_8 0x2
-#define APIC_TDR_DIV_16 0x3
-#define APIC_TDR_DIV_32 0x8
-#define APIC_TDR_DIV_64 0x9
-#define APIC_TDR_DIV_128 0xA
-
-#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
-
-#define MAX_IO_APICS 8
-
-/*
- * the local APIC register structure, memory mapped. Not terribly well
- * tested, but we might eventually use this one in the future - the
- * problem why we cannot use it right now is the P5 APIC, it has an
- * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
- */
-#define u32 unsigned int
-
-#define lapic ((volatile struct local_apic *)APIC_BASE)
-
-struct local_apic {
-
-/*000*/ struct { u32 __reserved[4]; } __reserved_01;
-
-/*010*/ struct { u32 __reserved[4]; } __reserved_02;
-
-/*020*/ struct { /* APIC ID Register */
- u32 __reserved_1 : 24,
- phys_apic_id : 4,
- __reserved_2 : 4;
- u32 __reserved[3];
- } id;
-
-/*030*/ const
- struct { /* APIC Version Register */
- u32 version : 8,
- __reserved_1 : 8,
- max_lvt : 8,
- __reserved_2 : 8;
- u32 __reserved[3];
- } version;
-
-/*040*/ struct { u32 __reserved[4]; } __reserved_03;
-
-/*050*/ struct { u32 __reserved[4]; } __reserved_04;
-
-/*060*/ struct { u32 __reserved[4]; } __reserved_05;
-
-/*070*/ struct { u32 __reserved[4]; } __reserved_06;
-
-/*080*/ struct { /* Task Priority Register */
- u32 priority : 8,
- __reserved_1 : 24;
- u32 __reserved_2[3];
- } tpr;
-
-/*090*/ const
- struct { /* Arbitration Priority Register */
- u32 priority : 8,
- __reserved_1 : 24;
- u32 __reserved_2[3];
- } apr;
-
-/*0A0*/ const
- struct { /* Processor Priority Register */
- u32 priority : 8,
- __reserved_1 : 24;
- u32 __reserved_2[3];
- } ppr;
-
-/*0B0*/ struct { /* End Of Interrupt Register */
- u32 eoi;
- u32 __reserved[3];
- } eoi;
-
-/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
-
-/*0D0*/ struct { /* Logical Destination Register */
- u32 __reserved_1 : 24,
- logical_dest : 8;
- u32 __reserved_2[3];
- } ldr;
-
-/*0E0*/ struct { /* Destination Format Register */
- u32 __reserved_1 : 28,
- model : 4;
- u32 __reserved_2[3];
- } dfr;
-
-/*0F0*/ struct { /* Spurious Interrupt Vector Register */
- u32 spurious_vector : 8,
- apic_enabled : 1,
- focus_cpu : 1,
- __reserved_2 : 22;
- u32 __reserved_3[3];
- } svr;
-
-/*100*/ struct { /* In Service Register */
-/*170*/ u32 bitfield;
- u32 __reserved[3];
- } isr [8];
-
-/*180*/ struct { /* Trigger Mode Register */
-/*1F0*/ u32 bitfield;
- u32 __reserved[3];
- } tmr [8];
-
-/*200*/ struct { /* Interrupt Request Register */
-/*270*/ u32 bitfield;
- u32 __reserved[3];
- } irr [8];
-
-/*280*/ union { /* Error Status Register */
- struct {
- u32 send_cs_error : 1,
- receive_cs_error : 1,
- send_accept_error : 1,
- receive_accept_error : 1,
- __reserved_1 : 1,
- send_illegal_vector : 1,
- receive_illegal_vector : 1,
- illegal_register_address : 1,
- __reserved_2 : 24;
- u32 __reserved_3[3];
- } error_bits;
- struct {
- u32 errors;
- u32 __reserved_3[3];
- } all_errors;
- } esr;
-
-/*290*/ struct { u32 __reserved[4]; } __reserved_08;
-
-/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
-
-/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
-
-/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
-
-/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
-
-/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
-
-/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
-
-/*300*/ struct { /* Interrupt Command Register 1 */
- u32 vector : 8,
- delivery_mode : 3,
- destination_mode : 1,
- delivery_status : 1,
- __reserved_1 : 1,
- level : 1,
- trigger : 1,
- __reserved_2 : 2,
- shorthand : 2,
- __reserved_3 : 12;
- u32 __reserved_4[3];
- } icr1;
-
-/*310*/ struct { /* Interrupt Command Register 2 */
- union {
- u32 __reserved_1 : 24,
- phys_dest : 4,
- __reserved_2 : 4;
- u32 __reserved_3 : 24,
- logical_dest : 8;
- } dest;
- u32 __reserved_4[3];
- } icr2;
-
-/*320*/ struct { /* LVT - Timer */
- u32 vector : 8,
- __reserved_1 : 4,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- timer_mode : 1,
- __reserved_3 : 14;
- u32 __reserved_4[3];
- } lvt_timer;
-
-/*330*/ struct { u32 __reserved[4]; } __reserved_15;
-
-/*340*/ struct { /* LVT - Performance Counter */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- __reserved_3 : 15;
- u32 __reserved_4[3];
- } lvt_pc;
-
-/*350*/ struct { /* LVT - LINT0 */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- polarity : 1,
- remote_irr : 1,
- trigger : 1,
- mask : 1,
- __reserved_2 : 15;
- u32 __reserved_3[3];
- } lvt_lint0;
-
-/*360*/ struct { /* LVT - LINT1 */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- polarity : 1,
- remote_irr : 1,
- trigger : 1,
- mask : 1,
- __reserved_2 : 15;
- u32 __reserved_3[3];
- } lvt_lint1;
-
-/*370*/ struct { /* LVT - Error */
- u32 vector : 8,
- __reserved_1 : 4,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- __reserved_3 : 15;
- u32 __reserved_4[3];
- } lvt_error;
-
-/*380*/ struct { /* Timer Initial Count Register */
- u32 initial_count;
- u32 __reserved_2[3];
- } timer_icr;
-
-/*390*/ const
- struct { /* Timer Current Count Register */
- u32 curr_count;
- u32 __reserved_2[3];
- } timer_ccr;
-
-/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
-
-/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
-
-/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
-
-/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
-
-/*3E0*/ struct { /* Timer Divide Configuration Register */
- u32 divisor : 4,
- __reserved_1 : 28;
- u32 __reserved_2[3];
- } timer_dcr;
-
-/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
-
-} __attribute__ ((packed));
-
-#undef u32
-
-#endif
+++ /dev/null
-#ifndef __ARCH_I386_ATOMIC__
-#define __ARCH_I386_ATOMIC__
-
-#include <linux/config.h>
-
-/*
- * Atomic operations that C can't guarantee us. Useful for
- * resource counting etc..
- */
-
-#ifdef CONFIG_SMP
-#define LOCK "lock ; "
-#else
-#define LOCK ""
-#endif
-
-/*
- * Make sure gcc doesn't try to be clever and move things around
- * on us. We need to use _exactly_ the address the user gave us,
- * not some alias that contains the same information.
- */
-typedef struct { volatile int counter; } atomic_t;
-
-#define ATOMIC_INIT(i) { (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-#define atomic_read(v) ((v)->counter)
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-#define atomic_set(v,i) (((v)->counter) = (i))
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v. Note that the guaranteed useful range
- * of an atomic_t is only 24 bits.
- */
-static __inline__ void atomic_add(int i, atomic_t *v)
-{
- __asm__ __volatile__(
- LOCK "addl %1,%0"
- :"=m" (v->counter)
- :"ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ void atomic_sub(int i, atomic_t *v)
-{
- __asm__ __volatile__(
- LOCK "subl %1,%0"
- :"=m" (v->counter)
- :"ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
-{
- unsigned char c;
-
- __asm__ __volatile__(
- LOCK "subl %2,%0; sete %1"
- :"=m" (v->counter), "=qm" (c)
- :"ir" (i), "m" (v->counter) : "memory");
- return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ void atomic_inc(atomic_t *v)
-{
- __asm__ __volatile__(
- LOCK "incl %0"
- :"=m" (v->counter)
- :"m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ void atomic_dec(atomic_t *v)
-{
- __asm__ __volatile__(
- LOCK "decl %0"
- :"=m" (v->counter)
- :"m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ int atomic_dec_and_test(atomic_t *v)
-{
- unsigned char c;
-
- __asm__ __volatile__(
- LOCK "decl %0; sete %1"
- :"=m" (v->counter), "=qm" (c)
- :"m" (v->counter) : "memory");
- return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ int atomic_inc_and_test(atomic_t *v)
-{
- unsigned char c;
-
- __asm__ __volatile__(
- LOCK "incl %0; sete %1"
- :"=m" (v->counter), "=qm" (c)
- :"m" (v->counter) : "memory");
- return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ int atomic_add_negative(int i, atomic_t *v)
-{
- unsigned char c;
-
- __asm__ __volatile__(
- LOCK "addl %2,%0; sets %1"
- :"=m" (v->counter), "=qm" (c)
- :"ir" (i), "m" (v->counter) : "memory");
- return c;
-}
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr) \
-__asm__ __volatile__(LOCK "andl %0,%1" \
-: : "r" (~(mask)),"m" (*addr) : "memory")
-
-#define atomic_set_mask(mask, addr) \
-__asm__ __volatile__(LOCK "orl %0,%1" \
-: : "r" (mask),"m" (*addr) : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
-#endif
+++ /dev/null
-#ifndef _I386_BITOPS_H
-#define _I386_BITOPS_H
-
-/*
- * Copyright 1992, Linus Torvalds.
- */
-
-#include <linux/config.h>
-
-/*
- * These have to be done with inline assembly: that way the bit-setting
- * is guaranteed to be atomic. All bit operations return 0 if the bit
- * was cleared before the operation and != 0 if it was not.
- *
- * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
- */
-
-#ifdef CONFIG_SMP
-#define LOCK_PREFIX "lock ; "
-#else
-#define LOCK_PREFIX ""
-#endif
-
-#define ADDR (*(volatile long *) addr)
-
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered. See __set_bit()
- * if you do not require the atomic guarantees.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static __inline__ void set_bit(int nr, volatile void * addr)
-{
- __asm__ __volatile__( LOCK_PREFIX
- "btsl %1,%0"
- :"=m" (ADDR)
- :"Ir" (nr));
-}
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __inline__ void __set_bit(int nr, volatile void * addr)
-{
- __asm__(
- "btsl %1,%0"
- :"=m" (ADDR)
- :"Ir" (nr));
-}
-
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered. However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
- * in order to ensure changes are visible on other processors.
- */
-static __inline__ void clear_bit(int nr, volatile void * addr)
-{
- __asm__ __volatile__( LOCK_PREFIX
- "btrl %1,%0"
- :"=m" (ADDR)
- :"Ir" (nr));
-}
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __inline__ void __change_bit(int nr, volatile void * addr)
-{
- __asm__ __volatile__(
- "btcl %1,%0"
- :"=m" (ADDR)
- :"Ir" (nr));
-}
-
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static __inline__ void change_bit(int nr, volatile void * addr)
-{
- __asm__ __volatile__( LOCK_PREFIX
- "btcl %1,%0"
- :"=m" (ADDR)
- :"Ir" (nr));
-}
-
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __inline__ int test_and_set_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__ __volatile__( LOCK_PREFIX
- "btsl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit),"=m" (ADDR)
- :"Ir" (nr) : "memory");
- return oldbit;
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail. You must protect multiple accesses with a lock.
- */
-static __inline__ int __test_and_set_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__(
- "btsl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit),"=m" (ADDR)
- :"Ir" (nr));
- return oldbit;
-}
-
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __inline__ int test_and_clear_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__ __volatile__( LOCK_PREFIX
- "btrl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit),"=m" (ADDR)
- :"Ir" (nr) : "memory");
- return oldbit;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail. You must protect multiple accesses with a lock.
- */
-static __inline__ int __test_and_clear_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__(
- "btrl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit),"=m" (ADDR)
- :"Ir" (nr));
- return oldbit;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static __inline__ int __test_and_change_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__ __volatile__(
- "btcl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit),"=m" (ADDR)
- :"Ir" (nr) : "memory");
- return oldbit;
-}
-
-/**
- * test_and_change_bit - Change a bit and return its new value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __inline__ int test_and_change_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__ __volatile__( LOCK_PREFIX
- "btcl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit),"=m" (ADDR)
- :"Ir" (nr) : "memory");
- return oldbit;
-}
-
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static int test_bit(int nr, const volatile void * addr);
-#endif
-
-static __inline__ int constant_test_bit(int nr, const volatile void * addr)
-{
- return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
-}
-
-static __inline__ int variable_test_bit(int nr, volatile void * addr)
-{
- int oldbit;
-
- __asm__ __volatile__(
- "btl %2,%1\n\tsbbl %0,%0"
- :"=r" (oldbit)
- :"m" (ADDR),"Ir" (nr));
- return oldbit;
-}
-
-#define test_bit(nr,addr) \
-(__builtin_constant_p(nr) ? \
- constant_test_bit((nr),(addr)) : \
- variable_test_bit((nr),(addr)))
-
-/**
- * find_first_zero_bit - find the first zero bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit-number of the first zero bit, not the number of the byte
- * containing a bit.
- */
-static __inline__ int find_first_zero_bit(void * addr, unsigned size)
-{
- int d0, d1, d2;
- int res;
-
- if (!size)
- return 0;
- /* This looks at memory. Mark it volatile to tell gcc not to move it around */
- __asm__ __volatile__(
- "movl $-1,%%eax\n\t"
- "xorl %%edx,%%edx\n\t"
- "repe; scasl\n\t"
- "je 1f\n\t"
- "xorl -4(%%edi),%%eax\n\t"
- "subl $4,%%edi\n\t"
- "bsfl %%eax,%%edx\n"
- "1:\tsubl %%ebx,%%edi\n\t"
- "shll $3,%%edi\n\t"
- "addl %%edi,%%edx"
- :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
- :"1" ((size + 31) >> 5), "2" (addr), "b" (addr));
- return res;
-}
-
-/**
- * find_next_zero_bit - find the first zero bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-static __inline__ int find_next_zero_bit (void * addr, int size, int offset)
-{
- unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
- int set = 0, bit = offset & 31, res;
-
- if (bit) {
- /*
- * Look for zero in first byte
- */
- __asm__("bsfl %1,%0\n\t"
- "jne 1f\n\t"
- "movl $32, %0\n"
- "1:"
- : "=r" (set)
- : "r" (~(*p >> bit)));
- if (set < (32 - bit))
- return set + offset;
- set = 32 - bit;
- p++;
- }
- /*
- * No zero yet, search remaining full bytes for a zero
- */
- res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
- return (offset + set + res);
-}
-
-/**
- * ffz - find first zero in word.
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-static __inline__ unsigned long ffz(unsigned long word)
-{
- __asm__("bsfl %1,%0"
- :"=r" (word)
- :"r" (~word));
- return word;
-}
-
-#ifdef __KERNEL__
-
-/**
- * ffs - find first bit set
- * @x: the word to search
- *
- * This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- */
-static __inline__ int ffs(int x)
-{
- int r;
-
- __asm__("bsfl %1,%0\n\t"
- "jnz 1f\n\t"
- "movl $-1,%0\n"
- "1:" : "=r" (r) : "g" (x));
- return r+1;
-}
-
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-#define hweight32(x) generic_hweight32(x)
-#define hweight16(x) generic_hweight16(x)
-#define hweight8(x) generic_hweight8(x)
-
-#endif /* __KERNEL__ */
-
-#ifdef __KERNEL__
-
-#define ext2_set_bit __test_and_set_bit
-#define ext2_clear_bit __test_and_clear_bit
-#define ext2_test_bit test_bit
-#define ext2_find_first_zero_bit find_first_zero_bit
-#define ext2_find_next_zero_bit find_next_zero_bit
-
-/* Bitmap functions for the minix filesystem. */
-#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,addr)
-#define minix_set_bit(nr,addr) __set_bit(nr,addr)
-#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,addr)
-#define minix_test_bit(nr,addr) test_bit(nr,addr)
-#define minix_find_first_zero_bit(addr,size) find_first_zero_bit(addr,size)
-
-#endif /* __KERNEL__ */
-
-#endif /* _I386_BITOPS_H */
+++ /dev/null
-#ifndef _LINUX_BOOT_H
-#define _LINUX_BOOT_H
-
-/* Don't touch these, unless you really know what you're doing. */
-#define DEF_INITSEG 0x9000
-#define DEF_SYSSEG 0x1000
-#define DEF_SETUPSEG 0x9020
-#define DEF_SYSSIZE 0x7F00
-
-/* Internal svga startup constants */
-#define NORMAL_VGA 0xffff /* 80x25 mode */
-#define EXTENDED_VGA 0xfffe /* 80x50 mode */
-#define ASK_VGA 0xfffd /* ask for it at bootup */
-
-#endif
+++ /dev/null
-/*
- * include/asm-i386/bugs.h
- *
- * Copyright (C) 1994 Linus Torvalds
- *
- * Cyrix stuff, June 1998 by:
- * - Rafael R. Reilova (moved everything from head.S),
- * <rreilova@ececs.uc.edu>
- * - Channing Corn (tests & fixes),
- * - Andrew D. Balsa (code cleanup).
- *
- * Pentium III FXSR, SSE support
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- */
-
-#include <linux/config.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/msr.h>
-
-
-static void __init check_fpu(void)
-{
- boot_cpu_data.fdiv_bug = 0;
-}
-
-static void __init check_hlt(void)
-{
- boot_cpu_data.hlt_works_ok = 1;
-}
-
-static void __init check_bugs(void)
-{
- identify_cpu(&boot_cpu_data);
-#ifndef CONFIG_SMP
- printk("CPU: ");
- print_cpu_info(&boot_cpu_data);
-#endif
- check_fpu();
- check_hlt();
- system_utsname.machine[1] = '0' +
- (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
-}
+++ /dev/null
-#ifndef _I386_BYTEORDER_H
-#define _I386_BYTEORDER_H
-
-#include <asm/types.h>
-
-#ifdef __GNUC__
-
-/* For avoiding bswap on i386 */
-#ifdef __KERNEL__
-#include <linux/config.h>
-#endif
-
-static __inline__ __const__ __u32 ___arch__swab32(__u32 x)
-{
-#ifdef CONFIG_X86_BSWAP
- __asm__("bswap %0" : "=r" (x) : "0" (x));
-#else
- __asm__("xchgb %b0,%h0\n\t" /* swap lower bytes */
- "rorl $16,%0\n\t" /* swap words */
- "xchgb %b0,%h0" /* swap higher bytes */
- :"=q" (x)
- : "0" (x));
-#endif
- return x;
-}
-
-static __inline__ __const__ __u16 ___arch__swab16(__u16 x)
-{
- __asm__("xchgb %b0,%h0" /* swap bytes */ \
- : "=q" (x) \
- : "0" (x)); \
- return x;
-}
-
-#define __arch__swab32(x) ___arch__swab32(x)
-#define __arch__swab16(x) ___arch__swab16(x)
-
-#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
-# define __BYTEORDER_HAS_U64__
-# define __SWAB_64_THRU_32__
-#endif
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
-
-#endif /* _I386_BYTEORDER_H */
+++ /dev/null
-/*
- * include/asm-i386/cache.h
- */
-#ifndef __ARCH_I386_CACHE_H
-#define __ARCH_I386_CACHE_H
-
-#include <linux/config.h>
-
-/* L1 cache line size */
-#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT)
-#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
-
-#endif
+++ /dev/null
-#ifndef _I386_CHECKSUM_H
-#define _I386_CHECKSUM_H
-
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-asmlinkage unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum);
-
-/*
- * the same as csum_partial, but copies from src while it
- * checksums, and handles user-space pointer exceptions correctly, when needed.
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-
-asmlinkage unsigned int csum_partial_copy_generic( const char *src, char *dst, int len, int sum,
- int *src_err_ptr, int *dst_err_ptr);
-
-/*
- * Note: when you get a NULL pointer exception here this means someone
- * passed in an incorrect kernel address to one of these functions.
- *
- * If you use these functions directly please don't forget the
- * verify_area().
- */
-static __inline__
-unsigned int csum_partial_copy_nocheck ( const char *src, char *dst,
- int len, int sum)
-{
- return csum_partial_copy_generic ( src, dst, len, sum, NULL, NULL);
-}
-
-static __inline__
-unsigned int csum_partial_copy_from_user ( const char *src, char *dst,
- int len, int sum, int *err_ptr)
-{
- return csum_partial_copy_generic ( src, dst, len, sum, err_ptr, NULL);
-}
-
-/*
- * These are the old (and unsafe) way of doing checksums, a warning message will be
- * printed if they are used and an exeption occurs.
- *
- * these functions should go away after some time.
- */
-
-#define csum_partial_copy_fromuser csum_partial_copy
-unsigned int csum_partial_copy( const char *src, char *dst, int len, int sum);
-
-/*
- * This is a version of ip_compute_csum() optimized for IP headers,
- * which always checksum on 4 octet boundaries.
- *
- * By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
- * Arnt Gulbrandsen.
- */
-static inline unsigned short ip_fast_csum(unsigned char * iph,
- unsigned int ihl) {
- unsigned int sum;
-
- __asm__ __volatile__("
- movl (%1), %0
- subl $4, %2
- jbe 2f
- addl 4(%1), %0
- adcl 8(%1), %0
- adcl 12(%1), %0
-1: adcl 16(%1), %0
- lea 4(%1), %1
- decl %2
- jne 1b
- adcl $0, %0
- movl %0, %2
- shrl $16, %0
- addw %w2, %w0
- adcl $0, %0
- notl %0
-2:
- "
- /* Since the input registers which are loaded with iph and ipl
- are modified, we must also specify them as outputs, or gcc
- will assume they contain their original values. */
- : "=r" (sum), "=r" (iph), "=r" (ihl)
- : "1" (iph), "2" (ihl));
- return(sum);
-}
-
-/*
- * Fold a partial checksum
- */
-
-static inline unsigned int csum_fold(unsigned int sum)
-{
- __asm__("
- addl %1, %0
- adcl $0xffff, %0
- "
- : "=r" (sum)
- : "r" (sum << 16), "0" (sum & 0xffff0000)
- );
- return (~sum) >> 16;
-}
-
-static inline unsigned long csum_tcpudp_nofold(unsigned long saddr,
- unsigned long daddr,
- unsigned short len,
- unsigned short proto,
- unsigned int sum)
-{
- __asm__("
- addl %1, %0
- adcl %2, %0
- adcl %3, %0
- adcl $0, %0
- "
- : "=r" (sum)
- : "g" (daddr), "g"(saddr), "g"((ntohs(len)<<16)+proto*256), "0"(sum));
- return sum;
-}
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-static inline unsigned short int csum_tcpudp_magic(unsigned long saddr,
- unsigned long daddr,
- unsigned short len,
- unsigned short proto,
- unsigned int sum)
-{
- return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
-}
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-
-static inline unsigned short ip_compute_csum(unsigned char * buff, int len) {
- return csum_fold (csum_partial(buff, len, 0));
-}
-
-#define _HAVE_ARCH_IPV6_CSUM
-static __inline__ unsigned short int csum_ipv6_magic(struct in6_addr *saddr,
- struct in6_addr *daddr,
- __u32 len,
- unsigned short proto,
- unsigned int sum)
-{
- __asm__("
- addl 0(%1), %0
- adcl 4(%1), %0
- adcl 8(%1), %0
- adcl 12(%1), %0
- adcl 0(%2), %0
- adcl 4(%2), %0
- adcl 8(%2), %0
- adcl 12(%2), %0
- adcl %3, %0
- adcl %4, %0
- adcl $0, %0
- "
- : "=&r" (sum)
- : "r" (saddr), "r" (daddr),
- "r"(htonl(len)), "r"(htonl(proto)), "0"(sum));
-
- return csum_fold(sum);
-}
-
-/*
- * Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static __inline__ unsigned int csum_and_copy_to_user (const char *src, char *dst,
- int len, int sum, int *err_ptr)
-{
- if (access_ok(VERIFY_WRITE, dst, len))
- return csum_partial_copy_generic(src, dst, len, sum, NULL, err_ptr);
-
- if (len)
- *err_ptr = -EFAULT;
-
- return -1; /* invalid checksum */
-}
-
-#endif
+++ /dev/null
-/*
- * cpufeature.h
- *
- * Defines x86 CPU feature bits
- */
-
-#ifndef __ASM_I386_CPUFEATURE_H
-#define __ASM_I386_CPUFEATURE_H
-
-/* Sample usage: CPU_FEATURE_P(cpu.x86_capability, FPU) */
-#define CPU_FEATURE_P(CAP, FEATURE) test_bit(CAP, X86_FEATURE_##FEATURE ##_BIT)
-
-#define NCAPINTS 4 /* Currently we have 4 32-bit words worth of info */
-
-/* Intel-defined CPU features, CPUID level 0x00000001, word 0 */
-#define X86_FEATURE_FPU (0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME (0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE (0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE (0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
-#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Architecture */
-#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC (0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP (0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR (0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE (0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA (0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
-#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN (0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH (0*32+19) /* Supports the CLFLUSH instruction */
-#define X86_FEATURE_DTES (0*32+21) /* Debug Trace Store */
-#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
- /* of FPU context), and CR4.OSFXSR available */
-#define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */
-#define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */
-#define X86_FEATURE_SELFSNOOP (0*32+27) /* CPU self snoop */
-#define X86_FEATURE_ACC (0*32+29) /* Automatic clock control */
-#define X86_FEATURE_IA64 (0*32+30) /* IA-64 processor */
-
-/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
-/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL (1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW (1*32+31) /* 3DNow! */
-
-/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY (2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN (2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI (2*32+ 3) /* LongRun table interface */
-
-/* Other features, Linux-defined mapping, word 3 */
-/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX (3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR (3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
-
-#endif /* __ASM_I386_CPUFEATURE_H */
-
-/*
- * Local Variables:
- * mode:c
- * comment-column:42
- * End:
- */
+++ /dev/null
-#ifndef _I386_CURRENT_H
-#define _I386_CURRENT_H
-
-struct task_struct;
-
-static inline struct task_struct * get_current(void)
-{
- struct task_struct *current;
- __asm__("andl %%esp,%0; ":"=r" (current) : "0" (~8191UL));
- return current;
- }
-
-#define current get_current()
-
-#endif /* !(_I386_CURRENT_H) */
+++ /dev/null
-#ifndef _I386_DEBUGREG_H
-#define _I386_DEBUGREG_H
-
-
-/* Indicate the register numbers for a number of the specific
- debug registers. Registers 0-3 contain the addresses we wish to trap on */
-#define DR_FIRSTADDR 0 /* u_debugreg[DR_FIRSTADDR] */
-#define DR_LASTADDR 3 /* u_debugreg[DR_LASTADDR] */
-
-#define DR_STATUS 6 /* u_debugreg[DR_STATUS] */
-#define DR_CONTROL 7 /* u_debugreg[DR_CONTROL] */
-
-/* Define a few things for the status register. We can use this to determine
- which debugging register was responsible for the trap. The other bits
- are either reserved or not of interest to us. */
-
-#define DR_TRAP0 (0x1) /* db0 */
-#define DR_TRAP1 (0x2) /* db1 */
-#define DR_TRAP2 (0x4) /* db2 */
-#define DR_TRAP3 (0x8) /* db3 */
-
-#define DR_STEP (0x4000) /* single-step */
-#define DR_SWITCH (0x8000) /* task switch */
-
-/* Now define a bunch of things for manipulating the control register.
- The top two bytes of the control register consist of 4 fields of 4
- bits - each field corresponds to one of the four debug registers,
- and indicates what types of access we trap on, and how large the data
- field is that we are looking at */
-
-#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
-#define DR_CONTROL_SIZE 4 /* 4 control bits per register */
-
-#define DR_RW_EXECUTE (0x0) /* Settings for the access types to trap on */
-#define DR_RW_WRITE (0x1)
-#define DR_RW_READ (0x3)
-
-#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
-#define DR_LEN_2 (0x4)
-#define DR_LEN_4 (0xC)
-
-/* The low byte to the control register determine which registers are
- enabled. There are 4 fields of two bits. One bit is "local", meaning
- that the processor will reset the bit after a task switch and the other
- is global meaning that we have to explicitly reset the bit. With linux,
- you can use either one, since we explicitly zero the register when we enter
- kernel mode. */
-
-#define DR_LOCAL_ENABLE_SHIFT 0 /* Extra shift to the local enable bit */
-#define DR_GLOBAL_ENABLE_SHIFT 1 /* Extra shift to the global enable bit */
-#define DR_ENABLE_SIZE 2 /* 2 enable bits per register */
-
-#define DR_LOCAL_ENABLE_MASK (0x55) /* Set local bits for all 4 regs */
-#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
-
-/* The second byte to the control register has a few special things.
- We can slow the instruction pipeline for instructions coming via the
- gdt or the ldt if we want to. I am not sure why this is an advantage */
-
-#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
-#define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */
-#define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */
-
-#endif
+++ /dev/null
-#ifndef _I386_DELAY_H
-#define _I386_DELAY_H
-
-/*
- * Copyright (C) 1993 Linus Torvalds
- *
- * Delay routines calling functions in arch/i386/lib/delay.c
- */
-
-extern void __bad_udelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __const_udelay(unsigned long usecs);
-extern void __delay(unsigned long loops);
-
-#define udelay(n) (__builtin_constant_p(n) ? \
- ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c6ul)) : \
- __udelay(n))
-
-#endif /* defined(_I386_DELAY_H) */
+++ /dev/null
-#ifndef __ARCH_DESC_H
-#define __ARCH_DESC_H
-
-#include <asm/ldt.h>
-
-#define __LDT(_X) (0)
-
-#define clear_LDT() ((void)0)
-#define load_LDT(_mm) ((void)0)
-
-#endif
+++ /dev/null
-#ifndef __I386_DIV64
-#define __I386_DIV64
-
-#define do_div(n,base) ({ \
- unsigned long __upper, __low, __high, __mod; \
- asm("":"=a" (__low), "=d" (__high):"A" (n)); \
- __upper = __high; \
- if (__high) { \
- __upper = __high % (base); \
- __high = __high / (base); \
- } \
- asm("divl %2":"=a" (__low), "=d" (__mod):"rm" (base), "0" (__low), "1" (__upper)); \
- asm("":"=A" (n):"a" (__low),"d" (__high)); \
- __mod; \
-})
-
-#endif
+++ /dev/null
-/* $Id: dma.h,v 1.7 1992/12/14 00:29:34 root Exp root $
- * linux/include/asm/dma.h: Defines for using and allocating dma channels.
- * Written by Hennus Bergman, 1992.
- * High DMA channel support & info by Hannu Savolainen
- * and John Boyd, Nov. 1992.
- */
-
-#ifndef _ASM_DMA_H
-#define _ASM_DMA_H
-
-#include <linux/config.h>
-#include <linux/spinlock.h> /* And spinlocks */
-#include <asm/io.h> /* need byte IO */
-#include <linux/delay.h>
-
-
-#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
-#define dma_outb outb_p
-#else
-#define dma_outb outb
-#endif
-
-#define dma_inb inb
-
-/*
- * NOTES about DMA transfers:
- *
- * controller 1: channels 0-3, byte operations, ports 00-1F
- * controller 2: channels 4-7, word operations, ports C0-DF
- *
- * - ALL registers are 8 bits only, regardless of transfer size
- * - channel 4 is not used - cascades 1 into 2.
- * - channels 0-3 are byte - addresses/counts are for physical bytes
- * - channels 5-7 are word - addresses/counts are for physical words
- * - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
- * - transfer count loaded to registers is 1 less than actual count
- * - controller 2 offsets are all even (2x offsets for controller 1)
- * - page registers for 5-7 don't use data bit 0, represent 128K pages
- * - page registers for 0-3 use bit 0, represent 64K pages
- *
- * DMA transfers are limited to the lower 16MB of _physical_ memory.
- * Note that addresses loaded into registers must be _physical_ addresses,
- * not logical addresses (which may differ if paging is active).
- *
- * Address mapping for channels 0-3:
- *
- * A23 ... A16 A15 ... A8 A7 ... A0 (Physical addresses)
- * | ... | | ... | | ... |
- * | ... | | ... | | ... |
- * | ... | | ... | | ... |
- * P7 ... P0 A7 ... A0 A7 ... A0
- * | Page | Addr MSB | Addr LSB | (DMA registers)
- *
- * Address mapping for channels 5-7:
- *
- * A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0 (Physical addresses)
- * | ... | \ \ ... \ \ \ ... \ \
- * | ... | \ \ ... \ \ \ ... \ (not used)
- * | ... | \ \ ... \ \ \ ... \
- * P7 ... P1 (0) A7 A6 ... A0 A7 A6 ... A0
- * | Page | Addr MSB | Addr LSB | (DMA registers)
- *
- * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
- * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
- * the hardware level, so odd-byte transfers aren't possible).
- *
- * Transfer count (_not # bytes_) is limited to 64K, represented as actual
- * count - 1 : 64K => 0xFFFF, 1 => 0x0000. Thus, count is always 1 or more,
- * and up to 128K bytes may be transferred on channels 5-7 in one operation.
- *
- */
-
-#define MAX_DMA_CHANNELS 8
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS (PAGE_OFFSET+0x1000000)
-
-/* 8237 DMA controllers */
-#define IO_DMA1_BASE 0x00 /* 8 bit slave DMA, channels 0..3 */
-#define IO_DMA2_BASE 0xC0 /* 16 bit master DMA, ch 4(=slave input)..7 */
-
-/* DMA controller registers */
-#define DMA1_CMD_REG 0x08 /* command register (w) */
-#define DMA1_STAT_REG 0x08 /* status register (r) */
-#define DMA1_REQ_REG 0x09 /* request register (w) */
-#define DMA1_MASK_REG 0x0A /* single-channel mask (w) */
-#define DMA1_MODE_REG 0x0B /* mode register (w) */
-#define DMA1_CLEAR_FF_REG 0x0C /* clear pointer flip-flop (w) */
-#define DMA1_TEMP_REG 0x0D /* Temporary Register (r) */
-#define DMA1_RESET_REG 0x0D /* Master Clear (w) */
-#define DMA1_CLR_MASK_REG 0x0E /* Clear Mask */
-#define DMA1_MASK_ALL_REG 0x0F /* all-channels mask (w) */
-
-#define DMA2_CMD_REG 0xD0 /* command register (w) */
-#define DMA2_STAT_REG 0xD0 /* status register (r) */
-#define DMA2_REQ_REG 0xD2 /* request register (w) */
-#define DMA2_MASK_REG 0xD4 /* single-channel mask (w) */
-#define DMA2_MODE_REG 0xD6 /* mode register (w) */
-#define DMA2_CLEAR_FF_REG 0xD8 /* clear pointer flip-flop (w) */
-#define DMA2_TEMP_REG 0xDA /* Temporary Register (r) */
-#define DMA2_RESET_REG 0xDA /* Master Clear (w) */
-#define DMA2_CLR_MASK_REG 0xDC /* Clear Mask */
-#define DMA2_MASK_ALL_REG 0xDE /* all-channels mask (w) */
-
-#define DMA_ADDR_0 0x00 /* DMA address registers */
-#define DMA_ADDR_1 0x02
-#define DMA_ADDR_2 0x04
-#define DMA_ADDR_3 0x06
-#define DMA_ADDR_4 0xC0
-#define DMA_ADDR_5 0xC4
-#define DMA_ADDR_6 0xC8
-#define DMA_ADDR_7 0xCC
-
-#define DMA_CNT_0 0x01 /* DMA count registers */
-#define DMA_CNT_1 0x03
-#define DMA_CNT_2 0x05
-#define DMA_CNT_3 0x07
-#define DMA_CNT_4 0xC2
-#define DMA_CNT_5 0xC6
-#define DMA_CNT_6 0xCA
-#define DMA_CNT_7 0xCE
-
-#define DMA_PAGE_0 0x87 /* DMA page registers */
-#define DMA_PAGE_1 0x83
-#define DMA_PAGE_2 0x81
-#define DMA_PAGE_3 0x82
-#define DMA_PAGE_5 0x8B
-#define DMA_PAGE_6 0x89
-#define DMA_PAGE_7 0x8A
-
-#define DMA_MODE_READ 0x44 /* I/O to memory, no autoinit, increment, single mode */
-#define DMA_MODE_WRITE 0x48 /* memory to I/O, no autoinit, increment, single mode */
-#define DMA_MODE_CASCADE 0xC0 /* pass thru DREQ->HRQ, DACK<-HLDA only */
-
-#define DMA_AUTOINIT 0x10
-
-
-extern spinlock_t dma_spin_lock;
-
-static __inline__ unsigned long claim_dma_lock(void)
-{
- unsigned long flags;
- spin_lock_irqsave(&dma_spin_lock, flags);
- return flags;
-}
-
-static __inline__ void release_dma_lock(unsigned long flags)
-{
- spin_unlock_irqrestore(&dma_spin_lock, flags);
-}
-
-/* enable/disable a specific DMA channel */
-static __inline__ void enable_dma(unsigned int dmanr)
-{
- if (dmanr<=3)
- dma_outb(dmanr, DMA1_MASK_REG);
- else
- dma_outb(dmanr & 3, DMA2_MASK_REG);
-}
-
-static __inline__ void disable_dma(unsigned int dmanr)
-{
- if (dmanr<=3)
- dma_outb(dmanr | 4, DMA1_MASK_REG);
- else
- dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
-}
-
-/* Clear the 'DMA Pointer Flip Flop'.
- * Write 0 for LSB/MSB, 1 for MSB/LSB access.
- * Use this once to initialize the FF to a known state.
- * After that, keep track of it. :-)
- * --- In order to do that, the DMA routines below should ---
- * --- only be used while holding the DMA lock ! ---
- */
-static __inline__ void clear_dma_ff(unsigned int dmanr)
-{
- if (dmanr<=3)
- dma_outb(0, DMA1_CLEAR_FF_REG);
- else
- dma_outb(0, DMA2_CLEAR_FF_REG);
-}
-
-/* set mode (above) for a specific DMA channel */
-static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
-{
- if (dmanr<=3)
- dma_outb(mode | dmanr, DMA1_MODE_REG);
- else
- dma_outb(mode | (dmanr&3), DMA2_MODE_REG);
-}
-
-/* Set only the page register bits of the transfer address.
- * This is used for successive transfers when we know the contents of
- * the lower 16 bits of the DMA current address register, but a 64k boundary
- * may have been crossed.
- */
-static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
-{
- switch(dmanr) {
- case 0:
- dma_outb(pagenr, DMA_PAGE_0);
- break;
- case 1:
- dma_outb(pagenr, DMA_PAGE_1);
- break;
- case 2:
- dma_outb(pagenr, DMA_PAGE_2);
- break;
- case 3:
- dma_outb(pagenr, DMA_PAGE_3);
- break;
- case 5:
- dma_outb(pagenr & 0xfe, DMA_PAGE_5);
- break;
- case 6:
- dma_outb(pagenr & 0xfe, DMA_PAGE_6);
- break;
- case 7:
- dma_outb(pagenr & 0xfe, DMA_PAGE_7);
- break;
- }
-}
-
-
-/* Set transfer address & page bits for specific DMA channel.
- * Assumes dma flipflop is clear.
- */
-static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
-{
- set_dma_page(dmanr, a>>16);
- if (dmanr <= 3) {
- dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
- dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
- } else {
- dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
- dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
- }
-}
-
-
-/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
- * a specific DMA channel.
- * You must ensure the parameters are valid.
- * NOTE: from a manual: "the number of transfers is one more
- * than the initial word count"! This is taken into account.
- * Assumes dma flip-flop is clear.
- * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
- */
-static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
-{
- count--;
- if (dmanr <= 3) {
- dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
- dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
- } else {
- dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
- dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
- }
-}
-
-
-/* Get DMA residue count. After a DMA transfer, this
- * should return zero. Reading this while a DMA transfer is
- * still in progress will return unpredictable results.
- * If called before the channel has been used, it may return 1.
- * Otherwise, it returns the number of _bytes_ left to transfer.
- *
- * Assumes DMA flip-flop is clear.
- */
-static __inline__ int get_dma_residue(unsigned int dmanr)
-{
- unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
- : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
-
- /* using short to get 16-bit wrap around */
- unsigned short count;
-
- count = 1 + dma_inb(io_port);
- count += dma_inb(io_port) << 8;
-
- return (dmanr<=3)? count : (count<<1);
-}
-
-
-/* These are in kernel/dma.c: */
-extern int request_dma(unsigned int dmanr, const char * device_id); /* reserve a DMA channel */
-extern void free_dma(unsigned int dmanr); /* release it again */
-
-/* From PCI */
-
-#ifdef CONFIG_PCI
-extern int isa_dma_bridge_buggy;
-#else
-#define isa_dma_bridge_buggy (0)
-#endif
-
-#endif /* _ASM_DMA_H */
+++ /dev/null
-#ifndef __ASMi386_ELF_H
-#define __ASMi386_ELF_H
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-
-#include <linux/utsname.h>
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-typedef struct user_fxsr_struct elf_fpxregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) \
- (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS ELFCLASS32
-#define ELF_DATA ELFDATA2LSB
-#define ELF_ARCH EM_386
-
-/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
- contains a pointer to a function which might be registered using `atexit'.
- This provides a mean for the dynamic linker to call DT_FINI functions for
- shared libraries that have been loaded before the code runs.
-
- A value of 0 tells we have no such handler.
-
- We might as well make sure everything else is cleared too (except for %esp),
- just to make things more deterministic.
- */
-#define ELF_PLAT_INIT(_r) do { \
- _r->ebx = 0; _r->ecx = 0; _r->edx = 0; \
- _r->esi = 0; _r->edi = 0; _r->ebp = 0; \
- _r->eax = 0; \
-} while (0)
-
-#define USE_ELF_CORE_DUMP
-#define ELF_EXEC_PAGESIZE 4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. */
-
-#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
-
-/* Wow, the "main" arch needs arch dependent functions too.. :) */
-
-/* regs is struct pt_regs, pr_reg is elf_gregset_t (which is
- now struct_user_regs, they are different) */
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs) \
- pr_reg[0] = regs->ebx; \
- pr_reg[1] = regs->ecx; \
- pr_reg[2] = regs->edx; \
- pr_reg[3] = regs->esi; \
- pr_reg[4] = regs->edi; \
- pr_reg[5] = regs->ebp; \
- pr_reg[6] = regs->eax; \
- pr_reg[7] = regs->xds; \
- pr_reg[8] = regs->xes; \
- /* fake once used fs and gs selectors? */ \
- pr_reg[9] = regs->xds; /* was fs and __fs */ \
- pr_reg[10] = regs->xds; /* was gs and __gs */ \
- pr_reg[11] = regs->orig_eax; \
- pr_reg[12] = regs->eip; \
- pr_reg[13] = regs->xcs; \
- pr_reg[14] = regs->eflags; \
- pr_reg[15] = regs->esp; \
- pr_reg[16] = regs->xss;
-
-/* This yields a mask that user programs can use to figure out what
- instruction set this CPU supports. This could be done in user space,
- but it's not easy, and we've already done it here. */
-
-#define ELF_HWCAP (boot_cpu_data.x86_capability[0])
-
-/* This yields a string that ld.so will use to load implementation
- specific libraries for optimization. This is more specific in
- intent than poking at uname or /proc/cpuinfo.
-
- For the moment, we have only optimizations for the Intel generations,
- but that could change... */
-
-#define ELF_PLATFORM (system_utsname.machine)
-
-#ifdef __KERNEL__
-#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX)
-#endif
-
-#endif
+++ /dev/null
-#ifndef _I386_ERRNO_H
-#define _I386_ERRNO_H
-
-#define EPERM 1 /* Operation not permitted */
-#define ENOENT 2 /* No such file or directory */
-#define ESRCH 3 /* No such process */
-#define EINTR 4 /* Interrupted system call */
-#define EIO 5 /* I/O error */
-#define ENXIO 6 /* No such device or address */
-#define E2BIG 7 /* Arg list too long */
-#define ENOEXEC 8 /* Exec format error */
-#define EBADF 9 /* Bad file number */
-#define ECHILD 10 /* No child processes */
-#define EAGAIN 11 /* Try again */
-#define ENOMEM 12 /* Out of memory */
-#define EACCES 13 /* Permission denied */
-#define EFAULT 14 /* Bad address */
-#define ENOTBLK 15 /* Block device required */
-#define EBUSY 16 /* Device or resource busy */
-#define EEXIST 17 /* File exists */
-#define EXDEV 18 /* Cross-device link */
-#define ENODEV 19 /* No such device */
-#define ENOTDIR 20 /* Not a directory */
-#define EISDIR 21 /* Is a directory */
-#define EINVAL 22 /* Invalid argument */
-#define ENFILE 23 /* File table overflow */
-#define EMFILE 24 /* Too many open files */
-#define ENOTTY 25 /* Not a typewriter */
-#define ETXTBSY 26 /* Text file busy */
-#define EFBIG 27 /* File too large */
-#define ENOSPC 28 /* No space left on device */
-#define ESPIPE 29 /* Illegal seek */
-#define EROFS 30 /* Read-only file system */
-#define EMLINK 31 /* Too many links */
-#define EPIPE 32 /* Broken pipe */
-#define EDOM 33 /* Math argument out of domain of func */
-#define ERANGE 34 /* Math result not representable */
-#define EDEADLK 35 /* Resource deadlock would occur */
-#define ENAMETOOLONG 36 /* File name too long */
-#define ENOLCK 37 /* No record locks available */
-#define ENOSYS 38 /* Function not implemented */
-#define ENOTEMPTY 39 /* Directory not empty */
-#define ELOOP 40 /* Too many symbolic links encountered */
-#define EWOULDBLOCK EAGAIN /* Operation would block */
-#define ENOMSG 42 /* No message of desired type */
-#define EIDRM 43 /* Identifier removed */
-#define ECHRNG 44 /* Channel number out of range */
-#define EL2NSYNC 45 /* Level 2 not synchronized */
-#define EL3HLT 46 /* Level 3 halted */
-#define EL3RST 47 /* Level 3 reset */
-#define ELNRNG 48 /* Link number out of range */
-#define EUNATCH 49 /* Protocol driver not attached */
-#define ENOCSI 50 /* No CSI structure available */
-#define EL2HLT 51 /* Level 2 halted */
-#define EBADE 52 /* Invalid exchange */
-#define EBADR 53 /* Invalid request descriptor */
-#define EXFULL 54 /* Exchange full */
-#define ENOANO 55 /* No anode */
-#define EBADRQC 56 /* Invalid request code */
-#define EBADSLT 57 /* Invalid slot */
-
-#define EDEADLOCK EDEADLK
-
-#define EBFONT 59 /* Bad font file format */
-#define ENOSTR 60 /* Device not a stream */
-#define ENODATA 61 /* No data available */
-#define ETIME 62 /* Timer expired */
-#define ENOSR 63 /* Out of streams resources */
-#define ENONET 64 /* Machine is not on the network */
-#define ENOPKG 65 /* Package not installed */
-#define EREMOTE 66 /* Object is remote */
-#define ENOLINK 67 /* Link has been severed */
-#define EADV 68 /* Advertise error */
-#define ESRMNT 69 /* Srmount error */
-#define ECOMM 70 /* Communication error on send */
-#define EPROTO 71 /* Protocol error */
-#define EMULTIHOP 72 /* Multihop attempted */
-#define EDOTDOT 73 /* RFS specific error */
-#define EBADMSG 74 /* Not a data message */
-#define EOVERFLOW 75 /* Value too large for defined data type */
-#define ENOTUNIQ 76 /* Name not unique on network */
-#define EBADFD 77 /* File descriptor in bad state */
-#define EREMCHG 78 /* Remote address changed */
-#define ELIBACC 79 /* Can not access a needed shared library */
-#define ELIBBAD 80 /* Accessing a corrupted shared library */
-#define ELIBSCN 81 /* .lib section in a.out corrupted */
-#define ELIBMAX 82 /* Attempting to link in too many shared libraries */
-#define ELIBEXEC 83 /* Cannot exec a shared library directly */
-#define EILSEQ 84 /* Illegal byte sequence */
-#define ERESTART 85 /* Interrupted system call should be restarted */
-#define ESTRPIPE 86 /* Streams pipe error */
-#define EUSERS 87 /* Too many users */
-#define ENOTSOCK 88 /* Socket operation on non-socket */
-#define EDESTADDRREQ 89 /* Destination address required */
-#define EMSGSIZE 90 /* Message too long */
-#define EPROTOTYPE 91 /* Protocol wrong type for socket */
-#define ENOPROTOOPT 92 /* Protocol not available */
-#define EPROTONOSUPPORT 93 /* Protocol not supported */
-#define ESOCKTNOSUPPORT 94 /* Socket type not supported */
-#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */
-#define EPFNOSUPPORT 96 /* Protocol family not supported */
-#define EAFNOSUPPORT 97 /* Address family not supported by protocol */
-#define EADDRINUSE 98 /* Address already in use */
-#define EADDRNOTAVAIL 99 /* Cannot assign requested address */
-#define ENETDOWN 100 /* Network is down */
-#define ENETUNREACH 101 /* Network is unreachable */
-#define ENETRESET 102 /* Network dropped connection because of reset */
-#define ECONNABORTED 103 /* Software caused connection abort */
-#define ECONNRESET 104 /* Connection reset by peer */
-#define ENOBUFS 105 /* No buffer space available */
-#define EISCONN 106 /* Transport endpoint is already connected */
-#define ENOTCONN 107 /* Transport endpoint is not connected */
-#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */
-#define ETOOMANYREFS 109 /* Too many references: cannot splice */
-#define ETIMEDOUT 110 /* Connection timed out */
-#define ECONNREFUSED 111 /* Connection refused */
-#define EHOSTDOWN 112 /* Host is down */
-#define EHOSTUNREACH 113 /* No route to host */
-#define EALREADY 114 /* Operation already in progress */
-#define EINPROGRESS 115 /* Operation now in progress */
-#define ESTALE 116 /* Stale NFS file handle */
-#define EUCLEAN 117 /* Structure needs cleaning */
-#define ENOTNAM 118 /* Not a XENIX named type file */
-#define ENAVAIL 119 /* No XENIX semaphores available */
-#define EISNAM 120 /* Is a named type file */
-#define EREMOTEIO 121 /* Remote I/O error */
-#define EDQUOT 122 /* Quota exceeded */
-
-#define ENOMEDIUM 123 /* No medium found */
-#define EMEDIUMTYPE 124 /* Wrong medium type */
-
-#endif
+++ /dev/null
-#ifndef _I386_FCNTL_H
-#define _I386_FCNTL_H
-
-/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
- located on an ext2 file system */
-#define O_ACCMODE 0003
-#define O_RDONLY 00
-#define O_WRONLY 01
-#define O_RDWR 02
-#define O_CREAT 0100 /* not fcntl */
-#define O_EXCL 0200 /* not fcntl */
-#define O_NOCTTY 0400 /* not fcntl */
-#define O_TRUNC 01000 /* not fcntl */
-#define O_APPEND 02000
-#define O_NONBLOCK 04000
-#define O_NDELAY O_NONBLOCK
-#define O_SYNC 010000
-#define FASYNC 020000 /* fcntl, for BSD compatibility */
-#define O_DIRECT 040000 /* direct disk access hint */
-#define O_LARGEFILE 0100000
-#define O_DIRECTORY 0200000 /* must be a directory */
-#define O_NOFOLLOW 0400000 /* don't follow links */
-
-#define F_DUPFD 0 /* dup */
-#define F_GETFD 1 /* get close_on_exec */
-#define F_SETFD 2 /* set/clear close_on_exec */
-#define F_GETFL 3 /* get file->f_flags */
-#define F_SETFL 4 /* set file->f_flags */
-#define F_GETLK 5
-#define F_SETLK 6
-#define F_SETLKW 7
-
-#define F_SETOWN 8 /* for sockets. */
-#define F_GETOWN 9 /* for sockets. */
-#define F_SETSIG 10 /* for sockets. */
-#define F_GETSIG 11 /* for sockets. */
-
-#define F_GETLK64 12 /* using 'struct flock64' */
-#define F_SETLK64 13
-#define F_SETLKW64 14
-
-/* for F_[GET|SET]FL */
-#define FD_CLOEXEC 1 /* actually anything with low bit set goes */
-
-/* for posix fcntl() and lockf() */
-#define F_RDLCK 0
-#define F_WRLCK 1
-#define F_UNLCK 2
-
-/* for old implementation of bsd flock () */
-#define F_EXLCK 4 /* or 3 */
-#define F_SHLCK 8 /* or 4 */
-
-/* for leases */
-#define F_INPROGRESS 16
-
-/* operations for bsd flock(), also used by the kernel implementation */
-#define LOCK_SH 1 /* shared lock */
-#define LOCK_EX 2 /* exclusive lock */
-#define LOCK_NB 4 /* or'd with one of the above to prevent
- blocking */
-#define LOCK_UN 8 /* remove lock */
-
-#define LOCK_MAND 32 /* This is a mandatory flock */
-#define LOCK_READ 64 /* ... Which allows concurrent read operations */
-#define LOCK_WRITE 128 /* ... Which allows concurrent write operations */
-#define LOCK_RW 192 /* ... Which allows concurrent read & write ops */
-
-struct flock {
- short l_type;
- short l_whence;
- off_t l_start;
- off_t l_len;
- pid_t l_pid;
-};
-
-struct flock64 {
- short l_type;
- short l_whence;
- loff_t l_start;
- loff_t l_len;
- pid_t l_pid;
-};
-
-#define F_LINUX_SPECIFIC_BASE 1024
-
-#endif
+++ /dev/null
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- *
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- */
-
-#ifndef _ASM_FIXMAP_H
-#define _ASM_FIXMAP_H
-
-#include <linux/config.h>
-#include <linux/kernel.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process. We allocate these special addresses
- * from the end of virtual memory (0xfffff000) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-enum fixed_addresses {
- FIX_BLKRING_BASE,
- __end_of_fixed_addresses
-};
-
-extern void __set_fixmap (enum fixed_addresses idx,
- unsigned long phys, pgprot_t flags);
-
-#define set_fixmap(idx, phys) \
- __set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys) \
- __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-/*
- * used by vmalloc.c.
- *
- * Leave one empty page between vmalloc'ed areas and
- * the start of the fixmap, and leave one page empty
- * at the top of mem..
- */
-#define FIXADDR_TOP (HYPERVISOR_VIRT_START - 2*PAGE_SIZE)
-#define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE)
-
-#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without tranlation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static inline unsigned long fix_to_virt(const unsigned int idx)
-{
- /*
- * this branch gets completely eliminated after inlining,
- * except when someone tries to use fixaddr indices in an
- * illegal way. (such as mixing up address types or using
- * out-of-range indices).
- *
- * If it doesn't get removed, the linker will complain
- * loudly with a reasonably clear error message..
- */
- if (idx >= __end_of_fixed_addresses)
- __this_fixmap_does_not_exist();
-
- return __fix_to_virt(idx);
-}
-
-#endif
+++ /dev/null
-/*
- * Architecture specific parts of the Floppy driver
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1995
- */
-#ifndef __ASM_I386_FLOPPY_H
-#define __ASM_I386_FLOPPY_H
-
-#include <linux/vmalloc.h>
-
-
-/*
- * The DMA channel used by the floppy controller cannot access data at
- * addresses >= 16MB
- *
- * Went back to the 1MB limit, as some people had problems with the floppy
- * driver otherwise. It doesn't matter much for performance anyway, as most
- * floppy accesses go through the track buffer.
- */
-#define _CROSS_64KB(a,s,vdma) \
-(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
-
-#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
-
-
-#define SW fd_routine[use_virtual_dma&1]
-#define CSW fd_routine[can_use_virtual_dma & 1]
-
-
-#define fd_inb(port) inb_p(port)
-#define fd_outb(port,value) outb_p(port,value)
-
-#define fd_request_dma() CSW._request_dma(FLOPPY_DMA,"floppy")
-#define fd_free_dma() CSW._free_dma(FLOPPY_DMA)
-#define fd_enable_irq() enable_irq(FLOPPY_IRQ)
-#define fd_disable_irq() disable_irq(FLOPPY_IRQ)
-#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL)
-#define fd_get_dma_residue() SW._get_dma_residue(FLOPPY_DMA)
-#define fd_dma_mem_alloc(size) SW._dma_mem_alloc(size)
-#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
-
-#define FLOPPY_CAN_FALLBACK_ON_NODMA
-
-static int virtual_dma_count;
-static int virtual_dma_residue;
-static char *virtual_dma_addr;
-static int virtual_dma_mode;
-static int doing_pdma;
-
-static void floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
-{
- register unsigned char st;
-
-#undef TRACE_FLPY_INT
-#define NO_FLOPPY_ASSEMBLER
-
-#ifdef TRACE_FLPY_INT
- static int calls=0;
- static int bytes=0;
- static int dma_wait=0;
-#endif
- if(!doing_pdma) {
- floppy_interrupt(irq, dev_id, regs);
- return;
- }
-
-#ifdef TRACE_FLPY_INT
- if(!calls)
- bytes = virtual_dma_count;
-#endif
-
-#ifndef NO_FLOPPY_ASSEMBLER
- __asm__ (
- "testl %1,%1
- je 3f
-1: inb %w4,%b0
- andb $160,%b0
- cmpb $160,%b0
- jne 2f
- incw %w4
- testl %3,%3
- jne 4f
- inb %w4,%b0
- movb %0,(%2)
- jmp 5f
-4: movb (%2),%0
- outb %b0,%w4
-5: decw %w4
- outb %0,$0x80
- decl %1
- incl %2
- testl %1,%1
- jne 1b
-3: inb %w4,%b0
-2: "
- : "=a" ((char) st),
- "=c" ((long) virtual_dma_count),
- "=S" ((long) virtual_dma_addr)
- : "b" ((long) virtual_dma_mode),
- "d" ((short) virtual_dma_port+4),
- "1" ((long) virtual_dma_count),
- "2" ((long) virtual_dma_addr));
-#else
- {
- register int lcount;
- register char *lptr;
-
- st = 1;
- for(lcount=virtual_dma_count, lptr=virtual_dma_addr;
- lcount; lcount--, lptr++) {
- st=inb(virtual_dma_port+4) & 0xa0 ;
- if(st != 0xa0)
- break;
- if(virtual_dma_mode)
- outb_p(*lptr, virtual_dma_port+5);
- else
- *lptr = inb_p(virtual_dma_port+5);
- }
- virtual_dma_count = lcount;
- virtual_dma_addr = lptr;
- st = inb(virtual_dma_port+4);
- }
-#endif
-
-#ifdef TRACE_FLPY_INT
- calls++;
-#endif
- if(st == 0x20)
- return;
- if(!(st & 0x20)) {
- virtual_dma_residue += virtual_dma_count;
- virtual_dma_count=0;
-#ifdef TRACE_FLPY_INT
- printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
- virtual_dma_count, virtual_dma_residue, calls, bytes,
- dma_wait);
- calls = 0;
- dma_wait=0;
-#endif
- doing_pdma = 0;
- floppy_interrupt(irq, dev_id, regs);
- return;
- }
-#ifdef TRACE_FLPY_INT
- if(!virtual_dma_count)
- dma_wait++;
-#endif
-}
-
-static void fd_disable_dma(void)
-{
- if(! (can_use_virtual_dma & 1))
- disable_dma(FLOPPY_DMA);
- doing_pdma = 0;
- virtual_dma_residue += virtual_dma_count;
- virtual_dma_count=0;
-}
-
-static int vdma_request_dma(unsigned int dmanr, const char * device_id)
-{
- return 0;
-}
-
-static void vdma_nop(unsigned int dummy)
-{
-}
-
-
-static int vdma_get_dma_residue(unsigned int dummy)
-{
- return virtual_dma_count + virtual_dma_residue;
-}
-
-
-static int fd_request_irq(void)
-{
- if(can_use_virtual_dma)
- return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT,
- "floppy", NULL);
- else
- return request_irq(FLOPPY_IRQ, floppy_interrupt,
- SA_INTERRUPT|SA_SAMPLE_RANDOM,
- "floppy", NULL);
-
-}
-
-static unsigned long dma_mem_alloc(unsigned long size)
-{
- return __get_dma_pages(GFP_KERNEL,get_order(size));
-}
-
-
-static unsigned long vdma_mem_alloc(unsigned long size)
-{
- return (unsigned long) vmalloc(size);
-
-}
-
-#define nodma_mem_alloc(size) vdma_mem_alloc(size)
-
-static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
-{
- if((unsigned int) addr >= (unsigned int) high_memory)
- return vfree((void *)addr);
- else
- free_pages(addr, get_order(size));
-}
-
-#define fd_dma_mem_free(addr, size) _fd_dma_mem_free(addr, size)
-
-static void _fd_chose_dma_mode(char *addr, unsigned long size)
-{
- if(can_use_virtual_dma == 2) {
- if((unsigned int) addr >= (unsigned int) high_memory ||
- virt_to_bus(addr) >= 0x1000000 ||
- _CROSS_64KB(addr, size, 0))
- use_virtual_dma = 1;
- else
- use_virtual_dma = 0;
- } else {
- use_virtual_dma = can_use_virtual_dma & 1;
- }
-}
-
-#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
-
-
-static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
- doing_pdma = 1;
- virtual_dma_port = io;
- virtual_dma_mode = (mode == DMA_MODE_WRITE);
- virtual_dma_addr = addr;
- virtual_dma_count = size;
- virtual_dma_residue = 0;
- return 0;
-}
-
-static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-#ifdef FLOPPY_SANITY_CHECK
- if (CROSS_64KB(addr, size)) {
- printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
- return -1;
- }
-#endif
- /* actual, physical DMA */
- doing_pdma = 0;
- clear_dma_ff(FLOPPY_DMA);
- set_dma_mode(FLOPPY_DMA,mode);
- set_dma_addr(FLOPPY_DMA,virt_to_bus(addr));
- set_dma_count(FLOPPY_DMA,size);
- enable_dma(FLOPPY_DMA);
- return 0;
-}
-
-struct fd_routine_l {
- int (*_request_dma)(unsigned int dmanr, const char * device_id);
- void (*_free_dma)(unsigned int dmanr);
- int (*_get_dma_residue)(unsigned int dummy);
- unsigned long (*_dma_mem_alloc) (unsigned long size);
- int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
-} fd_routine[] = {
- {
- request_dma,
- free_dma,
- get_dma_residue,
- dma_mem_alloc,
- hard_dma_setup
- },
- {
- vdma_request_dma,
- vdma_nop,
- vdma_get_dma_residue,
- vdma_mem_alloc,
- vdma_dma_setup
- }
-};
-
-
-static int FDC1 = 0x3f0;
-static int FDC2 = -1;
-
-/*
- * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
- * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
- * coincides with another rtc CMOS user. Paul G.
- */
-#define FLOPPY0_TYPE ({ \
- unsigned long flags; \
- unsigned char val; \
- spin_lock_irqsave(&rtc_lock, flags); \
- val = (CMOS_READ(0x10) >> 4) & 15; \
- spin_unlock_irqrestore(&rtc_lock, flags); \
- val; \
-})
-
-#define FLOPPY1_TYPE ({ \
- unsigned long flags; \
- unsigned char val; \
- spin_lock_irqsave(&rtc_lock, flags); \
- val = CMOS_READ(0x10) & 15; \
- spin_unlock_irqrestore(&rtc_lock, flags); \
- val; \
-})
-
-#define N_FDC 2
-#define N_DRIVE 8
-
-#define FLOPPY_MOTOR_MASK 0xf0
-
-#define AUTO_DMA
-
-#define EXTRA_FLOPPY_PARAMS
-
-#endif /* __ASM_I386_FLOPPY_H */
+++ /dev/null
-#ifndef __ASM_HARDIRQ_H
-#define __ASM_HARDIRQ_H
-
-#include <linux/config.h>
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-/* assembly code in softirq.h is sensitive to the offsets of these fields */
-typedef struct {
- unsigned int __softirq_pending;
- unsigned int __local_irq_count;
- unsigned int __local_bh_count;
- unsigned int __syscall_count;
- struct task_struct * __ksoftirqd_task; /* waitqueue is too large */
- unsigned int __nmi_count; /* arch dependent */
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */
-
-/*
- * Are we in an interrupt context? Either doing bottom half
- * or hardware interrupt processing?
- */
-#define in_interrupt() ({ int __cpu = smp_processor_id(); \
- (local_irq_count(__cpu) + local_bh_count(__cpu) != 0); })
-
-#define in_irq() (local_irq_count(smp_processor_id()) != 0)
-
-#ifndef CONFIG_SMP
-
-#define hardirq_trylock(cpu) (local_irq_count(cpu) == 0)
-#define hardirq_endlock(cpu) do { } while (0)
-
-#define irq_enter(cpu, irq) (local_irq_count(cpu)++)
-#define irq_exit(cpu, irq) (local_irq_count(cpu)--)
-
-#define synchronize_irq() barrier()
-
-#else
-
-#include <asm/atomic.h>
-#include <asm/smp.h>
-
-extern unsigned char global_irq_holder;
-extern unsigned volatile long global_irq_lock; /* long for set_bit -RR */
-
-static inline int irqs_running (void)
-{
- int i;
-
- for (i = 0; i < smp_num_cpus; i++)
- if (local_irq_count(i))
- return 1;
- return 0;
-}
-
-static inline void release_irqlock(int cpu)
-{
- /* if we didn't own the irq lock, just ignore.. */
- if (global_irq_holder == (unsigned char) cpu) {
- global_irq_holder = NO_PROC_ID;
- clear_bit(0,&global_irq_lock);
- }
-}
-
-static inline void irq_enter(int cpu, int irq)
-{
- ++local_irq_count(cpu);
-
- while (test_bit(0,&global_irq_lock)) {
- cpu_relax();
- }
-}
-
-static inline void irq_exit(int cpu, int irq)
-{
- --local_irq_count(cpu);
-}
-
-static inline int hardirq_trylock(int cpu)
-{
- return !local_irq_count(cpu) && !test_bit(0,&global_irq_lock);
-}
-
-#define hardirq_endlock(cpu) do { } while (0)
-
-extern void synchronize_irq(void);
-
-#endif /* CONFIG_SMP */
-
-#endif /* __ASM_HARDIRQ_H */
+++ /dev/null
-/*
- * linux/include/asm-i386/hdreg.h
- *
- * Copyright (C) 1994-1996 Linus Torvalds & authors
- */
-
-#ifndef __ASMi386_HDREG_H
-#define __ASMi386_HDREG_H
-
-typedef unsigned short ide_ioreg_t;
-
-#endif /* __ASMi386_HDREG_H */
+++ /dev/null
-
-#error "Highmem unsupported!"
+++ /dev/null
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- * linux/include/asm/hw_irq.h
- *
- * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- */
-
-#include <linux/config.h>
-#include <linux/smp.h>
-#include <asm/atomic.h>
-#include <asm/irq.h>
-
-#define SYSCALL_VECTOR 0x80
-#define KDBENTER_VECTOR 0x81
-
-extern int irq_vector[NR_IRQS];
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-extern char _stext, _etext;
-
-extern unsigned long prof_cpu_mask;
-extern unsigned int * prof_buffer;
-extern unsigned long prof_len;
-extern unsigned long prof_shift;
-
-/*
- * x86 profiling function, SMP safe. We might want to do this in
- * assembly totally?
- */
-static inline void x86_do_profile (unsigned long eip)
-{
- if (!prof_buffer)
- return;
-
- /*
- * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
- * (default is all CPUs.)
- */
- if (!((1<<smp_processor_id()) & prof_cpu_mask))
- return;
-
- eip -= (unsigned long) &_stext;
- eip >>= prof_shift;
- /*
- * Don't ignore out-of-bounds EIP values silently,
- * put them into the last histogram slot, so if
- * present, they will show up as a sharp peak.
- */
- if (eip > prof_len-1)
- eip = prof_len-1;
- atomic_inc((atomic_t *)&prof_buffer[eip]);
-}
-
-static inline void hw_resend_irq(struct hw_interrupt_type *h,
- unsigned int i)
-{}
-
-#endif /* _ASM_HW_IRQ_H */
+++ /dev/null
-/******************************************************************************
- * hypervisor.h
- *
- * Linux-specific hypervisor handling.
- *
- * Copyright (c) 2002, K A Fraser
- */
-
-#ifndef __HYPERVISOR_H__
-#define __HYPERVISOR_H__
-
-#include <asm/hypervisor-ifs/hypervisor-if.h>
-#include <asm/ptrace.h>
-
-/* arch/xeno/kernel/setup.c */
-union start_info_union
-{
- start_info_t start_info;
- char padding[512];
-};
-extern union start_info_union start_info_union;
-#define start_info (start_info_union.start_info)
-
-/* arch/xeno/kernel/hypervisor.c */
-void do_hypervisor_callback(struct pt_regs *regs);
-
-
-/* arch/xeno/mm/hypervisor.c */
-/*
- * NB. ptr values should be PHYSICAL, not MACHINE. 'vals' should be already
- * be MACHINE addresses.
- */
-
-extern unsigned int pt_update_queue_idx;
-
-void queue_l1_entry_update(unsigned long ptr, unsigned long val);
-void queue_l2_entry_update(unsigned long ptr, unsigned long val);
-void queue_pt_switch(unsigned long ptr);
-void queue_tlb_flush(void);
-void queue_invlpg(unsigned long ptr);
-void queue_pgd_pin(unsigned long ptr);
-void queue_pgd_unpin(unsigned long ptr);
-void queue_pte_pin(unsigned long ptr);
-void queue_pte_unpin(unsigned long ptr);
-
-#define PT_UPDATE_DEBUG 0
-
-#if PT_UPDATE_DEBUG > 0
-typedef struct {
- unsigned long ptr, val, pteval;
- void *ptep;
- int line; char *file;
-} page_update_debug_t;
-extern page_update_debug_t update_debug_queue[];
-#define queue_l1_entry_update(_p,_v) ({ \
- update_debug_queue[pt_update_queue_idx].ptr = (_p); \
- update_debug_queue[pt_update_queue_idx].val = (_v); \
- update_debug_queue[pt_update_queue_idx].line = __LINE__; \
- update_debug_queue[pt_update_queue_idx].file = __FILE__; \
- queue_l1_entry_update((_p),(_v)); \
-})
-#define queue_l2_entry_update(_p,_v) ({ \
- update_debug_queue[pt_update_queue_idx].ptr = (_p); \
- update_debug_queue[pt_update_queue_idx].val = (_v); \
- update_debug_queue[pt_update_queue_idx].line = __LINE__; \
- update_debug_queue[pt_update_queue_idx].file = __FILE__; \
- queue_l2_entry_update((_p),(_v)); \
-})
-#endif
-
-#if PT_UPDATE_DEBUG > 1
-#undef queue_l1_entry_update
-#undef queue_l2_entry_update
-#define queue_l1_entry_update(_p,_v) ({ \
- update_debug_queue[pt_update_queue_idx].ptr = (_p); \
- update_debug_queue[pt_update_queue_idx].val = (_v); \
- update_debug_queue[pt_update_queue_idx].line = __LINE__; \
- update_debug_queue[pt_update_queue_idx].file = __FILE__; \
- printk("L1 %s %d: %08lx (%08lx -> %08lx)\n", __FILE__, __LINE__, \
- phys_to_machine(_p), *(unsigned long *)__va(_p), \
- (unsigned long)(_v)); \
- queue_l1_entry_update((_p),(_v)); \
-})
-#define queue_l2_entry_update(_p,_v) ({ \
- update_debug_queue[pt_update_queue_idx].ptr = (_p); \
- update_debug_queue[pt_update_queue_idx].val = (_v); \
- update_debug_queue[pt_update_queue_idx].line = __LINE__; \
- update_debug_queue[pt_update_queue_idx].file = __FILE__; \
- printk("L2 %s %d: %08lx (%08lx -> %08lx)\n", __FILE__, __LINE__, \
- phys_to_machine(_p), *(unsigned long *)__va(_p), \
- (unsigned long)(_v)); \
- queue_l2_entry_update((_p),(_v)); \
-})
-#define queue_pt_switch(_p) ({ \
- printk("PTSWITCH %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
- queue_pt_switch(_p); \
-})
-#define queue_tlb_flush() ({ \
- printk("TLB FLUSH %s %d\n", __FILE__, __LINE__); \
- queue_tlb_flush(); \
-})
-#define queue_invlpg(_p) ({ \
- printk("INVLPG %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
- queue_invlpg(_p); \
-})
-#define queue_pgd_pin(_p) ({ \
- printk("PGD PIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
- queue_pgd_pin(_p); \
-})
-#define queue_pgd_unpin(_p) ({ \
- printk("PGD UNPIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
- queue_pgd_unpin(_p); \
-})
-#define queue_pte_pin(_p) ({ \
- printk("PTE PIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
- queue_pte_pin(_p); \
-})
-#define queue_pte_unpin(_p) ({ \
- printk("PTE UNPIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
- queue_pte_unpin(_p); \
-})
-#endif
-
-void _flush_page_update_queue(void);
-static inline int flush_page_update_queue(void)
-{
- unsigned int idx = pt_update_queue_idx;
- if ( idx != 0 ) _flush_page_update_queue();
- return idx;
-}
-#define XENO_flush_page_update_queue() (_flush_page_update_queue())
-
-
-/*
- * Assembler stubs for hyper-calls.
- */
-
-static inline int HYPERVISOR_set_trap_table(trap_info_t *table)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_set_trap_table),
- "b" (table) );
-
- return ret;
-}
-
-
-static inline int HYPERVISOR_pt_update(page_update_request_t *req, int count)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_pt_update),
- "b" (req), "c" (count) );
-
- return ret;
-}
-
-
-static inline int HYPERVISOR_console_write(const char *str, int count)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_console_write),
- "b" (str), "c" (count) );
-
-
- return ret;
-}
-
-static inline int HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_set_gdt),
- "b" (frame_list), "c" (entries) );
-
-
- return ret;
-}
-
-static inline int HYPERVISOR_stack_and_ldt_switch(
- unsigned long ss, unsigned long esp, unsigned long ldts)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_stack_and_ldt_switch),
- "b" (ss), "c" (esp), "d" (ldts) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_net_update(void)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_net_update) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_fpu_taskswitch(void)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_fpu_taskswitch) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_do_sched_op(void *sched_op)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_sched_op),
- "b" (sched_op) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_exit(void)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_exit) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_dom0_op(void *dom0_op)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_dom0_op),
- "b" (dom0_op) : "memory" );
-
- return ret;
-}
-
-static inline int HYPERVISOR_network_op(void *network_op)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_network_op),
- "b" (network_op) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_block_io_op(void)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_block_io_op) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_set_debugreg(int reg, unsigned long value)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_set_debugreg),
- "b" (reg), "c" (value) );
-
- return ret;
-}
-
-static inline unsigned long HYPERVISOR_get_debugreg(int reg)
-{
- unsigned long ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_get_debugreg),
- "b" (reg) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_update_descriptor(
- unsigned long pa, unsigned long word1, unsigned long word2)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_set_gdt),
- "b" (pa), "c" (word1), "d" (word2) );
-
- return ret;
-}
-
-static inline int HYPERVISOR_set_fast_trap(int idx)
-{
- int ret;
- __asm__ __volatile__ (
- TRAP_INSTR
- : "=a" (ret) : "0" (__HYPERVISOR_set_fast_trap),
- "b" (idx) );
-
- return ret;
-}
-
-#endif /* __HYPERVISOR_H__ */
+++ /dev/null
-/*
- * include/asm-i386/i387.h
- *
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-
-#ifndef __ASM_I386_I387_H
-#define __ASM_I386_I387_H
-
-#include <linux/sched.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-
-extern void init_fpu(void);
-/*
- * FPU lazy state save handling...
- */
-extern void save_init_fpu( struct task_struct *tsk );
-extern void restore_fpu( struct task_struct *tsk );
-
-extern void kernel_fpu_begin(void);
-#define kernel_fpu_end() stts()
-
-
-#define unlazy_fpu( tsk ) do { \
- if ( tsk->flags & PF_USEDFPU ) \
- save_init_fpu( tsk ); \
-} while (0)
-
-#define clear_fpu( tsk ) do { \
- if ( tsk->flags & PF_USEDFPU ) { \
- asm volatile("fwait"); \
- tsk->flags &= ~PF_USEDFPU; \
- stts(); \
- } \
-} while (0)
-
-/*
- * FPU state interaction...
- */
-extern unsigned short get_fpu_cwd( struct task_struct *tsk );
-extern unsigned short get_fpu_swd( struct task_struct *tsk );
-extern unsigned short get_fpu_twd( struct task_struct *tsk );
-extern unsigned short get_fpu_mxcsr( struct task_struct *tsk );
-
-extern void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd );
-extern void set_fpu_swd( struct task_struct *tsk, unsigned short swd );
-extern void set_fpu_twd( struct task_struct *tsk, unsigned short twd );
-extern void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr );
-
-#define load_mxcsr( val ) do { \
- unsigned long __mxcsr = ((unsigned long)(val) & 0xffbf); \
- asm volatile( "ldmxcsr %0" : : "m" (__mxcsr) ); \
-} while (0)
-
-/*
- * Signal frame handlers...
- */
-extern int save_i387( struct _fpstate *buf );
-extern int restore_i387( struct _fpstate *buf );
-
-/*
- * ptrace request handers...
- */
-extern int get_fpregs( struct user_i387_struct *buf,
- struct task_struct *tsk );
-extern int set_fpregs( struct task_struct *tsk,
- struct user_i387_struct *buf );
-
-extern int get_fpxregs( struct user_fxsr_struct *buf,
- struct task_struct *tsk );
-extern int set_fpxregs( struct task_struct *tsk,
- struct user_fxsr_struct *buf );
-
-/*
- * FPU state for core dumps...
- */
-extern int dump_fpu( struct pt_regs *regs,
- struct user_i387_struct *fpu );
-extern int dump_extended_fpu( struct pt_regs *regs,
- struct user_fxsr_struct *fpu );
-
-#endif /* __ASM_I386_I387_H */
+++ /dev/null
-/*
- * linux/include/asm-i386/ide.h
- *
- * Copyright (C) 1994-1996 Linus Torvalds & authors
- */
-
-/*
- * This file contains the i386 architecture specific IDE code.
- */
-
-#ifndef __ASMi386_IDE_H
-#define __ASMi386_IDE_H
-
-#ifdef __KERNEL__
-
-#include <linux/config.h>
-
-#ifndef MAX_HWIFS
-# ifdef CONFIG_BLK_DEV_IDEPCI
-#define MAX_HWIFS 10
-# else
-#define MAX_HWIFS 6
-# endif
-#endif
-
-#define ide__sti() __sti()
-
-static __inline__ int ide_default_irq(ide_ioreg_t base)
-{
- switch (base) {
- case 0x1f0: return 14;
- case 0x170: return 15;
- case 0x1e8: return 11;
- case 0x168: return 10;
- case 0x1e0: return 8;
- case 0x160: return 12;
- default:
- return 0;
- }
-}
-
-static __inline__ ide_ioreg_t ide_default_io_base(int index)
-{
- switch (index) {
- case 0: return 0x1f0;
- case 1: return 0x170;
- case 2: return 0x1e8;
- case 3: return 0x168;
- case 4: return 0x1e0;
- case 5: return 0x160;
- default:
- return 0;
- }
-}
-
-static __inline__ void ide_init_hwif_ports(hw_regs_t *hw, ide_ioreg_t data_port, ide_ioreg_t ctrl_port, int *irq)
-{
- ide_ioreg_t reg = data_port;
- int i;
-
- for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
- hw->io_ports[i] = reg;
- reg += 1;
- }
- if (ctrl_port) {
- hw->io_ports[IDE_CONTROL_OFFSET] = ctrl_port;
- } else {
- hw->io_ports[IDE_CONTROL_OFFSET] = hw->io_ports[IDE_DATA_OFFSET] + 0x206;
- }
- if (irq != NULL)
- *irq = 0;
- hw->io_ports[IDE_IRQ_OFFSET] = 0;
-}
-
-static __inline__ void ide_init_default_hwifs(void)
-{
-#ifndef CONFIG_BLK_DEV_IDEPCI
- hw_regs_t hw;
- int index;
-
- for(index = 0; index < MAX_HWIFS; index++) {
- ide_init_hwif_ports(&hw, ide_default_io_base(index), 0, NULL);
- hw.irq = ide_default_irq(ide_default_io_base(index));
- ide_register_hw(&hw, NULL);
- }
-#endif /* CONFIG_BLK_DEV_IDEPCI */
-}
-
-typedef union {
- unsigned all : 8; /* all of the bits together */
- struct {
- unsigned head : 4; /* always zeros here */
- unsigned unit : 1; /* drive select number, 0 or 1 */
- unsigned bit5 : 1; /* always 1 */
- unsigned lba : 1; /* using LBA instead of CHS */
- unsigned bit7 : 1; /* always 1 */
- } b;
- } select_t;
-
-#define ide_request_irq(irq,hand,flg,dev,id) request_irq((irq),(hand),(flg),(dev),(id))
-#define ide_free_irq(irq,dev_id) free_irq((irq), (dev_id))
-#define ide_check_region(from,extent) check_region((from), (extent))
-#define ide_request_region(from,extent,name) request_region((from), (extent), (name))
-#define ide_release_region(from,extent) release_region((from), (extent))
-
-/*
- * The following are not needed for the non-m68k ports
- */
-#define ide_ack_intr(hwif) (1)
-#define ide_fix_driveid(id) do {} while (0)
-#define ide_release_lock(lock) do {} while (0)
-#define ide_get_lock(lock, hdlr, data) do {} while (0)
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASMi386_IDE_H */
+++ /dev/null
-#error "<asm/init.h> should never be used - use <linux/init.h> instead"
+++ /dev/null
-#ifndef _ASM_IO_H
-#define _ASM_IO_H
-
-#include <linux/config.h>
-#include <asm/hypervisor.h>
-/*
- * This file contains the definitions for the x86 IO instructions
- * inb/inw/inl/outb/outw/outl and the "string versions" of the same
- * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
- * versions of the single-IO instructions (inb_p/inw_p/..).
- *
- * This file is not meant to be obfuscating: it's just complicated
- * to (a) handle it all in a way that makes gcc able to optimize it
- * as well as possible and (b) trying to avoid writing the same thing
- * over and over again with slight variations and possibly making a
- * mistake somewhere.
- */
-
-/*
- * Thanks to James van Artsdalen for a better timing-fix than
- * the two short jumps: using outb's to a nonexistent port seems
- * to guarantee better timings even on fast machines.
- *
- * On the other hand, I'd like to be sure of a non-existent port:
- * I feel a bit unsafe about using 0x80 (should be safe, though)
- *
- * Linus
- */
-
- /*
- * Bit simplified and optimized by Jan Hubicka
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
- *
- * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
- * isa_read[wl] and isa_write[wl] fixed
- * - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#define IO_SPACE_LIMIT 0xffff
-
-#define XQUAD_PORTIO_BASE 0xfe400000
-#define XQUAD_PORTIO_LEN 0x40000 /* 256k per quad. Only remapping 1st */
-
-#ifdef __KERNEL__
-
-#include <linux/vmalloc.h>
-
-/*
- * Temporary debugging check to catch old code using
- * unmapped ISA addresses. Will be removed in 2.4.
- */
-#if CONFIG_DEBUG_IOVIRT
- extern void *__io_virt_debug(unsigned long x, const char *file, int line);
- extern unsigned long __io_phys_debug(unsigned long x, const char *file, int line);
- #define __io_virt(x) __io_virt_debug((unsigned long)(x), __FILE__, __LINE__)
-//#define __io_phys(x) __io_phys_debug((unsigned long)(x), __FILE__, __LINE__)
-#else
- #define __io_virt(x) ((void *)(x))
-//#define __io_phys(x) __pa(x)
-#endif
-
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void * address)
-{
- return __pa(address);
-}
-
-static inline void * phys_to_virt(unsigned long address)
-{
- return __va(address);
-}
-
-/*
- * Change virtual addresses to machine addresses and vv.
- * These are equally trivial.
- */
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page) ((page - mem_map) << PAGE_SHIFT)
-
-/*
- * IO bus memory addresses are also 1:1 with the physical address
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-#define page_to_bus page_to_phys
-
-/*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the x86 architecture, we just read/write the
- * memory location directly.
- */
-
-#define readb(addr) (*(volatile unsigned char *) __io_virt(addr))
-#define readw(addr) (*(volatile unsigned short *) __io_virt(addr))
-#define readl(addr) (*(volatile unsigned int *) __io_virt(addr))
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-
-#define writeb(b,addr) (*(volatile unsigned char *) __io_virt(addr) = (b))
-#define writew(b,addr) (*(volatile unsigned short *) __io_virt(addr) = (b))
-#define writel(b,addr) (*(volatile unsigned int *) __io_virt(addr) = (b))
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-
-#define memset_io(a,b,c) memset(__io_virt(a),(b),(c))
-#define memcpy_fromio(a,b,c) memcpy((a),__io_virt(b),(c))
-#define memcpy_toio(a,b,c) memcpy(__io_virt(a),(b),(c))
-
-/*
- * ISA space is 'always mapped' on a typical x86 system, no need to
- * explicitly ioremap() it. The fact that the ISA IO space is mapped
- * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
- * are physical addresses. The following constant pointer can be
- * used as the IO-area pointer (it can be iounmapped as well, so the
- * analogy with PCI is quite large):
- */
-#define __ISA_IO_base ((char *)(PAGE_OFFSET))
-
-#define isa_readb(a) readb(__ISA_IO_base + (a))
-#define isa_readw(a) readw(__ISA_IO_base + (a))
-#define isa_readl(a) readl(__ISA_IO_base + (a))
-#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
-#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
-#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
-#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c))
-#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c))
-#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c))
-
-
-/*
- * Again, i386 does not require mem IO specific function.
- */
-
-#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),__io_virt(b),(c),(d))
-#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),__io_virt(__ISA_IO_base + (b)),(c),(d))
-
-static inline int check_signature(unsigned long io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
-static inline int isa_check_signature(unsigned long io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (isa_readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
-/*
- * Cache management
- *
- * This needed for two cases
- * 1. Out of order aware processors
- * 2. Accidentally out of order processors (PPro errata #51)
- */
-
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
-
-static inline void flush_write_buffers(void)
-{
- __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
-}
-
-#define dma_cache_inv(_start,_size) flush_write_buffers()
-#define dma_cache_wback(_start,_size) flush_write_buffers()
-#define dma_cache_wback_inv(_start,_size) flush_write_buffers()
-
-#else
-
-/* Nothing to do */
-
-#define dma_cache_inv(_start,_size) do { } while (0)
-#define dma_cache_wback(_start,_size) do { } while (0)
-#define dma_cache_wback_inv(_start,_size) do { } while (0)
-#define flush_write_buffers()
-
-#endif
-
-#endif /* __KERNEL__ */
-
-#ifdef SLOW_IO_BY_JUMPING
-#define __SLOW_DOWN_IO "\njmp 1f\n1:\tjmp 1f\n1:"
-#else
-#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
-#endif
-
-#ifdef REALLY_SLOW_IO
-#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
-#else
-#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
-#endif
-
-#ifdef CONFIG_MULTIQUAD
-extern void *xquad_portio; /* Where the IO area was mapped */
-#endif /* CONFIG_MULTIQUAD */
-
-/*
- * Talk about misusing macros..
- */
-#define __OUT1(s,x) \
-static inline void out##s(unsigned x value, unsigned short port) {
-
-#define __OUT2(s,s1,s2) \
-__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"
-
-#ifdef CONFIG_MULTIQUAD
-/* Make the default portio routines operate on quad 0 for now */
-#define __OUT(s,s1,x) \
-__OUT1(s##_local,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
-__OUT1(s##_p_local,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \
-__OUTQ0(s,s,x) \
-__OUTQ0(s,s##_p,x)
-#else
-#define __OUT(s,s1,x) \
-__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
-__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));}
-#endif /* CONFIG_MULTIQUAD */
-
-#ifdef CONFIG_MULTIQUAD
-#define __OUTQ0(s,ss,x) /* Do the equivalent of the portio op on quad 0 */ \
-static inline void out##ss(unsigned x value, unsigned short port) { \
- if (xquad_portio) \
- write##s(value, (unsigned long) xquad_portio + port); \
- else /* We're still in early boot, running on quad 0 */ \
- out##ss##_local(value, port); \
-}
-
-#define __INQ0(s,ss) /* Do the equivalent of the portio op on quad 0 */ \
-static inline RETURN_TYPE in##ss(unsigned short port) { \
- if (xquad_portio) \
- return read##s((unsigned long) xquad_portio + port); \
- else /* We're still in early boot, running on quad 0 */ \
- return in##ss##_local(port); \
-}
-#endif /* CONFIG_MULTIQUAD */
-
-#define __IN1(s) \
-static inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;
-
-#define __IN2(s,s1,s2) \
-__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"
-
-#ifdef CONFIG_MULTIQUAD
-#define __IN(s,s1,i...) \
-__IN1(s##_local) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
-__IN1(s##_p_local) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
-__INQ0(s,s) \
-__INQ0(s,s##_p)
-#else
-#define __IN(s,s1,i...) \
-__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
-__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; }
-#endif /* CONFIG_MULTIQUAD */
-
-#define __INS(s) \
-static inline void ins##s(unsigned short port, void * addr, unsigned long count) \
-{ __asm__ __volatile__ ("rep ; ins" #s \
-: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
-
-#define __OUTS(s) \
-static inline void outs##s(unsigned short port, const void * addr, unsigned long count) \
-{ __asm__ __volatile__ ("rep ; outs" #s \
-: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
-
-#define RETURN_TYPE unsigned char
-__IN(b,"")
-#undef RETURN_TYPE
-#define RETURN_TYPE unsigned short
-__IN(w,"")
-#undef RETURN_TYPE
-#define RETURN_TYPE unsigned int
-__IN(l,"")
-#undef RETURN_TYPE
-
-__OUT(b,"b",char)
-__OUT(w,"w",short)
-__OUT(l,,int)
-
-__INS(b)
-__INS(w)
-__INS(l)
-
-__OUTS(b)
-__OUTS(w)
-__OUTS(l)
-
-#endif
+++ /dev/null
-#ifndef __ASM_IO_APIC_H
-#define __ASM_IO_APIC_H
-
-#include <linux/config.h>
-#include <asm/types.h>
-
-/*
- * Intel IO-APIC support for SMP and UP systems.
- *
- * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
- */
-
-#ifdef CONFIG_X86_IO_APIC
-
-#define APIC_MISMATCH_DEBUG
-
-#define IO_APIC_BASE(idx) \
- ((volatile int *)__fix_to_virt(FIX_IO_APIC_BASE_0 + idx))
-
-/*
- * The structure of the IO-APIC:
- */
-struct IO_APIC_reg_00 {
- __u32 __reserved_2 : 24,
- ID : 4,
- __reserved_1 : 4;
-} __attribute__ ((packed));
-
-struct IO_APIC_reg_01 {
- __u32 version : 8,
- __reserved_2 : 7,
- PRQ : 1,
- entries : 8,
- __reserved_1 : 8;
-} __attribute__ ((packed));
-
-struct IO_APIC_reg_02 {
- __u32 __reserved_2 : 24,
- arbitration : 4,
- __reserved_1 : 4;
-} __attribute__ ((packed));
-
-/*
- * # of IO-APICs and # of IRQ routing registers
- */
-extern int nr_ioapics;
-extern int nr_ioapic_registers[MAX_IO_APICS];
-
-enum ioapic_irq_destination_types {
- dest_Fixed = 0,
- dest_LowestPrio = 1,
- dest_SMI = 2,
- dest__reserved_1 = 3,
- dest_NMI = 4,
- dest_INIT = 5,
- dest__reserved_2 = 6,
- dest_ExtINT = 7
-};
-
-struct IO_APIC_route_entry {
- __u32 vector : 8,
- delivery_mode : 3, /* 000: FIXED
- * 001: lowest prio
- * 111: ExtINT
- */
- dest_mode : 1, /* 0: physical, 1: logical */
- delivery_status : 1,
- polarity : 1,
- irr : 1,
- trigger : 1, /* 0: edge, 1: level */
- mask : 1, /* 0: enabled, 1: disabled */
- __reserved_2 : 15;
-
- union { struct { __u32
- __reserved_1 : 24,
- physical_dest : 4,
- __reserved_2 : 4;
- } physical;
-
- struct { __u32
- __reserved_1 : 24,
- logical_dest : 8;
- } logical;
- } dest;
-
-} __attribute__ ((packed));
-
-/*
- * MP-BIOS irq configuration table structures:
- */
-
-/* I/O APIC entries */
-extern struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
-
-/* # of MP IRQ source entries */
-extern int mp_irq_entries;
-
-/* MP IRQ source entries */
-extern struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
-
-/* non-0 if default (table-less) MP configuration */
-extern int mpc_default_type;
-
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
-{
- *IO_APIC_BASE(apic) = reg;
- return *(IO_APIC_BASE(apic)+4);
-}
-
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
-{
- *IO_APIC_BASE(apic) = reg;
- *(IO_APIC_BASE(apic)+4) = value;
-}
-
-/*
- * Re-write a value: to be used for read-modify-write
- * cycles where the read already set up the index register.
- */
-static inline void io_apic_modify(unsigned int apic, unsigned int value)
-{
- *(IO_APIC_BASE(apic)+4) = value;
-}
-
-/*
- * Synchronize the IO-APIC and the CPU by doing
- * a dummy read from the IO-APIC
- */
-static inline void io_apic_sync(unsigned int apic)
-{
- (void) *(IO_APIC_BASE(apic)+4);
-}
-
-/* 1 if "noapic" boot option passed */
-extern int skip_ioapic_setup;
-
-/*
- * If we use the IO-APIC for IRQ routing, disable automatic
- * assignment of PCI IRQ's.
- */
-#define io_apic_assign_pci_irqs (mp_irq_entries && !skip_ioapic_setup)
-
-#else /* !CONFIG_X86_IO_APIC */
-#define io_apic_assign_pci_irqs 0
-#endif
-
-#endif
+++ /dev/null
-/* $Id: ioctl.h,v 1.5 1993/07/19 21:53:50 root Exp root $
- *
- * linux/ioctl.h for Linux by H.H. Bergman.
- */
-
-#ifndef _ASMI386_IOCTL_H
-#define _ASMI386_IOCTL_H
-
-/* ioctl command encoding: 32 bits total, command in lower 16 bits,
- * size of the parameter structure in the lower 14 bits of the
- * upper 16 bits.
- * Encoding the size of the parameter structure in the ioctl request
- * is useful for catching programs compiled with old versions
- * and to avoid overwriting user space outside the user buffer area.
- * The highest 2 bits are reserved for indicating the ``access mode''.
- * NOTE: This limits the max parameter size to 16kB -1 !
- */
-
-/*
- * The following is for compatibility across the various Linux
- * platforms. The i386 ioctl numbering scheme doesn't really enforce
- * a type field. De facto, however, the top 8 bits of the lower 16
- * bits are indeed used as a type field, so we might just as well make
- * this explicit here. Please be sure to use the decoding macros
- * below from now on.
- */
-#define _IOC_NRBITS 8
-#define _IOC_TYPEBITS 8
-#define _IOC_SIZEBITS 14
-#define _IOC_DIRBITS 2
-
-#define _IOC_NRMASK ((1 << _IOC_NRBITS)-1)
-#define _IOC_TYPEMASK ((1 << _IOC_TYPEBITS)-1)
-#define _IOC_SIZEMASK ((1 << _IOC_SIZEBITS)-1)
-#define _IOC_DIRMASK ((1 << _IOC_DIRBITS)-1)
-
-#define _IOC_NRSHIFT 0
-#define _IOC_TYPESHIFT (_IOC_NRSHIFT+_IOC_NRBITS)
-#define _IOC_SIZESHIFT (_IOC_TYPESHIFT+_IOC_TYPEBITS)
-#define _IOC_DIRSHIFT (_IOC_SIZESHIFT+_IOC_SIZEBITS)
-
-/*
- * Direction bits.
- */
-#define _IOC_NONE 0U
-#define _IOC_WRITE 1U
-#define _IOC_READ 2U
-
-#define _IOC(dir,type,nr,size) \
- (((dir) << _IOC_DIRSHIFT) | \
- ((type) << _IOC_TYPESHIFT) | \
- ((nr) << _IOC_NRSHIFT) | \
- ((size) << _IOC_SIZESHIFT))
-
-/* used to create numbers */
-#define _IO(type,nr) _IOC(_IOC_NONE,(type),(nr),0)
-#define _IOR(type,nr,size) _IOC(_IOC_READ,(type),(nr),sizeof(size))
-#define _IOW(type,nr,size) _IOC(_IOC_WRITE,(type),(nr),sizeof(size))
-#define _IOWR(type,nr,size) _IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
-
-/* used to decode ioctl numbers.. */
-#define _IOC_DIR(nr) (((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
-#define _IOC_TYPE(nr) (((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
-#define _IOC_NR(nr) (((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
-#define _IOC_SIZE(nr) (((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
-
-/* ...and for the drivers/sound files... */
-
-#define IOC_IN (_IOC_WRITE << _IOC_DIRSHIFT)
-#define IOC_OUT (_IOC_READ << _IOC_DIRSHIFT)
-#define IOC_INOUT ((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
-#define IOCSIZE_MASK (_IOC_SIZEMASK << _IOC_SIZESHIFT)
-#define IOCSIZE_SHIFT (_IOC_SIZESHIFT)
-
-#endif /* _ASMI386_IOCTL_H */
+++ /dev/null
-#ifndef __ARCH_I386_IOCTLS_H__
-#define __ARCH_I386_IOCTLS_H__
-
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS 0x5401
-#define TCSETS 0x5402
-#define TCSETSW 0x5403
-#define TCSETSF 0x5404
-#define TCGETA 0x5405
-#define TCSETA 0x5406
-#define TCSETAW 0x5407
-#define TCSETAF 0x5408
-#define TCSBRK 0x5409
-#define TCXONC 0x540A
-#define TCFLSH 0x540B
-#define TIOCEXCL 0x540C
-#define TIOCNXCL 0x540D
-#define TIOCSCTTY 0x540E
-#define TIOCGPGRP 0x540F
-#define TIOCSPGRP 0x5410
-#define TIOCOUTQ 0x5411
-#define TIOCSTI 0x5412
-#define TIOCGWINSZ 0x5413
-#define TIOCSWINSZ 0x5414
-#define TIOCMGET 0x5415
-#define TIOCMBIS 0x5416
-#define TIOCMBIC 0x5417
-#define TIOCMSET 0x5418
-#define TIOCGSOFTCAR 0x5419
-#define TIOCSSOFTCAR 0x541A
-#define FIONREAD 0x541B
-#define TIOCINQ FIONREAD
-#define TIOCLINUX 0x541C
-#define TIOCCONS 0x541D
-#define TIOCGSERIAL 0x541E
-#define TIOCSSERIAL 0x541F
-#define TIOCPKT 0x5420
-#define FIONBIO 0x5421
-#define TIOCNOTTY 0x5422
-#define TIOCSETD 0x5423
-#define TIOCGETD 0x5424
-#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */
-#define TIOCTTYGSTRUCT 0x5426 /* For debugging only */
-#define TIOCSBRK 0x5427 /* BSD compatibility */
-#define TIOCCBRK 0x5428 /* BSD compatibility */
-#define TIOCGSID 0x5429 /* Return the session ID of FD */
-#define TIOCGPTN _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK _IOW('T',0x31, int) /* Lock/unlock Pty */
-
-#define FIONCLEX 0x5450 /* these numbers need to be adjusted. */
-#define FIOCLEX 0x5451
-#define FIOASYNC 0x5452
-#define TIOCSERCONFIG 0x5453
-#define TIOCSERGWILD 0x5454
-#define TIOCSERSWILD 0x5455
-#define TIOCGLCKTRMIOS 0x5456
-#define TIOCSLCKTRMIOS 0x5457
-#define TIOCSERGSTRUCT 0x5458 /* For debugging only */
-#define TIOCSERGETLSR 0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */
-#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */
-#define TIOCGHAYESESP 0x545E /* Get Hayes ESP configuration */
-#define TIOCSHAYESESP 0x545F /* Set Hayes ESP configuration */
-
-/* Used for packet mode */
-#define TIOCPKT_DATA 0
-#define TIOCPKT_FLUSHREAD 1
-#define TIOCPKT_FLUSHWRITE 2
-#define TIOCPKT_STOP 4
-#define TIOCPKT_START 8
-#define TIOCPKT_NOSTOP 16
-#define TIOCPKT_DOSTOP 32
-
-#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */
-
-#endif
+++ /dev/null
-#ifndef __i386_IPC_H__
-#define __i386_IPC_H__
-
-/*
- * These are used to wrap system calls on x86.
- *
- * See arch/i386/kernel/sys_i386.c for ugly details..
- */
-struct ipc_kludge {
- struct msgbuf *msgp;
- long msgtyp;
-};
-
-#define SEMOP 1
-#define SEMGET 2
-#define SEMCTL 3
-#define MSGSND 11
-#define MSGRCV 12
-#define MSGGET 13
-#define MSGCTL 14
-#define SHMAT 21
-#define SHMDT 22
-#define SHMGET 23
-#define SHMCTL 24
-
-/* Used by the DIPC package, try and avoid reusing it */
-#define DIPC 25
-
-#define IPCCALL(version,op) ((version)<<16 | (op))
-
-#endif
+++ /dev/null
-#ifndef __i386_IPCBUF_H__
-#define __i386_IPCBUF_H__
-
-/*
- * The ipc64_perm structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 32-bit mode_t and seq
- * - 2 miscellaneous 32-bit values
- */
-
-struct ipc64_perm
-{
- __kernel_key_t key;
- __kernel_uid32_t uid;
- __kernel_gid32_t gid;
- __kernel_uid32_t cuid;
- __kernel_gid32_t cgid;
- __kernel_mode_t mode;
- unsigned short __pad1;
- unsigned short seq;
- unsigned short __pad2;
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* __i386_IPCBUF_H__ */
+++ /dev/null
-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- * linux/include/asm/irq.h
- *
- * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- * IRQ/IPI changes taken from work by Thomas Radke
- * <tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/config.h>
-#include <asm/hypervisor.h>
-#include <asm/ptrace.h>
-
-#define NET_TX_IRQ _EVENT_NET_TX
-#define NET_RX_IRQ _EVENT_NET_RX
-#define NET2_TX_IRQ _EVENT_NET2_TX
-#define NET2_RX_IRQ _EVENT_NET2_RX
-#define TIMER_IRQ _EVENT_TIMER
-
-#define NR_IRQS (sizeof(HYPERVISOR_shared_info->events) * 8)
-
-#define irq_cannonicalize(_irq) (_irq)
-
-extern void disable_irq(unsigned int);
-extern void disable_irq_nosync(unsigned int);
-extern void enable_irq(unsigned int);
-extern unsigned int do_IRQ(int, struct pt_regs *);
-
-#endif /* _ASM_IRQ_H */
+++ /dev/null
-/*
- * Minimalist Kernel Debugger
- *
- * Copyright (C) 1999 Silicon Graphics, Inc.
- * Copyright (C) Scott Lurndal (slurn@engr.sgi.com)
- * Copyright (C) Scott Foehner (sfoehner@engr.sgi.com)
- * Copyright (C) Srinivasa Thirumalachar (sprasad@engr.sgi.com)
- *
- * See the file LIA-COPYRIGHT for additional information.
- *
- * Written March 1999 by Scott Lurndal at Silicon Graphics, Inc.
- *
- * Modifications from:
- * Richard Bass 1999/07/20
- * Many bug fixes and enhancements.
- * Scott Foehner
- * Port to ia64
- * Scott Lurndal 1999/12/12
- * v1.0 restructuring.
- */
-#if !defined(_ASM_KDB_H)
-#define _ASM_KDB_H
-
- /*
- * KDB_ENTER() is a macro which causes entry into the kernel
- * debugger from any point in the kernel code stream. If it
- * is intended to be used from interrupt level, it must use
- * a non-maskable entry method.
- */
-#define KDB_ENTER() asm("\tint $129\n")
-
- /*
- * Define the exception frame for this architeture
- */
-struct pt_regs;
-typedef struct pt_regs *kdb_eframe_t;
-
- /*
- * Needed for exported symbols.
- */
-typedef unsigned long kdb_machreg_t;
-
-#define kdb_machreg_fmt "0x%lx"
-#define kdb_machreg_fmt0 "0x%08lx"
-#define kdb_bfd_vma_fmt "0x%lx"
-#define kdb_bfd_vma_fmt0 "0x%08lx"
-#define kdb_elfw_addr_fmt "0x%x"
-#define kdb_elfw_addr_fmt0 "0x%08x"
-
- /*
- * Per cpu arch specific kdb state. Must be in range 0xff000000.
- */
-#define KDB_STATE_A_IF 0x01000000 /* Saved IF flag */
-
- /*
- * Interface from kernel trap handling code to kernel debugger.
- */
-extern int kdba_callback_die(struct pt_regs *, int, long, void*);
-extern int kdba_callback_bp(struct pt_regs *, int, long, void*);
-extern int kdba_callback_debug(struct pt_regs *, int, long, void *);
-
-#endif /* ASM_KDB_H */
+++ /dev/null
-/*
- * Minimalist Kernel Debugger
- *
- * Copyright (C) 1999 Silicon Graphics, Inc.
- * Copyright (C) Scott Lurndal (slurn@engr.sgi.com)
- * Copyright (C) Scott Foehner (sfoehner@engr.sgi.com)
- * Copyright (C) Srinivasa Thirumalachar (sprasad@engr.sgi.com)
- *
- * See the file LIA-COPYRIGHT for additional information.
- *
- * Written March 1999 by Scott Lurndal at Silicon Graphics, Inc.
- *
- * Modifications from:
- * Richard Bass 1999/07/20
- * Many bug fixes and enhancements.
- * Scott Foehner
- * Port to ia64
- * Scott Lurndal 1999/12/12
- * v1.0 restructuring.
- * Keith Owens 2000/05/23
- * KDB v1.2
- */
-#if !defined(_ASM_KDBPRIVATE_H)
-#define _ASM_KDBPRIVATE_H
-
-typedef unsigned char kdb_machinst_t;
-
- /*
- * KDB_MAXBPT describes the total number of breakpoints
- * supported by this architecure.
- */
-#define KDB_MAXBPT 16
- /*
- * KDB_MAXHARDBPT describes the total number of hardware
- * breakpoint registers that exist.
- */
-#define KDB_MAXHARDBPT 4
- /*
- * Provide space for KDB_MAX_COMMANDS commands.
- */
-#define KDB_MAX_COMMANDS 125
-
- /*
- * Platform specific environment entries
- */
-#define KDB_PLATFORM_ENV "IDMODE=x86", "BYTESPERWORD=4", "IDCOUNT=16"
-
- /*
- * Define the direction that the stack grows
- */
-#define KDB_STACK_DIRECTION (-1) /* Stack grows down */
-
- /*
- * Support for ia32 debug registers
- */
-typedef struct _kdbhard_bp {
- kdb_machreg_t bph_reg; /* Register this breakpoint uses */
-
- unsigned int bph_free:1; /* Register available for use */
- unsigned int bph_data:1; /* Data Access breakpoint */
-
- unsigned int bph_write:1; /* Write Data breakpoint */
- unsigned int bph_mode:2; /* 0=inst, 1=write, 2=io, 3=read */
- unsigned int bph_length:2; /* 0=1, 1=2, 2=BAD, 3=4 (bytes) */
-} kdbhard_bp_t;
-
-extern kdbhard_bp_t kdb_hardbreaks[/* KDB_MAXHARDBPT */];
-
-#define IA32_BREAKPOINT_INSTRUCTION 0xcc
-
-#define DR6_BT 0x00008000
-#define DR6_BS 0x00004000
-#define DR6_BD 0x00002000
-
-#define DR6_B3 0x00000008
-#define DR6_B2 0x00000004
-#define DR6_B1 0x00000002
-#define DR6_B0 0x00000001
-
-#define DR7_RW_VAL(dr, drnum) \
- (((dr) >> (16 + (4 * (drnum)))) & 0x3)
-
-#define DR7_RW_SET(dr, drnum, rw) \
- do { \
- (dr) &= ~(0x3 << (16 + (4 * (drnum)))); \
- (dr) |= (((rw) & 0x3) << (16 + (4 * (drnum)))); \
- } while (0)
-
-#define DR7_RW0(dr) DR7_RW_VAL(dr, 0)
-#define DR7_RW0SET(dr,rw) DR7_RW_SET(dr, 0, rw)
-#define DR7_RW1(dr) DR7_RW_VAL(dr, 1)
-#define DR7_RW1SET(dr,rw) DR7_RW_SET(dr, 1, rw)
-#define DR7_RW2(dr) DR7_RW_VAL(dr, 2)
-#define DR7_RW2SET(dr,rw) DR7_RW_SET(dr, 2, rw)
-#define DR7_RW3(dr) DR7_RW_VAL(dr, 3)
-#define DR7_RW3SET(dr,rw) DR7_RW_SET(dr, 3, rw)
-
-
-#define DR7_LEN_VAL(dr, drnum) \
- (((dr) >> (18 + (4 * (drnum)))) & 0x3)
-
-#define DR7_LEN_SET(dr, drnum, rw) \
- do { \
- (dr) &= ~(0x3 << (18 + (4 * (drnum)))); \
- (dr) |= (((rw) & 0x3) << (18 + (4 * (drnum)))); \
- } while (0)
-#define DR7_LEN0(dr) DR7_LEN_VAL(dr, 0)
-#define DR7_LEN0SET(dr,len) DR7_LEN_SET(dr, 0, len)
-#define DR7_LEN1(dr) DR7_LEN_VAL(dr, 1)
-#define DR7_LEN1SET(dr,len) DR7_LEN_SET(dr, 1, len)
-#define DR7_LEN2(dr) DR7_LEN_VAL(dr, 2)
-#define DR7_LEN2SET(dr,len) DR7_LEN_SET(dr, 2, len)
-#define DR7_LEN3(dr) DR7_LEN_VAL(dr, 3)
-#define DR7_LEN3SET(dr,len) DR7_LEN_SET(dr, 3, len)
-
-#define DR7_G0(dr) (((dr)>>1)&0x1)
-#define DR7_G0SET(dr) ((dr) |= 0x2)
-#define DR7_G0CLR(dr) ((dr) &= ~0x2)
-#define DR7_G1(dr) (((dr)>>3)&0x1)
-#define DR7_G1SET(dr) ((dr) |= 0x8)
-#define DR7_G1CLR(dr) ((dr) &= ~0x8)
-#define DR7_G2(dr) (((dr)>>5)&0x1)
-#define DR7_G2SET(dr) ((dr) |= 0x20)
-#define DR7_G2CLR(dr) ((dr) &= ~0x20)
-#define DR7_G3(dr) (((dr)>>7)&0x1)
-#define DR7_G3SET(dr) ((dr) |= 0x80)
-#define DR7_G3CLR(dr) ((dr) &= ~0x80)
-
-#define DR7_L0(dr) (((dr))&0x1)
-#define DR7_L0SET(dr) ((dr) |= 0x1)
-#define DR7_L0CLR(dr) ((dr) &= ~0x1)
-#define DR7_L1(dr) (((dr)>>2)&0x1)
-#define DR7_L1SET(dr) ((dr) |= 0x4)
-#define DR7_L1CLR(dr) ((dr) &= ~0x4)
-#define DR7_L2(dr) (((dr)>>4)&0x1)
-#define DR7_L2SET(dr) ((dr) |= 0x10)
-#define DR7_L2CLR(dr) ((dr) &= ~0x10)
-#define DR7_L3(dr) (((dr)>>6)&0x1)
-#define DR7_L3SET(dr) ((dr) |= 0x40)
-#define DR7_L3CLR(dr) ((dr) &= ~0x40)
-
-#define DR7_GD 0x00002000 /* General Detect Enable */
-#define DR7_GE 0x00000200 /* Global exact */
-#define DR7_LE 0x00000100 /* Local exact */
-
-extern kdb_machreg_t kdba_getdr6(void);
-extern void kdba_putdr6(kdb_machreg_t);
-
-extern kdb_machreg_t kdba_getdr7(void);
-
-extern kdb_machreg_t kdba_getdr(int);
-extern void kdba_putdr(int, kdb_machreg_t);
-
-extern kdb_machreg_t kdb_getcr(int);
-
-#define KDB_HAVE_LONGJMP
-#ifdef KDB_HAVE_LONGJMP
-/*
- * Support for setjmp/longjmp
- */
-#define JB_BX 0
-#define JB_SI 1
-#define JB_DI 2
-#define JB_BP 3
-#define JB_SP 4
-#define JB_PC 5
-
-typedef struct __kdb_jmp_buf {
- unsigned long regs[6]; /* kdba_setjmp assumes fixed offsets here */
-} kdb_jmp_buf;
-
-extern int kdba_setjmp(kdb_jmp_buf *);
-extern void kdba_longjmp(kdb_jmp_buf *, int);
-
-extern kdb_jmp_buf kdbjmpbuf[];
-#endif /* KDB_HAVE_LONGJMP */
-
-#endif /* !_ASM_KDBPRIVATE_H */
+++ /dev/null
-/*
- * linux/include/asm-i386/keyboard.h
- *
- * Created 3 Nov 1996 by Geert Uytterhoeven
- */
-
-/*
- * This file contains the i386 architecture specific keyboard definitions
- */
-
-#ifndef _I386_KEYBOARD_H
-#define _I386_KEYBOARD_H
-
-#ifdef __KERNEL__
-
-#include <linux/kernel.h>
-#include <linux/ioport.h>
-#include <linux/kd.h>
-#include <linux/pm.h>
-#include <asm/io.h>
-
-#define KEYBOARD_IRQ 1
-#define DISABLE_KBD_DURING_INTERRUPTS 0
-
-extern int pckbd_setkeycode(unsigned int scancode, unsigned int keycode);
-extern int pckbd_getkeycode(unsigned int scancode);
-extern int pckbd_translate(unsigned char scancode, unsigned char *keycode,
- char raw_mode);
-extern char pckbd_unexpected_up(unsigned char keycode);
-extern void pckbd_leds(unsigned char leds);
-extern void pckbd_init_hw(void);
-extern int pckbd_pm_resume(struct pm_dev *, pm_request_t, void *);
-extern pm_callback pm_kbd_request_override;
-extern unsigned char pckbd_sysrq_xlate[128];
-
-#define kbd_setkeycode pckbd_setkeycode
-#define kbd_getkeycode pckbd_getkeycode
-#define kbd_translate pckbd_translate
-#define kbd_unexpected_up pckbd_unexpected_up
-#define kbd_leds pckbd_leds
-#define kbd_init_hw pckbd_init_hw
-#define kbd_sysrq_xlate pckbd_sysrq_xlate
-
-#define SYSRQ_KEY 0x54
-#define E1_PAUSE 119 /* PAUSE key */
-
-/* resource allocation */
-#define kbd_request_region()
-#define kbd_request_irq(handler) request_irq(KEYBOARD_IRQ, handler, 0, \
- "keyboard", NULL)
-
-/* How to access the keyboard macros on this platform. */
-#define kbd_read_input() inb(KBD_DATA_REG)
-#define kbd_read_status() inb(KBD_STATUS_REG)
-#define kbd_write_output(val) outb(val, KBD_DATA_REG)
-#define kbd_write_command(val) outb(val, KBD_CNTL_REG)
-
-/* Some stoneage hardware needs delays after some operations. */
-#define kbd_pause() do { } while(0)
-
-/*
- * Machine specific bits for the PS/2 driver
- */
-
-#define AUX_IRQ 12
-
-#define aux_request_irq(hand, dev_id) \
- request_irq(AUX_IRQ, hand, SA_SHIRQ, "PS/2 Mouse", dev_id)
-
-#define aux_free_irq(dev_id) free_irq(AUX_IRQ, dev_id)
-
-#endif /* __KERNEL__ */
-#endif /* _I386_KEYBOARD_H */
+++ /dev/null
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-enum km_type {
- KM_BOUNCE_READ,
- KM_SKB_DATA,
- KM_SKB_DATA_SOFTIRQ,
- KM_USER0,
- KM_USER1,
- KM_TYPE_NR
-};
-
-#endif
+++ /dev/null
-/*
- * ldt.h
- *
- * Definitions of structures used with the modify_ldt system call.
- */
-#ifndef _LINUX_LDT_H
-#define _LINUX_LDT_H
-
-/* Maximum number of LDT entries supported. */
-#define LDT_ENTRIES 8192
-/* The size of each LDT entry. */
-#define LDT_ENTRY_SIZE 8
-
-#ifndef __ASSEMBLY__
-struct modify_ldt_ldt_s {
- unsigned int entry_number;
- unsigned long base_addr;
- unsigned int limit;
- unsigned int seg_32bit:1;
- unsigned int contents:2;
- unsigned int read_exec_only:1;
- unsigned int limit_in_pages:1;
- unsigned int seg_not_present:1;
- unsigned int useable:1;
-};
-
-#define MODIFY_LDT_CONTENTS_DATA 0
-#define MODIFY_LDT_CONTENTS_STACK 1
-#define MODIFY_LDT_CONTENTS_CODE 2
-
-#endif /* !__ASSEMBLY__ */
-#endif
+++ /dev/null
-/* $Id: linux_logo.h,v 1.8 1998/07/30 16:30:24 jj Exp $
- * include/asm-i386/linux_logo.h: This is a linux logo
- * to be displayed on boot.
- *
- * Copyright (C) 1996 Larry Ewing (lewing@isc.tamu.edu)
- * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
- *
- * You can put anything here, but:
- * LINUX_LOGO_COLORS has to be less than 224
- * image size has to be 80x80
- * values have to start from 0x20
- * (i.e. RGB(linux_logo_red[0],
- * linux_logo_green[0],
- * linux_logo_blue[0]) is color 0x20)
- * BW image has to be 80x80 as well, with MS bit
- * on the left
- * Serial_console ascii image can be any size,
- * but should contain %s to display the version
- */
-
-#include <linux/init.h>
-#include <linux/version.h>
-
-#define linux_logo_banner "Linux/ia32 version " UTS_RELEASE
-
-#include <linux/linux_logo.h>
-
+++ /dev/null
-/*
- * SMP locks primitives for building ix86 locks
- * (not yet used).
- *
- * Alan Cox, alan@redhat.com, 1995
- */
-
-/*
- * This would be much easier but far less clear and easy
- * to borrow for other processors if it was just assembler.
- */
-
-static __inline__ void prim_spin_lock(struct spinlock *sp)
-{
- int processor=smp_processor_id();
-
- /*
- * Grab the lock bit
- */
-
- while(lock_set_bit(0,&sp->lock))
- {
- /*
- * Failed, but that's cos we own it!
- */
-
- if(sp->cpu==processor)
- {
- sp->users++;
- return 0;
- }
- /*
- * Spin in the cache S state if possible
- */
- while(sp->lock)
- {
- /*
- * Wait for any invalidates to go off
- */
-
- if(smp_invalidate_needed&(1<<processor))
- while(lock_clear_bit(processor,&smp_invalidate_needed))
- local_flush_tlb();
- sp->spins++;
- }
- /*
- * Someone wrote the line, we go 'I' and get
- * the cache entry. Now try to regrab
- */
- }
- sp->users++;sp->cpu=processor;
- return 1;
-}
-
-/*
- * Release a spin lock
- */
-
-static __inline__ int prim_spin_unlock(struct spinlock *sp)
-{
- /* This is safe. The decrement is still guarded by the lock. A multilock would
- not be safe this way */
- if(!--sp->users)
- {
- sp->cpu= NO_PROC_ID;lock_clear_bit(0,&sp->lock);
- return 1;
- }
- return 0;
-}
-
-
-/*
- * Non blocking lock grab
- */
-
-static __inline__ int prim_spin_lock_nb(struct spinlock *sp)
-{
- if(lock_set_bit(0,&sp->lock))
- return 0; /* Locked already */
- sp->users++;
- return 1; /* We got the lock */
-}
-
-
-/*
- * These wrap the locking primitives up for usage
- */
-
-static __inline__ void spinlock(struct spinlock *sp)
-{
- if(sp->priority<current->lock_order)
- panic("lock order violation: %s (%d)\n", sp->name, current->lock_order);
- if(prim_spin_lock(sp))
- {
- /*
- * We got a new lock. Update the priority chain
- */
- sp->oldpri=current->lock_order;
- current->lock_order=sp->priority;
- }
-}
-
-static __inline__ void spinunlock(struct spinlock *sp)
-{
- int pri;
- if(current->lock_order!=sp->priority)
- panic("lock release order violation %s (%d)\n", sp->name, current->lock_order);
- pri=sp->oldpri;
- if(prim_spin_unlock(sp))
- {
- /*
- * Update the debugging lock priority chain. We dumped
- * our last right to the lock.
- */
- current->lock_order=sp->pri;
- }
-}
-
-static __inline__ void spintestlock(struct spinlock *sp)
-{
- /*
- * We do no sanity checks, it's legal to optimistically
- * get a lower lock.
- */
- prim_spin_lock_nb(sp);
-}
-
-static __inline__ void spintestunlock(struct spinlock *sp)
-{
- /*
- * A testlock doesn't update the lock chain so we
- * must not update it on free
- */
- prim_spin_unlock(sp);
-}
+++ /dev/null
-#ifndef _I386_MATH_EMU_H
-#define _I386_MATH_EMU_H
-
-#include <asm/sigcontext.h>
-
-int restore_i387_soft(void *s387, struct _fpstate *buf);
-int save_i387_soft(void *s387, struct _fpstate * buf);
-
-/* This structure matches the layout of the data saved to the stack
- following a device-not-present interrupt, part of it saved
- automatically by the 80386/80486.
- */
-struct info {
- long ___orig_eip;
- long ___ebx;
- long ___ecx;
- long ___edx;
- long ___esi;
- long ___edi;
- long ___ebp;
- long ___eax;
- long ___ds;
- long ___es;
- long ___orig_eax;
- long ___eip;
- long ___cs;
- long ___eflags;
- long ___esp;
- long ___ss;
- long ___vm86_es; /* This and the following only in vm86 mode */
- long ___vm86_ds;
- long ___vm86_fs;
- long ___vm86_gs;
-};
-#endif
+++ /dev/null
-/*
- * Machine dependent access functions for RTC registers.
- */
-#ifndef _ASM_MC146818RTC_H
-#define _ASM_MC146818RTC_H
-
-#include <asm/io.h>
-
-#ifndef RTC_PORT
-#define RTC_PORT(x) (0x70 + (x))
-#define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */
-#endif
-
-/*
- * The yet supported machines all access the RTC index register via
- * an ISA port access but the way to access the date register differs ...
- */
-#define CMOS_READ(addr) ({ \
-outb_p((addr),RTC_PORT(0)); \
-inb_p(RTC_PORT(1)); \
-})
-#define CMOS_WRITE(val, addr) ({ \
-outb_p((addr),RTC_PORT(0)); \
-outb_p((val),RTC_PORT(1)); \
-})
-
-#define RTC_IRQ 8
-
-#endif /* _ASM_MC146818RTC_H */
+++ /dev/null
-#ifndef MCA_DMA_H
-#define MCA_DMA_H
-
-#include <asm/io.h>
-#include <linux/ioport.h>
-
-/*
- * Microchannel specific DMA stuff. DMA on an MCA machine is fairly similar to
- * standard PC dma, but it certainly has its quirks. DMA register addresses
- * are in a different place and there are some added functions. Most of this
- * should be pretty obvious on inspection. Note that the user must divide
- * count by 2 when using 16-bit dma; that is not handled by these functions.
- *
- * Ramen Noodles are yummy.
- *
- * 1998 Tymm Twillman <tymm@computer.org>
- */
-
-/*
- * Registers that are used by the DMA controller; FN is the function register
- * (tell the controller what to do) and EXE is the execution register (how
- * to do it)
- */
-
-#define MCA_DMA_REG_FN 0x18
-#define MCA_DMA_REG_EXE 0x1A
-
-/*
- * Functions that the DMA controller can do
- */
-
-#define MCA_DMA_FN_SET_IO 0x00
-#define MCA_DMA_FN_SET_ADDR 0x20
-#define MCA_DMA_FN_GET_ADDR 0x30
-#define MCA_DMA_FN_SET_COUNT 0x40
-#define MCA_DMA_FN_GET_COUNT 0x50
-#define MCA_DMA_FN_GET_STATUS 0x60
-#define MCA_DMA_FN_SET_MODE 0x70
-#define MCA_DMA_FN_SET_ARBUS 0x80
-#define MCA_DMA_FN_MASK 0x90
-#define MCA_DMA_FN_RESET_MASK 0xA0
-#define MCA_DMA_FN_MASTER_CLEAR 0xD0
-
-/*
- * Modes (used by setting MCA_DMA_FN_MODE in the function register)
- *
- * Note that the MODE_READ is read from memory (write to device), and
- * MODE_WRITE is vice-versa.
- */
-
-#define MCA_DMA_MODE_XFER 0x04 /* read by default */
-#define MCA_DMA_MODE_READ 0x04 /* same as XFER */
-#define MCA_DMA_MODE_WRITE 0x08 /* OR with MODE_XFER to use */
-#define MCA_DMA_MODE_IO 0x01 /* DMA from IO register */
-#define MCA_DMA_MODE_16 0x40 /* 16 bit xfers */
-
-
-/**
- * mca_enable_dma - channel to enable DMA on
- * @dmanr: DMA channel
- *
- * Enable the MCA bus DMA on a channel. This can be called from
- * IRQ context.
- */
-
-static __inline__ void mca_enable_dma(unsigned int dmanr)
-{
- outb(MCA_DMA_FN_RESET_MASK | dmanr, MCA_DMA_REG_FN);
-}
-
-/**
- * mca_disble_dma - channel to disable DMA on
- * @dmanr: DMA channel
- *
- * Enable the MCA bus DMA on a channel. This can be called from
- * IRQ context.
- */
-
-static __inline__ void mca_disable_dma(unsigned int dmanr)
-{
- outb(MCA_DMA_FN_MASK | dmanr, MCA_DMA_REG_FN);
-}
-
-/**
- * mca_set_dma_addr - load a 24bit DMA address
- * @dmanr: DMA channel
- * @a: 24bit bus address
- *
- * Load the address register in the DMA controller. This has a 24bit
- * limitation (16Mb).
- */
-
-static __inline__ void mca_set_dma_addr(unsigned int dmanr, unsigned int a)
-{
- outb(MCA_DMA_FN_SET_ADDR | dmanr, MCA_DMA_REG_FN);
- outb(a & 0xff, MCA_DMA_REG_EXE);
- outb((a >> 8) & 0xff, MCA_DMA_REG_EXE);
- outb((a >> 16) & 0xff, MCA_DMA_REG_EXE);
-}
-
-/**
- * mca_get_dma_addr - load a 24bit DMA address
- * @dmanr: DMA channel
- *
- * Read the address register in the DMA controller. This has a 24bit
- * limitation (16Mb). The return is a bus address.
- */
-
-static __inline__ unsigned int mca_get_dma_addr(unsigned int dmanr)
-{
- unsigned int addr;
-
- outb(MCA_DMA_FN_GET_ADDR | dmanr, MCA_DMA_REG_FN);
- addr = inb(MCA_DMA_REG_EXE);
- addr |= inb(MCA_DMA_REG_EXE) << 8;
- addr |= inb(MCA_DMA_REG_EXE) << 16;
-
- return addr;
-}
-
-/**
- * mca_set_dma_count - load a 16bit transfer count
- * @dmanr: DMA channel
- * @count: count
- *
- * Set the DMA count for this channel. This can be up to 64Kbytes.
- * Setting a count of zero will not do what you expect.
- */
-
-static __inline__ void mca_set_dma_count(unsigned int dmanr, unsigned int count)
-{
- count--; /* transfers one more than count -- correct for this */
-
- outb(MCA_DMA_FN_SET_COUNT | dmanr, MCA_DMA_REG_FN);
- outb(count & 0xff, MCA_DMA_REG_EXE);
- outb((count >> 8) & 0xff, MCA_DMA_REG_EXE);
-}
-
-/**
- * mca_get_dma_residue - get the remaining bytes to transfer
- * @dmanr: DMA channel
- *
- * This function returns the number of bytes left to transfer
- * on this DMA channel.
- */
-
-static __inline__ unsigned int mca_get_dma_residue(unsigned int dmanr)
-{
- unsigned short count;
-
- outb(MCA_DMA_FN_GET_COUNT | dmanr, MCA_DMA_REG_FN);
- count = 1 + inb(MCA_DMA_REG_EXE);
- count += inb(MCA_DMA_REG_EXE) << 8;
-
- return count;
-}
-
-/**
- * mca_set_dma_io - set the port for an I/O transfer
- * @dmanr: DMA channel
- * @io_addr: an I/O port number
- *
- * Unlike the ISA bus DMA controllers the DMA on MCA bus can transfer
- * with an I/O port target.
- */
-
-static __inline__ void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
-{
- /*
- * DMA from a port address -- set the io address
- */
-
- outb(MCA_DMA_FN_SET_IO | dmanr, MCA_DMA_REG_FN);
- outb(io_addr & 0xff, MCA_DMA_REG_EXE);
- outb((io_addr >> 8) & 0xff, MCA_DMA_REG_EXE);
-}
-
-/**
- * mca_set_dma_mode - set the DMA mode
- * @dmanr: DMA channel
- * @mode: mode to set
- *
- * The DMA controller supports several modes. The mode values you can
- * set are :
- *
- * %MCA_DMA_MODE_READ when reading from the DMA device.
- *
- * %MCA_DMA_MODE_WRITE to writing to the DMA device.
- *
- * %MCA_DMA_MODE_IO to do DMA to or from an I/O port.
- *
- * %MCA_DMA_MODE_16 to do 16bit transfers.
- *
- */
-
-static __inline__ void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
-{
- outb(MCA_DMA_FN_SET_MODE | dmanr, MCA_DMA_REG_FN);
- outb(mode, MCA_DMA_REG_EXE);
-}
-
-#endif /* MCA_DMA_H */
+++ /dev/null
-#ifndef __I386_MMAN_H__
-#define __I386_MMAN_H__
-
-#define PROT_READ 0x1 /* page can be read */
-#define PROT_WRITE 0x2 /* page can be written */
-#define PROT_EXEC 0x4 /* page can be executed */
-#define PROT_NONE 0x0 /* page can not be accessed */
-
-#define MAP_SHARED 0x01 /* Share changes */
-#define MAP_PRIVATE 0x02 /* Changes are private */
-#define MAP_TYPE 0x0f /* Mask for type of mapping */
-#define MAP_FIXED 0x10 /* Interpret addr exactly */
-#define MAP_ANONYMOUS 0x20 /* don't use a file */
-
-#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
-#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
-#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
-#define MAP_LOCKED 0x2000 /* pages are locked */
-#define MAP_NORESERVE 0x4000 /* don't check for reservations */
-
-#define MS_ASYNC 1 /* sync memory asynchronously */
-#define MS_INVALIDATE 2 /* invalidate the caches */
-#define MS_SYNC 4 /* synchronous memory sync */
-
-#define MCL_CURRENT 1 /* lock all current mappings */
-#define MCL_FUTURE 2 /* lock all future mappings */
-
-#define MADV_NORMAL 0x0 /* default page-in behavior */
-#define MADV_RANDOM 0x1 /* page-in minimum required */
-#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
-#define MADV_WILLNEED 0x3 /* pre-fault pages */
-#define MADV_DONTNEED 0x4 /* discard these pages */
-
-/* compatibility flags */
-#define MAP_ANON MAP_ANONYMOUS
-#define MAP_FILE 0
-
-#endif /* __I386_MMAN_H__ */
+++ /dev/null
-
-#ifndef __i386_MMU_H
-#define __i386_MMU_H
-
-#include <linux/list.h>
-
-/* describes dirrectly mapped vma nodes */
-typedef struct {
- struct list_head list;
- unsigned long vm_start;
- unsigned long vm_end;
-} direct_mmap_node_t;
-
-/*
- * The i386 doesn't have a mmu context, but
- * we put the segment information here.
- */
-typedef struct {
- void *segments;
- unsigned long cpuvalid;
- struct list_head direct_list;
-} mm_context_t;
-
-#endif
+++ /dev/null
-
-#ifndef __I386_MMU_CONTEXT_H
-#define __I386_MMU_CONTEXT_H
-
-#include <linux/config.h>
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
-
-/*
- * possibly do the LDT unload here?
- */
-
-extern int init_new_context(struct task_struct *tsk, struct mm_struct *);
-extern void destroy_context(struct mm_struct *);
-
-//#define destroy_context(mm) do { } while(0)
-//#define init_new_context(tsk,mm) 0
-
-#ifdef CONFIG_SMP
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk, unsigned cpu)
-{
- if(cpu_tlbstate[cpu].state == TLBSTATE_OK)
- cpu_tlbstate[cpu].state = TLBSTATE_LAZY;
-}
-#else
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk, unsigned cpu)
-{
-}
-#endif
-
-extern pgd_t *cur_pgd;
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk, unsigned cpu)
-{
- if (prev != next) {
- /* stop flush ipis for the previous mm */
- clear_bit(cpu, &prev->cpu_vm_mask);
- /*
- * Re-load LDT if necessary
- */
- if (prev->context.segments != next->context.segments)
- load_LDT(next);
-#ifdef CONFIG_SMP
- cpu_tlbstate[cpu].state = TLBSTATE_OK;
- cpu_tlbstate[cpu].active_mm = next;
-#endif
- set_bit(cpu, &next->cpu_vm_mask);
- set_bit(cpu, &next->context.cpuvalid);
- /* Re-load page tables */
- cur_pgd = next->pgd;
- queue_pt_switch(__pa(cur_pgd));
- XENO_flush_page_update_queue();
- }
-#ifdef CONFIG_SMP
- else {
- cpu_tlbstate[cpu].state = TLBSTATE_OK;
- if(cpu_tlbstate[cpu].active_mm != next)
- BUG();
- if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) {
- /* We were in lazy tlb mode and leave_mm disabled
- * tlb flush IPI delivery. We must flush our tlb.
- */
- local_flush_tlb();
- }
- if (!test_and_set_bit(cpu, &next->context.cpuvalid))
- load_LDT(next);
- }
-#endif
-}
-
-#define activate_mm(prev, next) \
- switch_mm((prev),(next),NULL,smp_processor_id())
-
-#endif
+++ /dev/null
-#ifndef _ASM_MMX_H
-#define _ASM_MMX_H
-
-/*
- * MMX 3Dnow! helper operations
- */
-
-#include <linux/types.h>
-
-extern void *_mmx_memcpy(void *to, const void *from, size_t size);
-extern void mmx_clear_page(void *page);
-extern void mmx_copy_page(void *to, void *from);
-
-#endif
+++ /dev/null
-#ifndef _ASM_I386_MODULE_H
-#define _ASM_I386_MODULE_H
-/*
- * This file contains the i386 architecture specific module code.
- */
-
-#define module_map(x) vmalloc(x)
-#define module_unmap(x) vfree(x)
-#define module_arch_init(x) (0)
-#define arch_init_modules(x) do { } while (0)
-
-#endif /* _ASM_I386_MODULE_H */
+++ /dev/null
-#ifndef __ASM_MPSPEC_H
-#define __ASM_MPSPEC_H
-
-/*
- * Structure definitions for SMP machines following the
- * Intel Multiprocessing Specification 1.1 and 1.4.
- */
-
-/*
- * This tag identifies where the SMP configuration
- * information is.
- */
-
-#define SMP_MAGIC_IDENT (('_'<<24)|('P'<<16)|('M'<<8)|'_')
-
-/*
- * a maximum of 16 APICs with the current APIC ID architecture.
- */
-#ifdef CONFIG_MULTIQUAD
-#define MAX_APICS 256
-#else /* !CONFIG_MULTIQUAD */
-#define MAX_APICS 16
-#endif /* CONFIG_MULTIQUAD */
-
-#define MAX_MPC_ENTRY 1024
-
-struct intel_mp_floating
-{
- char mpf_signature[4]; /* "_MP_" */
- unsigned long mpf_physptr; /* Configuration table address */
- unsigned char mpf_length; /* Our length (paragraphs) */
- unsigned char mpf_specification;/* Specification version */
- unsigned char mpf_checksum; /* Checksum (makes sum 0) */
- unsigned char mpf_feature1; /* Standard or configuration ? */
- unsigned char mpf_feature2; /* Bit7 set for IMCR|PIC */
- unsigned char mpf_feature3; /* Unused (0) */
- unsigned char mpf_feature4; /* Unused (0) */
- unsigned char mpf_feature5; /* Unused (0) */
-};
-
-struct mp_config_table
-{
- char mpc_signature[4];
-#define MPC_SIGNATURE "PCMP"
- unsigned short mpc_length; /* Size of table */
- char mpc_spec; /* 0x01 */
- char mpc_checksum;
- char mpc_oem[8];
- char mpc_productid[12];
- unsigned long mpc_oemptr; /* 0 if not present */
- unsigned short mpc_oemsize; /* 0 if not present */
- unsigned short mpc_oemcount;
- unsigned long mpc_lapic; /* APIC address */
- unsigned long reserved;
-};
-
-/* Followed by entries */
-
-#define MP_PROCESSOR 0
-#define MP_BUS 1
-#define MP_IOAPIC 2
-#define MP_INTSRC 3
-#define MP_LINTSRC 4
-#define MP_TRANSLATION 192 /* Used by IBM NUMA-Q to describe node locality */
-
-struct mpc_config_processor
-{
- unsigned char mpc_type;
- unsigned char mpc_apicid; /* Local APIC number */
- unsigned char mpc_apicver; /* Its versions */
- unsigned char mpc_cpuflag;
-#define CPU_ENABLED 1 /* Processor is available */
-#define CPU_BOOTPROCESSOR 2 /* Processor is the BP */
- unsigned long mpc_cpufeature;
-#define CPU_STEPPING_MASK 0x0F
-#define CPU_MODEL_MASK 0xF0
-#define CPU_FAMILY_MASK 0xF00
- unsigned long mpc_featureflag; /* CPUID feature value */
- unsigned long mpc_reserved[2];
-};
-
-struct mpc_config_bus
-{
- unsigned char mpc_type;
- unsigned char mpc_busid;
- unsigned char mpc_bustype[6] __attribute((packed));
-};
-
-/* List of Bus Type string values, Intel MP Spec. */
-#define BUSTYPE_EISA "EISA"
-#define BUSTYPE_ISA "ISA"
-#define BUSTYPE_INTERN "INTERN" /* Internal BUS */
-#define BUSTYPE_MCA "MCA"
-#define BUSTYPE_VL "VL" /* Local bus */
-#define BUSTYPE_PCI "PCI"
-#define BUSTYPE_PCMCIA "PCMCIA"
-#define BUSTYPE_CBUS "CBUS"
-#define BUSTYPE_CBUSII "CBUSII"
-#define BUSTYPE_FUTURE "FUTURE"
-#define BUSTYPE_MBI "MBI"
-#define BUSTYPE_MBII "MBII"
-#define BUSTYPE_MPI "MPI"
-#define BUSTYPE_MPSA "MPSA"
-#define BUSTYPE_NUBUS "NUBUS"
-#define BUSTYPE_TC "TC"
-#define BUSTYPE_VME "VME"
-#define BUSTYPE_XPRESS "XPRESS"
-
-struct mpc_config_ioapic
-{
- unsigned char mpc_type;
- unsigned char mpc_apicid;
- unsigned char mpc_apicver;
- unsigned char mpc_flags;
-#define MPC_APIC_USABLE 0x01
- unsigned long mpc_apicaddr;
-};
-
-struct mpc_config_intsrc
-{
- unsigned char mpc_type;
- unsigned char mpc_irqtype;
- unsigned short mpc_irqflag;
- unsigned char mpc_srcbus;
- unsigned char mpc_srcbusirq;
- unsigned char mpc_dstapic;
- unsigned char mpc_dstirq;
-};
-
-enum mp_irq_source_types {
- mp_INT = 0,
- mp_NMI = 1,
- mp_SMI = 2,
- mp_ExtINT = 3
-};
-
-#define MP_IRQDIR_DEFAULT 0
-#define MP_IRQDIR_HIGH 1
-#define MP_IRQDIR_LOW 3
-
-
-struct mpc_config_lintsrc
-{
- unsigned char mpc_type;
- unsigned char mpc_irqtype;
- unsigned short mpc_irqflag;
- unsigned char mpc_srcbusid;
- unsigned char mpc_srcbusirq;
- unsigned char mpc_destapic;
-#define MP_APIC_ALL 0xFF
- unsigned char mpc_destapiclint;
-};
-
-struct mp_config_oemtable
-{
- char oem_signature[4];
-#define MPC_OEM_SIGNATURE "_OEM"
- unsigned short oem_length; /* Size of table */
- char oem_rev; /* 0x01 */
- char oem_checksum;
- char mpc_oem[8];
-};
-
-struct mpc_config_translation
-{
- unsigned char mpc_type;
- unsigned char trans_len;
- unsigned char trans_type;
- unsigned char trans_quad;
- unsigned char trans_global;
- unsigned char trans_local;
- unsigned short trans_reserved;
-};
-
-/*
- * Default configurations
- *
- * 1 2 CPU ISA 82489DX
- * 2 2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
- * 3 2 CPU EISA 82489DX
- * 4 2 CPU MCA 82489DX
- * 5 2 CPU ISA+PCI
- * 6 2 CPU EISA+PCI
- * 7 2 CPU MCA+PCI
- */
-
-#ifdef CONFIG_MULTIQUAD
-#define MAX_IRQ_SOURCES 512
-#else /* !CONFIG_MULTIQUAD */
-#define MAX_IRQ_SOURCES 256
-#endif /* CONFIG_MULTIQUAD */
-
-#define MAX_MP_BUSSES 32
-enum mp_bustype {
- MP_BUS_ISA = 1,
- MP_BUS_EISA,
- MP_BUS_PCI,
- MP_BUS_MCA
-};
-extern int mp_bus_id_to_type [MAX_MP_BUSSES];
-extern int mp_bus_id_to_pci_bus [MAX_MP_BUSSES];
-
-extern unsigned int boot_cpu_physical_apicid;
-extern unsigned long phys_cpu_present_map;
-extern int smp_found_config;
-extern void find_smp_config (void);
-extern void get_smp_config (void);
-extern int nr_ioapics;
-extern int apic_version [MAX_APICS];
-extern int mp_bus_id_to_type [MAX_MP_BUSSES];
-extern int mp_irq_entries;
-extern struct mpc_config_intsrc mp_irqs [MAX_IRQ_SOURCES];
-extern int mpc_default_type;
-extern int mp_bus_id_to_pci_bus [MAX_MP_BUSSES];
-extern int mp_current_pci_id;
-extern unsigned long mp_lapic_addr;
-extern int pic_mode;
-extern int using_apic_timer;
-
-#endif
-
+++ /dev/null
-#ifndef _I386_MSGBUF_H
-#define _I386_MSGBUF_H
-
-/*
- * The msqid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
- struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
- unsigned long __unused1;
- __kernel_time_t msg_rtime; /* last msgrcv time */
- unsigned long __unused2;
- __kernel_time_t msg_ctime; /* last change time */
- unsigned long __unused3;
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-#endif /* _I386_MSGBUF_H */
+++ /dev/null
-#ifndef __ASM_MSR_H
-#define __ASM_MSR_H
-
-/*
- * Access to machine-specific registers (available on 586 and better only)
- * Note: the rd* operations modify the parameters directly (without using
- * pointer indirection), this allows gcc to optimize better
- */
-
-#define rdmsr(msr,val1,val2) \
- __asm__ __volatile__("rdmsr" \
- : "=a" (val1), "=d" (val2) \
- : "c" (msr))
-
-#define wrmsr(msr,val1,val2) \
- __asm__ __volatile__("wrmsr" \
- : /* no outputs */ \
- : "c" (msr), "a" (val1), "d" (val2))
-
-#define rdtsc(low,high) \
- __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))
-
-#define rdtscl(low) \
- __asm__ __volatile__("rdtsc" : "=a" (low) : : "edx")
-
-#define rdtscll(val) \
- __asm__ __volatile__("rdtsc" : "=A" (val))
-
-#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
-
-#define rdpmc(counter,low,high) \
- __asm__ __volatile__("rdpmc" \
- : "=a" (low), "=d" (high) \
- : "c" (counter))
-
-/* symbolic names for some interesting MSRs */
-/* Intel defined MSRs. */
-#define MSR_IA32_P5_MC_ADDR 0
-#define MSR_IA32_P5_MC_TYPE 1
-#define MSR_IA32_PLATFORM_ID 0x17
-#define MSR_IA32_EBL_CR_POWERON 0x2a
-
-#define MSR_IA32_APICBASE 0x1b
-#define MSR_IA32_APICBASE_BSP (1<<8)
-#define MSR_IA32_APICBASE_ENABLE (1<<11)
-#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
-
-#define MSR_IA32_UCODE_WRITE 0x79
-#define MSR_IA32_UCODE_REV 0x8b
-
-#define MSR_IA32_PERFCTR0 0xc1
-#define MSR_IA32_PERFCTR1 0xc2
-
-#define MSR_IA32_BBL_CR_CTL 0x119
-
-#define MSR_IA32_MCG_CAP 0x179
-#define MSR_IA32_MCG_STATUS 0x17a
-#define MSR_IA32_MCG_CTL 0x17b
-
-#define MSR_IA32_EVNTSEL0 0x186
-#define MSR_IA32_EVNTSEL1 0x187
-
-#define MSR_IA32_DEBUGCTLMSR 0x1d9
-#define MSR_IA32_LASTBRANCHFROMIP 0x1db
-#define MSR_IA32_LASTBRANCHTOIP 0x1dc
-#define MSR_IA32_LASTINTFROMIP 0x1dd
-#define MSR_IA32_LASTINTTOIP 0x1de
-
-#define MSR_IA32_MC0_CTL 0x400
-#define MSR_IA32_MC0_STATUS 0x401
-#define MSR_IA32_MC0_ADDR 0x402
-#define MSR_IA32_MC0_MISC 0x403
-
-/* AMD Defined MSRs */
-#define MSR_K6_EFER 0xC0000080
-#define MSR_K6_STAR 0xC0000081
-#define MSR_K6_WHCR 0xC0000082
-#define MSR_K6_UWCCR 0xC0000085
-#define MSR_K6_PSOR 0xC0000087
-#define MSR_K6_PFIR 0xC0000088
-
-#define MSR_K7_EVNTSEL0 0xC0010000
-#define MSR_K7_PERFCTR0 0xC0010004
-
-/* Centaur-Hauls/IDT defined MSRs. */
-#define MSR_IDT_FCR1 0x107
-#define MSR_IDT_FCR2 0x108
-#define MSR_IDT_FCR3 0x109
-#define MSR_IDT_FCR4 0x10a
-
-#define MSR_IDT_MCR0 0x110
-#define MSR_IDT_MCR1 0x111
-#define MSR_IDT_MCR2 0x112
-#define MSR_IDT_MCR3 0x113
-#define MSR_IDT_MCR4 0x114
-#define MSR_IDT_MCR5 0x115
-#define MSR_IDT_MCR6 0x116
-#define MSR_IDT_MCR7 0x117
-#define MSR_IDT_MCR_CTRL 0x120
-
-/* VIA Cyrix defined MSRs*/
-#define MSR_VIA_FCR 0x1107
-
-#endif /* __ASM_MSR_H */
+++ /dev/null
-/* Generic MTRR (Memory Type Range Register) ioctls.
-
- Copyright (C) 1997-1999 Richard Gooch
-
- This library is free software; you can redistribute it and/or
- modify it under the terms of the GNU Library General Public
- License as published by the Free Software Foundation; either
- version 2 of the License, or (at your option) any later version.
-
- This library is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- Library General Public License for more details.
-
- You should have received a copy of the GNU Library General Public
- License along with this library; if not, write to the Free
- Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-
- Richard Gooch may be reached by email at rgooch@atnf.csiro.au
- The postal address is:
- Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
-*/
-#ifndef _LINUX_MTRR_H
-#define _LINUX_MTRR_H
-
-#include <linux/config.h>
-#include <linux/ioctl.h>
-
-#define MTRR_IOCTL_BASE 'M'
-
-struct mtrr_sentry
-{
- unsigned long base; /* Base address */
- unsigned long size; /* Size of region */
- unsigned int type; /* Type of region */
-};
-
-struct mtrr_gentry
-{
- unsigned int regnum; /* Register number */
- unsigned long base; /* Base address */
- unsigned long size; /* Size of region */
- unsigned int type; /* Type of region */
-};
-
-/* These are the various ioctls */
-#define MTRRIOC_ADD_ENTRY _IOW(MTRR_IOCTL_BASE, 0, struct mtrr_sentry)
-#define MTRRIOC_SET_ENTRY _IOW(MTRR_IOCTL_BASE, 1, struct mtrr_sentry)
-#define MTRRIOC_DEL_ENTRY _IOW(MTRR_IOCTL_BASE, 2, struct mtrr_sentry)
-#define MTRRIOC_GET_ENTRY _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
-#define MTRRIOC_KILL_ENTRY _IOW(MTRR_IOCTL_BASE, 4, struct mtrr_sentry)
-#define MTRRIOC_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 5, struct mtrr_sentry)
-#define MTRRIOC_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 6, struct mtrr_sentry)
-#define MTRRIOC_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 7, struct mtrr_sentry)
-#define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
-#define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry)
-
-/* These are the region types */
-#define MTRR_TYPE_UNCACHABLE 0
-#define MTRR_TYPE_WRCOMB 1
-/*#define MTRR_TYPE_ 2*/
-/*#define MTRR_TYPE_ 3*/
-#define MTRR_TYPE_WRTHROUGH 4
-#define MTRR_TYPE_WRPROT 5
-#define MTRR_TYPE_WRBACK 6
-#define MTRR_NUM_TYPES 7
-
-#ifdef MTRR_NEED_STRINGS
-static char *mtrr_strings[MTRR_NUM_TYPES] =
-{
- "uncachable", /* 0 */
- "write-combining", /* 1 */
- "?", /* 2 */
- "?", /* 3 */
- "write-through", /* 4 */
- "write-protect", /* 5 */
- "write-back", /* 6 */
-};
-#endif
-
-#ifdef __KERNEL__
-
-/* The following functions are for use by other drivers */
-# ifdef CONFIG_MTRR
-extern int mtrr_add (unsigned long base, unsigned long size,
- unsigned int type, char increment);
-extern int mtrr_add_page (unsigned long base, unsigned long size,
- unsigned int type, char increment);
-extern int mtrr_del (int reg, unsigned long base, unsigned long size);
-extern int mtrr_del_page (int reg, unsigned long base, unsigned long size);
-extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
-# else
-static __inline__ int mtrr_add (unsigned long base, unsigned long size,
- unsigned int type, char increment)
-{
- return -ENODEV;
-}
-static __inline__ int mtrr_add_page (unsigned long base, unsigned long size,
- unsigned int type, char increment)
-{
- return -ENODEV;
-}
-static __inline__ int mtrr_del (int reg, unsigned long base,
- unsigned long size)
-{
- return -ENODEV;
-}
-static __inline__ int mtrr_del_page (int reg, unsigned long base,
- unsigned long size)
-{
- return -ENODEV;
-}
-
-static __inline__ void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) {;}
-
-# endif
-
-/* The following functions are for initialisation: don't use them! */
-extern int mtrr_init (void);
-# if defined(CONFIG_SMP) && defined(CONFIG_MTRR)
-extern void mtrr_init_boot_cpu (void);
-extern void mtrr_init_secondary_cpu (void);
-# endif
-
-#endif
-
-#endif /* _LINUX_MTRR_H */
+++ /dev/null
-/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $
- * linux/include/asm-i386/namei.h
- *
- * Included from linux/fs/namei.c
- */
-
-#ifndef __I386_NAMEI_H
-#define __I386_NAMEI_H
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-
-#define __emul_prefix() NULL
-
-#endif /* __I386_NAMEI_H */
+++ /dev/null
-#ifndef _I386_PAGE_H
-#define _I386_PAGE_H
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT 12
-#define PAGE_SIZE (1UL << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE-1))
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/config.h>
-#include <asm/hypervisor.h>
-
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-#define clear_page(page) mmx_clear_page((void *)(page))
-#define copy_page(to,from) mmx_copy_page(to,from)
-
-#else
-
-/*
- * On older X86 processors its not a win to use MMX here it seems.
- * Maybe the K6-III ?
- */
-
-#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
-#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE)
-
-#endif
-
-#define clear_user_page(page, vaddr) clear_page(page)
-#define copy_user_page(to, from, vaddr) copy_page(to, from)
-
-/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
-extern unsigned long *phys_to_machine_mapping;
-#define pfn_to_mfn(_pfn) (phys_to_machine_mapping[(_pfn)])
-#define mfn_to_pfn(_mfn) (machine_to_phys_mapping[(_mfn)])
-static inline unsigned long phys_to_machine(unsigned long phys)
-{
- unsigned long machine = pfn_to_mfn(phys >> PAGE_SHIFT);
- machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK);
- return machine;
-}
-static inline unsigned long machine_to_phys(unsigned long machine)
-{
- unsigned long phys = mfn_to_pfn(machine >> PAGE_SHIFT);
- phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK);
- return phys;
-}
-
-/*
- * These are used to make use of C type-checking..
- */
-#if CONFIG_X86_PAE
-typedef struct { unsigned long pte_low, pte_high; } pte_t;
-typedef struct { unsigned long long pmd; } pmd_t;
-typedef struct { unsigned long long pgd; } pgd_t;
-#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
-#else
-typedef struct { unsigned long pte_low; } pte_t;
-typedef struct { unsigned long pmd; } pmd_t;
-typedef struct { unsigned long pgd; } pgd_t;
-static inline unsigned long pte_val(pte_t x)
-{
- unsigned long ret = x.pte_low;
- if ( (ret & 1) ) ret = machine_to_phys(ret);
- return ret;
-}
-#endif
-#define PTE_MASK PAGE_MASK
-
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-static inline unsigned long pmd_val(pmd_t x)
-{
- unsigned long ret = x.pmd;
- if ( (ret & 1) ) ret = machine_to_phys(ret);
- return ret;
-}
-#define pgd_val(x) ({ BUG(); (unsigned long)0; })
-#define pgprot_val(x) ((x).pgprot)
-
-static inline pte_t __pte(unsigned long x)
-{
- if ( (x & 1) ) x = phys_to_machine(x);
- return ((pte_t) { (x) });
-}
-static inline pmd_t __pmd(unsigned long x)
-{
- if ( (x & 1) ) x = phys_to_machine(x);
- return ((pmd_t) { (x) });
-}
-#define __pgd(x) ({ BUG(); (pgprot_t) { 0 }; })
-#define __pgprot(x) ((pgprot_t) { (x) } )
-
-#endif /* !__ASSEMBLY__ */
-
-/* to align the pointer to the (next) page boundary */
-#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
-
-/*
- * This handles the memory map.. We could make this a config
- * option, but too many people screw it up, and too few need
- * it.
- *
- * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
- * a virtual address space of one gigabyte, which limits the
- * amount of physical memory you can use to about 950MB.
- *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
- */
-
-#define __PAGE_OFFSET (0xC0000000)
-
-#ifndef __ASSEMBLY__
-
-/*
- * Tell the user there is some problem. Beep too, so we can
- * see^H^H^Hhear bugs in early bootup as well!
- */
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-extern void do_BUG(const char *file, int line);
-#define BUG() do { \
- do_BUG(__FILE__, __LINE__); \
- __asm__ __volatile__("ud2"); \
-} while (0)
-#else
-#define BUG() __asm__ __volatile__(".byte 0x0f,0x0b")
-#endif
-
-#define PAGE_BUG(page) do { \
- BUG(); \
-} while (0)
-
-/* Pure 2^n version of get_order */
-static __inline__ int get_order(unsigned long size)
-{
- int order;
-
- size = (size-1) >> (PAGE_SHIFT-1);
- order = -1;
- do {
- size >>= 1;
- order++;
- } while (size);
- return order;
-}
-
-#endif /* __ASSEMBLY__ */
-
-#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET)
-#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET)
-#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
-#define virt_to_page(kaddr) (mem_map + (__pa(kaddr) >> PAGE_SHIFT))
-#define VALID_PAGE(page) ((page - mem_map) < max_mapnr)
-
-#endif /* __KERNEL__ */
-
-#endif /* _I386_PAGE_H */
+++ /dev/null
-#ifndef _ASMi386_PARAM_H
-#define _ASMi386_PARAM_H
-
-#ifndef HZ
-#define HZ 100
-#endif
-
-#define EXEC_PAGESIZE 4096
-
-#ifndef NGROUPS
-#define NGROUPS 32
-#endif
-
-#ifndef NOGROUP
-#define NOGROUP (-1)
-#endif
-
-#define MAXHOSTNAMELEN 64 /* max length of hostname */
-
-#ifdef __KERNEL__
-# define CLOCKS_PER_SEC 100 /* frequency at which times() counts */
-#endif
-
-#endif
+++ /dev/null
-/*
- * parport.h: ia32-specific parport initialisation
- *
- * Copyright (C) 1999, 2000 Tim Waugh <tim@cyberelk.demon.co.uk>
- *
- * This file should only be included by drivers/parport/parport_pc.c.
- */
-
-#ifndef _ASM_I386_PARPORT_H
-#define _ASM_I386_PARPORT_H 1
-
-static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
-static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
-{
- return parport_pc_find_isa_ports (autoirq, autodma);
-}
-
-#endif /* !(_ASM_I386_PARPORT_H) */
+++ /dev/null
-#ifndef _I386_PGALLOC_H
-#define _I386_PGALLOC_H
-
-#include <linux/config.h>
-#include <asm/processor.h>
-#include <asm/hypervisor.h>
-#include <linux/threads.h>
-
-/*
- * Quick lists are aligned so that least significant bits of array pointer
- * are all zero when list is empty, and all one when list is full.
- */
-#define QUICKLIST_ENTRIES 256
-#define QUICKLIST_EMPTY(_l) !((unsigned long)(_l) & ((QUICKLIST_ENTRIES*4)-1))
-#define QUICKLIST_FULL(_l) QUICKLIST_EMPTY((_l)+1)
-#define pgd_quicklist (current_cpu_data.pgd_quick)
-#define pmd_quicklist (current_cpu_data.pmd_quick)
-#define pte_quicklist (current_cpu_data.pte_quick)
-#define pgtable_cache_size (current_cpu_data.pgtable_cache_sz)
-
-#define pmd_populate(mm, pmd, pte) \
- do { \
- set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \
- XENO_flush_page_update_queue(); \
- } while ( 0 )
-
-static __inline__ pgd_t *get_pgd_slow(void)
-{
- pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
- pgd_t *kpgd;
- pmd_t *kpmd;
- pte_t *kpte;
-
- if (pgd) {
- memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
- memcpy(pgd + USER_PTRS_PER_PGD,
- init_mm.pgd + USER_PTRS_PER_PGD,
- (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
- kpgd = pgd_offset_k((unsigned long)pgd);
- kpmd = pmd_offset(kpgd, (unsigned long)pgd);
- kpte = pte_offset(kpmd, (unsigned long)pgd);
- queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)&~_PAGE_RW);
- queue_pgd_pin(__pa(pgd));
- }
-
- return pgd;
-}
-
-static __inline__ void free_pgd_slow(pgd_t *pgd)
-{
- pgd_t *kpgd;
- pmd_t *kpmd;
- pte_t *kpte;
- queue_pgd_unpin(__pa(pgd));
- kpgd = pgd_offset_k((unsigned long)pgd);
- kpmd = pmd_offset(kpgd, (unsigned long)pgd);
- kpte = pte_offset(kpmd, (unsigned long)pgd);
- queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)|_PAGE_RW);
- free_page((unsigned long)pgd);
-}
-
-static __inline__ pgd_t *get_pgd_fast(void)
-{
- unsigned long ret;
-
- if ( !QUICKLIST_EMPTY(pgd_quicklist) ) {
- ret = *(--pgd_quicklist);
- pgtable_cache_size--;
- } else
- ret = (unsigned long)get_pgd_slow();
- return (pgd_t *)ret;
-}
-
-static __inline__ void free_pgd_fast(pgd_t *pgd)
-{
- if ( !QUICKLIST_FULL(pgd_quicklist) ) {
- *(pgd_quicklist++) = (unsigned long)pgd;
- pgtable_cache_size++;
- } else
- free_pgd_slow(pgd);
-}
-
-static inline pte_t *pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
- pte_t *pte;
- pgd_t *kpgd;
- pmd_t *kpmd;
- pte_t *kpte;
-
- pte = (pte_t *) __get_free_page(GFP_KERNEL);
- if (pte)
- {
- clear_page(pte);
- kpgd = pgd_offset_k((unsigned long)pte);
- kpmd = pmd_offset(kpgd, (unsigned long)pte);
- kpte = pte_offset(kpmd, (unsigned long)pte);
- queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)&~_PAGE_RW);
- queue_pte_pin(__pa(pte));
- }
- return pte;
-}
-
-static __inline__ void pte_free_slow(pte_t *pte)
-{
- pgd_t *kpgd;
- pmd_t *kpmd;
- pte_t *kpte;
- queue_pte_unpin(__pa(pte));
- kpgd = pgd_offset_k((unsigned long)pte);
- kpmd = pmd_offset(kpgd, (unsigned long)pte);
- kpte = pte_offset(kpmd, (unsigned long)pte);
- queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)|_PAGE_RW);
- free_page((unsigned long)pte);
-}
-
-static inline pte_t *pte_alloc_one_fast(struct mm_struct *mm, unsigned long address)
-{
- unsigned long ret = 0;
- if ( !QUICKLIST_EMPTY(pte_quicklist) ) {
- ret = *(--pte_quicklist);
- pgtable_cache_size--;
- }
- return (pte_t *)ret;
-}
-
-static __inline__ void pte_free_fast(pte_t *pte)
-{
- if ( !QUICKLIST_FULL(pte_quicklist) ) {
- *(pte_quicklist++) = (unsigned long)pte;
- pgtable_cache_size++;
- } else
- pte_free_slow(pte);
-}
-
-#define pte_free(pte) pte_free_fast(pte)
-#define pgd_alloc(mm) get_pgd_fast()
-#define pgd_free(pgd) free_pgd_fast(pgd)
-
-#define pmd_alloc_one_fast(mm, addr) ({ BUG(); ((pmd_t *)1); })
-#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
-#define pmd_free_slow(x) do { } while (0)
-#define pmd_free_fast(x) do { } while (0)
-#define pmd_free(x) do { } while (0)
-#define pgd_populate(mm, pmd, pte) BUG()
-
-extern int do_check_pgt_cache(int, int);
-
-/*
- * - flush_tlb() flushes the current mm struct TLBs
- * - flush_tlb_all() flushes all processes TLBs
- * - flush_tlb_mm(mm) flushes the specified mm context TLB's
- * - flush_tlb_page(vma, vmaddr) flushes one page
- * - flush_tlb_range(mm, start, end) flushes a range of pages
- * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
- */
-
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
- if ( mm == current->active_mm ) queue_tlb_flush();
- XENO_flush_page_update_queue();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
- unsigned long addr)
-{
- if ( vma->vm_mm == current->active_mm ) queue_invlpg(addr);
- XENO_flush_page_update_queue();
-}
-
-static inline void flush_tlb_range(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- if ( mm == current->active_mm ) queue_tlb_flush();
- XENO_flush_page_update_queue();
-}
-
-static inline void flush_tlb_pgtables(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- /* i386 does not keep any page table caches in TLB */
- XENO_flush_page_update_queue();
-}
-
-#endif /* _I386_PGALLOC_H */
+++ /dev/null
-#ifndef _I386_PGTABLE_2LEVEL_H
-#define _I386_PGTABLE_2LEVEL_H
-
-/*
- * traditional i386 two-level paging structure:
- */
-
-#define PGDIR_SHIFT 22
-#define PTRS_PER_PGD 1024
-
-/*
- * the i386 is two-level, so we don't really have any
- * PMD directory physically.
- */
-#define PMD_SHIFT 22
-#define PTRS_PER_PMD 1
-
-#define PTRS_PER_PTE 1024
-
-#define pte_ERROR(e) \
- printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
-#define pmd_ERROR(e) \
- printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
-#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-static inline int pgd_none(pgd_t pgd) { return 0; }
-static inline int pgd_bad(pgd_t pgd) { return 0; }
-static inline int pgd_present(pgd_t pgd) { return 1; }
-#define pgd_clear(xp) do { } while (0)
-
-#define set_pte(pteptr, pteval) queue_l1_entry_update(__pa(pteptr), (pteval).pte_low)
-#define set_pmd(pmdptr, pmdval) queue_l2_entry_update(__pa(pmdptr), (pmdval).pmd)
-#define set_pgd(pgdptr, pgdval) ((void)0)
-
-#define pgd_page(pgd) \
-((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
-
-static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
-{
- return (pmd_t *) dir;
-}
-
-/*
- * A note on implementation of this atomic 'get-and-clear' operation.
- * This is actually very simple because XenoLinux can only run on a single
- * processor. Therefore, we cannot race other processors setting the 'accessed'
- * or 'dirty' bits on a page-table entry.
- * Even if pages are shared between domains, that is not a problem because
- * each domain will have separate page tables, with their own versions of
- * accessed & dirty state.
- */
-static inline pte_t ptep_get_and_clear(pte_t *xp)
-{
- pte_t pte = *xp;
- queue_l1_entry_update(__pa(xp), 0);
- return pte;
-}
-
-#define pte_same(a, b) ((a).pte_low == (b).pte_low)
-#define pte_page(x) (mem_map+((unsigned long)((pte_val(x) >> PAGE_SHIFT))))
-#define pte_none(x) (!(x).pte_low)
-#define __mk_pte(page_nr,pgprot) __pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
-
-#endif /* _I386_PGTABLE_2LEVEL_H */
+++ /dev/null
-#ifndef _I386_PGTABLE_3LEVEL_H
-#define _I386_PGTABLE_3LEVEL_H
-
-#error "PAE unsupported"
-
-/*
- * Intel Physical Address Extension (PAE) Mode - three-level page
- * tables on PPro+ CPUs.
- *
- * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
- */
-
-/*
- * PGDIR_SHIFT determines what a top-level page table entry can map
- */
-#define PGDIR_SHIFT 30
-#define PTRS_PER_PGD 4
-
-/*
- * PMD_SHIFT determines the size of the area a middle-level
- * page table can map
- */
-#define PMD_SHIFT 21
-#define PTRS_PER_PMD 512
-
-/*
- * entries per page directory level
- */
-#define PTRS_PER_PTE 512
-
-#define pte_ERROR(e) \
- printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
-#define pmd_ERROR(e) \
- printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
-#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
-
-static inline int pgd_none(pgd_t pgd) { return 0; }
-static inline int pgd_bad(pgd_t pgd) { return 0; }
-static inline int pgd_present(pgd_t pgd) { return 1; }
-
-/* Rules for using set_pte: the pte being assigned *must* be
- * either not present or in a state where the hardware will
- * not attempt to update the pte. In places where this is
- * not possible, use pte_get_and_clear to obtain the old pte
- * value and then use set_pte to update it. -ben
- */
-static inline void set_pte(pte_t *ptep, pte_t pte)
-{
- ptep->pte_high = pte.pte_high;
- smp_wmb();
- ptep->pte_low = pte.pte_low;
-}
-#define set_pmd(pmdptr,pmdval) \
- set_64bit((unsigned long long *)(pmdptr),pmd_val(pmdval))
-#define set_pgd(pgdptr,pgdval) \
- set_64bit((unsigned long long *)(pgdptr),pgd_val(pgdval))
-
-/*
- * Pentium-II erratum A13: in PAE mode we explicitly have to flush
- * the TLB via cr3 if the top-level pgd is changed...
- * We do not let the generic code free and clear pgd entries due to
- * this erratum.
- */
-static inline void pgd_clear (pgd_t * pgd) { }
-
-#define pgd_page(pgd) \
-((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, address) ((pmd_t *) pgd_page(*(dir)) + \
- __pmd_offset(address))
-
-static inline pte_t ptep_get_and_clear(pte_t *ptep)
-{
- pte_t res;
-
- /* xchg acts as a barrier before the setting of the high bits */
- res.pte_low = xchg(&ptep->pte_low, 0);
- res.pte_high = ptep->pte_high;
- ptep->pte_high = 0;
-
- return res;
-}
-
-static inline int pte_same(pte_t a, pte_t b)
-{
- return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
-}
-
-#define pte_page(x) (mem_map+(((x).pte_low >> PAGE_SHIFT) | ((x).pte_high << (32 - PAGE_SHIFT))))
-#define pte_none(x) (!(x).pte_low && !(x).pte_high)
-
-static inline pte_t __mk_pte(unsigned long page_nr, pgprot_t pgprot)
-{
- pte_t pte;
-
- pte.pte_high = page_nr >> (32 - PAGE_SHIFT);
- pte.pte_low = (page_nr << PAGE_SHIFT) | pgprot_val(pgprot);
- return pte;
-}
-
-#endif /* _I386_PGTABLE_3LEVEL_H */
+++ /dev/null
-#ifndef _I386_PGTABLE_H
-#define _I386_PGTABLE_H
-
-#include <linux/config.h>
-
-#define HAVE_ARCH_UNMAPPED_AREA
-
-/*
- * The Linux memory management assumes a three-level page table setup. On
- * the i386, we use that, but "fold" the mid level into the top-level page
- * table, so that we physically have the same two-level page table as the
- * i386 mmu expects.
- *
- * This file contains the functions and defines necessary to modify and use
- * the i386 page table tree.
- */
-#ifndef __ASSEMBLY__
-#include <asm/processor.h>
-#include <asm/hypervisor.h>
-#include <linux/threads.h>
-#include <asm/fixmap.h>
-
-#ifndef _I386_BITOPS_H
-#include <asm/bitops.h>
-#endif
-
-#define swapper_pg_dir 0
-extern void paging_init(void);
-
-/* Caches aren't brain-dead on the intel. */
-#define flush_cache_all() do { } while (0)
-#define flush_cache_mm(mm) do { } while (0)
-#define flush_cache_range(mm, start, end) do { } while (0)
-#define flush_cache_page(vma, vmaddr) do { } while (0)
-#define flush_page_to_ram(page) do { } while (0)
-#define flush_dcache_page(page) do { } while (0)
-#define flush_icache_range(start, end) do { } while (0)
-#define flush_icache_page(vma,pg) do { } while (0)
-
-extern unsigned long pgkern_mask;
-
-#define __flush_tlb() ({ queue_tlb_flush(); XENO_flush_page_update_queue(); })
-#define __flush_tlb_global() __flush_tlb()
-#define __flush_tlb_all() __flush_tlb_global()
-#define __flush_tlb_one(addr) ({ queue_invlpg(addr); XENO_flush_page_update_queue(); })
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[1024];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * The Linux x86 paging architecture is 'compile-time dual-mode', it
- * implements both the traditional 2-level x86 page tables and the
- * newer 3-level PAE-mode page tables.
- */
-#ifndef __ASSEMBLY__
-#if CONFIG_X86_PAE
-# include <asm/pgtable-3level.h>
-
-/*
- * Need to initialise the X86 PAE caches
- */
-extern void pgtable_cache_init(void);
-
-#else
-# include <asm/pgtable-2level.h>
-
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init() do { } while (0)
-
-#endif
-#endif
-
-#define PMD_SIZE (1UL << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
-#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
-
-#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
-#define FIRST_USER_PGD_NR 0
-
-#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
-#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
-
-#define TWOLEVEL_PGDIR_SHIFT 22
-#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
-#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
-
-
-#ifndef __ASSEMBLY__
-/* 4MB is just a nice "safety zone". Also, we align to a fresh pde. */
-#define VMALLOC_OFFSET (4*1024*1024)
-#define VMALLOC_START (((unsigned long) high_memory + 2*VMALLOC_OFFSET-1) & \
- ~(VMALLOC_OFFSET-1))
-#define VMALLOC_VMADDR(x) ((unsigned long)(x))
-#define VMALLOC_END (FIXADDR_START - 2*PAGE_SIZE)
-
-#define _PAGE_BIT_PRESENT 0
-#define _PAGE_BIT_RW 1
-#define _PAGE_BIT_USER 2
-#define _PAGE_BIT_PWT 3
-#define _PAGE_BIT_PCD 4
-#define _PAGE_BIT_ACCESSED 5
-#define _PAGE_BIT_DIRTY 6
-#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */
-#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
-
-#define _PAGE_PRESENT 0x001
-#define _PAGE_RW 0x002
-#define _PAGE_USER 0x004
-#define _PAGE_PWT 0x008
-#define _PAGE_PCD 0x010
-#define _PAGE_ACCESSED 0x020
-#define _PAGE_DIRTY 0x040
-#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
-#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
-
-#define _PAGE_PROTNONE 0x080 /* If not present */
-
-#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-
-#define __PAGE_KERNEL \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-#define __PAGE_KERNEL_NOCACHE \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED)
-#define __PAGE_KERNEL_RO \
- (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED)
-
-#if 0
-#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
-#else
-#define MAKE_GLOBAL(x) __pgprot(x)
-#endif
-
-#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
-
-/*
- * The i386 can't do page protection for execute, and considers that
- * the same are read. Also, write permissions imply read permissions.
- * This is the closest we can get..
- */
-#define __P000 PAGE_NONE
-#define __P001 PAGE_READONLY
-#define __P010 PAGE_COPY
-#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY
-#define __P101 PAGE_READONLY
-#define __P110 PAGE_COPY
-#define __P111 PAGE_COPY
-
-#define __S000 PAGE_NONE
-#define __S001 PAGE_READONLY
-#define __S010 PAGE_SHARED
-#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY
-#define __S101 PAGE_READONLY
-#define __S110 PAGE_SHARED
-#define __S111 PAGE_SHARED
-
-#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-#define pte_clear(xp) queue_l1_entry_update(__pa(xp), 0)
-
-#define pmd_none(x) (!(x).pmd)
-#define pmd_present(x) ((x).pmd & _PAGE_PRESENT)
-#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
-#define pmd_bad(x) (((x).pmd & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-
-/*
- * Permanent address of a page. Obviously must never be
- * called on a highmem page.
- */
-#define page_address(page) ((page)->virtual)
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
-static inline int pte_exec(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
-static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; }
-static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; }
-static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; }
-
-static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
-static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
-static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
-static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
-static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; }
-static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
-static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
-static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; }
-static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
-static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; }
-
-static inline int ptep_test_and_clear_dirty(pte_t *ptep)
-{
- unsigned long pteval = *(unsigned long *)ptep;
- int ret = pteval & _PAGE_DIRTY;
- if ( ret ) queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_DIRTY);
- return ret;
-}
-static inline int ptep_test_and_clear_young(pte_t *ptep)
-{
- unsigned long pteval = *(unsigned long *)ptep;
- int ret = pteval & _PAGE_ACCESSED;
- if ( ret ) queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_ACCESSED);
- return ret;
-}
-static inline void ptep_set_wrprotect(pte_t *ptep)
-{
- unsigned long pteval = *(unsigned long *)ptep;
- if ( (pteval & _PAGE_RW) )
- queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_RW);
-}
-static inline void ptep_mkdirty(pte_t *ptep)
-{
- unsigned long pteval = *(unsigned long *)ptep;
- if ( !(pteval & _PAGE_DIRTY) )
- queue_l1_entry_update(__pa(ptep), pteval | _PAGE_DIRTY);
-}
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-
-#define mk_pte(page, pgprot) __mk_pte((page) - mem_map, (pgprot))
-
-/* This takes a physical page address that is used by the remapping functions */
-#define mk_pte_phys(physpage, pgprot) __mk_pte((physpage) >> PAGE_SHIFT, pgprot)
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
- pte.pte_low &= _PAGE_CHG_MASK;
- pte.pte_low |= pgprot_val(newprot);
- return pte;
-}
-
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
-#define pmd_page(pmd) \
-((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
-
-/* to find an entry in a page-table-directory. */
-#define pgd_index(address) ((address >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
-
-#define __pgd_offset(address) pgd_index(address)
-
-#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-#define __pmd_offset(address) \
- (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-
-/* Find an entry in the third-level page table.. */
-#define __pte_offset(address) \
- ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset(dir, address) ((pte_t *) pmd_page(*(dir)) + \
- __pte_offset(address))
-
-/*
- * The i386 doesn't have any external MMU info: the kernel page
- * tables contain all the necessary information.
- */
-#define update_mmu_cache(vma,address,pte) do { } while (0)
-
-/* Encode and de-code a swap entry */
-#define SWP_TYPE(x) (((x).val >> 1) & 0x3f)
-#define SWP_OFFSET(x) ((x).val >> 8)
-#define SWP_ENTRY(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
-#define pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low })
-#define swp_entry_to_pte(x) ((pte_t) { (x).val })
-
-#endif /* !__ASSEMBLY__ */
-
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-#define PageSkip(page) (0)
-#define kern_addr_valid(addr) (1)
-
-#define io_remap_page_range remap_page_range
-
-#endif /* _I386_PGTABLE_H */
+++ /dev/null
-#ifndef __i386_POLL_H
-#define __i386_POLL_H
-
-/* These are specified by iBCS2 */
-#define POLLIN 0x0001
-#define POLLPRI 0x0002
-#define POLLOUT 0x0004
-#define POLLERR 0x0008
-#define POLLHUP 0x0010
-#define POLLNVAL 0x0020
-
-/* The rest seem to be more-or-less nonstandard. Check them! */
-#define POLLRDNORM 0x0040
-#define POLLRDBAND 0x0080
-#define POLLWRNORM 0x0100
-#define POLLWRBAND 0x0200
-#define POLLMSG 0x0400
-
-struct pollfd {
- int fd;
- short events;
- short revents;
-};
-
-#endif
+++ /dev/null
-#ifndef __ARCH_I386_POSIX_TYPES_H
-#define __ARCH_I386_POSIX_TYPES_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc. Also, we cannot
- * assume GCC is being used.
- */
-
-typedef unsigned short __kernel_dev_t;
-typedef unsigned long __kernel_ino_t;
-typedef unsigned short __kernel_mode_t;
-typedef unsigned short __kernel_nlink_t;
-typedef long __kernel_off_t;
-typedef int __kernel_pid_t;
-typedef unsigned short __kernel_ipc_pid_t;
-typedef unsigned short __kernel_uid_t;
-typedef unsigned short __kernel_gid_t;
-typedef unsigned int __kernel_size_t;
-typedef int __kernel_ssize_t;
-typedef int __kernel_ptrdiff_t;
-typedef long __kernel_time_t;
-typedef long __kernel_suseconds_t;
-typedef long __kernel_clock_t;
-typedef int __kernel_daddr_t;
-typedef char * __kernel_caddr_t;
-typedef unsigned short __kernel_uid16_t;
-typedef unsigned short __kernel_gid16_t;
-typedef unsigned int __kernel_uid32_t;
-typedef unsigned int __kernel_gid32_t;
-
-typedef unsigned short __kernel_old_uid_t;
-typedef unsigned short __kernel_old_gid_t;
-
-#ifdef __GNUC__
-typedef long long __kernel_loff_t;
-#endif
-
-typedef struct {
-#if defined(__KERNEL__) || defined(__USE_ALL)
- int val[2];
-#else /* !defined(__KERNEL__) && !defined(__USE_ALL) */
- int __val[2];
-#endif /* !defined(__KERNEL__) && !defined(__USE_ALL) */
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
-
-#undef __FD_SET
-#define __FD_SET(fd,fdsetp) \
- __asm__ __volatile__("btsl %1,%0": \
- "=m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
-
-#undef __FD_CLR
-#define __FD_CLR(fd,fdsetp) \
- __asm__ __volatile__("btrl %1,%0": \
- "=m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
-
-#undef __FD_ISSET
-#define __FD_ISSET(fd,fdsetp) (__extension__ ({ \
- unsigned char __result; \
- __asm__ __volatile__("btl %1,%2 ; setb %0" \
- :"=q" (__result) :"r" ((int) (fd)), \
- "m" (*(__kernel_fd_set *) (fdsetp))); \
- __result; }))
-
-#undef __FD_ZERO
-#define __FD_ZERO(fdsetp) \
-do { \
- int __d0, __d1; \
- __asm__ __volatile__("cld ; rep ; stosl" \
- :"=m" (*(__kernel_fd_set *) (fdsetp)), \
- "=&c" (__d0), "=&D" (__d1) \
- :"a" (0), "1" (__FDSET_LONGS), \
- "2" ((__kernel_fd_set *) (fdsetp)) : "memory"); \
-} while (0)
-
-#endif /* defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) */
-
-#endif
+++ /dev/null
-/*
- * include/asm-i386/processor.h
- *
- * Copyright (C) 1994 Linus Torvalds
- */
-
-#ifndef __ASM_I386_PROCESSOR_H
-#define __ASM_I386_PROCESSOR_H
-
-#include <asm/math_emu.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/types.h>
-#include <asm/sigcontext.h>
-#include <asm/cpufeature.h>
-#include <linux/cache.h>
-#include <linux/config.h>
-#include <linux/threads.h>
-
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter").
- */
-#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
-
-/*
- * CPU type and hardware bug flags. Kept separately for each CPU.
- * Members of this structure are referenced in head.S, so think twice
- * before touching them. [mj]
- */
-
-struct cpuinfo_x86 {
- __u8 x86; /* CPU family */
- __u8 x86_vendor; /* CPU vendor */
- __u8 x86_model;
- __u8 x86_mask;
- char wp_works_ok; /* It doesn't on 386's */
- char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */
- char hard_math;
- char rfu;
- int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */
- __u32 x86_capability[NCAPINTS];
- char x86_vendor_id[16];
- char x86_model_id[64];
- int x86_cache_size; /* in KB - valid for CPUS which support this
- call */
- int fdiv_bug;
- int f00f_bug;
- int coma_bug;
- unsigned long loops_per_jiffy;
- unsigned long *pgd_quick;
- unsigned long *pmd_quick;
- unsigned long *pte_quick;
- unsigned long pgtable_cache_sz;
-} __attribute__((__aligned__(SMP_CACHE_BYTES)));
-
-#define X86_VENDOR_INTEL 0
-#define X86_VENDOR_CYRIX 1
-#define X86_VENDOR_AMD 2
-#define X86_VENDOR_UMC 3
-#define X86_VENDOR_NEXGEN 4
-#define X86_VENDOR_CENTAUR 5
-#define X86_VENDOR_RISE 6
-#define X86_VENDOR_TRANSMETA 7
-#define X86_VENDOR_UNKNOWN 0xff
-
-/*
- * capabilities of CPUs
- */
-
-extern struct cpuinfo_x86 boot_cpu_data;
-extern struct tss_struct init_tss[NR_CPUS];
-
-#ifdef CONFIG_SMP
-extern struct cpuinfo_x86 cpu_data[];
-#define current_cpu_data cpu_data[smp_processor_id()]
-#else
-#define cpu_data (&boot_cpu_data)
-#define current_cpu_data boot_cpu_data
-#endif
-
-#define cpu_has_pge (test_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability))
-#define cpu_has_pse (test_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability))
-#define cpu_has_pae (test_bit(X86_FEATURE_PAE, boot_cpu_data.x86_capability))
-#define cpu_has_tsc (test_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability))
-#define cpu_has_de (test_bit(X86_FEATURE_DE, boot_cpu_data.x86_capability))
-#define cpu_has_vme (test_bit(X86_FEATURE_VME, boot_cpu_data.x86_capability))
-#define cpu_has_fxsr (test_bit(X86_FEATURE_FXSR, boot_cpu_data.x86_capability))
-#define cpu_has_xmm (test_bit(X86_FEATURE_XMM, boot_cpu_data.x86_capability))
-#define cpu_has_fpu (test_bit(X86_FEATURE_FPU, boot_cpu_data.x86_capability))
-#define cpu_has_apic (test_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability))
-
-extern char ignore_irq13;
-
-extern void identify_cpu(struct cpuinfo_x86 *);
-extern void print_cpu_info(struct cpuinfo_x86 *);
-
-/*
- * EFLAGS bits
- */
-#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
-#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
-#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */
-#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
-#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */
-#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */
-#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */
-#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */
-#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */
-#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
-#define X86_EFLAGS_NT 0x00004000 /* Nested Task */
-#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */
-#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */
-#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */
-#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */
-#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */
-#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */
-
-/*
- * Generic CPUID function
- */
-static inline void cpuid(int op, int *eax, int *ebx, int *ecx, int *edx)
-{
- __asm__("cpuid"
- : "=a" (*eax),
- "=b" (*ebx),
- "=c" (*ecx),
- "=d" (*edx)
- : "0" (op));
-}
-
-/*
- * CPUID functions returning a single datum
- */
-static inline unsigned int cpuid_eax(unsigned int op)
-{
- unsigned int eax;
-
- __asm__("cpuid"
- : "=a" (eax)
- : "0" (op)
- : "bx", "cx", "dx");
- return eax;
-}
-static inline unsigned int cpuid_ebx(unsigned int op)
-{
- unsigned int eax, ebx;
-
- __asm__("cpuid"
- : "=a" (eax), "=b" (ebx)
- : "0" (op)
- : "cx", "dx" );
- return ebx;
-}
-static inline unsigned int cpuid_ecx(unsigned int op)
-{
- unsigned int eax, ecx;
-
- __asm__("cpuid"
- : "=a" (eax), "=c" (ecx)
- : "0" (op)
- : "bx", "dx" );
- return ecx;
-}
-static inline unsigned int cpuid_edx(unsigned int op)
-{
- unsigned int eax, edx;
-
- __asm__("cpuid"
- : "=a" (eax), "=d" (edx)
- : "0" (op)
- : "bx", "cx");
- return edx;
-}
-
-/*
- * Intel CPU features in CR4
- */
-#define X86_CR4_VME 0x0001 /* enable vm86 extensions */
-#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */
-#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */
-#define X86_CR4_DE 0x0008 /* enable debugging extensions */
-#define X86_CR4_PSE 0x0010 /* enable page size extensions */
-#define X86_CR4_PAE 0x0020 /* enable physical address extensions */
-#define X86_CR4_MCE 0x0040 /* Machine check enable */
-#define X86_CR4_PGE 0x0080 /* enable global pages */
-#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */
-#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */
-#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */
-
-extern unsigned long mmu_cr4_features;
-
-#include <asm/hypervisor.h>
-
-static inline void set_in_cr4 (unsigned long mask)
-{
- HYPERVISOR_console_write("No set_in_cr4", 13);
-}
-
-static inline void clear_in_cr4 (unsigned long mask)
-{
- HYPERVISOR_console_write("No clear_in_cr4", 15);
-}
-
-/*
- * Cyrix CPU configuration register indexes
- */
-#define CX86_CCR0 0xc0
-#define CX86_CCR1 0xc1
-#define CX86_CCR2 0xc2
-#define CX86_CCR3 0xc3
-#define CX86_CCR4 0xe8
-#define CX86_CCR5 0xe9
-#define CX86_CCR6 0xea
-#define CX86_CCR7 0xeb
-#define CX86_DIR0 0xfe
-#define CX86_DIR1 0xff
-#define CX86_ARR_BASE 0xc4
-#define CX86_RCR_BASE 0xdc
-
-/*
- * Cyrix CPU indexed register access macros
- */
-
-#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
-
-#define setCx86(reg, data) do { \
- outb((reg), 0x22); \
- outb((data), 0x23); \
-} while (0)
-
-/*
- * Bus types (default is ISA, but people can check others with these..)
- */
-#ifdef CONFIG_EISA
-extern int EISA_bus;
-#else
-#define EISA_bus (0)
-#endif
-extern int MCA_bus;
-
-/* from system description table in BIOS. Mostly for MCA use, but
-others may find it useful. */
-extern unsigned int machine_id;
-extern unsigned int machine_submodel_id;
-extern unsigned int BIOS_revision;
-extern unsigned int mca_pentium_flag;
-
-/*
- * User space process size: 3GB (default).
- */
-#define TASK_SIZE (PAGE_OFFSET)
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define TASK_UNMAPPED_BASE (TASK_SIZE / 3)
-
-/*
- * Size of io_bitmap in longwords: 32 is ports 0-0x3ff.
- */
-#define IO_BITMAP_SIZE 32
-#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
-#define INVALID_IO_BITMAP_OFFSET 0x8000
-
-struct i387_fsave_struct {
- long cwd;
- long swd;
- long twd;
- long fip;
- long fcs;
- long foo;
- long fos;
- long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
- long status; /* software status information */
-};
-
-struct i387_fxsave_struct {
- unsigned short cwd;
- unsigned short swd;
- unsigned short twd;
- unsigned short fop;
- long fip;
- long fcs;
- long foo;
- long fos;
- long mxcsr;
- long reserved;
- long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
- long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
- long padding[56];
-} __attribute__ ((aligned (16)));
-
-struct i387_soft_struct {
- long cwd;
- long swd;
- long twd;
- long fip;
- long fcs;
- long foo;
- long fos;
- long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
- unsigned char ftop, changed, lookahead, no_update, rm, alimit;
- struct info *info;
- unsigned long entry_eip;
-};
-
-union i387_union {
- struct i387_fsave_struct fsave;
- struct i387_fxsave_struct fxsave;
- struct i387_soft_struct soft;
-};
-
-typedef struct {
- unsigned long seg;
-} mm_segment_t;
-
-struct tss_struct {
- unsigned short back_link,__blh;
- unsigned long esp0;
- unsigned short ss0,__ss0h;
- unsigned long esp1;
- unsigned short ss1,__ss1h;
- unsigned long esp2;
- unsigned short ss2,__ss2h;
- unsigned long __cr3;
- unsigned long eip;
- unsigned long eflags;
- unsigned long eax,ecx,edx,ebx;
- unsigned long esp;
- unsigned long ebp;
- unsigned long esi;
- unsigned long edi;
- unsigned short es, __esh;
- unsigned short cs, __csh;
- unsigned short ss, __ssh;
- unsigned short ds, __dsh;
- unsigned short fs, __fsh;
- unsigned short gs, __gsh;
- unsigned short ldt, __ldth;
- unsigned short trace, bitmap;
- unsigned long io_bitmap[IO_BITMAP_SIZE+1];
- /*
- * pads the TSS to be cacheline-aligned (size is 0x100)
- */
- unsigned long __cacheline_filler[5];
-};
-
-struct thread_struct {
- unsigned long esp0;
- unsigned long eip;
- unsigned long esp;
- unsigned long fs;
- unsigned long gs;
-/* Hardware debugging registers */
- unsigned long debugreg[8]; /* %%db0-7 debug registers */
-/* fault info */
- unsigned long cr2, trap_no, error_code;
-/* floating point info */
- union i387_union i387;
-/* virtual 86 mode info */
- struct vm86_struct * vm86_info;
- unsigned long screen_bitmap;
- unsigned long v86flags, v86mask, v86mode, saved_esp0;
-};
-
-#define INIT_THREAD { 0 }
-
-#define INIT_TSS { \
- 0,0, /* back_link, __blh */ \
- sizeof(init_stack) + (long) &init_stack, /* esp0 */ \
- __KERNEL_DS, 0, /* ss0 */ \
- 0,0,0,0,0,0, /* stack1, stack2 */ \
- 0, /* cr3 */ \
- 0,0, /* eip,eflags */ \
- 0,0,0,0, /* eax,ecx,edx,ebx */ \
- 0,0,0,0, /* esp,ebp,esi,edi */ \
- 0,0,0,0,0,0, /* es,cs,ss */ \
- 0,0,0,0,0,0, /* ds,fs,gs */ \
- __LDT(0),0, /* ldt */ \
- 0, INVALID_IO_BITMAP_OFFSET, /* tace, bitmap */ \
- {~0, } /* ioperm */ \
-}
-
-#define start_thread(regs, new_eip, new_esp) do { \
- __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \
- set_fs(USER_DS); \
- regs->xds = __USER_DS; \
- regs->xes = __USER_DS; \
- regs->xss = __USER_DS; \
- regs->xcs = __USER_CS; \
- regs->eip = new_eip; \
- regs->esp = new_esp; \
-} while (0)
-
-/* Forward declaration, a strange C thing */
-struct task_struct;
-struct mm_struct;
-
-/* Free all resources held by a thread. */
-extern void release_thread(struct task_struct *);
-/*
- * create a kernel thread without removing it from tasklists
- */
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
-/* Copy and release all segment info associated with a VM */
-extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
-extern void release_segments(struct mm_struct * mm);
-
-/*
- * Return saved PC of a blocked thread.
- */
-static inline unsigned long thread_saved_pc(struct thread_struct *t)
-{
- return ((unsigned long *)t->esp)[3];
-}
-
-unsigned long get_wchan(struct task_struct *p);
-#define KSTK_EIP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1019])
-#define KSTK_ESP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1022])
-
-#define THREAD_SIZE (2*PAGE_SIZE)
-#define alloc_task_struct() ((struct task_struct *) __get_free_pages(GFP_KERNEL,1))
-#define free_task_struct(p) free_pages((unsigned long) (p), 1)
-#define get_task_struct(tsk) atomic_inc(&virt_to_page(tsk)->count)
-
-#define init_task (init_task_union.task)
-#define init_stack (init_task_union.stack)
-
-struct microcode {
- unsigned int hdrver;
- unsigned int rev;
- unsigned int date;
- unsigned int sig;
- unsigned int cksum;
- unsigned int ldrver;
- unsigned int pf;
- unsigned int reserved[5];
- unsigned int bits[500];
-};
-
-/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
-#define MICROCODE_IOCFREE _IO('6',0)
-
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
- __asm__ __volatile__("rep;nop");
-}
-
-#define cpu_relax() rep_nop()
-
-/* Prefetch instructions for Pentium III and AMD Athlon */
-#ifdef CONFIG_MPENTIUMIII
-
-#define ARCH_HAS_PREFETCH
-extern inline void prefetch(const void *x)
-{
- __asm__ __volatile__ ("prefetchnta (%0)" : : "r"(x));
-}
-
-#elif CONFIG_X86_USE_3DNOW
-
-#define ARCH_HAS_PREFETCH
-#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
-
-extern inline void prefetch(const void *x)
-{
- __asm__ __volatile__ ("prefetch (%0)" : : "r"(x));
-}
-
-extern inline void prefetchw(const void *x)
-{
- __asm__ __volatile__ ("prefetchw (%0)" : : "r"(x));
-}
-#define spin_lock_prefetch(x) prefetchw(x)
-
-#endif
-
-#define TF_MASK 0x100
-
-#endif /* __ASM_I386_PROCESSOR_H */
+++ /dev/null
-#ifndef _I386_PTRACE_H
-#define _I386_PTRACE_H
-
-#define EBX 0
-#define ECX 1
-#define EDX 2
-#define ESI 3
-#define EDI 4
-#define EBP 5
-#define EAX 6
-#define DS 7
-#define ES 8
-#define FS 9
-#define GS 10
-#define ORIG_EAX 11
-#define EIP 12
-#define CS 13
-#define EFL 14
-#define UESP 15
-#define SS 16
-#define FRAME_SIZE 17
-
-/* this struct defines the way the registers are stored on the
- stack during a system call. */
-
-struct pt_regs {
- long ebx;
- long ecx;
- long edx;
- long esi;
- long edi;
- long ebp;
- long eax;
- int xds;
- int xes;
- long orig_eax;
- long eip;
- int xcs;
- long eflags;
- long esp;
- int xss;
-};
-
-/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
-#define PTRACE_GETREGS 12
-#define PTRACE_SETREGS 13
-#define PTRACE_GETFPREGS 14
-#define PTRACE_SETFPREGS 15
-#define PTRACE_GETFPXREGS 18
-#define PTRACE_SETFPXREGS 19
-
-#define PTRACE_SETOPTIONS 21
-
-/* options set using PTRACE_SETOPTIONS */
-#define PTRACE_O_TRACESYSGOOD 0x00000001
-
-enum EFLAGS {
- EF_CF = 0x00000001,
- EF_PF = 0x00000004,
- EF_AF = 0x00000010,
- EF_ZF = 0x00000040,
- EF_SF = 0x00000080,
- EF_TF = 0x00000100,
- EF_IE = 0x00000200,
- EF_DF = 0x00000400,
- EF_OF = 0x00000800,
- EF_IOPL = 0x00003000,
- EF_IOPL_RING0 = 0x00000000,
- EF_IOPL_RING1 = 0x00001000,
- EF_IOPL_RING2 = 0x00002000,
- EF_NT = 0x00004000, /* nested task */
- EF_RF = 0x00010000, /* resume */
- EF_VM = 0x00020000, /* virtual mode */
- EF_AC = 0x00040000, /* alignment */
- EF_VIF = 0x00080000, /* virtual interrupt */
- EF_VIP = 0x00100000, /* virtual interrupt pending */
- EF_ID = 0x00200000, /* id */
-};
-
-#ifdef __KERNEL__
-#define user_mode(regs) ((regs) && (3 & (regs)->xcs))
-#define instruction_pointer(regs) ((regs) ? (regs)->eip : NULL)
-extern void show_regs(struct pt_regs *);
-#endif
-
-#endif
+++ /dev/null
-#ifndef _I386_RESOURCE_H
-#define _I386_RESOURCE_H
-
-/*
- * Resource limits
- */
-
-#define RLIMIT_CPU 0 /* CPU time in ms */
-#define RLIMIT_FSIZE 1 /* Maximum filesize */
-#define RLIMIT_DATA 2 /* max data size */
-#define RLIMIT_STACK 3 /* max stack size */
-#define RLIMIT_CORE 4 /* max core file size */
-#define RLIMIT_RSS 5 /* max resident set size */
-#define RLIMIT_NPROC 6 /* max number of processes */
-#define RLIMIT_NOFILE 7 /* max number of open files */
-#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */
-#define RLIMIT_AS 9 /* address space limit */
-#define RLIMIT_LOCKS 10 /* maximum file locks held */
-
-#define RLIM_NLIMITS 11
-
-/*
- * SuS says limits have to be unsigned.
- * Which makes a ton more sense anyway.
- */
-#define RLIM_INFINITY (~0UL)
-
-#ifdef __KERNEL__
-
-#define INIT_RLIMITS \
-{ \
- { RLIM_INFINITY, RLIM_INFINITY }, \
- { RLIM_INFINITY, RLIM_INFINITY }, \
- { RLIM_INFINITY, RLIM_INFINITY }, \
- { _STK_LIM, RLIM_INFINITY }, \
- { 0, RLIM_INFINITY }, \
- { RLIM_INFINITY, RLIM_INFINITY }, \
- { 0, 0 }, \
- { INR_OPEN, INR_OPEN }, \
- { RLIM_INFINITY, RLIM_INFINITY }, \
- { RLIM_INFINITY, RLIM_INFINITY }, \
- { RLIM_INFINITY, RLIM_INFINITY }, \
-}
-
-#endif /* __KERNEL__ */
-
-#endif
+++ /dev/null
-/* include/asm-i386/rwlock.h
- *
- * Helpers used by both rw spinlocks and rw semaphores.
- *
- * Based in part on code from semaphore.h and
- * spinlock.h Copyright 1996 Linus Torvalds.
- *
- * Copyright 1999 Red Hat, Inc.
- *
- * Written by Benjamin LaHaise.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#ifndef _ASM_I386_RWLOCK_H
-#define _ASM_I386_RWLOCK_H
-
-#define RW_LOCK_BIAS 0x01000000
-#define RW_LOCK_BIAS_STR "0x01000000"
-
-#define __build_read_lock_ptr(rw, helper) \
- asm volatile(LOCK "subl $1,(%0)\n\t" \
- "js 2f\n" \
- "1:\n" \
- ".section .text.lock,\"ax\"\n" \
- "2:\tcall " helper "\n\t" \
- "jmp 1b\n" \
- ".previous" \
- ::"a" (rw) : "memory")
-
-#define __build_read_lock_const(rw, helper) \
- asm volatile(LOCK "subl $1,%0\n\t" \
- "js 2f\n" \
- "1:\n" \
- ".section .text.lock,\"ax\"\n" \
- "2:\tpushl %%eax\n\t" \
- "leal %0,%%eax\n\t" \
- "call " helper "\n\t" \
- "popl %%eax\n\t" \
- "jmp 1b\n" \
- ".previous" \
- :"=m" (*(volatile int *)rw) : : "memory")
-
-#define __build_read_lock(rw, helper) do { \
- if (__builtin_constant_p(rw)) \
- __build_read_lock_const(rw, helper); \
- else \
- __build_read_lock_ptr(rw, helper); \
- } while (0)
-
-#define __build_write_lock_ptr(rw, helper) \
- asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
- "jnz 2f\n" \
- "1:\n" \
- ".section .text.lock,\"ax\"\n" \
- "2:\tcall " helper "\n\t" \
- "jmp 1b\n" \
- ".previous" \
- ::"a" (rw) : "memory")
-
-#define __build_write_lock_const(rw, helper) \
- asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
- "jnz 2f\n" \
- "1:\n" \
- ".section .text.lock,\"ax\"\n" \
- "2:\tpushl %%eax\n\t" \
- "leal %0,%%eax\n\t" \
- "call " helper "\n\t" \
- "popl %%eax\n\t" \
- "jmp 1b\n" \
- ".previous" \
- :"=m" (*(volatile int *)rw) : : "memory")
-
-#define __build_write_lock(rw, helper) do { \
- if (__builtin_constant_p(rw)) \
- __build_write_lock_const(rw, helper); \
- else \
- __build_write_lock_ptr(rw, helper); \
- } while (0)
-
-#endif
+++ /dev/null
-/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
- *
- * Written by David Howells (dhowells@redhat.com).
- *
- * Derived from asm-i386/semaphore.h
- *
- *
- * The MSW of the count is the negated number of active writers and waiting
- * lockers, and the LSW is the total number of active locks
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
- * uncontended lock. This can be determined because XADD returns the old value.
- * Readers increment by 1 and see a positive value when uncontended, negative
- * if there are writers (and maybe) readers waiting (in which case it goes to
- * sleep).
- *
- * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
- * be extended to 65534 by manually checking the whole MSW rather than relying
- * on the S flag.
- *
- * The value of ACTIVE_BIAS supports up to 65535 active processes.
- *
- * This should be totally fair - if anything is waiting, a process that wants a
- * lock will go to the back of the queue. When the currently active lock is
- * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consequtive readers at the
- * front, then they'll all be woken up, but no other readers will be.
- */
-
-#ifndef _I386_RWSEM_H
-#define _I386_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error please dont include asm/rwsem.h directly, use linux/rwsem.h instead
-#endif
-
-#ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
-extern struct rw_semaphore *FASTCALL(rwsem_down_read_failed(struct rw_semaphore *sem));
-extern struct rw_semaphore *FASTCALL(rwsem_down_write_failed(struct rw_semaphore *sem));
-extern struct rw_semaphore *FASTCALL(rwsem_wake(struct rw_semaphore *));
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
- signed long count;
-#define RWSEM_UNLOCKED_VALUE 0x00000000
-#define RWSEM_ACTIVE_BIAS 0x00000001
-#define RWSEM_ACTIVE_MASK 0x0000ffff
-#define RWSEM_WAITING_BIAS (-0x00010000)
-#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
- spinlock_t wait_lock;
- struct list_head wait_list;
-#if RWSEM_DEBUG
- int debug;
-#endif
-};
-
-/*
- * initialisation
- */
-#if RWSEM_DEBUG
-#define __RWSEM_DEBUG_INIT , 0
-#else
-#define __RWSEM_DEBUG_INIT /* */
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, LIST_HEAD_INIT((name).wait_list) \
- __RWSEM_DEBUG_INIT }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
- sem->count = RWSEM_UNLOCKED_VALUE;
- spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-#if RWSEM_DEBUG
- sem->debug = 0;
-#endif
-}
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
- __asm__ __volatile__(
- "# beginning down_read\n\t"
-LOCK_PREFIX " incl (%%eax)\n\t" /* adds 0x00000001, returns the old value */
- " js 2f\n\t" /* jump if we weren't granted the lock */
- "1:\n\t"
- ".section .text.lock,\"ax\"\n"
- "2:\n\t"
- " pushl %%ecx\n\t"
- " pushl %%edx\n\t"
- " call rwsem_down_read_failed\n\t"
- " popl %%edx\n\t"
- " popl %%ecx\n\t"
- " jmp 1b\n"
- ".previous"
- "# ending down_read\n\t"
- : "+m"(sem->count)
- : "a"(sem)
- : "memory", "cc");
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
- int tmp;
-
- tmp = RWSEM_ACTIVE_WRITE_BIAS;
- __asm__ __volatile__(
- "# beginning down_write\n\t"
-LOCK_PREFIX " xadd %0,(%%eax)\n\t" /* subtract 0x0000ffff, returns the old value */
- " testl %0,%0\n\t" /* was the count 0 before? */
- " jnz 2f\n\t" /* jump if we weren't granted the lock */
- "1:\n\t"
- ".section .text.lock,\"ax\"\n"
- "2:\n\t"
- " pushl %%ecx\n\t"
- " call rwsem_down_write_failed\n\t"
- " popl %%ecx\n\t"
- " jmp 1b\n"
- ".previous\n"
- "# ending down_write"
- : "+d"(tmp), "+m"(sem->count)
- : "a"(sem)
- : "memory", "cc");
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
- __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
- __asm__ __volatile__(
- "# beginning __up_read\n\t"
-LOCK_PREFIX " xadd %%edx,(%%eax)\n\t" /* subtracts 1, returns the old value */
- " js 2f\n\t" /* jump if the lock is being waited upon */
- "1:\n\t"
- ".section .text.lock,\"ax\"\n"
- "2:\n\t"
- " decw %%dx\n\t" /* do nothing if still outstanding active readers */
- " jnz 1b\n\t"
- " pushl %%ecx\n\t"
- " call rwsem_wake\n\t"
- " popl %%ecx\n\t"
- " jmp 1b\n"
- ".previous\n"
- "# ending __up_read\n"
- : "+m"(sem->count), "+d"(tmp)
- : "a"(sem)
- : "memory", "cc");
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
- __asm__ __volatile__(
- "# beginning __up_write\n\t"
- " movl %2,%%edx\n\t"
-LOCK_PREFIX " xaddl %%edx,(%%eax)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */
- " jnz 2f\n\t" /* jump if the lock is being waited upon */
- "1:\n\t"
- ".section .text.lock,\"ax\"\n"
- "2:\n\t"
- " decw %%dx\n\t" /* did the active count reduce to 0? */
- " jnz 1b\n\t" /* jump back if not */
- " pushl %%ecx\n\t"
- " call rwsem_wake\n\t"
- " popl %%ecx\n\t"
- " jmp 1b\n"
- ".previous\n"
- "# ending __up_write\n"
- : "+m"(sem->count)
- : "a"(sem), "i"(-RWSEM_ACTIVE_WRITE_BIAS)
- : "memory", "cc", "edx");
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
-{
- __asm__ __volatile__(
-LOCK_PREFIX "addl %1,%0"
- :"=m"(sem->count)
- :"ir"(delta), "m"(sem->count));
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
-{
- int tmp = delta;
-
- __asm__ __volatile__(
-LOCK_PREFIX "xadd %0,(%2)"
- : "+r"(tmp), "=m"(sem->count)
- : "r"(sem), "m"(sem->count)
- : "memory");
-
- return tmp+delta;
-}
-
-#endif /* __KERNEL__ */
-#endif /* _I386_RWSEM_H */
+++ /dev/null
-#ifndef _I386_SCATTERLIST_H
-#define _I386_SCATTERLIST_H
-
-struct scatterlist {
- char * address; /* Location data is to be transferred to, NULL for
- * highmem page */
- struct page * page; /* Location for highmem page, if any */
- unsigned int offset;/* for highmem, page offset */
-
- dma_addr_t dma_address;
- unsigned int length;
-};
-
-#define ISA_DMA_THRESHOLD (0x00ffffff)
-
-#endif /* !(_I386_SCATTERLIST_H) */
+++ /dev/null
-#ifndef _ASM_SEGMENT_H
-#define _ASM_SEGMENT_H
-
-#define __KERNEL_CS 0x11
-#define __KERNEL_DS 0x19
-
-#define __USER_CS 0x23
-#define __USER_DS 0x2B
-
-#endif
+++ /dev/null
-#ifndef _I386_SEMAPHORE_H
-#define _I386_SEMAPHORE_H
-
-#include <linux/linkage.h>
-
-#ifdef __KERNEL__
-
-/*
- * SMP- and interrupt-safe semaphores..
- *
- * (C) Copyright 1996 Linus Torvalds
- *
- * Modified 1996-12-23 by Dave Grothe <dave@gcom.com> to fix bugs in
- * the original code and to make semaphore waits
- * interruptible so that processes waiting on
- * semaphores can be killed.
- * Modified 1999-02-14 by Andrea Arcangeli, split the sched.c helper
- * functions in asm/sempahore-helper.h while fixing a
- * potential and subtle race discovered by Ulrich Schmid
- * in down_interruptible(). Since I started to play here I
- * also implemented the `trylock' semaphore operation.
- * 1999-07-02 Artur Skawina <skawina@geocities.com>
- * Optimized "0(ecx)" -> "(ecx)" (the assembler does not
- * do this). Changed calling sequences from push/jmp to
- * traditional call/ret.
- * Modified 2001-01-01 Andreas Franck <afranck@gmx.de>
- * Some hacks to ensure compatibility with recent
- * GCC snapshots, to avoid stack corruption when compiling
- * with -fomit-frame-pointer. It's not sure if this will
- * be fixed in GCC, as our previous implementation was a
- * bit dubious.
- *
- * If you would like to see an analysis of this implementation, please
- * ftp to gcom.com and download the file
- * /pub/linux/src/semaphore/semaphore-2.0.24.tar.gz.
- *
- */
-
-#include <asm/system.h>
-#include <asm/atomic.h>
-#include <linux/wait.h>
-#include <linux/rwsem.h>
-
-struct semaphore {
- atomic_t count;
- int sleepers;
- wait_queue_head_t wait;
-#if WAITQUEUE_DEBUG
- long __magic;
-#endif
-};
-
-#if WAITQUEUE_DEBUG
-# define __SEM_DEBUG_INIT(name) \
- , (int)&(name).__magic
-#else
-# define __SEM_DEBUG_INIT(name)
-#endif
-
-#define __SEMAPHORE_INITIALIZER(name,count) \
-{ ATOMIC_INIT(count), 0, __WAIT_QUEUE_HEAD_INITIALIZER((name).wait) \
- __SEM_DEBUG_INIT(name) }
-
-#define __MUTEX_INITIALIZER(name) \
- __SEMAPHORE_INITIALIZER(name,1)
-
-#define __DECLARE_SEMAPHORE_GENERIC(name,count) \
- struct semaphore name = __SEMAPHORE_INITIALIZER(name,count)
-
-#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name,1)
-#define DECLARE_MUTEX_LOCKED(name) __DECLARE_SEMAPHORE_GENERIC(name,0)
-
-static inline void sema_init (struct semaphore *sem, int val)
-{
-/*
- * *sem = (struct semaphore)__SEMAPHORE_INITIALIZER((*sem),val);
- *
- * i'd rather use the more flexible initialization above, but sadly
- * GCC 2.7.2.3 emits a bogus warning. EGCS doesnt. Oh well.
- */
- atomic_set(&sem->count, val);
- sem->sleepers = 0;
- init_waitqueue_head(&sem->wait);
-#if WAITQUEUE_DEBUG
- sem->__magic = (int)&sem->__magic;
-#endif
-}
-
-static inline void init_MUTEX (struct semaphore *sem)
-{
- sema_init(sem, 1);
-}
-
-static inline void init_MUTEX_LOCKED (struct semaphore *sem)
-{
- sema_init(sem, 0);
-}
-
-asmlinkage void __down_failed(void /* special register calling convention */);
-asmlinkage int __down_failed_interruptible(void /* params in registers */);
-asmlinkage int __down_failed_trylock(void /* params in registers */);
-asmlinkage void __up_wakeup(void /* special register calling convention */);
-
-asmlinkage void __down(struct semaphore * sem);
-asmlinkage int __down_interruptible(struct semaphore * sem);
-asmlinkage int __down_trylock(struct semaphore * sem);
-asmlinkage void __up(struct semaphore * sem);
-
-/*
- * This is ugly, but we want the default case to fall through.
- * "__down_failed" is a special asm handler that calls the C
- * routine that actually waits. See arch/i386/kernel/semaphore.c
- */
-static inline void down(struct semaphore * sem)
-{
-#if WAITQUEUE_DEBUG
- CHECK_MAGIC(sem->__magic);
-#endif
-
- __asm__ __volatile__(
- "# atomic down operation\n\t"
- LOCK "decl %0\n\t" /* --sem->count */
- "js 2f\n"
- "1:\n"
- ".section .text.lock,\"ax\"\n"
- "2:\tcall __down_failed\n\t"
- "jmp 1b\n"
- ".previous"
- :"=m" (sem->count)
- :"c" (sem)
- :"memory");
-}
-
-/*
- * Interruptible try to acquire a semaphore. If we obtained
- * it, return zero. If we were interrupted, returns -EINTR
- */
-static inline int down_interruptible(struct semaphore * sem)
-{
- int result;
-
-#if WAITQUEUE_DEBUG
- CHECK_MAGIC(sem->__magic);
-#endif
-
- __asm__ __volatile__(
- "# atomic interruptible down operation\n\t"
- LOCK "decl %1\n\t" /* --sem->count */
- "js 2f\n\t"
- "xorl %0,%0\n"
- "1:\n"
- ".section .text.lock,\"ax\"\n"
- "2:\tcall __down_failed_interruptible\n\t"
- "jmp 1b\n"
- ".previous"
- :"=a" (result), "=m" (sem->count)
- :"c" (sem)
- :"memory");
- return result;
-}
-
-/*
- * Non-blockingly attempt to down() a semaphore.
- * Returns zero if we acquired it
- */
-static inline int down_trylock(struct semaphore * sem)
-{
- int result;
-
-#if WAITQUEUE_DEBUG
- CHECK_MAGIC(sem->__magic);
-#endif
-
- __asm__ __volatile__(
- "# atomic interruptible down operation\n\t"
- LOCK "decl %1\n\t" /* --sem->count */
- "js 2f\n\t"
- "xorl %0,%0\n"
- "1:\n"
- ".section .text.lock,\"ax\"\n"
- "2:\tcall __down_failed_trylock\n\t"
- "jmp 1b\n"
- ".previous"
- :"=a" (result), "=m" (sem->count)
- :"c" (sem)
- :"memory");
- return result;
-}
-
-/*
- * Note! This is subtle. We jump to wake people up only if
- * the semaphore was negative (== somebody was waiting on it).
- * The default case (no contention) will result in NO
- * jumps for both down() and up().
- */
-static inline void up(struct semaphore * sem)
-{
-#if WAITQUEUE_DEBUG
- CHECK_MAGIC(sem->__magic);
-#endif
- __asm__ __volatile__(
- "# atomic up operation\n\t"
- LOCK "incl %0\n\t" /* ++sem->count */
- "jle 2f\n"
- "1:\n"
- ".section .text.lock,\"ax\"\n"
- "2:\tcall __up_wakeup\n\t"
- "jmp 1b\n"
- ".previous"
- :"=m" (sem->count)
- :"c" (sem)
- :"memory");
-}
-
-#endif
-#endif
+++ /dev/null
-#ifndef _I386_SEMBUF_H
-#define _I386_SEMBUF_H
-
-/*
- * The semid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
- struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
- __kernel_time_t sem_otime; /* last semop time */
- unsigned long __unused1;
- __kernel_time_t sem_ctime; /* last change time */
- unsigned long __unused2;
- unsigned long sem_nsems; /* no. of semaphores in array */
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _I386_SEMBUF_H */
+++ /dev/null
-/*
- * include/asm-i386/serial.h
- */
-
-#include <linux/config.h>
-
-/*
- * This assumes you have a 1.8432 MHz clock for your UART.
- *
- * It'd be nice if someone built a serial card with a 24.576 MHz
- * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
- */
-#define BASE_BAUD ( 1843200 / 16 )
-
-/* Standard COM flags (except for COM4, because of the 8514 problem) */
-#ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
-#else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
-#endif
-
-#ifdef CONFIG_SERIAL_MANY_PORTS
-#define FOURPORT_FLAGS ASYNC_FOURPORT
-#define ACCENT_FLAGS 0
-#define BOCA_FLAGS 0
-#define HUB6_FLAGS 0
-#define RS_TABLE_SIZE 64
-#else
-#define RS_TABLE_SIZE
-#endif
-
-#define MCA_COM_FLAGS (STD_COM_FLAGS|ASYNC_BOOT_ONLYMCA)
-
-/*
- * The following define the access methods for the HUB6 card. All
- * access is through two ports for all 24 possible chips. The card is
- * selected through the high 2 bits, the port on that card with the
- * "middle" 3 bits, and the register on that port with the bottom
- * 3 bits.
- *
- * While the access port and interrupt is configurable, the default
- * port locations are 0x302 for the port control register, and 0x303
- * for the data read/write register. Normally, the interrupt is at irq3
- * but can be anything from 3 to 7 inclusive. Note that using 3 will
- * require disabling com2.
- */
-
-#define C_P(card,port) (((card)<<6|(port)<<3) + 1)
-
-#define STD_SERIAL_PORT_DEFNS \
- /* UART CLK PORT IRQ FLAGS */ \
- { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS }, /* ttyS0 */ \
- { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS }, /* ttyS1 */ \
- { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS }, /* ttyS2 */ \
- { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */
-
-
-#ifdef CONFIG_SERIAL_MANY_PORTS
-#define EXTRA_SERIAL_PORT_DEFNS \
- { 0, BASE_BAUD, 0x1A0, 9, FOURPORT_FLAGS }, /* ttyS4 */ \
- { 0, BASE_BAUD, 0x1A8, 9, FOURPORT_FLAGS }, /* ttyS5 */ \
- { 0, BASE_BAUD, 0x1B0, 9, FOURPORT_FLAGS }, /* ttyS6 */ \
- { 0, BASE_BAUD, 0x1B8, 9, FOURPORT_FLAGS }, /* ttyS7 */ \
- { 0, BASE_BAUD, 0x2A0, 5, FOURPORT_FLAGS }, /* ttyS8 */ \
- { 0, BASE_BAUD, 0x2A8, 5, FOURPORT_FLAGS }, /* ttyS9 */ \
- { 0, BASE_BAUD, 0x2B0, 5, FOURPORT_FLAGS }, /* ttyS10 */ \
- { 0, BASE_BAUD, 0x2B8, 5, FOURPORT_FLAGS }, /* ttyS11 */ \
- { 0, BASE_BAUD, 0x330, 4, ACCENT_FLAGS }, /* ttyS12 */ \
- { 0, BASE_BAUD, 0x338, 4, ACCENT_FLAGS }, /* ttyS13 */ \
- { 0, BASE_BAUD, 0x000, 0, 0 }, /* ttyS14 (spare) */ \
- { 0, BASE_BAUD, 0x000, 0, 0 }, /* ttyS15 (spare) */ \
- { 0, BASE_BAUD, 0x100, 12, BOCA_FLAGS }, /* ttyS16 */ \
- { 0, BASE_BAUD, 0x108, 12, BOCA_FLAGS }, /* ttyS17 */ \
- { 0, BASE_BAUD, 0x110, 12, BOCA_FLAGS }, /* ttyS18 */ \
- { 0, BASE_BAUD, 0x118, 12, BOCA_FLAGS }, /* ttyS19 */ \
- { 0, BASE_BAUD, 0x120, 12, BOCA_FLAGS }, /* ttyS20 */ \
- { 0, BASE_BAUD, 0x128, 12, BOCA_FLAGS }, /* ttyS21 */ \
- { 0, BASE_BAUD, 0x130, 12, BOCA_FLAGS }, /* ttyS22 */ \
- { 0, BASE_BAUD, 0x138, 12, BOCA_FLAGS }, /* ttyS23 */ \
- { 0, BASE_BAUD, 0x140, 12, BOCA_FLAGS }, /* ttyS24 */ \
- { 0, BASE_BAUD, 0x148, 12, BOCA_FLAGS }, /* ttyS25 */ \
- { 0, BASE_BAUD, 0x150, 12, BOCA_FLAGS }, /* ttyS26 */ \
- { 0, BASE_BAUD, 0x158, 12, BOCA_FLAGS }, /* ttyS27 */ \
- { 0, BASE_BAUD, 0x160, 12, BOCA_FLAGS }, /* ttyS28 */ \
- { 0, BASE_BAUD, 0x168, 12, BOCA_FLAGS }, /* ttyS29 */ \
- { 0, BASE_BAUD, 0x170, 12, BOCA_FLAGS }, /* ttyS30 */ \
- { 0, BASE_BAUD, 0x178, 12, BOCA_FLAGS }, /* ttyS31 */
-#else
-#define EXTRA_SERIAL_PORT_DEFNS
-#endif
-
-/* You can have up to four HUB6's in the system, but I've only
- * included two cards here for a total of twelve ports.
- */
-#if (defined(CONFIG_HUB6) && defined(CONFIG_SERIAL_MANY_PORTS))
-#define HUB6_SERIAL_PORT_DFNS \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,0) }, /* ttyS32 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,1) }, /* ttyS33 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,2) }, /* ttyS34 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,3) }, /* ttyS35 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,4) }, /* ttyS36 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,5) }, /* ttyS37 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,0) }, /* ttyS38 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,1) }, /* ttyS39 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,2) }, /* ttyS40 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,3) }, /* ttyS41 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,4) }, /* ttyS42 */ \
- { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,5) }, /* ttyS43 */
-#else
-#define HUB6_SERIAL_PORT_DFNS
-#endif
-
-#ifdef CONFIG_MCA
-#define MCA_SERIAL_PORT_DFNS \
- { 0, BASE_BAUD, 0x3220, 3, MCA_COM_FLAGS }, \
- { 0, BASE_BAUD, 0x3228, 3, MCA_COM_FLAGS }, \
- { 0, BASE_BAUD, 0x4220, 3, MCA_COM_FLAGS }, \
- { 0, BASE_BAUD, 0x4228, 3, MCA_COM_FLAGS }, \
- { 0, BASE_BAUD, 0x5220, 3, MCA_COM_FLAGS }, \
- { 0, BASE_BAUD, 0x5228, 3, MCA_COM_FLAGS },
-#else
-#define MCA_SERIAL_PORT_DFNS
-#endif
-
-#define SERIAL_PORT_DFNS \
- STD_SERIAL_PORT_DEFNS \
- EXTRA_SERIAL_PORT_DEFNS \
- HUB6_SERIAL_PORT_DFNS \
- MCA_SERIAL_PORT_DFNS
-
+++ /dev/null
-/*
- * Just a place holder. We don't want to have to test x86 before
- * we include stuff
- */
-
-#ifndef _i386_SETUP_H
-#define _i386_SETUP_H
-
-
-#endif /* _i386_SETUP_H */
+++ /dev/null
-#ifndef _I386_SHMBUF_H
-#define _I386_SHMBUF_H
-
-/*
- * The shmid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- unsigned long __unused1;
- __kernel_time_t shm_dtime; /* last detach time */
- unsigned long __unused2;
- __kernel_time_t shm_ctime; /* last change time */
- unsigned long __unused3;
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-struct shminfo64 {
- unsigned long shmmax;
- unsigned long shmmin;
- unsigned long shmmni;
- unsigned long shmseg;
- unsigned long shmall;
- unsigned long __unused1;
- unsigned long __unused2;
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _I386_SHMBUF_H */
+++ /dev/null
-#ifndef _ASMI386_SHMPARAM_H
-#define _ASMI386_SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */
-
-#endif /* _ASMI386_SHMPARAM_H */
+++ /dev/null
-#ifndef _ASMi386_SIGCONTEXT_H
-#define _ASMi386_SIGCONTEXT_H
-
-/*
- * As documented in the iBCS2 standard..
- *
- * The first part of "struct _fpstate" is just the normal i387
- * hardware setup, the extra "status" word is used to save the
- * coprocessor status word before entering the handler.
- *
- * Pentium III FXSR, SSE support
- * Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * The FPU state data structure has had to grow to accomodate the
- * extended FPU state required by the Streaming SIMD Extensions.
- * There is no documented standard to accomplish this at the moment.
- */
-struct _fpreg {
- unsigned short significand[4];
- unsigned short exponent;
-};
-
-struct _fpxreg {
- unsigned short significand[4];
- unsigned short exponent;
- unsigned short padding[3];
-};
-
-struct _xmmreg {
- unsigned long element[4];
-};
-
-struct _fpstate {
- /* Regular FPU environment */
- unsigned long cw;
- unsigned long sw;
- unsigned long tag;
- unsigned long ipoff;
- unsigned long cssel;
- unsigned long dataoff;
- unsigned long datasel;
- struct _fpreg _st[8];
- unsigned short status;
- unsigned short magic; /* 0xffff = regular FPU data only */
-
- /* FXSR FPU environment */
- unsigned long _fxsr_env[6]; /* FXSR FPU env is ignored */
- unsigned long mxcsr;
- unsigned long reserved;
- struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */
- struct _xmmreg _xmm[8];
- unsigned long padding[56];
-};
-
-#define X86_FXSR_MAGIC 0x0000
-
-struct sigcontext {
- unsigned short gs, __gsh;
- unsigned short fs, __fsh;
- unsigned short es, __esh;
- unsigned short ds, __dsh;
- unsigned long edi;
- unsigned long esi;
- unsigned long ebp;
- unsigned long esp;
- unsigned long ebx;
- unsigned long edx;
- unsigned long ecx;
- unsigned long eax;
- unsigned long trapno;
- unsigned long err;
- unsigned long eip;
- unsigned short cs, __csh;
- unsigned long eflags;
- unsigned long esp_at_signal;
- unsigned short ss, __ssh;
- struct _fpstate * fpstate;
- unsigned long oldmask;
- unsigned long cr2;
-};
-
-
-#endif
+++ /dev/null
-#ifndef _I386_SIGINFO_H
-#define _I386_SIGINFO_H
-
-#include <linux/types.h>
-
-/* XXX: This structure was copied from the Alpha; is there an iBCS version? */
-
-typedef union sigval {
- int sival_int;
- void *sival_ptr;
-} sigval_t;
-
-#define SI_MAX_SIZE 128
-#define SI_PAD_SIZE ((SI_MAX_SIZE/sizeof(int)) - 3)
-
-typedef struct siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[SI_PAD_SIZE];
-
- /* kill() */
- struct {
- pid_t _pid; /* sender's pid */
- uid_t _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- unsigned int _timer1;
- unsigned int _timer2;
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- pid_t _pid; /* sender's pid */
- uid_t _uid; /* sender's uid */
- sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- pid_t _pid; /* which child */
- uid_t _uid; /* sender's uid */
- int _status; /* exit code */
- clock_t _utime;
- clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- void *_addr; /* faulting insn/memory ref. */
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
- } _sifields;
-} siginfo_t;
-
-/*
- * How these fields are to be accessed.
- */
-#define si_pid _sifields._kill._pid
-#define si_uid _sifields._kill._uid
-#define si_status _sifields._sigchld._status
-#define si_utime _sifields._sigchld._utime
-#define si_stime _sifields._sigchld._stime
-#define si_value _sifields._rt._sigval
-#define si_int _sifields._rt._sigval.sival_int
-#define si_ptr _sifields._rt._sigval.sival_ptr
-#define si_addr _sifields._sigfault._addr
-#define si_band _sifields._sigpoll._band
-#define si_fd _sifields._sigpoll._fd
-
-#ifdef __KERNEL__
-#define __SI_MASK 0xffff0000
-#define __SI_KILL (0 << 16)
-#define __SI_TIMER (1 << 16)
-#define __SI_POLL (2 << 16)
-#define __SI_FAULT (3 << 16)
-#define __SI_CHLD (4 << 16)
-#define __SI_RT (5 << 16)
-#define __SI_CODE(T,N) ((T) << 16 | ((N) & 0xffff))
-#else
-#define __SI_KILL 0
-#define __SI_TIMER 0
-#define __SI_POLL 0
-#define __SI_FAULT 0
-#define __SI_CHLD 0
-#define __SI_RT 0
-#define __SI_CODE(T,N) (N)
-#endif
-
-/*
- * si_code values
- * Digital reserves positive values for kernel-generated signals.
- */
-#define SI_USER 0 /* sent by kill, sigsend, raise */
-#define SI_KERNEL 0x80 /* sent by the kernel from somewhere */
-#define SI_QUEUE -1 /* sent by sigqueue */
-#define SI_TIMER __SI_CODE(__SI_TIMER,-2) /* sent by timer expiration */
-#define SI_MESGQ -3 /* sent by real time mesq state change */
-#define SI_ASYNCIO -4 /* sent by AIO completion */
-#define SI_SIGIO -5 /* sent by queued SIGIO */
-
-#define SI_FROMUSER(siptr) ((siptr)->si_code <= 0)
-#define SI_FROMKERNEL(siptr) ((siptr)->si_code > 0)
-
-/*
- * SIGILL si_codes
- */
-#define ILL_ILLOPC (__SI_FAULT|1) /* illegal opcode */
-#define ILL_ILLOPN (__SI_FAULT|2) /* illegal operand */
-#define ILL_ILLADR (__SI_FAULT|3) /* illegal addressing mode */
-#define ILL_ILLTRP (__SI_FAULT|4) /* illegal trap */
-#define ILL_PRVOPC (__SI_FAULT|5) /* privileged opcode */
-#define ILL_PRVREG (__SI_FAULT|6) /* privileged register */
-#define ILL_COPROC (__SI_FAULT|7) /* coprocessor error */
-#define ILL_BADSTK (__SI_FAULT|8) /* internal stack error */
-#define NSIGILL 8
-
-/*
- * SIGFPE si_codes
- */
-#define FPE_INTDIV (__SI_FAULT|1) /* integer divide by zero */
-#define FPE_INTOVF (__SI_FAULT|2) /* integer overflow */
-#define FPE_FLTDIV (__SI_FAULT|3) /* floating point divide by zero */
-#define FPE_FLTOVF (__SI_FAULT|4) /* floating point overflow */
-#define FPE_FLTUND (__SI_FAULT|5) /* floating point underflow */
-#define FPE_FLTRES (__SI_FAULT|6) /* floating point inexact result */
-#define FPE_FLTINV (__SI_FAULT|7) /* floating point invalid operation */
-#define FPE_FLTSUB (__SI_FAULT|8) /* subscript out of range */
-#define NSIGFPE 8
-
-/*
- * SIGSEGV si_codes
- */
-#define SEGV_MAPERR (__SI_FAULT|1) /* address not mapped to object */
-#define SEGV_ACCERR (__SI_FAULT|2) /* invalid permissions for mapped object */
-#define NSIGSEGV 2
-
-/*
- * SIGBUS si_codes
- */
-#define BUS_ADRALN (__SI_FAULT|1) /* invalid address alignment */
-#define BUS_ADRERR (__SI_FAULT|2) /* non-existant physical address */
-#define BUS_OBJERR (__SI_FAULT|3) /* object specific hardware error */
-#define NSIGBUS 3
-
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_BRKPT (__SI_FAULT|1) /* process breakpoint */
-#define TRAP_TRACE (__SI_FAULT|2) /* process trace trap */
-#define NSIGTRAP 2
-
-/*
- * SIGCHLD si_codes
- */
-#define CLD_EXITED (__SI_CHLD|1) /* child has exited */
-#define CLD_KILLED (__SI_CHLD|2) /* child was killed */
-#define CLD_DUMPED (__SI_CHLD|3) /* child terminated abnormally */
-#define CLD_TRAPPED (__SI_CHLD|4) /* traced child has trapped */
-#define CLD_STOPPED (__SI_CHLD|5) /* child has stopped */
-#define CLD_CONTINUED (__SI_CHLD|6) /* stopped child has continued */
-#define NSIGCHLD 6
-
-/*
- * SIGPOLL si_codes
- */
-#define POLL_IN (__SI_POLL|1) /* data input available */
-#define POLL_OUT (__SI_POLL|2) /* output buffers available */
-#define POLL_MSG (__SI_POLL|3) /* input message available */
-#define POLL_ERR (__SI_POLL|4) /* i/o error */
-#define POLL_PRI (__SI_POLL|5) /* high priority input available */
-#define POLL_HUP (__SI_POLL|6) /* device disconnected */
-#define NSIGPOLL 6
-
-/*
- * sigevent definitions
- *
- * It seems likely that SIGEV_THREAD will have to be handled from
- * userspace, libpthread transmuting it to SIGEV_SIGNAL, which the
- * thread manager then catches and does the appropriate nonsense.
- * However, everything is written out here so as to not get lost.
- */
-#define SIGEV_SIGNAL 0 /* notify via signal */
-#define SIGEV_NONE 1 /* other notification: meaningless */
-#define SIGEV_THREAD 2 /* deliver via thread creation */
-
-#define SIGEV_MAX_SIZE 64
-#define SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3)
-
-typedef struct sigevent {
- sigval_t sigev_value;
- int sigev_signo;
- int sigev_notify;
- union {
- int _pad[SIGEV_PAD_SIZE];
-
- struct {
- void (*_function)(sigval_t);
- void *_attribute; /* really pthread_attr_t */
- } _sigev_thread;
- } _sigev_un;
-} sigevent_t;
-
-#define sigev_notify_function _sigev_un._sigev_thread._function
-#define sigev_notify_attributes _sigev_un._sigev_thread._attribute
-
-#ifdef __KERNEL__
-#include <linux/string.h>
-
-static inline void copy_siginfo(siginfo_t *to, siginfo_t *from)
-{
- if (from->si_code < 0)
- memcpy(to, from, sizeof(siginfo_t));
- else
- /* _sigchld is currently the largest know union member */
- memcpy(to, from, 3*sizeof(int) + sizeof(from->_sifields._sigchld));
-}
-
-extern int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from);
-
-#endif /* __KERNEL__ */
-
-#endif
+++ /dev/null
-#ifndef _ASMi386_SIGNAL_H
-#define _ASMi386_SIGNAL_H
-
-#include <linux/types.h>
-
-/* Avoid too many header ordering problems. */
-struct siginfo;
-
-#ifdef __KERNEL__
-/* Most things should be clean enough to redefine this at will, if care
- is taken to make libc match. */
-
-#define _NSIG 64
-#define _NSIG_BPW 32
-#define _NSIG_WORDS (_NSIG / _NSIG_BPW)
-
-typedef unsigned long old_sigset_t; /* at least 32 bits */
-
-typedef struct {
- unsigned long sig[_NSIG_WORDS];
-} sigset_t;
-
-#else
-/* Here we must cater to libcs that poke about in kernel headers. */
-
-#define NSIG 32
-typedef unsigned long sigset_t;
-
-#endif /* __KERNEL__ */
-
-#define SIGHUP 1
-#define SIGINT 2
-#define SIGQUIT 3
-#define SIGILL 4
-#define SIGTRAP 5
-#define SIGABRT 6
-#define SIGIOT 6
-#define SIGBUS 7
-#define SIGFPE 8
-#define SIGKILL 9
-#define SIGUSR1 10
-#define SIGSEGV 11
-#define SIGUSR2 12
-#define SIGPIPE 13
-#define SIGALRM 14
-#define SIGTERM 15
-#define SIGSTKFLT 16
-#define SIGCHLD 17
-#define SIGCONT 18
-#define SIGSTOP 19
-#define SIGTSTP 20
-#define SIGTTIN 21
-#define SIGTTOU 22
-#define SIGURG 23
-#define SIGXCPU 24
-#define SIGXFSZ 25
-#define SIGVTALRM 26
-#define SIGPROF 27
-#define SIGWINCH 28
-#define SIGIO 29
-#define SIGPOLL SIGIO
-/*
-#define SIGLOST 29
-*/
-#define SIGPWR 30
-#define SIGSYS 31
-#define SIGUNUSED 31
-
-/* These should not be considered constants from userland. */
-#define SIGRTMIN 32
-#define SIGRTMAX (_NSIG-1)
-
-/*
- * SA_FLAGS values:
- *
- * SA_ONSTACK indicates that a registered stack_t will be used.
- * SA_INTERRUPT is a no-op, but left due to historical reasons. Use the
- * SA_RESTART flag to get restarting signals (which were the default long ago)
- * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
- * SA_RESETHAND clears the handler when the signal is delivered.
- * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
- * SA_NODEFER prevents the current signal from being masked in the handler.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_NOCLDSTOP 0x00000001
-#define SA_NOCLDWAIT 0x00000002 /* not supported yet */
-#define SA_SIGINFO 0x00000004
-#define SA_ONSTACK 0x08000000
-#define SA_RESTART 0x10000000
-#define SA_NODEFER 0x40000000
-#define SA_RESETHAND 0x80000000
-
-#define SA_NOMASK SA_NODEFER
-#define SA_ONESHOT SA_RESETHAND
-#define SA_INTERRUPT 0x20000000 /* dummy -- ignored */
-
-#define SA_RESTORER 0x04000000
-
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK 1
-#define SS_DISABLE 2
-
-#define MINSIGSTKSZ 2048
-#define SIGSTKSZ 8192
-
-#ifdef __KERNEL__
-
-/*
- * These values of sa_flags are used only by the kernel as part of the
- * irq handling routines.
- *
- * SA_INTERRUPT is also used by the irq handling routines.
- * SA_SHIRQ is for shared interrupt support on PCI and EISA.
- */
-#define SA_PROBE SA_ONESHOT
-#define SA_SAMPLE_RANDOM SA_RESTART
-#define SA_SHIRQ 0x04000000
-#endif
-
-#define SIG_BLOCK 0 /* for blocking signals */
-#define SIG_UNBLOCK 1 /* for unblocking signals */
-#define SIG_SETMASK 2 /* for setting the signal mask */
-
-/* Type of a signal handler. */
-typedef void (*__sighandler_t)(int);
-
-#define SIG_DFL ((__sighandler_t)0) /* default signal handling */
-#define SIG_IGN ((__sighandler_t)1) /* ignore signal */
-#define SIG_ERR ((__sighandler_t)-1) /* error return from signal */
-
-#ifdef __KERNEL__
-struct old_sigaction {
- __sighandler_t sa_handler;
- old_sigset_t sa_mask;
- unsigned long sa_flags;
- void (*sa_restorer)(void);
-};
-
-struct sigaction {
- __sighandler_t sa_handler;
- unsigned long sa_flags;
- void (*sa_restorer)(void);
- sigset_t sa_mask; /* mask last for extensibility */
-};
-
-struct k_sigaction {
- struct sigaction sa;
-};
-#else
-/* Here we must cater to libcs that poke about in kernel headers. */
-
-struct sigaction {
- union {
- __sighandler_t _sa_handler;
- void (*_sa_sigaction)(int, struct siginfo *, void *);
- } _u;
- sigset_t sa_mask;
- unsigned long sa_flags;
- void (*sa_restorer)(void);
-};
-
-#define sa_handler _u._sa_handler
-#define sa_sigaction _u._sa_sigaction
-
-#endif /* __KERNEL__ */
-
-typedef struct sigaltstack {
- void *ss_sp;
- int ss_flags;
- size_t ss_size;
-} stack_t;
-
-#ifdef __KERNEL__
-#include <asm/sigcontext.h>
-
-#define __HAVE_ARCH_SIG_BITOPS
-
-static __inline__ void sigaddset(sigset_t *set, int _sig)
-{
- __asm__("btsl %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
-}
-
-static __inline__ void sigdelset(sigset_t *set, int _sig)
-{
- __asm__("btrl %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
-}
-
-static __inline__ int __const_sigismember(sigset_t *set, int _sig)
-{
- unsigned long sig = _sig - 1;
- return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
-}
-
-static __inline__ int __gen_sigismember(sigset_t *set, int _sig)
-{
- int ret;
- __asm__("btl %2,%1\n\tsbbl %0,%0"
- : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
- return ret;
-}
-
-#define sigismember(set,sig) \
- (__builtin_constant_p(sig) ? \
- __const_sigismember((set),(sig)) : \
- __gen_sigismember((set),(sig)))
-
-#define sigmask(sig) (1UL << ((sig) - 1))
-
-static __inline__ int sigfindinword(unsigned long word)
-{
- __asm__("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc");
- return word;
-}
-
-#endif /* __KERNEL__ */
-
-#endif
+++ /dev/null
-#ifndef __ASM_SMP_H
-#define __ASM_SMP_H
-
-/*
- * We need the APIC definitions automatically as part of 'smp.h'
- */
-#ifndef __ASSEMBLY__
-#include <linux/config.h>
-#include <linux/threads.h>
-#include <linux/ptrace.h>
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-#ifndef __ASSEMBLY__
-#include <asm/bitops.h>
-#include <asm/mpspec.h>
-#ifdef CONFIG_X86_IO_APIC
-#include <asm/io_apic.h>
-#endif
-#include <asm/apic.h>
-#endif
-#endif
-
-#ifdef CONFIG_SMP
-# define TARGET_CPUS cpu_online_map
-# define INT_DELIVERY_MODE 1 /* logical delivery broadcast to all procs */
-#else
-# define INT_DELIVERY_MODE 1 /* logical delivery */
-# define TARGET_CPUS 0x01
-#endif
-
-#ifndef clustered_apic_mode
- #define clustered_apic_mode (0)
- #define esr_disable (0)
-#endif
-
-#ifdef CONFIG_SMP
-#ifndef __ASSEMBLY__
-
-/*
- * Private routines/data
- */
-
-extern void smp_alloc_memory(void);
-extern unsigned long phys_cpu_present_map;
-extern unsigned long cpu_online_map;
-extern volatile unsigned long smp_invalidate_needed;
-extern int pic_mode;
-extern void smp_flush_tlb(void);
-extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs);
-extern void smp_send_reschedule(int cpu);
-extern void smp_invalidate_rcv(void); /* Process an NMI */
-extern void (*mtrr_hook) (void);
-extern void zap_low_mappings (void);
-
-/*
- * On x86 all CPUs are mapped 1:1 to the APIC space.
- * This simplifies scheduling and IPI sending and
- * compresses data structures.
- */
-static inline int cpu_logical_map(int cpu)
-{
- return cpu;
-}
-static inline int cpu_number_map(int cpu)
-{
- return cpu;
-}
-
-/*
- * Some lowlevel functions might want to know about
- * the real APIC ID <-> CPU # mapping.
- */
-#define MAX_APICID 256
-extern volatile int cpu_to_physical_apicid[NR_CPUS];
-extern volatile int physical_apicid_to_cpu[MAX_APICID];
-extern volatile int cpu_to_logical_apicid[NR_CPUS];
-extern volatile int logical_apicid_to_cpu[MAX_APICID];
-
-/*
- * General functions that each host system must provide.
- */
-
-extern void smp_boot_cpus(void);
-extern void smp_store_cpu_info(int id); /* Store per CPU info (like the initial udelay numbers */
-
-/*
- * This function is needed by all SMP systems. It must _always_ be valid
- * from the initial startup. We map APIC_BASE very early in page_setup(),
- * so this is correct in the x86 case.
- */
-
-#define smp_processor_id() (current->processor)
-
-#endif /* !__ASSEMBLY__ */
-
-#define NO_PROC_ID 0xFF /* No processor magic marker */
-
-/*
- * This magic constant controls our willingness to transfer
- * a process across CPUs. Such a transfer incurs misses on the L1
- * cache, and on a P6 or P5 with multiple L2 caches L2 hits. My
- * gut feeling is this will vary by board in value. For a board
- * with separate L2 cache it probably depends also on the RSS, and
- * for a board with shared L2 cache it ought to decay fast as other
- * processes are run.
- */
-
-#define PROC_CHANGE_PENALTY 15 /* Schedule penalty */
-
-#endif
-#endif
+++ /dev/null
-/*
- * <asm/smplock.h>
- *
- * i386 SMP lock implementation
- */
-#include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/sched.h>
-#include <asm/current.h>
-
-extern spinlock_t kernel_flag;
-
-#define kernel_locked() spin_is_locked(&kernel_flag)
-
-/*
- * Release global kernel lock and global interrupt lock
- */
-#define release_kernel_lock(task, cpu) \
-do { \
- if (task->lock_depth >= 0) \
- spin_unlock(&kernel_flag); \
- release_irqlock(cpu); \
- __sti(); \
-} while (0)
-
-/*
- * Re-acquire the kernel lock
- */
-#define reacquire_kernel_lock(task) \
-do { \
- if (task->lock_depth >= 0) \
- spin_lock(&kernel_flag); \
-} while (0)
-
-
-/*
- * Getting the big kernel lock.
- *
- * This cannot happen asynchronously,
- * so we only need to worry about other
- * CPU's.
- */
-static __inline__ void lock_kernel(void)
-{
-#if 1
- if (!++current->lock_depth)
- spin_lock(&kernel_flag);
-#else
- __asm__ __volatile__(
- "incl %1\n\t"
- "jne 9f"
- spin_lock_string
- "\n9:"
- :"=m" (__dummy_lock(&kernel_flag)),
- "=m" (current->lock_depth));
-#endif
-}
-
-static __inline__ void unlock_kernel(void)
-{
- if (current->lock_depth < 0)
- BUG();
-#if 1
- if (--current->lock_depth < 0)
- spin_unlock(&kernel_flag);
-#else
- __asm__ __volatile__(
- "decl %1\n\t"
- "jns 9f\n\t"
- spin_unlock_string
- "\n9:"
- :"=m" (__dummy_lock(&kernel_flag)),
- "=m" (current->lock_depth));
-#endif
-}
+++ /dev/null
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockoptions(2) */
-#define SOL_SOCKET 1
-
-#define SO_DEBUG 1
-#define SO_REUSEADDR 2
-#define SO_TYPE 3
-#define SO_ERROR 4
-#define SO_DONTROUTE 5
-#define SO_BROADCAST 6
-#define SO_SNDBUF 7
-#define SO_RCVBUF 8
-#define SO_KEEPALIVE 9
-#define SO_OOBINLINE 10
-#define SO_NO_CHECK 11
-#define SO_PRIORITY 12
-#define SO_LINGER 13
-#define SO_BSDCOMPAT 14
-/* To add :#define SO_REUSEPORT 15 */
-#define SO_PASSCRED 16
-#define SO_PEERCRED 17
-#define SO_RCVLOWAT 18
-#define SO_SNDLOWAT 19
-#define SO_RCVTIMEO 20
-#define SO_SNDTIMEO 21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION 22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
-#define SO_SECURITY_ENCRYPTION_NETWORK 24
-
-#define SO_BINDTODEVICE 25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER 26
-#define SO_DETACH_FILTER 27
-
-#define SO_PEERNAME 28
-#define SO_TIMESTAMP 29
-#define SCM_TIMESTAMP SO_TIMESTAMP
-
-#define SO_ACCEPTCONN 30
-
-/* Nasty libc5 fixup - bletch */
-#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
-/* Socket types. */
-#define SOCK_STREAM 1 /* stream (connection) socket */
-#define SOCK_DGRAM 2 /* datagram (conn.less) socket */
-#define SOCK_RAW 3 /* raw socket */
-#define SOCK_RDM 4 /* reliably-delivered message */
-#define SOCK_SEQPACKET 5 /* sequential packet socket */
-#define SOCK_PACKET 10 /* linux specific way of */
- /* getting packets at the dev */
- /* level. For writing rarp and */
- /* other similar things on the */
- /* user level. */
-#define SOCK_MAX (SOCK_PACKET+1)
-#endif
-
-#endif /* _ASM_SOCKET_H */
+++ /dev/null
-#ifndef __ARCH_I386_SOCKIOS__
-#define __ARCH_I386_SOCKIOS__
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN 0x8901
-#define SIOCSPGRP 0x8902
-#define FIOGETOWN 0x8903
-#define SIOCGPGRP 0x8904
-#define SIOCATMARK 0x8905
-#define SIOCGSTAMP 0x8906 /* Get stamp */
-
-#endif
+++ /dev/null
-#ifndef __ASM_SOFTIRQ_H
-#define __ASM_SOFTIRQ_H
-
-#include <asm/atomic.h>
-#include <asm/hardirq.h>
-
-#define __cpu_bh_enable(cpu) \
- do { barrier(); local_bh_count(cpu)--; } while (0)
-#define cpu_bh_disable(cpu) \
- do { local_bh_count(cpu)++; barrier(); } while (0)
-
-#define local_bh_disable() cpu_bh_disable(smp_processor_id())
-#define __local_bh_enable() __cpu_bh_enable(smp_processor_id())
-
-#define in_softirq() (local_bh_count(smp_processor_id()) != 0)
-
-/*
- * NOTE: this assembly code assumes:
- *
- * (char *)&local_bh_count - 8 == (char *)&softirq_pending
- *
- * If you change the offsets in irq_stat then you have to
- * update this code as well.
- */
-#define local_bh_enable() \
-do { \
- unsigned int *ptr = &local_bh_count(smp_processor_id()); \
- \
- barrier(); \
- if (!--*ptr) \
- __asm__ __volatile__ ( \
- "cmpl $0, -8(%0);" \
- "jnz 2f;" \
- "1:;" \
- \
- ".section .text.lock,\"ax\";" \
- "2: pushl %%eax; pushl %%ecx; pushl %%edx;" \
- "call %c1;" \
- "popl %%edx; popl %%ecx; popl %%eax;" \
- "jmp 1b;" \
- ".previous;" \
- \
- : /* no output */ \
- : "r" (ptr), "i" (do_softirq) \
- /* no registers clobbered */ ); \
-} while (0)
-
-#endif /* __ASM_SOFTIRQ_H */
+++ /dev/null
-#ifndef __ASM_SPINLOCK_H
-#define __ASM_SPINLOCK_H
-
-#include <asm/atomic.h>
-#include <asm/rwlock.h>
-#include <asm/page.h>
-#include <linux/config.h>
-
-extern int printk(const char * fmt, ...)
- __attribute__ ((format (printf, 1, 2)));
-
-/* It seems that people are forgetting to
- * initialize their spinlocks properly, tsk tsk.
- * Remember to turn this off in 2.4. -ben
- */
-#if defined(CONFIG_DEBUG_SPINLOCK)
-#define SPINLOCK_DEBUG 1
-#else
-#define SPINLOCK_DEBUG 0
-#endif
-
-/*
- * Your basic SMP spinlocks, allowing only a single CPU anywhere
- */
-
-typedef struct {
- volatile unsigned int lock;
-#if SPINLOCK_DEBUG
- unsigned magic;
-#endif
-} spinlock_t;
-
-#define SPINLOCK_MAGIC 0xdead4ead
-
-#if SPINLOCK_DEBUG
-#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC
-#else
-#define SPINLOCK_MAGIC_INIT /* */
-#endif
-
-#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT }
-
-#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0)
-
-/*
- * Simple spin lock operations. There are two variants, one clears IRQ's
- * on the local processor, one does not.
- *
- * We make no fairness assumptions. They have a cost.
- */
-
-#define spin_is_locked(x) (*(volatile char *)(&(x)->lock) <= 0)
-#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x))
-
-#define spin_lock_string \
- "\n1:\t" \
- "lock ; decb %0\n\t" \
- "js 2f\n" \
- ".section .text.lock,\"ax\"\n" \
- "2:\t" \
- "cmpb $0,%0\n\t" \
- "rep;nop\n\t" \
- "jle 2b\n\t" \
- "jmp 1b\n" \
- ".previous"
-
-/*
- * This works. Despite all the confusion.
- * (except on PPro SMP or if we are using OOSTORE)
- * (PPro errata 66, 92)
- */
-
-#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
-
-#define spin_unlock_string \
- "movb $1,%0" \
- :"=m" (lock->lock) : : "memory"
-
-
-static inline void spin_unlock(spinlock_t *lock)
-{
-#if SPINLOCK_DEBUG
- if (lock->magic != SPINLOCK_MAGIC)
- BUG();
- if (!spin_is_locked(lock))
- BUG();
-#endif
- __asm__ __volatile__(
- spin_unlock_string
- );
-}
-
-#else
-
-#define spin_unlock_string \
- "xchgb %b0, %1" \
- :"=q" (oldval), "=m" (lock->lock) \
- :"0" (oldval) : "memory"
-
-static inline void spin_unlock(spinlock_t *lock)
-{
- char oldval = 1;
-#if SPINLOCK_DEBUG
- if (lock->magic != SPINLOCK_MAGIC)
- BUG();
- if (!spin_is_locked(lock))
- BUG();
-#endif
- __asm__ __volatile__(
- spin_unlock_string
- );
-}
-
-#endif
-
-static inline int spin_trylock(spinlock_t *lock)
-{
- char oldval;
- __asm__ __volatile__(
- "xchgb %b0,%1"
- :"=q" (oldval), "=m" (lock->lock)
- :"0" (0) : "memory");
- return oldval > 0;
-}
-
-static inline void spin_lock(spinlock_t *lock)
-{
-#if SPINLOCK_DEBUG
- __label__ here;
-here:
- if (lock->magic != SPINLOCK_MAGIC) {
-printk("eip: %p\n", &&here);
- BUG();
- }
-#endif
- __asm__ __volatile__(
- spin_lock_string
- :"=m" (lock->lock) : : "memory");
-}
-
-
-/*
- * Read-write spinlocks, allowing multiple readers
- * but only one writer.
- *
- * NOTE! it is quite common to have readers in interrupts
- * but no interrupt writers. For those circumstances we
- * can "mix" irq-safe locks - any writer needs to get a
- * irq-safe write-lock, but readers can get non-irqsafe
- * read-locks.
- */
-typedef struct {
- volatile unsigned int lock;
-#if SPINLOCK_DEBUG
- unsigned magic;
-#endif
-} rwlock_t;
-
-#define RWLOCK_MAGIC 0xdeaf1eed
-
-#if SPINLOCK_DEBUG
-#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC
-#else
-#define RWLOCK_MAGIC_INIT /* */
-#endif
-
-#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT }
-
-#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0)
-
-/*
- * On x86, we implement read-write locks as a 32-bit counter
- * with the high bit (sign) being the "contended" bit.
- *
- * The inline assembly is non-obvious. Think about it.
- *
- * Changed to use the same technique as rw semaphores. See
- * semaphore.h for details. -ben
- */
-/* the spinlock helpers are in arch/i386/kernel/semaphore.c */
-
-static inline void read_lock(rwlock_t *rw)
-{
-#if SPINLOCK_DEBUG
- if (rw->magic != RWLOCK_MAGIC)
- BUG();
-#endif
- __build_read_lock(rw, "__read_lock_failed");
-}
-
-static inline void write_lock(rwlock_t *rw)
-{
-#if SPINLOCK_DEBUG
- if (rw->magic != RWLOCK_MAGIC)
- BUG();
-#endif
- __build_write_lock(rw, "__write_lock_failed");
-}
-
-#define read_unlock(rw) asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory")
-#define write_unlock(rw) asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory")
-
-static inline int write_trylock(rwlock_t *lock)
-{
- atomic_t *count = (atomic_t *)lock;
- if (atomic_sub_and_test(RW_LOCK_BIAS, count))
- return 1;
- atomic_add(RW_LOCK_BIAS, count);
- return 0;
-}
-
-#endif /* __ASM_SPINLOCK_H */
+++ /dev/null
-#ifndef _I386_STAT_H
-#define _I386_STAT_H
-
-struct __old_kernel_stat {
- unsigned short st_dev;
- unsigned short st_ino;
- unsigned short st_mode;
- unsigned short st_nlink;
- unsigned short st_uid;
- unsigned short st_gid;
- unsigned short st_rdev;
- unsigned long st_size;
- unsigned long st_atime;
- unsigned long st_mtime;
- unsigned long st_ctime;
-};
-
-struct stat {
- unsigned short st_dev;
- unsigned short __pad1;
- unsigned long st_ino;
- unsigned short st_mode;
- unsigned short st_nlink;
- unsigned short st_uid;
- unsigned short st_gid;
- unsigned short st_rdev;
- unsigned short __pad2;
- unsigned long st_size;
- unsigned long st_blksize;
- unsigned long st_blocks;
- unsigned long st_atime;
- unsigned long __unused1;
- unsigned long st_mtime;
- unsigned long __unused2;
- unsigned long st_ctime;
- unsigned long __unused3;
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-/* This matches struct stat64 in glibc2.1, hence the absolutely
- * insane amounts of padding around dev_t's.
- */
-struct stat64 {
- unsigned short st_dev;
- unsigned char __pad0[10];
-
-#define STAT64_HAS_BROKEN_ST_INO 1
- unsigned long __st_ino;
-
- unsigned int st_mode;
- unsigned int st_nlink;
-
- unsigned long st_uid;
- unsigned long st_gid;
-
- unsigned short st_rdev;
- unsigned char __pad3[10];
-
- long long st_size;
- unsigned long st_blksize;
-
- unsigned long st_blocks; /* Number 512-byte blocks allocated. */
- unsigned long __pad4; /* future possible st_blocks high bits */
-
- unsigned long st_atime;
- unsigned long __pad5;
-
- unsigned long st_mtime;
- unsigned long __pad6;
-
- unsigned long st_ctime;
- unsigned long __pad7; /* will be high 32 bits of ctime someday */
-
- unsigned long long st_ino;
-};
-
-#endif
+++ /dev/null
-#ifndef _I386_STATFS_H
-#define _I386_STATFS_H
-
-#ifndef __KERNEL_STRICT_NAMES
-
-#include <linux/types.h>
-
-typedef __kernel_fsid_t fsid_t;
-
-#endif
-
-struct statfs {
- long f_type;
- long f_bsize;
- long f_blocks;
- long f_bfree;
- long f_bavail;
- long f_files;
- long f_ffree;
- __kernel_fsid_t f_fsid;
- long f_namelen;
- long f_spare[6];
-};
-
-#endif
+++ /dev/null
-#ifndef _I386_STRING_I486_H_
-#define _I386_STRING_I486_H_
-
-/*
- * This string-include defines all string functions as inline
- * functions. Use gcc. It also assumes ds=es=data space, this should be
- * normal. Most of the string-functions are rather heavily hand-optimized,
- * see especially strtok,strstr,str[c]spn. They should work, but are not
- * very easy to understand. Everything is done entirely within the register
- * set, making the functions fast and clean.
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- * Revised and optimized for i486/pentium
- * 1994/03/15 by Alberto Vignani/Davide Parodi @crf.it
- *
- * Split into 2 CPU specific files by Alan Cox to keep #ifdef noise down.
- *
- * 1999/10/5 Proper register args for newer GCCs and minor bugs
- * fixed - Petko Manolov (petkan@spct.net)
- * 1999/10/14 3DNow memscpy() added - Petkan
- * 2000/05/09 extern changed to static in function definitions
- * and a few cleanups - Petkan
- */
-
-#define __HAVE_ARCH_STRCPY
-static inline char * strcpy(char * dest,const char *src)
-{
-register char *tmp= (char *)dest;
-register char dummy;
-__asm__ __volatile__(
- "\n1:\t"
- "movb (%0),%2\n\t"
- "incl %0\n\t"
- "movb %2,(%1)\n\t"
- "incl %1\n\t"
- "testb %2,%2\n\t"
- "jne 1b"
- :"=r" (src), "=r" (tmp), "=q" (dummy)
- :"0" (src), "1" (tmp)
- :"memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRNCPY
-static inline char * strncpy(char * dest,const char *src,size_t count)
-{
-register char *tmp= (char *)dest;
-register char dummy;
-if (count) {
-__asm__ __volatile__(
- "\n1:\t"
- "movb (%0),%2\n\t"
- "incl %0\n\t"
- "movb %2,(%1)\n\t"
- "incl %1\n\t"
- "decl %3\n\t"
- "je 3f\n\t"
- "testb %2,%2\n\t"
- "jne 1b\n\t"
- "2:\tmovb %2,(%1)\n\t"
- "incl %1\n\t"
- "decl %3\n\t"
- "jne 2b\n\t"
- "3:"
- :"=r" (src), "=r" (tmp), "=q" (dummy), "=r" (count)
- :"0" (src), "1" (tmp), "3" (count)
- :"memory");
- } /* if (count) */
-return dest;
-}
-
-#define __HAVE_ARCH_STRCAT
-static inline char * strcat(char * dest,const char * src)
-{
-register char *tmp = (char *)(dest-1);
-register char dummy;
-__asm__ __volatile__(
- "\n1:\tincl %1\n\t"
- "cmpb $0,(%1)\n\t"
- "jne 1b\n"
- "2:\tmovb (%2),%b0\n\t"
- "incl %2\n\t"
- "movb %b0,(%1)\n\t"
- "incl %1\n\t"
- "testb %b0,%b0\n\t"
- "jne 2b\n"
- :"=q" (dummy), "=r" (tmp), "=r" (src)
- :"1" (tmp), "2" (src)
- :"memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRNCAT
-static inline char * strncat(char * dest,const char * src,size_t count)
-{
-register char *tmp = (char *)(dest-1);
-register char dummy;
-__asm__ __volatile__(
- "\n1:\tincl %1\n\t"
- "cmpb $0,(%1)\n\t"
- "jne 1b\n"
- "2:\tdecl %3\n\t"
- "js 3f\n\t"
- "movb (%2),%b0\n\t"
- "incl %2\n\t"
- "movb %b0,(%1)\n\t"
- "incl %1\n\t"
- "testb %b0,%b0\n\t"
- "jne 2b\n"
- "3:\txorb %0,%0\n\t"
- "movb %b0,(%1)\n\t"
- :"=q" (dummy), "=r" (tmp), "=r" (src), "=r" (count)
- :"1" (tmp), "2" (src), "3" (count)
- :"memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRCMP
-static inline int strcmp(const char * cs,const char * ct)
-{
-register int __res;
-__asm__ __volatile__(
- "\n1:\tmovb (%1),%b0\n\t"
- "incl %1\n\t"
- "cmpb %b0,(%2)\n\t"
- "jne 2f\n\t"
- "incl %2\n\t"
- "testb %b0,%b0\n\t"
- "jne 1b\n\t"
- "xorl %0,%0\n\t"
- "jmp 3f\n"
- "2:\tmovl $1,%0\n\t"
- "jb 3f\n\t"
- "negl %0\n"
- "3:"
- :"=q" (__res), "=r" (cs), "=r" (ct)
- :"1" (cs), "2" (ct)
- : "memory" );
-return __res;
-}
-
-#define __HAVE_ARCH_STRNCMP
-static inline int strncmp(const char * cs,const char * ct,size_t count)
-{
-register int __res;
-__asm__ __volatile__(
- "\n1:\tdecl %3\n\t"
- "js 2f\n\t"
- "movb (%1),%b0\n\t"
- "incl %1\n\t"
- "cmpb %b0,(%2)\n\t"
- "jne 3f\n\t"
- "incl %2\n\t"
- "testb %b0,%b0\n\t"
- "jne 1b\n"
- "2:\txorl %0,%0\n\t"
- "jmp 4f\n"
- "3:\tmovl $1,%0\n\t"
- "jb 4f\n\t"
- "negl %0\n"
- "4:"
- :"=q" (__res), "=r" (cs), "=r" (ct), "=r" (count)
- :"1" (cs), "2" (ct), "3" (count));
-return __res;
-}
-
-#define __HAVE_ARCH_STRCHR
-static inline char * strchr(const char * s, int c)
-{
-register char * __res;
-__asm__ __volatile__(
- "movb %%al,%%ah\n"
- "1:\tmovb (%1),%%al\n\t"
- "cmpb %%ah,%%al\n\t"
- "je 2f\n\t"
- "incl %1\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b\n\t"
- "xorl %1,%1\n"
- "2:\tmovl %1,%0\n\t"
- :"=a" (__res), "=r" (s)
- :"0" (c), "1" (s));
-return __res;
-}
-
-#define __HAVE_ARCH_STRRCHR
-static inline char * strrchr(const char * s, int c)
-{
-int d0, d1;
-register char * __res;
-__asm__ __volatile__(
- "movb %%al,%%ah\n"
- "1:\tlodsb\n\t"
- "cmpb %%ah,%%al\n\t"
- "jne 2f\n\t"
- "leal -1(%%esi),%0\n"
- "2:\ttestb %%al,%%al\n\t"
- "jne 1b"
- :"=d" (__res), "=&S" (d0), "=&a" (d1)
- :"0" (0), "1" (s), "2" (c));
-return __res;
-}
-
-
-#define __HAVE_ARCH_STRCSPN
-static inline size_t strcspn(const char * cs, const char * ct)
-{
-int d0, d1;
-register char * __res;
-__asm__ __volatile__(
- "movl %6,%%edi\n\t"
- "repne\n\t"
- "scasb\n\t"
- "notl %%ecx\n\t"
- "decl %%ecx\n\t"
- "movl %%ecx,%%edx\n"
- "1:\tlodsb\n\t"
- "testb %%al,%%al\n\t"
- "je 2f\n\t"
- "movl %6,%%edi\n\t"
- "movl %%edx,%%ecx\n\t"
- "repne\n\t"
- "scasb\n\t"
- "jne 1b\n"
- "2:\tdecl %0"
- :"=S" (__res), "=&a" (d0), "=&c" (d1)
- :"0" (cs), "1" (0), "2" (0xffffffff), "g" (ct)
- :"dx", "di");
-return __res-cs;
-}
-
-
-#define __HAVE_ARCH_STRLEN
-static inline size_t strlen(const char * s)
-{
-/*
- * slightly slower on a 486, but with better chances of
- * register allocation
- */
-register char dummy, *tmp= (char *)s;
-__asm__ __volatile__(
- "\n1:\t"
- "movb\t(%0),%1\n\t"
- "incl\t%0\n\t"
- "testb\t%1,%1\n\t"
- "jne\t1b"
- :"=r" (tmp),"=q" (dummy)
- :"0" (s)
- : "memory" );
-return (tmp-s-1);
-}
-
-/* Added by Gertjan van Wingerde to make minix and sysv module work */
-#define __HAVE_ARCH_STRNLEN
-static inline size_t strnlen(const char * s, size_t count)
-{
-int d0;
-register int __res;
-__asm__ __volatile__(
- "movl %3,%0\n\t"
- "jmp 2f\n"
- "1:\tcmpb $0,(%0)\n\t"
- "je 3f\n\t"
- "incl %0\n"
- "2:\tdecl %2\n\t"
- "cmpl $-1,%2\n\t"
- "jne 1b\n"
- "3:\tsubl %3,%0"
- :"=a" (__res), "=&d" (d0)
- :"1" (count), "c" (s));
-return __res;
-}
-/* end of additional stuff */
-
-
-/*
- * These ought to get tweaked to do some cache priming.
- */
-
-static inline void * __memcpy_by4(void * to, const void * from, size_t n)
-{
-register void *tmp = (void *)to;
-register int dummy1,dummy2;
-__asm__ __volatile__ (
- "\n1:\tmovl (%2),%0\n\t"
- "addl $4,%2\n\t"
- "movl %0,(%1)\n\t"
- "addl $4,%1\n\t"
- "decl %3\n\t"
- "jnz 1b"
- :"=r" (dummy1), "=r" (tmp), "=r" (from), "=r" (dummy2)
- :"1" (tmp), "2" (from), "3" (n/4)
- :"memory");
-return (to);
-}
-
-static inline void * __memcpy_by2(void * to, const void * from, size_t n)
-{
-register void *tmp = (void *)to;
-register int dummy1,dummy2;
-__asm__ __volatile__ (
- "shrl $1,%3\n\t"
- "jz 2f\n" /* only a word */
- "1:\tmovl (%2),%0\n\t"
- "addl $4,%2\n\t"
- "movl %0,(%1)\n\t"
- "addl $4,%1\n\t"
- "decl %3\n\t"
- "jnz 1b\n"
- "2:\tmovw (%2),%w0\n\t"
- "movw %w0,(%1)"
- :"=r" (dummy1), "=r" (tmp), "=r" (from), "=r" (dummy2)
- :"1" (tmp), "2" (from), "3" (n/2)
- :"memory");
-return (to);
-}
-
-static inline void * __memcpy_g(void * to, const void * from, size_t n)
-{
-int d0, d1, d2;
-register void *tmp = (void *)to;
-__asm__ __volatile__ (
- "shrl $1,%%ecx\n\t"
- "jnc 1f\n\t"
- "movsb\n"
- "1:\tshrl $1,%%ecx\n\t"
- "jnc 2f\n\t"
- "movsw\n"
- "2:\trep\n\t"
- "movsl"
- :"=&c" (d0), "=&D" (d1), "=&S" (d2)
- :"0" (n), "1" ((long) tmp), "2" ((long) from)
- :"memory");
-return (to);
-}
-
-#define __memcpy_c(d,s,count) \
-((count%4==0) ? \
- __memcpy_by4((d),(s),(count)) : \
- ((count%2==0) ? \
- __memcpy_by2((d),(s),(count)) : \
- __memcpy_g((d),(s),(count))))
-
-#define __memcpy(d,s,count) \
-(__builtin_constant_p(count) ? \
- __memcpy_c((d),(s),(count)) : \
- __memcpy_g((d),(s),(count)))
-
-#define __HAVE_ARCH_MEMCPY
-
-#include <linux/config.h>
-
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-/*
-** This CPU favours 3DNow strongly (eg AMD K6-II, K6-III, Athlon)
-*/
-
-static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
-{
- if (len < 512)
- return __memcpy_c(to, from, len);
- return _mmx_memcpy(to, from, len);
-}
-
-static inline void *__memcpy3d(void *to, const void *from, size_t len)
-{
- if(len < 512)
- return __memcpy_g(to, from, len);
- return _mmx_memcpy(to, from, len);
-}
-
-#define memcpy(d, s, count) \
-(__builtin_constant_p(count) ? \
- __constant_memcpy3d((d),(s),(count)) : \
- __memcpy3d((d),(s),(count)))
-
-#else /* CONFIG_X86_USE_3DNOW */
-
-/*
-** Generic routines
-*/
-
-
-#define memcpy(d, s, count) __memcpy(d, s, count)
-
-#endif /* CONFIG_X86_USE_3DNOW */
-
-
-extern void __struct_cpy_bug( void );
-
-#define struct_cpy(x,y) \
-({ \
- if (sizeof(*(x)) != sizeof(*(y))) \
- __struct_cpy_bug; \
- memcpy(x, y, sizeof(*(x))); \
-})
-
-
-#define __HAVE_ARCH_MEMMOVE
-static inline void * memmove(void * dest,const void * src, size_t n)
-{
-int d0, d1, d2;
-register void *tmp = (void *)dest;
-if (dest<src)
-__asm__ __volatile__ (
- "rep\n\t"
- "movsb"
- :"=&c" (d0), "=&S" (d1), "=&D" (d2)
- :"0" (n), "1" (src), "2" (tmp)
- :"memory");
-else
-__asm__ __volatile__ (
- "std\n\t"
- "rep\n\t"
- "movsb\n\t"
- "cld"
- :"=&c" (d0), "=&S" (d1), "=&D" (d2)
- :"0" (n), "1" (n-1+(const char *)src), "2" (n-1+(char *)tmp)
- :"memory");
-return dest;
-}
-
-
-#define __HAVE_ARCH_MEMCMP
-static inline int memcmp(const void * cs,const void * ct,size_t count)
-{
-int d0, d1, d2;
-register int __res;
-__asm__ __volatile__(
- "repe\n\t"
- "cmpsb\n\t"
- "je 1f\n\t"
- "sbbl %0,%0\n\t"
- "orb $1,%b0\n"
- "1:"
- :"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
- :"0" (0), "1" (cs), "2" (ct), "3" (count));
-return __res;
-}
-
-
-#define __HAVE_ARCH_MEMCHR
-static inline void * memchr(const void * cs,int c,size_t count)
-{
-int d0;
-register void * __res;
-if (!count)
- return NULL;
-__asm__ __volatile__(
- "repne\n\t"
- "scasb\n\t"
- "je 1f\n\t"
- "movl $1,%0\n"
- "1:\tdecl %0"
- :"=D" (__res), "=&c" (d0)
- :"a" (c), "0" (cs), "1" (count));
-return __res;
-}
-
-#define __memset_cc(s,c,count) \
-((count%4==0) ? \
- __memset_cc_by4((s),(c),(count)) : \
- ((count%2==0) ? \
- __memset_cc_by2((s),(c),(count)) : \
- __memset_cg((s),(c),(count))))
-
-#define __memset_gc(s,c,count) \
-((count%4==0) ? \
- __memset_gc_by4((s),(c),(count)) : \
- ((count%2==0) ? \
- __memset_gc_by2((s),(c),(count)) : \
- __memset_gg((s),(c),(count))))
-
-#define __HAVE_ARCH_MEMSET
-#define memset(s,c,count) \
-(__builtin_constant_p(c) ? \
- (__builtin_constant_p(count) ? \
- __memset_cc((s),(c),(count)) : \
- __memset_cg((s),(c),(count))) : \
- (__builtin_constant_p(count) ? \
- __memset_gc((s),(c),(count)) : \
- __memset_gg((s),(c),(count))))
-
-static inline void * __memset_cc_by4(void * s, char c, size_t count)
-{
-/*
- * register char *tmp = s;
- */
-register char *tmp = (char *)s;
-register int dummy;
-__asm__ __volatile__ (
- "\n1:\tmovl %2,(%0)\n\t"
- "addl $4,%0\n\t"
- "decl %1\n\t"
- "jnz 1b"
- :"=r" (tmp), "=r" (dummy)
- :"q" (0x01010101UL * (unsigned char) c), "0" (tmp), "1" (count/4)
- :"memory");
-return s;
-}
-
-static inline void * __memset_cc_by2(void * s, char c, size_t count)
-{
-register void *tmp = (void *)s;
-register int dummy;
-__asm__ __volatile__ (
- "shrl $1,%1\n\t" /* may be divisible also by 4 */
- "jz 2f\n"
- "\n1:\tmovl %2,(%0)\n\t"
- "addl $4,%0\n\t"
- "decl %1\n\t"
- "jnz 1b\n"
- "2:\tmovw %w2,(%0)"
- :"=r" (tmp), "=r" (dummy)
- :"q" (0x01010101UL * (unsigned char) c), "0" (tmp), "1" (count/2)
- :"memory");
-return s;
-}
-
-static inline void * __memset_gc_by4(void * s, char c, size_t count)
-{
-register void *tmp = (void *)s;
-register int dummy;
-__asm__ __volatile__ (
- "movb %b0,%h0\n"
- "pushw %w0\n\t"
- "shll $16,%0\n\t"
- "popw %w0\n"
- "1:\tmovl %0,(%1)\n\t"
- "addl $4,%1\n\t"
- "decl %2\n\t"
- "jnz 1b\n"
- :"=q" (c), "=r" (tmp), "=r" (dummy)
- :"0" ((unsigned) c), "1" (tmp), "2" (count/4)
- :"memory");
-return s;
-}
-
-static inline void * __memset_gc_by2(void * s, char c, size_t count)
-{
-register void *tmp = (void *)s;
-register int dummy1,dummy2;
-__asm__ __volatile__ (
- "movb %b0,%h0\n\t"
- "shrl $1,%2\n\t" /* may be divisible also by 4 */
- "jz 2f\n\t"
- "pushw %w0\n\t"
- "shll $16,%0\n\t"
- "popw %w0\n"
- "1:\tmovl %0,(%1)\n\t"
- "addl $4,%1\n\t"
- "decl %2\n\t"
- "jnz 1b\n"
- "2:\tmovw %w0,(%1)"
- :"=q" (dummy1), "=r" (tmp), "=r" (dummy2)
- :"0" ((unsigned) c), "1" (tmp), "2" (count/2)
- :"memory");
-return s;
-}
-
-static inline void * __memset_cg(void * s, char c, size_t count)
-{
-int d0, d1;
-register void *tmp = (void *)s;
-__asm__ __volatile__ (
- "shrl $1,%%ecx\n\t"
- "rep\n\t"
- "stosw\n\t"
- "jnc 1f\n\t"
- "movb %%al,(%%edi)\n"
- "1:"
- :"=&c" (d0), "=&D" (d1)
- :"a" (0x0101U * (unsigned char) c), "0" (count), "1" (tmp)
- :"memory");
-return s;
-}
-
-static inline void * __memset_gg(void * s,char c,size_t count)
-{
-int d0, d1, d2;
-register void *tmp = (void *)s;
-__asm__ __volatile__ (
- "movb %%al,%%ah\n\t"
- "shrl $1,%%ecx\n\t"
- "rep\n\t"
- "stosw\n\t"
- "jnc 1f\n\t"
- "movb %%al,(%%edi)\n"
- "1:"
- :"=&c" (d0), "=&D" (d1), "=&D" (d2)
- :"0" (count), "1" (tmp), "2" (c)
- :"memory");
-return s;
-}
-
-
-/*
- * find the first occurrence of byte 'c', or 1 past the area if none
- */
-#define __HAVE_ARCH_MEMSCAN
-static inline void * memscan(void * addr, int c, size_t size)
-{
- if (!size)
- return addr;
- __asm__("repnz; scasb
- jnz 1f
- dec %%edi
-1: "
- : "=D" (addr), "=c" (size)
- : "0" (addr), "1" (size), "a" (c));
- return addr;
-}
-
-#endif
+++ /dev/null
-#ifndef _I386_STRING_H_
-#define _I386_STRING_H_
-
-#ifdef __KERNEL__
-#include <linux/config.h>
-/*
- * On a 486 or Pentium, we are better off not using the
- * byte string operations. But on a 386 or a PPro the
- * byte string ops are faster than doing it by hand
- * (MUCH faster on a Pentium).
- *
- * Also, the byte strings actually work correctly. Forget
- * the i486 routines for now as they may be broken..
- */
-#if FIXED_486_STRING && defined(CONFIG_X86_USE_STRING_486)
-#include <asm/string-486.h>
-#else
-
-/*
- * This string-include defines all string functions as inline
- * functions. Use gcc. It also assumes ds=es=data space, this should be
- * normal. Most of the string-functions are rather heavily hand-optimized,
- * see especially strtok,strstr,str[c]spn. They should work, but are not
- * very easy to understand. Everything is done entirely within the register
- * set, making the functions fast and clean. String instructions have been
- * used through-out, making for "slightly" unclear code :-)
- *
- * NO Copyright (C) 1991, 1992 Linus Torvalds,
- * consider these trivial functions to be PD.
- */
-
-#define __HAVE_ARCH_STRCPY
-static inline char * strcpy(char * dest,const char *src)
-{
-int d0, d1, d2;
-__asm__ __volatile__(
- "1:\tlodsb\n\t"
- "stosb\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b"
- : "=&S" (d0), "=&D" (d1), "=&a" (d2)
- :"0" (src),"1" (dest) : "memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRNCPY
-static inline char * strncpy(char * dest,const char *src,size_t count)
-{
-int d0, d1, d2, d3;
-__asm__ __volatile__(
- "1:\tdecl %2\n\t"
- "js 2f\n\t"
- "lodsb\n\t"
- "stosb\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b\n\t"
- "rep\n\t"
- "stosb\n"
- "2:"
- : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
- :"0" (src),"1" (dest),"2" (count) : "memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRCAT
-static inline char * strcat(char * dest,const char * src)
-{
-int d0, d1, d2, d3;
-__asm__ __volatile__(
- "repne\n\t"
- "scasb\n\t"
- "decl %1\n"
- "1:\tlodsb\n\t"
- "stosb\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b"
- : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
- : "0" (src), "1" (dest), "2" (0), "3" (0xffffffff):"memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRNCAT
-static inline char * strncat(char * dest,const char * src,size_t count)
-{
-int d0, d1, d2, d3;
-__asm__ __volatile__(
- "repne\n\t"
- "scasb\n\t"
- "decl %1\n\t"
- "movl %8,%3\n"
- "1:\tdecl %3\n\t"
- "js 2f\n\t"
- "lodsb\n\t"
- "stosb\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b\n"
- "2:\txorl %2,%2\n\t"
- "stosb"
- : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
- : "0" (src),"1" (dest),"2" (0),"3" (0xffffffff), "g" (count)
- : "memory");
-return dest;
-}
-
-#define __HAVE_ARCH_STRCMP
-static inline int strcmp(const char * cs,const char * ct)
-{
-int d0, d1;
-register int __res;
-__asm__ __volatile__(
- "1:\tlodsb\n\t"
- "scasb\n\t"
- "jne 2f\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b\n\t"
- "xorl %%eax,%%eax\n\t"
- "jmp 3f\n"
- "2:\tsbbl %%eax,%%eax\n\t"
- "orb $1,%%al\n"
- "3:"
- :"=a" (__res), "=&S" (d0), "=&D" (d1)
- :"1" (cs),"2" (ct));
-return __res;
-}
-
-#define __HAVE_ARCH_STRNCMP
-static inline int strncmp(const char * cs,const char * ct,size_t count)
-{
-register int __res;
-int d0, d1, d2;
-__asm__ __volatile__(
- "1:\tdecl %3\n\t"
- "js 2f\n\t"
- "lodsb\n\t"
- "scasb\n\t"
- "jne 3f\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b\n"
- "2:\txorl %%eax,%%eax\n\t"
- "jmp 4f\n"
- "3:\tsbbl %%eax,%%eax\n\t"
- "orb $1,%%al\n"
- "4:"
- :"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
- :"1" (cs),"2" (ct),"3" (count));
-return __res;
-}
-
-#define __HAVE_ARCH_STRCHR
-static inline char * strchr(const char * s, int c)
-{
-int d0;
-register char * __res;
-__asm__ __volatile__(
- "movb %%al,%%ah\n"
- "1:\tlodsb\n\t"
- "cmpb %%ah,%%al\n\t"
- "je 2f\n\t"
- "testb %%al,%%al\n\t"
- "jne 1b\n\t"
- "movl $1,%1\n"
- "2:\tmovl %1,%0\n\t"
- "decl %0"
- :"=a" (__res), "=&S" (d0) : "1" (s),"0" (c));
-return __res;
-}
-
-#define __HAVE_ARCH_STRRCHR
-static inline char * strrchr(const char * s, int c)
-{
-int d0, d1;
-register char * __res;
-__asm__ __volatile__(
- "movb %%al,%%ah\n"
- "1:\tlodsb\n\t"
- "cmpb %%ah,%%al\n\t"
- "jne 2f\n\t"
- "leal -1(%%esi),%0\n"
- "2:\ttestb %%al,%%al\n\t"
- "jne 1b"
- :"=g" (__res), "=&S" (d0), "=&a" (d1) :"0" (0),"1" (s),"2" (c));
-return __res;
-}
-
-#define __HAVE_ARCH_STRLEN
-static inline size_t strlen(const char * s)
-{
-int d0;
-register int __res;
-__asm__ __volatile__(
- "repne\n\t"
- "scasb\n\t"
- "notl %0\n\t"
- "decl %0"
- :"=c" (__res), "=&D" (d0) :"1" (s),"a" (0), "0" (0xffffffff));
-return __res;
-}
-
-static inline void * __memcpy(void * to, const void * from, size_t n)
-{
-int d0, d1, d2;
-__asm__ __volatile__(
- "rep ; movsl\n\t"
- "testb $2,%b4\n\t"
- "je 1f\n\t"
- "movsw\n"
- "1:\ttestb $1,%b4\n\t"
- "je 2f\n\t"
- "movsb\n"
- "2:"
- : "=&c" (d0), "=&D" (d1), "=&S" (d2)
- :"0" (n/4), "q" (n),"1" ((long) to),"2" ((long) from)
- : "memory");
-return (to);
-}
-
-/*
- * This looks horribly ugly, but the compiler can optimize it totally,
- * as the count is constant.
- */
-static inline void * __constant_memcpy(void * to, const void * from, size_t n)
-{
- switch (n) {
- case 0:
- return to;
- case 1:
- *(unsigned char *)to = *(const unsigned char *)from;
- return to;
- case 2:
- *(unsigned short *)to = *(const unsigned short *)from;
- return to;
- case 3:
- *(unsigned short *)to = *(const unsigned short *)from;
- *(2+(unsigned char *)to) = *(2+(const unsigned char *)from);
- return to;
- case 4:
- *(unsigned long *)to = *(const unsigned long *)from;
- return to;
- case 6: /* for Ethernet addresses */
- *(unsigned long *)to = *(const unsigned long *)from;
- *(2+(unsigned short *)to) = *(2+(const unsigned short *)from);
- return to;
- case 8:
- *(unsigned long *)to = *(const unsigned long *)from;
- *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
- return to;
- case 12:
- *(unsigned long *)to = *(const unsigned long *)from;
- *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
- *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
- return to;
- case 16:
- *(unsigned long *)to = *(const unsigned long *)from;
- *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
- *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
- *(3+(unsigned long *)to) = *(3+(const unsigned long *)from);
- return to;
- case 20:
- *(unsigned long *)to = *(const unsigned long *)from;
- *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
- *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
- *(3+(unsigned long *)to) = *(3+(const unsigned long *)from);
- *(4+(unsigned long *)to) = *(4+(const unsigned long *)from);
- return to;
- }
-#define COMMON(x) \
-__asm__ __volatile__( \
- "rep ; movsl" \
- x \
- : "=&c" (d0), "=&D" (d1), "=&S" (d2) \
- : "0" (n/4),"1" ((long) to),"2" ((long) from) \
- : "memory");
-{
- int d0, d1, d2;
- switch (n % 4) {
- case 0: COMMON(""); return to;
- case 1: COMMON("\n\tmovsb"); return to;
- case 2: COMMON("\n\tmovsw"); return to;
- default: COMMON("\n\tmovsw\n\tmovsb"); return to;
- }
-}
-
-#undef COMMON
-}
-
-#define __HAVE_ARCH_MEMCPY
-
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-/*
- * This CPU favours 3DNow strongly (eg AMD Athlon)
- */
-
-static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
-{
- if (len < 512)
- return __constant_memcpy(to, from, len);
- return _mmx_memcpy(to, from, len);
-}
-
-static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
-{
- if (len < 512)
- return __memcpy(to, from, len);
- return _mmx_memcpy(to, from, len);
-}
-
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy3d((t),(f),(n)) : \
- __memcpy3d((t),(f),(n)))
-
-#else
-
-/*
- * No 3D Now!
- */
-
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy((t),(f),(n)) : \
- __memcpy((t),(f),(n)))
-
-#endif
-
-/*
- * struct_cpy(x,y), copy structure *x into (matching structure) *y.
- *
- * We get link-time errors if the structure sizes do not match.
- * There is no runtime overhead, it's all optimized away at
- * compile time.
- */
-extern void __struct_cpy_bug (void);
-
-#define struct_cpy(x,y) \
-({ \
- if (sizeof(*(x)) != sizeof(*(y))) \
- __struct_cpy_bug; \
- memcpy(x, y, sizeof(*(x))); \
-})
-
-#define __HAVE_ARCH_MEMMOVE
-static inline void * memmove(void * dest,const void * src, size_t n)
-{
-int d0, d1, d2;
-if (dest<src)
-__asm__ __volatile__(
- "rep\n\t"
- "movsb"
- : "=&c" (d0), "=&S" (d1), "=&D" (d2)
- :"0" (n),"1" (src),"2" (dest)
- : "memory");
-else
-__asm__ __volatile__(
- "std\n\t"
- "rep\n\t"
- "movsb\n\t"
- "cld"
- : "=&c" (d0), "=&S" (d1), "=&D" (d2)
- :"0" (n),
- "1" (n-1+(const char *)src),
- "2" (n-1+(char *)dest)
- :"memory");
-return dest;
-}
-
-#define memcmp __builtin_memcmp
-
-#define __HAVE_ARCH_MEMCHR
-static inline void * memchr(const void * cs,int c,size_t count)
-{
-int d0;
-register void * __res;
-if (!count)
- return NULL;
-__asm__ __volatile__(
- "repne\n\t"
- "scasb\n\t"
- "je 1f\n\t"
- "movl $1,%0\n"
- "1:\tdecl %0"
- :"=D" (__res), "=&c" (d0) : "a" (c),"0" (cs),"1" (count));
-return __res;
-}
-
-static inline void * __memset_generic(void * s, char c,size_t count)
-{
-int d0, d1;
-__asm__ __volatile__(
- "rep\n\t"
- "stosb"
- : "=&c" (d0), "=&D" (d1)
- :"a" (c),"1" (s),"0" (count)
- :"memory");
-return s;
-}
-
-/* we might want to write optimized versions of these later */
-#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
-
-/*
- * memset(x,0,y) is a reasonably common thing to do, so we want to fill
- * things 32 bits at a time even when we don't know the size of the
- * area at compile-time..
- */
-static inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
-{
-int d0, d1;
-__asm__ __volatile__(
- "rep ; stosl\n\t"
- "testb $2,%b3\n\t"
- "je 1f\n\t"
- "stosw\n"
- "1:\ttestb $1,%b3\n\t"
- "je 2f\n\t"
- "stosb\n"
- "2:"
- : "=&c" (d0), "=&D" (d1)
- :"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
- :"memory");
-return (s);
-}
-
-/* Added by Gertjan van Wingerde to make minix and sysv module work */
-#define __HAVE_ARCH_STRNLEN
-static inline size_t strnlen(const char * s, size_t count)
-{
-int d0;
-register int __res;
-__asm__ __volatile__(
- "movl %2,%0\n\t"
- "jmp 2f\n"
- "1:\tcmpb $0,(%0)\n\t"
- "je 3f\n\t"
- "incl %0\n"
- "2:\tdecl %1\n\t"
- "cmpl $-1,%1\n\t"
- "jne 1b\n"
- "3:\tsubl %2,%0"
- :"=a" (__res), "=&d" (d0)
- :"c" (s),"1" (count));
-return __res;
-}
-/* end of additional stuff */
-
-#define __HAVE_ARCH_STRSTR
-
-extern char *strstr(const char *cs, const char *ct);
-
-/*
- * This looks horribly ugly, but the compiler can optimize it totally,
- * as we by now know that both pattern and count is constant..
- */
-static inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
-{
- switch (count) {
- case 0:
- return s;
- case 1:
- *(unsigned char *)s = pattern;
- return s;
- case 2:
- *(unsigned short *)s = pattern;
- return s;
- case 3:
- *(unsigned short *)s = pattern;
- *(2+(unsigned char *)s) = pattern;
- return s;
- case 4:
- *(unsigned long *)s = pattern;
- return s;
- }
-#define COMMON(x) \
-__asm__ __volatile__( \
- "rep ; stosl" \
- x \
- : "=&c" (d0), "=&D" (d1) \
- : "a" (pattern),"0" (count/4),"1" ((long) s) \
- : "memory")
-{
- int d0, d1;
- switch (count % 4) {
- case 0: COMMON(""); return s;
- case 1: COMMON("\n\tstosb"); return s;
- case 2: COMMON("\n\tstosw"); return s;
- default: COMMON("\n\tstosw\n\tstosb"); return s;
- }
-}
-
-#undef COMMON
-}
-
-#define __constant_c_x_memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_c_and_count_memset((s),(c),(count)) : \
- __constant_c_memset((s),(c),(count)))
-
-#define __memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_count_memset((s),(c),(count)) : \
- __memset_generic((s),(c),(count)))
-
-#define __HAVE_ARCH_MEMSET
-#define memset(s, c, count) \
-(__builtin_constant_p(c) ? \
- __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
- __memset((s),(c),(count)))
-
-/*
- * find the first occurrence of byte 'c', or 1 past the area if none
- */
-#define __HAVE_ARCH_MEMSCAN
-static inline void * memscan(void * addr, int c, size_t size)
-{
- if (!size)
- return addr;
- __asm__("repnz; scasb\n\t"
- "jnz 1f\n\t"
- "dec %%edi\n"
- "1:"
- : "=D" (addr), "=c" (size)
- : "0" (addr), "1" (size), "a" (c));
- return addr;
-}
-
-#endif /* CONFIG_X86_USE_STRING_486 */
-#endif /* __KERNEL__ */
-
-#endif
+++ /dev/null
-#ifndef __ASM_SYSTEM_H
-#define __ASM_SYSTEM_H
-
-#include <linux/config.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <asm/segment.h>
-#include <asm/hypervisor.h>
-#include <linux/bitops.h> /* for LOCK_PREFIX */
-
-#ifdef __KERNEL__
-
-struct task_struct; /* one of the stranger aspects of C forward declarations.. */
-extern void FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
-
-#define prepare_to_switch() do { } while(0)
-#define switch_to(prev,next,last) do { \
- asm volatile("pushl %%esi\n\t" \
- "pushl %%edi\n\t" \
- "pushl %%ebp\n\t" \
- "movl %%esp,%0\n\t" /* save ESP */ \
- "movl %3,%%esp\n\t" /* restore ESP */ \
- "movl $1f,%1\n\t" /* save EIP */ \
- "pushl %4\n\t" /* restore EIP */ \
- "jmp __switch_to\n" \
- "1:\t" \
- "popl %%ebp\n\t" \
- "popl %%edi\n\t" \
- "popl %%esi\n\t" \
- :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \
- "=b" (last) \
- :"m" (next->thread.esp),"m" (next->thread.eip), \
- "a" (prev), "d" (next), \
- "b" (prev)); \
-} while (0)
-
-#define _set_base(addr,base) do { unsigned long __pr; \
-__asm__ __volatile__ ("movw %%dx,%1\n\t" \
- "rorl $16,%%edx\n\t" \
- "movb %%dl,%2\n\t" \
- "movb %%dh,%3" \
- :"=&d" (__pr) \
- :"m" (*((addr)+2)), \
- "m" (*((addr)+4)), \
- "m" (*((addr)+7)), \
- "0" (base) \
- ); } while(0)
-
-#define _set_limit(addr,limit) do { unsigned long __lr; \
-__asm__ __volatile__ ("movw %%dx,%1\n\t" \
- "rorl $16,%%edx\n\t" \
- "movb %2,%%dh\n\t" \
- "andb $0xf0,%%dh\n\t" \
- "orb %%dh,%%dl\n\t" \
- "movb %%dl,%2" \
- :"=&d" (__lr) \
- :"m" (*(addr)), \
- "m" (*((addr)+6)), \
- "0" (limit) \
- ); } while(0)
-
-#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
-#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 )
-
-static inline unsigned long _get_base(char * addr)
-{
- unsigned long __base;
- __asm__("movb %3,%%dh\n\t"
- "movb %2,%%dl\n\t"
- "shll $16,%%edx\n\t"
- "movw %1,%%dx"
- :"=&d" (__base)
- :"m" (*((addr)+2)),
- "m" (*((addr)+4)),
- "m" (*((addr)+7)));
- return __base;
-}
-
-#define get_base(ldt) _get_base( ((char *)&(ldt)) )
-
-/*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
- */
-#define loadsegment(seg,value) \
- asm volatile("\n" \
- "1:\t" \
- "movl %0,%%" #seg "\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3:\t" \
- "pushl $0\n\t" \
- "popl %%" #seg "\n\t" \
- "jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n\t" \
- ".align 4\n\t" \
- ".long 1b,3b\n" \
- ".previous" \
- : :"m" (*(unsigned int *)&(value)))
-
-#define clts() ((void)0)
-#define read_cr0() ({ \
- unsigned int __dummy; \
- __asm__( \
- "movl %%cr0,%0\n\t" \
- :"=r" (__dummy)); \
- __dummy; \
-})
-#define write_cr0(x) \
- __asm__("movl %0,%%cr0": :"r" (x));
-
-#define read_cr4() ({ \
- unsigned int __dummy; \
- __asm__( \
- "movl %%cr4,%0\n\t" \
- :"=r" (__dummy)); \
- __dummy; \
-})
-#define write_cr4(x) \
- __asm__("movl %0,%%cr4": :"r" (x));
-#define stts() (HYPERVISOR_fpu_taskswitch())
-
-#endif /* __KERNEL__ */
-
-#define wbinvd() \
- __asm__ __volatile__ ("wbinvd": : :"memory");
-
-static inline unsigned long get_limit(unsigned long segment)
-{
- unsigned long __limit;
- __asm__("lsll %1,%0"
- :"=r" (__limit):"r" (segment));
- return __limit+1;
-}
-
-#define nop() __asm__ __volatile__ ("nop")
-
-#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
-
-#define tas(ptr) (xchg((ptr),1))
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((struct __xchg_dummy *)(x))
-
-
-/*
- * The semantics of XCHGCMP8B are a bit strange, this is why
- * there is a loop and the loading of %%eax and %%edx has to
- * be inside. This inlines well in most cases, the cached
- * cost is around ~38 cycles. (in the future we might want
- * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
- * might have an implicit FPU-save as a cost, so it's not
- * clear which path to go.)
- */
-static inline void __set_64bit (unsigned long long * ptr,
- unsigned int low, unsigned int high)
-{
- __asm__ __volatile__ (
- "\n1:\t"
- "movl (%0), %%eax\n\t"
- "movl 4(%0), %%edx\n\t"
- "cmpxchg8b (%0)\n\t"
- "jnz 1b"
- : /* no outputs */
- : "D"(ptr),
- "b"(low),
- "c"(high)
- : "ax","dx","memory");
-}
-
-static inline void __set_64bit_constant (unsigned long long *ptr,
- unsigned long long value)
-{
- __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
-}
-#define ll_low(x) *(((unsigned int*)&(x))+0)
-#define ll_high(x) *(((unsigned int*)&(x))+1)
-
-static inline void __set_64bit_var (unsigned long long *ptr,
- unsigned long long value)
-{
- __set_64bit(ptr,ll_low(value), ll_high(value));
-}
-
-#define set_64bit(ptr,value) \
-(__builtin_constant_p(value) ? \
- __set_64bit_constant(ptr, value) : \
- __set_64bit_var(ptr, value) )
-
-#define _set_64bit(ptr,value) \
-(__builtin_constant_p(value) ? \
- __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
- __set_64bit(ptr, ll_low(value), ll_high(value)) )
-
-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- * but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
- switch (size) {
- case 1:
- __asm__ __volatile__("xchgb %b0,%1"
- :"=q" (x)
- :"m" (*__xg(ptr)), "0" (x)
- :"memory");
- break;
- case 2:
- __asm__ __volatile__("xchgw %w0,%1"
- :"=r" (x)
- :"m" (*__xg(ptr)), "0" (x)
- :"memory");
- break;
- case 4:
- __asm__ __volatile__("xchgl %0,%1"
- :"=r" (x)
- :"m" (*__xg(ptr)), "0" (x)
- :"memory");
- break;
- }
- return x;
-}
-
-/*
- * Atomic compare and exchange. Compare OLD with MEM, if identical,
- * store NEW in MEM. Return the initial value in MEM. Success is
- * indicated by comparing RETURN with OLD.
- */
-
-#ifdef CONFIG_X86_CMPXCHG
-#define __HAVE_ARCH_CMPXCHG 1
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
- unsigned long new, int size)
-{
- unsigned long prev;
- switch (size) {
- case 1:
- __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
- : "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
- : "memory");
- return prev;
- case 2:
- __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
- : "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
- : "memory");
- return prev;
- case 4:
- __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
- : "=a"(prev)
- : "q"(new), "m"(*__xg(ptr)), "0"(old)
- : "memory");
- return prev;
- }
- return old;
-}
-
-#define cmpxchg(ptr,o,n)\
- ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
- (unsigned long)(n),sizeof(*(ptr))))
-
-#else
-/* Compiling for a 386 proper. Is it worth implementing via cli/sti? */
-#endif
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- *
- * For now, "wmb()" doesn't actually do anything, as all
- * Intel CPU's follow what Intel calls a *Processor Order*,
- * in which all writes are seen in the program order even
- * outside the CPU.
- *
- * I expect future Intel CPU's to have a weaker ordering,
- * but I'd also expect them to finally get their act together
- * and add some real memory barriers if so.
- *
- * Some non intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-
-#define mb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
-#define rmb() mb()
-
-#ifdef CONFIG_X86_OOSTORE
-#define wmb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
-#else
-#define wmb() __asm__ __volatile__ ("": : :"memory")
-#endif
-
-#ifdef CONFIG_SMP
-#define smp_mb() mb()
-#define smp_rmb() rmb()
-#define smp_wmb() wmb()
-#else
-#define smp_mb() barrier()
-#define smp_rmb() barrier()
-#define smp_wmb() barrier()
-#endif
-
-#define set_mb(var, value) do { xchg(&var, value); } while (0)
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define __save_flags(x) ((x) = HYPERVISOR_shared_info->events_enable); barrier()
-#define __restore_flags(x) \
-do { \
- shared_info_t *_shared = HYPERVISOR_shared_info; \
- _shared->events_enable = (x); \
- barrier(); \
- if ( _shared->events && (x) ) do_hypervisor_callback(NULL); \
-} while (0)
-#define __cli() (HYPERVISOR_shared_info->events_enable = 0); barrier()
-#define __sti() \
-do { \
- shared_info_t *_shared = HYPERVISOR_shared_info; \
- _shared->events_enable = 1; \
- barrier(); \
- if ( _shared->events ) do_hypervisor_callback(NULL); \
-} while (0)
-#define safe_halt() ((void)0)
-
-/* For spinlocks etc */
-#define local_irq_save(x) ((x) = HYPERVISOR_shared_info->events_enable); (HYPERVISOR_shared_info->events_enable = 0); barrier()
-#define local_irq_restore(x) __restore_flags(x)
-#define local_irq_disable() __cli()
-#define local_irq_enable() __sti()
-
-#ifdef CONFIG_SMP
-
-extern void __global_cli(void);
-extern void __global_sti(void);
-extern unsigned long __global_save_flags(void);
-extern void __global_restore_flags(unsigned long);
-#define cli() __global_cli()
-#define sti() __global_sti()
-#define save_flags(x) ((x)=__global_save_flags())
-#define restore_flags(x) __global_restore_flags(x)
-
-#else
-
-#define cli() __cli()
-#define sti() __sti()
-#define save_flags(x) __save_flags(x)
-#define restore_flags(x) __restore_flags(x)
-
-#endif
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-void disable_hlt(void);
-void enable_hlt(void);
-
-extern unsigned long dmi_broken;
-extern int is_sony_vaio_laptop;
-
-#define BROKEN_ACPI_Sx 0x0001
-#define BROKEN_INIT_AFTER_S1 0x0002
-
-#endif
+++ /dev/null
-#ifndef __ARCH_I386_TERMBITS_H__
-#define __ARCH_I386_TERMBITS_H__
-
-#include <linux/posix_types.h>
-
-typedef unsigned char cc_t;
-typedef unsigned int speed_t;
-typedef unsigned int tcflag_t;
-
-#define NCCS 19
-struct termios {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK 0000001
-#define BRKINT 0000002
-#define IGNPAR 0000004
-#define PARMRK 0000010
-#define INPCK 0000020
-#define ISTRIP 0000040
-#define INLCR 0000100
-#define IGNCR 0000200
-#define ICRNL 0000400
-#define IUCLC 0001000
-#define IXON 0002000
-#define IXANY 0004000
-#define IXOFF 0010000
-#define IMAXBEL 0020000
-
-/* c_oflag bits */
-#define OPOST 0000001
-#define OLCUC 0000002
-#define ONLCR 0000004
-#define OCRNL 0000010
-#define ONOCR 0000020
-#define ONLRET 0000040
-#define OFILL 0000100
-#define OFDEL 0000200
-#define NLDLY 0000400
-#define NL0 0000000
-#define NL1 0000400
-#define CRDLY 0003000
-#define CR0 0000000
-#define CR1 0001000
-#define CR2 0002000
-#define CR3 0003000
-#define TABDLY 0014000
-#define TAB0 0000000
-#define TAB1 0004000
-#define TAB2 0010000
-#define TAB3 0014000
-#define XTABS 0014000
-#define BSDLY 0020000
-#define BS0 0000000
-#define BS1 0020000
-#define VTDLY 0040000
-#define VT0 0000000
-#define VT1 0040000
-#define FFDLY 0100000
-#define FF0 0000000
-#define FF1 0100000
-
-/* c_cflag bit meaning */
-#define CBAUD 0010017
-#define B0 0000000 /* hang up */
-#define B50 0000001
-#define B75 0000002
-#define B110 0000003
-#define B134 0000004
-#define B150 0000005
-#define B200 0000006
-#define B300 0000007
-#define B600 0000010
-#define B1200 0000011
-#define B1800 0000012
-#define B2400 0000013
-#define B4800 0000014
-#define B9600 0000015
-#define B19200 0000016
-#define B38400 0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE 0000060
-#define CS5 0000000
-#define CS6 0000020
-#define CS7 0000040
-#define CS8 0000060
-#define CSTOPB 0000100
-#define CREAD 0000200
-#define PARENB 0000400
-#define PARODD 0001000
-#define HUPCL 0002000
-#define CLOCAL 0004000
-#define CBAUDEX 0010000
-#define B57600 0010001
-#define B115200 0010002
-#define B230400 0010003
-#define B460800 0010004
-#define B500000 0010005
-#define B576000 0010006
-#define B921600 0010007
-#define B1000000 0010010
-#define B1152000 0010011
-#define B1500000 0010012
-#define B2000000 0010013
-#define B2500000 0010014
-#define B3000000 0010015
-#define B3500000 0010016
-#define B4000000 0010017
-#define CIBAUD 002003600000 /* input baud rate (not used) */
-#define CMSPAR 010000000000 /* mark or space (stick) parity */
-#define CRTSCTS 020000000000 /* flow control */
-
-/* c_lflag bits */
-#define ISIG 0000001
-#define ICANON 0000002
-#define XCASE 0000004
-#define ECHO 0000010
-#define ECHOE 0000020
-#define ECHOK 0000040
-#define ECHONL 0000100
-#define NOFLSH 0000200
-#define TOSTOP 0000400
-#define ECHOCTL 0001000
-#define ECHOPRT 0002000
-#define ECHOKE 0004000
-#define FLUSHO 0010000
-#define PENDIN 0040000
-#define IEXTEN 0100000
-
-/* tcflow() and TCXONC use these */
-#define TCOOFF 0
-#define TCOON 1
-#define TCIOFF 2
-#define TCION 3
-
-/* tcflush() and TCFLSH use these */
-#define TCIFLUSH 0
-#define TCOFLUSH 1
-#define TCIOFLUSH 2
-
-/* tcsetattr uses these */
-#define TCSANOW 0
-#define TCSADRAIN 1
-#define TCSAFLUSH 2
-
-#endif
+++ /dev/null
-#ifndef _I386_TERMIOS_H
-#define _I386_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
- unsigned short ws_row;
- unsigned short ws_col;
- unsigned short ws_xpixel;
- unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
- unsigned short c_iflag; /* input mode flags */
- unsigned short c_oflag; /* output mode flags */
- unsigned short c_cflag; /* control mode flags */
- unsigned short c_lflag; /* local mode flags */
- unsigned char c_line; /* line discipline */
- unsigned char c_cc[NCC]; /* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE 0x001
-#define TIOCM_DTR 0x002
-#define TIOCM_RTS 0x004
-#define TIOCM_ST 0x008
-#define TIOCM_SR 0x010
-#define TIOCM_CTS 0x020
-#define TIOCM_CAR 0x040
-#define TIOCM_RNG 0x080
-#define TIOCM_DSR 0x100
-#define TIOCM_CD TIOCM_CAR
-#define TIOCM_RI TIOCM_RNG
-#define TIOCM_OUT1 0x2000
-#define TIOCM_OUT2 0x4000
-#define TIOCM_LOOP 0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-/* line disciplines */
-#define N_TTY 0
-#define N_SLIP 1
-#define N_MOUSE 2
-#define N_PPP 3
-#define N_STRIP 4
-#define N_AX25 5
-#define N_X25 6 /* X.25 async */
-#define N_6PACK 7
-#define N_MASC 8 /* Reserved for Mobitex module <kaz@cafe.net> */
-#define N_R3964 9 /* Reserved for Simatic R3964 module */
-#define N_PROFIBUS_FDL 10 /* Reserved for Profibus <Dave@mvhi.com> */
-#define N_IRDA 11 /* Linux IR - http://irda.sourceforge.net/ */
-#define N_SMSBLOCK 12 /* SMS block mode - for talking to GSM data cards about SMS messages */
-#define N_HDLC 13 /* synchronous HDLC */
-#define N_SYNC_PPP 14 /* synchronous PPP */
-#define N_HCI 15 /* Bluetooth HCI UART */
-
-#ifdef __KERNEL__
-
-/* intr=^C quit=^\ erase=del kill=^U
- eof=^D vtime=\0 vmin=\1 sxtc=\0
- start=^Q stop=^S susp=^Z eol=\0
- reprint=^R discard=^U werase=^W lnext=^V
- eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
- unsigned short __tmp; \
- get_user(__tmp,&(termio)->x); \
- *(unsigned short *) &(termios)->x = __tmp; \
-}
-
-#define user_termio_to_kernel_termios(termios, termio) \
-({ \
- SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
- SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
- SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
- SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
- copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
-})
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-#define kernel_termios_to_user_termio(termio, termios) \
-({ \
- put_user((termios)->c_iflag, &(termio)->c_iflag); \
- put_user((termios)->c_oflag, &(termio)->c_oflag); \
- put_user((termios)->c_cflag, &(termio)->c_cflag); \
- put_user((termios)->c_lflag, &(termio)->c_lflag); \
- put_user((termios)->c_line, &(termio)->c_line); \
- copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
-})
-
-#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios))
-#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios))
-
-#endif /* __KERNEL__ */
-
-#endif /* _I386_TERMIOS_H */
+++ /dev/null
-/*
- * linux/include/asm-i386/timex.h
- *
- * i386 architecture timex specifications
- */
-#ifndef _ASMi386_TIMEX_H
-#define _ASMi386_TIMEX_H
-
-#include <linux/config.h>
-#include <asm/msr.h>
-
-#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */
-#define CLOCK_TICK_FACTOR 20 /* Factor of both 1000000 and CLOCK_TICK_RATE */
-#define FINETUNE ((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \
- (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \
- << (SHIFT_SCALE-SHIFT_HZ)) / HZ)
-
-/*
- * Standard way to access the cycle counter on i586+ CPUs.
- * Currently only used on SMP.
- *
- * If you really have a SMP machine with i486 chips or older,
- * compile for that, and this will just always return zero.
- * That's ok, it just means that the nicer scheduling heuristics
- * won't work for you.
- *
- * We only use the low 32 bits, and we'd simply better make sure
- * that we reschedule before that wraps. Scheduling at least every
- * four billion cycles just basically sounds like a good idea,
- * regardless of how fast the machine is.
- */
-typedef unsigned long long cycles_t;
-
-extern cycles_t cacheflush_time;
-
-static inline cycles_t get_cycles (void)
-{
-#ifndef CONFIG_X86_TSC
- return 0;
-#else
- unsigned long long ret;
-
- rdtscll(ret);
- return ret;
-#endif
-}
-
-extern unsigned long cpu_khz;
-
-#endif
+++ /dev/null
-#include <asm-generic/tlb.h>
+++ /dev/null
-#ifndef _I386_TYPES_H
-#define _I386_TYPES_H
-
-typedef unsigned short umode_t;
-
-/*
- * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
- * header files exported to user space
- */
-
-typedef __signed__ char __s8;
-typedef unsigned char __u8;
-
-typedef __signed__ short __s16;
-typedef unsigned short __u16;
-
-typedef __signed__ int __s32;
-typedef unsigned int __u32;
-
-#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
-typedef __signed__ long long __s64;
-typedef unsigned long long __u64;
-#endif
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-#ifdef __KERNEL__
-
-#include <linux/config.h>
-
-typedef signed char s8;
-typedef unsigned char u8;
-
-typedef signed short s16;
-typedef unsigned short u16;
-
-typedef signed int s32;
-typedef unsigned int u32;
-
-typedef signed long long s64;
-typedef unsigned long long u64;
-
-#define BITS_PER_LONG 32
-
-/* DMA addresses come in generic and 64-bit flavours. */
-
-#ifdef CONFIG_HIGHMEM
-typedef u64 dma_addr_t;
-#else
-typedef u32 dma_addr_t;
-#endif
-typedef u64 dma64_addr_t;
-
-#endif /* __KERNEL__ */
-
-#endif
+++ /dev/null
-#ifndef __i386_UACCESS_H
-#define __i386_UACCESS_H
-
-/*
- * User space memory access functions
- */
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <linux/prefetch.h>
-#include <asm/page.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not. If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) })
-
-
-#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF)
-#define USER_DS MAKE_MM_SEG(PAGE_OFFSET)
-
-#define get_ds() (KERNEL_DS)
-#define get_fs() (current->addr_limit)
-#define set_fs(x) (current->addr_limit = (x))
-
-#define segment_eq(a,b) ((a).seg == (b).seg)
-
-extern int __verify_write(const void *, unsigned long);
-
-#define __addr_ok(addr) ((unsigned long)(addr) < (current->addr_limit.seg))
-
-/*
- * Uhhuh, this needs 33-bit arithmetic. We have a carry..
- */
-#define __range_ok(addr,size) ({ \
- unsigned long flag,sum; \
- asm("addl %3,%1 ; sbbl %0,%0; cmpl %1,%4; sbbl $0,%0" \
- :"=&r" (flag), "=r" (sum) \
- :"1" (addr),"g" ((int)(size)),"g" (current->addr_limit.seg)); \
- flag; })
-
-#ifdef CONFIG_X86_WP_WORKS_OK
-
-#define access_ok(type,addr,size) (__range_ok(addr,size) == 0)
-
-#else
-
-#define access_ok(type,addr,size) ( (__range_ok(addr,size) == 0) && \
- ((type) == VERIFY_READ || boot_cpu_data.wp_works_ok || \
- segment_eq(get_fs(),KERNEL_DS) || \
- __verify_write((void *)(addr),(size))))
-
-#endif
-
-static inline int verify_area(int type, const void * addr, unsigned long size)
-{
- return access_ok(type,addr,size) ? 0 : -EFAULT;
-}
-
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise. */
-extern unsigned long search_exception_table(unsigned long);
-
-
-/*
- * These are the main single-value transfer routines. They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the uglyness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
-extern void __get_user_1(void);
-extern void __get_user_2(void);
-extern void __get_user_4(void);
-
-#define __get_user_x(size,ret,x,ptr) \
- __asm__ __volatile__("call __get_user_" #size \
- :"=a" (ret),"=d" (x) \
- :"0" (ptr))
-
-/* Careful: we have to cast the result to the type of the pointer for sign reasons */
-#define get_user(x,ptr) \
-({ int __ret_gu,__val_gu; \
- switch(sizeof (*(ptr))) { \
- case 1: __get_user_x(1,__ret_gu,__val_gu,ptr); break; \
- case 2: __get_user_x(2,__ret_gu,__val_gu,ptr); break; \
- case 4: __get_user_x(4,__ret_gu,__val_gu,ptr); break; \
- default: __get_user_x(X,__ret_gu,__val_gu,ptr); break; \
- } \
- (x) = (__typeof__(*(ptr)))__val_gu; \
- __ret_gu; \
-})
-
-extern void __put_user_1(void);
-extern void __put_user_2(void);
-extern void __put_user_4(void);
-extern void __put_user_8(void);
-
-extern void __put_user_bad(void);
-
-#define put_user(x,ptr) \
- __put_user_check((__typeof__(*(ptr)))(x),(ptr),sizeof(*(ptr)))
-
-#define __get_user(x,ptr) \
- __get_user_nocheck((x),(ptr),sizeof(*(ptr)))
-#define __put_user(x,ptr) \
- __put_user_nocheck((__typeof__(*(ptr)))(x),(ptr),sizeof(*(ptr)))
-
-#define __put_user_nocheck(x,ptr,size) \
-({ \
- long __pu_err; \
- __put_user_size((x),(ptr),(size),__pu_err); \
- __pu_err; \
-})
-
-
-#define __put_user_check(x,ptr,size) \
-({ \
- long __pu_err = -EFAULT; \
- __typeof__(*(ptr)) *__pu_addr = (ptr); \
- if (access_ok(VERIFY_WRITE,__pu_addr,size)) \
- __put_user_size((x),__pu_addr,(size),__pu_err); \
- __pu_err; \
-})
-
-#define __put_user_u64(x, addr, err) \
- __asm__ __volatile__( \
- "1: movl %%eax,0(%2)\n" \
- "2: movl %%edx,4(%2)\n" \
- "3:\n" \
- ".section .fixup,\"ax\"\n" \
- "4: movl %3,%0\n" \
- " jmp 3b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 1b,4b\n" \
- " .long 2b,4b\n" \
- ".previous" \
- : "=r"(err) \
- : "A" (x), "r" (addr), "i"(-EFAULT), "0"(err))
-
-#define __put_user_size(x,ptr,size,retval) \
-do { \
- retval = 0; \
- switch (size) { \
- case 1: __put_user_asm(x,ptr,retval,"b","b","iq"); break; \
- case 2: __put_user_asm(x,ptr,retval,"w","w","ir"); break; \
- case 4: __put_user_asm(x,ptr,retval,"l","","ir"); break; \
- case 8: __put_user_u64(x,ptr,retval); break; \
- default: __put_user_bad(); \
- } \
-} while (0)
-
-struct __large_struct { unsigned long buf[100]; };
-#define __m(x) (*(struct __large_struct *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-#define __put_user_asm(x, addr, err, itype, rtype, ltype) \
- __asm__ __volatile__( \
- "1: mov"itype" %"rtype"1,%2\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl %3,%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 1b,3b\n" \
- ".previous" \
- : "=r"(err) \
- : ltype (x), "m"(__m(addr)), "i"(-EFAULT), "0"(err))
-
-
-#define __get_user_nocheck(x,ptr,size) \
-({ \
- long __gu_err, __gu_val; \
- __get_user_size(__gu_val,(ptr),(size),__gu_err); \
- (x) = (__typeof__(*(ptr)))__gu_val; \
- __gu_err; \
-})
-
-extern long __get_user_bad(void);
-
-#define __get_user_size(x,ptr,size,retval) \
-do { \
- retval = 0; \
- switch (size) { \
- case 1: __get_user_asm(x,ptr,retval,"b","b","=q"); break; \
- case 2: __get_user_asm(x,ptr,retval,"w","w","=r"); break; \
- case 4: __get_user_asm(x,ptr,retval,"l","","=r"); break; \
- default: (x) = __get_user_bad(); \
- } \
-} while (0)
-
-#define __get_user_asm(x, addr, err, itype, rtype, ltype) \
- __asm__ __volatile__( \
- "1: mov"itype" %2,%"rtype"1\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl %3,%0\n" \
- " xor"itype" %"rtype"1,%"rtype"1\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 1b,3b\n" \
- ".previous" \
- : "=r"(err), ltype (x) \
- : "m"(__m(addr)), "i"(-EFAULT), "0"(err))
-
-
-/*
- * Copy To/From Userspace
- */
-
-/* Generic arbitrary sized copy. */
-#define __copy_user(to,from,size) \
-do { \
- int __d0, __d1; \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- " movl %3,%0\n" \
- "1: rep; movsb\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: lea 0(%3,%0,4),%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,2b\n" \
- ".previous" \
- : "=&c"(size), "=&D" (__d0), "=&S" (__d1) \
- : "r"(size & 3), "0"(size / 4), "1"(to), "2"(from) \
- : "memory"); \
-} while (0)
-
-#define __copy_user_zeroing(to,from,size) \
-do { \
- int __d0, __d1; \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- " movl %3,%0\n" \
- "1: rep; movsb\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: lea 0(%3,%0,4),%0\n" \
- "4: pushl %0\n" \
- " pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " rep; stosb\n" \
- " popl %%eax\n" \
- " popl %0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,4b\n" \
- ".previous" \
- : "=&c"(size), "=&D" (__d0), "=&S" (__d1) \
- : "r"(size & 3), "0"(size / 4), "1"(to), "2"(from) \
- : "memory"); \
-} while (0)
-
-/* We let the __ versions of copy_from/to_user inline, because they're often
- * used in fast paths and have only a small space overhead.
- */
-static inline unsigned long
-__generic_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
-{
- __copy_user_zeroing(to,from,n);
- return n;
-}
-
-static inline unsigned long
-__generic_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
-{
- __copy_user(to,from,n);
- return n;
-}
-
-
-/* Optimize just a little bit when we know the size of the move. */
-#define __constant_copy_user(to, from, size) \
-do { \
- int __d0, __d1; \
- switch (size & 3) { \
- default: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1:\n" \
- ".section .fixup,\"ax\"\n" \
- "2: shl $2,%0\n" \
- " jmp 1b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,2b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- case 1: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1: movsb\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: shl $2,%0\n" \
- "4: incl %0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,4b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- case 2: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1: movsw\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: shl $2,%0\n" \
- "4: addl $2,%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,4b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- case 3: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1: movsw\n" \
- "2: movsb\n" \
- "3:\n" \
- ".section .fixup,\"ax\"\n" \
- "4: shl $2,%0\n" \
- "5: addl $2,%0\n" \
- "6: incl %0\n" \
- " jmp 3b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,4b\n" \
- " .long 1b,5b\n" \
- " .long 2b,6b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- } \
-} while (0)
-
-/* Optimize just a little bit when we know the size of the move. */
-#define __constant_copy_user_zeroing(to, from, size) \
-do { \
- int __d0, __d1; \
- switch (size & 3) { \
- default: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1:\n" \
- ".section .fixup,\"ax\"\n" \
- "2: pushl %0\n" \
- " pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " rep; stosl\n" \
- " popl %%eax\n" \
- " popl %0\n" \
- " shl $2,%0\n" \
- " jmp 1b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,2b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- case 1: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1: movsb\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: pushl %0\n" \
- " pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " rep; stosl\n" \
- " stosb\n" \
- " popl %%eax\n" \
- " popl %0\n" \
- " shl $2,%0\n" \
- " incl %0\n" \
- " jmp 2b\n" \
- "4: pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " stosb\n" \
- " popl %%eax\n" \
- " incl %0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,4b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- case 2: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1: movsw\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: pushl %0\n" \
- " pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " rep; stosl\n" \
- " stosw\n" \
- " popl %%eax\n" \
- " popl %0\n" \
- " shl $2,%0\n" \
- " addl $2,%0\n" \
- " jmp 2b\n" \
- "4: pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " stosw\n" \
- " popl %%eax\n" \
- " addl $2,%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,4b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- case 3: \
- __asm__ __volatile__( \
- "0: rep; movsl\n" \
- "1: movsw\n" \
- "2: movsb\n" \
- "3:\n" \
- ".section .fixup,\"ax\"\n" \
- "4: pushl %0\n" \
- " pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " rep; stosl\n" \
- " stosw\n" \
- " stosb\n" \
- " popl %%eax\n" \
- " popl %0\n" \
- " shl $2,%0\n" \
- " addl $3,%0\n" \
- " jmp 2b\n" \
- "5: pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " stosw\n" \
- " stosb\n" \
- " popl %%eax\n" \
- " addl $3,%0\n" \
- " jmp 2b\n" \
- "6: pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " stosb\n" \
- " popl %%eax\n" \
- " incl %0\n" \
- " jmp 3b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .align 4\n" \
- " .long 0b,4b\n" \
- " .long 1b,5b\n" \
- " .long 2b,6b\n" \
- ".previous" \
- : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
- : "1"(from), "2"(to), "0"(size/4) \
- : "memory"); \
- break; \
- } \
-} while (0)
-
-unsigned long __generic_copy_to_user(void *, const void *, unsigned long);
-unsigned long __generic_copy_from_user(void *, const void *, unsigned long);
-
-static inline unsigned long
-__constant_copy_to_user(void *to, const void *from, unsigned long n)
-{
- prefetch(from);
- if (access_ok(VERIFY_WRITE, to, n))
- __constant_copy_user(to,from,n);
- return n;
-}
-
-static inline unsigned long
-__constant_copy_from_user(void *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- __constant_copy_user_zeroing(to,from,n);
- else
- memset(to, 0, n);
- return n;
-}
-
-static inline unsigned long
-__constant_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
-{
- __constant_copy_user(to,from,n);
- return n;
-}
-
-static inline unsigned long
-__constant_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
-{
- __constant_copy_user_zeroing(to,from,n);
- return n;
-}
-
-#define copy_to_user(to,from,n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_to_user((to),(from),(n)) : \
- __generic_copy_to_user((to),(from),(n)))
-
-#define copy_from_user(to,from,n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_from_user((to),(from),(n)) : \
- __generic_copy_from_user((to),(from),(n)))
-
-#define __copy_to_user(to,from,n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_to_user_nocheck((to),(from),(n)) : \
- __generic_copy_to_user_nocheck((to),(from),(n)))
-
-#define __copy_from_user(to,from,n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_from_user_nocheck((to),(from),(n)) : \
- __generic_copy_from_user_nocheck((to),(from),(n)))
-
-long strncpy_from_user(char *dst, const char *src, long count);
-long __strncpy_from_user(char *dst, const char *src, long count);
-#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
-long strnlen_user(const char *str, long n);
-unsigned long clear_user(void *mem, unsigned long len);
-unsigned long __clear_user(void *mem, unsigned long len);
-
-#endif /* __i386_UACCESS_H */
+++ /dev/null
-#ifndef _ASMi386_UCONTEXT_H
-#define _ASMi386_UCONTEXT_H
-
-struct ucontext {
- unsigned long uc_flags;
- struct ucontext *uc_link;
- stack_t uc_stack;
- struct sigcontext uc_mcontext;
- sigset_t uc_sigmask; /* mask last for extensibility */
-};
-
-#endif /* !_ASMi386_UCONTEXT_H */
+++ /dev/null
-#ifndef __I386_UNALIGNED_H
-#define __I386_UNALIGNED_H
-
-/*
- * The i386 can do unaligned accesses itself.
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
- */
-
-/**
- * get_unaligned - get value from possibly mis-aligned location
- * @ptr: pointer to value
- *
- * This macro should be used for accessing values larger in size than
- * single bytes at locations that are expected to be improperly aligned,
- * e.g. retrieving a u16 value from a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define get_unaligned(ptr) (*(ptr))
-
-/**
- * put_unaligned - put value to a possibly mis-aligned location
- * @val: value to place
- * @ptr: pointer to location
- *
- * This macro should be used for placing values larger in size than
- * single bytes at locations that are expected to be improperly aligned,
- * e.g. writing a u16 value to a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
-
-#endif
+++ /dev/null
-#ifndef _ASM_I386_UNISTD_H_
-#define _ASM_I386_UNISTD_H_
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_exit 1
-#define __NR_fork 2
-#define __NR_read 3
-#define __NR_write 4
-#define __NR_open 5
-#define __NR_close 6
-#define __NR_waitpid 7
-#define __NR_creat 8
-#define __NR_link 9
-#define __NR_unlink 10
-#define __NR_execve 11
-#define __NR_chdir 12
-#define __NR_time 13
-#define __NR_mknod 14
-#define __NR_chmod 15
-#define __NR_lchown 16
-#define __NR_break 17
-#define __NR_oldstat 18
-#define __NR_lseek 19
-#define __NR_getpid 20
-#define __NR_mount 21
-#define __NR_umount 22
-#define __NR_setuid 23
-#define __NR_getuid 24
-#define __NR_stime 25
-#define __NR_ptrace 26
-#define __NR_alarm 27
-#define __NR_oldfstat 28
-#define __NR_pause 29
-#define __NR_utime 30
-#define __NR_stty 31
-#define __NR_gtty 32
-#define __NR_access 33
-#define __NR_nice 34
-#define __NR_ftime 35
-#define __NR_sync 36
-#define __NR_kill 37
-#define __NR_rename 38
-#define __NR_mkdir 39
-#define __NR_rmdir 40
-#define __NR_dup 41
-#define __NR_pipe 42
-#define __NR_times 43
-#define __NR_prof 44
-#define __NR_brk 45
-#define __NR_setgid 46
-#define __NR_getgid 47
-#define __NR_signal 48
-#define __NR_geteuid 49
-#define __NR_getegid 50
-#define __NR_acct 51
-#define __NR_umount2 52
-#define __NR_lock 53
-#define __NR_ioctl 54
-#define __NR_fcntl 55
-#define __NR_mpx 56
-#define __NR_setpgid 57
-#define __NR_ulimit 58
-#define __NR_oldolduname 59
-#define __NR_umask 60
-#define __NR_chroot 61
-#define __NR_ustat 62
-#define __NR_dup2 63
-#define __NR_getppid 64
-#define __NR_getpgrp 65
-#define __NR_setsid 66
-#define __NR_sigaction 67
-#define __NR_sgetmask 68
-#define __NR_ssetmask 69
-#define __NR_setreuid 70
-#define __NR_setregid 71
-#define __NR_sigsuspend 72
-#define __NR_sigpending 73
-#define __NR_sethostname 74
-#define __NR_setrlimit 75
-#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */
-#define __NR_getrusage 77
-#define __NR_gettimeofday 78
-#define __NR_settimeofday 79
-#define __NR_getgroups 80
-#define __NR_setgroups 81
-#define __NR_select 82
-#define __NR_symlink 83
-#define __NR_oldlstat 84
-#define __NR_readlink 85
-#define __NR_uselib 86
-#define __NR_swapon 87
-#define __NR_reboot 88
-#define __NR_readdir 89
-#define __NR_mmap 90
-#define __NR_munmap 91
-#define __NR_truncate 92
-#define __NR_ftruncate 93
-#define __NR_fchmod 94
-#define __NR_fchown 95
-#define __NR_getpriority 96
-#define __NR_setpriority 97
-#define __NR_profil 98
-#define __NR_statfs 99
-#define __NR_fstatfs 100
-#define __NR_ioperm 101
-#define __NR_socketcall 102
-#define __NR_syslog 103
-#define __NR_setitimer 104
-#define __NR_getitimer 105
-#define __NR_stat 106
-#define __NR_lstat 107
-#define __NR_fstat 108
-#define __NR_olduname 109
-#define __NR_iopl 110
-#define __NR_vhangup 111
-#define __NR_idle 112
-#define __NR_vm86old 113
-#define __NR_wait4 114
-#define __NR_swapoff 115
-#define __NR_sysinfo 116
-#define __NR_ipc 117
-#define __NR_fsync 118
-#define __NR_sigreturn 119
-#define __NR_clone 120
-#define __NR_setdomainname 121
-#define __NR_uname 122
-#define __NR_modify_ldt 123
-#define __NR_adjtimex 124
-#define __NR_mprotect 125
-#define __NR_sigprocmask 126
-#define __NR_create_module 127
-#define __NR_init_module 128
-#define __NR_delete_module 129
-#define __NR_get_kernel_syms 130
-#define __NR_quotactl 131
-#define __NR_getpgid 132
-#define __NR_fchdir 133
-#define __NR_bdflush 134
-#define __NR_sysfs 135
-#define __NR_personality 136
-#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
-#define __NR_setfsuid 138
-#define __NR_setfsgid 139
-#define __NR__llseek 140
-#define __NR_getdents 141
-#define __NR__newselect 142
-#define __NR_flock 143
-#define __NR_msync 144
-#define __NR_readv 145
-#define __NR_writev 146
-#define __NR_getsid 147
-#define __NR_fdatasync 148
-#define __NR__sysctl 149
-#define __NR_mlock 150
-#define __NR_munlock 151
-#define __NR_mlockall 152
-#define __NR_munlockall 153
-#define __NR_sched_setparam 154
-#define __NR_sched_getparam 155
-#define __NR_sched_setscheduler 156
-#define __NR_sched_getscheduler 157
-#define __NR_sched_yield 158
-#define __NR_sched_get_priority_max 159
-#define __NR_sched_get_priority_min 160
-#define __NR_sched_rr_get_interval 161
-#define __NR_nanosleep 162
-#define __NR_mremap 163
-#define __NR_setresuid 164
-#define __NR_getresuid 165
-#define __NR_vm86 166
-#define __NR_query_module 167
-#define __NR_poll 168
-#define __NR_nfsservctl 169
-#define __NR_setresgid 170
-#define __NR_getresgid 171
-#define __NR_prctl 172
-#define __NR_rt_sigreturn 173
-#define __NR_rt_sigaction 174
-#define __NR_rt_sigprocmask 175
-#define __NR_rt_sigpending 176
-#define __NR_rt_sigtimedwait 177
-#define __NR_rt_sigqueueinfo 178
-#define __NR_rt_sigsuspend 179
-#define __NR_pread 180
-#define __NR_pwrite 181
-#define __NR_chown 182
-#define __NR_getcwd 183
-#define __NR_capget 184
-#define __NR_capset 185
-#define __NR_sigaltstack 186
-#define __NR_sendfile 187
-#define __NR_getpmsg 188 /* some people actually want streams */
-#define __NR_putpmsg 189 /* some people actually want streams */
-#define __NR_vfork 190
-#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
-#define __NR_mmap2 192
-#define __NR_truncate64 193
-#define __NR_ftruncate64 194
-#define __NR_stat64 195
-#define __NR_lstat64 196
-#define __NR_fstat64 197
-#define __NR_lchown32 198
-#define __NR_getuid32 199
-#define __NR_getgid32 200
-#define __NR_geteuid32 201
-#define __NR_getegid32 202
-#define __NR_setreuid32 203
-#define __NR_setregid32 204
-#define __NR_getgroups32 205
-#define __NR_setgroups32 206
-#define __NR_fchown32 207
-#define __NR_setresuid32 208
-#define __NR_getresuid32 209
-#define __NR_setresgid32 210
-#define __NR_getresgid32 211
-#define __NR_chown32 212
-#define __NR_setuid32 213
-#define __NR_setgid32 214
-#define __NR_setfsuid32 215
-#define __NR_setfsgid32 216
-#define __NR_pivot_root 217
-#define __NR_mincore 218
-#define __NR_madvise 219
-#define __NR_madvise1 219 /* delete when C lib stub is removed */
-#define __NR_getdents64 220
-#define __NR_fcntl64 221
-#define __NR_security 223 /* syscall for security modules */
-#define __NR_gettid 224
-#define __NR_readahead 225
-
-/* user-visible error numbers are in the range -1 - -124: see <asm-i386/errno.h> */
-
-#define __syscall_return(type, res) \
-do { \
- if ((unsigned long)(res) >= (unsigned long)(-125)) { \
- errno = -(res); \
- res = -1; \
- } \
- return (type) (res); \
-} while (0)
-
-/* XXX - _foo needs to be __foo, while __NR_bar could be _NR_bar. */
-#define _syscall0(type,name) \
-type name(void) \
-{ \
-long __res; \
-__asm__ volatile ("int $0x80" \
- : "=a" (__res) \
- : "0" (__NR_##name)); \
-__syscall_return(type,__res); \
-}
-
-#define _syscall1(type,name,type1,arg1) \
-type name(type1 arg1) \
-{ \
-long __res; \
-__asm__ volatile ("int $0x80" \
- : "=a" (__res) \
- : "0" (__NR_##name),"b" ((long)(arg1))); \
-__syscall_return(type,__res); \
-}
-
-#define _syscall2(type,name,type1,arg1,type2,arg2) \
-type name(type1 arg1,type2 arg2) \
-{ \
-long __res; \
-__asm__ volatile ("int $0x80" \
- : "=a" (__res) \
- : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2))); \
-__syscall_return(type,__res); \
-}
-
-#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \
-type name(type1 arg1,type2 arg2,type3 arg3) \
-{ \
-long __res; \
-__asm__ volatile ("int $0x80" \
- : "=a" (__res) \
- : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
- "d" ((long)(arg3))); \
-__syscall_return(type,__res); \
-}
-
-#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
-type name (type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
-{ \
-long __res; \
-__asm__ volatile ("int $0x80" \
- : "=a" (__res) \
- : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
- "d" ((long)(arg3)),"S" ((long)(arg4))); \
-__syscall_return(type,__res); \
-}
-
-#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
- type5,arg5) \
-type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5) \
-{ \
-long __res; \
-__asm__ volatile ("int $0x80" \
- : "=a" (__res) \
- : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
- "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5))); \
-__syscall_return(type,__res); \
-}
-
-#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
- type5,arg5,type6,arg6) \
-type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5,type6 arg6) \
-{ \
-long __res; \
-__asm__ volatile ("push %%ebp ; movl %%eax,%%ebp ; movl %1,%%eax ; int $0x80 ; pop %%ebp" \
- : "=a" (__res) \
- : "i" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
- "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)), \
- "0" ((long)(arg6))); \
-__syscall_return(type,__res); \
-}
-
-#ifdef __KERNEL_SYSCALLS__
-
-/*
- * we need this inline - forking from kernel space will result
- * in NO COPY ON WRITE (!!!), until an execve is executed. This
- * is no problem, but for the stack. This is handled by not letting
- * main() use the stack at all after fork(). Thus, no function
- * calls - which means inline code for fork too, as otherwise we
- * would use the stack upon exit from 'fork()'.
- *
- * Actually only pause and fork are needed inline, so that there
- * won't be any messing with the stack from main(), but we define
- * some others too.
- */
-#define __NR__exit __NR_exit
-static inline _syscall0(int,pause)
-static inline _syscall0(int,sync)
-static inline _syscall0(pid_t,setsid)
-static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count)
-static inline _syscall3(int,read,int,fd,char *,buf,off_t,count)
-static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count)
-static inline _syscall1(int,dup,int,fd)
-static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp)
-static inline _syscall3(int,open,const char *,file,int,flag,int,mode)
-static inline _syscall1(int,close,int,fd)
-static inline _syscall1(int,_exit,int,exitcode)
-static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options)
-static inline _syscall1(int,delete_module,const char *,name)
-
-static inline pid_t wait(int * wait_stat)
-{
- return waitpid(-1,wait_stat,0);
-}
-
-#endif
-
-#endif /* _ASM_I386_UNISTD_H_ */
+++ /dev/null
-#ifndef _I386_USER_H
-#define _I386_USER_H
-
-#include <asm/page.h>
-#include <linux/ptrace.h>
-/* Core file format: The core file is written in such a way that gdb
- can understand it and provide useful information to the user (under
- linux we use the 'trad-core' bfd). There are quite a number of
- obstacles to being able to view the contents of the floating point
- registers, and until these are solved you will not be able to view the
- contents of them. Actually, you can read in the core file and look at
- the contents of the user struct to find out what the floating point
- registers contain.
- The actual file contents are as follows:
- UPAGE: 1 page consisting of a user struct that tells gdb what is present
- in the file. Directly after this is a copy of the task_struct, which
- is currently not used by gdb, but it may come in useful at some point.
- All of the registers are stored as part of the upage. The upage should
- always be only one page.
- DATA: The data area is stored. We use current->end_text to
- current->brk to pick up all of the user variables, plus any memory
- that may have been malloced. No attempt is made to determine if a page
- is demand-zero or if a page is totally unused, we just cover the entire
- range. All of the addresses are rounded in such a way that an integral
- number of pages is written.
- STACK: We need the stack information in order to get a meaningful
- backtrace. We need to write the data from (esp) to
- current->start_stack, so we round each of these off in order to be able
- to write an integer number of pages.
- The minimum core file size is 3 pages, or 12288 bytes.
-*/
-
-/*
- * Pentium III FXSR, SSE support
- * Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
- * interacting with the FXSR-format floating point environment. Floating
- * point data can be accessed in the regular format in the usual manner,
- * and both the standard and SIMD floating point data can be accessed via
- * the new ptrace requests. In either case, changes to the FPU environment
- * will be reflected in the task's state as expected.
- */
-
-struct user_i387_struct {
- long cwd;
- long swd;
- long twd;
- long fip;
- long fcs;
- long foo;
- long fos;
- long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
-};
-
-struct user_fxsr_struct {
- unsigned short cwd;
- unsigned short swd;
- unsigned short twd;
- unsigned short fop;
- long fip;
- long fcs;
- long foo;
- long fos;
- long mxcsr;
- long reserved;
- long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
- long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
- long padding[56];
-};
-
-/*
- * This is the old layout of "struct pt_regs", and
- * is still the layout used by user mode (the new
- * pt_regs doesn't have all registers as the kernel
- * doesn't use the extra segment registers)
- */
-struct user_regs_struct {
- long ebx, ecx, edx, esi, edi, ebp, eax;
- unsigned short ds, __ds, es, __es;
- unsigned short fs, __fs, gs, __gs;
- long orig_eax, eip;
- unsigned short cs, __cs;
- long eflags, esp;
- unsigned short ss, __ss;
-};
-
-/* When the kernel dumps core, it starts by dumping the user struct -
- this will be used by gdb to figure out where the data and stack segments
- are within the file, and what virtual addresses to use. */
-struct user{
-/* We start with the registers, to mimic the way that "memory" is returned
- from the ptrace(3,...) function. */
- struct user_regs_struct regs; /* Where the registers are actually stored */
-/* ptrace does not yet supply these. Someday.... */
- int u_fpvalid; /* True if math co-processor being used. */
- /* for this mess. Not yet used. */
- struct user_i387_struct i387; /* Math Co-processor registers. */
-/* The rest of this junk is to help gdb figure out what goes where */
- unsigned long int u_tsize; /* Text segment size (pages). */
- unsigned long int u_dsize; /* Data segment size (pages). */
- unsigned long int u_ssize; /* Stack segment size (pages). */
- unsigned long start_code; /* Starting virtual address of text. */
- unsigned long start_stack; /* Starting virtual address of stack area.
- This is actually the bottom of the stack,
- the top of the stack is always found in the
- esp register. */
- long int signal; /* Signal that caused the core dump. */
- int reserved; /* No longer used */
- struct user_pt_regs * u_ar0; /* Used by gdb to help find the values for */
- /* the registers. */
- struct user_i387_struct* u_fpstate; /* Math Co-processor pointer. */
- unsigned long magic; /* To uniquely identify a core file */
- char u_comm[32]; /* User command that was responsible */
- int u_debugreg[8];
-};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
-#endif /* _I386_USER_H */
+++ /dev/null
-/*
- * Access to VGA videoram
- *
- * (c) 1998 Martin Mares <mj@ucw.cz>
- */
-
-#ifndef _LINUX_ASM_VGA_H_
-#define _LINUX_ASM_VGA_H_
-
-/*
- * On the PC, we can just recalculate addresses and then
- * access the videoram directly without any black magic.
- */
-
-#define VGA_MAP_MEM(x) (unsigned long)phys_to_virt(x)
-
-#define vga_readb(x) (*(x))
-#define vga_writeb(x,y) (*(y) = (x))
-
-#endif
+++ /dev/null
-/*
- * include/asm-i386/xor.h
- *
- * Optimized RAID-5 checksumming functions for MMX and SSE.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * You should have received a copy of the GNU General Public License
- * (for example /usr/src/linux/COPYING); if not, write to the Free
- * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/*
- * High-speed RAID5 checksumming functions utilizing MMX instructions.
- * Copyright (C) 1998 Ingo Molnar.
- */
-
-#define FPU_SAVE \
- do { \
- if (!(current->flags & PF_USEDFPU)) \
- __asm__ __volatile__ (" clts;\n"); \
- __asm__ __volatile__ ("fsave %0; fwait": "=m"(fpu_save[0])); \
- } while (0)
-
-#define FPU_RESTORE \
- do { \
- __asm__ __volatile__ ("frstor %0": : "m"(fpu_save[0])); \
- if (!(current->flags & PF_USEDFPU)) \
- stts(); \
- } while (0)
-
-#define LD(x,y) " movq 8*("#x")(%1), %%mm"#y" ;\n"
-#define ST(x,y) " movq %%mm"#y", 8*("#x")(%1) ;\n"
-#define XO1(x,y) " pxor 8*("#x")(%2), %%mm"#y" ;\n"
-#define XO2(x,y) " pxor 8*("#x")(%3), %%mm"#y" ;\n"
-#define XO3(x,y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
-#define XO4(x,y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
-
-
-static void
-xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
- unsigned long lines = bytes >> 7;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- XO1(i,0) \
- ST(i,0) \
- XO1(i+1,1) \
- ST(i+1,1) \
- XO1(i+2,2) \
- ST(i+2,2) \
- XO1(i+3,3) \
- ST(i+3,3)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $128, %1 ;\n"
- " addl $128, %2 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2)
- : "memory");
-
- FPU_RESTORE;
-}
-
-static void
-xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3)
-{
- unsigned long lines = bytes >> 7;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- XO2(i,0) \
- ST(i,0) \
- XO2(i+1,1) \
- ST(i+1,1) \
- XO2(i+2,2) \
- ST(i+2,2) \
- XO2(i+3,3) \
- ST(i+3,3)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $128, %1 ;\n"
- " addl $128, %2 ;\n"
- " addl $128, %3 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2), "r" (p3)
- : "memory");
-
- FPU_RESTORE;
-}
-
-static void
-xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4)
-{
- unsigned long lines = bytes >> 7;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- XO2(i,0) \
- XO2(i+1,1) \
- XO2(i+2,2) \
- XO2(i+3,3) \
- XO3(i,0) \
- ST(i,0) \
- XO3(i+1,1) \
- ST(i+1,1) \
- XO3(i+2,2) \
- ST(i+2,2) \
- XO3(i+3,3) \
- ST(i+3,3)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $128, %1 ;\n"
- " addl $128, %2 ;\n"
- " addl $128, %3 ;\n"
- " addl $128, %4 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2), "r" (p3), "r" (p4)
- : "memory");
-
- FPU_RESTORE;
-}
-
-static void
-xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
- unsigned long lines = bytes >> 7;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- XO2(i,0) \
- XO2(i+1,1) \
- XO2(i+2,2) \
- XO2(i+3,3) \
- XO3(i,0) \
- XO3(i+1,1) \
- XO3(i+2,2) \
- XO3(i+3,3) \
- XO4(i,0) \
- ST(i,0) \
- XO4(i+1,1) \
- ST(i+1,1) \
- XO4(i+2,2) \
- ST(i+2,2) \
- XO4(i+3,3) \
- ST(i+3,3)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $128, %1 ;\n"
- " addl $128, %2 ;\n"
- " addl $128, %3 ;\n"
- " addl $128, %4 ;\n"
- " addl $128, %5 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "g" (lines),
- "r" (p1), "r" (p2), "r" (p3), "r" (p4), "r" (p5)
- : "memory");
-
- FPU_RESTORE;
-}
-
-#undef LD
-#undef XO1
-#undef XO2
-#undef XO3
-#undef XO4
-#undef ST
-#undef BLOCK
-
-static void
-xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
- unsigned long lines = bytes >> 6;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
- " .align 32 ;\n"
- " 1: ;\n"
- " movq (%1), %%mm0 ;\n"
- " movq 8(%1), %%mm1 ;\n"
- " pxor (%2), %%mm0 ;\n"
- " movq 16(%1), %%mm2 ;\n"
- " movq %%mm0, (%1) ;\n"
- " pxor 8(%2), %%mm1 ;\n"
- " movq 24(%1), %%mm3 ;\n"
- " movq %%mm1, 8(%1) ;\n"
- " pxor 16(%2), %%mm2 ;\n"
- " movq 32(%1), %%mm4 ;\n"
- " movq %%mm2, 16(%1) ;\n"
- " pxor 24(%2), %%mm3 ;\n"
- " movq 40(%1), %%mm5 ;\n"
- " movq %%mm3, 24(%1) ;\n"
- " pxor 32(%2), %%mm4 ;\n"
- " movq 48(%1), %%mm6 ;\n"
- " movq %%mm4, 32(%1) ;\n"
- " pxor 40(%2), %%mm5 ;\n"
- " movq 56(%1), %%mm7 ;\n"
- " movq %%mm5, 40(%1) ;\n"
- " pxor 48(%2), %%mm6 ;\n"
- " pxor 56(%2), %%mm7 ;\n"
- " movq %%mm6, 48(%1) ;\n"
- " movq %%mm7, 56(%1) ;\n"
-
- " addl $64, %1 ;\n"
- " addl $64, %2 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2)
- : "memory");
-
- FPU_RESTORE;
-}
-
-static void
-xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3)
-{
- unsigned long lines = bytes >> 6;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
- " .align 32,0x90 ;\n"
- " 1: ;\n"
- " movq (%1), %%mm0 ;\n"
- " movq 8(%1), %%mm1 ;\n"
- " pxor (%2), %%mm0 ;\n"
- " movq 16(%1), %%mm2 ;\n"
- " pxor 8(%2), %%mm1 ;\n"
- " pxor (%3), %%mm0 ;\n"
- " pxor 16(%2), %%mm2 ;\n"
- " movq %%mm0, (%1) ;\n"
- " pxor 8(%3), %%mm1 ;\n"
- " pxor 16(%3), %%mm2 ;\n"
- " movq 24(%1), %%mm3 ;\n"
- " movq %%mm1, 8(%1) ;\n"
- " movq 32(%1), %%mm4 ;\n"
- " movq 40(%1), %%mm5 ;\n"
- " pxor 24(%2), %%mm3 ;\n"
- " movq %%mm2, 16(%1) ;\n"
- " pxor 32(%2), %%mm4 ;\n"
- " pxor 24(%3), %%mm3 ;\n"
- " pxor 40(%2), %%mm5 ;\n"
- " movq %%mm3, 24(%1) ;\n"
- " pxor 32(%3), %%mm4 ;\n"
- " pxor 40(%3), %%mm5 ;\n"
- " movq 48(%1), %%mm6 ;\n"
- " movq %%mm4, 32(%1) ;\n"
- " movq 56(%1), %%mm7 ;\n"
- " pxor 48(%2), %%mm6 ;\n"
- " movq %%mm5, 40(%1) ;\n"
- " pxor 56(%2), %%mm7 ;\n"
- " pxor 48(%3), %%mm6 ;\n"
- " pxor 56(%3), %%mm7 ;\n"
- " movq %%mm6, 48(%1) ;\n"
- " movq %%mm7, 56(%1) ;\n"
-
- " addl $64, %1 ;\n"
- " addl $64, %2 ;\n"
- " addl $64, %3 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2), "r" (p3)
- : "memory" );
-
- FPU_RESTORE;
-}
-
-static void
-xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4)
-{
- unsigned long lines = bytes >> 6;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
- " .align 32,0x90 ;\n"
- " 1: ;\n"
- " movq (%1), %%mm0 ;\n"
- " movq 8(%1), %%mm1 ;\n"
- " pxor (%2), %%mm0 ;\n"
- " movq 16(%1), %%mm2 ;\n"
- " pxor 8(%2), %%mm1 ;\n"
- " pxor (%3), %%mm0 ;\n"
- " pxor 16(%2), %%mm2 ;\n"
- " pxor 8(%3), %%mm1 ;\n"
- " pxor (%4), %%mm0 ;\n"
- " movq 24(%1), %%mm3 ;\n"
- " pxor 16(%3), %%mm2 ;\n"
- " pxor 8(%4), %%mm1 ;\n"
- " movq %%mm0, (%1) ;\n"
- " movq 32(%1), %%mm4 ;\n"
- " pxor 24(%2), %%mm3 ;\n"
- " pxor 16(%4), %%mm2 ;\n"
- " movq %%mm1, 8(%1) ;\n"
- " movq 40(%1), %%mm5 ;\n"
- " pxor 32(%2), %%mm4 ;\n"
- " pxor 24(%3), %%mm3 ;\n"
- " movq %%mm2, 16(%1) ;\n"
- " pxor 40(%2), %%mm5 ;\n"
- " pxor 32(%3), %%mm4 ;\n"
- " pxor 24(%4), %%mm3 ;\n"
- " movq %%mm3, 24(%1) ;\n"
- " movq 56(%1), %%mm7 ;\n"
- " movq 48(%1), %%mm6 ;\n"
- " pxor 40(%3), %%mm5 ;\n"
- " pxor 32(%4), %%mm4 ;\n"
- " pxor 48(%2), %%mm6 ;\n"
- " movq %%mm4, 32(%1) ;\n"
- " pxor 56(%2), %%mm7 ;\n"
- " pxor 40(%4), %%mm5 ;\n"
- " pxor 48(%3), %%mm6 ;\n"
- " pxor 56(%3), %%mm7 ;\n"
- " movq %%mm5, 40(%1) ;\n"
- " pxor 48(%4), %%mm6 ;\n"
- " pxor 56(%4), %%mm7 ;\n"
- " movq %%mm6, 48(%1) ;\n"
- " movq %%mm7, 56(%1) ;\n"
-
- " addl $64, %1 ;\n"
- " addl $64, %2 ;\n"
- " addl $64, %3 ;\n"
- " addl $64, %4 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2), "r" (p3), "r" (p4)
- : "memory");
-
- FPU_RESTORE;
-}
-
-static void
-xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
- unsigned long lines = bytes >> 6;
- char fpu_save[108];
-
- FPU_SAVE;
-
- __asm__ __volatile__ (
- " .align 32,0x90 ;\n"
- " 1: ;\n"
- " movq (%1), %%mm0 ;\n"
- " movq 8(%1), %%mm1 ;\n"
- " pxor (%2), %%mm0 ;\n"
- " pxor 8(%2), %%mm1 ;\n"
- " movq 16(%1), %%mm2 ;\n"
- " pxor (%3), %%mm0 ;\n"
- " pxor 8(%3), %%mm1 ;\n"
- " pxor 16(%2), %%mm2 ;\n"
- " pxor (%4), %%mm0 ;\n"
- " pxor 8(%4), %%mm1 ;\n"
- " pxor 16(%3), %%mm2 ;\n"
- " movq 24(%1), %%mm3 ;\n"
- " pxor (%5), %%mm0 ;\n"
- " pxor 8(%5), %%mm1 ;\n"
- " movq %%mm0, (%1) ;\n"
- " pxor 16(%4), %%mm2 ;\n"
- " pxor 24(%2), %%mm3 ;\n"
- " movq %%mm1, 8(%1) ;\n"
- " pxor 16(%5), %%mm2 ;\n"
- " pxor 24(%3), %%mm3 ;\n"
- " movq 32(%1), %%mm4 ;\n"
- " movq %%mm2, 16(%1) ;\n"
- " pxor 24(%4), %%mm3 ;\n"
- " pxor 32(%2), %%mm4 ;\n"
- " movq 40(%1), %%mm5 ;\n"
- " pxor 24(%5), %%mm3 ;\n"
- " pxor 32(%3), %%mm4 ;\n"
- " pxor 40(%2), %%mm5 ;\n"
- " movq %%mm3, 24(%1) ;\n"
- " pxor 32(%4), %%mm4 ;\n"
- " pxor 40(%3), %%mm5 ;\n"
- " movq 48(%1), %%mm6 ;\n"
- " movq 56(%1), %%mm7 ;\n"
- " pxor 32(%5), %%mm4 ;\n"
- " pxor 40(%4), %%mm5 ;\n"
- " pxor 48(%2), %%mm6 ;\n"
- " pxor 56(%2), %%mm7 ;\n"
- " movq %%mm4, 32(%1) ;\n"
- " pxor 48(%3), %%mm6 ;\n"
- " pxor 56(%3), %%mm7 ;\n"
- " pxor 40(%5), %%mm5 ;\n"
- " pxor 48(%4), %%mm6 ;\n"
- " pxor 56(%4), %%mm7 ;\n"
- " movq %%mm5, 40(%1) ;\n"
- " pxor 48(%5), %%mm6 ;\n"
- " pxor 56(%5), %%mm7 ;\n"
- " movq %%mm6, 48(%1) ;\n"
- " movq %%mm7, 56(%1) ;\n"
-
- " addl $64, %1 ;\n"
- " addl $64, %2 ;\n"
- " addl $64, %3 ;\n"
- " addl $64, %4 ;\n"
- " addl $64, %5 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "g" (lines),
- "r" (p1), "r" (p2), "r" (p3), "r" (p4), "r" (p5)
- : "memory");
-
- FPU_RESTORE;
-}
-
-static struct xor_block_template xor_block_pII_mmx = {
- name: "pII_mmx",
- do_2: xor_pII_mmx_2,
- do_3: xor_pII_mmx_3,
- do_4: xor_pII_mmx_4,
- do_5: xor_pII_mmx_5,
-};
-
-static struct xor_block_template xor_block_p5_mmx = {
- name: "p5_mmx",
- do_2: xor_p5_mmx_2,
- do_3: xor_p5_mmx_3,
- do_4: xor_p5_mmx_4,
- do_5: xor_p5_mmx_5,
-};
-
-#undef FPU_SAVE
-#undef FPU_RESTORE
-
-/*
- * Cache avoiding checksumming functions utilizing KNI instructions
- * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
- */
-
-#define XMMS_SAVE \
- __asm__ __volatile__ ( \
- "movl %%cr0,%0 ;\n\t" \
- "clts ;\n\t" \
- "movups %%xmm0,(%1) ;\n\t" \
- "movups %%xmm1,0x10(%1) ;\n\t" \
- "movups %%xmm2,0x20(%1) ;\n\t" \
- "movups %%xmm3,0x30(%1) ;\n\t" \
- : "=r" (cr0) \
- : "r" (xmm_save) \
- : "memory")
-
-#define XMMS_RESTORE \
- __asm__ __volatile__ ( \
- "sfence ;\n\t" \
- "movups (%1),%%xmm0 ;\n\t" \
- "movups 0x10(%1),%%xmm1 ;\n\t" \
- "movups 0x20(%1),%%xmm2 ;\n\t" \
- "movups 0x30(%1),%%xmm3 ;\n\t" \
- "movl %0,%%cr0 ;\n\t" \
- : \
- : "r" (cr0), "r" (xmm_save) \
- : "memory")
-
-#define OFFS(x) "16*("#x")"
-#define PF_OFFS(x) "256+16*("#x")"
-#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n"
-#define LD(x,y) " movaps "OFFS(x)"(%1), %%xmm"#y" ;\n"
-#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%1) ;\n"
-#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n"
-#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n"
-#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n"
-#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n"
-#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n"
-#define XO1(x,y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n"
-#define XO2(x,y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n"
-#define XO3(x,y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n"
-#define XO4(x,y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n"
-#define XO5(x,y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n"
-
-
-static void
-xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
- unsigned long lines = bytes >> 8;
- char xmm_save[16*4];
- int cr0;
-
- XMMS_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- LD(i,0) \
- LD(i+1,1) \
- PF1(i) \
- PF1(i+2) \
- LD(i+2,2) \
- LD(i+3,3) \
- PF0(i+4) \
- PF0(i+6) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- ST(i,0) \
- ST(i+1,1) \
- ST(i+2,2) \
- ST(i+3,3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2)
- : "memory");
-
- XMMS_RESTORE;
-}
-
-static void
-xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3)
-{
- unsigned long lines = bytes >> 8;
- char xmm_save[16*4];
- int cr0;
-
- XMMS_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- PF1(i) \
- PF1(i+2) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- PF2(i) \
- PF2(i+2) \
- PF0(i+4) \
- PF0(i+6) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- XO2(i,0) \
- XO2(i+1,1) \
- XO2(i+2,2) \
- XO2(i+3,3) \
- ST(i,0) \
- ST(i+1,1) \
- ST(i+2,2) \
- ST(i+3,3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " addl $256, %3 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r"(p2), "r"(p3)
- : "memory" );
-
- XMMS_RESTORE;
-}
-
-static void
-xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4)
-{
- unsigned long lines = bytes >> 8;
- char xmm_save[16*4];
- int cr0;
-
- XMMS_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- PF1(i) \
- PF1(i+2) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- PF2(i) \
- PF2(i+2) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- PF3(i) \
- PF3(i+2) \
- PF0(i+4) \
- PF0(i+6) \
- XO2(i,0) \
- XO2(i+1,1) \
- XO2(i+2,2) \
- XO2(i+3,3) \
- XO3(i,0) \
- XO3(i+1,1) \
- XO3(i+2,2) \
- XO3(i+3,3) \
- ST(i,0) \
- ST(i+1,1) \
- ST(i+2,2) \
- ST(i+3,3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " addl $256, %3 ;\n"
- " addl $256, %4 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2), "r" (p3), "r" (p4)
- : "memory" );
-
- XMMS_RESTORE;
-}
-
-static void
-xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
- unsigned long lines = bytes >> 8;
- char xmm_save[16*4];
- int cr0;
-
- XMMS_SAVE;
-
- __asm__ __volatile__ (
-#undef BLOCK
-#define BLOCK(i) \
- PF1(i) \
- PF1(i+2) \
- LD(i,0) \
- LD(i+1,1) \
- LD(i+2,2) \
- LD(i+3,3) \
- PF2(i) \
- PF2(i+2) \
- XO1(i,0) \
- XO1(i+1,1) \
- XO1(i+2,2) \
- XO1(i+3,3) \
- PF3(i) \
- PF3(i+2) \
- XO2(i,0) \
- XO2(i+1,1) \
- XO2(i+2,2) \
- XO2(i+3,3) \
- PF4(i) \
- PF4(i+2) \
- PF0(i+4) \
- PF0(i+6) \
- XO3(i,0) \
- XO3(i+1,1) \
- XO3(i+2,2) \
- XO3(i+3,3) \
- XO4(i,0) \
- XO4(i+1,1) \
- XO4(i+2,2) \
- XO4(i+3,3) \
- ST(i,0) \
- ST(i+1,1) \
- ST(i+2,2) \
- ST(i+3,3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " addl $256, %3 ;\n"
- " addl $256, %4 ;\n"
- " addl $256, %5 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- :
- : "r" (lines),
- "r" (p1), "r" (p2), "r" (p3), "r" (p4), "r" (p5)
- : "memory");
-
- XMMS_RESTORE;
-}
-
-static struct xor_block_template xor_block_pIII_sse = {
- name: "pIII_sse",
- do_2: xor_sse_2,
- do_3: xor_sse_3,
- do_4: xor_sse_4,
- do_5: xor_sse_5,
-};
-
-/* Also try the generic routines. */
-#include <asm-generic/xor.h>
-
-#undef XOR_TRY_TEMPLATES
-#define XOR_TRY_TEMPLATES \
- do { \
- xor_speed(&xor_block_8regs); \
- xor_speed(&xor_block_32regs); \
- if (cpu_has_xmm) \
- xor_speed(&xor_block_pIII_sse); \
- if (md_cpu_has_mmx()) { \
- xor_speed(&xor_block_pII_mmx); \
- xor_speed(&xor_block_p5_mmx); \
- } \
- } while (0)
-
-/* We force the use of the SSE xor block because it can write around L2.
- We may also be able to load into the L1 only depending on how the cpu
- deals with a load to a line that is being prefetched. */
-#define XOR_SELECT_TEMPLATE(FASTEST) \
- (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
+++ /dev/null
-#ifndef _BLK_H
-#define _BLK_H
-
-#include <linux/blkdev.h>
-#include <linux/locks.h>
-#include <linux/config.h>
-#include <linux/spinlock.h>
-
-/*
- * Spinlock for protecting the request queue which
- * is mucked around with in interrupts on potentially
- * multiple CPU's..
- */
-extern spinlock_t io_request_lock;
-
-/*
- * Initialization functions.
- */
-extern int isp16_init(void);
-extern int cdu31a_init(void);
-extern int acsi_init(void);
-extern int mcd_init(void);
-extern int mcdx_init(void);
-extern int sbpcd_init(void);
-extern int aztcd_init(void);
-extern int sony535_init(void);
-extern int gscd_init(void);
-extern int cm206_init(void);
-extern int optcd_init(void);
-extern int sjcd_init(void);
-extern int cdi_init(void);
-extern int hd_init(void);
-extern int ide_init(void);
-extern int xd_init(void);
-extern int mfm_init(void);
-extern int loop_init(void);
-extern int md_init(void);
-extern int ap_init(void);
-extern int ddv_init(void);
-extern int z2_init(void);
-extern int swim3_init(void);
-extern int swimiop_init(void);
-extern int amiga_floppy_init(void);
-extern int atari_floppy_init(void);
-extern int ez_init(void);
-extern int bpcd_init(void);
-extern int ps2esdi_init(void);
-extern int jsfd_init(void);
-extern int viodasd_init(void);
-extern int viocd_init(void);
-extern int xlblk_init(void);
-
-#if defined(CONFIG_ARCH_S390)
-extern int dasd_init(void);
-extern int xpram_init(void);
-extern int tapeblock_init(void);
-#endif /* CONFIG_ARCH_S390 */
-
-extern void set_device_ro(kdev_t dev,int flag);
-void add_blkdev_randomness(int major);
-
-extern int floppy_init(void);
-extern void rd_load(void);
-extern int rd_init(void);
-extern int rd_doload; /* 1 = load ramdisk, 0 = don't load */
-extern int rd_prompt; /* 1 = prompt for ramdisk, 0 = don't prompt */
-extern int rd_image_start; /* starting block # of image */
-
-#ifdef CONFIG_BLK_DEV_INITRD
-
-#define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */
-
-extern unsigned long initrd_start,initrd_end;
-extern int mount_initrd; /* zero if initrd should not be mounted */
-extern int initrd_below_start_ok; /* 1 if it is not an error if initrd_start < memory_start */
-void initrd_init(void);
-
-#endif
-
-
-/*
- * end_request() and friends. Must be called with the request queue spinlock
- * acquired. All functions called within end_request() _must_be_ atomic.
- *
- * Several drivers define their own end_request and call
- * end_that_request_first() and end_that_request_last()
- * for parts of the original function. This prevents
- * code duplication in drivers.
- */
-
-static inline void blkdev_dequeue_request(struct request * req)
-{
- list_del(&req->queue);
-}
-
-int end_that_request_first(struct request *req, int uptodate, char *name);
-void end_that_request_last(struct request *req);
-
-#if defined(MAJOR_NR) || defined(IDE_DRIVER)
-
-#undef DEVICE_ON
-#undef DEVICE_OFF
-
-/*
- * Add entries as needed.
- */
-
-#ifdef IDE_DRIVER
-
-#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
-#define DEVICE_NAME "ide"
-
-#elif (MAJOR_NR == RAMDISK_MAJOR)
-
-/* ram disk */
-#define DEVICE_NAME "ramdisk"
-#define DEVICE_NR(device) (MINOR(device))
-#define DEVICE_NO_RANDOM
-
-#elif (MAJOR_NR == Z2RAM_MAJOR)
-
-/* Zorro II Ram */
-#define DEVICE_NAME "Z2RAM"
-#define DEVICE_REQUEST do_z2_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == FLOPPY_MAJOR)
-
-static void floppy_off(unsigned int nr);
-
-#define DEVICE_NAME "floppy"
-#define DEVICE_INTR do_floppy
-#define DEVICE_REQUEST do_fd_request
-#define DEVICE_NR(device) ( (MINOR(device) & 3) | ((MINOR(device) & 0x80 ) >> 5 ))
-#define DEVICE_OFF(device) floppy_off(DEVICE_NR(device))
-
-#elif (MAJOR_NR == HD_MAJOR)
-
-/* Hard disk: timeout is 6 seconds. */
-#define DEVICE_NAME "hard disk"
-#define DEVICE_INTR do_hd
-#define TIMEOUT_VALUE (6*HZ)
-#define DEVICE_REQUEST do_hd_request
-#define DEVICE_NR(device) (MINOR(device)>>6)
-
-#elif (SCSI_DISK_MAJOR(MAJOR_NR))
-
-#define DEVICE_NAME "scsidisk"
-#define TIMEOUT_VALUE (2*HZ)
-#define DEVICE_NR(device) (((MAJOR(device) & SD_MAJOR_MASK) << (8 - 4)) + (MINOR(device) >> 4))
-
-/* Kludge to use the same number for both char and block major numbers */
-#elif (MAJOR_NR == MD_MAJOR) && defined(MD_DRIVER)
-
-#define DEVICE_NAME "Multiple devices driver"
-#define DEVICE_REQUEST do_md_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == SCSI_TAPE_MAJOR)
-
-#define DEVICE_NAME "scsitape"
-#define DEVICE_INTR do_st
-#define DEVICE_NR(device) (MINOR(device) & 0x7f)
-
-#elif (MAJOR_NR == OSST_MAJOR)
-
-#define DEVICE_NAME "onstream"
-#define DEVICE_INTR do_osst
-#define DEVICE_NR(device) (MINOR(device) & 0x7f)
-#define DEVICE_ON(device)
-#define DEVICE_OFF(device)
-
-#elif (MAJOR_NR == SCSI_CDROM_MAJOR)
-
-#define DEVICE_NAME "CD-ROM"
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == XT_DISK_MAJOR)
-
-#define DEVICE_NAME "xt disk"
-#define DEVICE_REQUEST do_xd_request
-#define DEVICE_NR(device) (MINOR(device) >> 6)
-
-#elif (MAJOR_NR == PS2ESDI_MAJOR)
-
-#define DEVICE_NAME "PS/2 ESDI"
-#define DEVICE_REQUEST do_ps2esdi_request
-#define DEVICE_NR(device) (MINOR(device) >> 6)
-
-#elif (MAJOR_NR == CDU31A_CDROM_MAJOR)
-
-#define DEVICE_NAME "CDU31A"
-#define DEVICE_REQUEST do_cdu31a_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == ACSI_MAJOR) && (defined(CONFIG_ATARI_ACSI) || defined(CONFIG_ATARI_ACSI_MODULE))
-
-#define DEVICE_NAME "ACSI"
-#define DEVICE_INTR do_acsi
-#define DEVICE_REQUEST do_acsi_request
-#define DEVICE_NR(device) (MINOR(device) >> 4)
-
-#elif (MAJOR_NR == MITSUMI_CDROM_MAJOR)
-
-#define DEVICE_NAME "Mitsumi CD-ROM"
-/* #define DEVICE_INTR do_mcd */
-#define DEVICE_REQUEST do_mcd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == MITSUMI_X_CDROM_MAJOR)
-
-#define DEVICE_NAME "Mitsumi CD-ROM"
-/* #define DEVICE_INTR do_mcdx */
-#define DEVICE_REQUEST do_mcdx_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == MATSUSHITA_CDROM_MAJOR)
-
-#define DEVICE_NAME "Matsushita CD-ROM controller #1"
-#define DEVICE_REQUEST do_sbpcd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == MATSUSHITA_CDROM2_MAJOR)
-
-#define DEVICE_NAME "Matsushita CD-ROM controller #2"
-#define DEVICE_REQUEST do_sbpcd2_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == MATSUSHITA_CDROM3_MAJOR)
-
-#define DEVICE_NAME "Matsushita CD-ROM controller #3"
-#define DEVICE_REQUEST do_sbpcd3_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == MATSUSHITA_CDROM4_MAJOR)
-
-#define DEVICE_NAME "Matsushita CD-ROM controller #4"
-#define DEVICE_REQUEST do_sbpcd4_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == AZTECH_CDROM_MAJOR)
-
-#define DEVICE_NAME "Aztech CD-ROM"
-#define DEVICE_REQUEST do_aztcd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == CDU535_CDROM_MAJOR)
-
-#define DEVICE_NAME "SONY-CDU535"
-#define DEVICE_INTR do_cdu535
-#define DEVICE_REQUEST do_cdu535_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == GOLDSTAR_CDROM_MAJOR)
-
-#define DEVICE_NAME "Goldstar R420"
-#define DEVICE_REQUEST do_gscd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == CM206_CDROM_MAJOR)
-#define DEVICE_NAME "Philips/LMS CD-ROM cm206"
-#define DEVICE_REQUEST do_cm206_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == OPTICS_CDROM_MAJOR)
-
-#define DEVICE_NAME "DOLPHIN 8000AT CD-ROM"
-#define DEVICE_REQUEST do_optcd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == SANYO_CDROM_MAJOR)
-
-#define DEVICE_NAME "Sanyo H94A CD-ROM"
-#define DEVICE_REQUEST do_sjcd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == APBLOCK_MAJOR)
-
-#define DEVICE_NAME "apblock"
-#define DEVICE_REQUEST ap_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == DDV_MAJOR)
-
-#define DEVICE_NAME "ddv"
-#define DEVICE_REQUEST ddv_request
-#define DEVICE_NR(device) (MINOR(device)>>PARTN_BITS)
-
-#elif (MAJOR_NR == MFM_ACORN_MAJOR)
-
-#define DEVICE_NAME "mfm disk"
-#define DEVICE_INTR do_mfm
-#define DEVICE_REQUEST do_mfm_request
-#define DEVICE_NR(device) (MINOR(device) >> 6)
-
-#elif (MAJOR_NR == NBD_MAJOR)
-
-#define DEVICE_NAME "nbd"
-#define DEVICE_REQUEST do_nbd_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == MDISK_MAJOR)
-
-#define DEVICE_NAME "mdisk"
-#define DEVICE_REQUEST mdisk_request
-#define DEVICE_NR(device) (MINOR(device))
-
-#elif (MAJOR_NR == DASD_MAJOR)
-
-#define DEVICE_NAME "dasd"
-#define DEVICE_REQUEST do_dasd_request
-#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
-
-#elif (MAJOR_NR == I2O_MAJOR)
-
-#define DEVICE_NAME "I2O block"
-#define DEVICE_REQUEST i2ob_request
-#define DEVICE_NR(device) (MINOR(device)>>4)
-
-#elif (MAJOR_NR == COMPAQ_SMART2_MAJOR)
-
-#define DEVICE_NAME "ida"
-#define TIMEOUT_VALUE (25*HZ)
-#define DEVICE_REQUEST do_ida_request
-#define DEVICE_NR(device) (MINOR(device) >> 4)
-
-#elif (MAJOR_NR == XLBLK_MAJOR)
-
-#define DEVICE_NAME "xeno disk"
-#define DEVICE_REQUEST do_xlblk_request
-/* #define DEVICE_INTR */
-#define DEVICE_NR(device) (MINOR(device))
-
-#endif /* MAJOR_NR == whatever */
-
-/* provide DEVICE_xxx defaults, if not explicitly defined
- * above in the MAJOR_NR==xxx if-elif tree */
-#ifndef DEVICE_ON
-#define DEVICE_ON(device) do {} while (0)
-#endif
-#ifndef DEVICE_OFF
-#define DEVICE_OFF(device) do {} while (0)
-#endif
-
-#if (MAJOR_NR != SCSI_TAPE_MAJOR) && (MAJOR_NR != OSST_MAJOR)
-#if !defined(IDE_DRIVER)
-
-#ifndef CURRENT
-#define CURRENT blkdev_entry_next_request(&blk_dev[MAJOR_NR].request_queue.queue_head)
-#endif
-#ifndef QUEUE_EMPTY
-#define QUEUE_EMPTY list_empty(&blk_dev[MAJOR_NR].request_queue.queue_head)
-#endif
-
-#ifndef DEVICE_NAME
-#define DEVICE_NAME "unknown"
-#endif
-
-#define CURRENT_DEV DEVICE_NR(CURRENT->rq_dev)
-
-#ifdef DEVICE_INTR
-static void (*DEVICE_INTR)(void) = NULL;
-#endif
-
-#define SET_INTR(x) (DEVICE_INTR = (x))
-
-#ifdef DEVICE_REQUEST
-static void (DEVICE_REQUEST)(request_queue_t *);
-#endif
-
-#ifdef DEVICE_INTR
-#define CLEAR_INTR SET_INTR(NULL)
-#else
-#define CLEAR_INTR
-#endif
-
-#define INIT_REQUEST \
- if (QUEUE_EMPTY) {\
- CLEAR_INTR; \
- return; \
- } \
- if (MAJOR(CURRENT->rq_dev) != MAJOR_NR) \
- panic(DEVICE_NAME ": request list destroyed"); \
- if (CURRENT->bh) { \
- if (!buffer_locked(CURRENT->bh)) \
- panic(DEVICE_NAME ": block not locked"); \
- }
-
-#endif /* !defined(IDE_DRIVER) */
-
-
-#ifndef LOCAL_END_REQUEST /* If we have our own end_request, we do not want to include this mess */
-
-#if ! SCSI_BLK_MAJOR(MAJOR_NR) && (MAJOR_NR != COMPAQ_SMART2_MAJOR)
-
-static inline void end_request(int uptodate) {
- struct request *req = CURRENT;
-
- if (end_that_request_first(req, uptodate, DEVICE_NAME))
- return;
-
-#ifndef DEVICE_NO_RANDOM
- add_blkdev_randomness(MAJOR(req->rq_dev));
-#endif
- DEVICE_OFF(req->rq_dev);
- blkdev_dequeue_request(req);
- end_that_request_last(req);
-}
-
-#endif /* ! SCSI_BLK_MAJOR(MAJOR_NR) */
-#endif /* LOCAL_END_REQUEST */
-
-#endif /* (MAJOR_NR != SCSI_TAPE_MAJOR) */
-#endif /* defined(MAJOR_NR) || defined(IDE_DRIVER) */
-
-#endif /* _BLK_H */
+++ /dev/null
-#ifndef _LINUX_MAJOR_H
-#define _LINUX_MAJOR_H
-
-/*
- * This file has definitions for major device numbers.
- * For the device number assignments, see Documentation/devices.txt.
- */
-
-/* limits */
-
-/*
- * Important: Don't change this to 256. Major number 255 is and must be
- * reserved for future expansion into a larger dev_t space.
- */
-#define MAX_CHRDEV 255
-#define MAX_BLKDEV 255
-
-#define UNNAMED_MAJOR 0
-#define MEM_MAJOR 1
-#define RAMDISK_MAJOR 1
-#define FLOPPY_MAJOR 2
-#define PTY_MASTER_MAJOR 2
-#define IDE0_MAJOR 3
-#define PTY_SLAVE_MAJOR 3
-#define HD_MAJOR IDE0_MAJOR
-#define TTY_MAJOR 4
-#define TTYAUX_MAJOR 5
-#define LP_MAJOR 6
-#define VCS_MAJOR 7
-#define LOOP_MAJOR 7
-#define SCSI_DISK0_MAJOR 8
-#define SCSI_TAPE_MAJOR 9
-#define MD_MAJOR 9
-#define MISC_MAJOR 10
-#define SCSI_CDROM_MAJOR 11
-#define QIC02_TAPE_MAJOR 12
-#define XT_DISK_MAJOR 13
-#define SOUND_MAJOR 14
-#define CDU31A_CDROM_MAJOR 15
-#define JOYSTICK_MAJOR 15
-#define GOLDSTAR_CDROM_MAJOR 16
-#define OPTICS_CDROM_MAJOR 17
-#define SANYO_CDROM_MAJOR 18
-#define CYCLADES_MAJOR 19
-#define CYCLADESAUX_MAJOR 20
-#define MITSUMI_X_CDROM_MAJOR 20
-#define MFM_ACORN_MAJOR 21 /* ARM Linux /dev/mfm */
-#define SCSI_GENERIC_MAJOR 21
-#define Z8530_MAJOR 34
-#define DIGI_MAJOR 23
-#define IDE1_MAJOR 22
-#define DIGICU_MAJOR 22
-#define MITSUMI_CDROM_MAJOR 23
-#define CDU535_CDROM_MAJOR 24
-#define STL_SERIALMAJOR 24
-#define MATSUSHITA_CDROM_MAJOR 25
-#define STL_CALLOUTMAJOR 25
-#define MATSUSHITA_CDROM2_MAJOR 26
-#define QIC117_TAPE_MAJOR 27
-#define MATSUSHITA_CDROM3_MAJOR 27
-#define MATSUSHITA_CDROM4_MAJOR 28
-#define STL_SIOMEMMAJOR 28
-#define ACSI_MAJOR 28
-#define AZTECH_CDROM_MAJOR 29
-#define GRAPHDEV_MAJOR 29 /* SparcLinux & Linux/68k /dev/fb */
-#define SHMIQ_MAJOR 85 /* Linux/mips, SGI /dev/shmiq */
-#define CM206_CDROM_MAJOR 32
-#define IDE2_MAJOR 33
-#define IDE3_MAJOR 34
-#define XPRAM_MAJOR 35 /* expanded storage on S/390 = "slow ram" */
- /* proposed by Peter */
-#define NETLINK_MAJOR 36
-#define PS2ESDI_MAJOR 36
-#define IDETAPE_MAJOR 37
-#define Z2RAM_MAJOR 37
-#define APBLOCK_MAJOR 38 /* AP1000 Block device */
-#define DDV_MAJOR 39 /* AP1000 DDV block device */
-#define NBD_MAJOR 43 /* Network block device */
-#define RISCOM8_NORMAL_MAJOR 48
-#define DAC960_MAJOR 48 /* 48..55 */
-#define RISCOM8_CALLOUT_MAJOR 49
-#define MKISS_MAJOR 55
-#define DSP56K_MAJOR 55 /* DSP56001 processor device */
-
-#define IDE4_MAJOR 56
-#define IDE5_MAJOR 57
-
-#define LVM_BLK_MAJOR 58 /* Logical Volume Manager */
-
-#define SCSI_DISK1_MAJOR 65
-#define SCSI_DISK2_MAJOR 66
-#define SCSI_DISK3_MAJOR 67
-#define SCSI_DISK4_MAJOR 68
-#define SCSI_DISK5_MAJOR 69
-#define SCSI_DISK6_MAJOR 70
-#define SCSI_DISK7_MAJOR 71
-
-
-#define COMPAQ_SMART2_MAJOR 72
-#define COMPAQ_SMART2_MAJOR1 73
-#define COMPAQ_SMART2_MAJOR2 74
-#define COMPAQ_SMART2_MAJOR3 75
-#define COMPAQ_SMART2_MAJOR4 76
-#define COMPAQ_SMART2_MAJOR5 77
-#define COMPAQ_SMART2_MAJOR6 78
-#define COMPAQ_SMART2_MAJOR7 79
-
-#define SPECIALIX_NORMAL_MAJOR 75
-#define SPECIALIX_CALLOUT_MAJOR 76
-
-#define COMPAQ_CISS_MAJOR 104
-#define COMPAQ_CISS_MAJOR1 105
-#define COMPAQ_CISS_MAJOR2 106
-#define COMPAQ_CISS_MAJOR3 107
-#define COMPAQ_CISS_MAJOR4 108
-#define COMPAQ_CISS_MAJOR5 109
-#define COMPAQ_CISS_MAJOR6 110
-#define COMPAQ_CISS_MAJOR7 111
-
-#define ATARAID_MAJOR 114
-
-#define DASD_MAJOR 94 /* Official assignations from Peter */
-
-#define MDISK_MAJOR 95 /* Official assignations from Peter */
-
-#define I2O_MAJOR 80 /* 80->87 */
-
-#define IDE6_MAJOR 88
-#define IDE7_MAJOR 89
-#define IDE8_MAJOR 90
-#define IDE9_MAJOR 91
-
-#define UBD_MAJOR 98
-
-#define AURORA_MAJOR 79
-
-#define JSFD_MAJOR 99
-
-#define PHONE_MAJOR 100
-
-#define LVM_CHAR_MAJOR 109 /* Logical Volume Manager */
-
-#define UMEM_MAJOR 116 /* http://www.umem.com/ Battery Backed RAM */
-
-#define XLBLK_MAJOR 123 /* XenoLinux Block Device */
-
-#define RTF_MAJOR 150
-#define RAW_MAJOR 162
-
-#define USB_ACM_MAJOR 166
-#define USB_ACM_AUX_MAJOR 167
-#define USB_CHAR_MAJOR 180
-
-#define UNIX98_PTY_MASTER_MAJOR 128
-#define UNIX98_PTY_MAJOR_COUNT 8
-#define UNIX98_PTY_SLAVE_MAJOR (UNIX98_PTY_MASTER_MAJOR+UNIX98_PTY_MAJOR_COUNT)
-
-#define VXVM_MAJOR 199 /* VERITAS volume i/o driver */
-#define VXSPEC_MAJOR 200 /* VERITAS volume config driver */
-#define VXDMP_MAJOR 201 /* VERITAS volume multipath driver */
-
-#define MSR_MAJOR 202
-#define CPUID_MAJOR 203
-
-#define OSST_MAJOR 206 /* OnStream-SCx0 SCSI tape */
-
-#define IBM_TTY3270_MAJOR 227 /* Official allocations now */
-#define IBM_FS3270_MAJOR 228
-
-/*
- * Tests for SCSI devices.
- */
-
-#define SCSI_DISK_MAJOR(M) ((M) == SCSI_DISK0_MAJOR || \
- ((M) >= SCSI_DISK1_MAJOR && (M) <= SCSI_DISK7_MAJOR))
-
-#define SCSI_BLK_MAJOR(M) \
- (SCSI_DISK_MAJOR(M) \
- || (M) == SCSI_CDROM_MAJOR)
-
-static __inline__ int scsi_blk_major(int m) {
- return SCSI_BLK_MAJOR(m);
-}
-
-/*
- * Tests for IDE devices
- */
-#define IDE_DISK_MAJOR(M) ((M) == IDE0_MAJOR || (M) == IDE1_MAJOR || \
- (M) == IDE2_MAJOR || (M) == IDE3_MAJOR || \
- (M) == IDE4_MAJOR || (M) == IDE5_MAJOR || \
- (M) == IDE6_MAJOR || (M) == IDE7_MAJOR || \
- (M) == IDE8_MAJOR || (M) == IDE9_MAJOR)
-
-static __inline__ int ide_blk_major(int m)
-{
- return IDE_DISK_MAJOR(m);
-}
-
-#endif
+++ /dev/null
-/*
- * linux/include/linux/sunrpc/debug.h
- *
- * Debugging support for sunrpc module
- *
- * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
- */
-
-#ifndef _LINUX_SUNRPC_DEBUG_H_
-#define _LINUX_SUNRPC_DEBUG_H_
-
-#include <linux/config.h>
-
-#include <linux/timer.h>
-#include <linux/tqueue.h>
-
-/*
- * Enable RPC debugging/profiling.
- */
-/*#ifdef CONFIG_SYSCTL*/
-/*#define RPC_DEBUG*/
-/*#endif*/
-/* #define RPC_PROFILE */
-
-/*
- * RPC debug facilities
- */
-#define RPCDBG_XPRT 0x0001
-#define RPCDBG_CALL 0x0002
-#define RPCDBG_DEBUG 0x0004
-#define RPCDBG_NFS 0x0008
-#define RPCDBG_AUTH 0x0010
-#define RPCDBG_PMAP 0x0020
-#define RPCDBG_SCHED 0x0040
-#define RPCDBG_SVCSOCK 0x0100
-#define RPCDBG_SVCDSP 0x0200
-#define RPCDBG_MISC 0x0400
-#define RPCDBG_ALL 0x7fff
-
-#ifdef __KERNEL__
-
-/*
- * Debugging macros etc
- */
-#ifdef RPC_DEBUG
-extern unsigned int rpc_debug;
-extern unsigned int nfs_debug;
-extern unsigned int nfsd_debug;
-extern unsigned int nlm_debug;
-#endif
-
-#define dprintk(args...) dfprintk(FACILITY, ## args)
-
-#undef ifdebug
-#ifdef RPC_DEBUG
-# define ifdebug(fac) if (rpc_debug & RPCDBG_##fac)
-# define dfprintk(fac, args...) do { ifdebug(fac) printk(args); } while(0)
-# define RPC_IFDEBUG(x) x
-#else
-# define dfprintk(fac, args...) do ; while (0)
-# define RPC_IFDEBUG(x)
-#endif
-
-#ifdef RPC_PROFILE
-# define pprintk(args...) printk(## args)
-#else
-# define pprintk(args...) do ; while (0)
-#endif
-
-/*
- * Sysctl interface for RPC debugging
- */
-#ifdef RPC_DEBUG
-void rpc_register_sysctl(void);
-void rpc_unregister_sysctl(void);
-#endif
-
-#endif /* __KERNEL__ */
-
-/*
- * Declarations for the sysctl debug interface, which allows to read or
- * change the debug flags for rpc, nfs, nfsd, and lockd. Since the sunrpc
- * module currently registers its sysctl table dynamically, the sysctl path
- * for module FOO is <CTL_SUNRPC, CTL_FOODEBUG>.
- */
-#define CTL_SUNRPC 7249 /* arbitrary and hopefully unused */
-
-enum {
- CTL_RPCDEBUG = 1,
- CTL_NFSDEBUG,
- CTL_NFSDDEBUG,
- CTL_NLMDEBUG,
-};
-
-#endif /* _LINUX_SUNRPC_DEBUG_H_ */
+++ /dev/null
-/*
- * linux/init/main.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * GK 2/5/95 - Changed to support mounting root fs via NFS
- * Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96
- * Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96
- * Simplified starting of init: Michael A. Griffith <grif@acm.org>
- */
-
-#define __KERNEL_SYSCALLS__
-
-#include <linux/config.h>
-#include <linux/proc_fs.h>
-#include <linux/devfs_fs_kernel.h>
-#include <linux/unistd.h>
-#include <linux/string.h>
-#include <linux/ctype.h>
-#include <linux/delay.h>
-#include <linux/utsname.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/smp_lock.h>
-#include <linux/blk.h>
-#include <linux/hdreg.h>
-#include <linux/iobuf.h>
-#include <linux/bootmem.h>
-#include <linux/tty.h>
-
-#include <asm/io.h>
-#include <asm/bugs.h>
-
-#if defined(CONFIG_ARCH_S390)
-#include <asm/s390mach.h>
-#include <asm/ccwcache.h>
-#endif
-
-#ifdef CONFIG_PCI
-#include <linux/pci.h>
-#endif
-
-#ifdef CONFIG_DIO
-#include <linux/dio.h>
-#endif
-
-#ifdef CONFIG_ZORRO
-#include <linux/zorro.h>
-#endif
-
-#ifdef CONFIG_MTRR
-# include <asm/mtrr.h>
-#endif
-
-#ifdef CONFIG_NUBUS
-#include <linux/nubus.h>
-#endif
-
-#ifdef CONFIG_ISAPNP
-#include <linux/isapnp.h>
-#endif
-
-#ifdef CONFIG_IRDA
-extern int irda_proto_init(void);
-extern int irda_device_init(void);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/smp.h>
-#endif
-
-#if defined(CONFIG_KDB)
-#include <linux/kdb.h>
-#endif
-
-/*
- * Versions of gcc older than that listed below may actually compile
- * and link okay, but the end product can have subtle run time bugs.
- * To avoid associated bogus bug reports, we flatly refuse to compile
- * with a gcc that is known to be too old from the very beginning.
- */
-#if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 91)
-#error Sorry, your GCC is too old. It builds incorrect kernels.
-#endif
-
-extern char _stext, _etext;
-extern char *linux_banner;
-
-static int init(void *);
-
-extern void init_IRQ(void);
-extern void init_modules(void);
-extern void sock_init(void);
-extern void fork_init(unsigned long);
-extern void mca_init(void);
-extern void sbus_init(void);
-extern void ppc_init(void);
-extern void sysctl_init(void);
-extern void signals_init(void);
-extern int init_pcmcia_ds(void);
-
-extern void free_initmem(void);
-
-#ifdef CONFIG_TC
-extern void tc_init(void);
-#endif
-
-extern void ecard_init(void);
-
-#if defined(CONFIG_SYSVIPC)
-extern void ipc_init(void);
-#endif
-
-/*
- * Boot command-line arguments
- */
-#define MAX_INIT_ARGS 8
-#define MAX_INIT_ENVS 8
-
-extern void time_init(void);
-extern void softirq_init(void);
-
-int rows, cols;
-
-#ifdef CONFIG_BLK_DEV_INITRD
-unsigned int real_root_dev; /* do_proc_dointvec cannot handle kdev_t */
-#endif
-
-int root_mountflags = MS_RDONLY;
-char *execute_command;
-char root_device_name[64];
-
-
-static char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
-static char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
-
-static int __init profile_setup(char *str)
-{
- int par;
- if (get_option(&str,&par)) prof_shift = par;
- return 1;
-}
-
-__setup("profile=", profile_setup);
-
-
-static struct dev_name_struct {
- const char *name;
- const int num;
-} root_dev_names[] __initdata = {
- { "nfs", 0x00ff },
- { "xhda", 0x7b00 },
- { "hda", 0x0300 },
- { "hdb", 0x0340 },
- { "loop", 0x0700 },
- { "hdc", 0x1600 },
- { "hdd", 0x1640 },
- { "hde", 0x2100 },
- { "hdf", 0x2140 },
- { "hdg", 0x2200 },
- { "hdh", 0x2240 },
- { "hdi", 0x3800 },
- { "hdj", 0x3840 },
- { "hdk", 0x3900 },
- { "hdl", 0x3940 },
- { "hdm", 0x5800 },
- { "hdn", 0x5840 },
- { "hdo", 0x5900 },
- { "hdp", 0x5940 },
- { "hdq", 0x5A00 },
- { "hdr", 0x5A40 },
- { "hds", 0x5B00 },
- { "hdt", 0x5B40 },
- { "sda", 0x0800 },
- { "sdb", 0x0810 },
- { "sdc", 0x0820 },
- { "sdd", 0x0830 },
- { "sde", 0x0840 },
- { "sdf", 0x0850 },
- { "sdg", 0x0860 },
- { "sdh", 0x0870 },
- { "sdi", 0x0880 },
- { "sdj", 0x0890 },
- { "sdk", 0x08a0 },
- { "sdl", 0x08b0 },
- { "sdm", 0x08c0 },
- { "sdn", 0x08d0 },
- { "sdo", 0x08e0 },
- { "sdp", 0x08f0 },
- { "ada", 0x1c00 },
- { "adb", 0x1c10 },
- { "adc", 0x1c20 },
- { "add", 0x1c30 },
- { "ade", 0x1c40 },
- { "fd", 0x0200 },
- { "md", 0x0900 },
- { "xda", 0x0d00 },
- { "xdb", 0x0d40 },
- { "ram", 0x0100 },
- { "scd", 0x0b00 },
- { "mcd", 0x1700 },
- { "cdu535", 0x1800 },
- { "sonycd", 0x1800 },
- { "aztcd", 0x1d00 },
- { "cm206cd", 0x2000 },
- { "gscd", 0x1000 },
- { "sbpcd", 0x1900 },
- { "eda", 0x2400 },
- { "edb", 0x2440 },
- { "pda", 0x2d00 },
- { "pdb", 0x2d10 },
- { "pdc", 0x2d20 },
- { "pdd", 0x2d30 },
- { "pcd", 0x2e00 },
- { "pf", 0x2f00 },
- { "apblock", APBLOCK_MAJOR << 8},
- { "ddv", DDV_MAJOR << 8},
- { "jsfd", JSFD_MAJOR << 8},
-#if defined(CONFIG_ARCH_S390)
- { "dasda", (DASD_MAJOR << MINORBITS) },
- { "dasdb", (DASD_MAJOR << MINORBITS) + (1 << 2) },
- { "dasdc", (DASD_MAJOR << MINORBITS) + (2 << 2) },
- { "dasdd", (DASD_MAJOR << MINORBITS) + (3 << 2) },
- { "dasde", (DASD_MAJOR << MINORBITS) + (4 << 2) },
- { "dasdf", (DASD_MAJOR << MINORBITS) + (5 << 2) },
- { "dasdg", (DASD_MAJOR << MINORBITS) + (6 << 2) },
- { "dasdh", (DASD_MAJOR << MINORBITS) + (7 << 2) },
-#endif
-#if defined(CONFIG_BLK_CPQ_DA) || defined(CONFIG_BLK_CPQ_DA_MODULE)
- { "ida/c0d0p",0x4800 },
- { "ida/c0d1p",0x4810 },
- { "ida/c0d2p",0x4820 },
- { "ida/c0d3p",0x4830 },
- { "ida/c0d4p",0x4840 },
- { "ida/c0d5p",0x4850 },
- { "ida/c0d6p",0x4860 },
- { "ida/c0d7p",0x4870 },
- { "ida/c0d8p",0x4880 },
- { "ida/c0d9p",0x4890 },
- { "ida/c0d10p",0x48A0 },
- { "ida/c0d11p",0x48B0 },
- { "ida/c0d12p",0x48C0 },
- { "ida/c0d13p",0x48D0 },
- { "ida/c0d14p",0x48E0 },
- { "ida/c0d15p",0x48F0 },
-#endif
-#if defined(CONFIG_BLK_CPQ_CISS_DA) || defined(CONFIG_BLK_CPQ_CISS_DA_MODULE)
- { "cciss/c0d0p",0x6800 },
- { "cciss/c0d1p",0x6810 },
- { "cciss/c0d2p",0x6820 },
- { "cciss/c0d3p",0x6830 },
- { "cciss/c0d4p",0x6840 },
- { "cciss/c0d5p",0x6850 },
- { "cciss/c0d6p",0x6860 },
- { "cciss/c0d7p",0x6870 },
- { "cciss/c0d8p",0x6880 },
- { "cciss/c0d9p",0x6890 },
- { "cciss/c0d10p",0x68A0 },
- { "cciss/c0d11p",0x68B0 },
- { "cciss/c0d12p",0x68C0 },
- { "cciss/c0d13p",0x68D0 },
- { "cciss/c0d14p",0x68E0 },
- { "cciss/c0d15p",0x68F0 },
-#endif
- { "nftla", 0x5d00 },
- { "nftlb", 0x5d10 },
- { "nftlc", 0x5d20 },
- { "nftld", 0x5d30 },
- { "ftla", 0x2c00 },
- { "ftlb", 0x2c08 },
- { "ftlc", 0x2c10 },
- { "ftld", 0x2c18 },
- { "mtdblock", 0x1f00 },
- { NULL, 0 }
-};
-
-kdev_t __init name_to_kdev_t(char *line)
-{
- int base = 0;
-
- if (strncmp(line,"/dev/",5) == 0) {
- struct dev_name_struct *dev = root_dev_names;
- line += 5;
- do {
- int len = strlen(dev->name);
- if (strncmp(line,dev->name,len) == 0) {
- line += len;
- base = dev->num;
- break;
- }
- dev++;
- } while (dev->name);
- }
- return to_kdev_t(base + simple_strtoul(line,NULL,base?10:16));
-}
-
-static int __init root_dev_setup(char *line)
-{
- int i;
- char ch;
-
- ROOT_DEV = name_to_kdev_t(line);
- memset (root_device_name, 0, sizeof root_device_name);
- if (strncmp (line, "/dev/", 5) == 0) line += 5;
- for (i = 0; i < sizeof root_device_name - 1; ++i)
- {
- ch = line[i];
- if ( isspace (ch) || (ch == ',') || (ch == '\0') ) break;
- root_device_name[i] = ch;
- }
- return 1;
-}
-
-__setup("root=", root_dev_setup);
-
-static int __init checksetup(char *line)
-{
- struct kernel_param *p;
-
- p = &__setup_start;
- do {
- int n = strlen(p->str);
- if (!strncmp(line,p->str,n)) {
- if (p->setup_func(line+n))
- return 1;
- }
- p++;
- } while (p < &__setup_end);
- return 0;
-}
-
-/* this should be approx 2 Bo*oMips to start (note initial shift), and will
- still work even if initially too large, it will just take slightly longer */
-unsigned long loops_per_jiffy = (1<<12);
-
-/* This is the number of bits of precision for the loops_per_jiffy. Each
- bit takes on average 1.5/HZ seconds. This (like the original) is a little
- better than 1% */
-#define LPS_PREC 8
-
-void __init calibrate_delay(void)
-{
- unsigned long ticks, loopbit;
- int lps_precision = LPS_PREC;
-
- loops_per_jiffy = (1<<12);
-
- printk("Calibrating delay loop... ");
- while (loops_per_jiffy <<= 1) {
- /* wait for "start of" clock tick */
- ticks = jiffies;
- while (ticks == jiffies)
- /* nothing */;
- /* Go .. */
- ticks = jiffies;
- __delay(loops_per_jiffy);
- ticks = jiffies - ticks;
- if (ticks)
- break;
- }
-
-/* Do a binary approximation to get loops_per_jiffy set to equal one clock
- (up to lps_precision bits) */
- loops_per_jiffy >>= 1;
- loopbit = loops_per_jiffy;
- while ( lps_precision-- && (loopbit >>= 1) ) {
- loops_per_jiffy |= loopbit;
- ticks = jiffies;
- while (ticks == jiffies);
- ticks = jiffies;
- __delay(loops_per_jiffy);
- if (jiffies != ticks) /* longer than 1 tick */
- loops_per_jiffy &= ~loopbit;
- }
-
-/* Round the value and print it */
- printk("%lu.%02lu BogoMIPS\n",
- loops_per_jiffy/(500000/HZ),
- (loops_per_jiffy/(5000/HZ)) % 100);
-}
-
-static int __init readonly(char *str)
-{
- if (*str)
- return 0;
- root_mountflags |= MS_RDONLY;
- return 1;
-}
-
-static int __init readwrite(char *str)
-{
- if (*str)
- return 0;
- root_mountflags &= ~MS_RDONLY;
- return 1;
-}
-
-static int __init debug_kernel(char *str)
-{
- if (*str)
- return 0;
- console_loglevel = 10;
- return 1;
-}
-
-static int __init quiet_kernel(char *str)
-{
- if (*str)
- return 0;
- console_loglevel = 4;
- return 1;
-}
-
-__setup("ro", readonly);
-__setup("rw", readwrite);
-__setup("debug", debug_kernel);
-__setup("quiet", quiet_kernel);
-
-/*
- * This is a simple kernel command line parsing function: it parses
- * the command line, and fills in the arguments/environment to init
- * as appropriate. Any cmd-line option is taken to be an environment
- * variable if it contains the character '='.
- *
- * This routine also checks for options meant for the kernel.
- * These options are not given to init - they are for internal kernel use only.
- */
-static void __init parse_options(char *line)
-{
- char *next,*quote;
- int args, envs;
-
- if (!*line)
- return;
- args = 0;
- envs = 1; /* TERM is set to 'linux' by default */
- next = line;
- while ((line = next) != NULL) {
- quote = strchr(line,'"');
- next = strchr(line, ' ');
- while (next != NULL && quote != NULL && quote < next) {
- /* we found a left quote before the next blank
- * now we have to find the matching right quote
- */
- next = strchr(quote+1, '"');
- if (next != NULL) {
- quote = strchr(next+1, '"');
- next = strchr(next+1, ' ');
- }
- }
- if (next != NULL)
- *next++ = 0;
-#if defined(CONFIG_KDB)
- /* kdb, kdb=on, kdb=off, kdb=early */
- if (strncmp(line, "kdb", 3) == 0) {
- if (line[3] == '\0') {
- /* Backward compatibility, kdb with no option means early activation */
- printk("Boot flag kdb with no options is obsolete, use kdb=early\n");
- kdb_on = 1;
- kdb_flags |= KDB_FLAG_EARLYKDB;
- continue;
- }
- if (line[3] == '=') {
- if (strcmp(line+4, "on") == 0) {
- kdb_on = 1;
- continue;
- }
- if (strcmp(line+4, "off") == 0) {
- kdb_on = 0;
- continue;
- }
- if (strcmp(line+4, "early") == 0) {
- kdb_on = 1;
- kdb_flags |= KDB_FLAG_EARLYKDB;
- continue;
- }
- printk("Boot flag %s not recognised, assumed to be environment variable\n", line);
- }
- }
-#endif
- if (!strncmp(line,"init=",5)) {
- line += 5;
- execute_command = line;
- /* In case LILO is going to boot us with default command line,
- * it prepends "auto" before the whole cmdline which makes
- * the shell think it should execute a script with such name.
- * So we ignore all arguments entered _before_ init=... [MJ]
- */
- args = 0;
- continue;
- }
- if (checksetup(line))
- continue;
-
- /*
- * Then check if it's an environment variable or
- * an option.
- */
- if (strchr(line,'=')) {
- if (envs >= MAX_INIT_ENVS)
- break;
- envp_init[++envs] = line;
- } else {
- if (args >= MAX_INIT_ARGS)
- break;
- if (*line)
- argv_init[++args] = line;
- }
- }
- argv_init[args+1] = NULL;
- envp_init[envs+1] = NULL;
-}
-
-
-extern void setup_arch(char **);
-extern void cpu_idle(void);
-
-unsigned long wait_init_idle;
-
-#ifndef CONFIG_SMP
-
-#ifdef CONFIG_X86_LOCAL_APIC
-static void __init smp_init(void)
-{
- APIC_init_uniprocessor();
-}
-#else
-#define smp_init() do { } while (0)
-#endif
-
-#else
-
-
-/* Called by boot processor to activate the rest. */
-static void __init smp_init(void)
-{
- /* Get other processors into their bootup holding patterns. */
- smp_boot_cpus();
- wait_init_idle = cpu_online_map;
- clear_bit(current->processor, &wait_init_idle); /* Don't wait on me! */
-
- smp_threads_ready=1;
- smp_commence();
-
- /* Wait for the other cpus to set up their idle processes */
- printk("Waiting on wait_init_idle (map = 0x%lx)\n", wait_init_idle);
- while (wait_init_idle) {
- cpu_relax();
- barrier();
- }
- printk("All processors have done init_idle\n");
-}
-
-#endif
-
-/*
- * We need to finalize in a non-__init function or else race conditions
- * between the root thread and the init thread may cause start_kernel to
- * be reaped by free_initmem before the root thread has proceeded to
- * cpu_idle.
- */
-
-static void rest_init(void)
-{
- kernel_thread(init, NULL, CLONE_FS | CLONE_FILES | CLONE_SIGNAL);
- unlock_kernel();
- current->need_resched = 1;
- cpu_idle();
-}
-
-/*
- * Activate the first processor.
- */
-
-asmlinkage void __init start_kernel(void)
-{
- char * command_line;
- unsigned long mempages;
- extern char saved_command_line[];
-/*
- * Interrupts are still disabled. Do necessary setups, then
- * enable them
- */
- lock_kernel();
- printk(linux_banner);
- setup_arch(&command_line);
- printk("Kernel command line: %s\n", saved_command_line);
- parse_options(command_line);
- trap_init();
- init_IRQ();
- sched_init();
- softirq_init();
- time_init();
-
- /*
- * HACK ALERT! This is early. We're enabling the console before
- * we've done PCI setups etc, and console_init() must be aware of
- * this. But we do want output early, in case something goes wrong.
- */
- console_init();
-#ifdef CONFIG_MODULES
- init_modules();
-#endif
- if (prof_shift) {
- unsigned int size;
- /* only text is profiled */
- prof_len = (unsigned long) &_etext - (unsigned long) &_stext;
- prof_len >>= prof_shift;
-
- size = prof_len * sizeof(unsigned int) + PAGE_SIZE-1;
- prof_buffer = (unsigned int *) alloc_bootmem(size);
- }
-
- kmem_cache_init();
- sti();
- calibrate_delay();
-#ifdef CONFIG_BLK_DEV_INITRD
- if (initrd_start && !initrd_below_start_ok &&
- initrd_start < min_low_pfn << PAGE_SHIFT) {
- printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
- "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);
- initrd_start = 0;
- }
-#endif
- mem_init();
- kmem_cache_sizes_init();
-#if defined(CONFIG_KDB)
- kdb_init();
- if (KDB_FLAG(EARLYKDB)) {
- KDB_ENTER();
- }
-#endif
- mempages = num_physpages;
-
- fork_init(mempages);
- proc_caches_init();
- vfs_caches_init(mempages);
- buffer_init(mempages);
- page_cache_init(mempages);
-#if defined(CONFIG_ARCH_S390)
- ccwcache_init();
-#endif
- signals_init();
-#ifdef CONFIG_PROC_FS
- proc_root_init();
-#endif
-#if defined(CONFIG_SYSVIPC)
- ipc_init();
-#endif
- check_bugs();
- printk("POSIX conformance testing by UNIFIX\n");
-
- /*
- * We count on the initial thread going ok
- * Like idlers init is an unlocked kernel thread, which will
- * make syscalls (and thus be locked).
- */
- smp_init();
- rest_init();
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-static int do_linuxrc(void * shell)
-{
- static char *argv[] = { "linuxrc", NULL, };
-
- close(0);close(1);close(2);
- setsid();
- (void) open("/dev/console",O_RDWR,0);
- (void) dup(0);
- (void) dup(0);
- return execve(shell, argv, envp_init);
-}
-
-#endif
-
-struct task_struct *child_reaper = &init_task;
-
-static void __init do_initcalls(void)
-{
- initcall_t *call;
-
- call = &__initcall_start;
- do {
- (*call)();
- call++;
- } while (call < &__initcall_end);
-
- /* Make sure there is no pending stuff from the initcall sequence */
- flush_scheduled_tasks();
-}
-
-/*
- * Ok, the machine is now initialized. None of the devices
- * have been touched yet, but the CPU subsystem is up and
- * running, and memory and process management works.
- *
- * Now we can finally start doing some real work..
- */
-static void __init do_basic_setup(void)
-{
-
- /*
- * Tell the world that we're going to be the grim
- * reaper of innocent orphaned children.
- *
- * We don't want people to have to make incorrect
- * assumptions about where in the task array this
- * can be found.
- */
- child_reaper = current;
-
-#if defined(CONFIG_MTRR) /* Do this after SMP initialization */
-/*
- * We should probably create some architecture-dependent "fixup after
- * everything is up" style function where this would belong better
- * than in init/main.c..
- */
- mtrr_init();
-#endif
-
-#ifdef CONFIG_SYSCTL
- sysctl_init();
-#endif
-
- /*
- * Ok, at this point all CPU's should be initialized, so
- * we can start looking into devices..
- */
-#if defined(CONFIG_ARCH_S390)
- s390_init_machine_check();
-#endif
-
-#ifdef CONFIG_PCI
- pci_init();
-#endif
-#ifdef CONFIG_SBUS
- sbus_init();
-#endif
-#if defined(CONFIG_PPC)
- ppc_init();
-#endif
-#ifdef CONFIG_MCA
- mca_init();
-#endif
-#ifdef CONFIG_ARCH_ACORN
- ecard_init();
-#endif
-#ifdef CONFIG_ZORRO
- zorro_init();
-#endif
-#ifdef CONFIG_DIO
- dio_init();
-#endif
-#ifdef CONFIG_NUBUS
- nubus_init();
-#endif
-#ifdef CONFIG_ISAPNP
- isapnp_init();
-#endif
-#ifdef CONFIG_TC
- tc_init();
-#endif
-
- /* Networking initialization needs a process context */
- sock_init();
-
- start_context_thread();
- do_initcalls();
-
-#ifdef CONFIG_IRDA
- irda_proto_init();
- irda_device_init(); /* Must be done after protocol initialization */
-#endif
-#ifdef CONFIG_PCMCIA
- init_pcmcia_ds(); /* Do this last */
-#endif
-}
-
-extern void rd_load(void);
-extern void initrd_load(void);
-
-/*
- * Prepare the namespace - decide what/where to mount, load ramdisks, etc.
- */
-static void prepare_namespace(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
- int real_root_mountflags = root_mountflags;
- if (!initrd_start)
- mount_initrd = 0;
- if (mount_initrd)
- root_mountflags &= ~MS_RDONLY;
- real_root_dev = ROOT_DEV;
-#endif
-
-#ifdef CONFIG_BLK_DEV_RAM
-#ifdef CONFIG_BLK_DEV_INITRD
- if (mount_initrd)
- initrd_load();
- else
-#endif
- rd_load();
-#endif
-
- /* Mount the root filesystem.. */
- mount_root();
-
- mount_devfs_fs ();
-
-#ifdef CONFIG_BLK_DEV_INITRD
- root_mountflags = real_root_mountflags;
- if (mount_initrd && ROOT_DEV != real_root_dev
- && MAJOR(ROOT_DEV) == RAMDISK_MAJOR && MINOR(ROOT_DEV) == 0) {
- int error;
- int i, pid;
-
- pid = kernel_thread(do_linuxrc, "/linuxrc", SIGCHLD);
- if (pid > 0) {
- while (pid != wait(&i)) {
- current->policy |= SCHED_YIELD;
- schedule();
- }
- }
- if (MAJOR(real_root_dev) != RAMDISK_MAJOR
- || MINOR(real_root_dev) != 0) {
- error = change_root(real_root_dev,"/initrd");
- if (error)
- printk(KERN_ERR "Change root to /initrd: "
- "error %d\n",error);
- }
- }
-#endif
-}
-
-static int init(void * unused)
-{
- lock_kernel();
- do_basic_setup();
-
- prepare_namespace();
-
- /*
- * Ok, we have completed the initial bootup, and
- * we're essentially up and running. Get rid of the
- * initmem segments and start the user-mode stuff..
- */
- free_initmem();
- unlock_kernel();
-
- if (open("/dev/console", O_RDWR, 0) < 0)
- printk("Warning: unable to open an initial console.\n");
-
- (void) dup(0);
- (void) dup(0);
-
- /*
- * We try each of these until one succeeds.
- *
- * The Bourne shell can be used instead of init if we are
- * trying to recover a really broken machine.
- */
-
- if (execute_command)
- execve(execute_command,argv_init,envp_init);
- execve("/sbin/init",argv_init,envp_init);
- execve("/etc/init",argv_init,envp_init);
- execve("/bin/init",argv_init,envp_init);
- execve("/bin/sh",argv_init,envp_init);
- panic("No init found. Try passing init= option to kernel.");
-}
+++ /dev/null
-/*
- * linux/kernel/panic.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * This function is used through-out the kernel (including mm and fs)
- * to indicate a major problem.
- */
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/notifier.h>
-#include <linux/init.h>
-#include <linux/sysrq.h>
-#include <linux/interrupt.h>
-
-asmlinkage void sys_sync(void); /* it's really int */
-
-int panic_timeout;
-
-struct notifier_block *panic_notifier_list;
-
-static int __init panic_setup(char *str)
-{
- panic_timeout = simple_strtoul(str, NULL, 0);
- return 1;
-}
-
-__setup("panic=", panic_setup);
-
-/**
- * panic - halt the system
- * @fmt: The text string to print
- *
- * Display a message, then perform cleanups. Functions in the panic
- * notifier list are called after the filesystem cache is flushed (when possible).
- *
- * This function never returns.
- */
-
-NORET_TYPE void panic(const char * fmt, ...)
-{
- static char buf[1024];
- va_list args;
-#if defined(CONFIG_ARCH_S390)
- unsigned long caller = (unsigned long) __builtin_return_address(0);
-#endif
-
- bust_spinlocks(1);
- va_start(args, fmt);
- vsprintf(buf, fmt, args);
- va_end(args);
- printk(KERN_EMERG "Kernel panic: %s\n",buf);
- if (in_interrupt())
- printk(KERN_EMERG "In interrupt handler - not syncing\n");
- else if (!current->pid)
- printk(KERN_EMERG "In idle task - not syncing\n");
- else
- sys_sync();
- bust_spinlocks(0);
-
-#ifdef CONFIG_SMP
- smp_send_stop();
-#endif
-
- notifier_call_chain(&panic_notifier_list, 0, NULL);
-
- if (panic_timeout > 0)
- {
- /*
- * Delay timeout seconds before rebooting the machine.
- * We can't use the "normal" timers since we just panicked..
- */
- printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
- mdelay(panic_timeout*1000);
- /*
- * Should we run the reboot notifier. For the moment Im
- * choosing not too. It might crash, be corrupt or do
- * more harm than good for other reasons.
- */
- machine_restart(NULL);
- }
-#ifdef __sparc__
- {
- extern int stop_a_enabled;
- /* Make sure the user can actually press L1-A */
- stop_a_enabled = 1;
- printk("Press L1-A to return to the boot prom\n");
- }
-#endif
-#if defined(CONFIG_ARCH_S390)
- disabled_wait(caller);
-#endif
- sti();
- for(;;) {
- CHECK_EMERGENCY_SYNC
-#if defined(CONFIG_XENO)
- HYPERVISOR_exit();
-#endif
- }
-}
-
-/**
- * print_tainted - return a string to represent the kernel taint state.
- *
- * The string is overwritten by the next call to print_taint().
- */
-
-const char *print_tainted()
-{
- static char buf[20];
- if (tainted) {
- snprintf(buf, sizeof(buf), "Tainted: %c%c",
- tainted & 1 ? 'P' : 'G',
- tainted & 2 ? 'F' : ' ');
- }
- else
- snprintf(buf, sizeof(buf), "Not tainted");
- return(buf);
-}
-
-int tainted = 0;
+++ /dev/null
-export INSTALL_MOD_PATH=/local/scratch/kaf24/xeno/linux-install
-ARCH=xeno make -j 4 bzImage
-ARCH=xeno make -j 4 modules
-ARCH=xeno INSTALL_MOD_PATH=/anfs/nta3/xeno-roots/kaf24/root0 really make modules_install
-ARCH=xeno INSTALL_MOD_PATH=/anfs/nta3/xeno-roots/kaf24/root1 really make modules_install
-cp arch/xeno/boot/image.gz /usr/groups/pegasus/boot/kaf24/meteors/vmlinux.gz
+++ /dev/null
-/*
- * linux/mm/memory.c
- *
- * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
- */
-
-/*
- * demand-loading started 01.12.91 - seems it is high on the list of
- * things wanted, and it should be easy to implement. - Linus
- */
-
-/*
- * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
- * pages started 02.12.91, seems to work. - Linus.
- *
- * Tested sharing by executing about 30 /bin/sh: under the old kernel it
- * would have taken more than the 6M I have free, but it worked well as
- * far as I could see.
- *
- * Also corrected some "invalidate()"s - I wasn't doing enough of them.
- */
-
-/*
- * Real VM (paging to/from disk) started 18.12.91. Much more work and
- * thought has to go into this. Oh, well..
- * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
- * Found it. Everything seems to work now.
- * 20.12.91 - Ok, making the swap-device changeable like the root.
- */
-
-/*
- * 05.04.94 - Multi-page memory management added for v1.1.
- * Idea by Alex Bligh (alex@cconcepts.co.uk)
- *
- * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
- * (Gerhard.Wichert@pdb.siemens.de)
- */
-
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/swap.h>
-#include <linux/smp_lock.h>
-#include <linux/swapctl.h>
-#include <linux/iobuf.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/uaccess.h>
-#include <asm/tlb.h>
-
-unsigned long max_mapnr;
-unsigned long num_physpages;
-void * high_memory;
-struct page *highmem_start_page;
-
-/*
- * We special-case the C-O-W ZERO_PAGE, because it's such
- * a common occurrence (no need to read the page to know
- * that it's zero - better for the cache and memory subsystem).
- */
-static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address)
-{
- if (from == ZERO_PAGE(address)) {
- clear_user_highpage(to, address);
- return;
- }
- copy_user_highpage(to, from, address);
-}
-
-mem_map_t * mem_map;
-
-/*
- * Called by TLB shootdown
- */
-void __free_pte(pte_t pte)
-{
- struct page *page = pte_page(pte);
- if ((!VALID_PAGE(page)) || PageReserved(page))
- return;
- if (pte_dirty(pte))
- set_page_dirty(page);
- free_page_and_swap_cache(page);
-}
-
-
-/*
- * Note: this doesn't free the actual pages themselves. That
- * has been handled earlier when unmapping all the memory regions.
- */
-static inline void free_one_pmd(pmd_t * dir)
-{
- pte_t * pte;
-
- if (pmd_none(*dir))
- return;
- if (pmd_bad(*dir)) {
- pmd_ERROR(*dir);
- pmd_clear(dir);
- return;
- }
- pte = pte_offset(dir, 0);
- pmd_clear(dir);
- pte_free(pte);
-}
-
-static inline void free_one_pgd(pgd_t * dir)
-{
- int j;
- pmd_t * pmd;
-
- if (pgd_none(*dir))
- return;
- if (pgd_bad(*dir)) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
- return;
- }
- pmd = pmd_offset(dir, 0);
- pgd_clear(dir);
- for (j = 0; j < PTRS_PER_PMD ; j++) {
- prefetchw(pmd+j+(PREFETCH_STRIDE/16));
- free_one_pmd(pmd+j);
- }
- pmd_free(pmd);
-}
-
-/* Low and high watermarks for page table cache.
- The system should try to have pgt_water[0] <= cache elements <= pgt_water[1]
- */
-int pgt_cache_water[2] = { 25, 50 };
-
-/* Returns the number of pages freed */
-int check_pgt_cache(void)
-{
- return do_check_pgt_cache(pgt_cache_water[0], pgt_cache_water[1]);
-}
-
-
-/*
- * This function clears all user-level page tables of a process - this
- * is needed by execve(), so that old pages aren't in the way.
- */
-void clear_page_tables(struct mm_struct *mm, unsigned long first, int nr)
-{
- pgd_t * page_dir = mm->pgd;
-
- spin_lock(&mm->page_table_lock);
- page_dir += first;
- do {
- free_one_pgd(page_dir);
- page_dir++;
- } while (--nr);
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-}
-
-#define PTE_TABLE_MASK ((PTRS_PER_PTE-1) * sizeof(pte_t))
-#define PMD_TABLE_MASK ((PTRS_PER_PMD-1) * sizeof(pmd_t))
-
-/*
- * copy one vm_area from one task to the other. Assumes the page tables
- * already present in the new task to be cleared in the whole range
- * covered by this vma.
- *
- * 08Jan98 Merged into one routine from several inline routines to reduce
- * variable count and make things faster. -jj
- *
- * dst->page_table_lock is held on entry and exit,
- * but may be dropped within pmd_alloc() and pte_alloc().
- */
-int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma)
-{
- pgd_t * src_pgd, * dst_pgd;
- unsigned long address = vma->vm_start;
- unsigned long end = vma->vm_end;
- unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE;
-
- src_pgd = pgd_offset(src, address)-1;
- dst_pgd = pgd_offset(dst, address)-1;
-
- for (;;) {
- pmd_t * src_pmd, * dst_pmd;
-
- src_pgd++; dst_pgd++;
-
- /* copy_pmd_range */
-
- if (pgd_none(*src_pgd))
- goto skip_copy_pmd_range;
- if (pgd_bad(*src_pgd)) {
- pgd_ERROR(*src_pgd);
- pgd_clear(src_pgd);
-skip_copy_pmd_range: address = (address + PGDIR_SIZE) & PGDIR_MASK;
- if (!address || (address >= end))
- goto out;
- continue;
- }
-
- src_pmd = pmd_offset(src_pgd, address);
- dst_pmd = pmd_alloc(dst, dst_pgd, address);
- if (!dst_pmd)
- goto nomem;
-
- do {
- pte_t * src_pte, * dst_pte;
-
- /* copy_pte_range */
-
- if (pmd_none(*src_pmd))
- goto skip_copy_pte_range;
- if (pmd_bad(*src_pmd)) {
- pmd_ERROR(*src_pmd);
- pmd_clear(src_pmd);
-skip_copy_pte_range: address = (address + PMD_SIZE) & PMD_MASK;
- if (address >= end)
- goto out;
- goto cont_copy_pmd_range;
- }
-
- src_pte = pte_offset(src_pmd, address);
- dst_pte = pte_alloc(dst, dst_pmd, address);
- if (!dst_pte)
- goto nomem;
-
- spin_lock(&src->page_table_lock);
- do {
- pte_t pte = *src_pte;
- struct page *ptepage;
-
- /* copy_one_pte */
-
- if (pte_none(pte))
- goto cont_copy_pte_range_noset;
- if (!pte_present(pte)) {
- swap_duplicate(pte_to_swp_entry(pte));
- goto cont_copy_pte_range;
- }
- ptepage = pte_page(pte);
- if ((!VALID_PAGE(ptepage)) ||
- PageReserved(ptepage))
- goto cont_copy_pte_range;
-
- /* If it's a COW mapping, write protect it both in the parent and the child */
- if (cow) {
- /* XENO modification: modified ordering here to avoid RaW hazard. */
- pte = *src_pte;
- pte = pte_wrprotect(pte);
- ptep_set_wrprotect(src_pte);
- }
-
- /* If it's a shared mapping, mark it clean in the child */
- if (vma->vm_flags & VM_SHARED)
- pte = pte_mkclean(pte);
- pte = pte_mkold(pte);
- get_page(ptepage);
- dst->rss++;
-
-cont_copy_pte_range: set_pte(dst_pte, pte);
-cont_copy_pte_range_noset: address += PAGE_SIZE;
- if (address >= end)
- goto out_unlock;
- src_pte++;
- dst_pte++;
- } while ((unsigned long)src_pte & PTE_TABLE_MASK);
- spin_unlock(&src->page_table_lock);
-
-cont_copy_pmd_range: src_pmd++;
- dst_pmd++;
- } while ((unsigned long)src_pmd & PMD_TABLE_MASK);
- }
-out_unlock:
- spin_unlock(&src->page_table_lock);
-out:
- return 0;
-nomem:
- return -ENOMEM;
-}
-
-/*
- * Return indicates whether a page was freed so caller can adjust rss
- */
-static inline void forget_pte(pte_t page)
-{
- if (!pte_none(page)) {
- printk("forget_pte: old mapping existed!\n");
- BUG();
- }
-}
-
-static inline int zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address, unsigned long size)
-{
- unsigned long offset;
- pte_t * ptep;
- int freed = 0;
-
- if (pmd_none(*pmd))
- return 0;
- if (pmd_bad(*pmd)) {
- pmd_ERROR(*pmd);
- pmd_clear(pmd);
- return 0;
- }
- ptep = pte_offset(pmd, address);
- offset = address & ~PMD_MASK;
- if (offset + size > PMD_SIZE)
- size = PMD_SIZE - offset;
- size &= PAGE_MASK;
- for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
- pte_t pte = *ptep;
- if (pte_none(pte))
- continue;
- if (pte_present(pte)) {
- struct page *page = pte_page(pte);
- if (VALID_PAGE(page) && !PageReserved(page))
- freed ++;
- /* This will eventually call __free_pte on the pte. */
- tlb_remove_page(tlb, ptep, address + offset);
- } else {
- free_swap_and_cache(pte_to_swp_entry(pte));
- pte_clear(ptep);
- }
- }
-
- return freed;
-}
-
-static inline int zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir, unsigned long address, unsigned long size)
-{
- pmd_t * pmd;
- unsigned long end;
- int freed;
-
- if (pgd_none(*dir))
- return 0;
- if (pgd_bad(*dir)) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
- return 0;
- }
- pmd = pmd_offset(dir, address);
- end = address + size;
- if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
- end = ((address + PGDIR_SIZE) & PGDIR_MASK);
- freed = 0;
- do {
- freed += zap_pte_range(tlb, pmd, address, end - address);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address < end);
- return freed;
-}
-
-/*
- * remove user pages in a given range.
- */
-void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
-{
- mmu_gather_t *tlb;
- pgd_t * dir;
- unsigned long start = address, end = address + size;
- int freed = 0;
-
- dir = pgd_offset(mm, address);
-
- /*
- * This is a long-lived spinlock. That's fine.
- * There's no contention, because the page table
- * lock only protects against kswapd anyway, and
- * even if kswapd happened to be looking at this
- * process we _want_ it to get stuck.
- */
- if (address >= end)
- BUG();
- spin_lock(&mm->page_table_lock);
- flush_cache_range(mm, address, end);
- tlb = tlb_gather_mmu(mm);
-
- do {
- freed += zap_pmd_range(tlb, dir, address, end - address);
- address = (address + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (address && (address < end));
-
- /* this will flush any remaining tlb entries */
- tlb_finish_mmu(tlb, start, end);
-
- /*
- * Update rss for the mm_struct (not necessarily current->mm)
- * Notice that rss is an unsigned long.
- */
- if (mm->rss > freed)
- mm->rss -= freed;
- else
- mm->rss = 0;
- spin_unlock(&mm->page_table_lock);
-}
-
-
-/*
- * Do a quick page-table lookup for a single page.
- */
-static struct page * follow_page(unsigned long address, int write)
-{
- pgd_t *pgd;
- pmd_t *pmd;
- pte_t *ptep, pte;
-
- pgd = pgd_offset(current->mm, address);
- if (pgd_none(*pgd) || pgd_bad(*pgd))
- goto out;
-
- pmd = pmd_offset(pgd, address);
- if (pmd_none(*pmd) || pmd_bad(*pmd))
- goto out;
-
- ptep = pte_offset(pmd, address);
- if (!ptep)
- goto out;
-
- pte = *ptep;
- if (pte_present(pte)) {
- if (!write ||
- (pte_write(pte) && pte_dirty(pte)))
- return pte_page(pte);
- }
-
-out:
- return 0;
-}
-
-/*
- * Given a physical address, is there a useful struct page pointing to
- * it? This may become more complex in the future if we start dealing
- * with IO-aperture pages in kiobufs.
- */
-
-static inline struct page * get_page_map(struct page *page)
-{
- if (!VALID_PAGE(page))
- return 0;
- return page;
-}
-
-/*
- * Force in an entire range of pages from the current process's user VA,
- * and pin them in physical memory.
- */
-
-#define dprintk(x...)
-int map_user_kiobuf(int rw, struct kiobuf *iobuf, unsigned long va, size_t len)
-{
- unsigned long ptr, end;
- int err;
- struct mm_struct * mm;
- struct vm_area_struct * vma = 0;
- struct page * map;
- int i;
- int datain = (rw == READ);
-
- /* Make sure the iobuf is not already mapped somewhere. */
- if (iobuf->nr_pages)
- return -EINVAL;
-
- mm = current->mm;
- dprintk ("map_user_kiobuf: begin\n");
-
- ptr = va & PAGE_MASK;
- end = (va + len + PAGE_SIZE - 1) & PAGE_MASK;
- err = expand_kiobuf(iobuf, (end - ptr) >> PAGE_SHIFT);
- if (err)
- return err;
-
- down_read(&mm->mmap_sem);
-
- err = -EFAULT;
- iobuf->locked = 0;
- iobuf->offset = va & ~PAGE_MASK;
- iobuf->length = len;
-
- i = 0;
-
- /*
- * First of all, try to fault in all of the necessary pages
- */
- while (ptr < end) {
- if (!vma || ptr >= vma->vm_end) {
- vma = find_vma(current->mm, ptr);
- if (!vma)
- goto out_unlock;
- if (vma->vm_start > ptr) {
- if (!(vma->vm_flags & VM_GROWSDOWN))
- goto out_unlock;
- if (expand_stack(vma, ptr))
- goto out_unlock;
- }
- if (((datain) && (!(vma->vm_flags & VM_WRITE))) ||
- (!(vma->vm_flags & VM_READ))) {
- err = -EACCES;
- goto out_unlock;
- }
- }
- spin_lock(&mm->page_table_lock);
- while (!(map = follow_page(ptr, datain))) {
- int ret;
-
- spin_unlock(&mm->page_table_lock);
- ret = handle_mm_fault(current->mm, vma, ptr, datain);
- if (ret <= 0) {
- if (!ret)
- goto out_unlock;
- else {
- err = -ENOMEM;
- goto out_unlock;
- }
- }
- spin_lock(&mm->page_table_lock);
- }
- map = get_page_map(map);
- if (map) {
- flush_dcache_page(map);
- page_cache_get(map);
- } else
- printk (KERN_INFO "Mapped page missing [%d]\n", i);
- spin_unlock(&mm->page_table_lock);
- iobuf->maplist[i] = map;
- iobuf->nr_pages = ++i;
-
- ptr += PAGE_SIZE;
- }
-
- up_read(&mm->mmap_sem);
- dprintk ("map_user_kiobuf: end OK\n");
- return 0;
-
- out_unlock:
- up_read(&mm->mmap_sem);
- unmap_kiobuf(iobuf);
- dprintk ("map_user_kiobuf: end %d\n", err);
- return err;
-}
-
-/*
- * Mark all of the pages in a kiobuf as dirty
- *
- * We need to be able to deal with short reads from disk: if an IO error
- * occurs, the number of bytes read into memory may be less than the
- * size of the kiobuf, so we have to stop marking pages dirty once the
- * requested byte count has been reached.
- */
-
-void mark_dirty_kiobuf(struct kiobuf *iobuf, int bytes)
-{
- int index, offset, remaining;
- struct page *page;
-
- index = iobuf->offset >> PAGE_SHIFT;
- offset = iobuf->offset & ~PAGE_MASK;
- remaining = bytes;
- if (remaining > iobuf->length)
- remaining = iobuf->length;
-
- while (remaining > 0 && index < iobuf->nr_pages) {
- page = iobuf->maplist[index];
-
- if (!PageReserved(page))
- SetPageDirty(page);
-
- remaining -= (PAGE_SIZE - offset);
- offset = 0;
- index++;
- }
-}
-
-/*
- * Unmap all of the pages referenced by a kiobuf. We release the pages,
- * and unlock them if they were locked.
- */
-
-void unmap_kiobuf (struct kiobuf *iobuf)
-{
- int i;
- struct page *map;
-
- for (i = 0; i < iobuf->nr_pages; i++) {
- map = iobuf->maplist[i];
- if (map) {
- if (iobuf->locked)
- UnlockPage(map);
- page_cache_release(map);
- }
- }
-
- iobuf->nr_pages = 0;
- iobuf->locked = 0;
-}
-
-
-/*
- * Lock down all of the pages of a kiovec for IO.
- *
- * If any page is mapped twice in the kiovec, we return the error -EINVAL.
- *
- * The optional wait parameter causes the lock call to block until all
- * pages can be locked if set. If wait==0, the lock operation is
- * aborted if any locked pages are found and -EAGAIN is returned.
- */
-
-int lock_kiovec(int nr, struct kiobuf *iovec[], int wait)
-{
- struct kiobuf *iobuf;
- int i, j;
- struct page *page, **ppage;
- int doublepage = 0;
- int repeat = 0;
-
- repeat:
-
- for (i = 0; i < nr; i++) {
- iobuf = iovec[i];
-
- if (iobuf->locked)
- continue;
-
- ppage = iobuf->maplist;
- for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
- page = *ppage;
- if (!page)
- continue;
-
- if (TryLockPage(page)) {
- while (j--) {
- struct page *tmp = *--ppage;
- if (tmp)
- UnlockPage(tmp);
- }
- goto retry;
- }
- }
- iobuf->locked = 1;
- }
-
- return 0;
-
- retry:
-
- /*
- * We couldn't lock one of the pages. Undo the locking so far,
- * wait on the page we got to, and try again.
- */
-
- unlock_kiovec(nr, iovec);
- if (!wait)
- return -EAGAIN;
-
- /*
- * Did the release also unlock the page we got stuck on?
- */
- if (!PageLocked(page)) {
- /*
- * If so, we may well have the page mapped twice
- * in the IO address range. Bad news. Of
- * course, it _might_ just be a coincidence,
- * but if it happens more than once, chances
- * are we have a double-mapped page.
- */
- if (++doublepage >= 3)
- return -EINVAL;
-
- /* Try again... */
- wait_on_page(page);
- }
-
- if (++repeat < 16)
- goto repeat;
- return -EAGAIN;
-}
-
-/*
- * Unlock all of the pages of a kiovec after IO.
- */
-
-int unlock_kiovec(int nr, struct kiobuf *iovec[])
-{
- struct kiobuf *iobuf;
- int i, j;
- struct page *page, **ppage;
-
- for (i = 0; i < nr; i++) {
- iobuf = iovec[i];
-
- if (!iobuf->locked)
- continue;
- iobuf->locked = 0;
-
- ppage = iobuf->maplist;
- for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
- page = *ppage;
- if (!page)
- continue;
- UnlockPage(page);
- }
- }
- return 0;
-}
-
-static inline void zeromap_pte_range(pte_t * pte, unsigned long address,
- unsigned long size, pgprot_t prot)
-{
- unsigned long end;
-
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address), prot));
- pte_t oldpage = ptep_get_and_clear(pte);
- set_pte(pte, zero_pte);
- forget_pte(oldpage);
- address += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
-}
-
-static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address,
- unsigned long size, pgprot_t prot)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- do {
- pte_t * pte = pte_alloc(mm, pmd, address);
- if (!pte)
- return -ENOMEM;
- zeromap_pte_range(pte, address, end - address, prot);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
- return 0;
-}
-
-int zeromap_page_range(unsigned long address, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = address;
- unsigned long end = address + size;
- struct mm_struct *mm = current->mm;
-
- dir = pgd_offset(mm, address);
- flush_cache_range(mm, beg, end);
- if (address >= end)
- BUG();
-
- spin_lock(&mm->page_table_lock);
- do {
- pmd_t *pmd = pmd_alloc(mm, dir, address);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = zeromap_pmd_range(mm, pmd, address, end - address, prot);
- if (error)
- break;
- address = (address + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (address && (address < end));
- spin_unlock(&mm->page_table_lock);
- flush_tlb_range(mm, beg, end);
- return error;
-}
-
-/*
- * maps a range of physical memory into the requested pages. the old
- * mappings are removed. any references to nonexistent pages results
- * in null mappings (currently treated as "copy-on-access")
- */
-static inline void remap_pte_range(pte_t * pte, unsigned long address, unsigned long size,
- unsigned long phys_addr, pgprot_t prot)
-{
- unsigned long end;
-
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- struct page *page;
- pte_t oldpage;
- oldpage = ptep_get_and_clear(pte);
-
- page = virt_to_page(__va(phys_addr));
- if ((!VALID_PAGE(page)) || PageReserved(page))
- set_pte(pte, mk_pte_phys(phys_addr, prot));
- forget_pte(oldpage);
- address += PAGE_SIZE;
- phys_addr += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
-}
-
-static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long phys_addr, pgprot_t prot)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- phys_addr -= address;
- do {
- pte_t * pte = pte_alloc(mm, pmd, address);
- if (!pte)
- return -ENOMEM;
- remap_pte_range(pte, address, end - address, address + phys_addr, prot);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
- return 0;
-}
-
-/* Note: this is only safe if the mm semaphore is held when called. */
-int remap_page_range(unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
- struct mm_struct *mm = current->mm;
-
- phys_addr -= from;
- dir = pgd_offset(mm, from);
- flush_cache_range(mm, beg, end);
- if (from >= end)
- BUG();
-
- spin_lock(&mm->page_table_lock);
- do {
- pmd_t *pmd = pmd_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = remap_pmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
- if (error)
- break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (from && (from < end));
- spin_unlock(&mm->page_table_lock);
- flush_tlb_range(mm, beg, end);
- return error;
-}
-
-/*
- * Establish a new mapping:
- * - flush the old one
- * - update the page tables
- * - inform the TLB about the new one
- *
- * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
- */
-static inline void establish_pte(struct vm_area_struct * vma, unsigned long address, pte_t *page_table, pte_t entry)
-{
- set_pte(page_table, entry);
- flush_tlb_page(vma, address);
- update_mmu_cache(vma, address, entry);
-}
-
-/*
- * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
- */
-static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address,
- pte_t *page_table)
-{
- flush_page_to_ram(new_page);
- flush_cache_page(vma, address);
- establish_pte(vma, address, page_table, pte_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot))));
-}
-
-/*
- * This routine handles present pages, when users try to write
- * to a shared page. It is done by copying the page to a new address
- * and decrementing the shared-page counter for the old page.
- *
- * Goto-purists beware: the only reason for goto's here is that it results
- * in better assembly code.. The "default" path will see no jumps at all.
- *
- * Note that this routine assumes that the protection checks have been
- * done by the caller (the low-level page fault routine in most cases).
- * Thus we can safely just mark it writable once we've done any necessary
- * COW.
- *
- * We also mark the page dirty at this point even though the page will
- * change only once the write actually happens. This avoids a few races,
- * and potentially makes it more efficient.
- *
- * We hold the mm semaphore and the page_table_lock on entry and exit
- * with the page_table_lock released.
- */
-static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
- unsigned long address, pte_t *page_table, pte_t pte)
-{
- struct page *old_page, *new_page;
-
- old_page = pte_page(pte);
- if (!VALID_PAGE(old_page))
- goto bad_wp_page;
-
- if (!TryLockPage(old_page)) {
- int reuse = can_share_swap_page(old_page);
- unlock_page(old_page);
- if (reuse) {
- flush_cache_page(vma, address);
- establish_pte(vma, address, page_table, pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
- spin_unlock(&mm->page_table_lock);
- return 1; /* Minor fault */
- }
- }
-
- /*
- * Ok, we need to copy. Oh, well..
- */
- page_cache_get(old_page);
- spin_unlock(&mm->page_table_lock);
-
- new_page = alloc_page(GFP_HIGHUSER);
- if (!new_page)
- goto no_mem;
- copy_cow_page(old_page,new_page,address);
-
- /*
- * Re-check the pte - we dropped the lock
- */
- spin_lock(&mm->page_table_lock);
- if (pte_same(*page_table, pte)) {
- if (PageReserved(old_page))
- ++mm->rss;
- break_cow(vma, new_page, address, page_table);
- lru_cache_add(new_page);
-
- /* Free the old page.. */
- new_page = old_page;
- }
- spin_unlock(&mm->page_table_lock);
- page_cache_release(new_page);
- page_cache_release(old_page);
- return 1; /* Minor fault */
-
-bad_wp_page:
- spin_unlock(&mm->page_table_lock);
- printk("do_wp_page: bogus page at address %08lx (page 0x%lx)\n",address,(unsigned long)old_page);
- return -1;
-no_mem:
- page_cache_release(old_page);
- return -1;
-}
-
-static void vmtruncate_list(struct vm_area_struct *mpnt, unsigned long pgoff)
-{
- do {
- struct mm_struct *mm = mpnt->vm_mm;
- unsigned long start = mpnt->vm_start;
- unsigned long end = mpnt->vm_end;
- unsigned long len = end - start;
- unsigned long diff;
-
- /* mapping wholly truncated? */
- if (mpnt->vm_pgoff >= pgoff) {
- zap_page_range(mm, start, len);
- continue;
- }
-
- /* mapping wholly unaffected? */
- len = len >> PAGE_SHIFT;
- diff = pgoff - mpnt->vm_pgoff;
- if (diff >= len)
- continue;
-
- /* Ok, partially affected.. */
- start += diff << PAGE_SHIFT;
- len = (len - diff) << PAGE_SHIFT;
- zap_page_range(mm, start, len);
- } while ((mpnt = mpnt->vm_next_share) != NULL);
-}
-
-/*
- * Handle all mappings that got truncated by a "truncate()"
- * system call.
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page. Ugly, but necessary.
- */
-int vmtruncate(struct inode * inode, loff_t offset)
-{
- unsigned long pgoff;
- struct address_space *mapping = inode->i_mapping;
- unsigned long limit;
-
- if (inode->i_size < offset)
- goto do_expand;
- inode->i_size = offset;
- spin_lock(&mapping->i_shared_lock);
- if (!mapping->i_mmap && !mapping->i_mmap_shared)
- goto out_unlock;
-
- pgoff = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (mapping->i_mmap != NULL)
- vmtruncate_list(mapping->i_mmap, pgoff);
- if (mapping->i_mmap_shared != NULL)
- vmtruncate_list(mapping->i_mmap_shared, pgoff);
-
-out_unlock:
- spin_unlock(&mapping->i_shared_lock);
- truncate_inode_pages(mapping, offset);
- goto out_truncate;
-
-do_expand:
- limit = current->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY) {
- if (inode->i_size >= limit) {
- send_sig(SIGXFSZ, current, 0);
- goto out;
- }
- if (offset > limit) {
- send_sig(SIGXFSZ, current, 0);
- offset = limit;
- }
- }
- inode->i_size = offset;
-
-out_truncate:
- if (inode->i_op && inode->i_op->truncate) {
- lock_kernel();
- inode->i_op->truncate(inode);
- unlock_kernel();
- }
-out:
- return 0;
-}
-
-/*
- * Primitive swap readahead code. We simply read an aligned block of
- * (1 << page_cluster) entries in the swap area. This method is chosen
- * because it doesn't cost us any seek time. We also make sure to queue
- * the 'original' request together with the readahead ones...
- */
-void swapin_readahead(swp_entry_t entry)
-{
- int i, num;
- struct page *new_page;
- unsigned long offset;
-
- /*
- * Get the number of handles we should do readahead io to.
- */
- num = valid_swaphandles(entry, &offset);
- for (i = 0; i < num; offset++, i++) {
- /* Ok, do the async read-ahead now */
- new_page = read_swap_cache_async(SWP_ENTRY(SWP_TYPE(entry), offset));
- if (!new_page)
- break;
- page_cache_release(new_page);
- }
- return;
-}
-
-/*
- * We hold the mm semaphore and the page_table_lock on entry and
- * should release the pagetable lock on exit..
- */
-static int do_swap_page(struct mm_struct * mm,
- struct vm_area_struct * vma, unsigned long address,
- pte_t * page_table, pte_t orig_pte, int write_access)
-{
- struct page *page;
- swp_entry_t entry = pte_to_swp_entry(orig_pte);
- pte_t pte;
- int ret = 1;
-
- spin_unlock(&mm->page_table_lock);
- page = lookup_swap_cache(entry);
- if (!page) {
- swapin_readahead(entry);
- page = read_swap_cache_async(entry);
- if (!page) {
- /*
- * Back out if somebody else faulted in this pte while
- * we released the page table lock.
- */
- int retval;
- spin_lock(&mm->page_table_lock);
- retval = pte_same(*page_table, orig_pte) ? -1 : 1;
- spin_unlock(&mm->page_table_lock);
- return retval;
- }
-
- /* Had to read the page from swap area: Major fault */
- ret = 2;
- }
-
- lock_page(page);
-
- /*
- * Back out if somebody else faulted in this pte while we
- * released the page table lock.
- */
- spin_lock(&mm->page_table_lock);
- if (!pte_same(*page_table, orig_pte)) {
- spin_unlock(&mm->page_table_lock);
- unlock_page(page);
- page_cache_release(page);
- return 1;
- }
-
- /* The page isn't present yet, go ahead with the fault. */
-
- swap_free(entry);
- if (vm_swap_full())
- remove_exclusive_swap_page(page);
-
- mm->rss++;
- pte = mk_pte(page, vma->vm_page_prot);
- if (write_access && can_share_swap_page(page))
- pte = pte_mkdirty(pte_mkwrite(pte));
- unlock_page(page);
-
- flush_page_to_ram(page);
- flush_icache_page(vma, page);
- set_pte(page_table, pte);
-
- /* No need to invalidate - it was non-present before */
- update_mmu_cache(vma, address, pte);
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
- return ret;
-}
-
-/*
- * We are called with the MM semaphore and page_table_lock
- * spinlock held to protect against concurrent faults in
- * multithreaded programs.
- */
-static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, int write_access, unsigned long addr)
-{
- pte_t entry;
-
- /* Read-only mapping of ZERO_PAGE. */
- entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
-
- /* ..except if it's a write access */
- if (write_access) {
- struct page *page;
-
- /* Allocate our own private page. */
- spin_unlock(&mm->page_table_lock);
-
- page = alloc_page(GFP_HIGHUSER);
- if (!page)
- goto no_mem;
- clear_user_highpage(page, addr);
-
- spin_lock(&mm->page_table_lock);
- if (!pte_none(*page_table)) {
- page_cache_release(page);
- spin_unlock(&mm->page_table_lock);
- return 1;
- }
- mm->rss++;
- flush_page_to_ram(page);
- entry = pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
- lru_cache_add(page);
- }
-
- set_pte(page_table, entry);
-
- /* No need to invalidate - it was non-present before */
- update_mmu_cache(vma, addr, entry);
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
- return 1; /* Minor fault */
-
-no_mem:
- return -1;
-}
-
-/*
- * do_no_page() tries to create a new page mapping. It aggressively
- * tries to share with existing pages, but makes a separate copy if
- * the "write_access" parameter is true in order to avoid the next
- * page fault.
- *
- * As this is called only for pages that do not currently exist, we
- * do not need to flush old virtual caches or the TLB.
- *
- * This is called with the MM semaphore held and the page table
- * spinlock held. Exit with the spinlock released.
- */
-static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
- unsigned long address, int write_access, pte_t *page_table)
-{
- struct page * new_page;
- pte_t entry;
-
- if (!vma->vm_ops || !vma->vm_ops->nopage)
- return do_anonymous_page(mm, vma, page_table, write_access, address);
- spin_unlock(&mm->page_table_lock);
-
- new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
-
- if (new_page == NULL) /* no page was available -- SIGBUS */
- return 0;
- if (new_page == NOPAGE_OOM)
- return -1;
-
- /*
- * Should we do an early C-O-W break?
- */
- if (write_access && !(vma->vm_flags & VM_SHARED)) {
- struct page * page = alloc_page(GFP_HIGHUSER);
- if (!page)
- return -1;
- copy_highpage(page, new_page);
- page_cache_release(new_page);
- lru_cache_add(page);
- new_page = page;
- }
-
- spin_lock(&mm->page_table_lock);
- /*
- * This silly early PAGE_DIRTY setting removes a race
- * due to the bad i386 page protection. But it's valid
- * for other architectures too.
- *
- * Note that if write_access is true, we either now have
- * an exclusive copy of the page, or this is a shared mapping,
- * so we can make it writable and dirty to avoid having to
- * handle that later.
- */
- /* Only go through if we didn't race with anybody else... */
- if (pte_none(*page_table)) {
- ++mm->rss;
- flush_page_to_ram(new_page);
- flush_icache_page(vma, new_page);
- entry = mk_pte(new_page, vma->vm_page_prot);
- if (write_access)
- entry = pte_mkwrite(pte_mkdirty(entry));
- set_pte(page_table, entry);
- } else {
- /* One of our sibling threads was faster, back out. */
- page_cache_release(new_page);
- spin_unlock(&mm->page_table_lock);
- return 1;
- }
-
- /* no need to invalidate: a not-present page shouldn't be cached */
- update_mmu_cache(vma, address, entry);
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
- return 2; /* Major fault */
-}
-
-/*
- * These routines also need to handle stuff like marking pages dirty
- * and/or accessed for architectures that don't do it in hardware (most
- * RISC architectures). The early dirtying is also good on the i386.
- *
- * There is also a hook called "update_mmu_cache()" that architectures
- * with external mmu caches can use to update those (ie the Sparc or
- * PowerPC hashed page tables that act as extended TLBs).
- *
- * Note the "page_table_lock". It is to protect against kswapd removing
- * pages from under us. Note that kswapd only ever _removes_ pages, never
- * adds them. As such, once we have noticed that the page is not present,
- * we can drop the lock early.
- *
- * The adding of pages is protected by the MM semaphore (which we hold),
- * so we don't need to worry about a page being suddenly been added into
- * our VM.
- *
- * We enter with the pagetable spinlock held, we are supposed to
- * release it when done.
- */
-static inline int handle_pte_fault(struct mm_struct *mm,
- struct vm_area_struct * vma, unsigned long address,
- int write_access, pte_t * pte)
-{
- pte_t entry;
-
- entry = *pte;
- if (!pte_present(entry)) {
- /*
- * If it truly wasn't present, we know that kswapd
- * and the PTE updates will not touch it later. So
- * drop the lock.
- */
- if (pte_none(entry))
- return do_no_page(mm, vma, address, write_access, pte);
- return do_swap_page(mm, vma, address, pte, entry, write_access);
- }
-
- if (write_access) {
- if (!pte_write(entry))
- return do_wp_page(mm, vma, address, pte, entry);
-
- entry = pte_mkdirty(entry);
- }
- entry = pte_mkyoung(entry);
- establish_pte(vma, address, pte, entry);
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
- return 1;
-}
-
-/*
- * By the time we get here, we already hold the mm semaphore
- */
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
- unsigned long address, int write_access)
-{
- pgd_t *pgd;
- pmd_t *pmd;
-
- current->state = TASK_RUNNING;
- pgd = pgd_offset(mm, address);
-
- /*
- * We need the page table lock to synchronize with kswapd
- * and the SMP-safe atomic PTE updates.
- */
- spin_lock(&mm->page_table_lock);
- pmd = pmd_alloc(mm, pgd, address);
-
- if (pmd) {
- pte_t * pte = pte_alloc(mm, pmd, address);
- if (pte)
- return handle_pte_fault(mm, vma, address, write_access, pte);
- }
- spin_unlock(&mm->page_table_lock);
- return -1;
-}
-
-/*
- * Allocate page middle directory.
- *
- * We've already handled the fast-path in-line, and we own the
- * page table lock.
- *
- * On a two-level page table, this ends up actually being entirely
- * optimized away.
- */
-pmd_t *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
-{
- pmd_t *new;
-
- /* "fast" allocation can happen without dropping the lock.. */
- new = pmd_alloc_one_fast(mm, address);
- if (!new) {
- spin_unlock(&mm->page_table_lock);
- new = pmd_alloc_one(mm, address);
- spin_lock(&mm->page_table_lock);
- if (!new)
- return NULL;
-
- /*
- * Because we dropped the lock, we should re-check the
- * entry, as somebody else could have populated it..
- */
- if (!pgd_none(*pgd)) {
- pmd_free(new);
- goto out;
- }
- }
- pgd_populate(mm, pgd, new);
-out:
- return pmd_offset(pgd, address);
-}
-
-/*
- * Allocate the page table directory.
- *
- * We've already handled the fast-path in-line, and we own the
- * page table lock.
- */
-pte_t *pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
-{
- if (pmd_none(*pmd)) {
- pte_t *new;
-
- /* "fast" allocation can happen without dropping the lock.. */
- new = pte_alloc_one_fast(mm, address);
- if (!new) {
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
- new = pte_alloc_one(mm, address);
- spin_lock(&mm->page_table_lock);
- if (!new)
- return NULL;
-
- /*
- * Because we dropped the lock, we should re-check the
- * entry, as somebody else could have populated it..
- */
- if (!pmd_none(*pmd)) {
- pte_free(new);
- goto out;
- }
- }
- pmd_populate(mm, pmd, new);
- }
-out:
- return pte_offset(pmd, address);
-}
-
-/*
- * Simplistic page force-in..
- */
-int make_pages_present(unsigned long addr, unsigned long end)
-{
- int write;
- struct mm_struct *mm = current->mm;
- struct vm_area_struct * vma;
-
- vma = find_vma(mm, addr);
- write = (vma->vm_flags & VM_WRITE) != 0;
- if (addr >= end)
- BUG();
- do {
- if (handle_mm_fault(mm, vma, addr, write) < 0)
- return -1;
- addr += PAGE_SIZE;
- } while (addr < end);
- return 0;
-}
+++ /dev/null
-/*
- * linux/mm/remap.c
- *
- * (C) Copyright 1996 Linus Torvalds
- */
-
-#include <linux/slab.h>
-#include <linux/smp_lock.h>
-#include <linux/shm.h>
-#include <linux/mman.h>
-#include <linux/swap.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
-
-extern int vm_enough_memory(long pages);
-
-static inline pte_t *get_one_pte(struct mm_struct *mm, unsigned long addr)
-{
- pgd_t * pgd;
- pmd_t * pmd;
- pte_t * pte = NULL;
-
- pgd = pgd_offset(mm, addr);
- if (pgd_none(*pgd))
- goto end;
- if (pgd_bad(*pgd)) {
- pgd_ERROR(*pgd);
- pgd_clear(pgd);
- goto end;
- }
-
- pmd = pmd_offset(pgd, addr);
- if (pmd_none(*pmd))
- goto end;
- if (pmd_bad(*pmd)) {
- pmd_ERROR(*pmd);
- pmd_clear(pmd);
- goto end;
- }
-
- pte = pte_offset(pmd, addr);
- if (pte_none(*pte))
- pte = NULL;
-end:
- return pte;
-}
-
-static inline pte_t *alloc_one_pte(struct mm_struct *mm, unsigned long addr)
-{
- pmd_t * pmd;
- pte_t * pte = NULL;
-
- pmd = pmd_alloc(mm, pgd_offset(mm, addr), addr);
- if (pmd)
- pte = pte_alloc(mm, pmd, addr);
- return pte;
-}
-
-static inline int copy_one_pte(struct mm_struct *mm, pte_t * src, pte_t * dst)
-{
- int error = 0;
- pte_t pte;
-
- if (!pte_none(*src)) {
- pte = ptep_get_and_clear(src);
- if (!dst) {
- /* No dest? We must put it back. */
- dst = src;
- error++;
- }
- set_pte(dst, pte);
- }
- return error;
-}
-
-static int move_one_page(struct mm_struct *mm, unsigned long old_addr, unsigned long new_addr)
-{
- int error = 0;
- pte_t * src;
-
- spin_lock(&mm->page_table_lock);
- src = get_one_pte(mm, old_addr);
- if (src)
- error = copy_one_pte(mm, src, alloc_one_pte(mm, new_addr));
- spin_unlock(&mm->page_table_lock);
- return error;
-}
-
-static int move_page_tables(struct mm_struct * mm,
- unsigned long new_addr, unsigned long old_addr, unsigned long len)
-{
- unsigned long offset = len;
-
- flush_cache_range(mm, old_addr, old_addr + len);
-
- /*
- * This is not the clever way to do this, but we're taking the
- * easy way out on the assumption that most remappings will be
- * only a few pages.. This also makes error recovery easier.
- */
- while (offset) {
- offset -= PAGE_SIZE;
- if (move_one_page(mm, old_addr + offset, new_addr + offset))
- goto oops_we_failed;
- }
- flush_tlb_range(mm, old_addr, old_addr + len);
- return 0;
-
- /*
- * Ok, the move failed because we didn't have enough pages for
- * the new page table tree. This is unlikely, but we have to
- * take the possibility into account. In that case we just move
- * all the pages back (this will work, because we still have
- * the old page tables)
- */
-oops_we_failed:
- XENO_flush_page_update_queue();
- flush_cache_range(mm, new_addr, new_addr + len);
- while ((offset += PAGE_SIZE) < len)
- move_one_page(mm, new_addr + offset, old_addr + offset);
- XENO_flush_page_update_queue();
- zap_page_range(mm, new_addr, len);
- return -1;
-}
-
-static inline unsigned long move_vma(struct vm_area_struct * vma,
- unsigned long addr, unsigned long old_len, unsigned long new_len,
- unsigned long new_addr)
-{
- struct mm_struct * mm = vma->vm_mm;
- struct vm_area_struct * new_vma, * next, * prev;
- int allocated_vma;
-
- new_vma = NULL;
- next = find_vma_prev(mm, new_addr, &prev);
- if (next) {
- if (prev && prev->vm_end == new_addr &&
- can_vma_merge(prev, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
- spin_lock(&mm->page_table_lock);
- prev->vm_end = new_addr + new_len;
- spin_unlock(&mm->page_table_lock);
- new_vma = prev;
- if (next != prev->vm_next)
- BUG();
- if (prev->vm_end == next->vm_start && can_vma_merge(next, prev->vm_flags)) {
- spin_lock(&mm->page_table_lock);
- prev->vm_end = next->vm_end;
- __vma_unlink(mm, next, prev);
- spin_unlock(&mm->page_table_lock);
-
- mm->map_count--;
- kmem_cache_free(vm_area_cachep, next);
- }
- } else if (next->vm_start == new_addr + new_len &&
- can_vma_merge(next, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
- spin_lock(&mm->page_table_lock);
- next->vm_start = new_addr;
- spin_unlock(&mm->page_table_lock);
- new_vma = next;
- }
- } else {
- prev = find_vma(mm, new_addr-1);
- if (prev && prev->vm_end == new_addr &&
- can_vma_merge(prev, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
- spin_lock(&mm->page_table_lock);
- prev->vm_end = new_addr + new_len;
- spin_unlock(&mm->page_table_lock);
- new_vma = prev;
- }
- }
-
- allocated_vma = 0;
- if (!new_vma) {
- new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
- if (!new_vma)
- goto out;
- allocated_vma = 1;
- }
-
- if (!move_page_tables(current->mm, new_addr, addr, old_len)) {
- if (allocated_vma) {
- *new_vma = *vma;
- new_vma->vm_start = new_addr;
- new_vma->vm_end = new_addr+new_len;
- new_vma->vm_pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
- new_vma->vm_raend = 0;
- if (new_vma->vm_file)
- get_file(new_vma->vm_file);
- if (new_vma->vm_ops && new_vma->vm_ops->open)
- new_vma->vm_ops->open(new_vma);
- insert_vm_struct(current->mm, new_vma);
- }
- do_munmap(current->mm, addr, old_len);
- current->mm->total_vm += new_len >> PAGE_SHIFT;
- if (new_vma->vm_flags & VM_LOCKED) {
- current->mm->locked_vm += new_len >> PAGE_SHIFT;
- make_pages_present(new_vma->vm_start,
- new_vma->vm_end);
- }
- return new_addr;
- }
- if (allocated_vma)
- kmem_cache_free(vm_area_cachep, new_vma);
- out:
- return -ENOMEM;
-}
-
-/*
- * Expand (or shrink) an existing mapping, potentially moving it at the
- * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
- *
- * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
- * This option implies MREMAP_MAYMOVE.
- */
-unsigned long do_mremap(unsigned long addr,
- unsigned long old_len, unsigned long new_len,
- unsigned long flags, unsigned long new_addr)
-{
- struct vm_area_struct *vma;
- unsigned long ret = -EINVAL;
-
- if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
- goto out;
-
- if (addr & ~PAGE_MASK)
- goto out;
-
- old_len = PAGE_ALIGN(old_len);
- new_len = PAGE_ALIGN(new_len);
-
- /* new_addr is only valid if MREMAP_FIXED is specified */
- if (flags & MREMAP_FIXED) {
- if (new_addr & ~PAGE_MASK)
- goto out;
- if (!(flags & MREMAP_MAYMOVE))
- goto out;
-
- if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
- goto out;
-
- /* Check if the location we're moving into overlaps the
- * old location at all, and fail if it does.
- */
- if ((new_addr <= addr) && (new_addr+new_len) > addr)
- goto out;
-
- if ((addr <= new_addr) && (addr+old_len) > new_addr)
- goto out;
-
- do_munmap(current->mm, new_addr, new_len);
- }
-
- /*
- * Always allow a shrinking remap: that just unmaps
- * the unnecessary pages..
- */
- ret = addr;
- if (old_len >= new_len) {
- do_munmap(current->mm, addr+new_len, old_len - new_len);
- if (!(flags & MREMAP_FIXED) || (new_addr == addr))
- goto out;
- }
-
- /*
- * Ok, we need to grow.. or relocate.
- */
- ret = -EFAULT;
- vma = find_vma(current->mm, addr);
- if (!vma || vma->vm_start > addr)
- goto out;
- /* We can't remap across vm area boundaries */
- if (old_len > vma->vm_end - addr)
- goto out;
- if (vma->vm_flags & VM_DONTEXPAND) {
- if (new_len > old_len)
- goto out;
- }
- if (vma->vm_flags & VM_LOCKED) {
- unsigned long locked = current->mm->locked_vm << PAGE_SHIFT;
- locked += new_len - old_len;
- ret = -EAGAIN;
- if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
- goto out;
- }
- ret = -ENOMEM;
- if ((current->mm->total_vm << PAGE_SHIFT) + (new_len - old_len)
- > current->rlim[RLIMIT_AS].rlim_cur)
- goto out;
- /* Private writable mapping? Check memory availability.. */
- if ((vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
- !(flags & MAP_NORESERVE) &&
- !vm_enough_memory((new_len - old_len) >> PAGE_SHIFT))
- goto out;
-
- /* old_len exactly to the end of the area..
- * And we're not relocating the area.
- */
- if (old_len == vma->vm_end - addr &&
- !((flags & MREMAP_FIXED) && (addr != new_addr)) &&
- (old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
- unsigned long max_addr = TASK_SIZE;
- if (vma->vm_next)
- max_addr = vma->vm_next->vm_start;
- /* can we just expand the current mapping? */
- if (max_addr - addr >= new_len) {
- int pages = (new_len - old_len) >> PAGE_SHIFT;
- spin_lock(&vma->vm_mm->page_table_lock);
- vma->vm_end = addr + new_len;
- spin_unlock(&vma->vm_mm->page_table_lock);
- current->mm->total_vm += pages;
- if (vma->vm_flags & VM_LOCKED) {
- current->mm->locked_vm += pages;
- make_pages_present(addr + old_len,
- addr + new_len);
- }
- ret = addr;
- goto out;
- }
- }
-
- /*
- * We weren't able to just expand or shrink the area,
- * we need to create a new one and move it..
- */
- ret = -ENOMEM;
- if (flags & MREMAP_MAYMOVE) {
- if (!(flags & MREMAP_FIXED)) {
- unsigned long map_flags = 0;
- if (vma->vm_flags & VM_SHARED)
- map_flags |= MAP_SHARED;
-
- new_addr = get_unmapped_area(vma->vm_file, 0, new_len, vma->vm_pgoff, map_flags);
- ret = new_addr;
- if (new_addr & ~PAGE_MASK)
- goto out;
- }
- ret = move_vma(vma, addr, old_len, new_len, new_addr);
- }
-out:
- return ret;
-}
-
-asmlinkage unsigned long sys_mremap(unsigned long addr,
- unsigned long old_len, unsigned long new_len,
- unsigned long flags, unsigned long new_addr)
-{
- unsigned long ret;
-
- down_write(¤t->mm->mmap_sem);
- ret = do_mremap(addr, old_len, new_len, flags, new_addr);
- up_write(¤t->mm->mmap_sem);
- return ret;
-}
+++ /dev/null
-/*
- * linux/mm/swapfile.c
- *
- * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
- * Swap reorganised 29.12.95, Stephen Tweedie
- */
-
-#include <linux/slab.h>
-#include <linux/smp_lock.h>
-#include <linux/kernel_stat.h>
-#include <linux/swap.h>
-#include <linux/swapctl.h>
-#include <linux/blkdev.h> /* for blk_size */
-#include <linux/vmalloc.h>
-#include <linux/pagemap.h>
-#include <linux/shm.h>
-#include <linux/compiler.h>
-
-#include <asm/pgtable.h>
-
-spinlock_t swaplock = SPIN_LOCK_UNLOCKED;
-unsigned int nr_swapfiles;
-int total_swap_pages;
-static int swap_overflow;
-
-static const char Bad_file[] = "Bad swap file entry ";
-static const char Unused_file[] = "Unused swap file entry ";
-static const char Bad_offset[] = "Bad swap offset entry ";
-static const char Unused_offset[] = "Unused swap offset entry ";
-
-struct swap_list_t swap_list = {-1, -1};
-
-struct swap_info_struct swap_info[MAX_SWAPFILES];
-
-#define SWAPFILE_CLUSTER 256
-
-static inline int scan_swap_map(struct swap_info_struct *si)
-{
- unsigned long offset;
- /*
- * We try to cluster swap pages by allocating them
- * sequentially in swap. Once we've allocated
- * SWAPFILE_CLUSTER pages this way, however, we resort to
- * first-free allocation, starting a new cluster. This
- * prevents us from scattering swap pages all over the entire
- * swap partition, so that we reduce overall disk seek times
- * between swap pages. -- sct */
- if (si->cluster_nr) {
- while (si->cluster_next <= si->highest_bit) {
- offset = si->cluster_next++;
- if (si->swap_map[offset])
- continue;
- si->cluster_nr--;
- goto got_page;
- }
- }
- si->cluster_nr = SWAPFILE_CLUSTER;
-
- /* try to find an empty (even not aligned) cluster. */
- offset = si->lowest_bit;
- check_next_cluster:
- if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
- {
- int nr;
- for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
- if (si->swap_map[nr])
- {
- offset = nr+1;
- goto check_next_cluster;
- }
- /* We found a completly empty cluster, so start
- * using it.
- */
- goto got_page;
- }
- /* No luck, so now go finegrined as usual. -Andrea */
- for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) {
- if (si->swap_map[offset])
- continue;
- si->lowest_bit = offset+1;
- got_page:
- if (offset == si->lowest_bit)
- si->lowest_bit++;
- if (offset == si->highest_bit)
- si->highest_bit--;
- if (si->lowest_bit > si->highest_bit) {
- si->lowest_bit = si->max;
- si->highest_bit = 0;
- }
- si->swap_map[offset] = 1;
- nr_swap_pages--;
- si->cluster_next = offset+1;
- return offset;
- }
- si->lowest_bit = si->max;
- si->highest_bit = 0;
- return 0;
-}
-
-swp_entry_t get_swap_page(void)
-{
- struct swap_info_struct * p;
- unsigned long offset;
- swp_entry_t entry;
- int type, wrapped = 0;
-
- entry.val = 0; /* Out of memory */
- swap_list_lock();
- type = swap_list.next;
- if (type < 0)
- goto out;
- if (nr_swap_pages <= 0)
- goto out;
-
- while (1) {
- p = &swap_info[type];
- if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
- swap_device_lock(p);
- offset = scan_swap_map(p);
- swap_device_unlock(p);
- if (offset) {
- entry = SWP_ENTRY(type,offset);
- type = swap_info[type].next;
- if (type < 0 ||
- p->prio != swap_info[type].prio) {
- swap_list.next = swap_list.head;
- } else {
- swap_list.next = type;
- }
- goto out;
- }
- }
- type = p->next;
- if (!wrapped) {
- if (type < 0 || p->prio != swap_info[type].prio) {
- type = swap_list.head;
- wrapped = 1;
- }
- } else
- if (type < 0)
- goto out; /* out of swap space */
- }
-out:
- swap_list_unlock();
- return entry;
-}
-
-static struct swap_info_struct * swap_info_get(swp_entry_t entry)
-{
- struct swap_info_struct * p;
- unsigned long offset, type;
-
- if (!entry.val)
- goto out;
- type = SWP_TYPE(entry);
- if (type >= nr_swapfiles)
- goto bad_nofile;
- p = & swap_info[type];
- if (!(p->flags & SWP_USED))
- goto bad_device;
- offset = SWP_OFFSET(entry);
- if (offset >= p->max)
- goto bad_offset;
- if (!p->swap_map[offset])
- goto bad_free;
- swap_list_lock();
- if (p->prio > swap_info[swap_list.next].prio)
- swap_list.next = type;
- swap_device_lock(p);
- return p;
-
-bad_free:
- printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
- goto out;
-bad_offset:
- printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
- goto out;
-bad_device:
- printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
- goto out;
-bad_nofile:
- printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
-out:
- return NULL;
-}
-
-static void swap_info_put(struct swap_info_struct * p)
-{
- swap_device_unlock(p);
- swap_list_unlock();
-}
-
-static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
-{
- int count = p->swap_map[offset];
-
- if (count < SWAP_MAP_MAX) {
- count--;
- p->swap_map[offset] = count;
- if (!count) {
- if (offset < p->lowest_bit)
- p->lowest_bit = offset;
- if (offset > p->highest_bit)
- p->highest_bit = offset;
- nr_swap_pages++;
- }
- }
- return count;
-}
-
-/*
- * Caller has made sure that the swapdevice corresponding to entry
- * is still around or has not been recycled.
- */
-void swap_free(swp_entry_t entry)
-{
- struct swap_info_struct * p;
-
- p = swap_info_get(entry);
- if (p) {
- swap_entry_free(p, SWP_OFFSET(entry));
- swap_info_put(p);
- }
-}
-
-/*
- * Check if we're the only user of a swap page,
- * when the page is locked.
- */
-static int exclusive_swap_page(struct page *page)
-{
- int retval = 0;
- struct swap_info_struct * p;
- swp_entry_t entry;
-
- entry.val = page->index;
- p = swap_info_get(entry);
- if (p) {
- /* Is the only swap cache user the cache itself? */
- if (p->swap_map[SWP_OFFSET(entry)] == 1) {
- /* Recheck the page count with the pagecache lock held.. */
- spin_lock(&pagecache_lock);
- if (page_count(page) - !!page->buffers == 2)
- retval = 1;
- spin_unlock(&pagecache_lock);
- }
- swap_info_put(p);
- }
- return retval;
-}
-
-/*
- * We can use this swap cache entry directly
- * if there are no other references to it.
- *
- * Here "exclusive_swap_page()" does the real
- * work, but we opportunistically check whether
- * we need to get all the locks first..
- */
-int can_share_swap_page(struct page *page)
-{
- int retval = 0;
-
- if (!PageLocked(page))
- BUG();
- switch (page_count(page)) {
- case 3:
- if (!page->buffers)
- break;
- /* Fallthrough */
- case 2:
- if (!PageSwapCache(page))
- break;
- retval = exclusive_swap_page(page);
- break;
- case 1:
- if (PageReserved(page))
- break;
- retval = 1;
- }
- return retval;
-}
-
-/*
- * Work out if there are any other processes sharing this
- * swap cache page. Free it if you can. Return success.
- */
-int remove_exclusive_swap_page(struct page *page)
-{
- int retval;
- struct swap_info_struct * p;
- swp_entry_t entry;
-
- if (!PageLocked(page))
- BUG();
- if (!PageSwapCache(page))
- return 0;
- if (page_count(page) - !!page->buffers != 2) /* 2: us + cache */
- return 0;
-
- entry.val = page->index;
- p = swap_info_get(entry);
- if (!p)
- return 0;
-
- /* Is the only swap cache user the cache itself? */
- retval = 0;
- if (p->swap_map[SWP_OFFSET(entry)] == 1) {
- /* Recheck the page count with the pagecache lock held.. */
- spin_lock(&pagecache_lock);
- if (page_count(page) - !!page->buffers == 2) {
- __delete_from_swap_cache(page);
- SetPageDirty(page);
- retval = 1;
- }
- spin_unlock(&pagecache_lock);
- }
- swap_info_put(p);
-
- if (retval) {
- block_flushpage(page, 0);
- swap_free(entry);
- page_cache_release(page);
- }
-
- return retval;
-}
-
-/*
- * Free the swap entry like above, but also try to
- * free the page cache entry if it is the last user.
- */
-void free_swap_and_cache(swp_entry_t entry)
-{
- struct swap_info_struct * p;
- struct page *page = NULL;
-
- p = swap_info_get(entry);
- if (p) {
- if (swap_entry_free(p, SWP_OFFSET(entry)) == 1)
- page = find_trylock_page(&swapper_space, entry.val);
- swap_info_put(p);
- }
- if (page) {
- page_cache_get(page);
- /* Only cache user (+us), or swap space full? Free it! */
- if (page_count(page) == 2 || vm_swap_full()) {
- delete_from_swap_cache(page);
- SetPageDirty(page);
- }
- UnlockPage(page);
- page_cache_release(page);
- }
-}
-
-/*
- * The swap entry has been read in advance, and we return 1 to indicate
- * that the page has been used or is no longer needed.
- *
- * Always set the resulting pte to be nowrite (the same as COW pages
- * after one process has exited). We don't know just how many PTEs will
- * share this swap entry, so be cautious and let do_wp_page work out
- * what to do if a write is requested later.
- */
-/* mmlist_lock and vma->vm_mm->page_table_lock are held */
-static inline void unuse_pte(struct vm_area_struct * vma, unsigned long address,
- pte_t *dir, swp_entry_t entry, struct page* page)
-{
- pte_t pte = *dir;
-
- if (likely(pte_to_swp_entry(pte).val != entry.val))
- return;
- if (unlikely(pte_none(pte) || pte_present(pte)))
- return;
- get_page(page);
- set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
- swap_free(entry);
- ++vma->vm_mm->rss;
-}
-
-/* mmlist_lock and vma->vm_mm->page_table_lock are held */
-static inline void unuse_pmd(struct vm_area_struct * vma, pmd_t *dir,
- unsigned long address, unsigned long size, unsigned long offset,
- swp_entry_t entry, struct page* page)
-{
- pte_t * pte;
- unsigned long end;
-
- if (pmd_none(*dir))
- return;
- if (pmd_bad(*dir)) {
- pmd_ERROR(*dir);
- pmd_clear(dir);
- return;
- }
- pte = pte_offset(dir, address);
- offset += address & PMD_MASK;
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- unuse_pte(vma, offset+address-vma->vm_start, pte, entry, page);
- address += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
-}
-
-/* mmlist_lock and vma->vm_mm->page_table_lock are held */
-static inline void unuse_pgd(struct vm_area_struct * vma, pgd_t *dir,
- unsigned long address, unsigned long size,
- swp_entry_t entry, struct page* page)
-{
- pmd_t * pmd;
- unsigned long offset, end;
-
- if (pgd_none(*dir))
- return;
- if (pgd_bad(*dir)) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
- return;
- }
- pmd = pmd_offset(dir, address);
- offset = address & PGDIR_MASK;
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- if (address >= end)
- BUG();
- do {
- unuse_pmd(vma, pmd, address, end - address, offset, entry,
- page);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
-}
-
-/* mmlist_lock and vma->vm_mm->page_table_lock are held */
-static void unuse_vma(struct vm_area_struct * vma, pgd_t *pgdir,
- swp_entry_t entry, struct page* page)
-{
- unsigned long start = vma->vm_start, end = vma->vm_end;
-
- if (start >= end)
- BUG();
- do {
- unuse_pgd(vma, pgdir, start, end - start, entry, page);
- start = (start + PGDIR_SIZE) & PGDIR_MASK;
- pgdir++;
- } while (start && (start < end));
-}
-
-static void unuse_process(struct mm_struct * mm,
- swp_entry_t entry, struct page* page)
-{
- struct vm_area_struct* vma;
-
- /*
- * Go through process' page directory.
- */
- spin_lock(&mm->page_table_lock);
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- pgd_t * pgd = pgd_offset(mm, vma->vm_start);
- unuse_vma(vma, pgd, entry, page);
- }
- XENO_flush_page_update_queue();
- spin_unlock(&mm->page_table_lock);
- return;
-}
-
-/*
- * Scan swap_map from current position to next entry still in use.
- * Recycle to start on reaching the end, returning 0 when empty.
- */
-static int find_next_to_unuse(struct swap_info_struct *si, int prev)
-{
- int max = si->max;
- int i = prev;
- int count;
-
- /*
- * No need for swap_device_lock(si) here: we're just looking
- * for whether an entry is in use, not modifying it; false
- * hits are okay, and sys_swapoff() has already prevented new
- * allocations from this area (while holding swap_list_lock()).
- */
- for (;;) {
- if (++i >= max) {
- if (!prev) {
- i = 0;
- break;
- }
- /*
- * No entries in use at top of swap_map,
- * loop back to start and recheck there.
- */
- max = prev + 1;
- prev = 0;
- i = 1;
- }
- count = si->swap_map[i];
- if (count && count != SWAP_MAP_BAD)
- break;
- }
- return i;
-}
-
-/*
- * We completely avoid races by reading each swap page in advance,
- * and then search for the process using it. All the necessary
- * page table adjustments can then be made atomically.
- */
-static int try_to_unuse(unsigned int type)
-{
- struct swap_info_struct * si = &swap_info[type];
- struct mm_struct *start_mm;
- unsigned short *swap_map;
- unsigned short swcount;
- struct page *page;
- swp_entry_t entry;
- int i = 0;
- int retval = 0;
- int reset_overflow = 0;
-
- /*
- * When searching mms for an entry, a good strategy is to
- * start at the first mm we freed the previous entry from
- * (though actually we don't notice whether we or coincidence
- * freed the entry). Initialize this start_mm with a hold.
- *
- * A simpler strategy would be to start at the last mm we
- * freed the previous entry from; but that would take less
- * advantage of mmlist ordering (now preserved by swap_out()),
- * which clusters forked address spaces together, most recent
- * child immediately after parent. If we race with dup_mmap(),
- * we very much want to resolve parent before child, otherwise
- * we may miss some entries: using last mm would invert that.
- */
- start_mm = &init_mm;
- atomic_inc(&init_mm.mm_users);
-
- /*
- * Keep on scanning until all entries have gone. Usually,
- * one pass through swap_map is enough, but not necessarily:
- * mmput() removes mm from mmlist before exit_mmap() and its
- * zap_page_range(). That's not too bad, those entries are
- * on their way out, and handled faster there than here.
- * do_munmap() behaves similarly, taking the range out of mm's
- * vma list before zap_page_range(). But unfortunately, when
- * unmapping a part of a vma, it takes the whole out first,
- * then reinserts what's left after (might even reschedule if
- * open() method called) - so swap entries may be invisible
- * to swapoff for a while, then reappear - but that is rare.
- */
- while ((i = find_next_to_unuse(si, i))) {
- /*
- * Get a page for the entry, using the existing swap
- * cache page if there is one. Otherwise, get a clean
- * page and read the swap into it.
- */
- swap_map = &si->swap_map[i];
- entry = SWP_ENTRY(type, i);
- page = read_swap_cache_async(entry);
- if (!page) {
- /*
- * Either swap_duplicate() failed because entry
- * has been freed independently, and will not be
- * reused since sys_swapoff() already disabled
- * allocation from here, or alloc_page() failed.
- */
- if (!*swap_map)
- continue;
- retval = -ENOMEM;
- break;
- }
-
- /*
- * Don't hold on to start_mm if it looks like exiting.
- */
- if (atomic_read(&start_mm->mm_users) == 1) {
- mmput(start_mm);
- start_mm = &init_mm;
- atomic_inc(&init_mm.mm_users);
- }
-
- /*
- * Wait for and lock page. When do_swap_page races with
- * try_to_unuse, do_swap_page can handle the fault much
- * faster than try_to_unuse can locate the entry. This
- * apparently redundant "wait_on_page" lets try_to_unuse
- * defer to do_swap_page in such a case - in some tests,
- * do_swap_page and try_to_unuse repeatedly compete.
- */
- wait_on_page(page);
- lock_page(page);
-
- /*
- * Remove all references to entry, without blocking.
- * Whenever we reach init_mm, there's no address space
- * to search, but use it as a reminder to search shmem.
- */
- swcount = *swap_map;
- if (swcount > 1) {
- flush_page_to_ram(page);
- if (start_mm == &init_mm)
- shmem_unuse(entry, page);
- else
- unuse_process(start_mm, entry, page);
- }
- if (*swap_map > 1) {
- int set_start_mm = (*swap_map >= swcount);
- struct list_head *p = &start_mm->mmlist;
- struct mm_struct *new_start_mm = start_mm;
- struct mm_struct *mm;
-
- spin_lock(&mmlist_lock);
- while (*swap_map > 1 &&
- (p = p->next) != &start_mm->mmlist) {
- mm = list_entry(p, struct mm_struct, mmlist);
- swcount = *swap_map;
- if (mm == &init_mm) {
- set_start_mm = 1;
- shmem_unuse(entry, page);
- } else
- unuse_process(mm, entry, page);
- if (set_start_mm && *swap_map < swcount) {
- new_start_mm = mm;
- set_start_mm = 0;
- }
- }
- atomic_inc(&new_start_mm->mm_users);
- spin_unlock(&mmlist_lock);
- mmput(start_mm);
- start_mm = new_start_mm;
- }
-
- /*
- * How could swap count reach 0x7fff when the maximum
- * pid is 0x7fff, and there's no way to repeat a swap
- * page within an mm (except in shmem, where it's the
- * shared object which takes the reference count)?
- * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
- *
- * If that's wrong, then we should worry more about
- * exit_mmap() and do_munmap() cases described above:
- * we might be resetting SWAP_MAP_MAX too early here.
- * We know "Undead"s can happen, they're okay, so don't
- * report them; but do report if we reset SWAP_MAP_MAX.
- */
- if (*swap_map == SWAP_MAP_MAX) {
- swap_list_lock();
- swap_device_lock(si);
- nr_swap_pages++;
- *swap_map = 1;
- swap_device_unlock(si);
- swap_list_unlock();
- reset_overflow = 1;
- }
-
- /*
- * If a reference remains (rare), we would like to leave
- * the page in the swap cache; but try_to_swap_out could
- * then re-duplicate the entry once we drop page lock,
- * so we might loop indefinitely; also, that page could
- * not be swapped out to other storage meanwhile. So:
- * delete from cache even if there's another reference,
- * after ensuring that the data has been saved to disk -
- * since if the reference remains (rarer), it will be
- * read from disk into another page. Splitting into two
- * pages would be incorrect if swap supported "shared
- * private" pages, but they are handled by tmpfs files.
- * Note shmem_unuse already deleted its from swap cache.
- */
- swcount = *swap_map;
- if ((swcount > 0) != PageSwapCache(page))
- BUG();
- if ((swcount > 1) && PageDirty(page)) {
- rw_swap_page(WRITE, page);
- lock_page(page);
- }
- if (PageSwapCache(page))
- delete_from_swap_cache(page);
-
- /*
- * So we could skip searching mms once swap count went
- * to 1, we did not mark any present ptes as dirty: must
- * mark page dirty so try_to_swap_out will preserve it.
- */
- SetPageDirty(page);
- UnlockPage(page);
- page_cache_release(page);
-
- /*
- * Make sure that we aren't completely killing
- * interactive performance. Interruptible check on
- * signal_pending() would be nice, but changes the spec?
- */
- if (current->need_resched)
- schedule();
- }
-
- mmput(start_mm);
- if (reset_overflow) {
- printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
- swap_overflow = 0;
- }
- return retval;
-}
-
-asmlinkage long sys_swapoff(const char * specialfile)
-{
- struct swap_info_struct * p = NULL;
- unsigned short *swap_map;
- struct nameidata nd;
- int i, type, prev;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- err = user_path_walk(specialfile, &nd);
- if (err)
- goto out;
-
- lock_kernel();
- prev = -1;
- swap_list_lock();
- for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
- p = swap_info + type;
- if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
- if (p->swap_file == nd.dentry)
- break;
- }
- prev = type;
- }
- err = -EINVAL;
- if (type < 0) {
- swap_list_unlock();
- goto out_dput;
- }
-
- if (prev < 0) {
- swap_list.head = p->next;
- } else {
- swap_info[prev].next = p->next;
- }
- if (type == swap_list.next) {
- /* just pick something that's safe... */
- swap_list.next = swap_list.head;
- }
- nr_swap_pages -= p->pages;
- total_swap_pages -= p->pages;
- p->flags = SWP_USED;
- swap_list_unlock();
- unlock_kernel();
- err = try_to_unuse(type);
- lock_kernel();
- if (err) {
- /* re-insert swap space back into swap_list */
- swap_list_lock();
- for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
- if (p->prio >= swap_info[i].prio)
- break;
- p->next = i;
- if (prev < 0)
- swap_list.head = swap_list.next = p - swap_info;
- else
- swap_info[prev].next = p - swap_info;
- nr_swap_pages += p->pages;
- total_swap_pages += p->pages;
- p->flags = SWP_WRITEOK;
- swap_list_unlock();
- goto out_dput;
- }
- if (p->swap_device)
- blkdev_put(p->swap_file->d_inode->i_bdev, BDEV_SWAP);
- path_release(&nd);
-
- swap_list_lock();
- swap_device_lock(p);
- nd.mnt = p->swap_vfsmnt;
- nd.dentry = p->swap_file;
- p->swap_vfsmnt = NULL;
- p->swap_file = NULL;
- p->swap_device = 0;
- p->max = 0;
- swap_map = p->swap_map;
- p->swap_map = NULL;
- p->flags = 0;
- swap_device_unlock(p);
- swap_list_unlock();
- vfree(swap_map);
- err = 0;
-
-out_dput:
- unlock_kernel();
- path_release(&nd);
-out:
- return err;
-}
-
-int get_swaparea_info(char *buf)
-{
- char * page = (char *) __get_free_page(GFP_KERNEL);
- struct swap_info_struct *ptr = swap_info;
- int i, j, len = 0, usedswap;
-
- if (!page)
- return -ENOMEM;
-
- len += sprintf(buf, "Filename\t\t\tType\t\tSize\tUsed\tPriority\n");
- for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
- if ((ptr->flags & SWP_USED) && ptr->swap_map) {
- char * path = d_path(ptr->swap_file, ptr->swap_vfsmnt,
- page, PAGE_SIZE);
-
- len += sprintf(buf + len, "%-31s ", path);
-
- if (!ptr->swap_device)
- len += sprintf(buf + len, "file\t\t");
- else
- len += sprintf(buf + len, "partition\t");
-
- usedswap = 0;
- for (j = 0; j < ptr->max; ++j)
- switch (ptr->swap_map[j]) {
- case SWAP_MAP_BAD:
- case 0:
- continue;
- default:
- usedswap++;
- }
- len += sprintf(buf + len, "%d\t%d\t%d\n", ptr->pages << (PAGE_SHIFT - 10),
- usedswap << (PAGE_SHIFT - 10), ptr->prio);
- }
- }
- free_page((unsigned long) page);
- return len;
-}
-
-int is_swap_partition(kdev_t dev) {
- struct swap_info_struct *ptr = swap_info;
- int i;
-
- for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
- if (ptr->flags & SWP_USED)
- if (ptr->swap_device == dev)
- return 1;
- }
- return 0;
-}
-
-/*
- * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
- *
- * The swapon system call
- */
-asmlinkage long sys_swapon(const char * specialfile, int swap_flags)
-{
- struct swap_info_struct * p;
- struct nameidata nd;
- struct inode * swap_inode;
- unsigned int type;
- int i, j, prev;
- int error;
- static int least_priority = 0;
- union swap_header *swap_header = 0;
- int swap_header_version;
- int nr_good_pages = 0;
- unsigned long maxpages = 1;
- int swapfilesize;
- struct block_device *bdev = NULL;
- unsigned short *swap_map;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- lock_kernel();
- swap_list_lock();
- p = swap_info;
- for (type = 0 ; type < nr_swapfiles ; type++,p++)
- if (!(p->flags & SWP_USED))
- break;
- error = -EPERM;
- if (type >= MAX_SWAPFILES) {
- swap_list_unlock();
- goto out;
- }
- if (type >= nr_swapfiles)
- nr_swapfiles = type+1;
- p->flags = SWP_USED;
- p->swap_file = NULL;
- p->swap_vfsmnt = NULL;
- p->swap_device = 0;
- p->swap_map = NULL;
- p->lowest_bit = 0;
- p->highest_bit = 0;
- p->cluster_nr = 0;
- p->sdev_lock = SPIN_LOCK_UNLOCKED;
- p->next = -1;
- if (swap_flags & SWAP_FLAG_PREFER) {
- p->prio =
- (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
- } else {
- p->prio = --least_priority;
- }
- swap_list_unlock();
- error = user_path_walk(specialfile, &nd);
- if (error)
- goto bad_swap_2;
-
- p->swap_file = nd.dentry;
- p->swap_vfsmnt = nd.mnt;
- swap_inode = nd.dentry->d_inode;
- error = -EINVAL;
-
- if (S_ISBLK(swap_inode->i_mode)) {
- kdev_t dev = swap_inode->i_rdev;
- struct block_device_operations *bdops;
-
- p->swap_device = dev;
- set_blocksize(dev, PAGE_SIZE);
-
- bd_acquire(swap_inode);
- bdev = swap_inode->i_bdev;
- bdops = devfs_get_ops(devfs_get_handle_from_inode(swap_inode));
- if (bdops) bdev->bd_op = bdops;
-
- error = blkdev_get(bdev, FMODE_READ|FMODE_WRITE, 0, BDEV_SWAP);
- if (error)
- goto bad_swap_2;
- set_blocksize(dev, PAGE_SIZE);
- error = -ENODEV;
- if (!dev || (blk_size[MAJOR(dev)] &&
- !blk_size[MAJOR(dev)][MINOR(dev)]))
- goto bad_swap;
- swapfilesize = 0;
- if (blk_size[MAJOR(dev)])
- swapfilesize = blk_size[MAJOR(dev)][MINOR(dev)]
- >> (PAGE_SHIFT - 10);
- } else if (S_ISREG(swap_inode->i_mode))
- swapfilesize = swap_inode->i_size >> PAGE_SHIFT;
- else
- goto bad_swap;
-
- error = -EBUSY;
- for (i = 0 ; i < nr_swapfiles ; i++) {
- struct swap_info_struct *q = &swap_info[i];
- if (i == type || !q->swap_file)
- continue;
- if (swap_inode->i_mapping == q->swap_file->d_inode->i_mapping)
- goto bad_swap;
- }
-
- swap_header = (void *) __get_free_page(GFP_USER);
- if (!swap_header) {
- printk("Unable to start swapping: out of memory :-)\n");
- error = -ENOMEM;
- goto bad_swap;
- }
-
- lock_page(virt_to_page(swap_header));
- rw_swap_page_nolock(READ, SWP_ENTRY(type,0), (char *) swap_header);
-
- if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
- swap_header_version = 1;
- else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
- swap_header_version = 2;
- else {
- printk("Unable to find swap-space signature\n");
- error = -EINVAL;
- goto bad_swap;
- }
-
- switch (swap_header_version) {
- case 1:
- memset(((char *) swap_header)+PAGE_SIZE-10,0,10);
- j = 0;
- p->lowest_bit = 0;
- p->highest_bit = 0;
- for (i = 1 ; i < 8*PAGE_SIZE ; i++) {
- if (test_bit(i,(char *) swap_header)) {
- if (!p->lowest_bit)
- p->lowest_bit = i;
- p->highest_bit = i;
- maxpages = i+1;
- j++;
- }
- }
- nr_good_pages = j;
- p->swap_map = vmalloc(maxpages * sizeof(short));
- if (!p->swap_map) {
- error = -ENOMEM;
- goto bad_swap;
- }
- for (i = 1 ; i < maxpages ; i++) {
- if (test_bit(i,(char *) swap_header))
- p->swap_map[i] = 0;
- else
- p->swap_map[i] = SWAP_MAP_BAD;
- }
- break;
-
- case 2:
- /* Check the swap header's sub-version and the size of
- the swap file and bad block lists */
- if (swap_header->info.version != 1) {
- printk(KERN_WARNING
- "Unable to handle swap header version %d\n",
- swap_header->info.version);
- error = -EINVAL;
- goto bad_swap;
- }
-
- p->lowest_bit = 1;
- maxpages = SWP_OFFSET(SWP_ENTRY(0,~0UL)) - 1;
- if (maxpages > swap_header->info.last_page)
- maxpages = swap_header->info.last_page;
- p->highest_bit = maxpages - 1;
-
- error = -EINVAL;
- if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
- goto bad_swap;
-
- /* OK, set up the swap map and apply the bad block list */
- if (!(p->swap_map = vmalloc(maxpages * sizeof(short)))) {
- error = -ENOMEM;
- goto bad_swap;
- }
-
- error = 0;
- memset(p->swap_map, 0, maxpages * sizeof(short));
- for (i=0; i<swap_header->info.nr_badpages; i++) {
- int page = swap_header->info.badpages[i];
- if (page <= 0 || page >= swap_header->info.last_page)
- error = -EINVAL;
- else
- p->swap_map[page] = SWAP_MAP_BAD;
- }
- nr_good_pages = swap_header->info.last_page -
- swap_header->info.nr_badpages -
- 1 /* header page */;
- if (error)
- goto bad_swap;
- }
-
- if (swapfilesize && maxpages > swapfilesize) {
- printk(KERN_WARNING
- "Swap area shorter than signature indicates\n");
- error = -EINVAL;
- goto bad_swap;
- }
- if (!nr_good_pages) {
- printk(KERN_WARNING "Empty swap-file\n");
- error = -EINVAL;
- goto bad_swap;
- }
- p->swap_map[0] = SWAP_MAP_BAD;
- swap_list_lock();
- swap_device_lock(p);
- p->max = maxpages;
- p->flags = SWP_WRITEOK;
- p->pages = nr_good_pages;
- nr_swap_pages += nr_good_pages;
- total_swap_pages += nr_good_pages;
- printk(KERN_INFO "Adding Swap: %dk swap-space (priority %d)\n",
- nr_good_pages<<(PAGE_SHIFT-10), p->prio);
-
- /* insert swap space into swap_list: */
- prev = -1;
- for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
- if (p->prio >= swap_info[i].prio) {
- break;
- }
- prev = i;
- }
- p->next = i;
- if (prev < 0) {
- swap_list.head = swap_list.next = p - swap_info;
- } else {
- swap_info[prev].next = p - swap_info;
- }
- swap_device_unlock(p);
- swap_list_unlock();
- error = 0;
- goto out;
-bad_swap:
- if (bdev)
- blkdev_put(bdev, BDEV_SWAP);
-bad_swap_2:
- swap_list_lock();
- swap_map = p->swap_map;
- nd.mnt = p->swap_vfsmnt;
- nd.dentry = p->swap_file;
- p->swap_device = 0;
- p->swap_file = NULL;
- p->swap_vfsmnt = NULL;
- p->swap_map = NULL;
- p->flags = 0;
- if (!(swap_flags & SWAP_FLAG_PREFER))
- ++least_priority;
- swap_list_unlock();
- if (swap_map)
- vfree(swap_map);
- path_release(&nd);
-out:
- if (swap_header)
- free_page((long) swap_header);
- unlock_kernel();
- return error;
-}
-
-void si_swapinfo(struct sysinfo *val)
-{
- unsigned int i;
- unsigned long nr_to_be_unused = 0;
-
- swap_list_lock();
- for (i = 0; i < nr_swapfiles; i++) {
- unsigned int j;
- if (swap_info[i].flags != SWP_USED)
- continue;
- for (j = 0; j < swap_info[i].max; ++j) {
- switch (swap_info[i].swap_map[j]) {
- case 0:
- case SWAP_MAP_BAD:
- continue;
- default:
- nr_to_be_unused++;
- }
- }
- }
- val->freeswap = nr_swap_pages + nr_to_be_unused;
- val->totalswap = total_swap_pages + nr_to_be_unused;
- swap_list_unlock();
-}
-
-/*
- * Verify that a swap entry is valid and increment its swap map count.
- *
- * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
- * "permanent", but will be reclaimed by the next swapoff.
- */
-int swap_duplicate(swp_entry_t entry)
-{
- struct swap_info_struct * p;
- unsigned long offset, type;
- int result = 0;
-
- type = SWP_TYPE(entry);
- if (type >= nr_swapfiles)
- goto bad_file;
- p = type + swap_info;
- offset = SWP_OFFSET(entry);
-
- swap_device_lock(p);
- if (offset < p->max && p->swap_map[offset]) {
- if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
- p->swap_map[offset]++;
- result = 1;
- } else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
- if (swap_overflow++ < 5)
- printk(KERN_WARNING "swap_dup: swap entry overflow\n");
- p->swap_map[offset] = SWAP_MAP_MAX;
- result = 1;
- }
- }
- swap_device_unlock(p);
-out:
- return result;
-
-bad_file:
- printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
- goto out;
-}
-
-/*
- * Page lock needs to be held in all cases to prevent races with
- * swap file deletion.
- */
-int swap_count(struct page *page)
-{
- struct swap_info_struct * p;
- unsigned long offset, type;
- swp_entry_t entry;
- int retval = 0;
-
- entry.val = page->index;
- if (!entry.val)
- goto bad_entry;
- type = SWP_TYPE(entry);
- if (type >= nr_swapfiles)
- goto bad_file;
- p = type + swap_info;
- offset = SWP_OFFSET(entry);
- if (offset >= p->max)
- goto bad_offset;
- if (!p->swap_map[offset])
- goto bad_unused;
- retval = p->swap_map[offset];
-out:
- return retval;
-
-bad_entry:
- printk(KERN_ERR "swap_count: null entry!\n");
- goto out;
-bad_file:
- printk(KERN_ERR "swap_count: %s%08lx\n", Bad_file, entry.val);
- goto out;
-bad_offset:
- printk(KERN_ERR "swap_count: %s%08lx\n", Bad_offset, entry.val);
- goto out;
-bad_unused:
- printk(KERN_ERR "swap_count: %s%08lx\n", Unused_offset, entry.val);
- goto out;
-}
-
-/*
- * Prior swap_duplicate protects against swap device deletion.
- */
-void get_swaphandle_info(swp_entry_t entry, unsigned long *offset,
- kdev_t *dev, struct inode **swapf)
-{
- unsigned long type;
- struct swap_info_struct *p;
-
- type = SWP_TYPE(entry);
- if (type >= nr_swapfiles) {
- printk(KERN_ERR "rw_swap_page: %s%08lx\n", Bad_file, entry.val);
- return;
- }
-
- p = &swap_info[type];
- *offset = SWP_OFFSET(entry);
- if (*offset >= p->max && *offset != 0) {
- printk(KERN_ERR "rw_swap_page: %s%08lx\n", Bad_offset, entry.val);
- return;
- }
- if (p->swap_map && !p->swap_map[*offset]) {
- printk(KERN_ERR "rw_swap_page: %s%08lx\n", Unused_offset, entry.val);
- return;
- }
- if (!(p->flags & SWP_USED)) {
- printk(KERN_ERR "rw_swap_page: %s%08lx\n", Unused_file, entry.val);
- return;
- }
-
- if (p->swap_device) {
- *dev = p->swap_device;
- } else if (p->swap_file) {
- *swapf = p->swap_file->d_inode;
- } else {
- printk(KERN_ERR "rw_swap_page: no swap file or device\n");
- }
- return;
-}
-
-/*
- * swap_device_lock prevents swap_map being freed. Don't grab an extra
- * reference on the swaphandle, it doesn't matter if it becomes unused.
- */
-int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
-{
- int ret = 0, i = 1 << page_cluster;
- unsigned long toff;
- struct swap_info_struct *swapdev = SWP_TYPE(entry) + swap_info;
-
- if (!page_cluster) /* no readahead */
- return 0;
- toff = (SWP_OFFSET(entry) >> page_cluster) << page_cluster;
- if (!toff) /* first page is swap header */
- toff++, i--;
- *offset = toff;
-
- swap_device_lock(swapdev);
- do {
- /* Don't read-ahead past the end of the swap area */
- if (toff >= swapdev->max)
- break;
- /* Don't read in free or bad pages */
- if (!swapdev->swap_map[toff])
- break;
- if (swapdev->swap_map[toff] == SWAP_MAP_BAD)
- break;
- toff++;
- ret++;
- } while (--i);
- swap_device_unlock(swapdev);
- return ret;
-}
--- /dev/null
+VERSION = 2
+PATCHLEVEL = 4
+SUBLEVEL = 21
+EXTRAVERSION = -pre4-xeno
+
+KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
+
+ARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ -e s/arm.*/arm/ -e s/sa110/arm/)
+
+# Xeno hack XXX
+ARCH=xeno
+
+KERNELPATH=kernel-$(shell echo $(KERNELRELEASE) | sed -e "s/-//g")
+
+CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
+ else if [ -x /bin/bash ]; then echo /bin/bash; \
+ else echo sh; fi ; fi)
+TOPDIR := $(shell /bin/pwd)
+
+HPATH = $(TOPDIR)/include
+FINDHPATH = $(HPATH)/asm $(HPATH)/linux $(HPATH)/scsi $(HPATH)/net $(HPATH)/math-emu
+
+HOSTCC = gcc
+HOSTCFLAGS = -Wall -Wstrict-prototypes -O2 -fomit-frame-pointer
+
+CROSS_COMPILE =
+
+#
+# Include the make variables (CC, etc...)
+#
+
+AS = $(CROSS_COMPILE)as
+LD = $(CROSS_COMPILE)ld
+CC = $(CROSS_COMPILE)gcc
+CPP = $(CC) -E
+AR = $(CROSS_COMPILE)ar
+NM = $(CROSS_COMPILE)nm
+STRIP = $(CROSS_COMPILE)strip
+OBJCOPY = $(CROSS_COMPILE)objcopy
+OBJDUMP = $(CROSS_COMPILE)objdump
+MAKEFILES = $(TOPDIR)/.config
+GENKSYMS = /sbin/genksyms
+DEPMOD = /sbin/depmod
+MODFLAGS = -DMODULE
+CFLAGS_KERNEL =
+PERL = perl
+
+export VERSION PATCHLEVEL SUBLEVEL EXTRAVERSION KERNELRELEASE ARCH \
+ CONFIG_SHELL TOPDIR HPATH HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC \
+ CPP AR NM STRIP OBJCOPY OBJDUMP MAKE MAKEFILES GENKSYMS MODFLAGS PERL
+
+all: do-it-all
+
+#
+# Make "config" the default target if there is no configuration file or
+# "depend" the target if there is no top-level dependency information.
+#
+
+ifeq (.config,$(wildcard .config))
+include .config
+ifeq (.depend,$(wildcard .depend))
+include .depend
+do-it-all: Version vmlinux
+else
+CONFIGURATION = depend
+do-it-all: depend
+endif
+else
+CONFIGURATION = config
+do-it-all: config
+endif
+
+#
+# INSTALL_PATH specifies where to place the updated kernel and system map
+# images. Uncomment if you want to place them anywhere other than root.
+#
+
+#export INSTALL_PATH=/boot
+
+#
+# INSTALL_MOD_PATH specifies a prefix to MODLIB for module directory
+# relocations required by build roots. This is not defined in the
+# makefile but the arguement can be passed to make if needed.
+#
+
+MODLIB := $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
+export MODLIB
+
+#
+# standard CFLAGS
+#
+
+CPPFLAGS := -D__KERNEL__ -I$(HPATH)
+
+CFLAGS := $(CPPFLAGS) -Wall -Wstrict-prototypes -Wno-trigraphs -O2 \
+ -fno-strict-aliasing -fno-common
+ifndef CONFIG_FRAME_POINTER
+CFLAGS += -fomit-frame-pointer
+endif
+AFLAGS := -D__ASSEMBLY__ $(CPPFLAGS)
+
+#
+# ROOT_DEV specifies the default root-device when making the image.
+# This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case
+# the default of FLOPPY is used by 'build'.
+# This is i386 specific.
+#
+
+export ROOT_DEV = CURRENT
+
+#
+# If you want to preset the SVGA mode, uncomment the next line and
+# set SVGA_MODE to whatever number you want.
+# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
+# The number is the same as you would ordinarily press at bootup.
+# This is i386 specific.
+#
+
+export SVGA_MODE = -DSVGA_MODE=NORMAL_VGA
+
+#
+# If you want the RAM disk device, define this to be the size in blocks.
+# This is i386 specific.
+#
+
+#export RAMDISK = -DRAMDISK=512
+
+CORE_FILES =kernel/kernel.o mm/mm.o fs/fs.o ipc/ipc.o
+NETWORKS =net/network.o
+
+LIBS =$(TOPDIR)/lib/lib.a
+SUBDIRS =kernel drivers mm fs net ipc lib
+
+DRIVERS-n :=
+DRIVERS-y :=
+DRIVERS-m :=
+DRIVERS- :=
+
+DRIVERS-$(CONFIG_ACPI) += drivers/acpi/acpi.o
+DRIVERS-$(CONFIG_PARPORT) += drivers/parport/driver.o
+DRIVERS-y += drivers/char/char.o \
+ drivers/block/block.o \
+ drivers/misc/misc.o \
+ drivers/net/net.o
+DRIVERS-$(CONFIG_AGP) += drivers/char/agp/agp.o
+DRIVERS-$(CONFIG_DRM_NEW) += drivers/char/drm/drm.o
+DRIVERS-$(CONFIG_DRM_OLD) += drivers/char/drm-4.0/drm.o
+DRIVERS-$(CONFIG_NUBUS) += drivers/nubus/nubus.a
+DRIVERS-$(CONFIG_NET_FC) += drivers/net/fc/fc.o
+DRIVERS-$(CONFIG_DEV_APPLETALK) += drivers/net/appletalk/appletalk.o
+DRIVERS-$(CONFIG_TR) += drivers/net/tokenring/tr.o
+DRIVERS-$(CONFIG_WAN) += drivers/net/wan/wan.o
+DRIVERS-$(CONFIG_ARCNET) += drivers/net/arcnet/arcnetdrv.o
+DRIVERS-$(CONFIG_ATM) += drivers/atm/atm.o
+DRIVERS-$(CONFIG_IDE) += drivers/ide/idedriver.o
+DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
+DRIVERS-$(CONFIG_SCSI) += drivers/scsi/scsidrv.o
+DRIVERS-$(CONFIG_FUSION_BOOT) += drivers/message/fusion/fusion.o
+DRIVERS-$(CONFIG_IEEE1394) += drivers/ieee1394/ieee1394drv.o
+
+ifneq ($(CONFIG_CD_NO_IDESCSI)$(CONFIG_BLK_DEV_IDECD)$(CONFIG_BLK_DEV_SR)$(CONFIG_PARIDE_PCD),)
+DRIVERS-y += drivers/cdrom/driver.o
+endif
+
+DRIVERS-$(CONFIG_SOUND) += drivers/sound/sounddrivers.o
+DRIVERS-$(CONFIG_PCI) += drivers/pci/driver.o
+DRIVERS-$(CONFIG_MTD) += drivers/mtd/mtdlink.o
+DRIVERS-$(CONFIG_PCMCIA) += drivers/pcmcia/pcmcia.o
+DRIVERS-$(CONFIG_NET_PCMCIA) += drivers/net/pcmcia/pcmcia_net.o
+DRIVERS-$(CONFIG_NET_WIRELESS) += drivers/net/wireless/wireless_net.o
+DRIVERS-$(CONFIG_PCMCIA_CHRDEV) += drivers/char/pcmcia/pcmcia_char.o
+DRIVERS-$(CONFIG_DIO) += drivers/dio/dio.a
+DRIVERS-$(CONFIG_SBUS) += drivers/sbus/sbus_all.o
+DRIVERS-$(CONFIG_ZORRO) += drivers/zorro/driver.o
+DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
+DRIVERS-$(CONFIG_PPC32) += drivers/macintosh/macintosh.o
+DRIVERS-$(CONFIG_MAC) += drivers/macintosh/macintosh.o
+DRIVERS-$(CONFIG_ISAPNP) += drivers/pnp/pnp.o
+DRIVERS-$(CONFIG_SGI_IP22) += drivers/sgi/sgi.a
+DRIVERS-$(CONFIG_VT) += drivers/video/video.o
+DRIVERS-$(CONFIG_PARIDE) += drivers/block/paride/paride.a
+DRIVERS-$(CONFIG_HAMRADIO) += drivers/net/hamradio/hamradio.o
+DRIVERS-$(CONFIG_TC) += drivers/tc/tc.a
+DRIVERS-$(CONFIG_USB) += drivers/usb/usbdrv.o
+DRIVERS-y +=drivers/media/media.o
+DRIVERS-$(CONFIG_INPUT) += drivers/input/inputdrv.o
+DRIVERS-$(CONFIG_HIL) += drivers/hil/hil.o
+DRIVERS-$(CONFIG_I2O) += drivers/message/i2o/i2o.o
+DRIVERS-$(CONFIG_IRDA) += drivers/net/irda/irda.o
+DRIVERS-$(CONFIG_I2C) += drivers/i2c/i2c.o
+DRIVERS-$(CONFIG_PHONE) += drivers/telephony/telephony.o
+DRIVERS-$(CONFIG_MD) += drivers/md/mddev.o
+DRIVERS-$(CONFIG_GSC) += drivers/gsc/gscbus.o
+DRIVERS-$(CONFIG_BLUEZ) += drivers/bluetooth/bluetooth.o
+DRIVERS-$(CONFIG_HOTPLUG_PCI) += drivers/hotplug/vmlinux-obj.o
+DRIVERS-$(CONFIG_ISDN_BOOL) += drivers/isdn/vmlinux-obj.o
+
+DRIVERS := $(DRIVERS-y)
+
+
+# files removed with 'make clean'
+CLEAN_FILES = \
+ kernel/ksyms.lst include/linux/compile.h \
+ vmlinux System.map \
+ .tmp* \
+ drivers/char/consolemap_deftbl.c drivers/video/promcon_tbl.c \
+ drivers/char/conmakehash \
+ drivers/char/drm/*-mod.c \
+ drivers/pci/devlist.h drivers/pci/classlist.h drivers/pci/gen-devlist \
+ drivers/zorro/devlist.h drivers/zorro/gen-devlist \
+ drivers/sound/bin2hex drivers/sound/hex2hex \
+ drivers/atm/fore200e_mkfirm drivers/atm/{pca,sba}*{.bin,.bin1,.bin2} \
+ drivers/scsi/aic7xxx/aicasm/aicasm \
+ drivers/scsi/aic7xxx/aicasm/aicasm_gram.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_gram.h \
+ drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.h \
+ drivers/scsi/aic7xxx/aicasm/aicasm_macro_scan.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_scan.c \
+ drivers/scsi/aic7xxx/aicasm/aicdb.h \
+ drivers/scsi/aic7xxx/aicasm/y.tab.h \
+ drivers/scsi/53c700_d.h \
+ net/khttpd/make_times_h \
+ net/khttpd/times.h \
+ submenu*
+# directories removed with 'make clean'
+CLEAN_DIRS = \
+ modules
+
+# files removed with 'make mrproper'
+MRPROPER_FILES = \
+ include/linux/autoconf.h include/linux/version.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{afsk1200,afsk2666,fsk9600}.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{hapn4800,psk4800}.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{afsk2400_7,afsk2400_8}.h \
+ drivers/net/hamradio/soundmodem/gentbl \
+ drivers/sound/*_boot.h drivers/sound/.*.boot \
+ drivers/sound/msndinit.c \
+ drivers/sound/msndperm.c \
+ drivers/sound/pndsperm.c \
+ drivers/sound/pndspini.c \
+ drivers/atm/fore200e_*_fw.c drivers/atm/.fore200e_*.fw \
+ .version .config* config.in config.old \
+ scripts/tkparse scripts/kconfig.tk scripts/kconfig.tmp \
+ scripts/lxdialog/*.o scripts/lxdialog/lxdialog \
+ .menuconfig.log \
+ include/asm \
+ .hdepend scripts/mkdep scripts/split-include scripts/docproc \
+ $(TOPDIR)/include/linux/modversions.h \
+ kernel.spec
+
+# directories removed with 'make mrproper'
+MRPROPER_DIRS = \
+ include/config \
+ $(TOPDIR)/include/linux/modules
+
+
+include arch/$(ARCH)/Makefile
+
+# Extra cflags for kbuild 2.4. The default is to forbid includes by kernel code
+# from user space headers. Some UML code requires user space headers, in the
+# UML Makefiles add 'kbuild_2_4_nostdinc :=' before include Rules.make. No
+# other kernel code should include user space headers, if you need
+# 'kbuild_2_4_nostdinc :=' or -I/usr/include for kernel code and you are not UML
+# then your code is broken! KAO.
+
+kbuild_2_4_nostdinc := -nostdinc -iwithprefix include
+export kbuild_2_4_nostdinc
+
+export CPPFLAGS CFLAGS CFLAGS_KERNEL AFLAGS AFLAGS_KERNEL
+
+export NETWORKS DRIVERS LIBS HEAD LDFLAGS LINKFLAGS MAKEBOOT ASFLAGS
+
+.S.s:
+ $(CPP) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -o $*.s $<
+.S.o:
+ $(CC) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -c -o $*.o $<
+
+Version: dummy
+ @rm -f include/linux/compile.h
+
+boot: vmlinux
+ @$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C arch/$(ARCH)/boot
+
+vmlinux: include/linux/version.h $(CONFIGURATION) init/main.o init/version.o init/do_mounts.o linuxsubdirs
+ $(LD) $(LINKFLAGS) $(HEAD) init/main.o init/version.o init/do_mounts.o \
+ --start-group \
+ $(CORE_FILES) \
+ $(DRIVERS) \
+ $(NETWORKS) \
+ $(LIBS) \
+ --end-group \
+ -o vmlinux
+ $(NM) vmlinux | grep -v '\(compiled\)\|\(\.o$$\)\|\( [aUw] \)\|\(\.\.ng$$\)\|\(LASH[RL]DI\)' | sort > System.map
+
+symlinks:
+ rm -f include/asm
+ ( cd include ; ln -sf asm-$(ARCH) asm)
+ @if [ ! -d include/linux/modules ]; then \
+ mkdir include/linux/modules; \
+ fi
+
+oldconfig: symlinks
+ $(CONFIG_SHELL) scripts/Configure -d arch/$(ARCH)/config.in
+
+xconfig: symlinks
+ $(MAKE) -C scripts kconfig.tk
+ wish -f scripts/kconfig.tk
+
+menuconfig: include/linux/version.h symlinks
+ $(MAKE) -C scripts/lxdialog all
+ $(CONFIG_SHELL) scripts/Menuconfig arch/$(ARCH)/config.in
+
+config: symlinks
+ $(CONFIG_SHELL) scripts/Configure arch/$(ARCH)/config.in
+
+include/config/MARKER: scripts/split-include include/linux/autoconf.h
+ scripts/split-include include/linux/autoconf.h include/config
+ @ touch include/config/MARKER
+
+linuxsubdirs: $(patsubst %, _dir_%, $(SUBDIRS))
+
+$(patsubst %, _dir_%, $(SUBDIRS)) : dummy include/linux/version.h include/config/MARKER
+ $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C $(patsubst _dir_%, %, $@)
+
+$(TOPDIR)/include/linux/version.h: include/linux/version.h
+$(TOPDIR)/include/linux/compile.h: include/linux/compile.h
+
+newversion:
+ . scripts/mkversion > .tmpversion
+ @mv -f .tmpversion .version
+
+uts_len := 64
+uts_truncate := sed -e 's/\(.\{1,$(uts_len)\}\).*/\1/'
+
+include/linux/compile.h: $(CONFIGURATION) include/linux/version.h newversion
+ @echo -n \#`cat .version` > .ver1
+ @if [ -n "$(CONFIG_SMP)" ] ; then echo -n " SMP" >> .ver1; fi
+ @if [ -f .name ]; then echo -n \-`cat .name` >> .ver1; fi
+ @LANG=C echo ' '`date` >> .ver1
+ @echo \#define UTS_VERSION \"`cat .ver1 | $(uts_truncate)`\" > .ver
+ @LANG=C echo \#define LINUX_COMPILE_TIME \"`date +%T`\" >> .ver
+ @echo \#define LINUX_COMPILE_BY \"`whoami`\" >> .ver
+ @echo \#define LINUX_COMPILE_HOST \"`hostname | $(uts_truncate)`\" >> .ver
+ @([ -x /bin/dnsdomainname ] && /bin/dnsdomainname > .ver1) || \
+ ([ -x /bin/domainname ] && /bin/domainname > .ver1) || \
+ echo > .ver1
+ @echo \#define LINUX_COMPILE_DOMAIN \"`cat .ver1 | $(uts_truncate)`\" >> .ver
+ @echo \#define LINUX_COMPILER \"`$(CC) $(CFLAGS) -v 2>&1 | tail -1`\" >> .ver
+ @mv -f .ver $@
+ @rm -f .ver1
+
+include/linux/version.h: ./Makefile
+ @expr length "$(KERNELRELEASE)" \<= $(uts_len) > /dev/null || \
+ (echo KERNELRELEASE \"$(KERNELRELEASE)\" exceeds $(uts_len) characters >&2; false)
+ @echo \#define UTS_RELEASE \"$(KERNELRELEASE)\" > .ver
+ @echo \#define LINUX_VERSION_CODE `expr $(VERSION) \\* 65536 + $(PATCHLEVEL) \\* 256 + $(SUBLEVEL)` >> .ver
+ @echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))' >>.ver
+ @mv -f .ver $@
+
+comma := ,
+
+init/version.o: init/version.c include/linux/compile.h include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) -DUTS_MACHINE='"$(ARCH)"' -DKBUILD_BASENAME=$(subst $(comma),_,$(subst -,_,$(*F))) -c -o init/version.o init/version.c
+
+init/main.o: init/main.c include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -DKBUILD_BASENAME=$(subst $(comma),_,$(subst -,_,$(*F))) -c -o $@ $<
+
+init/do_mounts.o: init/do_mounts.c include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -DKBUILD_BASENAME=$(subst $(comma),_,$(subst -,_,$(*F))) -c -o $@ $<
+
+fs lib mm ipc kernel drivers net: dummy
+ $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" $(subst $@, _dir_$@, $@)
+
+TAGS: dummy
+ { find include/asm-${ARCH} -name '*.h' -print ; \
+ find include -type d \( -name "asm-*" -o -name config \) -prune -o -name '*.h' -print ; \
+ find $(SUBDIRS) init arch/${ARCH} -name '*.[chS]' ; } | grep -v SCCS | grep -v '\.svn' | etags -
+
+# Exuberant ctags works better with -I
+tags: dummy
+ CTAGSF=`ctags --version | grep -i exuberant >/dev/null && echo "-I __initdata,__exitdata,EXPORT_SYMBOL,EXPORT_SYMBOL_NOVERS"`; \
+ ctags $$CTAGSF `find include/asm-$(ARCH) -name '*.h'` && \
+ find include -type d \( -name "asm-*" -o -name config \) -prune -o -name '*.h' -print | xargs ctags $$CTAGSF -a && \
+ find $(SUBDIRS) init -name '*.[ch]' | xargs ctags $$CTAGSF -a
+
+ifdef CONFIG_MODULES
+ifdef CONFIG_MODVERSIONS
+MODFLAGS += -DMODVERSIONS -include $(HPATH)/linux/modversions.h
+endif
+
+.PHONY: modules
+modules: $(patsubst %, _mod_%, $(SUBDIRS))
+
+.PHONY: $(patsubst %, _mod_%, $(SUBDIRS))
+$(patsubst %, _mod_%, $(SUBDIRS)) : include/linux/version.h include/config/MARKER
+ $(MAKE) -C $(patsubst _mod_%, %, $@) CFLAGS="$(CFLAGS) $(MODFLAGS)" MAKING_MODULES=1 modules
+
+.PHONY: modules_install
+modules_install: _modinst_ $(patsubst %, _modinst_%, $(SUBDIRS)) _modinst_post
+
+.PHONY: _modinst_
+_modinst_:
+ @rm -rf $(MODLIB)/kernel
+ @rm -f $(MODLIB)/build
+ @mkdir -p $(MODLIB)/kernel
+ @ln -s $(TOPDIR) $(MODLIB)/build
+
+# If System.map exists, run depmod. This deliberately does not have a
+# dependency on System.map since that would run the dependency tree on
+# vmlinux. This depmod is only for convenience to give the initial
+# boot a modules.dep even before / is mounted read-write. However the
+# boot script depmod is the master version.
+ifeq "$(strip $(INSTALL_MOD_PATH))" ""
+depmod_opts :=
+else
+depmod_opts := -b $(INSTALL_MOD_PATH) -r
+endif
+.PHONY: _modinst_post
+_modinst_post: _modinst_post_pcmcia
+# if [ -r System.map ]; then $(DEPMOD) -ae -F System.map $(depmod_opts) $(KERNELRELEASE); fi
+
+# Backwards compatibilty symlinks for people still using old versions
+# of pcmcia-cs with hard coded pathnames on insmod. Remove
+# _modinst_post_pcmcia for kernel 2.4.1.
+.PHONY: _modinst_post_pcmcia
+_modinst_post_pcmcia:
+ cd $(MODLIB); \
+ mkdir -p pcmcia; \
+ find kernel -path '*/pcmcia/*' -name '*.o' | xargs -i -r ln -sf ../{} pcmcia
+
+.PHONY: $(patsubst %, _modinst_%, $(SUBDIRS))
+$(patsubst %, _modinst_%, $(SUBDIRS)) :
+ $(MAKE) -C $(patsubst _modinst_%, %, $@) modules_install
+
+# modules disabled....
+
+else
+modules modules_install: dummy
+ @echo
+ @echo "The present kernel configuration has modules disabled."
+ @echo "Type 'make config' and enable loadable module support."
+ @echo "Then build a kernel with module support enabled."
+ @echo
+ @exit 1
+endif
+
+clean: archclean
+ find . \( -name '*.[oas]' -o -name core -o -name '.*.flags' \) -type f -print \
+ | grep -v lxdialog/ | xargs rm -f
+ rm -f $(CLEAN_FILES)
+ rm -rf $(CLEAN_DIRS)
+ $(MAKE) -C Documentation/DocBook clean
+
+mrproper: clean archmrproper
+ find . \( -size 0 -o -name .depend \) -type f -print | xargs rm -f
+ rm -f $(MRPROPER_FILES)
+ rm -rf $(MRPROPER_DIRS)
+ $(MAKE) -C Documentation/DocBook mrproper
+
+distclean: mrproper
+ rm -f core `find . \( -not -type d \) -and \
+ \( -name '*.orig' -o -name '*.rej' -o -name '*~' \
+ -o -name '*.bak' -o -name '#*#' -o -name '.*.orig' \
+ -o -name '.*.rej' -o -name '.SUMS' -o -size 0 \) -type f -print` TAGS tags
+
+backup: mrproper
+ cd .. && tar cf - linux/ | gzip -9 > backup.gz
+ sync
+
+sgmldocs:
+ chmod 755 $(TOPDIR)/scripts/docgen
+ chmod 755 $(TOPDIR)/scripts/gen-all-syms
+ chmod 755 $(TOPDIR)/scripts/kernel-doc
+ $(MAKE) -C $(TOPDIR)/Documentation/DocBook books
+
+psdocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook ps
+
+pdfdocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook pdf
+
+htmldocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook html
+
+mandocs:
+ chmod 755 $(TOPDIR)/scripts/kernel-doc
+ chmod 755 $(TOPDIR)/scripts/split-man
+ $(MAKE) -C Documentation/DocBook man
+
+sums:
+ find . -type f -print | sort | xargs sum > .SUMS
+
+dep-files: scripts/mkdep archdep include/linux/version.h
+ scripts/mkdep -- init/*.c > .depend
+ scripts/mkdep -- `find $(FINDHPATH) \( -name SCCS -o -name .svn \) -prune -o -follow -name \*.h ! -name modversions.h -print` > .hdepend
+ $(MAKE) $(patsubst %,_sfdep_%,$(SUBDIRS)) _FASTDEP_ALL_SUB_DIRS="$(SUBDIRS)"
+ifdef CONFIG_MODVERSIONS
+ $(MAKE) update-modverfile
+endif
+
+ifdef CONFIG_MODVERSIONS
+MODVERFILE := $(TOPDIR)/include/linux/modversions.h
+else
+MODVERFILE :=
+endif
+export MODVERFILE
+
+depend dep: dep-files
+
+checkconfig:
+ find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w scripts/checkconfig.pl
+
+checkhelp:
+ find * -name [cC]onfig.in -print | sort | xargs $(PERL) -w scripts/checkhelp.pl
+
+checkincludes:
+ find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w scripts/checkincludes.pl
+
+ifdef CONFIGURATION
+..$(CONFIGURATION):
+ @echo
+ @echo "You have a bad or nonexistent" .$(CONFIGURATION) ": running 'make" $(CONFIGURATION)"'"
+ @echo
+ $(MAKE) $(CONFIGURATION)
+ @echo
+ @echo "Successful. Try re-making (ignore the error that follows)"
+ @echo
+ exit 1
+
+#dummy: ..$(CONFIGURATION)
+dummy:
+
+else
+
+dummy:
+
+endif
+
+include Rules.make
+
+#
+# This generates dependencies for the .h files.
+#
+
+scripts/mkdep: scripts/mkdep.c
+ $(HOSTCC) $(HOSTCFLAGS) -o scripts/mkdep scripts/mkdep.c
+
+scripts/split-include: scripts/split-include.c
+ $(HOSTCC) $(HOSTCFLAGS) -o scripts/split-include scripts/split-include.c
+
+#
+# RPM target
+#
+# If you do a make spec before packing the tarball you can rpm -ta it
+#
+spec:
+ . scripts/mkspec >kernel.spec
+
+#
+# Build a tar ball, generate an rpm from it and pack the result
+# There arw two bits of magic here
+# 1) The use of /. to avoid tar packing just the symlink
+# 2) Removing the .dep files as they have source paths in them that
+# will become invalid
+#
+rpm: clean spec
+ find . \( -size 0 -o -name .depend -o -name .hdepend \) -type f -print | xargs rm -f
+ set -e; \
+ cd $(TOPDIR)/.. ; \
+ ln -sf $(TOPDIR) $(KERNELPATH) ; \
+ tar -cvz --exclude CVS -f $(KERNELPATH).tar.gz $(KERNELPATH)/. ; \
+ rm $(KERNELPATH) ; \
+ cd $(TOPDIR) ; \
+ . scripts/mkversion > .version ; \
+ rpm -ta $(TOPDIR)/../$(KERNELPATH).tar.gz ; \
+ rm $(TOPDIR)/../$(KERNELPATH).tar.gz
--- /dev/null
+#
+# xeno/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina <skawina@geocities.com>
+# Added '-march' and '-mpreferred-stack-boundary' support
+#
+
+LD=$(CROSS_COMPILE)ld -m elf_i386
+OBJCOPY=$(CROSS_COMPILE)objcopy -O binary -R .note -R .comment -S
+LDFLAGS=-e stext
+LINKFLAGS =-T $(TOPDIR)/arch/xeno/vmlinux.lds $(LDFLAGS)
+
+CFLAGS += -pipe
+
+# prevent gcc from keeping the stack 16 byte aligned
+CFLAGS += $(shell if $(CC) -mpreferred-stack-boundary=2 -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-mpreferred-stack-boundary=2"; fi)
+
+ifdef CONFIG_M686
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MPENTIUMIII
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MPENTIUM4
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MK7
+CFLAGS += $(shell if $(CC) -march=athlon -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-march=athlon"; else echo "-march=i686 -malign-functions=4"; fi)
+endif
+
+HEAD := arch/xeno/kernel/head.o arch/xeno/kernel/init_task.o
+
+SUBDIRS += arch/xeno/kernel arch/xeno/mm arch/xeno/lib
+SUBDIRS += arch/xeno/drivers/console arch/xeno/drivers/network
+SUBDIRS += arch/xeno/drivers/dom0 arch/xeno/drivers/block
+
+CORE_FILES += arch/xeno/kernel/kernel.o arch/xeno/mm/mm.o
+CORE_FILES += arch/xeno/drivers/console/con.o
+CORE_FILES += arch/xeno/drivers/block/blk.o
+CORE_FILES += arch/xeno/drivers/network/net.o
+CORE_FILES += arch/xeno/drivers/dom0/dom0.o
+LIBS := $(TOPDIR)/arch/xeno/lib/lib.a $(LIBS) $(TOPDIR)/arch/xeno/lib/lib.a
+
+arch/xeno/kernel: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/kernel
+
+arch/xeno/mm: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/mm
+
+arch/xeno/drivers/console: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/console
+
+arch/xeno/drivers/network: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/network
+
+arch/xeno/drivers/block: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/block
+
+arch/xeno/drivers/dom0: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xeno/drivers/dom0
+
+MAKEBOOT = $(MAKE) -C arch/$(ARCH)/boot
+
+vmlinux: arch/xeno/vmlinux.lds
+
+FORCE: ;
+
+.PHONY: bzImage compressed clean archclean archmrproper archdep
+
+bzImage: vmlinux
+ @$(MAKEBOOT) image.gz
+
+archclean:
+ @$(MAKEBOOT) clean
+
+archmrproper:
+
+archdep:
+ @$(MAKEBOOT) dep
--- /dev/null
+#
+# arch/xeno/boot/Makefile
+#
+
+image.gz: image
+ gzip -f -9 < $< > $@
+
+image: $(TOPDIR)/vmlinux
+ # Guest OS header -- first 8 bytes are identifier 'XenoGues'.
+ echo -e -n 'XenoGues' >$@
+ # Guest OS header -- next 4 bytes are load address (0xC0000000).
+ echo -e -n '\000\000\000\300' >>$@
+ $(OBJCOPY) $< image.body
+ # Guest OS header is immediately followed by raw OS image.
+ # Start address must be at byte 0.
+ cat image.body >>$@
+ rm -f image.body
+
+dep:
+
+clean:
+ rm -f image image.gz
--- /dev/null
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/config-language.txt.
+#
+mainmenu_name "Linux Kernel Configuration"
+
+define_bool CONFIG_XENO y
+
+define_bool CONFIG_X86 y
+define_bool CONFIG_ISA y
+define_bool CONFIG_SBUS n
+
+define_bool CONFIG_UID16 y
+
+mainmenu_option next_comment
+comment 'Code maturity level options'
+bool 'Prompt for development and/or incomplete code/drivers' CONFIG_EXPERIMENTAL
+endmenu
+
+mainmenu_option next_comment
+comment 'Loadable module support'
+bool 'Enable loadable module support' CONFIG_MODULES
+if [ "$CONFIG_MODULES" = "y" ]; then
+ bool ' Set version information on all module symbols' CONFIG_MODVERSIONS
+ bool ' Kernel module loader' CONFIG_KMOD
+fi
+endmenu
+
+mainmenu_option next_comment
+comment 'Processor type and features'
+choice 'Processor family' \
+ "Pentium-Pro/Celeron/Pentium-II CONFIG_M686 \
+ Pentium-III/Celeron(Coppermine) CONFIG_MPENTIUMIII \
+ Pentium-4 CONFIG_MPENTIUM4 \
+ Athlon/Duron/K7 CONFIG_MK7" Pentium-Pro
+
+ define_bool CONFIG_X86_WP_WORKS_OK y
+ define_bool CONFIG_X86_INVLPG y
+ define_bool CONFIG_X86_CMPXCHG y
+ define_bool CONFIG_X86_XADD y
+ define_bool CONFIG_X86_BSWAP y
+ define_bool CONFIG_X86_POPAD_OK y
+ define_bool CONFIG_RWSEM_GENERIC_SPINLOCK n
+ define_bool CONFIG_RWSEM_XCHGADD_ALGORITHM y
+
+ define_bool CONFIG_X86_GOOD_APIC y
+ define_bool CONFIG_X86_PGE y
+ define_bool CONFIG_X86_USE_PPRO_CHECKSUM y
+ define_bool CONFIG_X86_TSC y
+
+if [ "$CONFIG_M686" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+if [ "$CONFIG_MPENTIUMIII" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+if [ "$CONFIG_MPENTIUM4" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 7
+fi
+if [ "$CONFIG_MK7" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 6
+ define_bool CONFIG_X86_USE_3DNOW y
+fi
+
+choice 'High Memory Support' \
+ "off CONFIG_NOHIGHMEM \
+ 4GB CONFIG_HIGHMEM4G \
+ 64GB CONFIG_HIGHMEM64G" off
+if [ "$CONFIG_HIGHMEM4G" = "y" ]; then
+ define_bool CONFIG_HIGHMEM y
+fi
+if [ "$CONFIG_HIGHMEM64G" = "y" ]; then
+ define_bool CONFIG_HIGHMEM y
+ define_bool CONFIG_X86_PAE y
+fi
+
+#bool 'Symmetric multi-processing support' CONFIG_SMP
+#if [ "$CONFIG_SMP" = "y" -a "$CONFIG_X86_CMPXCHG" = "y" ]; then
+# define_bool CONFIG_HAVE_DEC_LOCK y
+#fi
+endmenu
+
+mainmenu_option next_comment
+comment 'General setup'
+
+bool 'Networking support' CONFIG_NET
+
+bool 'System V IPC' CONFIG_SYSVIPC
+bool 'BSD Process Accounting' CONFIG_BSD_PROCESS_ACCT
+bool 'Sysctl support' CONFIG_SYSCTL
+if [ "$CONFIG_PROC_FS" = "y" ]; then
+ choice 'Kernel core (/proc/kcore) format' \
+ "ELF CONFIG_KCORE_ELF \
+ A.OUT CONFIG_KCORE_AOUT" ELF
+fi
+tristate 'Kernel support for a.out binaries' CONFIG_BINFMT_AOUT
+tristate 'Kernel support for ELF binaries' CONFIG_BINFMT_ELF
+tristate 'Kernel support for MISC binaries' CONFIG_BINFMT_MISC
+
+endmenu
+
+if [ "$CONFIG_NET" = "y" ]; then
+ source net/Config.in
+fi
+
+source drivers/block/Config.in
+define_bool CONFIG_BLK_DEV_IDE_MODES n
+define_bool CONFIG_BLK_DEV_HD n
+
+source fs/Config.in
+
+mainmenu_option next_comment
+comment 'Kernel hacking'
+
+bool 'Kernel debugging' CONFIG_DEBUG_KERNEL
+if [ "$CONFIG_DEBUG_KERNEL" != "n" ]; then
+ bool ' Debug high memory support' CONFIG_DEBUG_HIGHMEM
+ bool ' Debug memory allocations' CONFIG_DEBUG_SLAB
+ bool ' Memory mapped I/O debugging' CONFIG_DEBUG_IOVIRT
+ bool ' Magic SysRq key' CONFIG_MAGIC_SYSRQ
+ bool ' Spinlock debugging' CONFIG_DEBUG_SPINLOCK
+ bool ' Verbose BUG() reporting (adds 70K)' CONFIG_DEBUG_BUGVERBOSE
+ bool ' Load all symbols for debugging' CONFIG_KALLSYMS
+ bool ' Compile the kernel with frame pointers' CONFIG_FRAME_POINTER
+fi
+
+endmenu
--- /dev/null
+#
+# Automatically generated make config: don't edit
+#
+CONFIG_X86=y
+CONFIG_ISA=y
+# CONFIG_SBUS is not set
+CONFIG_UID16=y
+
+#
+# Code maturity level options
+#
+# CONFIG_EXPERIMENTAL is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODVERSIONS=y
+CONFIG_KMOD=y
+
+#
+# Processor type and features
+#
+# CONFIG_M386 is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+CONFIG_M686=y
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP2 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MCYRIXIII is not set
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_L1_CACHE_SHIFT=5
+CONFIG_X86_TSC=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_PGE=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
+# CONFIG_X86_CPUID is not set
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
+# CONFIG_MATH_EMULATION is not set
+# CONFIG_MTRR is not set
+# CONFIG_SMP is not set
+# CONFIG_X86_UP_APIC is not set
+
+#
+# General setup
+#
+CONFIG_NET=y
+# CONFIG_PCI is not set
+# CONFIG_EISA is not set
+# CONFIG_MCA is not set
+# CONFIG_HOTPLUG is not set
+# CONFIG_PCMCIA is not set
+# CONFIG_HOTPLUG_PCI is not set
+CONFIG_SYSVIPC=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_KCORE_ELF=y
+# CONFIG_KCORE_AOUT is not set
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_MISC is not set
+# CONFIG_PM is not set
+# CONFIG_APM_IGNORE_USER_SUSPEND is not set
+# CONFIG_APM_DO_ENABLE is not set
+# CONFIG_APM_CPU_IDLE is not set
+# CONFIG_APM_DISPLAY_BLANK is not set
+# CONFIG_APM_RTC_IS_GMT is not set
+# CONFIG_APM_ALLOW_INTS is not set
+# CONFIG_APM_REAL_MODE_POWER_OFF is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play configuration
+#
+# CONFIG_PNP is not set
+
+#
+# Block devices
+#
+# CONFIG_BLK_DEV_FD is not set
+# CONFIG_BLK_DEV_XD is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=4096
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_XENOLINUX_BLOCK=y
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+CONFIG_NETLINK=y
+CONFIG_RTNETLINK=y
+# CONFIG_NETLINK_DEV is not set
+# CONFIG_NETFILTER is not set
+CONFIG_FILTER=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_PNP=y
+# CONFIG_IP_PNP_DHCP is not set
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_INET_ECN is not set
+# CONFIG_SYN_COOKIES is not set
+
+#
+#
+#
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_DECNET is not set
+# CONFIG_BRIDGE is not set
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# ATA/IDE/MFM/RLL support
+#
+# CONFIG_IDE is not set
+# CONFIG_BLK_DEV_IDE_MODES is not set
+# CONFIG_BLK_DEV_HD is not set
+
+#
+# SCSI support
+#
+# CONFIG_SCSI is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION_BOOT is not set
+# CONFIG_FUSION_ISENSE is not set
+# CONFIG_FUSION_CTL is not set
+# CONFIG_FUSION_LAN is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+
+#
+# Network device support
+#
+# CONFIG_NETDEVICES is not set
+
+#
+# Amateur Radio support
+#
+# CONFIG_HAMRADIO is not set
+
+#
+# IrDA (infrared) support
+#
+# CONFIG_IRDA is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Old CD-ROM drivers (not SCSI, not IDE)
+#
+# CONFIG_CD_NO_IDESCSI is not set
+
+#
+# Input core support
+#
+# CONFIG_INPUT is not set
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+# CONFIG_SERIAL is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_UNIX98_PTYS is not set
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# Mice
+#
+# CONFIG_BUSMOUSE is not set
+# CONFIG_MOUSE is not set
+
+#
+# Joysticks
+#
+# CONFIG_INPUT_GAMEPORT is not set
+
+#
+# Input core support is needed for gameports
+#
+
+#
+# Input core support is needed for joysticks
+#
+# CONFIG_QIC02_TAPE is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_FTAPE is not set
+# CONFIG_AGP is not set
+# CONFIG_DRM is not set
+# CONFIG_MWAVE is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# File systems
+#
+# CONFIG_QUOTA is not set
+CONFIG_AUTOFS_FS=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_JBD=y
+# CONFIG_FAT_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_TMPFS is not set
+# CONFIG_RAMFS is not set
+# CONFIG_ISO9660_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_NTFS_FS is not set
+# CONFIG_HPFS_FS is not set
+CONFIG_PROC_FS=y
+# CONFIG_ROMFS_FS is not set
+CONFIG_EXT2_FS=y
+# CONFIG_SYSV_FS is not set
+# CONFIG_UDF_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+# CONFIG_CODA_FS is not set
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V3=y
+CONFIG_SUNRPC=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+# CONFIG_SMB_FS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_ZISOFS_FS is not set
+# CONFIG_ZLIB_FS_INFLATE is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_SMB_NLS is not set
+# CONFIG_NLS is not set
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+
+#
+# USB Controllers
+#
+
+#
+# USB Device Class drivers
+#
+
+#
+# USB Human Interface Devices (HID)
+#
+
+#
+# Input core support is needed for USB HID
+#
+
+#
+# USB Imaging devices
+#
+
+#
+# USB Multimedia devices
+#
+
+#
+# Video4Linux support is needed for USB Multimedia device support
+#
+
+#
+# USB Network adaptors
+#
+
+#
+# USB port drivers
+#
+
+#
+# USB Serial Converter support
+#
+
+#
+# USB Miscellaneous drivers
+#
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_HIGHMEM is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_IOVIRT is not set
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_KALLSYMS=y
+# CONFIG_FRAME_POINTER is not set
+
+# Grim cruft
+#
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_BLK_STATS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JBD_DEBUG is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+
+
+
+
--- /dev/null
+O_TARGET := blk.o
+obj-y := xl_block.o xl_block_test.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/******************************************************************************
+ * xl_block.c
+ *
+ * Xenolinux virtual block-device driver.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+
+#include <linux/fs.h>
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/major.h>
+
+#include <asm/hypervisor-ifs/block.h>
+#include <asm/hypervisor-ifs/hypervisor-if.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+#define MAJOR_NR XLBLK_MAJOR /* force defns in blk.h, must precede include */
+static int xlblk_major = XLBLK_MAJOR;
+#include <linux/blk.h>
+
+/* Copied from linux/ide.h */
+typedef unsigned char byte;
+
+void xlblk_ide_register_disk(int, unsigned long);
+
+#define XLBLK_MAX 32 /* Maximum minor devices we support */
+#define XLBLK_MAJOR_NAME "xhd"
+#define IDE_PARTN_BITS 6 /* from ide.h::PARTN_BITS */
+#define IDE_PARTN_MASK ((1<<IDE_PARTN_BITS)-1) /* from ide.h::PARTN_MASK */
+static int xlblk_blk_size[XLBLK_MAX];
+static int xlblk_blksize_size[XLBLK_MAX];
+static int xlblk_read_ahead;
+static int xlblk_hardsect_size[XLBLK_MAX];
+static int xlblk_max_sectors[XLBLK_MAX];
+
+#define XLBLK_RESPONSE_IRQ _EVENT_BLK_RESP
+
+#define DEBUG_IRQ _EVENT_DEBUG
+
+#if 0
+#define DPRINTK(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#define DPRINTK_IOCTL(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#else
+#define DPRINTK(_f, _a...) ((void)0)
+#define DPRINTK_IOCTL(_f, _a...) ((void)0)
+#endif
+
+static blk_ring_t *blk_ring;
+static unsigned int resp_cons; /* Response consumer for comms ring. */
+static xen_disk_info_t xen_disk_info;
+
+int hypervisor_request(void * id,
+ int operation,
+ char * buffer,
+ unsigned long block_number,
+ unsigned short block_size,
+ kdev_t device);
+
+
+/* ------------------------------------------------------------------------
+ */
+
+static int xenolinux_block_open(struct inode *inode, struct file *filep)
+{
+ DPRINTK("xenolinux_block_open\n");
+ return 0;
+}
+
+static int xenolinux_block_release(struct inode *inode, struct file *filep)
+{
+ DPRINTK("xenolinux_block_release\n");
+ return 0;
+}
+
+static int xenolinux_block_ioctl(struct inode *inode, struct file *filep,
+ unsigned command, unsigned long argument)
+{
+ int minor_dev;
+ struct hd_geometry *geo = (struct hd_geometry *)argument;
+
+ DPRINTK("xenolinux_block_ioctl\n");
+
+ /* check permissions */
+ if (!capable(CAP_SYS_ADMIN)) return -EPERM;
+ if (!inode) return -EINVAL;
+ minor_dev = MINOR(inode->i_rdev);
+ if (minor_dev >= XLBLK_MAX) return -ENODEV;
+
+ DPRINTK_IOCTL("command: 0x%x, argument: 0x%lx, minor: 0x%x\n",
+ command, (long) argument, minor_dev);
+
+ switch (command)
+ {
+ case BLKGETSIZE:
+ DPRINTK_IOCTL(" BLKGETSIZE: %x %lx\n", BLKGETSIZE,
+ (long) xen_disk_info.disks[0].capacity);
+ return put_user(xen_disk_info.disks[0].capacity,
+ (unsigned long *) argument);
+
+ case BLKRRPART:
+ DPRINTK_IOCTL(" BLKRRPART: %x\n", BLKRRPART);
+ break;
+
+ case BLKSSZGET:
+ DPRINTK_IOCTL(" BLKSSZGET: %x 0x%x\n", BLKSSZGET,
+ xlblk_hardsect_size[minor_dev]);
+ return xlblk_hardsect_size[minor_dev];
+
+ case HDIO_GETGEO:
+ DPRINTK_IOCTL(" HDIO_GETGEO: %x\n", HDIO_GETGEO);
+ if (!argument) return -EINVAL;
+ if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
+ if (put_user(0xff, (byte *)&geo->heads)) return -EFAULT;
+ if (put_user(0x3f, (byte *)&geo->sectors)) return -EFAULT;
+ if (put_user(0x106, (unsigned short *)&geo->cylinders)) return -EFAULT;
+ return 0;
+
+ case HDIO_GETGEO_BIG:
+ DPRINTK_IOCTL(" HDIO_GETGEO_BIG: %x\n", HDIO_GETGEO_BIG);
+ if (!argument) return -EINVAL;
+ if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
+ if (put_user(0xff, (byte *)&geo->heads)) return -EFAULT;
+ if (put_user(0x3f, (byte *)&geo->sectors)) return -EFAULT;
+ if (put_user(0x106, (unsigned int *) &geo->cylinders)) return -EFAULT;
+
+ return 0;
+
+ default:
+ DPRINTK_IOCTL(" eh? unknown ioctl\n");
+ break;
+ }
+
+ return 0;
+}
+
+static int xenolinux_block_check(kdev_t dev)
+{
+ DPRINTK("xenolinux_block_check\n");
+ return 0;
+}
+
+static int xenolinux_block_revalidate(kdev_t dev)
+{
+ DPRINTK("xenolinux_block_revalidate\n");
+ return 0;
+}
+
+/*
+ * hypervisor_request
+ *
+ * request block io
+ *
+ * id: for guest use only.
+ * operation: XEN_BLOCK_READ, XEN_BLOCK_WRITE or XEN_BLOCK_PROBE
+ * buffer: buffer to read/write into. this should be a
+ * virtual address in the guest os.
+ * block_number: block to read
+ * block_size: size of each block
+ * device: ide/hda is 768 or 0x300
+ */
+int hypervisor_request(void * id,
+ int operation,
+ char * buffer,
+ unsigned long block_number,
+ unsigned short block_size,
+ kdev_t device)
+{
+ int position;
+ void *buffer_ma;
+ kdev_t phys_device = (kdev_t) 0;
+ unsigned long sector_number = 0;
+ struct gendisk *gd;
+
+ /*
+ * Bail if there's no room in the request communication ring. This may be
+ * because we have a whole bunch of outstanding responses to process. No
+ * matter, as the response handler will kick the request queue.
+ */
+ if ( BLK_RING_INC(blk_ring->req_prod) == resp_cons )
+ return 1;
+
+ buffer_ma = (void *)phys_to_machine(virt_to_phys(buffer));
+
+ switch ( operation )
+ {
+ case XEN_BLOCK_PROBE:
+ phys_device = (kdev_t) 0;
+ sector_number = 0;
+ break;
+
+ case XEN_BLOCK_READ:
+ case XEN_BLOCK_WRITE:
+ if ( MAJOR(device) != XLBLK_MAJOR )
+ panic("error: xl_block::hypervisor_request: "
+ "unknown device [0x%x]\n", device);
+ phys_device = MKDEV(IDE0_MAJOR, 0);
+ /* Compute real buffer location on disk */
+ sector_number = block_number;
+ if ( (gd = (struct gendisk *)xen_disk_info.disks[0].gendisk) != NULL )
+ sector_number += gd->part[MINOR(device)&IDE_PARTN_MASK].start_sect;
+ break;
+
+ default:
+ panic("unknown op %d\n", operation);
+ }
+
+ /* Fill out a communications ring structure & trap to the hypervisor */
+ position = blk_ring->req_prod;
+ blk_ring->ring[position].req.id = id;
+ blk_ring->ring[position].req.operation = operation;
+ blk_ring->ring[position].req.buffer = buffer_ma;
+ blk_ring->ring[position].req.block_number = block_number;
+ blk_ring->ring[position].req.block_size = block_size;
+ blk_ring->ring[position].req.device = phys_device;
+ blk_ring->ring[position].req.sector_number = sector_number;
+
+ blk_ring->req_prod = BLK_RING_INC(position);
+
+ return 0;
+}
+
+
+/*
+ * do_xlblk_request
+ * read a block; request is in a request queue
+ */
+static void do_xlblk_request (request_queue_t *rq)
+{
+ struct request *req;
+ struct buffer_head *bh;
+ int rw, nsect, full, queued = 0;
+
+ DPRINTK("xlblk.c::do_xlblk_request for '%s'\n", DEVICE_NAME);
+
+ while ( !rq->plugged && !QUEUE_EMPTY )
+ {
+ if ( (req = CURRENT) == NULL ) goto out;
+
+ DPRINTK("do_xlblk_request %p: cmd %i, sec %lx, (%li/%li) bh:%p\n",
+ req, req->cmd, req->sector,
+ req->current_nr_sectors, req->nr_sectors, req->bh);
+
+ rw = req->cmd;
+ if ( rw == READA ) rw = READ;
+ if ((rw != READ) && (rw != WRITE))
+ panic("XenoLinux Virtual Block Device: bad cmd: %d\n", rw);
+
+ req->errors = 0;
+
+ bh = req->bh;
+ while ( bh != NULL )
+ {
+ full = hypervisor_request(
+ bh, (rw == READ) ? XEN_BLOCK_READ : XEN_BLOCK_WRITE,
+ bh->b_data, bh->b_rsector, bh->b_size, bh->b_dev);
+
+ if ( full ) goto out;
+
+ queued++;
+
+ /* Dequeue the buffer head from the request. */
+ nsect = bh->b_size >> 9;
+ req->bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+ bh = req->bh;
+
+ if ( bh != NULL )
+ {
+ /* There's another buffer head to do. Update the request. */
+ req->hard_sector += nsect;
+ req->hard_nr_sectors -= nsect;
+ req->sector = req->hard_sector;
+ req->nr_sectors = req->hard_nr_sectors;
+ req->current_nr_sectors = bh->b_size >> 9;
+ req->buffer = bh->b_data;
+ }
+ else
+ {
+ /* That was the last buffer head. Finalise the request. */
+ if ( end_that_request_first(req, 1, "XenBlk") ) BUG();
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+ }
+ }
+ }
+
+ out:
+ if ( queued != 0 ) HYPERVISOR_block_io_op();
+}
+
+
+static struct block_device_operations xenolinux_block_fops =
+{
+ open: xenolinux_block_open,
+ release: xenolinux_block_release,
+ ioctl: xenolinux_block_ioctl,
+ check_media_change: xenolinux_block_check,
+ revalidate: xenolinux_block_revalidate,
+};
+
+static void xlblk_response_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ int i;
+ unsigned long flags;
+ struct buffer_head *bh;
+
+ spin_lock_irqsave(&io_request_lock, flags);
+
+ for ( i = resp_cons;
+ i != blk_ring->resp_prod;
+ i = BLK_RING_INC(i) )
+ {
+ blk_ring_resp_entry_t *bret = &blk_ring->ring[i].resp;
+ if ( (bh = bret->id) != NULL ) bh->b_end_io(bh, 1);
+ }
+
+ resp_cons = i;
+
+ /* KAF: We can push work down at this point. We have the lock. */
+ do_xlblk_request(BLK_DEFAULT_QUEUE(MAJOR_NR));
+
+ spin_unlock_irqrestore(&io_request_lock, flags);
+}
+
+
+int __init xlblk_init(void)
+{
+ int i, error, result;
+
+ /* This mapping was created early at boot time. */
+ blk_ring = (blk_ring_t *)fix_to_virt(FIX_BLKRING_BASE);
+ blk_ring->req_prod = blk_ring->resp_prod = resp_cons = 0;
+
+ error = request_irq(XLBLK_RESPONSE_IRQ, xlblk_response_int, 0,
+ "xlblk-response", NULL);
+ if (error) {
+ printk(KERN_ALERT "Could not allocate receive interrupt\n");
+ goto fail;
+ }
+
+ memset (&xen_disk_info, 0, sizeof(xen_disk_info));
+ xen_disk_info.count = 0;
+
+ if ( hypervisor_request(NULL, XEN_BLOCK_PROBE, (char *) &xen_disk_info,
+ 0, 0, (kdev_t) 0) )
+ BUG();
+ HYPERVISOR_block_io_op();
+ while ( blk_ring->resp_prod != 1 ) barrier();
+ for ( i = 0; i < xen_disk_info.count; i++ )
+ {
+ printk (KERN_ALERT " %2d: type: %d, capacity: %ld\n",
+ i, xen_disk_info.disks[i].type,
+ xen_disk_info.disks[i].capacity);
+ }
+
+ SET_MODULE_OWNER(&xenolinux_block_fops);
+ result = register_blkdev(xlblk_major, "block", &xenolinux_block_fops);
+ if (result < 0) {
+ printk (KERN_ALERT "xenolinux block: can't get major %d\n",
+ xlblk_major);
+ return result;
+ }
+
+ /* initialize global arrays in drivers/block/ll_rw_block.c */
+ for (i = 0; i < XLBLK_MAX; i++) {
+ xlblk_blk_size[i] = xen_disk_info.disks[0].capacity;
+ xlblk_blksize_size[i] = 512;
+ xlblk_hardsect_size[i] = 512;
+ xlblk_max_sectors[i] = 128;
+ }
+ xlblk_read_ahead = 8;
+
+ blk_size[xlblk_major] = xlblk_blk_size;
+ blksize_size[xlblk_major] = xlblk_blksize_size;
+ hardsect_size[xlblk_major] = xlblk_hardsect_size;
+ read_ahead[xlblk_major] = xlblk_read_ahead;
+ max_sectors[xlblk_major] = xlblk_max_sectors;
+
+ blk_init_queue(BLK_DEFAULT_QUEUE(xlblk_major), do_xlblk_request);
+
+ /*
+ * Turn off barking 'headactive' mode. We dequeue buffer heads as
+ * soon as we pass them down to Xen.
+ */
+ blk_queue_headactive(BLK_DEFAULT_QUEUE(xlblk_major), 0);
+
+ xlblk_ide_register_disk(0, xen_disk_info.disks[0].capacity);
+
+ printk(KERN_ALERT
+ "XenoLinux Virtual Block Device Driver installed [device: %d]\n",
+ xlblk_major);
+ return 0;
+
+ fail:
+ return error;
+}
+
+void xlblk_ide_register_disk(int idx, unsigned long capacity)
+{
+ int units;
+ int minors;
+ struct gendisk *gd;
+
+ /* plagarized from ide-probe.c::init_gendisk */
+
+ units = 2; /* from ide.h::MAX_DRIVES */
+
+ minors = units * (1<<IDE_PARTN_BITS);
+ gd = kmalloc (sizeof(struct gendisk), GFP_KERNEL);
+ gd->sizes = kmalloc (minors * sizeof(int), GFP_KERNEL);
+ gd->part = kmalloc (minors * sizeof(struct hd_struct), GFP_KERNEL);
+ memset(gd->part, 0, minors * sizeof(struct hd_struct));
+
+ gd->major = xlblk_major;
+ gd->major_name = XLBLK_MAJOR_NAME;
+ gd->minor_shift = IDE_PARTN_BITS;
+ gd->max_p = 1<<IDE_PARTN_BITS;
+ gd->nr_real = units;
+ gd->real_devices = NULL;
+ gd->next = NULL;
+ gd->fops = &xenolinux_block_fops;
+ gd->de_arr = kmalloc (sizeof *gd->de_arr * units, GFP_KERNEL);
+ gd->flags = kmalloc (sizeof *gd->flags * units, GFP_KERNEL);
+
+ if (gd->de_arr)
+ memset (gd->de_arr, 0, sizeof *gd->de_arr * units);
+
+ if (gd->flags)
+ memset (gd->flags, 0, sizeof *gd->flags * units);
+
+ add_gendisk(gd);
+
+ xen_disk_info.disks[idx].gendisk = gd;
+
+ /* default disk size is just a big number. in the future, we
+ need a message to probe the devices to determine the actual size */
+ register_disk(gd, MKDEV(xlblk_major, 0), 1<<IDE_PARTN_BITS,
+ &xenolinux_block_fops, capacity);
+
+ return;
+}
+
+
+
+static void __exit xlblk_cleanup(void)
+{
+ /* CHANGE FOR MULTIQUEUE */
+ blk_cleanup_queue(BLK_DEFAULT_QUEUE(xlblk_major));
+
+ /* clean up global arrays */
+ read_ahead[xlblk_major] = 0;
+
+ if (blk_size[xlblk_major])
+ kfree(blk_size[xlblk_major]);
+ blk_size[xlblk_major] = NULL;
+
+ if (blksize_size[xlblk_major])
+ kfree(blksize_size[xlblk_major]);
+ blksize_size[xlblk_major] = NULL;
+
+ if (hardsect_size[xlblk_major])
+ kfree(hardsect_size[xlblk_major]);
+ hardsect_size[xlblk_major] = NULL;
+
+ /* XXX: free each gendisk */
+ if (unregister_blkdev(xlblk_major, "block"))
+ printk(KERN_ALERT
+ "XenoLinux Virtual Block Device Driver uninstalled w/ errs\n");
+ else
+ printk(KERN_ALERT
+ "XenoLinux Virtual Block Device Driver uninstalled\n");
+
+ return;
+}
+
+
+#ifdef MODULE
+module_init(xlblk_init);
+module_exit(xlblk_cleanup);
+#endif
--- /dev/null
+/******************************************************************************
+ * xenolinux_block_test.c
+ *
+ */
+#define EXPORT_SYMTAB
+
+#include <linux/config.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <asm/uaccess.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+
+#include <asm/hypervisor-ifs/block.h>
+#include <asm/hypervisor-ifs/hypervisor-if.h>
+
+/******************************************************************/
+
+static struct proc_dir_entry *bdt;
+static blk_ring_req_entry_t meta;
+static char * data;
+
+static int proc_read_bdt(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ switch (meta.operation)
+ {
+ case XEN_BLOCK_READ :
+ case XEN_BLOCK_WRITE :
+ {
+ return proc_dump_block(page, start, off, count, eof, data);
+ }
+ case XEN_BLOCK_DEBUG :
+ {
+ return proc_dump_debug(page, start, off, count, eof, data);
+ }
+ default :
+ {
+ printk(KERN_ALERT
+ "block device test error: unknown operation [%c]\n",
+ meta.operation);
+ return -EINVAL;
+ }
+ }
+}
+
+int proc_dump_debug(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ char header[100];
+ char dump[1024];
+
+ sprintf (header, "Block Device Test: Debug Dump\n\n");
+
+ sprintf (dump, "%s\n", meta.buffer);
+
+ if (data)
+ {
+ kfree(data);
+ }
+
+ strncpy (page, dump, count);
+ return strlen(page);
+}
+
+int proc_dump_block(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ char header[100];
+ char dump[1024];
+ char temp[100];
+ int loop;
+
+ sprintf (header, "Block Device Test\n\n%s blk num: %ld 0x%lx; size: %d 0x%x; device: 0x%x\n",
+ meta.operation == XEN_BLOCK_WRITE ? "write" : "read",
+ meta.block_number, meta.block_number,
+ meta.block_size, meta.block_size,
+ meta.device);
+
+ sprintf (dump, "%s", header);
+
+ if (meta.buffer)
+ {
+ for (loop = 0; loop < 100; loop++)
+ {
+ int i = meta.buffer[loop];
+
+ if (loop % 8 == 0)
+ {
+ sprintf (temp, "[%2d] ", loop);
+ strcat(dump, temp);
+ }
+ else if (loop % 2 == 0)
+ {
+ strcat(dump, " ");
+ }
+
+ sprintf (temp, " 0x%02x", i & 255);
+ strcat(dump, temp);
+ if ((loop + 1) % 8 == 0)
+ {
+ strcat(dump, "\n");
+ }
+ }
+ strcat(dump, "\n\n");
+ }
+
+ if (data)
+ {
+ kfree(data);
+ }
+
+ strncpy (page, dump, count);
+ return strlen(page);
+}
+
+int proc_write_bdt(struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ char *local = kmalloc((count + 1) * sizeof(char), GFP_KERNEL);
+ char opcode;
+ int block_number = 0;
+ int block_size = 0;
+ int device = 0;
+
+ if (copy_from_user(local, buffer, count))
+ {
+ return -EFAULT;
+ }
+ local[count] = '\0';
+
+ sscanf(local, "%c %i %i %i",
+ &opcode, &block_number, &block_size, &device);
+
+ if (opcode == 'r' || opcode == 'R')
+ {
+ meta.operation = XEN_BLOCK_READ;
+ }
+ else if (opcode == 'w' || opcode == 'W')
+ {
+ meta.operation = XEN_BLOCK_WRITE;
+ }
+ else if (opcode == 'd' || opcode == 'D')
+ {
+ meta.operation = XEN_BLOCK_DEBUG;
+ block_size = 10000;
+ }
+ else
+ {
+ printk(KERN_ALERT
+ "block device test error: unknown opcode [%c]\n", opcode);
+ return -EINVAL;
+ }
+
+ if (data)
+ {
+ kfree(data);
+ }
+ data = kmalloc(block_size * sizeof(char), GFP_KERNEL);
+ if (data == NULL)
+ {
+ kfree(local);
+ return -ENOMEM;
+ }
+
+ meta.block_number = block_number;
+ meta.block_size = block_size;
+ meta.device = device;
+ meta.buffer = data;
+
+ /* submit request */
+ hypervisor_request(0, meta.operation, meta.buffer,
+ meta.block_number, meta.block_size,
+ meta.device);
+ HYPERVISOR_block_io_op();
+ mdelay(1000); /* should wait for a proper acknowledgement/response. */
+
+ kfree(local);
+ return count;
+}
+
+
+static int __init init_module(void)
+{
+ int return_value = 0;
+
+ /* create proc entry */
+ bdt = create_proc_entry("bdt", 0644, NULL);
+ if (bdt == NULL)
+ {
+ return_value = -ENOMEM;
+ goto error;
+ }
+ bdt->data = NULL;
+ bdt->read_proc = proc_read_bdt;
+ bdt->write_proc = proc_write_bdt;
+ bdt->owner = THIS_MODULE;
+
+ memset(&meta, 0, sizeof(meta));
+
+ /* success */
+ printk(KERN_ALERT "XenoLinux Block Device Test installed\n");
+ return 0;
+
+ error:
+ return return_value;
+}
+
+static void __exit cleanup_module(void)
+{
+ if (data)
+ {
+ kfree(data);
+ }
+ printk(KERN_ALERT "XenoLinux Block Device Test uninstalled\n");
+}
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+O_TARGET := con.o
+obj-y := console.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/******************************************************************************
+ * console.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/serial.h>
+#include <linux/major.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/console.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/uaccess.h>
+#include <asm/hypervisor.h>
+
+/******************** Kernel console driver ********************************/
+
+static void kconsole_write(struct console *co, const char *s, unsigned count)
+{
+#define STRLEN 256
+ static char str[STRLEN];
+ static int pos = 0;
+ int len;
+
+ /* We buffer output until we see a newline, or until the buffer is full. */
+ while ( count != 0 )
+ {
+ len = ((STRLEN - pos) > count) ? count : STRLEN - pos;
+ memcpy(str + pos, s, len);
+ pos += len;
+ s += len;
+ count -= len;
+ if ( (pos == STRLEN) || (str[pos-1] == '\n') )
+ {
+ (void)HYPERVISOR_console_write(str, pos);
+ pos = 0;
+ }
+ }
+}
+
+static kdev_t kconsole_device(struct console *c)
+{
+ /*
+ * This is the magic that binds our "struct console" to our
+ * "tty_struct", defined below.
+ */
+ return MKDEV(TTY_MAJOR, 0);
+}
+
+static struct console kconsole_info = {
+ name: "xenocon",
+ write: kconsole_write,
+ device: kconsole_device,
+ flags: CON_PRINTBUFFER,
+ index: -1,
+};
+
+void xeno_console_init(void)
+{
+ register_console(&kconsole_info);
+}
+
+
+/******************** Initial /dev/console *********************************/
+
+
+static struct tty_driver console_driver;
+static int console_refcount;
+static struct tty_struct *console_table[1];
+static struct termios *console_termios[1];
+static struct termios *console_termios_locked[1];
+
+static int console_write_room(struct tty_struct *tty)
+{
+ return INT_MAX;
+}
+
+static int console_chars_in_buffer(struct tty_struct *tty)
+{
+ return 0;
+}
+
+static inline int console_xmit(int ch)
+{
+ char _ch = ch;
+ kconsole_write(NULL, &_ch, 1);
+ return 1;
+}
+
+static int console_write(struct tty_struct *tty, int from_user,
+ const u_char * buf, int count)
+{
+ int i;
+
+ if ( from_user && verify_area(VERIFY_READ, buf, count) )
+ {
+ return -EINVAL;
+ }
+
+ for ( i = 0; i < count; i++ )
+ {
+ char ch;
+ if ( from_user )
+ {
+ __get_user(ch, buf + i);
+ }
+ else
+ {
+ ch = buf[i];
+ }
+ console_xmit(ch);
+ }
+ return i;
+}
+
+static void console_put_char(struct tty_struct *tty, u_char ch)
+{
+ console_xmit(ch);
+}
+
+static int console_open(struct tty_struct *tty, struct file *filp)
+{
+ int line;
+
+ MOD_INC_USE_COUNT;
+ line = MINOR(tty->device) - tty->driver.minor_start;
+ if ( line )
+ {
+ MOD_DEC_USE_COUNT;
+ return -ENODEV;
+ }
+
+ tty->driver_data = NULL;
+
+ return 0;
+}
+
+static void console_close(struct tty_struct *tty, struct file *filp)
+{
+ MOD_DEC_USE_COUNT;
+}
+
+static int __init console_ini(void)
+{
+ memset(&console_driver, 0, sizeof(struct tty_driver));
+ console_driver.magic = TTY_DRIVER_MAGIC;
+ console_driver.driver_name = "xeno_console";
+ console_driver.name = "console";
+ console_driver.major = TTY_MAJOR;
+ console_driver.minor_start = 0;
+ console_driver.num = 1;
+ console_driver.type = TTY_DRIVER_TYPE_SERIAL;
+ console_driver.subtype = SERIAL_TYPE_NORMAL;
+ console_driver.init_termios = tty_std_termios;
+ console_driver.flags = TTY_DRIVER_REAL_RAW;
+ console_driver.refcount = &console_refcount;
+ console_driver.table = console_table;
+ console_driver.termios = console_termios;
+ console_driver.termios_locked = console_termios_locked;
+ /* Functions */
+ console_driver.open = console_open;
+ console_driver.close = console_close;
+ console_driver.write = console_write;
+ console_driver.write_room = console_write_room;
+ console_driver.put_char = console_put_char;
+ console_driver.chars_in_buffer = console_chars_in_buffer;
+
+ if ( tty_register_driver(&console_driver) )
+ {
+ printk(KERN_ERR "Couldn't register Xeno console driver\n");
+ }
+ else
+ {
+ printk("Xeno console successfully installed\n");
+ }
+
+ return 0;
+}
+
+static void __exit console_fin(void)
+{
+ int ret;
+
+ ret = tty_unregister_driver(&console_driver);
+ if ( ret != 0 )
+ {
+ printk(KERN_ERR "Unable to unregister Xeno console driver: %d\n", ret);
+ }
+}
+
+module_init(console_ini);
+module_exit(console_fin);
+
--- /dev/null
+O_TARGET := dom0.o
+obj-y := dom0_memory.o dom0_core.o vfr.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * domain 0 block driver interface
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
+static int __init init_module(void)
+{
+ request_module("xl_block");
+ printk("Successfully installed domain 0 block interface\n");
+
+
+ return 0;
+}
+
+static void __exit cleanup_module(void)
+{
+ printk("Successfully de-installed domain-0 block interface\n");
+ return 0;
+}
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+/******************************************************************************
+ * dom0_core.c
+ *
+ * Interface to privileged domain-0 commands.
+ *
+ * Copyright (c) 2002, K A Fraser, B Dragovic
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+
+#include "dom0_ops.h"
+
+/* Private proc-file data structures. */
+typedef struct proc_data {
+ unsigned int domain;
+ unsigned long map_size;
+} dom_procdata_t;
+
+typedef struct proc_mem_data {
+ unsigned long pfn;
+ int tot_pages;
+} proc_memdata_t;
+
+#define XENO_BASE "xeno"
+#define DOM0_CMD_INTF "dom0_cmd"
+#define DOM0_NEWDOM "new_dom_data"
+
+#define MAX_LEN 16
+#define DOM_DIR "dom"
+#define DOM_MEM "mem"
+#define DOM_VIF "vif"
+
+#define MAP_DISCONT 1
+
+static struct proc_dir_entry *xeno_base;
+static struct proc_dir_entry *dom0_cmd_intf;
+static struct proc_dir_entry *proc_ft;
+
+unsigned long direct_mmap(unsigned long, unsigned long, pgprot_t, int, int);
+int direct_unmap(unsigned long, unsigned long);
+int direct_disc_unmap(unsigned long, unsigned long, int);
+
+static unsigned char readbuf[1204];
+
+static int cmd_read_proc(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ strcpy(page, readbuf);
+ *readbuf = '\0';
+ *eof = 1;
+ *start = page;
+ return strlen(page);
+}
+
+static ssize_t dom_vif_read(struct file * file, char * buff, size_t size, loff_t * off)
+{
+ char hyp_buf[128]; // Hypervisor is going to write its reply here.
+ network_op_t op;
+ static int finished = 0;
+
+ // This seems to be the only way to make the OS stop making read requests
+ // to the file. When we use the fileoperations version of read, offset
+ // seems to be ignored altogether.
+
+ if (finished)
+ {
+ finished = 0;
+ return 0;
+ }
+
+ op.cmd = NETWORK_OP_VIFQUERY;
+ op.u.vif_query.domain = (unsigned int) ((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
+ op.u.vif_query.buf = hyp_buf;
+
+ strcpy(hyp_buf, "Error getting domain's vif list from hypervisor.\n"); // This will be replaced if everything works.
+
+ (void)HYPERVISOR_network_op(&op);
+
+ if (*off >= (strlen(hyp_buf)+1)) return 0;
+
+ copy_to_user(buff, hyp_buf, strlen(hyp_buf));
+
+ finished = 1;
+
+ return strlen(hyp_buf)+1;
+}
+
+struct file_operations dom_vif_ops = {
+ read: dom_vif_read
+};
+
+
+static void create_proc_dom_entries(int dom)
+{
+ struct proc_dir_entry * dir;
+ dom_procdata_t * dom_data;
+ char dir_name[MAX_LEN];
+ struct proc_dir_entry * file;
+
+ snprintf(dir_name, MAX_LEN, "%s%d", DOM_DIR, dom);
+
+ dom_data = (dom_procdata_t *)kmalloc(sizeof(dom_procdata_t), GFP_KERNEL);
+ dom_data->domain = dom;
+
+ dir = proc_mkdir(dir_name, xeno_base);
+ dir->data = dom_data;
+
+ file = create_proc_entry(DOM_VIF, 0600, dir);
+ if (file != NULL)
+ {
+ file->owner = THIS_MODULE;
+ file->nlink = 1;
+ file->proc_fops = &dom_vif_ops;
+ file->data = (void *) dom;
+ }
+}
+
+static ssize_t dom_mem_write(struct file * file, const char * buff,
+ size_t size , loff_t * off)
+{
+ dom_mem_t mem_data;
+
+ copy_from_user(&mem_data, (dom_mem_t *)buff, sizeof(dom_mem_t));
+
+ if(direct_disc_unmap(mem_data.vaddr, mem_data.start_pfn,
+ mem_data.tot_pages) == 0){
+ return sizeof(sizeof(dom_mem_t));
+ } else {
+ return -1;
+ }
+}
+
+static ssize_t dom_mem_read(struct file * file, char * buff, size_t size, loff_t * off)
+{
+ unsigned long addr;
+ pgprot_t prot;
+
+ proc_memdata_t * mem_data = (proc_memdata_t *)((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
+
+ prot = PAGE_SHARED;
+
+ /* remap the range using xen specific routines */
+
+ addr = direct_mmap(mem_data->pfn << PAGE_SHIFT, mem_data->tot_pages << PAGE_SHIFT, prot, MAP_DISCONT, mem_data->tot_pages);
+
+ copy_to_user((unsigned long *)buff, &addr, sizeof(addr));
+
+ return sizeof(addr);
+}
+
+struct file_operations dom_mem_ops = {
+ read: dom_mem_read,
+ write: dom_mem_write,
+};
+
+static int dom_map_mem(unsigned int dom, unsigned long pfn, int tot_pages)
+{
+ int ret = -ENOENT;
+ struct proc_dir_entry * pd = xeno_base->subdir;
+ struct proc_dir_entry * file;
+ proc_memdata_t * memdata;
+
+ while(pd != NULL){
+
+ if((pd->mode & S_IFDIR) && ((dom_procdata_t *)pd->data)->domain == dom){
+
+ /* check if there is already an entry for mem and if so
+ * remove it.
+ */
+ remove_proc_entry(DOM_MEM, pd);
+
+ /* create new entry with parameters describing what to do
+ * when it is mmaped.
+ */
+ file = create_proc_entry(DOM_MEM, 0600, pd);
+ if(file != NULL)
+ {
+ file->owner = THIS_MODULE;
+ file->nlink = 1;
+ file->proc_fops = &dom_mem_ops;
+
+ memdata = (proc_memdata_t *)kmalloc(sizeof(proc_memdata_t), GFP_KERNEL);
+ memdata->pfn = pfn;
+ memdata->tot_pages = tot_pages;
+ file->data = memdata;
+
+ ret = 0;
+ break;
+ }
+
+ ret = -EAGAIN;
+ break;
+ }
+ pd = pd->next;
+ }
+
+ return ret;
+}
+
+/* function used to retrieve data associated with new domain */
+static ssize_t dom_data_read(struct file * file, char * buff, size_t size, loff_t * off)
+{
+ dom0_newdomain_t * dom_data = (dom0_newdomain_t *)
+ ((struct proc_dir_entry *)file->f_dentry->d_inode->u.generic_ip)->data;
+
+ copy_to_user((dom0_newdomain_t *)buff, dom_data, sizeof(dom0_newdomain_t));
+
+ remove_proc_entry(DOM0_NEWDOM, xeno_base);
+
+ kfree(dom_data);
+
+ return sizeof(dom0_newdomain_t);
+}
+
+struct file_operations newdom_data_fops = {
+ read: dom_data_read,
+};
+
+static int cmd_write_proc(struct file *file, const char *buffer,
+ u_long count, void *data)
+{
+ dom0_op_t op;
+ int ret = 0;
+ struct proc_dir_entry * new_dom_id;
+ dom0_newdomain_t * params;
+ int i;
+ unsigned long p;
+
+ copy_from_user(&op, buffer, sizeof(dom0_op_t));
+
+ /* do some sanity checks */
+ if(op.cmd > MAX_CMD){
+ ret = -ENOSYS;
+ goto out;
+ }
+
+ if ( op.cmd == MAP_DOM_MEM )
+ {
+ ret = dom_map_mem(op.u.dommem.domain, op.u.dommem.start_pfn,
+ op.u.dommem.tot_pages);
+ }
+ else if ( op.cmd == DO_PGUPDATES )
+ {
+ ret = HYPERVISOR_pt_update(op.u.pgupdate.pgt_update_arr,
+ op.u.pgupdate.num_pgt_updates);
+ }
+ else
+ {
+ ret = HYPERVISOR_dom0_op(&op);
+
+ /* if new domain created, create proc entries */
+ if(op.cmd == DOM0_NEWDOMAIN){
+ create_proc_dom_entries(ret);
+
+ params = (dom0_newdomain_t *)kmalloc(sizeof(dom0_newdomain_t),
+ GFP_KERNEL);
+ params->memory_kb = op.u.newdomain.memory_kb;
+ params->pg_head = op.u.newdomain.pg_head;
+ params->num_vifs = op.u.newdomain.num_vifs;
+ params->domain = op.u.newdomain.domain;
+
+ /* now notify user space of the new domain's id */
+ new_dom_id = create_proc_entry(DOM0_NEWDOM, 0600, xeno_base);
+ if ( new_dom_id != NULL )
+ {
+ new_dom_id->owner = THIS_MODULE;
+ new_dom_id->nlink = 1;
+ new_dom_id->proc_fops = &newdom_data_fops;
+ new_dom_id->data = (void *)params;
+ }
+
+ }
+
+ }
+
+out:
+ return ret;
+
+}
+
+static int __init init_module(void)
+{
+ /* xeno proc root setup */
+ xeno_base = proc_mkdir(XENO_BASE, &proc_root);
+
+ /* xeno control interface */
+ *readbuf = '\0';
+ dom0_cmd_intf = create_proc_entry (DOM0_CMD_INTF, 0600, xeno_base);
+ if ( dom0_cmd_intf != NULL )
+ {
+ dom0_cmd_intf->owner = THIS_MODULE;
+ dom0_cmd_intf->nlink = 1;
+ dom0_cmd_intf->read_proc = cmd_read_proc;
+ dom0_cmd_intf->write_proc = cmd_write_proc;
+ }
+
+ /* set up /proc entries for dom 0 */
+ create_proc_dom_entries(0);
+
+ return 0;
+}
+
+
+static void __exit cleanup_module(void)
+{
+ if ( dom0_cmd_intf == NULL ) return;
+ remove_proc_entry("dom0", &proc_root);
+ dom0_cmd_intf = NULL;
+}
+
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/list.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <asm/mmu.h>
+
+#include "dom0_ops.h"
+
+#define MAP_CONT 0
+#define MAP_DISCONT 1
+
+extern struct list_head * find_direct(struct list_head *, unsigned long);
+
+/*
+ * bd240: functions below perform direct mapping to the real physical pages
+ * needed for mapping various hypervisor specific structures needed in dom0
+ * userspace by various management applications such as domain builder etc.
+ */
+
+#define direct_set_pte(pteptr, pteval) queue_l1_entry_update(__pa(pteptr)|PGREQ_UNCHECKED_UPDATE, (pteval).pte_low)
+
+#define direct_pte_clear(pteptr) queue_l1_entry_update(__pa(pteptr)|PGREQ_UNCHECKED_UPDATE, 0)
+
+#define __direct_pte(x) ((pte_t) { (x) } )
+#define __direct_mk_pte(page_nr,pgprot) __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+#define direct_mk_pte_phys(physpage, pgprot) __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline void forget_pte(pte_t page)
+{
+ if (!pte_none(page)) {
+ printk("forget_pte: old mapping existed!\n");
+ BUG();
+ }
+}
+
+static inline void direct_remappte_range(pte_t * pte, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ pte_t oldpage;
+ oldpage = ptep_get_and_clear(pte);
+
+ direct_set_pte(pte, direct_mk_pte_phys(phys_addr, prot));
+
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ phys_addr += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+
+}
+
+static inline int direct_remappmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ phys_addr -= address;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ direct_remappte_range(pte, address, end - address, address + phys_addr, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+/* Note: this is only safe if the mm semaphore is held when called. */
+int direct_remap_page_range(unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = from;
+ unsigned long end = from + size;
+ struct mm_struct *mm = current->mm;
+
+ phys_addr -= from;
+ dir = pgd_offset(mm, from);
+ flush_cache_range(mm, beg, end);
+ if (from >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, from);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = direct_remappmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
+ if (error)
+ break;
+ from = (from + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (from && (from < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * used for remapping discontiguous bits of domain's memory, pages to map are
+ * found from frame table beginning at the given first_pg index
+ */
+int direct_remap_disc_page_range(unsigned long from,
+ unsigned long first_pg, int tot_pages, pgprot_t prot)
+{
+ dom0_op_t dom0_op;
+ unsigned long *pfns = get_free_page(GFP_KERNEL);
+ unsigned long start = from;
+ int pages, i;
+
+ while ( tot_pages != 0 )
+ {
+ dom0_op.cmd = DOM0_GETMEMLIST;
+ dom0_op.u.getmemlist.start_pfn = first_pg;
+ pages = 1023;
+ dom0_op.u.getmemlist.num_pfns = 1024;
+ if ( tot_pages < 1024 )
+ dom0_op.u.getmemlist.num_pfns = pages = tot_pages;
+ dom0_op.u.getmemlist.buffer = pfns;
+ (void)HYPERVISOR_dom0_op(&dom0_op);
+ first_pg = pfns[1023];
+
+ for ( i = 0; i < pages; i++ )
+ {
+ if(direct_remap_page_range(start, pfns[i] << PAGE_SHIFT,
+ PAGE_SIZE, prot))
+ goto out;
+ start += PAGE_SIZE;
+ tot_pages--;
+ }
+ }
+
+out:
+ free_page(pfns);
+ return tot_pages;
+}
+
+/* below functions replace standard sys_mmap and sys_munmap which are absolutely useless
+ * for direct memory mapping. direct_zap* functions are minor ammendments to the
+ * original versions in mm/memory.c. the changes are to enable unmapping of real physical
+ * addresses.
+ */
+
+unsigned long direct_mmap(unsigned long phys_addr, unsigned long size,
+ pgprot_t prot, int flag, int tot_pages)
+{
+ direct_mmap_node_t * dmmap;
+ struct list_head * entry;
+ unsigned long addr;
+ int ret = 0;
+
+ if(!capable(CAP_SYS_ADMIN)){
+ ret = -EPERM;
+ goto out;
+ }
+
+ /* get unmapped area invokes xen specific arch_get_unmapped_area */
+ addr = get_unmapped_area(NULL, 0, size, 0, 0);
+ if(addr & ~PAGE_MASK){
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* add node on the list of directly mapped areas, make sure the
+ * list remains sorted.
+ */
+ dmmap = (direct_mmap_node_t *)kmalloc(sizeof(direct_mmap_node_t), GFP_KERNEL);
+ dmmap->vm_start = addr;
+ dmmap->vm_end = addr + size;
+ entry = find_direct(¤t->mm->context.direct_list, addr);
+ if(entry != ¤t->mm->context.direct_list){
+ list_add_tail(&dmmap->list, entry);
+ } else {
+ list_add_tail(&dmmap->list, ¤t->mm->context.direct_list);
+ }
+
+ /* and perform the mapping */
+ if(flag == MAP_DISCONT){
+ ret = direct_remap_disc_page_range(addr, phys_addr >> PAGE_SHIFT,
+ tot_pages, prot);
+ } else {
+ ret = direct_remap_page_range(addr, phys_addr, size, prot);
+ }
+
+ if(ret == 0)
+ ret = addr;
+
+out:
+ return ret;
+}
+
+/* most of the checks, refcnt updates, cache stuff have been thrown out as they are not
+ * needed
+ */
+static inline int direct_zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address,
+ unsigned long size)
+{
+ unsigned long offset;
+ pte_t * ptep;
+ int freed = 0;
+
+ if (pmd_none(*pmd))
+ return 0;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return 0;
+ }
+ ptep = pte_offset(pmd, address);
+ offset = address & ~PMD_MASK;
+ if (offset + size > PMD_SIZE)
+ size = PMD_SIZE - offset;
+ size &= PAGE_MASK;
+ for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
+ pte_t pte = *ptep;
+ if (pte_none(pte))
+ continue;
+ freed ++;
+ direct_pte_clear(ptep);
+ }
+
+ return freed;
+}
+
+static inline int direct_zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir,
+ unsigned long address, unsigned long size)
+{
+ pmd_t * pmd;
+ unsigned long end;
+ int freed;
+
+ if (pgd_none(*dir))
+ return 0;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return 0;
+ }
+ pmd = pmd_offset(dir, address);
+ end = address + size;
+ if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
+ end = ((address + PGDIR_SIZE) & PGDIR_MASK);
+ freed = 0;
+ do {
+ freed += direct_zap_pte_range(tlb, pmd, address, end - address);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address < end);
+ return freed;
+}
+
+/*
+ * remove user pages in a given range.
+ */
+void direct_zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
+{
+ mmu_gather_t *tlb;
+ pgd_t * dir;
+ unsigned long start = address, end = address + size;
+ int freed = 0;
+
+ dir = pgd_offset(mm, address);
+
+ /*
+ * This is a long-lived spinlock. That's fine.
+ * There's no contention, because the page table
+ * lock only protects against kswapd anyway, and
+ * even if kswapd happened to be looking at this
+ * process we _want_ it to get stuck.
+ */
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ flush_cache_range(mm, address, end);
+ tlb = tlb_gather_mmu(mm);
+
+ do {
+ freed += direct_zap_pmd_range(tlb, dir, address, end - address);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+
+ /* this will flush any remaining tlb entries */
+ tlb_finish_mmu(tlb, start, end);
+
+ /* decrementing rss removed */
+
+ spin_unlock(&mm->page_table_lock);
+}
+
+int direct_unmap(unsigned long addr, unsigned long size)
+{
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if(node->vm_start == addr)
+ break;
+ curr = curr->next;
+ }
+
+ if(curr == direct_list)
+ return -1;
+
+ list_del(&node->list);
+ kfree(node);
+
+ direct_zap_page_range(current->mm, addr, size);
+
+ return 0;
+}
+
+int direct_disc_unmap(unsigned long from, unsigned long first_pg, int tot_pages)
+{
+ int count = 0;
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+
+ if(node->vm_start == from)
+ break;
+ curr = curr->next;
+ }
+
+ if(curr == direct_list)
+ return -1;
+
+ list_del(&node->list);
+ kfree(node);
+
+ while(count < tot_pages){
+ direct_zap_page_range(current->mm, from, PAGE_SIZE);
+ from += PAGE_SIZE;
+ count++;
+ }
+
+ return 0;
+}
--- /dev/null
+/******************************************************************************
+ * dom0_ops.h
+ *
+ * Process command requests from domain-0 guest OS.
+ *
+ * Copyright (c) 2002, K A Fraser, B Dragovic
+ */
+
+#define DOM0_NEWDOMAIN 0
+#define DOM0_KILLDOMAIN 1
+#define DOM0_GETMEMLIST 2
+#define DOM0_STARTDOM 4
+#define MAP_DOM_MEM 6 /* Not passed down to Xen */
+#define DO_PGUPDATES 7 /* Not passed down to Xen */
+#define MAX_CMD 8
+
+#define MAX_CMD_LEN 256
+
+typedef struct dom0_newdomain_st
+{
+ unsigned int domain;
+ unsigned int memory_kb;
+ unsigned int num_vifs; // temporary
+ unsigned long pg_head; // return parameter
+} dom0_newdomain_t;
+
+typedef struct dom0_killdomain_st
+{
+ unsigned int domain;
+} dom0_killdomain_t;
+
+typedef struct dom0_getmemlist_st
+{
+ unsigned long start_pfn;
+ unsigned long num_pfns;
+ void *buffer;
+} dom0_getmemlist_t;
+
+/* This is entirely processed by XenoLinux */
+typedef struct dom_mem
+{
+ unsigned int domain;
+ unsigned long vaddr;
+ unsigned long start_pfn;
+ int tot_pages;
+} dom_mem_t;
+
+/* This is entirely processed by XenoLinux */
+typedef struct dom_pgupdate
+{
+ unsigned long pgt_update_arr;
+ unsigned long num_pgt_updates;
+} dom_pgupdate_t;
+
+typedef struct domain_launch
+{
+ unsigned int domain;
+ unsigned long l2_pgt_addr;
+ unsigned long virt_load_addr;
+ unsigned long virt_shinfo_addr;
+ unsigned long virt_startinfo_addr;
+ unsigned int num_vifs;
+ char cmd_line[MAX_CMD_LEN];
+} dom_meminfo_t;
+
+typedef struct dom0_op_st
+{
+ unsigned long cmd;
+ union
+ {
+ dom0_newdomain_t newdomain;
+ dom0_killdomain_t killdomain;
+ dom0_getmemlist_t getmemlist;
+ dom_mem_t dommem;
+ dom_pgupdate_t pgupdate;
+ dom_meminfo_t meminfo;
+ }
+ u;
+} dom0_op_t;
+
--- /dev/null
+/******************************************************************************
+ * vfr.c
+ *
+ * Interface to the virtual firewall/router.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+
+#include <asm/hypervisor-ifs/network.h>
+
+static struct proc_dir_entry *proc_vfr;
+
+static unsigned char readbuf[1024];
+
+/* Helpers, implemented at the bottom. */
+u32 getipaddr(const char *buff, unsigned int len);
+u16 antous(const char *buff, int len);
+int anton(const char *buff, int len);
+
+static int vfr_read_proc(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ strcpy(page, readbuf);
+ *readbuf = '\0';
+ *eof = 1;
+ *start = page;
+ return strlen(page);
+}
+
+/* The format for the vfr interface is as follows:
+ *
+ * COMMAND <field>=<val> [<field>=<val> [...]]
+ *
+ * where:
+ *
+ * COMMAND = { ACCEPT | COUNT }
+ *
+ * field=val pairs are as follows:
+ *
+ * field = { srcaddr | dstaddr }
+ * val is a dot seperated, numeric IP address.
+ *
+ * field = { srcport | dstport }
+ * val is a (16-bit) unsigned int
+ *
+ * field = { proto }
+ * val = { IP | TCP | UDP | ARP }
+ *
+ */
+
+#define isspace(_x) ( ((_x)==' ') || ((_x)=='\t') || ((_x)=='\v') || \
+ ((_x)=='\f') || ((_x)=='\r') || ((_x)=='\n') )
+
+static int vfr_write_proc(struct file *file, const char *buffer,
+ u_long count, void *data)
+{
+ network_op_t op;
+ int ret, len;
+ int ts, te, tl; // token start, end, and length
+ int fs, fe, fl; // field.
+
+ len = count;
+ ts = te = 0;
+
+ memset(&op, 0, sizeof(network_op_t));
+
+ // get the command:
+ while ( count && isspace(buffer[ts]) ) { ts++; count--; } // skip spaces.
+ te = ts;
+ while ( count && !isspace(buffer[te]) ) { te++; count--; } // command end
+ if ( te <= ts ) goto bad;
+ tl = te - ts;
+
+ if ( strncmp(&buffer[ts], "ADD", tl) == 0 )
+ {
+ op.cmd = NETWORK_OP_ADDRULE;
+ }
+ else if ( strncmp(&buffer[ts], "DELETE", tl) == 0 )
+ {
+ op.cmd = NETWORK_OP_DELETERULE;
+ }
+ else if ( strncmp(&buffer[ts], "PRINT", tl) == 0 )
+ {
+ op.cmd = NETWORK_OP_GETRULELIST;
+ goto doneparsing;
+ }
+
+ ts = te;
+
+ // get the action
+ while ( count && (buffer[ts] == ' ') ) { ts++; count--; } // skip spaces.
+ te = ts;
+ while ( count && (buffer[te] != ' ') ) { te++; count--; } // command end
+ if ( te <= ts ) goto bad;
+ tl = te - ts;
+
+ if ( strncmp(&buffer[ts], "ACCEPT", tl) == 0 )
+ {
+ op.u.net_rule.action = NETWORK_ACTION_ACCEPT;
+ goto keyval;
+ }
+ if ( strncmp(&buffer[ts], "COUNT", tl) == 0 )
+ {
+ op.u.net_rule.action = NETWORK_ACTION_COUNT;
+ goto keyval;
+ }
+
+ // default case;
+ return (len);
+
+
+ // get the key=val pairs.
+ keyval:
+ while (count)
+ {
+ //get field
+ ts = te; while ( count && isspace(buffer[ts]) ) { ts++; count--; }
+ te = ts;
+ while ( count && !isspace(buffer[te]) && (buffer[te] != '=') )
+ { te++; count--; }
+ if ( te <= ts )
+ goto doneparsing;
+ tl = te - ts;
+ fs = ts; fe = te; fl = tl; // save the field markers.
+ // skip " = " (ignores extra equals.)
+ while ( count && (isspace(buffer[te]) || (buffer[te] == '=')) )
+ { te++; count--; }
+ ts = te;
+ while ( count && !isspace(buffer[te]) ) { te++; count--; }
+ tl = te - ts;
+
+ if ( (fl <= 0) || (tl <= 0) ) goto bad;
+
+ if (strncmp(&buffer[fs], "srcaddr", fl) == 0)
+ {
+ op.u.net_rule.src_addr = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstaddr", fl) == 0)
+ {
+ op.u.net_rule.dst_addr = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcaddrmask", fl) == 0)
+ {
+ op.u.net_rule.src_addr_mask = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstaddrmask", fl) == 0)
+ {
+ op.u.net_rule.dst_addr_mask = getipaddr(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcport", fl) == 0)
+ {
+ op.u.net_rule.src_port = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstport", fl) == 0)
+ {
+ op.u.net_rule.dst_port = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcportmask", fl) == 0)
+ {
+ op.u.net_rule.src_port_mask = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstportmask", fl) == 0)
+ {
+ op.u.net_rule.dst_port_mask = antous(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "srcint", fl) == 0)
+ {
+ op.u.net_rule.src_interface = anton(&buffer[ts], tl);
+ }
+ else if (strncmp(&buffer[fs], "dstint", fl) == 0)
+ {
+ op.u.net_rule.dst_interface = anton(&buffer[ts], tl);
+ }
+ else if ( (strncmp(&buffer[fs], "proto", fl) == 0))
+ {
+ if (strncmp(&buffer[ts], "any", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_ANY;
+ if (strncmp(&buffer[ts], "ip", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_IP;
+ if (strncmp(&buffer[ts], "tcp", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_TCP;
+ if (strncmp(&buffer[ts], "udp", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_UDP;
+ if (strncmp(&buffer[ts], "arp", tl) == 0)
+ op.u.net_rule.proto = NETWORK_PROTO_ARP;
+
+ }
+ }
+
+ doneparsing:
+ ret = HYPERVISOR_network_op(&op);
+ return(len);
+
+ bad:
+ return(len);
+
+
+}
+
+static int __init init_module(void)
+{
+ *readbuf = '\0';
+ proc_vfr = create_proc_entry ("vfr", 0600, &proc_root);
+ if ( proc_vfr != NULL )
+ {
+ proc_vfr->owner = THIS_MODULE;
+ proc_vfr->nlink = 1;
+ proc_vfr->read_proc = vfr_read_proc;
+ proc_vfr->write_proc = vfr_write_proc;
+ printk("Successfully installed virtual firewall/router interface\n");
+ }
+ return 0;
+}
+
+static void __exit cleanup_module(void)
+{
+ if ( proc_vfr == NULL ) return;
+ remove_proc_entry("vfr", &proc_root);
+ proc_vfr = NULL;
+}
+
+module_init(init_module);
+module_exit(cleanup_module);
+
+/* Helper functions start here: */
+
+int anton(const char *buff, int len)
+{
+ int ret;
+ char c;
+ int sign = 1;
+
+ ret = 0;
+
+ if (len == 0) return 0;
+ if (*buff == '-') { sign = -1; buff++; len--; }
+
+ while ( (len) && ((c = *buff) >= '0') && (c <= '9') )
+ {
+ ret *= 10;
+ ret += c - '0';
+ buff++; len--;
+ }
+
+ ret *= sign;
+ return ret;
+}
+
+u16 antous(const char *buff, int len)
+{
+ u16 ret;
+ char c;
+
+ ret = 0;
+
+ while ( (len) && ((c = *buff) >= '0') && (c <= '9') )
+ {
+ ret *= 10;
+ ret += c - '0';
+ buff++; len--;
+ }
+
+ return ret;
+}
+
+u32 getipaddr(const char *buff, unsigned int len)
+{
+ int i;
+ char c;
+ u32 ret, val;
+
+ ret = 0; val = 0;
+
+ while ( len )
+ {
+ if (!((((c = *buff) >= '0') && ( c <= '9')) || ( c == '.' ) ) )
+ {
+ return(0); // malformed.
+ }
+
+ if ( c == '.' ) {
+ if (val > 255) return (0); //malformed.
+ ret = ret << 8;
+ ret += val;
+ val = 0;
+ len--; buff++;
+ continue;
+ }
+ val *= 10;
+ val += c - '0';
+ buff++; len--;
+ }
+ ret = ret << 8;
+ ret += val;
+
+ return (ret);
+}
+
--- /dev/null
+O_TARGET := net.o
+obj-y := network.o
+include $(TOPDIR)/Rules.make
--- /dev/null
+/******************************************************************************
+ * network.c
+ *
+ * Virtual network driver for XenoLinux.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+
+#include <asm/io.h>
+#include <net/sock.h>
+
+#define NET_TX_IRQ _EVENT_NET_TX
+#define NET_RX_IRQ _EVENT_NET_RX
+
+#define TX_MAX_ENTRIES (TX_RING_SIZE - 2)
+#define RX_MAX_ENTRIES (RX_RING_SIZE - 2)
+
+#define TX_RING_INC(_i) (((_i)+1) & (TX_RING_SIZE-1))
+#define RX_RING_INC(_i) (((_i)+1) & (RX_RING_SIZE-1))
+#define TX_RING_ADD(_i,_j) (((_i)+(_j)) & (TX_RING_SIZE-1))
+#define RX_RING_ADD(_i,_j) (((_i)+(_j)) & (RX_RING_SIZE-1))
+
+#define RX_BUF_SIZE ((PAGE_SIZE/2)+1) /* Fool the slab allocator :-) */
+
+static void network_rx_int(int irq, void *dev_id, struct pt_regs *ptregs);
+static void network_tx_int(int irq, void *dev_id, struct pt_regs *ptregs);
+static void network_tx_buf_gc(struct net_device *dev);
+static void network_alloc_rx_buffers(struct net_device *dev);
+static void network_free_rx_buffers(struct net_device *dev);
+static void cleanup_module(void);
+
+static struct list_head dev_list;
+
+/*
+ * RX RING: RX_IDX <= rx_cons <= rx_prod
+ * TX RING: TX_IDX <= tx_cons <= tx_prod
+ * (*_IDX allocated privately here, *_cons & *_prod shared with hypervisor)
+ */
+struct net_private
+{
+ struct list_head list;
+ struct net_device *dev;
+
+ struct net_device_stats stats;
+ struct sk_buff **tx_skb_ring;
+ struct sk_buff **rx_skb_ring;
+ atomic_t tx_entries;
+ unsigned int rx_idx, tx_idx, tx_full;
+ net_ring_t *net_ring;
+ spinlock_t tx_lock;
+};
+
+
+static int network_open(struct net_device *dev)
+{
+ struct net_private *np = dev->priv;
+ int error = 0;
+
+ np->rx_idx = np->tx_idx = np->tx_full = 0;
+
+ memset(&np->stats, 0, sizeof(np->stats));
+
+ spin_lock_init(&np->tx_lock);
+
+ atomic_set(&np->tx_entries, 0);
+
+ np->net_ring->tx_prod = np->net_ring->tx_cons = np->net_ring->tx_event = 0;
+ np->net_ring->rx_prod = np->net_ring->rx_cons = np->net_ring->rx_event = 0;
+ np->net_ring->tx_ring = NULL;
+ np->net_ring->rx_ring = NULL;
+
+ np->tx_skb_ring = kmalloc(TX_RING_SIZE * sizeof(struct sk_buff *),
+ GFP_KERNEL);
+ np->rx_skb_ring = kmalloc(RX_RING_SIZE * sizeof(struct sk_buff *),
+ GFP_KERNEL);
+ np->net_ring->tx_ring = kmalloc(TX_RING_SIZE * sizeof(tx_entry_t),
+ GFP_KERNEL);
+ np->net_ring->rx_ring = kmalloc(RX_RING_SIZE * sizeof(rx_entry_t),
+ GFP_KERNEL);
+ if ( (np->tx_skb_ring == NULL) || (np->rx_skb_ring == NULL) ||
+ (np->net_ring->tx_ring == NULL) || (np->net_ring->rx_ring == NULL) )
+ {
+ printk(KERN_WARNING "%s; Could not allocate ring memory\n", dev->name);
+ error = -ENOBUFS;
+ goto fail;
+ }
+
+ network_alloc_rx_buffers(dev);
+
+ error = request_irq(NET_RX_IRQ, network_rx_int, 0,
+ "net-rx", dev);
+ if ( error )
+ {
+ printk(KERN_WARNING "%s: Could not allocate receive interrupt\n",
+ dev->name);
+ network_free_rx_buffers(dev);
+ goto fail;
+ }
+
+ error = request_irq(NET_TX_IRQ, network_tx_int, 0,
+ "net-tx", dev);
+ if ( error )
+ {
+ printk(KERN_WARNING "%s: Could not allocate transmit interrupt\n",
+ dev->name);
+ free_irq(NET_RX_IRQ, dev);
+ network_free_rx_buffers(dev);
+ goto fail;
+ }
+
+ printk("XenoLinux Virtual Network Driver installed as %s\n", dev->name);
+
+ netif_start_queue(dev);
+
+ MOD_INC_USE_COUNT;
+
+ return 0;
+
+ fail:
+ if ( np->net_ring->rx_ring ) kfree(np->net_ring->rx_ring);
+ if ( np->net_ring->tx_ring ) kfree(np->net_ring->tx_ring);
+ if ( np->rx_skb_ring ) kfree(np->rx_skb_ring);
+ if ( np->tx_skb_ring ) kfree(np->tx_skb_ring);
+ kfree(np);
+ return error;
+}
+
+
+static void network_tx_buf_gc(struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+ unsigned long flags;
+
+ spin_lock_irqsave(&np->tx_lock, flags);
+
+ for ( i = np->tx_idx; i != np->net_ring->tx_cons; i = TX_RING_INC(i) )
+ {
+ skb = np->tx_skb_ring[i];
+ dev_kfree_skb_any(skb);
+ atomic_dec(&np->tx_entries);
+ }
+
+ np->tx_idx = i;
+
+ if ( np->tx_full && (atomic_read(&np->tx_entries) < TX_MAX_ENTRIES) )
+ {
+ np->tx_full = 0;
+ netif_wake_queue(dev);
+ }
+
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+}
+
+inline unsigned long get_ppte(unsigned long addr)
+{
+ unsigned long ppte;
+ pgd_t *pgd; pmd_t *pmd; pte_t *ptep;
+ pgd = pgd_offset_k(addr);
+
+ if ( pgd_none(*pgd) || pgd_bad(*pgd) ) BUG();
+
+ pmd = pmd_offset(pgd, addr);
+ if ( pmd_none(*pmd) || pmd_bad(*pmd) ) BUG();
+
+ ptep = pte_offset(pmd, addr);
+ ppte = (unsigned long)phys_to_machine(virt_to_phys(ptep));
+
+ return ppte;
+}
+
+static void network_alloc_rx_buffers(struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+ unsigned int end = RX_RING_ADD(np->rx_idx, RX_MAX_ENTRIES);
+
+ for ( i = np->net_ring->rx_prod; i != end; i = RX_RING_INC(i) )
+ {
+ skb = dev_alloc_skb(RX_BUF_SIZE);
+ if ( skb == NULL ) break;
+ skb->dev = dev;
+ skb_reserve(skb, 2); /* word align the IP header */
+ np->rx_skb_ring[i] = skb;
+ np->net_ring->rx_ring[i].addr = get_ppte((unsigned long)skb->head);
+ np->net_ring->rx_ring[i].size = RX_BUF_SIZE - 16; /* arbitrary */
+ }
+
+ np->net_ring->rx_prod = i;
+
+ np->net_ring->rx_event = RX_RING_INC(np->rx_idx);
+
+ HYPERVISOR_net_update();
+}
+
+
+static void network_free_rx_buffers(struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+
+ for ( i = np->rx_idx; i != np->net_ring->rx_prod; i = RX_RING_INC(i) )
+ {
+ skb = np->rx_skb_ring[i];
+ dev_kfree_skb(skb);
+ }
+}
+
+static int network_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ unsigned int i;
+ struct net_private *np = (struct net_private *)dev->priv;
+
+ if ( np->tx_full )
+ {
+ printk(KERN_WARNING "%s: full queue wasn't stopped!\n", dev->name);
+ netif_stop_queue(dev);
+ return -ENOBUFS;
+ }
+ i = np->net_ring->tx_prod;
+
+ if ( (((unsigned long)skb->data & ~PAGE_MASK) + skb->len) >= PAGE_SIZE )
+ {
+ struct sk_buff *new_skb = alloc_skb(RX_BUF_SIZE, GFP_KERNEL);
+ skb_put(new_skb, skb->len);
+ memcpy(new_skb->data, skb->data, skb->len);
+ kfree_skb(skb);
+ skb = new_skb;
+ }
+
+ np->tx_skb_ring[i] = skb;
+ np->net_ring->tx_ring[i].addr =
+ (unsigned long)phys_to_machine(virt_to_phys(skb->data));
+ np->net_ring->tx_ring[i].size = skb->len;
+ np->net_ring->tx_prod = TX_RING_INC(i);
+ atomic_inc(&np->tx_entries);
+
+ np->stats.tx_bytes += skb->len;
+ np->stats.tx_packets++;
+
+ spin_lock_irq(&np->tx_lock);
+ if ( atomic_read(&np->tx_entries) >= TX_MAX_ENTRIES )
+ {
+ np->tx_full = 1;
+ netif_stop_queue(dev);
+ np->net_ring->tx_event =
+ TX_RING_ADD(np->tx_idx, atomic_read(&np->tx_entries) >> 1);
+ }
+ else
+ {
+ /* Avoid unnecessary tx interrupts. */
+ np->net_ring->tx_event = TX_RING_INC(np->net_ring->tx_prod);
+ }
+ spin_unlock_irq(&np->tx_lock);
+
+ /* Must do this after setting tx_event: race with updates of tx_cons. */
+ network_tx_buf_gc(dev);
+
+ HYPERVISOR_net_update();
+
+ return 0;
+}
+
+
+static void network_rx_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ unsigned int i;
+ struct net_device *dev = (struct net_device *)dev_id;
+ struct net_private *np = dev->priv;
+ struct sk_buff *skb;
+
+ again:
+ for ( i = np->rx_idx; i != np->net_ring->rx_cons; i = RX_RING_INC(i) )
+ {
+ if (np->net_ring->rx_ring[i].status != RING_STATUS_OK)
+ {
+ printk("bad buffer on RX ring!(%d)\n",
+ np->net_ring->rx_ring[i].status);
+ continue;
+ }
+ skb = np->rx_skb_ring[i];
+
+ phys_to_machine_mapping[virt_to_phys(skb->head) >> PAGE_SHIFT] =
+ (*(unsigned long *)phys_to_virt(
+ machine_to_phys(np->net_ring->rx_ring[i].addr))
+ ) >> PAGE_SHIFT;
+
+ skb_put(skb, np->net_ring->rx_ring[i].size);
+ skb->protocol = eth_type_trans(skb, dev);
+
+ /*
+ * Set up shinfo -- from alloc_skb This was particularily nasty: the
+ * shared info is hidden at the back of the data area (presumably so it
+ * can be shared), but on page flip it gets very spunked.
+ */
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+
+ np->stats.rx_packets++;
+
+ np->stats.rx_bytes += np->net_ring->rx_ring[i].size;
+ netif_rx(skb);
+ dev->last_rx = jiffies;
+ }
+
+ np->rx_idx = i;
+
+ network_alloc_rx_buffers(dev);
+
+ /* Deal with hypervisor racing our resetting of rx_event. */
+ smp_mb();
+ if ( np->net_ring->rx_cons != i ) goto again;
+}
+
+
+static void network_tx_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ struct net_device *dev = (struct net_device *)dev_id;
+ network_tx_buf_gc(dev);
+}
+
+
+int network_close(struct net_device *dev)
+{
+ struct net_private *np = dev->priv;
+
+ netif_stop_queue(dev);
+
+ free_irq(NET_RX_IRQ, dev);
+ free_irq(NET_TX_IRQ, dev);
+
+ /*
+ * XXXX This cannot be done safely until be have a proper interface
+ * for setting up and tearing down virtual interfaces on the fly.
+ * Currently the receive buffers are locked down by Xen and we have
+ * no sensible way of retrieving them.
+ */
+#if 0
+ network_free_rx_buffers(dev);
+ kfree(np->net_ring->rx_ring);
+ kfree(np->net_ring->tx_ring);
+#endif
+
+ kfree(np->rx_skb_ring);
+ kfree(np->tx_skb_ring);
+
+ MOD_DEC_USE_COUNT;
+
+ return 0;
+}
+
+
+static struct net_device_stats *network_get_stats(struct net_device *dev)
+{
+ struct net_private *np = (struct net_private *)dev->priv;
+ return &np->stats;
+}
+
+
+int __init init_module(void)
+{
+ int i, err;
+ struct net_device *dev;
+ struct net_private *np;
+
+ INIT_LIST_HEAD(&dev_list);
+
+ for ( i = 0; i < start_info.num_net_rings; i++ )
+ {
+ dev = alloc_etherdev(sizeof(struct net_private));
+ if ( dev == NULL )
+ {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ np = dev->priv;
+ np->net_ring = start_info.net_rings + i;
+
+ SET_MODULE_OWNER(dev);
+ dev->open = network_open;
+ dev->hard_start_xmit = network_start_xmit;
+ dev->stop = network_close;
+ dev->get_stats = network_get_stats;
+
+ memset(dev->dev_addr, 0, ETH_ALEN);
+ *(unsigned int *)(dev->dev_addr + 1) = i;
+
+ if ( (err = register_netdev(dev)) != 0 )
+ {
+ kfree(dev);
+ goto fail;
+ }
+
+ np->dev = dev;
+ list_add(&np->list, &dev_list);
+ }
+
+ return 0;
+
+ fail:
+ cleanup_module();
+ return err;
+}
+
+
+static void cleanup_module(void)
+{
+ struct net_private *np;
+ struct net_device *dev;
+
+ while ( !list_empty(&dev_list) )
+ {
+ np = list_entry(dev_list.next, struct net_private, list);
+ list_del(&np->list);
+ dev = np->dev;
+ unregister_netdev(dev);
+ kfree(dev);
+ }
+}
+
+
+module_init(init_module);
+module_exit(cleanup_module);
--- /dev/null
+
+.S.o:
+ $(CC) $(AFLAGS) -traditional -c $< -o $*.o
+
+all: kernel.o head.o init_task.o
+
+O_TARGET := kernel.o
+
+export-objs := i386_ksyms.o
+
+obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \
+ ptrace.o ioport.o ldt.o setup.o time.o sys_i386.o \
+ i386_ksyms.o i387.o hypervisor.o
+
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * linux/arch/i386/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * entry.S contains the system-call and fault low-level handling routines.
+ * This also contains the timer-interrupt handler, as well as all interrupts
+ * and faults that can result in a task-switch.
+ *
+ * NOTE: This code handles signal-recognition, which happens every time
+ * after a timer-interrupt and after each system call.
+ *
+ * I changed all the .align's to 4 (16 byte alignment), as that's faster
+ * on a 486.
+ *
+ * Stack layout in 'ret_from_system_call':
+ * ptrace needs to have all regs on the stack.
+ * if the order here is changed, it needs to be
+ * updated in fork.c:copy_process, signal.c:do_signal,
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - orig_eax
+ * 28(%esp) - %eip
+ * 2C(%esp) - %cs
+ * 30(%esp) - %eflags
+ * 34(%esp) - %oldesp
+ * 38(%esp) - %oldss
+ *
+ * "current" is in register %ebx during any slow entries.
+ */
+
+#include <linux/config.h>
+#include <linux/sys.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+
+EBX = 0x00
+ECX = 0x04
+EDX = 0x08
+ESI = 0x0C
+EDI = 0x10
+EBP = 0x14
+EAX = 0x18
+DS = 0x1C
+ES = 0x20
+ORIG_EAX = 0x24
+EIP = 0x28
+CS = 0x2C
+EFLAGS = 0x30
+OLDESP = 0x34
+OLDSS = 0x38
+
+CF_MASK = 0x00000001
+TF_MASK = 0x00000100
+IF_MASK = 0x00000200
+DF_MASK = 0x00000400
+NT_MASK = 0x00004000
+
+/*
+ * these are offsets into the task-struct.
+ */
+state = 0
+flags = 4
+sigpending = 8
+addr_limit = 12
+exec_domain = 16
+need_resched = 20
+tsk_ptrace = 24
+processor = 52
+
+ENOSYS = 38
+
+
+#define SAVE_ALL \
+ cld; \
+ pushl %es; \
+ pushl %ds; \
+ pushl %eax; \
+ pushl %ebp; \
+ pushl %edi; \
+ pushl %esi; \
+ pushl %edx; \
+ pushl %ecx; \
+ pushl %ebx; \
+ movl $(__KERNEL_DS),%edx; \
+ movl %edx,%ds; \
+ movl %edx,%es;
+
+#define RESTORE_ALL \
+ popl %ebx; \
+ popl %ecx; \
+ popl %edx; \
+ popl %esi; \
+ popl %edi; \
+ popl %ebp; \
+ popl %eax; \
+1: popl %ds; \
+2: popl %es; \
+ addl $4,%esp; \
+3: iret; \
+.section .fixup,"ax"; \
+4: movl $0,(%esp); \
+ jmp 1b; \
+5: movl $0,(%esp); \
+ jmp 2b; \
+6: pushl %ss; \
+ popl %ds; \
+ pushl %ss; \
+ popl %es; \
+ pushl $11; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,4b; \
+ .long 2b,5b; \
+ .long 3b,6b; \
+.previous
+
+#define GET_CURRENT(reg) \
+ movl $-8192, reg; \
+ andl %esp, reg
+
+ENTRY(ret_from_fork)
+ pushl %ebx
+ call SYMBOL_NAME(schedule_tail)
+ addl $4, %esp
+ GET_CURRENT(%ebx)
+ testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
+ jne tracesys_exit
+ jmp ret_from_sys_call
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ENTRY(system_call)
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
+ jne tracesys
+ cmpl $(NR_syscalls),%eax
+ jae badsys
+ call *SYMBOL_NAME(sys_call_table)(,%eax,4)
+ movl %eax,EAX(%esp) # save the return value
+ENTRY(ret_from_sys_call)
+ movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
+ xorl %eax,%eax
+ movl %eax,4(%esi) # need_resched and signals atomic test
+ret_syscall_tests:
+ cmpl $0,need_resched(%ebx)
+ jne reschedule
+ cmpl $0,sigpending(%ebx)
+ je safesti # ensure need_resched updates are seen
+signal_return:
+ btsl %eax,4(%esi) # reenable event callbacks
+ movl %esp,%eax
+ xorl %edx,%edx
+ call SYMBOL_NAME(do_signal)
+ jmp ret_from_sys_call
+
+ ALIGN
+restore_all:
+ RESTORE_ALL
+
+ ALIGN
+tracesys:
+ movl $-ENOSYS,EAX(%esp)
+ call SYMBOL_NAME(syscall_trace)
+ movl ORIG_EAX(%esp),%eax
+ cmpl $(NR_syscalls),%eax
+ jae tracesys_exit
+ call *SYMBOL_NAME(sys_call_table)(,%eax,4)
+ movl %eax,EAX(%esp) # save the return value
+tracesys_exit:
+ call SYMBOL_NAME(syscall_trace)
+ jmp ret_from_sys_call
+badsys:
+ movl $-ENOSYS,EAX(%esp)
+ jmp ret_from_sys_call
+
+ ALIGN
+ENTRY(ret_from_intr)
+ GET_CURRENT(%ebx)
+ret_from_exception:
+ movb CS(%esp),%al
+ testl $2,%eax
+ jne ret_from_sys_call
+ jmp restore_all
+
+ ALIGN
+reschedule:
+ btsl %eax,4(%esi) # reenable event callbacks
+ call SYMBOL_NAME(schedule) # test
+ jmp ret_from_sys_call
+
+ENTRY(divide_error)
+ pushl $0 # no error code
+ pushl $ SYMBOL_NAME(do_divide_error)
+ ALIGN
+error_code:
+ pushl %ds
+ pushl %eax
+ xorl %eax,%eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax # eax = -1
+ pushl %ecx
+ pushl %ebx
+ GET_CURRENT(%ebx)
+ cld
+ movl %es,%ecx
+ movl ORIG_EAX(%esp), %esi # get the error code
+ movl ES(%esp), %edi # get the function address
+ movl %eax, ORIG_EAX(%esp)
+ movl %ecx, ES(%esp)
+ movl %esp,%edx
+ pushl %esi # push the error code
+ pushl %edx # push the pt_regs pointer
+ movl $(__KERNEL_DS),%edx
+ movl %edx,%ds
+ movl %edx,%es
+ call *%edi
+ addl $8,%esp
+ jmp ret_from_exception
+
+# A note on the "critical region" in our callback handler.
+# We want to avoid stacking callback handlers due to events occurring
+# during handling of the last event. To do this, we keep events disabled
+# until we've done all processing. HOWEVER, we must enable events before
+# popping the stack frame (can't be done atomically) and so it would still
+# be possible to get enough handler activations to overflow the stack.
+# Although unlikely, bugs of that kind are hard to track down, so we'd
+# like to avoid the possibility.
+# So, on entry to the handler we detect whether we interrupted an
+# existing activation in its critical region -- if so, we pop the current
+# activation and restart the handler using the previous one.
+ENTRY(hypervisor_callback)
+ pushl %eax
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ movl EIP(%esp),%eax
+ cmpl $scrit,%eax
+ jb 11f
+ cmpl $ecrit,%eax
+ jb critical_region_fixup
+11: push %esp
+ call do_hypervisor_callback
+ add $4,%esp
+ movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
+ xorl %eax,%eax
+ movb CS(%esp),%cl
+ test $2,%cl # slow return to ring 2 or 3
+ jne ret_syscall_tests
+safesti:btsl %eax,4(%esi) # reenable event callbacks
+scrit: /**** START OF CRITICAL REGION ****/
+ cmpl %eax,(%esi)
+ jne 14f # process more events if necessary...
+ RESTORE_ALL
+14: btrl %eax,4(%esi)
+ jmp 11b
+ecrit: /**** END OF CRITICAL REGION ****/
+# [How we do the fixup]. We want to merge the current stack frame with the
+# just-interrupted frame. How we do this depends on where in the critical
+# region the interrupted handler was executing, and so how many saved
+# registers are in each frame. We do this quickly using the lookup table
+# 'critical_fixup_table'. For each byte offset in the critical region, it
+# provides the number of bytes which have already been popped from the
+# interrupted stack frame.
+critical_region_fixup:
+ addl $critical_fixup_table-scrit,%eax
+ movzbl (%eax),%eax # %eax contains num bytes popped
+ mov %esp,%esi
+ add %eax,%esi # %esi points at end of src region
+ mov %esp,%edi
+ add $0x34,%edi # %edi points at end of dst region
+ mov %eax,%ecx
+ shr $2,%ecx # convert words to bytes
+ je 16f # skip loop if nothing to copy
+15: subl $4,%esi # pre-decrementing copy loop
+ subl $4,%edi
+ movl (%esi),%eax
+ movl %eax,(%edi)
+ loop 15b
+16: movl %edi,%esp # final %edi is top of merged stack
+ jmp 11b
+
+critical_fixup_table:
+ .byte 0x00,0x00 # cmpl %eax,(%esi)
+ .byte 0x00,0x00 # jne 14f
+ .byte 0x00 # pop %ebx
+ .byte 0x04 # pop %ecx
+ .byte 0x08 # pop %edx
+ .byte 0x0c # pop %esi
+ .byte 0x10 # pop %edi
+ .byte 0x14 # pop %ebp
+ .byte 0x18 # pop %eax
+ .byte 0x1c # pop %ds
+ .byte 0x20 # pop %es
+ .byte 0x24,0x24,0x24 # add $4,%esp
+ .byte 0x28 # iret
+ .byte 0x00,0x00,0x00,0x00 # btrl %eax,4(%esi)
+ .byte 0x00,0x00 # jmp 11b
+
+# Hypervisor uses this for application faults while it executes.
+ENTRY(failsafe_callback)
+1: pop %ds
+2: pop %es
+3: iret
+.section .fixup,"ax"; \
+4: movl $0,(%esp); \
+ jmp 1b; \
+5: movl $0,(%esp); \
+ jmp 2b; \
+6: pushl %ss; \
+ popl %ds; \
+ pushl %ss; \
+ popl %es; \
+ pushl $11; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,4b; \
+ .long 2b,5b; \
+ .long 3b,6b; \
+.previous
+
+ENTRY(coprocessor_error)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_coprocessor_error)
+ jmp error_code
+
+ENTRY(simd_coprocessor_error)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_simd_coprocessor_error)
+ jmp error_code
+
+ENTRY(device_not_available)
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ call SYMBOL_NAME(math_state_restore)
+ jmp ret_from_exception
+
+ENTRY(debug)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_debug)
+ jmp error_code
+
+ENTRY(int3)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_int3)
+ jmp error_code
+
+ENTRY(overflow)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_overflow)
+ jmp error_code
+
+ENTRY(bounds)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_bounds)
+ jmp error_code
+
+ENTRY(invalid_op)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_invalid_op)
+ jmp error_code
+
+ENTRY(coprocessor_segment_overrun)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_coprocessor_segment_overrun)
+ jmp error_code
+
+ENTRY(double_fault)
+ pushl $ SYMBOL_NAME(do_double_fault)
+ jmp error_code
+
+ENTRY(invalid_TSS)
+ pushl $ SYMBOL_NAME(do_invalid_TSS)
+ jmp error_code
+
+ENTRY(segment_not_present)
+ pushl $ SYMBOL_NAME(do_segment_not_present)
+ jmp error_code
+
+ENTRY(stack_segment)
+ pushl $ SYMBOL_NAME(do_stack_segment)
+ jmp error_code
+
+ENTRY(general_protection)
+ pushl $ SYMBOL_NAME(do_general_protection)
+ jmp error_code
+
+ENTRY(alignment_check)
+ pushl $ SYMBOL_NAME(do_alignment_check)
+ jmp error_code
+
+# This handler is special, because it gets an extra value on its stack,
+# which is the linear faulting address.
+ENTRY(page_fault)
+ pushl %ds
+ pushl %eax
+ xorl %eax,%eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax # eax = -1
+ pushl %ecx
+ pushl %ebx
+ GET_CURRENT(%ebx)
+ cld
+ movl %es,%ecx
+ movl ORIG_EAX(%esp), %esi # get the error code
+ movl ES(%esp), %edi # get the faulting address
+ movl %eax, ORIG_EAX(%esp)
+ movl %ecx, ES(%esp)
+ movl %esp,%edx
+ pushl %edi # push the faulting address
+ pushl %esi # push the error code
+ pushl %edx # push the pt_regs pointer
+ movl $(__KERNEL_DS),%edx
+ movl %edx,%ds
+ movl %edx,%es
+ call SYMBOL_NAME(do_page_fault)
+ addl $12,%esp
+ jmp ret_from_exception
+
+ENTRY(machine_check)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_machine_check)
+ jmp error_code
+
+ENTRY(spurious_interrupt_bug)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_spurious_interrupt_bug)
+ jmp error_code
+
+.data
+ENTRY(sys_call_table)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 0 - old "setup()" system call*/
+ .long SYMBOL_NAME(sys_exit)
+ .long SYMBOL_NAME(sys_fork)
+ .long SYMBOL_NAME(sys_read)
+ .long SYMBOL_NAME(sys_write)
+ .long SYMBOL_NAME(sys_open) /* 5 */
+ .long SYMBOL_NAME(sys_close)
+ .long SYMBOL_NAME(sys_waitpid)
+ .long SYMBOL_NAME(sys_creat)
+ .long SYMBOL_NAME(sys_link)
+ .long SYMBOL_NAME(sys_unlink) /* 10 */
+ .long SYMBOL_NAME(sys_execve)
+ .long SYMBOL_NAME(sys_chdir)
+ .long SYMBOL_NAME(sys_time)
+ .long SYMBOL_NAME(sys_mknod)
+ .long SYMBOL_NAME(sys_chmod) /* 15 */
+ .long SYMBOL_NAME(sys_lchown16)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old break syscall holder */
+ .long SYMBOL_NAME(sys_stat)
+ .long SYMBOL_NAME(sys_lseek)
+ .long SYMBOL_NAME(sys_getpid) /* 20 */
+ .long SYMBOL_NAME(sys_mount)
+ .long SYMBOL_NAME(sys_oldumount)
+ .long SYMBOL_NAME(sys_setuid16)
+ .long SYMBOL_NAME(sys_getuid16)
+ .long SYMBOL_NAME(sys_stime) /* 25 */
+ .long SYMBOL_NAME(sys_ptrace)
+ .long SYMBOL_NAME(sys_alarm)
+ .long SYMBOL_NAME(sys_fstat)
+ .long SYMBOL_NAME(sys_pause)
+ .long SYMBOL_NAME(sys_utime) /* 30 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old stty syscall holder */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old gtty syscall holder */
+ .long SYMBOL_NAME(sys_access)
+ .long SYMBOL_NAME(sys_nice)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 35 */ /* old ftime syscall holder */
+ .long SYMBOL_NAME(sys_sync)
+ .long SYMBOL_NAME(sys_kill)
+ .long SYMBOL_NAME(sys_rename)
+ .long SYMBOL_NAME(sys_mkdir)
+ .long SYMBOL_NAME(sys_rmdir) /* 40 */
+ .long SYMBOL_NAME(sys_dup)
+ .long SYMBOL_NAME(sys_pipe)
+ .long SYMBOL_NAME(sys_times)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old prof syscall holder */
+ .long SYMBOL_NAME(sys_brk) /* 45 */
+ .long SYMBOL_NAME(sys_setgid16)
+ .long SYMBOL_NAME(sys_getgid16)
+ .long SYMBOL_NAME(sys_signal)
+ .long SYMBOL_NAME(sys_geteuid16)
+ .long SYMBOL_NAME(sys_getegid16) /* 50 */
+ .long SYMBOL_NAME(sys_acct)
+ .long SYMBOL_NAME(sys_umount) /* recycled never used phys() */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old lock syscall holder */
+ .long SYMBOL_NAME(sys_ioctl)
+ .long SYMBOL_NAME(sys_fcntl) /* 55 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old mpx syscall holder */
+ .long SYMBOL_NAME(sys_setpgid)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old ulimit syscall holder */
+ .long SYMBOL_NAME(sys_olduname)
+ .long SYMBOL_NAME(sys_umask) /* 60 */
+ .long SYMBOL_NAME(sys_chroot)
+ .long SYMBOL_NAME(sys_ustat)
+ .long SYMBOL_NAME(sys_dup2)
+ .long SYMBOL_NAME(sys_getppid)
+ .long SYMBOL_NAME(sys_getpgrp) /* 65 */
+ .long SYMBOL_NAME(sys_setsid)
+ .long SYMBOL_NAME(sys_sigaction)
+ .long SYMBOL_NAME(sys_sgetmask)
+ .long SYMBOL_NAME(sys_ssetmask)
+ .long SYMBOL_NAME(sys_setreuid16) /* 70 */
+ .long SYMBOL_NAME(sys_setregid16)
+ .long SYMBOL_NAME(sys_sigsuspend)
+ .long SYMBOL_NAME(sys_sigpending)
+ .long SYMBOL_NAME(sys_sethostname)
+ .long SYMBOL_NAME(sys_setrlimit) /* 75 */
+ .long SYMBOL_NAME(sys_old_getrlimit)
+ .long SYMBOL_NAME(sys_getrusage)
+ .long SYMBOL_NAME(sys_gettimeofday)
+ .long SYMBOL_NAME(sys_settimeofday)
+ .long SYMBOL_NAME(sys_getgroups16) /* 80 */
+ .long SYMBOL_NAME(sys_setgroups16)
+ .long SYMBOL_NAME(old_select)
+ .long SYMBOL_NAME(sys_symlink)
+ .long SYMBOL_NAME(sys_lstat)
+ .long SYMBOL_NAME(sys_readlink) /* 85 */
+ .long SYMBOL_NAME(sys_uselib)
+ .long SYMBOL_NAME(sys_swapon)
+ .long SYMBOL_NAME(sys_reboot)
+ .long SYMBOL_NAME(old_readdir)
+ .long SYMBOL_NAME(old_mmap) /* 90 */
+ .long SYMBOL_NAME(sys_munmap)
+ .long SYMBOL_NAME(sys_truncate)
+ .long SYMBOL_NAME(sys_ftruncate)
+ .long SYMBOL_NAME(sys_fchmod)
+ .long SYMBOL_NAME(sys_fchown16) /* 95 */
+ .long SYMBOL_NAME(sys_getpriority)
+ .long SYMBOL_NAME(sys_setpriority)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old profil syscall holder */
+ .long SYMBOL_NAME(sys_statfs)
+ .long SYMBOL_NAME(sys_fstatfs) /* 100 */
+ .long SYMBOL_NAME(sys_ioperm)
+ .long SYMBOL_NAME(sys_socketcall)
+ .long SYMBOL_NAME(sys_syslog)
+ .long SYMBOL_NAME(sys_setitimer)
+ .long SYMBOL_NAME(sys_getitimer) /* 105 */
+ .long SYMBOL_NAME(sys_newstat)
+ .long SYMBOL_NAME(sys_newlstat)
+ .long SYMBOL_NAME(sys_newfstat)
+ .long SYMBOL_NAME(sys_uname)
+ .long SYMBOL_NAME(sys_iopl) /* 110 */
+ .long SYMBOL_NAME(sys_vhangup)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old "idle" system call */
+ .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
+ .long SYMBOL_NAME(sys_wait4)
+ .long SYMBOL_NAME(sys_swapoff) /* 115 */
+ .long SYMBOL_NAME(sys_sysinfo)
+ .long SYMBOL_NAME(sys_ipc)
+ .long SYMBOL_NAME(sys_fsync)
+ .long SYMBOL_NAME(sys_sigreturn)
+ .long SYMBOL_NAME(sys_clone) /* 120 */
+ .long SYMBOL_NAME(sys_setdomainname)
+ .long SYMBOL_NAME(sys_newuname)
+ .long SYMBOL_NAME(sys_modify_ldt)
+ .long SYMBOL_NAME(sys_adjtimex)
+ .long SYMBOL_NAME(sys_mprotect) /* 125 */
+ .long SYMBOL_NAME(sys_sigprocmask)
+ .long SYMBOL_NAME(sys_create_module)
+ .long SYMBOL_NAME(sys_init_module)
+ .long SYMBOL_NAME(sys_delete_module)
+ .long SYMBOL_NAME(sys_get_kernel_syms) /* 130 */
+ .long SYMBOL_NAME(sys_quotactl)
+ .long SYMBOL_NAME(sys_getpgid)
+ .long SYMBOL_NAME(sys_fchdir)
+ .long SYMBOL_NAME(sys_bdflush)
+ .long SYMBOL_NAME(sys_sysfs) /* 135 */
+ .long SYMBOL_NAME(sys_personality)
+ .long SYMBOL_NAME(sys_ni_syscall) /* for afs_syscall */
+ .long SYMBOL_NAME(sys_setfsuid16)
+ .long SYMBOL_NAME(sys_setfsgid16)
+ .long SYMBOL_NAME(sys_llseek) /* 140 */
+ .long SYMBOL_NAME(sys_getdents)
+ .long SYMBOL_NAME(sys_select)
+ .long SYMBOL_NAME(sys_flock)
+ .long SYMBOL_NAME(sys_msync)
+ .long SYMBOL_NAME(sys_readv) /* 145 */
+ .long SYMBOL_NAME(sys_writev)
+ .long SYMBOL_NAME(sys_getsid)
+ .long SYMBOL_NAME(sys_fdatasync)
+ .long SYMBOL_NAME(sys_sysctl)
+ .long SYMBOL_NAME(sys_mlock) /* 150 */
+ .long SYMBOL_NAME(sys_munlock)
+ .long SYMBOL_NAME(sys_mlockall)
+ .long SYMBOL_NAME(sys_munlockall)
+ .long SYMBOL_NAME(sys_sched_setparam)
+ .long SYMBOL_NAME(sys_sched_getparam) /* 155 */
+ .long SYMBOL_NAME(sys_sched_setscheduler)
+ .long SYMBOL_NAME(sys_sched_getscheduler)
+ .long SYMBOL_NAME(sys_sched_yield)
+ .long SYMBOL_NAME(sys_sched_get_priority_max)
+ .long SYMBOL_NAME(sys_sched_get_priority_min) /* 160 */
+ .long SYMBOL_NAME(sys_sched_rr_get_interval)
+ .long SYMBOL_NAME(sys_nanosleep)
+ .long SYMBOL_NAME(sys_mremap)
+ .long SYMBOL_NAME(sys_setresuid16)
+ .long SYMBOL_NAME(sys_getresuid16) /* 165 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
+ .long SYMBOL_NAME(sys_query_module)
+ .long SYMBOL_NAME(sys_poll)
+ .long SYMBOL_NAME(sys_nfsservctl)
+ .long SYMBOL_NAME(sys_setresgid16) /* 170 */
+ .long SYMBOL_NAME(sys_getresgid16)
+ .long SYMBOL_NAME(sys_prctl)
+ .long SYMBOL_NAME(sys_rt_sigreturn)
+ .long SYMBOL_NAME(sys_rt_sigaction)
+ .long SYMBOL_NAME(sys_rt_sigprocmask) /* 175 */
+ .long SYMBOL_NAME(sys_rt_sigpending)
+ .long SYMBOL_NAME(sys_rt_sigtimedwait)
+ .long SYMBOL_NAME(sys_rt_sigqueueinfo)
+ .long SYMBOL_NAME(sys_rt_sigsuspend)
+ .long SYMBOL_NAME(sys_pread) /* 180 */
+ .long SYMBOL_NAME(sys_pwrite)
+ .long SYMBOL_NAME(sys_chown16)
+ .long SYMBOL_NAME(sys_getcwd)
+ .long SYMBOL_NAME(sys_capget)
+ .long SYMBOL_NAME(sys_capset) /* 185 */
+ .long SYMBOL_NAME(sys_sigaltstack)
+ .long SYMBOL_NAME(sys_sendfile)
+ .long SYMBOL_NAME(sys_ni_syscall) /* streams1 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* streams2 */
+ .long SYMBOL_NAME(sys_vfork) /* 190 */
+ .long SYMBOL_NAME(sys_getrlimit)
+ .long SYMBOL_NAME(sys_mmap2)
+ .long SYMBOL_NAME(sys_truncate64)
+ .long SYMBOL_NAME(sys_ftruncate64)
+ .long SYMBOL_NAME(sys_stat64) /* 195 */
+ .long SYMBOL_NAME(sys_lstat64)
+ .long SYMBOL_NAME(sys_fstat64)
+ .long SYMBOL_NAME(sys_lchown)
+ .long SYMBOL_NAME(sys_getuid)
+ .long SYMBOL_NAME(sys_getgid) /* 200 */
+ .long SYMBOL_NAME(sys_geteuid)
+ .long SYMBOL_NAME(sys_getegid)
+ .long SYMBOL_NAME(sys_setreuid)
+ .long SYMBOL_NAME(sys_setregid)
+ .long SYMBOL_NAME(sys_getgroups) /* 205 */
+ .long SYMBOL_NAME(sys_setgroups)
+ .long SYMBOL_NAME(sys_fchown)
+ .long SYMBOL_NAME(sys_setresuid)
+ .long SYMBOL_NAME(sys_getresuid)
+ .long SYMBOL_NAME(sys_setresgid) /* 210 */
+ .long SYMBOL_NAME(sys_getresgid)
+ .long SYMBOL_NAME(sys_chown)
+ .long SYMBOL_NAME(sys_setuid)
+ .long SYMBOL_NAME(sys_setgid)
+ .long SYMBOL_NAME(sys_setfsuid) /* 215 */
+ .long SYMBOL_NAME(sys_setfsgid)
+ .long SYMBOL_NAME(sys_pivot_root)
+ .long SYMBOL_NAME(sys_mincore)
+ .long SYMBOL_NAME(sys_madvise)
+ .long SYMBOL_NAME(sys_getdents64) /* 220 */
+ .long SYMBOL_NAME(sys_fcntl64)
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for TUX */
+ .long SYMBOL_NAME(sys_ni_syscall) /* Reserved for Security */
+ .long SYMBOL_NAME(sys_gettid)
+ .long SYMBOL_NAME(sys_readahead) /* 225 */
+ .long SYMBOL_NAME(sys_setxattr)
+ .long SYMBOL_NAME(sys_lsetxattr)
+ .long SYMBOL_NAME(sys_fsetxattr)
+ .long SYMBOL_NAME(sys_getxattr)
+ .long SYMBOL_NAME(sys_lgetxattr) /* 230 */
+ .long SYMBOL_NAME(sys_fgetxattr)
+ .long SYMBOL_NAME(sys_listxattr)
+ .long SYMBOL_NAME(sys_llistxattr)
+ .long SYMBOL_NAME(sys_flistxattr)
+ .long SYMBOL_NAME(sys_removexattr) /* 235 */
+ .long SYMBOL_NAME(sys_lremovexattr)
+ .long SYMBOL_NAME(sys_fremovexattr)
+ .long SYMBOL_NAME(sys_tkill)
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for sendfile64 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* 240 reserved for futex */
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for sched_setaffinity */
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for sched_getaffinity */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_set_thread_area */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_get_thread_area */
+ .long SYMBOL_NAME(sys_ni_syscall) /* 245 sys_io_setup */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_destroy */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_getevents */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_submit */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_cancel */
+ .long SYMBOL_NAME(sys_ni_syscall) /* 250 sys_alloc_hugepages */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_free_hugepages */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_exit_group */
+
+ .rept NR_syscalls-(.-sys_call_table)/4
+ .long SYMBOL_NAME(sys_ni_syscall)
+ .endr
--- /dev/null
+
+.text
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+/* Offsets in start_info structure */
+#define SHARED_INFO 4
+#define MOD_START 12
+#define MOD_LEN 16
+
+startup_32:
+ cld
+
+ lss stack_start,%esp
+
+ /* Copy initrd somewhere safe before it's clobbered by BSS. */
+ mov MOD_LEN(%esi),%ecx
+ shr $2,%ecx
+ jz 2f /* bail from copy loop if no initrd */
+ mov $SYMBOL_NAME(_end),%edi
+ add MOD_LEN(%esi),%edi
+ mov MOD_START(%esi),%eax
+ add MOD_LEN(%esi),%eax
+1: sub $4,%eax
+ sub $4,%edi
+ mov (%eax),%ebx
+ mov %ebx,(%edi)
+ loop 1b
+ mov %edi,MOD_START(%esi)
+
+ /* Clear BSS first so that there are no surprises... */
+2: xorl %eax,%eax
+ movl $SYMBOL_NAME(__bss_start),%edi
+ movl $SYMBOL_NAME(_end),%ecx
+ subl %edi,%ecx
+ rep stosb
+
+ /* Copy the necessary stuff from start_info structure. */
+ /* We need to copy shared_info early, so that sti/cli work */
+ mov SHARED_INFO(%esi),%eax
+ mov %eax,SYMBOL_NAME(HYPERVISOR_shared_info)
+ mov $SYMBOL_NAME(start_info_union),%edi
+ mov $128,%ecx
+ rep movsl
+
+ jmp SYMBOL_NAME(start_kernel)
+
+ENTRY(stack_start)
+ .long SYMBOL_NAME(init_task_union)+8192, __KERNEL_DS
+
+.org 0x1000
+ENTRY(empty_zero_page)
+
+.org 0x2000
+ENTRY(cpu0_pte_quicklist)
+
+.org 0x2400
+ENTRY(cpu0_pgd_quicklist)
+
+.org 0x2800
+ENTRY(stext)
+ENTRY(_stext)
--- /dev/null
+/******************************************************************************
+ * hypervisor.c
+ *
+ * Communication to/from hypervisor.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <asm/atomic.h>
+#include <linux/irq.h>
+#include <asm/hypervisor.h>
+#include <asm/system.h>
+#include <asm/ptrace.h>
+
+static unsigned long event_mask = 0;
+
+void frobb(void) {}
+
+void do_hypervisor_callback(struct pt_regs *regs)
+{
+ unsigned long events, flags;
+ shared_info_t *shared = HYPERVISOR_shared_info;
+
+ do {
+ /* Specialised local_irq_save(). */
+ flags = shared->events_enable;
+ shared->events_enable = 0;
+ barrier();
+
+ events = xchg(&shared->events, 0);
+ events &= event_mask;
+
+ __asm__ __volatile__ (
+ " push %1 ;"
+ " sub $4,%%esp ;"
+ " jmp 2f ;"
+ "1: btrl %%eax,%0 ;" /* clear bit */
+ " mov %%eax,(%%esp) ;"
+ " call do_IRQ ;" /* do_IRQ(event) */
+ "2: bsfl %0,%%eax ;" /* %eax == bit # */
+ " jnz 1b ;"
+ " add $8,%%esp ;"
+ /* we use %ebx because it is callee-saved */
+ : : "b" (events), "r" (regs)
+ /* clobbered by callback function calls */
+ : "eax", "ecx", "edx", "memory" );
+
+ /* Specialised local_irq_restore(). */
+ shared->events_enable = flags;
+ barrier();
+ }
+ while ( shared->events );
+}
+
+
+
+/*
+ * Define interface to generic handling in irq.c
+ */
+
+static unsigned int startup_hypervisor_event(unsigned int irq)
+{
+ set_bit(irq, &event_mask);
+ return 0;
+}
+
+static void shutdown_hypervisor_event(unsigned int irq)
+{
+ clear_bit(irq, &event_mask);
+}
+
+static void enable_hypervisor_event(unsigned int irq)
+{
+ set_bit(irq, &event_mask);
+}
+
+static void disable_hypervisor_event(unsigned int irq)
+{
+ clear_bit(irq, &event_mask);
+}
+
+static void ack_hypervisor_event(unsigned int irq)
+{
+ if ( !(event_mask & (1<<irq)) )
+ {
+ printk("Unexpected hypervisor event %d\n", irq);
+ atomic_inc(&irq_err_count);
+ }
+}
+
+static void end_hypervisor_event(unsigned int irq)
+{
+}
+
+static struct hw_interrupt_type hypervisor_irq_type = {
+ "Hypervisor-event",
+ startup_hypervisor_event,
+ shutdown_hypervisor_event,
+ enable_hypervisor_event,
+ disable_hypervisor_event,
+ ack_hypervisor_event,
+ end_hypervisor_event,
+ NULL
+};
+
+void __init init_IRQ(void)
+{
+ int i;
+
+ for ( i = 0; i < NR_IRQS; i++ )
+ {
+ irq_desc[i].status = IRQ_DISABLED;
+ irq_desc[i].action = 0;
+ irq_desc[i].depth = 1;
+ irq_desc[i].handler = &hypervisor_irq_type;
+ }
+}
--- /dev/null
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/user.h>
+#include <linux/elfcore.h>
+#include <linux/mca.h>
+#include <linux/sched.h>
+#include <linux/in6.h>
+#include <linux/interrupt.h>
+#include <linux/smp_lock.h>
+#include <linux/pm.h>
+//XXX ??? #include <linux/pci.h>
+#include <linux/apm_bios.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/tty.h>
+
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include <asm/io.h>
+#include <asm/hardirq.h>
+#include <asm/delay.h>
+#include <asm/irq.h>
+#include <asm/mmx.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+
+extern void dump_thread(struct pt_regs *, struct user *);
+extern spinlock_t rtc_lock;
+
+#if defined(CONFIG_APMXXX) || defined(CONFIG_APM_MODULEXXX)
+extern void machine_real_restart(unsigned char *, int);
+EXPORT_SYMBOL(machine_real_restart);
+extern void default_idle(void);
+EXPORT_SYMBOL(default_idle);
+#endif
+
+#ifdef CONFIG_SMP
+extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
+extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
+#endif
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
+extern struct drive_info_struct drive_info;
+EXPORT_SYMBOL(drive_info);
+#endif
+
+// XXX extern unsigned long get_cmos_time(void);
+
+/* platform dependent support */
+EXPORT_SYMBOL(boot_cpu_data);
+EXPORT_SYMBOL(__verify_write);
+EXPORT_SYMBOL(dump_thread);
+EXPORT_SYMBOL(dump_fpu);
+EXPORT_SYMBOL(dump_extended_fpu);
+EXPORT_SYMBOL(enable_irq);
+EXPORT_SYMBOL(disable_irq);
+EXPORT_SYMBOL(disable_irq_nosync);
+EXPORT_SYMBOL(probe_irq_mask);
+EXPORT_SYMBOL(kernel_thread);
+EXPORT_SYMBOL(pm_idle);
+EXPORT_SYMBOL(pm_power_off);
+EXPORT_SYMBOL(apm_info);
+//EXPORT_SYMBOL(gdt);
+EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_DEBUG_IOVIRT
+EXPORT_SYMBOL(__io_virt_debug);
+#endif
+
+EXPORT_SYMBOL_NOVERS(__down_failed);
+EXPORT_SYMBOL_NOVERS(__down_failed_interruptible);
+EXPORT_SYMBOL_NOVERS(__down_failed_trylock);
+EXPORT_SYMBOL_NOVERS(__up_wakeup);
+/* Networking helper routines. */
+EXPORT_SYMBOL(csum_partial_copy_generic);
+/* Delay loops */
+EXPORT_SYMBOL(__udelay);
+EXPORT_SYMBOL(__delay);
+EXPORT_SYMBOL(__const_udelay);
+
+EXPORT_SYMBOL_NOVERS(__get_user_1);
+EXPORT_SYMBOL_NOVERS(__get_user_2);
+EXPORT_SYMBOL_NOVERS(__get_user_4);
+
+EXPORT_SYMBOL(strtok);
+EXPORT_SYMBOL(strpbrk);
+EXPORT_SYMBOL(strstr);
+
+EXPORT_SYMBOL(strncpy_from_user);
+EXPORT_SYMBOL(__strncpy_from_user);
+EXPORT_SYMBOL(clear_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__generic_copy_from_user);
+EXPORT_SYMBOL(__generic_copy_to_user);
+EXPORT_SYMBOL(strnlen_user);
+
+#ifdef CONFIG_X86_USE_3DNOW
+EXPORT_SYMBOL(_mmx_memcpy);
+EXPORT_SYMBOL(mmx_clear_page);
+EXPORT_SYMBOL(mmx_copy_page);
+#endif
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(cpu_data);
+EXPORT_SYMBOL(kernel_flag_cacheline);
+EXPORT_SYMBOL(smp_num_cpus);
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL_NOVERS(__write_lock_failed);
+EXPORT_SYMBOL_NOVERS(__read_lock_failed);
+
+/* Global SMP irq stuff */
+EXPORT_SYMBOL(synchronize_irq);
+EXPORT_SYMBOL(global_irq_holder);
+EXPORT_SYMBOL(__global_cli);
+EXPORT_SYMBOL(__global_sti);
+EXPORT_SYMBOL(__global_save_flags);
+EXPORT_SYMBOL(__global_restore_flags);
+EXPORT_SYMBOL(smp_call_function);
+
+/* TLB flushing */
+EXPORT_SYMBOL(flush_tlb_page);
+#endif
+
+#ifdef CONFIG_X86_IO_APIC
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+#endif
+
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(screen_info);
+#endif
+
+EXPORT_SYMBOL(get_wchan);
+
+EXPORT_SYMBOL(rtc_lock);
+
+#undef memcpy
+#undef memset
+extern void * memset(void *,int,__kernel_size_t);
+extern void * memcpy(void *,const void *,__kernel_size_t);
+EXPORT_SYMBOL_NOVERS(memcpy);
+EXPORT_SYMBOL_NOVERS(memset);
+
+#ifdef CONFIG_HAVE_DEC_LOCK
+EXPORT_SYMBOL(atomic_dec_and_lock);
+#endif
+
+#ifdef CONFIG_MULTIQUAD
+EXPORT_SYMBOL(xquad_portio);
+#endif
--- /dev/null
+/*
+ * linux/arch/i386/kernel/i387.c
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/math_emu.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+#define HAVE_HWFP 1
+
+static union i387_union empty_fpu_state;
+
+void __init boot_init_fpu(void)
+{
+ memset(&empty_fpu_state, 0, sizeof(union i387_union));
+
+ if (!cpu_has_fxsr) {
+ empty_fpu_state.fsave.cwd = 0xffff037f;
+ empty_fpu_state.fsave.swd = 0xffff0000;
+ empty_fpu_state.fsave.twd = 0xffffffff;
+ empty_fpu_state.fsave.fos = 0xffff0000;
+ } else {
+ empty_fpu_state.fxsave.cwd = 0x37f;
+ if (cpu_has_xmm)
+ empty_fpu_state.fxsave.mxcsr = 0x1f80;
+ }
+}
+
+void load_empty_fpu(struct task_struct * tsk)
+{
+ memcpy(&tsk->thread.i387, &empty_fpu_state, sizeof(union i387_union));
+}
+
+/*
+ * The _current_ task is using the FPU for the first time
+ * so initialize it and set the mxcsr to its default
+ * value at reset if we support XMM instructions and then
+ * remeber the current task has used the FPU.
+ */
+void init_fpu(void)
+{
+ if (cpu_has_fxsr)
+ asm volatile("fxrstor %0" : : "m" (empty_fpu_state.fxsave));
+ else
+ __asm__("fninit");
+ current->used_math = 1;
+}
+
+/*
+ * FPU lazy state save handling.
+ */
+
+static inline void __save_init_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxsave %0 ; fnclex"
+ : "=m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "fnsave %0 ; fwait"
+ : "=m" (tsk->thread.i387.fsave) );
+ }
+ tsk->flags &= ~PF_USEDFPU;
+}
+
+void save_init_fpu( struct task_struct *tsk )
+{
+ __save_init_fpu(tsk);
+ stts();
+}
+
+void kernel_fpu_begin(void)
+{
+ struct task_struct *tsk = current;
+
+ if (tsk->flags & PF_USEDFPU) {
+ __save_init_fpu(tsk);
+ return;
+ }
+ clts();
+}
+
+void restore_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxrstor %0"
+ : : "m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "frstor %0"
+ : : "m" (tsk->thread.i387.fsave) );
+ }
+}
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr( unsigned short twd )
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+ return tmp;
+}
+
+static inline unsigned long twd_fxsr_to_i387( struct i387_fxsave_struct *fxsave )
+{
+ struct _fpxreg *st = NULL;
+ unsigned long twd = (unsigned long) fxsave->twd;
+ unsigned long tag;
+ unsigned long ret = 0xffff0000;
+ int i;
+
+#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16);
+
+ for ( i = 0 ; i < 8 ; i++ ) {
+ if ( twd & 0x1 ) {
+ st = (struct _fpxreg *) FPREG_ADDR( fxsave, i );
+
+ switch ( st->exponent & 0x7fff ) {
+ case 0x7fff:
+ tag = 2; /* Special */
+ break;
+ case 0x0000:
+ if ( !st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3] ) {
+ tag = 1; /* Zero */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ default:
+ if ( st->significand[3] & 0x8000 ) {
+ tag = 0; /* Valid */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ }
+ } else {
+ tag = 3; /* Empty */
+ }
+ ret |= (tag << (2 * i));
+ twd = twd >> 1;
+ }
+ return ret;
+}
+
+/*
+ * FPU state interaction.
+ */
+
+unsigned short get_fpu_cwd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.cwd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.cwd;
+ }
+}
+
+unsigned short get_fpu_swd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.swd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.swd;
+ }
+}
+
+unsigned short get_fpu_twd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.twd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.twd;
+ }
+}
+
+unsigned short get_fpu_mxcsr( struct task_struct *tsk )
+{
+ if ( cpu_has_xmm ) {
+ return tsk->thread.i387.fxsave.mxcsr;
+ } else {
+ return 0x1f80;
+ }
+}
+
+void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.cwd = cwd;
+ } else {
+ tsk->thread.i387.fsave.cwd = ((long)cwd | 0xffff0000);
+ }
+}
+
+void set_fpu_swd( struct task_struct *tsk, unsigned short swd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.swd = swd;
+ } else {
+ tsk->thread.i387.fsave.swd = ((long)swd | 0xffff0000);
+ }
+}
+
+void set_fpu_twd( struct task_struct *tsk, unsigned short twd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.twd = twd_i387_to_fxsr(twd);
+ } else {
+ tsk->thread.i387.fsave.twd = ((long)twd | 0xffff0000);
+ }
+}
+
+void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr )
+{
+ if ( cpu_has_xmm ) {
+ tsk->thread.i387.fxsave.mxcsr = (mxcsr & 0xffbf);
+ }
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+static inline int convert_fxsr_to_user( struct _fpstate *buf,
+ struct i387_fxsave_struct *fxsave )
+{
+ unsigned long env[7];
+ struct _fpreg *to;
+ struct _fpxreg *from;
+ int i;
+
+ env[0] = (unsigned long)fxsave->cwd | 0xffff0000;
+ env[1] = (unsigned long)fxsave->swd | 0xffff0000;
+ env[2] = twd_fxsr_to_i387(fxsave);
+ env[3] = fxsave->fip;
+ env[4] = fxsave->fcs | ((unsigned long)fxsave->fop << 16);
+ env[5] = fxsave->foo;
+ env[6] = fxsave->fos;
+
+ if ( __copy_to_user( buf, env, 7 * sizeof(unsigned long) ) )
+ return 1;
+
+ to = &buf->_st[0];
+ from = (struct _fpxreg *) &fxsave->st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if ( __copy_to_user( to, from, sizeof(*to) ) )
+ return 1;
+ }
+ return 0;
+}
+
+static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave,
+ struct _fpstate *buf )
+{
+ unsigned long env[7];
+ struct _fpxreg *to;
+ struct _fpreg *from;
+ int i;
+
+ if ( __copy_from_user( env, buf, 7 * sizeof(long) ) )
+ return 1;
+
+ fxsave->cwd = (unsigned short)(env[0] & 0xffff);
+ fxsave->swd = (unsigned short)(env[1] & 0xffff);
+ fxsave->twd = twd_i387_to_fxsr((unsigned short)(env[2] & 0xffff));
+ fxsave->fip = env[3];
+ fxsave->fop = (unsigned short)((env[4] & 0xffff0000) >> 16);
+ fxsave->fcs = (env[4] & 0xffff);
+ fxsave->foo = env[5];
+ fxsave->fos = env[6];
+
+ to = (struct _fpxreg *) &fxsave->st_space[0];
+ from = &buf->_st[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if ( __copy_from_user( to, from, sizeof(*from) ) )
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+
+static inline int save_i387_fsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+
+ unlazy_fpu( tsk );
+ tsk->thread.i387.fsave.status = tsk->thread.i387.fsave.swd;
+ if ( __copy_to_user( buf, &tsk->thread.i387.fsave,
+ sizeof(struct i387_fsave_struct) ) )
+ return -1;
+ return 1;
+}
+
+static inline int save_i387_fxsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ int err = 0;
+
+ unlazy_fpu( tsk );
+
+ if ( convert_fxsr_to_user( buf, &tsk->thread.i387.fxsave ) )
+ return -1;
+
+ err |= __put_user( tsk->thread.i387.fxsave.swd, &buf->status );
+ err |= __put_user( X86_FXSR_MAGIC, &buf->magic );
+ if ( err )
+ return -1;
+
+ if ( __copy_to_user( &buf->_fxsr_env[0], &tsk->thread.i387.fxsave,
+ sizeof(struct i387_fxsave_struct) ) )
+ return -1;
+ return 1;
+}
+
+int save_i387( struct _fpstate *buf )
+{
+ if ( !current->used_math )
+ return 0;
+
+ /* This will cause a "finit" to be triggered by the next
+ * attempted FPU operation by the 'current' process.
+ */
+ current->used_math = 0;
+
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return save_i387_fxsave( buf );
+ } else {
+ return save_i387_fsave( buf );
+ }
+ } else {
+ return save_i387_soft( ¤t->thread.i387.soft, buf );
+ }
+}
+
+static inline int restore_i387_fsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ clear_fpu( tsk );
+ return __copy_from_user( &tsk->thread.i387.fsave, buf,
+ sizeof(struct i387_fsave_struct) );
+}
+
+static inline int restore_i387_fxsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ clear_fpu( tsk );
+ if ( __copy_from_user( &tsk->thread.i387.fxsave, &buf->_fxsr_env[0],
+ sizeof(struct i387_fxsave_struct) ) )
+ return 1;
+ /* mxcsr bit 6 and 31-16 must be zero for security reasons */
+ tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+ return convert_fxsr_from_user( &tsk->thread.i387.fxsave, buf );
+}
+
+int restore_i387( struct _fpstate *buf )
+{
+ int err;
+
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ err = restore_i387_fxsave( buf );
+ } else {
+ err = restore_i387_fsave( buf );
+ }
+ } else {
+ err = restore_i387_soft( ¤t->thread.i387.soft, buf );
+ }
+ current->used_math = 1;
+ return err;
+}
+
+/*
+ * ptrace request handlers.
+ */
+
+static inline int get_fpregs_fsave( struct user_i387_struct *buf,
+ struct task_struct *tsk )
+{
+ return __copy_to_user( buf, &tsk->thread.i387.fsave,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline int get_fpregs_fxsave( struct user_i387_struct *buf,
+ struct task_struct *tsk )
+{
+ return convert_fxsr_to_user( (struct _fpstate *)buf,
+ &tsk->thread.i387.fxsave );
+}
+
+int get_fpregs( struct user_i387_struct *buf, struct task_struct *tsk )
+{
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return get_fpregs_fxsave( buf, tsk );
+ } else {
+ return get_fpregs_fsave( buf, tsk );
+ }
+ } else {
+ return save_i387_soft( &tsk->thread.i387.soft,
+ (struct _fpstate *)buf );
+ }
+}
+
+static inline int set_fpregs_fsave( struct task_struct *tsk,
+ struct user_i387_struct *buf )
+{
+ return __copy_from_user( &tsk->thread.i387.fsave, buf,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline int set_fpregs_fxsave( struct task_struct *tsk,
+ struct user_i387_struct *buf )
+{
+ return convert_fxsr_from_user( &tsk->thread.i387.fxsave,
+ (struct _fpstate *)buf );
+}
+
+int set_fpregs( struct task_struct *tsk, struct user_i387_struct *buf )
+{
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return set_fpregs_fxsave( tsk, buf );
+ } else {
+ return set_fpregs_fsave( tsk, buf );
+ }
+ } else {
+ return restore_i387_soft( &tsk->thread.i387.soft,
+ (struct _fpstate *)buf );
+ }
+}
+
+int get_fpxregs( struct user_fxsr_struct *buf, struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ if (__copy_to_user( (void *)buf, &tsk->thread.i387.fxsave,
+ sizeof(struct user_fxsr_struct) ))
+ return -EFAULT;
+ return 0;
+ } else {
+ return -EIO;
+ }
+}
+
+int set_fpxregs( struct task_struct *tsk, struct user_fxsr_struct *buf )
+{
+ if ( cpu_has_fxsr ) {
+ __copy_from_user( &tsk->thread.i387.fxsave, (void *)buf,
+ sizeof(struct user_fxsr_struct) );
+ /* mxcsr bit 6 and 31-16 must be zero for security reasons */
+ tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+ return 0;
+ } else {
+ return -EIO;
+ }
+}
+
+/*
+ * FPU state for core dumps.
+ */
+
+static inline void copy_fpu_fsave( struct task_struct *tsk,
+ struct user_i387_struct *fpu )
+{
+ memcpy( fpu, &tsk->thread.i387.fsave,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline void copy_fpu_fxsave( struct task_struct *tsk,
+ struct user_i387_struct *fpu )
+{
+ unsigned short *to;
+ unsigned short *from;
+ int i;
+
+ memcpy( fpu, &tsk->thread.i387.fxsave, 7 * sizeof(long) );
+
+ to = (unsigned short *)&fpu->st_space[0];
+ from = (unsigned short *)&tsk->thread.i387.fxsave.st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to += 5, from += 8 ) {
+ memcpy( to, from, 5 * sizeof(unsigned short) );
+ }
+}
+
+int dump_fpu( struct pt_regs *regs, struct user_i387_struct *fpu )
+{
+ int fpvalid;
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk->used_math;
+ if ( fpvalid ) {
+ unlazy_fpu( tsk );
+ if ( cpu_has_fxsr ) {
+ copy_fpu_fxsave( tsk, fpu );
+ } else {
+ copy_fpu_fsave( tsk, fpu );
+ }
+ }
+
+ return fpvalid;
+}
+
+int dump_extended_fpu( struct pt_regs *regs, struct user_fxsr_struct *fpu )
+{
+ int fpvalid;
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk->used_math && cpu_has_fxsr;
+ if ( fpvalid ) {
+ unlazy_fpu( tsk );
+ memcpy( fpu, &tsk->thread.i387.fxsave,
+ sizeof(struct user_fxsr_struct) );
+ }
+
+ return fpvalid;
+}
--- /dev/null
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+static struct fs_struct init_fs = INIT_FS;
+static struct files_struct init_files = INIT_FILES;
+static struct signal_struct init_signals = INIT_SIGNALS;
+struct mm_struct init_mm = INIT_MM(init_mm);
+
+/*
+ * Initial task structure.
+ *
+ * We need to make sure that this is 8192-byte aligned due to the
+ * way process stacks are handled. This is done by having a special
+ * "init_task" linker map entry..
+ */
+union task_union init_task_union
+ __attribute__((__section__(".data.init_task"))) =
+ { INIT_TASK(init_task_union.task) };
+
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data.cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+struct tss_struct init_tss[NR_CPUS] __cacheline_aligned = { [0 ... NR_CPUS-1] = INIT_TSS };
+
--- /dev/null
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+
+asmlinkage int sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+{
+ /* No IO permission! */
+ return -EPERM;
+}
+
+
+asmlinkage int sys_iopl(unsigned long unused)
+{
+ /* The hypervisor won't allow it! */
+ return -EPERM;
+}
--- /dev/null
+/*
+ * linux/arch/i386/kernel/irq.c
+ *
+ * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ */
+
+/*
+ * (mostly architecture independent, will move to kernel/irq.c in 2.5.)
+ *
+ * IRQs are in fact implemented a bit like signal handlers for the kernel.
+ * Naturally it's not a 1:1 relation, but there are similarities.
+ */
+
+#include <linux/config.h>
+#include <linux/ptrace.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+
+#include <asm/atomic.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/irq.h>
+
+
+
+/*
+ * Linux has a controller-independent x86 interrupt architecture.
+ * every controller has a 'controller-template', that is used
+ * by the main code to do the right thing. Each driver-visible
+ * interrupt source is transparently wired to the apropriate
+ * controller. Thus drivers need not be aware of the
+ * interrupt-controller.
+ *
+ * Various interrupt controllers we handle: 8259 PIC, SMP IO-APIC,
+ * PIIX4's internal 8259 PIC and SGI's Visual Workstation Cobalt (IO-)APIC.
+ * (IO-APICs assumed to be messaging to Pentium local-APICs)
+ *
+ * the code is designed to be easily extended with new/different
+ * interrupt controllers, without having to do assembly magic.
+ */
+
+/*
+ * Controller mappings for all interrupt sources:
+ */
+irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned =
+ { [0 ... NR_IRQS-1] = { 0, &no_irq_type, NULL, 0, SPIN_LOCK_UNLOCKED}};
+
+static void register_irq_proc (unsigned int irq);
+
+/*
+ * Special irq handlers.
+ */
+
+void no_action(int cpl, void *dev_id, struct pt_regs *regs) { }
+
+/*
+ * Generic no controller code
+ */
+
+static void enable_none(unsigned int irq) { }
+static unsigned int startup_none(unsigned int irq) { return 0; }
+static void disable_none(unsigned int irq) { }
+static void ack_none(unsigned int irq)
+{
+ printk("unexpected IRQ trap at vector %02x\n", irq);
+}
+
+/* startup is the same as "enable", shutdown is same as "disable" */
+#define shutdown_none disable_none
+#define end_none enable_none
+
+struct hw_interrupt_type no_irq_type = {
+ "none",
+ startup_none,
+ shutdown_none,
+ enable_none,
+ disable_none,
+ ack_none,
+ end_none
+};
+
+atomic_t irq_err_count;
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+atomic_t irq_mis_count;
+#endif
+#endif
+
+/*
+ * Generic, controller-independent functions:
+ */
+
+int get_irq_list(char *buf)
+{
+ int i, j;
+ struct irqaction * action;
+ char *p = buf;
+
+ p += sprintf(p, " ");
+ for (j=0; j<smp_num_cpus; j++)
+ p += sprintf(p, "CPU%d ",j);
+ *p++ = '\n';
+
+ for (i = 0 ; i < NR_IRQS ; i++) {
+ action = irq_desc[i].action;
+ if (!action)
+ continue;
+ p += sprintf(p, "%3d: ",i);
+#ifndef CONFIG_SMP
+ p += sprintf(p, "%10u ", kstat_irqs(i));
+#else
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ kstat.irqs[cpu_logical_map(j)][i]);
+#endif
+ p += sprintf(p, " %14s", irq_desc[i].handler->typename);
+ p += sprintf(p, " %s", action->name);
+
+ for (action=action->next; action; action = action->next)
+ p += sprintf(p, ", %s", action->name);
+ *p++ = '\n';
+ }
+ p += sprintf(p, "NMI: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ nmi_count(cpu_logical_map(j)));
+ p += sprintf(p, "\n");
+#if CONFIG_X86_LOCAL_APIC
+ p += sprintf(p, "LOC: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ apic_timer_irqs[cpu_logical_map(j)]);
+ p += sprintf(p, "\n");
+#endif
+ p += sprintf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+ p += sprintf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
+#endif
+#endif
+ return p - buf;
+}
+
+
+/*
+ * Global interrupt locks for SMP. Allow interrupts to come in on any
+ * CPU, yet make cli/sti act globally to protect critical regions..
+ */
+
+#ifdef CONFIG_SMP
+unsigned char global_irq_holder = NO_PROC_ID;
+unsigned volatile long global_irq_lock; /* pendantic: long for set_bit --RR */
+
+extern void show_stack(unsigned long* esp);
+
+static void show(char * str)
+{
+ int i;
+ int cpu = smp_processor_id();
+
+ printk("\n%s, CPU %d:\n", str, cpu);
+ printk("irq: %d [",irqs_running());
+ for(i=0;i < smp_num_cpus;i++)
+ printk(" %d",local_irq_count(i));
+ printk(" ]\nbh: %d [",spin_is_locked(&global_bh_lock) ? 1 : 0);
+ for(i=0;i < smp_num_cpus;i++)
+ printk(" %d",local_bh_count(i));
+
+ printk(" ]\nStack dumps:");
+ for(i = 0; i < smp_num_cpus; i++) {
+ unsigned long esp;
+ if (i == cpu)
+ continue;
+ printk("\nCPU %d:",i);
+ esp = init_tss[i].esp0;
+ if (!esp) {
+ /* tss->esp0 is set to NULL in cpu_init(),
+ * it's initialized when the cpu returns to user
+ * space. -- manfreds
+ */
+ printk(" <unknown> ");
+ continue;
+ }
+ esp &= ~(THREAD_SIZE-1);
+ esp += sizeof(struct task_struct);
+ show_stack((void*)esp);
+ }
+ printk("\nCPU %d:",cpu);
+ show_stack(NULL);
+ printk("\n");
+}
+
+#define MAXCOUNT 100000000
+
+/*
+ * I had a lockup scenario where a tight loop doing
+ * spin_unlock()/spin_lock() on CPU#1 was racing with
+ * spin_lock() on CPU#0. CPU#0 should have noticed spin_unlock(), but
+ * apparently the spin_unlock() information did not make it
+ * through to CPU#0 ... nasty, is this by design, do we have to limit
+ * 'memory update oscillation frequency' artificially like here?
+ *
+ * Such 'high frequency update' races can be avoided by careful design, but
+ * some of our major constructs like spinlocks use similar techniques,
+ * it would be nice to clarify this issue. Set this define to 0 if you
+ * want to check whether your system freezes. I suspect the delay done
+ * by SYNC_OTHER_CORES() is in correlation with 'snooping latency', but
+ * i thought that such things are guaranteed by design, since we use
+ * the 'LOCK' prefix.
+ */
+#define SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND 0
+
+#if SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND
+# define SYNC_OTHER_CORES(x) udelay(x+1)
+#else
+/*
+ * We have to allow irqs to arrive between __sti and __cli
+ */
+# define SYNC_OTHER_CORES(x) __asm__ __volatile__ ("nop")
+#endif
+
+static inline void wait_on_irq(int cpu)
+{
+ int count = MAXCOUNT;
+
+ for (;;) {
+
+ /*
+ * Wait until all interrupts are gone. Wait
+ * for bottom half handlers unless we're
+ * already executing in one..
+ */
+ if (!irqs_running())
+ if (local_bh_count(cpu) || !spin_is_locked(&global_bh_lock))
+ break;
+
+ /* Duh, we have to loop. Release the lock to avoid deadlocks */
+ clear_bit(0,&global_irq_lock);
+
+ for (;;) {
+ if (!--count) {
+ show("wait_on_irq");
+ count = ~0;
+ }
+ __sti();
+ SYNC_OTHER_CORES(cpu);
+ __cli();
+ if (irqs_running())
+ continue;
+ if (global_irq_lock)
+ continue;
+ if (!local_bh_count(cpu) && spin_is_locked(&global_bh_lock))
+ continue;
+ if (!test_and_set_bit(0,&global_irq_lock))
+ break;
+ }
+ }
+}
+
+/*
+ * This is called when we want to synchronize with
+ * interrupts. We may for example tell a device to
+ * stop sending interrupts: but to make sure there
+ * are no interrupts that are executing on another
+ * CPU we need to call this function.
+ */
+void synchronize_irq(void)
+{
+ if (irqs_running()) {
+ /* Stupid approach */
+ cli();
+ sti();
+ }
+}
+
+static inline void get_irqlock(int cpu)
+{
+ if (test_and_set_bit(0,&global_irq_lock)) {
+ /* do we already hold the lock? */
+ if ((unsigned char) cpu == global_irq_holder)
+ return;
+ /* Uhhuh.. Somebody else got it. Wait.. */
+ do {
+ do {
+ rep_nop();
+ } while (test_bit(0,&global_irq_lock));
+ } while (test_and_set_bit(0,&global_irq_lock));
+ }
+ /*
+ * We also to make sure that nobody else is running
+ * in an interrupt context.
+ */
+ wait_on_irq(cpu);
+
+ /*
+ * Ok, finally..
+ */
+ global_irq_holder = cpu;
+}
+
+void __global_cli(void)
+{
+ panic("__global_cli");
+}
+
+void __global_sti(void)
+{
+ panic("__global_sti");
+}
+
+/*
+ * SMP flags value to restore to:
+ * 0 - global cli
+ * 1 - global sti
+ * 2 - local cli
+ * 3 - local sti
+ */
+unsigned long __global_save_flags(void)
+{
+ panic("__global_save_flags");
+}
+
+void __global_restore_flags(unsigned long flags)
+{
+ panic("__global_restore_flags");
+}
+
+#endif
+
+/*
+ * This should really return information about whether
+ * we should do bottom half handling etc. Right now we
+ * end up _always_ checking the bottom half, which is a
+ * waste of time and is not what some drivers would
+ * prefer.
+ */
+int handle_IRQ_event(unsigned int irq, struct pt_regs * regs, struct irqaction * action)
+{
+ int status;
+ int cpu = smp_processor_id();
+
+ irq_enter(cpu, irq);
+
+ status = 1; /* Force the "do bottom halves" bit */
+
+ if (!(action->flags & SA_INTERRUPT))
+ __sti();
+
+ do {
+ status |= action->flags;
+ action->handler(irq, action->dev_id, regs);
+ action = action->next;
+ } while (action);
+ if (status & SA_SAMPLE_RANDOM)
+ add_interrupt_randomness(irq);
+ __cli();
+
+ irq_exit(cpu, irq);
+
+ return status;
+}
+
+/*
+ * Generic enable/disable code: this just calls
+ * down into the PIC-specific version for the actual
+ * hardware disable after having gotten the irq
+ * controller lock.
+ */
+
+/**
+ * disable_irq_nosync - disable an irq without waiting
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Disables and Enables are
+ * nested.
+ * Unlike disable_irq(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
+ *
+ * This function may be called from IRQ context.
+ */
+
+inline void disable_irq_nosync(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->depth++) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->disable(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/**
+ * disable_irq - disable an irq and wait for completion
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Enables and Disables are
+ * nested.
+ * This function waits for any pending IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while
+ * holding a resource the IRQ handler may need you will deadlock.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+
+void disable_irq(unsigned int irq)
+{
+ disable_irq_nosync(irq);
+
+ if (!local_irq_count(smp_processor_id())) {
+ do {
+ barrier();
+ cpu_relax();
+ } while (irq_desc[irq].status & IRQ_INPROGRESS);
+ }
+}
+
+/**
+ * enable_irq - enable handling of an irq
+ * @irq: Interrupt to enable
+ *
+ * Undoes the effect of one call to disable_irq(). If this
+ * matches the last disable, processing of interrupts on this
+ * IRQ line is re-enabled.
+ *
+ * This function may be called from IRQ context.
+ */
+
+void enable_irq(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ switch (desc->depth) {
+ case 1: {
+ unsigned int status = desc->status & ~IRQ_DISABLED;
+ desc->status = status;
+ if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
+ desc->status = status | IRQ_REPLAY;
+ hw_resend_irq(desc->handler,irq);
+ }
+ desc->handler->enable(irq);
+ /* fall-through */
+ }
+ default:
+ desc->depth--;
+ break;
+ case 0:
+ printk("enable_irq(%u) unbalanced from %p\n", irq,
+ __builtin_return_address(0));
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+asmlinkage unsigned int do_IRQ(int irq, struct pt_regs *regs)
+{
+ /*
+ * We ack quickly, we don't want the irq controller
+ * thinking we're snobs just because some other CPU has
+ * disabled global interrupts (we have already done the
+ * INT_ACK cycles, it's too late to try to pretend to the
+ * controller that we aren't taking the interrupt).
+ *
+ * 0 return value means that this irq is already being
+ * handled by some other CPU. (or is disabled)
+ */
+ int cpu = smp_processor_id();
+ irq_desc_t *desc = irq_desc + irq;
+ struct irqaction * action;
+ unsigned int status;
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+ long esp;
+
+ /* Debugging check for stack overflow: is there less than 1KB free? */
+ __asm__ __volatile__("andl %%esp,%0" : "=r" (esp) : "0" (8191));
+ if (unlikely(esp < (sizeof(struct task_struct) + 1024))) {
+ extern void show_stack(unsigned long *);
+
+ printk("do_IRQ: stack overflow: %ld\n",
+ esp - sizeof(struct task_struct));
+ __asm__ __volatile__("movl %%esp,%0" : "=r" (esp));
+ show_stack((void *)esp);
+ }
+#endif
+
+ kstat.irqs[cpu][irq]++;
+ spin_lock(&desc->lock);
+ desc->handler->ack(irq);
+ /*
+ REPLAY is when Linux resends an IRQ that was dropped earlier
+ WAITING is used by probe to mark irqs that are being tested
+ */
+ status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
+ status |= IRQ_PENDING; /* we _want_ to handle it */
+
+ /*
+ * If the IRQ is disabled for whatever reason, we cannot
+ * use the action we have.
+ */
+ action = NULL;
+ if (!(status & (IRQ_DISABLED | IRQ_INPROGRESS))) {
+ action = desc->action;
+ status &= ~IRQ_PENDING; /* we commit to handling */
+ status |= IRQ_INPROGRESS; /* we are handling it */
+ }
+ desc->status = status;
+
+ /*
+ * If there is no IRQ handler or it was disabled, exit early.
+ Since we set PENDING, if another processor is handling
+ a different instance of this same irq, the other processor
+ will take care of it.
+ */
+ if (!action)
+ goto out;
+
+ /*
+ * Edge triggered interrupts need to remember
+ * pending events.
+ * This applies to any hw interrupts that allow a second
+ * instance of the same irq to arrive while we are in do_IRQ
+ * or in the handler. But the code here only handles the _second_
+ * instance of the irq, not the third or fourth. So it is mostly
+ * useful for irq hardware that does not mask cleanly in an
+ * SMP environment.
+ */
+ for (;;) {
+ spin_unlock(&desc->lock);
+ handle_IRQ_event(irq, regs, action);
+ spin_lock(&desc->lock);
+
+ if (!(desc->status & IRQ_PENDING))
+ break;
+ desc->status &= ~IRQ_PENDING;
+ }
+ desc->status &= ~IRQ_INPROGRESS;
+out:
+ /*
+ * The ->end() handler has to deal with interrupts which got
+ * disabled while the handler was running.
+ */
+ desc->handler->end(irq);
+ spin_unlock(&desc->lock);
+
+ if (softirq_pending(cpu))
+ do_softirq();
+ return 1;
+}
+
+/**
+ * request_irq - allocate an interrupt line
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs
+ * @irqflags: Interrupt type flags
+ * @devname: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the
+ * interrupt line and IRQ handling. From the point this
+ * call is made your handler function may be invoked. Since
+ * your handler function must clear any interrupt the board
+ * raises, you must take care both to initialise your hardware
+ * and to set up the interrupt handler in the right order.
+ *
+ * Dev_id must be globally unique. Normally the address of the
+ * device data structure is used as the cookie. Since the handler
+ * receives this value it makes sense to use it.
+ *
+ * If your interrupt is shared you must pass a non NULL dev_id
+ * as this is required when freeing the interrupt.
+ *
+ * Flags:
+ *
+ * SA_SHIRQ Interrupt is shared
+ *
+ * SA_INTERRUPT Disable local interrupts while processing
+ *
+ * SA_SAMPLE_RANDOM The interrupt can be used for entropy
+ *
+ */
+
+int request_irq(unsigned int irq,
+ void (*handler)(int, void *, struct pt_regs *),
+ unsigned long irqflags,
+ const char * devname,
+ void *dev_id)
+{
+ int retval;
+ struct irqaction * action;
+
+#if 1
+ /*
+ * Sanity-check: shared interrupts should REALLY pass in
+ * a real dev-ID, otherwise we'll have trouble later trying
+ * to figure out which interrupt is which (messes up the
+ * interrupt freeing logic etc).
+ */
+ if (irqflags & SA_SHIRQ) {
+ if (!dev_id)
+ printk("Bad boy: %s (at 0x%x) called us without a dev_id!\n", devname, (&irq)[-1]);
+ }
+#endif
+
+ if (irq >= NR_IRQS)
+ return -EINVAL;
+ if (!handler)
+ return -EINVAL;
+
+ action = (struct irqaction *)
+ kmalloc(sizeof(struct irqaction), GFP_KERNEL);
+ if (!action)
+ return -ENOMEM;
+
+ action->handler = handler;
+ action->flags = irqflags;
+ action->mask = 0;
+ action->name = devname;
+ action->next = NULL;
+ action->dev_id = dev_id;
+
+ retval = setup_irq(irq, action);
+ if (retval)
+ kfree(action);
+ return retval;
+}
+
+/**
+ * free_irq - free an interrupt
+ * @irq: Interrupt line to free
+ * @dev_id: Device identity to free
+ *
+ * Remove an interrupt handler. The handler is removed and if the
+ * interrupt line is no longer in use by any driver it is disabled.
+ * On a shared IRQ the caller must ensure the interrupt is disabled
+ * on the card it drives before calling this function. The function
+ * does not return until any executing interrupts for this IRQ
+ * have completed.
+ *
+ * This function may be called from interrupt context.
+ *
+ * Bugs: Attempting to free an irq in a handler for the same irq hangs
+ * the machine.
+ */
+
+void free_irq(unsigned int irq, void *dev_id)
+{
+ irq_desc_t *desc;
+ struct irqaction **p;
+ unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return;
+
+ desc = irq_desc + irq;
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ for (;;) {
+ struct irqaction * action = *p;
+ if (action) {
+ struct irqaction **pp = p;
+ p = &action->next;
+ if (action->dev_id != dev_id)
+ continue;
+
+ /* Found it - now remove it from the list of entries */
+ *pp = action->next;
+ if (!desc->action) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->shutdown(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+#ifdef CONFIG_SMP
+ /* Wait to make sure it's not being used on another CPU */
+ while (desc->status & IRQ_INPROGRESS) {
+ barrier();
+ cpu_relax();
+ }
+#endif
+ kfree(action);
+ return;
+ }
+ printk("Trying to free free IRQ%d\n",irq);
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return;
+ }
+}
+
+/*
+ * IRQ autodetection code..
+ *
+ * This depends on the fact that any interrupt that
+ * comes in on to an unassigned handler will get stuck
+ * with "IRQ_WAITING" cleared and the interrupt
+ * disabled.
+ */
+
+static DECLARE_MUTEX(probe_sem);
+
+/**
+ * probe_irq_on - begin an interrupt autodetect
+ *
+ * Commence probing for an interrupt. The interrupts are scanned
+ * and a mask of potential interrupt lines is returned.
+ *
+ */
+
+unsigned long probe_irq_on(void)
+{
+ unsigned int i;
+ irq_desc_t *desc;
+ unsigned long val;
+ unsigned long delay;
+
+ down(&probe_sem);
+ /*
+ * something may have generated an irq long ago and we want to
+ * flush such a longstanding irq before considering it as spurious.
+ */
+ for (i = NR_IRQS-1; i > 0; i--) {
+ desc = irq_desc + i;
+
+ spin_lock_irq(&desc->lock);
+ if (!irq_desc[i].action)
+ irq_desc[i].handler->startup(i);
+ spin_unlock_irq(&desc->lock);
+ }
+
+ /* Wait for longstanding interrupts to trigger. */
+ for (delay = jiffies + HZ/50; time_after(delay, jiffies); )
+ /* about 20ms delay */ synchronize_irq();
+
+ /*
+ * enable any unassigned irqs
+ * (we must startup again here because if a longstanding irq
+ * happened in the previous stage, it may have masked itself)
+ */
+ for (i = NR_IRQS-1; i > 0; i--) {
+ desc = irq_desc + i;
+
+ spin_lock_irq(&desc->lock);
+ if (!desc->action) {
+ desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
+ if (desc->handler->startup(i))
+ desc->status |= IRQ_PENDING;
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+
+ /*
+ * Wait for spurious interrupts to trigger
+ */
+ for (delay = jiffies + HZ/10; time_after(delay, jiffies); )
+ /* about 100ms delay */ synchronize_irq();
+
+ /*
+ * Now filter out any obviously spurious interrupts
+ */
+ val = 0;
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ /* It triggered already - consider it spurious. */
+ if (!(status & IRQ_WAITING)) {
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ } else
+ if (i < 32)
+ val |= 1 << i;
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+
+ return val;
+}
+
+/*
+ * Return a mask of triggered interrupts (this
+ * can handle only legacy ISA interrupts).
+ */
+
+/**
+ * probe_irq_mask - scan a bitmap of interrupt lines
+ * @val: mask of interrupts to consider
+ *
+ * Scan the ISA bus interrupt lines and return a bitmap of
+ * active interrupts. The interrupt probe logic state is then
+ * returned to its previous value.
+ *
+ * Note: we need to scan all the irq's even though we will
+ * only return ISA irq numbers - just so that we reset them
+ * all to a known state.
+ */
+unsigned int probe_irq_mask(unsigned long val)
+{
+ int i;
+ unsigned int mask;
+
+ mask = 0;
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ if (i < 16 && !(status & IRQ_WAITING))
+ mask |= 1 << i;
+
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+ up(&probe_sem);
+
+ return mask & val;
+}
+
+/*
+ * Return the one interrupt that triggered (this can
+ * handle any interrupt source).
+ */
+
+/**
+ * probe_irq_off - end an interrupt autodetect
+ * @val: mask of potential interrupts (unused)
+ *
+ * Scans the unused interrupt lines and returns the line which
+ * appears to have triggered the interrupt. If no interrupt was
+ * found then zero is returned. If more than one interrupt is
+ * found then minus the first candidate is returned to indicate
+ * their is doubt.
+ *
+ * The interrupt probe logic state is returned to its previous
+ * value.
+ *
+ * BUGS: When used in a module (which arguably shouldnt happen)
+ * nothing prevents two IRQ probe callers from overlapping. The
+ * results of this are non-optimal.
+ */
+
+int probe_irq_off(unsigned long val)
+{
+ int i, irq_found, nr_irqs;
+
+ nr_irqs = 0;
+ irq_found = 0;
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ if (!(status & IRQ_WAITING)) {
+ if (!nr_irqs)
+ irq_found = i;
+ nr_irqs++;
+ }
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+ up(&probe_sem);
+
+ if (nr_irqs > 1)
+ irq_found = -irq_found;
+ return irq_found;
+}
+
+/* this was setup_x86_irq but it seems pretty generic */
+int setup_irq(unsigned int irq, struct irqaction * new)
+{
+ int shared = 0;
+ unsigned long flags;
+ struct irqaction *old, **p;
+ irq_desc_t *desc = irq_desc + irq;
+
+ /*
+ * Some drivers like serial.c use request_irq() heavily,
+ * so we have to be careful not to interfere with a
+ * running system.
+ */
+ if (new->flags & SA_SAMPLE_RANDOM) {
+ /*
+ * This function might sleep, we want to call it first,
+ * outside of the atomic block.
+ * Yes, this might clear the entropy pool if the wrong
+ * driver is attempted to be loaded, without actually
+ * installing a new handler, but is this really a problem,
+ * only the sysadmin is able to do this.
+ */
+ rand_initialize_irq(irq);
+ }
+
+ /*
+ * The following block of code has to be executed atomically
+ */
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ if ((old = *p) != NULL) {
+ /* Can't share interrupts unless both agree to */
+ if (!(old->flags & new->flags & SA_SHIRQ)) {
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return -EBUSY;
+ }
+
+ /* add new interrupt at end of irq queue */
+ do {
+ p = &old->next;
+ old = *p;
+ } while (old);
+ shared = 1;
+ }
+
+ *p = new;
+
+ if (!shared) {
+ desc->depth = 0;
+ desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | IRQ_WAITING);
+ desc->handler->startup(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+ register_irq_proc(irq);
+ return 0;
+}
+
+static struct proc_dir_entry * root_irq_dir;
+static struct proc_dir_entry * irq_dir [NR_IRQS];
+
+#define HEX_DIGITS 8
+
+static unsigned int parse_hex_value (const char *buffer,
+ unsigned long count, unsigned long *ret)
+{
+ unsigned char hexnum [HEX_DIGITS];
+ unsigned long value;
+ int i;
+
+ if (!count)
+ return -EINVAL;
+ if (count > HEX_DIGITS)
+ count = HEX_DIGITS;
+ if (copy_from_user(hexnum, buffer, count))
+ return -EFAULT;
+
+ /*
+ * Parse the first 8 characters as a hex string, any non-hex char
+ * is end-of-string. '00e1', 'e1', '00E1', 'E1' are all the same.
+ */
+ value = 0;
+
+ for (i = 0; i < count; i++) {
+ unsigned int c = hexnum[i];
+
+ switch (c) {
+ case '0' ... '9': c -= '0'; break;
+ case 'a' ... 'f': c -= 'a'-10; break;
+ case 'A' ... 'F': c -= 'A'-10; break;
+ default:
+ goto out;
+ }
+ value = (value << 4) | c;
+ }
+out:
+ *ret = value;
+ return 0;
+}
+
+#if CONFIG_SMP
+
+static struct proc_dir_entry * smp_affinity_entry [NR_IRQS];
+
+static unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL };
+static int irq_affinity_read_proc (char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ if (count < HEX_DIGITS+1)
+ return -EINVAL;
+ return sprintf (page, "%08lx\n", irq_affinity[(long)data]);
+}
+
+static int irq_affinity_write_proc (struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ int irq = (long) data, full_count = count, err;
+ unsigned long new_value;
+
+ if (!irq_desc[irq].handler->set_affinity)
+ return -EIO;
+
+ err = parse_hex_value(buffer, count, &new_value);
+
+ /*
+ * Do not allow disabling IRQs completely - it's a too easy
+ * way to make the system unusable accidentally :-) At least
+ * one online CPU still has to be targeted.
+ */
+ if (!(new_value & cpu_online_map))
+ return -EINVAL;
+
+ irq_affinity[irq] = new_value;
+ irq_desc[irq].handler->set_affinity(irq, new_value);
+
+ return full_count;
+}
+
+#endif
+
+static int prof_cpu_mask_read_proc (char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ unsigned long *mask = (unsigned long *) data;
+ if (count < HEX_DIGITS+1)
+ return -EINVAL;
+ return sprintf (page, "%08lx\n", *mask);
+}
+
+static int prof_cpu_mask_write_proc (struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ unsigned long *mask = (unsigned long *) data, full_count = count, err;
+ unsigned long new_value;
+
+ err = parse_hex_value(buffer, count, &new_value);
+ if (err)
+ return err;
+
+ *mask = new_value;
+ return full_count;
+}
+
+#define MAX_NAMELEN 10
+
+static void register_irq_proc (unsigned int irq)
+{
+ char name [MAX_NAMELEN];
+
+ if (!root_irq_dir || (irq_desc[irq].handler == &no_irq_type) ||
+ irq_dir[irq])
+ return;
+
+ memset(name, 0, MAX_NAMELEN);
+ sprintf(name, "%d", irq);
+
+ /* create /proc/irq/1234 */
+ irq_dir[irq] = proc_mkdir(name, root_irq_dir);
+
+#if CONFIG_SMP
+ {
+ struct proc_dir_entry *entry;
+
+ /* create /proc/irq/1234/smp_affinity */
+ entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]);
+
+ if (entry) {
+ entry->nlink = 1;
+ entry->data = (void *)(long)irq;
+ entry->read_proc = irq_affinity_read_proc;
+ entry->write_proc = irq_affinity_write_proc;
+ }
+
+ smp_affinity_entry[irq] = entry;
+ }
+#endif
+}
+
+unsigned long prof_cpu_mask = -1;
+
+void init_irq_proc (void)
+{
+ struct proc_dir_entry *entry;
+ int i;
+
+ /* create /proc/irq */
+ root_irq_dir = proc_mkdir("irq", 0);
+
+ /* create /proc/irq/prof_cpu_mask */
+ entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
+
+ if (!entry)
+ return;
+
+ entry->nlink = 1;
+ entry->data = (void *)&prof_cpu_mask;
+ entry->read_proc = prof_cpu_mask_read_proc;
+ entry->write_proc = prof_cpu_mask_write_proc;
+
+ /*
+ * Create entries for all existing IRQs.
+ */
+ for (i = 0; i < NR_IRQS; i++)
+ register_irq_proc(i);
+}
+
--- /dev/null
+/*
+ * linux/kernel/ldt.c
+ *
+ * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+
+/*
+ * XXX KAF (28/7/02): This stuff is only used for DOS emulation, and is
+ * the default way of finding current TCB in linuxthreads. Supporting
+ * table update svia the hypervisor is feasible, but a hassle: for now,
+ * recompiling linuxthreads is the most sensible option.
+ *
+ * Oh, this may become an issue depending on what JVM we use for
+ * running the xeno-daemon.
+ */
+
+asmlinkage int sys_modify_ldt(int func, void *ptr, unsigned long bytecount)
+{
+ return -ENOSYS;
+}
--- /dev/null
+/*
+ * linux/arch/i386/kernel/process.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+
+#define __KERNEL_SYSCALLS__
+#include <stdarg.h>
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/mc146818rtc.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/ldt.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+#include <linux/irq.h>
+
+asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+
+int hlt_counter;
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+
+/*
+ * Power off function, if any
+ */
+void (*pm_power_off)(void);
+
+void disable_hlt(void)
+{
+ hlt_counter++;
+}
+
+void enable_hlt(void)
+{
+ hlt_counter--;
+}
+
+/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle (void)
+{
+ /* endless idle loop with no priority at all */
+ init_idle();
+ current->nice = 20;
+ current->counter = -100;
+
+ while (1) {
+ while (!current->need_resched)
+ HYPERVISOR_do_sched_op(NULL);
+ schedule();
+ check_pgt_cache();
+ }
+}
+
+void machine_restart(char * __unused)
+{
+ HYPERVISOR_exit();
+}
+
+void machine_halt(void)
+{
+ HYPERVISOR_exit();
+}
+
+void machine_power_off(void)
+{
+ HYPERVISOR_exit();
+}
+
+extern void show_trace(unsigned long* esp);
+
+void show_regs(struct pt_regs * regs)
+{
+ printk("\n");
+ printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
+ printk("EIP: %04x:[<%08lx>] CPU: %d",0xffff & regs->xcs,regs->eip, smp_processor_id());
+ if (regs->xcs & 2)
+ printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
+ printk(" EFLAGS: %08lx %s\n",regs->eflags, print_tainted());
+ printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+ regs->eax,regs->ebx,regs->ecx,regs->edx);
+ printk("ESI: %08lx EDI: %08lx EBP: %08lx",
+ regs->esi, regs->edi, regs->ebp);
+ printk(" DS: %04x ES: %04x\n",
+ 0xffff & regs->xds,0xffff & regs->xes);
+
+ show_trace(®s->esp);
+}
+
+/*
+ * No need to lock the MM as we are the last user
+ */
+void release_segments(struct mm_struct *mm)
+{
+ void * ldt = mm->context.segments;
+
+ /*
+ * free the LDT
+ */
+ if (ldt) {
+ mm->context.segments = NULL;
+ clear_LDT();
+ vfree(ldt);
+ }
+}
+
+/*
+ * Create a kernel thread
+ */
+int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+{
+ long retval, d0;
+
+ __asm__ __volatile__(
+ "movl %%esp,%%esi\n\t"
+ "int $0x80\n\t" /* Linux/i386 system call */
+ "cmpl %%esp,%%esi\n\t" /* child or parent? */
+ "je 1f\n\t" /* parent - jump */
+ /* Load the argument into eax, and push it. That way, it does
+ * not matter whether the called function is compiled with
+ * -mregparm or not. */
+ "movl %4,%%eax\n\t"
+ "pushl %%eax\n\t"
+ "call *%5\n\t" /* call fn */
+ "movl %3,%0\n\t" /* exit */
+ "int $0x80\n"
+ "1:\t"
+ :"=&a" (retval), "=&S" (d0)
+ :"0" (__NR_clone), "i" (__NR_exit),
+ "r" (arg), "r" (fn),
+ "b" (flags | CLONE_VM)
+ : "memory");
+
+ return retval;
+}
+
+/*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+ /* nothing to do ... */
+}
+
+void flush_thread(void)
+{
+ struct task_struct *tsk = current;
+
+ memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
+
+ /*
+ * Forget coprocessor state..
+ */
+ clear_fpu(tsk);
+ tsk->used_math = 0;
+}
+
+void release_thread(struct task_struct *dead_task)
+{
+ if (dead_task->mm) {
+ void * ldt = dead_task->mm->context.segments;
+
+ // temporary debugging check
+ if (ldt) {
+ printk("WARNING: dead process %8s still has LDT? <%p>\n",
+ dead_task->comm, ldt);
+ BUG();
+ }
+ }
+}
+
+/*
+ * we do not have to muck with descriptors here, that is
+ * done in switch_mm() as needed.
+ */
+void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
+{
+ struct mm_struct * old_mm;
+ void *old_ldt, *ldt;
+
+ ldt = NULL;
+ old_mm = current->mm;
+ if (old_mm && (old_ldt = old_mm->context.segments) != NULL) {
+ /*
+ * Completely new LDT, we initialize it from the parent:
+ */
+ ldt = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE);
+ if (!ldt)
+ printk(KERN_WARNING "ldt allocation failed\n");
+ else
+ memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_SIZE);
+ }
+ new_mm->context.segments = ldt;
+ new_mm->context.cpuvalid = ~0UL; /* valid on all CPU's - they can't have stale data */
+}
+
+/*
+ * Save a segment.
+ */
+#define savesegment(seg,value) \
+ asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))
+
+int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
+ unsigned long unused,
+ struct task_struct * p, struct pt_regs * regs)
+{
+ struct pt_regs * childregs;
+
+ childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;
+ struct_cpy(childregs, regs);
+ childregs->eax = 0;
+ childregs->esp = esp;
+
+ p->thread.esp = (unsigned long) childregs;
+ p->thread.esp0 = (unsigned long) (childregs+1);
+
+ p->thread.eip = (unsigned long) ret_from_fork;
+
+ savesegment(fs,p->thread.fs);
+ savesegment(gs,p->thread.gs);
+
+ unlazy_fpu(current);
+ struct_cpy(&p->thread.i387, ¤t->thread.i387);
+
+ return 0;
+}
+
+/*
+ * fill in the user structure for a core dump..
+ */
+void dump_thread(struct pt_regs * regs, struct user * dump)
+{
+ int i;
+
+/* changed the size calculations - should hopefully work better. lbt */
+ dump->magic = CMAGIC;
+ dump->start_code = 0;
+ dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
+ dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
+ dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
+ dump->u_dsize -= dump->u_tsize;
+ dump->u_ssize = 0;
+ for (i = 0; i < 8; i++)
+ dump->u_debugreg[i] = current->thread.debugreg[i];
+
+ if (dump->start_stack < TASK_SIZE)
+ dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;
+
+ dump->regs.ebx = regs->ebx;
+ dump->regs.ecx = regs->ecx;
+ dump->regs.edx = regs->edx;
+ dump->regs.esi = regs->esi;
+ dump->regs.edi = regs->edi;
+ dump->regs.ebp = regs->ebp;
+ dump->regs.eax = regs->eax;
+ dump->regs.ds = regs->xds;
+ dump->regs.es = regs->xes;
+ savesegment(fs,dump->regs.fs);
+ savesegment(gs,dump->regs.gs);
+ dump->regs.orig_eax = regs->orig_eax;
+ dump->regs.eip = regs->eip;
+ dump->regs.cs = regs->xcs;
+ dump->regs.eflags = regs->eflags;
+ dump->regs.esp = regs->esp;
+ dump->regs.ss = regs->xss;
+
+ dump->u_fpvalid = dump_fpu (regs, &dump->i387);
+}
+
+/*
+ * switch_to(x,yn) should switch tasks from x to y.
+ *
+ * We fsave/fwait so that an exception goes off at the right time
+ * (as a call from the fsave or fwait in effect) rather than to
+ * the wrong process. Lazy FP saving no longer makes any sense
+ * with modern CPU's, and this simplifies a lot of things (SMP
+ * and UP become the same).
+ *
+ * NOTE! We used to use the x86 hardware context switching. The
+ * reason for not using it any more becomes apparent when you
+ * try to recover gracefully from saved state that is no longer
+ * valid (stale segment register values in particular). With the
+ * hardware task-switch, there is no way to fix up bad state in
+ * a reasonable manner.
+ *
+ * The fact that Intel documents the hardware task-switching to
+ * be slow is a fairly red herring - this code is not noticeably
+ * faster. However, there _is_ some room for improvement here,
+ * so the performance issues may eventually be a valid point.
+ * More important, however, is the fact that this allows us much
+ * more flexibility.
+ */
+void __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
+{
+ struct thread_struct *prev = &prev_p->thread,
+ *next = &next_p->thread;
+
+ unlazy_fpu(prev_p);
+
+ HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, next->esp0, 0);
+
+ /*
+ * Save away %fs and %gs. No need to save %es and %ds, as
+ * those are always kernel segments while inside the kernel.
+ */
+ asm volatile("movl %%fs,%0":"=m" (*(int *)&prev->fs));
+ asm volatile("movl %%gs,%0":"=m" (*(int *)&prev->gs));
+
+ /*
+ * Restore %fs and %gs.
+ */
+ loadsegment(fs, next->fs);
+ loadsegment(gs, next->gs);
+
+ /*
+ * Now maybe reload the debug registers
+ */
+ if ( next->debugreg[7] != 0 )
+ {
+ HYPERVISOR_set_debugreg(0, next->debugreg[0]);
+ HYPERVISOR_set_debugreg(1, next->debugreg[1]);
+ HYPERVISOR_set_debugreg(2, next->debugreg[2]);
+ HYPERVISOR_set_debugreg(3, next->debugreg[3]);
+ /* no 4 and 5 */
+ HYPERVISOR_set_debugreg(6, next->debugreg[6]);
+ HYPERVISOR_set_debugreg(7, next->debugreg[7]);
+ }
+}
+
+asmlinkage int sys_fork(struct pt_regs regs)
+{
+ return do_fork(SIGCHLD, regs.esp, ®s, 0);
+}
+
+asmlinkage int sys_clone(struct pt_regs regs)
+{
+ unsigned long clone_flags;
+ unsigned long newsp;
+
+ clone_flags = regs.ebx;
+ newsp = regs.ecx;
+ if (!newsp)
+ newsp = regs.esp;
+ return do_fork(clone_flags, newsp, ®s, 0);
+}
+
+/*
+ * This is trivial, and on the face of it looks like it
+ * could equally well be done in user mode.
+ *
+ * Not so, for quite unobvious reasons - register pressure.
+ * In user mode vfork() cannot have a stack frame, and if
+ * done by calling the "clone()" system call directly, you
+ * do not have enough call-clobbered registers to hold all
+ * the information you need.
+ */
+asmlinkage int sys_vfork(struct pt_regs regs)
+{
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0);
+}
+
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage int sys_execve(struct pt_regs regs)
+{
+ int error;
+ char * filename;
+
+ filename = getname((char *) regs.ebx);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ goto out;
+ error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, ®s);
+ if (error == 0)
+ current->ptrace &= ~PT_DTRACE;
+ putname(filename);
+ out:
+ return error;
+}
+
+/*
+ * These bracket the sleeping functions..
+ */
+extern void scheduling_functions_start_here(void);
+extern void scheduling_functions_end_here(void);
+#define first_sched ((unsigned long) scheduling_functions_start_here)
+#define last_sched ((unsigned long) scheduling_functions_end_here)
+
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ebp, esp, eip;
+ unsigned long stack_page;
+ int count = 0;
+ if (!p || p == current || p->state == TASK_RUNNING)
+ return 0;
+ stack_page = (unsigned long)p;
+ esp = p->thread.esp;
+ if (!stack_page || esp < stack_page || esp > 8188+stack_page)
+ return 0;
+ /* include/asm-i386/system.h:switch_to() pushes ebp last. */
+ ebp = *(unsigned long *) esp;
+ do {
+ if (ebp < stack_page || ebp > 8184+stack_page)
+ return 0;
+ eip = *(unsigned long *) (ebp+4);
+ if (eip < first_sched || eip >= last_sched)
+ return eip;
+ ebp = *(unsigned long *) ebp;
+ } while (count++ < 16);
+ return 0;
+}
+#undef last_sched
+#undef first_sched
--- /dev/null
+/* ptrace.c */
+/* By Ross Biro 1/23/92 */
+/*
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/debugreg.h>
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+/* determines which flags the user has access to. */
+/* 1 = access 0 = no access */
+#define FLAG_MASK 0x00044dd5
+
+/* set's the trap flag. */
+#define TRAP_FLAG 0x100
+
+/*
+ * Offset of eflags on child stack..
+ */
+#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))
+
+/*
+ * this routine will get a word off of the processes privileged stack.
+ * the offset is how far from the base addr as stored in the TSS.
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int get_stack_long(struct task_struct *task, int offset)
+{
+ unsigned char *stack;
+
+ stack = (unsigned char *)task->thread.esp0;
+ stack += offset;
+ return (*((int *)stack));
+}
+
+/*
+ * this routine will put a word on the processes privileged stack.
+ * the offset is how far from the base addr as stored in the TSS.
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int put_stack_long(struct task_struct *task, int offset,
+ unsigned long data)
+{
+ unsigned char * stack;
+
+ stack = (unsigned char *) task->thread.esp0;
+ stack += offset;
+ *(unsigned long *) stack = data;
+ return 0;
+}
+
+static int putreg(struct task_struct *child,
+ unsigned long regno, unsigned long value)
+{
+ switch (regno >> 2) {
+ case FS:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ child->thread.fs = value;
+ return 0;
+ case GS:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ child->thread.gs = value;
+ return 0;
+ case DS:
+ case ES:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ value &= 0xffff;
+ break;
+ case SS:
+ case CS:
+ if ((value & 3) != 3)
+ return -EIO;
+ value &= 0xffff;
+ break;
+ case EFL:
+ value &= FLAG_MASK;
+ value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
+ break;
+ }
+ if (regno > GS*4)
+ regno -= 2*4;
+ put_stack_long(child, regno - sizeof(struct pt_regs), value);
+ return 0;
+}
+
+static unsigned long getreg(struct task_struct *child,
+ unsigned long regno)
+{
+ unsigned long retval = ~0UL;
+
+ switch (regno >> 2) {
+ case FS:
+ retval = child->thread.fs;
+ break;
+ case GS:
+ retval = child->thread.gs;
+ break;
+ case DS:
+ case ES:
+ case SS:
+ case CS:
+ retval = 0xffff;
+ /* fall through */
+ default:
+ if (regno > GS*4)
+ regno -= 2*4;
+ regno = regno - sizeof(struct pt_regs);
+ retval &= get_stack_long(child, regno);
+ }
+ return retval;
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure the single step bit is not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+ long tmp;
+
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+}
+
+asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
+{
+ struct task_struct *child;
+ struct user * dummy = NULL;
+ int i, ret;
+
+ lock_kernel();
+ ret = -EPERM;
+ if (request == PTRACE_TRACEME) {
+ /* are we already being traced? */
+ if (current->ptrace & PT_PTRACED)
+ goto out;
+ /* set the ptrace bit in the process flags. */
+ current->ptrace |= PT_PTRACED;
+ ret = 0;
+ goto out;
+ }
+ ret = -ESRCH;
+ read_lock(&tasklist_lock);
+ child = find_task_by_pid(pid);
+ if (child)
+ get_task_struct(child);
+ read_unlock(&tasklist_lock);
+ if (!child)
+ goto out;
+
+ ret = -EPERM;
+ if (pid == 1) /* you may not mess with init */
+ goto out_tsk;
+
+ if (request == PTRACE_ATTACH) {
+ ret = ptrace_attach(child);
+ goto out_tsk;
+ }
+
+ ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ if (ret < 0)
+ goto out_tsk;
+
+ switch (request) {
+ /* when I and D space are separate, these will need to be fixed. */
+ case PTRACE_PEEKTEXT: /* read word at location addr. */
+ case PTRACE_PEEKDATA: {
+ unsigned long tmp;
+ int copied;
+
+ copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+ ret = -EIO;
+ if (copied != sizeof(tmp))
+ break;
+ ret = put_user(tmp,(unsigned long *) data);
+ break;
+ }
+
+ /* read the word at location addr in the USER area. */
+ case PTRACE_PEEKUSR: {
+ unsigned long tmp;
+
+ ret = -EIO;
+ if ((addr & 3) || addr < 0 ||
+ addr > sizeof(struct user) - 3)
+ break;
+
+ tmp = 0; /* Default return condition */
+ if(addr < FRAME_SIZE*sizeof(long))
+ tmp = getreg(child, addr);
+ if(addr >= (long) &dummy->u_debugreg[0] &&
+ addr <= (long) &dummy->u_debugreg[7]){
+ addr -= (long) &dummy->u_debugreg[0];
+ addr = addr >> 2;
+ tmp = child->thread.debugreg[addr];
+ }
+ ret = put_user(tmp,(unsigned long *) data);
+ break;
+ }
+
+ /* when I and D space are separate, this will have to be fixed. */
+ case PTRACE_POKETEXT: /* write the word at location addr. */
+ case PTRACE_POKEDATA:
+ ret = 0;
+ if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
+ break;
+ ret = -EIO;
+ break;
+
+ case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
+ ret = -EIO;
+ if ((addr & 3) || addr < 0 ||
+ addr > sizeof(struct user) - 3)
+ break;
+
+ if (addr < FRAME_SIZE*sizeof(long)) {
+ ret = putreg(child, addr, data);
+ break;
+ }
+ /* We need to be very careful here. We implicitly
+ want to modify a portion of the task_struct, and we
+ have to be selective about what portions we allow someone
+ to modify. */
+
+ ret = -EIO;
+ if(addr >= (long) &dummy->u_debugreg[0] &&
+ addr <= (long) &dummy->u_debugreg[7]){
+
+ if(addr == (long) &dummy->u_debugreg[4]) break;
+ if(addr == (long) &dummy->u_debugreg[5]) break;
+ if(addr < (long) &dummy->u_debugreg[4] &&
+ ((unsigned long) data) >= TASK_SIZE-3) break;
+
+ if(addr == (long) &dummy->u_debugreg[7]) {
+ data &= ~DR_CONTROL_RESERVED;
+ for(i=0; i<4; i++)
+ if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
+ goto out_tsk;
+ }
+
+ addr -= (long) &dummy->u_debugreg;
+ addr = addr >> 2;
+ child->thread.debugreg[addr] = data;
+ ret = 0;
+ }
+ break;
+
+ case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
+ case PTRACE_CONT: { /* restart after signal. */
+ long tmp;
+
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ if (request == PTRACE_SYSCALL)
+ child->ptrace |= PT_TRACESYS;
+ else
+ child->ptrace &= ~PT_TRACESYS;
+ child->exit_code = data;
+ /* make sure the single step bit is not set. */
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET,tmp);
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+/*
+ * make the child exit. Best I can do is send it a sigkill.
+ * perhaps it should be put in the status that it wants to
+ * exit.
+ */
+ case PTRACE_KILL: {
+ long tmp;
+
+ ret = 0;
+ if (child->state == TASK_ZOMBIE) /* already dead */
+ break;
+ child->exit_code = SIGKILL;
+ /* make sure the single step bit is not set. */
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+ wake_up_process(child);
+ break;
+ }
+
+ case PTRACE_SINGLESTEP: { /* set the trap flag. */
+ long tmp;
+
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ child->ptrace &= ~PT_TRACESYS;
+ if ((child->ptrace & PT_DTRACE) == 0) {
+ /* Spurious delayed TF traps may occur */
+ child->ptrace |= PT_DTRACE;
+ }
+ tmp = get_stack_long(child, EFL_OFFSET) | TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+ child->exit_code = data;
+ /* give it a chance to run. */
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_DETACH:
+ /* detach a process that was attached. */
+ ret = ptrace_detach(child, data);
+ break;
+
+ case PTRACE_GETREGS: { /* Get all gp regs from the child. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
+ ret = -EIO;
+ break;
+ }
+ for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+ __put_user(getreg(child, i),(unsigned long *) data);
+ data += sizeof(long);
+ }
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_SETREGS: { /* Set all gp regs in the child. */
+ unsigned long tmp;
+ if (!access_ok(VERIFY_READ, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
+ ret = -EIO;
+ break;
+ }
+ for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+ __get_user(tmp, (unsigned long *) data);
+ putreg(child, i, tmp);
+ data += sizeof(long);
+ }
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETFPREGS: { /* Get the child FPU state. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data,
+ sizeof(struct user_i387_struct))) {
+ ret = -EIO;
+ break;
+ }
+ ret = 0;
+ if ( !child->used_math )
+ load_empty_fpu(child);
+ get_fpregs((struct user_i387_struct *)data, child);
+ break;
+ }
+
+ case PTRACE_SETFPREGS: { /* Set the child FPU state. */
+ if (!access_ok(VERIFY_READ, (unsigned *)data,
+ sizeof(struct user_i387_struct))) {
+ ret = -EIO;
+ break;
+ }
+ child->used_math = 1;
+ set_fpregs(child, (struct user_i387_struct *)data);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data,
+ sizeof(struct user_fxsr_struct))) {
+ ret = -EIO;
+ break;
+ }
+ if ( !child->used_math )
+ load_empty_fpu(child);
+ ret = get_fpxregs((struct user_fxsr_struct *)data, child);
+ break;
+ }
+
+ case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
+ if (!access_ok(VERIFY_READ, (unsigned *)data,
+ sizeof(struct user_fxsr_struct))) {
+ ret = -EIO;
+ break;
+ }
+ child->used_math = 1;
+ ret = set_fpxregs(child, (struct user_fxsr_struct *)data);
+ break;
+ }
+
+ case PTRACE_SETOPTIONS: {
+ if (data & PTRACE_O_TRACESYSGOOD)
+ child->ptrace |= PT_TRACESYSGOOD;
+ else
+ child->ptrace &= ~PT_TRACESYSGOOD;
+ ret = 0;
+ break;
+ }
+
+ default:
+ ret = -EIO;
+ break;
+ }
+out_tsk:
+ free_task_struct(child);
+out:
+ unlock_kernel();
+ return ret;
+}
+
+asmlinkage void syscall_trace(void)
+{
+ if ((current->ptrace & (PT_PTRACED|PT_TRACESYS)) !=
+ (PT_PTRACED|PT_TRACESYS))
+ return;
+ /* the 0x80 provides a way for the tracing parent to distinguish
+ between a syscall stop and SIGTRAP delivery */
+ current->exit_code = SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
+ ? 0x80 : 0);
+ current->state = TASK_STOPPED;
+ notify_parent(current, SIGCHLD);
+ schedule();
+ /*
+ * this isn't the same as continuing with a signal, but it will do
+ * for normal use. strace only continues with a signal if the
+ * stopping signal is not SIGTRAP. -brl
+ */
+ if (current->exit_code) {
+ send_sig(current->exit_code, current, 1);
+ current->exit_code = 0;
+ }
+}
--- /dev/null
+/*
+ * i386 semaphore implementation.
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ *
+ * Portions Copyright 1999 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@redhat.com>
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/semaphore.h>
+
+/*
+ * Semaphores are implemented using a two-way counter:
+ * The "count" variable is decremented for each process
+ * that tries to acquire the semaphore, while the "sleeping"
+ * variable is a count of such acquires.
+ *
+ * Notably, the inline "up()" and "down()" functions can
+ * efficiently test if they need to do any extra work (up
+ * needs to do something only if count was negative before
+ * the increment operation.
+ *
+ * "sleeping" and the contention routine ordering is
+ * protected by the semaphore spinlock.
+ *
+ * Note that these functions are only called when there is
+ * contention on the lock, and as such all this is the
+ * "non-critical" part of the whole semaphore business. The
+ * critical part is the inline stuff in <asm/semaphore.h>
+ * where we want to avoid any extra jumps and calls.
+ */
+
+/*
+ * Logic:
+ * - only on a boundary condition do we need to care. When we go
+ * from a negative count to a non-negative, we wake people up.
+ * - when we go from a non-negative count to a negative do we
+ * (a) synchronize with the "sleeper" count and (b) make sure
+ * that we're on the wakeup list before we synchronize so that
+ * we cannot lose wakeup events.
+ */
+
+void __up(struct semaphore *sem)
+{
+ wake_up(&sem->wait);
+}
+
+static spinlock_t semaphore_lock = SPIN_LOCK_UNLOCKED;
+
+void __down(struct semaphore * sem)
+{
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+
+ spin_lock_irq(&semaphore_lock);
+ sem->sleepers++;
+ for (;;) {
+ int sleepers = sem->sleepers;
+
+ /*
+ * Add "everybody else" into it. They aren't
+ * playing, because we own the spinlock.
+ */
+ if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+ sem->sleepers = 0;
+ break;
+ }
+ sem->sleepers = 1; /* us - see -1 above */
+ spin_unlock_irq(&semaphore_lock);
+
+ schedule();
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ spin_lock_irq(&semaphore_lock);
+ }
+ spin_unlock_irq(&semaphore_lock);
+ remove_wait_queue(&sem->wait, &wait);
+ tsk->state = TASK_RUNNING;
+ wake_up(&sem->wait);
+}
+
+int __down_interruptible(struct semaphore * sem)
+{
+ int retval = 0;
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+ tsk->state = TASK_INTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+
+ spin_lock_irq(&semaphore_lock);
+ sem->sleepers ++;
+ for (;;) {
+ int sleepers = sem->sleepers;
+
+ /*
+ * With signals pending, this turns into
+ * the trylock failure case - we won't be
+ * sleeping, and we* can't get the lock as
+ * it has contention. Just correct the count
+ * and exit.
+ */
+ if (signal_pending(current)) {
+ retval = -EINTR;
+ sem->sleepers = 0;
+ atomic_add(sleepers, &sem->count);
+ break;
+ }
+
+ /*
+ * Add "everybody else" into it. They aren't
+ * playing, because we own the spinlock. The
+ * "-1" is because we're still hoping to get
+ * the lock.
+ */
+ if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+ sem->sleepers = 0;
+ break;
+ }
+ sem->sleepers = 1; /* us - see -1 above */
+ spin_unlock_irq(&semaphore_lock);
+
+ schedule();
+ tsk->state = TASK_INTERRUPTIBLE;
+ spin_lock_irq(&semaphore_lock);
+ }
+ spin_unlock_irq(&semaphore_lock);
+ tsk->state = TASK_RUNNING;
+ remove_wait_queue(&sem->wait, &wait);
+ wake_up(&sem->wait);
+ return retval;
+}
+
+/*
+ * Trylock failed - make sure we correct for
+ * having decremented the count.
+ *
+ * We could have done the trylock with a
+ * single "cmpxchg" without failure cases,
+ * but then it wouldn't work on a 386.
+ */
+int __down_trylock(struct semaphore * sem)
+{
+ int sleepers;
+ unsigned long flags;
+
+ spin_lock_irqsave(&semaphore_lock, flags);
+ sleepers = sem->sleepers + 1;
+ sem->sleepers = 0;
+
+ /*
+ * Add "everybody else" and us into it. They aren't
+ * playing, because we own the spinlock.
+ */
+ if (!atomic_add_negative(sleepers, &sem->count))
+ wake_up(&sem->wait);
+
+ spin_unlock_irqrestore(&semaphore_lock, flags);
+ return 1;
+}
+
+
+/*
+ * The semaphore operations have a special calling sequence that
+ * allow us to do a simpler in-line version of them. These routines
+ * need to convert that sequence back into the C sequence when
+ * there is contention on the semaphore.
+ *
+ * %ecx contains the semaphore pointer on entry. Save the C-clobbered
+ * registers (%eax, %edx and %ecx) except %eax when used as a return
+ * value..
+ */
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed\n"
+"__down_failed:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %eax\n\t"
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+ "popl %eax\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed_interruptible\n"
+"__down_failed_interruptible:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down_interruptible\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed_trylock\n"
+"__down_failed_trylock:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down_trylock\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __up_wakeup\n"
+"__up_wakeup:\n\t"
+ "pushl %eax\n\t"
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __up\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+ "popl %eax\n\t"
+ "ret"
+);
+
+/*
+ * rw spinlock fallbacks
+ */
+#if defined(CONFIG_SMP)
+asm(
+".text\n"
+".align 4\n"
+".globl __write_lock_failed\n"
+"__write_lock_failed:\n\t"
+ LOCK "addl $" RW_LOCK_BIAS_STR ",(%eax)\n"
+"1: rep; nop\n\t"
+ "cmpl $" RW_LOCK_BIAS_STR ",(%eax)\n\t"
+ "jne 1b\n\t"
+ LOCK "subl $" RW_LOCK_BIAS_STR ",(%eax)\n\t"
+ "jnz __write_lock_failed\n\t"
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __read_lock_failed\n"
+"__read_lock_failed:\n\t"
+ LOCK "incl (%eax)\n"
+"1: rep; nop\n\t"
+ "cmpl $1,(%eax)\n\t"
+ "js 1b\n\t"
+ LOCK "decl (%eax)\n\t"
+ "js __read_lock_failed\n\t"
+ "ret"
+);
+#endif
--- /dev/null
+/*
+ * linux/arch/i386/kernel/setup.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/tty.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/apm_bios.h>
+#ifdef CONFIG_BLK_DEV_RAM
+#include <linux/blk.h>
+#endif
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <asm/processor.h>
+#include <linux/console.h>
+#include <asm/mtrr.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/msr.h>
+#include <asm/desc.h>
+#include <asm/dma.h>
+#include <asm/mpspec.h>
+#include <asm/mmu_context.h>
+#include <asm/hypervisor.h>
+
+shared_info_t *HYPERVISOR_shared_info;
+
+unsigned long *phys_to_machine_mapping;
+
+/*
+ * Machine setup..
+ */
+
+char ignore_irq13; /* set if exception 16 works */
+struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
+
+unsigned long mmu_cr4_features;
+
+/*
+ * Bus types ..
+ */
+#ifdef CONFIG_EISA
+int EISA_bus;
+#endif
+int MCA_bus;
+
+/* for MCA, but anyone else can use it if they want */
+unsigned int machine_id;
+unsigned int machine_submodel_id;
+unsigned int BIOS_revision;
+unsigned int mca_pentium_flag;
+
+/* For PCI or other memory-mapped resources */
+unsigned long pci_mem_start = 0x10000000;
+
+/*
+ * Setup options
+ */
+struct drive_info_struct { char dummy[32]; } drive_info;
+struct screen_info screen_info;
+struct apm_info apm_info;
+struct sys_desc_table_struct {
+ unsigned short length;
+ unsigned char table[0];
+};
+
+unsigned char aux_device_present;
+
+extern int root_mountflags;
+extern char _text, _etext, _edata, _end;
+
+int enable_acpi_smp_table;
+
+/* Raw start-of-day parameters from the hypervisor. */
+union start_info_union start_info_union;
+
+#define COMMAND_LINE_SIZE 256
+static char command_line[COMMAND_LINE_SIZE];
+char saved_command_line[COMMAND_LINE_SIZE];
+
+static void __init parse_mem_cmdline (char ** cmdline_p)
+{
+ char c = ' ', *to = command_line, *from = saved_command_line;
+ int len = 0;
+
+ /* Save unparsed command line copy for /proc/cmdline */
+ memcpy(saved_command_line, start_info.cmd_line, COMMAND_LINE_SIZE);
+ saved_command_line[COMMAND_LINE_SIZE-1] = '\0';
+
+ for (;;) {
+ /*
+ * "mem=nopentium" disables the 4MB page tables.
+ * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
+ * to <mem>, overriding the bios size.
+ * "mem=XXX[KkmM]@XXX[KkmM]" defines a memory region from
+ * <start> to <start>+<mem>, overriding the bios size.
+ */
+ if (c == ' ' && !memcmp(from, "mem=", 4)) {
+ if (to != command_line)
+ to--;
+ if (!memcmp(from+4, "nopentium", 9)) {
+ from += 9+4;
+ } else if (!memcmp(from+4, "exactmap", 8)) {
+ from += 8+4;
+ } else {
+ (void)memparse(from+4, &from);
+ if (*from == '@')
+ (void)memparse(from+1, &from);
+ }
+ }
+
+ c = *(from++);
+ if (!c)
+ break;
+ if (COMMAND_LINE_SIZE <= ++len)
+ break;
+ *(to++) = c;
+ }
+ *to = '\0';
+ *cmdline_p = command_line;
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+ unsigned long start_pfn, max_pfn, max_low_pfn;
+ unsigned long bootmap_size;
+ unsigned long i;
+
+ extern void hypervisor_callback(void);
+ extern void failsafe_callback(void);
+
+ extern unsigned long cpu0_pte_quicklist[];
+ extern unsigned long cpu0_pgd_quicklist[];
+
+ HYPERVISOR_shared_info->event_address =
+ (unsigned long)hypervisor_callback;
+ HYPERVISOR_shared_info->failsafe_address =
+ (unsigned long)failsafe_callback;
+
+ boot_cpu_data.pgd_quick = cpu0_pgd_quicklist;
+ boot_cpu_data.pte_quick = cpu0_pte_quicklist;
+
+ ROOT_DEV = MKDEV(RAMDISK_MAJOR,0);
+ memset(&drive_info, 0, sizeof(drive_info));
+ memset(&screen_info, 0, sizeof(screen_info));
+ memset(&apm_info.bios, 0, sizeof(apm_info.bios));
+ aux_device_present = 0;
+#ifdef CONFIG_BLK_DEV_RAM
+ rd_image_start = 0;
+ rd_prompt = 0;
+ rd_doload = 0;
+#endif
+
+ root_mountflags &= ~MS_RDONLY;
+ init_mm.start_code = (unsigned long) &_text;
+ init_mm.end_code = (unsigned long) &_etext;
+ init_mm.end_data = (unsigned long) &_edata;
+ init_mm.brk = (unsigned long) &_end;
+
+ parse_mem_cmdline(cmdline_p);
+
+#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
+#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
+#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
+
+/*
+ * 128MB for vmalloc and initrd
+ */
+#define VMALLOC_RESERVE (unsigned long)(128 << 20)
+#define MAXMEM (unsigned long)(HYPERVISOR_VIRT_START-PAGE_OFFSET-VMALLOC_RESERVE)
+#define MAXMEM_PFN PFN_DOWN(MAXMEM)
+#define MAX_NONPAE_PFN (1 << 20)
+
+ /*
+ * partially used pages are not usable - thus
+ * we are rounding upwards:
+ */
+#ifdef CONFIG_BLK_DEV_INITRD
+ if ( start_info.mod_start )
+ start_pfn = PFN_UP(__pa(start_info.mod_start + start_info.mod_len));
+ else
+#endif
+ start_pfn = PFN_UP(__pa(&_end));
+ max_pfn = start_info.nr_pages;
+
+ /*
+ * Determine low and high memory ranges:
+ */
+ max_low_pfn = max_pfn;
+ if (max_low_pfn > MAXMEM_PFN) {
+ max_low_pfn = MAXMEM_PFN;
+#ifndef CONFIG_HIGHMEM
+ /* Maximum memory usable is what is directly addressable */
+ printk(KERN_WARNING "Warning only %ldMB will be used.\n",
+ MAXMEM>>20);
+ if (max_pfn > MAX_NONPAE_PFN)
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ else
+ printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+#else /* !CONFIG_HIGHMEM */
+#ifndef CONFIG_X86_PAE
+ if (max_pfn > MAX_NONPAE_PFN) {
+ max_pfn = MAX_NONPAE_PFN;
+ printk(KERN_WARNING "Warning only 4GB will be used.\n");
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ }
+#endif /* !CONFIG_X86_PAE */
+#endif /* !CONFIG_HIGHMEM */
+ }
+
+#ifdef CONFIG_HIGHMEM
+ highstart_pfn = highend_pfn = max_pfn;
+ if (max_pfn > MAXMEM_PFN) {
+ highstart_pfn = MAXMEM_PFN;
+ printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
+ pages_to_mb(highend_pfn - highstart_pfn));
+ }
+#endif
+
+ /*
+ * Initialize the boot-time allocator, and free up all RAM.
+ * Then reserve space for OS image, and the bootmem bitmap.
+ */
+ bootmap_size = init_bootmem(start_pfn, max_low_pfn);
+ free_bootmem(0, PFN_PHYS(max_low_pfn));
+ reserve_bootmem(0, PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1);
+
+ /* Now reserve space for the hypervisor-provided page tables. */
+ {
+ unsigned long *pgd = (unsigned long *)start_info.pt_base;
+ unsigned long pte;
+ int i;
+ reserve_bootmem(__pa(pgd), PAGE_SIZE);
+ for ( i = 0; i < (HYPERVISOR_VIRT_START>>22); i++ )
+ {
+ unsigned long pgde = *pgd++;
+ if ( !(pgde & 1) ) continue;
+ pte = machine_to_phys(pgde & PAGE_MASK);
+ reserve_bootmem(pte, PAGE_SIZE);
+ }
+ }
+ cur_pgd = init_mm.pgd = (pgd_t *)start_info.pt_base;
+
+ /* Now initialise the physical->machine mapping table. */
+ phys_to_machine_mapping = alloc_bootmem(max_pfn * sizeof(unsigned long));
+ for ( i = 0; i < max_pfn; i++ )
+ {
+ unsigned long pgde, *ppte;
+ unsigned long pfn = i + (PAGE_OFFSET >> PAGE_SHIFT);
+ pgde = *((unsigned long *)start_info.pt_base + (pfn >> 10));
+ ppte = (unsigned long *)machine_to_phys(pgde & PAGE_MASK) + (pfn&1023);
+ phys_to_machine_mapping[i] =
+ (*(unsigned long *)__va(ppte)) >> PAGE_SHIFT;
+ }
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (start_info.mod_start) {
+ if ((__pa(start_info.mod_start) + start_info.mod_len) <=
+ (max_low_pfn << PAGE_SHIFT)) {
+ initrd_start = start_info.mod_start;
+ initrd_end = initrd_start + start_info.mod_len;
+ initrd_below_start_ok = 1;
+ }
+ else {
+ printk(KERN_ERR "initrd extends beyond end of memory "
+ "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
+ __pa(start_info.mod_start) + start_info.mod_len,
+ max_low_pfn << PAGE_SHIFT);
+ initrd_start = 0;
+ }
+ }
+#endif
+
+ paging_init();
+}
+
+static int cachesize_override __initdata = -1;
+static int __init cachesize_setup(char *str)
+{
+ get_option (&str, &cachesize_override);
+ return 1;
+}
+__setup("cachesize=", cachesize_setup);
+
+
+static int __init get_model_name(struct cpuinfo_x86 *c)
+{
+ unsigned int *v;
+ char *p, *q;
+
+ if (cpuid_eax(0x80000000) < 0x80000004)
+ return 0;
+
+ v = (unsigned int *) c->x86_model_id;
+ cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
+ cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
+ cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
+ c->x86_model_id[48] = 0;
+
+ /* Intel chips right-justify this string for some dumb reason;
+ undo that brain damage */
+ p = q = &c->x86_model_id[0];
+ while ( *p == ' ' )
+ p++;
+ if ( p != q ) {
+ while ( *p )
+ *q++ = *p++;
+ while ( q <= &c->x86_model_id[48] )
+ *q++ = '\0'; /* Zero-pad the rest */
+ }
+
+ return 1;
+}
+
+
+static void __init display_cacheinfo(struct cpuinfo_x86 *c)
+{
+ unsigned int n, dummy, ecx, edx, l2size;
+
+ n = cpuid_eax(0x80000000);
+
+ if (n >= 0x80000005) {
+ cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
+ printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
+ edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+ c->x86_cache_size=(ecx>>24)+(edx>>24);
+ }
+
+ if (n < 0x80000006) /* Some chips just has a large L1. */
+ return;
+
+ ecx = cpuid_ecx(0x80000006);
+ l2size = ecx >> 16;
+
+ /* AMD errata T13 (order #21922) */
+ if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) {
+ if (c->x86_model == 3 && c->x86_mask == 0) /* Duron Rev A0 */
+ l2size = 64;
+ if (c->x86_model == 4 &&
+ (c->x86_mask==0 || c->x86_mask==1)) /* Tbird rev A1/A2 */
+ l2size = 256;
+ }
+
+ /* Intel PIII Tualatin. This comes in two flavours.
+ * One has 256kb of cache, the other 512. We have no way
+ * to determine which, so we use a boottime override
+ * for the 512kb model, and assume 256 otherwise.
+ */
+ if ((c->x86_vendor == X86_VENDOR_INTEL) && (c->x86 == 6) &&
+ (c->x86_model == 11) && (l2size == 0))
+ l2size = 256;
+
+ /* VIA C3 CPUs (670-68F) need further shifting. */
+ if (c->x86_vendor == X86_VENDOR_CENTAUR && (c->x86 == 6) &&
+ ((c->x86_model == 7) || (c->x86_model == 8))) {
+ l2size = l2size >> 8;
+ }
+
+ /* Allow user to override all this if necessary. */
+ if (cachesize_override != -1)
+ l2size = cachesize_override;
+
+ if ( l2size == 0 )
+ return; /* Again, no L2 cache is possible */
+
+ c->x86_cache_size = l2size;
+
+ printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
+ l2size, ecx & 0xFF);
+}
+
+
+static int __init init_amd(struct cpuinfo_x86 *c)
+{
+ int r;
+
+ /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+ clear_bit(0*32+31, &c->x86_capability);
+
+ r = get_model_name(c);
+
+ switch(c->x86)
+ {
+ case 6: /* An Athlon/Duron. We can trust the BIOS probably */
+ break;
+ default:
+ panic("Unsupported AMD processor\n");
+ }
+
+ display_cacheinfo(c);
+ return r;
+}
+
+
+static void __init init_intel(struct cpuinfo_x86 *c)
+{
+ char *p = NULL;
+ unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */
+
+ if (c->cpuid_level > 1) {
+ /* supports eax=2 call */
+ int i, j, n;
+ int regs[4];
+ unsigned char *dp = (unsigned char *)regs;
+
+ /* Number of times to iterate */
+ n = cpuid_eax(2) & 0xFF;
+
+ for ( i = 0 ; i < n ; i++ ) {
+ cpuid(2, ®s[0], ®s[1], ®s[2], ®s[3]);
+
+ /* If bit 31 is set, this is an unknown format */
+ for ( j = 0 ; j < 3 ; j++ ) {
+ if ( regs[j] < 0 ) regs[j] = 0;
+ }
+
+ /* Byte 0 is level count, not a descriptor */
+ for ( j = 1 ; j < 16 ; j++ ) {
+ unsigned char des = dp[j];
+ unsigned char dl, dh;
+ unsigned int cs;
+
+ dh = des >> 4;
+ dl = des & 0x0F;
+
+ /* Black magic... */
+
+ switch ( dh )
+ {
+ case 0:
+ switch ( dl ) {
+ case 6:
+ /* L1 I cache */
+ l1i += 8;
+ break;
+ case 8:
+ /* L1 I cache */
+ l1i += 16;
+ break;
+ case 10:
+ /* L1 D cache */
+ l1d += 8;
+ break;
+ case 12:
+ /* L1 D cache */
+ l1d += 16;
+ break;
+ default:;
+ /* TLB, or unknown */
+ }
+ break;
+ case 2:
+ if ( dl ) {
+ /* L3 cache */
+ cs = (dl-1) << 9;
+ l3 += cs;
+ }
+ break;
+ case 4:
+ if ( c->x86 > 6 && dl ) {
+ /* P4 family */
+ /* L3 cache */
+ cs = 128 << (dl-1);
+ l3 += cs;
+ break;
+ }
+ /* else same as 8 - fall through */
+ case 8:
+ if ( dl ) {
+ /* L2 cache */
+ cs = 128 << (dl-1);
+ l2 += cs;
+ }
+ break;
+ case 6:
+ if (dl > 5) {
+ /* L1 D cache */
+ cs = 8<<(dl-6);
+ l1d += cs;
+ }
+ break;
+ case 7:
+ if ( dl >= 8 )
+ {
+ /* L2 cache */
+ cs = 64<<(dl-8);
+ l2 += cs;
+ } else {
+ /* L0 I cache, count as L1 */
+ cs = dl ? (16 << (dl-1)) : 12;
+ l1i += cs;
+ }
+ break;
+ default:
+ /* TLB, or something else we don't know about */
+ break;
+ }
+ }
+ }
+ if ( l1i || l1d )
+ printk(KERN_INFO "CPU: L1 I cache: %dK, L1 D cache: %dK\n",
+ l1i, l1d);
+ if ( l2 )
+ printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);
+ if ( l3 )
+ printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);
+
+ /*
+ * This assumes the L3 cache is shared; it typically lives in
+ * the northbridge. The L1 caches are included by the L2
+ * cache, and so should not be included for the purpose of
+ * SMP switching weights.
+ */
+ c->x86_cache_size = l2 ? l2 : (l1i+l1d);
+ }
+
+ /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it */
+ if ( c->x86 == 6 && c->x86_model < 3 && c->x86_mask < 3 )
+ clear_bit(X86_FEATURE_SEP, &c->x86_capability);
+
+ /* Names for the Pentium II/Celeron processors
+ detectable only by also checking the cache size.
+ Dixon is NOT a Celeron. */
+ if (c->x86 == 6) {
+ switch (c->x86_model) {
+ case 5:
+ if (l2 == 0)
+ p = "Celeron (Covington)";
+ if (l2 == 256)
+ p = "Mobile Pentium II (Dixon)";
+ break;
+
+ case 6:
+ if (l2 == 128)
+ p = "Celeron (Mendocino)";
+ break;
+
+ case 8:
+ if (l2 == 128)
+ p = "Celeron (Coppermine)";
+ break;
+ }
+ }
+
+ if ( p )
+ strcpy(c->x86_model_id, p);
+}
+
+void __init get_cpu_vendor(struct cpuinfo_x86 *c)
+{
+ char *v = c->x86_vendor_id;
+
+ if (!strcmp(v, "GenuineIntel"))
+ c->x86_vendor = X86_VENDOR_INTEL;
+ else if (!strcmp(v, "AuthenticAMD"))
+ c->x86_vendor = X86_VENDOR_AMD;
+ else
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+}
+
+struct cpu_model_info {
+ int vendor;
+ int family;
+ char *model_names[16];
+};
+
+/* Naming convention should be: <Name> [(<Codename>)] */
+/* This table only is used unless init_<vendor>() below doesn't set it; */
+/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */
+static struct cpu_model_info cpu_models[] __initdata = {
+ { X86_VENDOR_INTEL, 6,
+ { "Pentium Pro A-step", "Pentium Pro", NULL, "Pentium II (Klamath)",
+ NULL, "Pentium II (Deschutes)", "Mobile Pentium II",
+ "Pentium III (Katmai)", "Pentium III (Coppermine)", NULL,
+ "Pentium III (Cascades)", NULL, NULL, NULL, NULL }},
+ { X86_VENDOR_AMD, 6, /* Is this this really necessary?? */
+ { "Athlon", "Athlon",
+ "Athlon", NULL, "Athlon", NULL,
+ NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL }}
+};
+
+/* Look up CPU names by table lookup. */
+static char __init *table_lookup_model(struct cpuinfo_x86 *c)
+{
+ struct cpu_model_info *info = cpu_models;
+ int i;
+
+ if ( c->x86_model >= 16 )
+ return NULL; /* Range check */
+
+ for ( i = 0 ; i < sizeof(cpu_models)/sizeof(struct cpu_model_info) ; i++ ) {
+ if ( info->vendor == c->x86_vendor &&
+ info->family == c->x86 ) {
+ return info->model_names[c->x86_model];
+ }
+ info++;
+ }
+ return NULL; /* Not found */
+}
+
+
+
+/* Standard macro to see if a specific flag is changeable */
+static inline int flag_is_changeable_p(u32 flag)
+{
+ u32 f1, f2;
+
+ asm("pushfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "movl %0,%1\n\t"
+ "xorl %2,%0\n\t"
+ "pushl %0\n\t"
+ "popfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "popfl\n\t"
+ : "=&r" (f1), "=&r" (f2)
+ : "ir" (flag));
+
+ return ((f1^f2) & flag) != 0;
+}
+
+
+/* Probe for the CPUID instruction */
+static int __init have_cpuid_p(void)
+{
+ return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+
+
+
+/*
+ * This does the hard work of actually picking apart the CPU stuff...
+ */
+void __init identify_cpu(struct cpuinfo_x86 *c)
+{
+ int junk, i;
+ u32 xlvl, tfms;
+
+ c->loops_per_jiffy = loops_per_jiffy;
+ c->x86_cache_size = -1;
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+ c->cpuid_level = -1; /* CPUID not detected */
+ c->x86_model = c->x86_mask = 0; /* So far unknown... */
+ c->x86_vendor_id[0] = '\0'; /* Unset */
+ c->x86_model_id[0] = '\0'; /* Unset */
+ memset(&c->x86_capability, 0, sizeof c->x86_capability);
+ c->hard_math = 1;
+
+ if ( !have_cpuid_p() ) {
+ panic("Processor must support CPUID\n");
+ } else {
+ /* CPU does have CPUID */
+
+ /* Get vendor name */
+ cpuid(0x00000000, &c->cpuid_level,
+ (int *)&c->x86_vendor_id[0],
+ (int *)&c->x86_vendor_id[8],
+ (int *)&c->x86_vendor_id[4]);
+
+ get_cpu_vendor(c);
+ /* Initialize the standard set of capabilities */
+ /* Note that the vendor-specific code below might override */
+
+ /* Intel-defined flags: level 0x00000001 */
+ if ( c->cpuid_level >= 0x00000001 ) {
+ cpuid(0x00000001, &tfms, &junk, &junk,
+ &c->x86_capability[0]);
+ c->x86 = (tfms >> 8) & 15;
+ c->x86_model = (tfms >> 4) & 15;
+ c->x86_mask = tfms & 15;
+ } else {
+ /* Have CPUID level 0 only - unheard of */
+ c->x86 = 4;
+ }
+
+ /* AMD-defined flags: level 0x80000001 */
+ xlvl = cpuid_eax(0x80000000);
+ if ( (xlvl & 0xffff0000) == 0x80000000 ) {
+ if ( xlvl >= 0x80000001 )
+ c->x86_capability[1] = cpuid_edx(0x80000001);
+ if ( xlvl >= 0x80000004 )
+ get_model_name(c); /* Default name */
+ }
+
+ /* Transmeta-defined flags: level 0x80860001 */
+ xlvl = cpuid_eax(0x80860000);
+ if ( (xlvl & 0xffff0000) == 0x80860000 ) {
+ if ( xlvl >= 0x80860001 )
+ c->x86_capability[2] = cpuid_edx(0x80860001);
+ }
+ }
+
+ printk(KERN_DEBUG "CPU: Before vendor init, caps: %08x %08x %08x, vendor = %d\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_vendor);
+
+ /*
+ * Vendor-specific initialization. In this section we
+ * canonicalize the feature flags, meaning if there are
+ * features a certain CPU supports which CPUID doesn't
+ * tell us, CPUID claiming incorrect flags, or other bugs,
+ * we handle them here.
+ *
+ * At the end of this section, c->x86_capability better
+ * indicate the features this CPU genuinely supports!
+ */
+ switch ( c->x86_vendor ) {
+ case X86_VENDOR_AMD:
+ init_amd(c);
+ break;
+
+ case X86_VENDOR_INTEL:
+ init_intel(c);
+ break;
+
+ default:
+ panic("Unsupported CPU vendor\n");
+ }
+
+ printk(KERN_DEBUG "CPU: After vendor init, caps: %08x %08x %08x %08x\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_capability[3]);
+
+
+ /* If the model name is still unset, do table lookup. */
+ if ( !c->x86_model_id[0] ) {
+ char *p;
+ p = table_lookup_model(c);
+ if ( p )
+ strcpy(c->x86_model_id, p);
+ else
+ /* Last resort... */
+ sprintf(c->x86_model_id, "%02x/%02x",
+ c->x86_vendor, c->x86_model);
+ }
+
+ /* Now the feature flags better reflect actual CPU features! */
+
+ printk(KERN_DEBUG "CPU: After generic, caps: %08x %08x %08x %08x\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_capability[3]);
+
+ /*
+ * On SMP, boot_cpu_data holds the common feature set between
+ * all CPUs; so make sure that we indicate which features are
+ * common between the CPUs. The first time this routine gets
+ * executed, c == &boot_cpu_data.
+ */
+ if ( c != &boot_cpu_data ) {
+ /* AND the already accumulated flags with these */
+ for ( i = 0 ; i < NCAPINTS ; i++ )
+ boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+ }
+
+ printk(KERN_DEBUG "CPU: Common caps: %08x %08x %08x %08x\n",
+ boot_cpu_data.x86_capability[0],
+ boot_cpu_data.x86_capability[1],
+ boot_cpu_data.x86_capability[2],
+ boot_cpu_data.x86_capability[3]);
+}
+
+
+/* These need to match <asm/processor.h> */
+static char *cpu_vendor_names[] __initdata = {
+ "Intel", "Cyrix", "AMD", "UMC", "NexGen", "Centaur", "Rise", "Transmeta" };
+
+
+void __init print_cpu_info(struct cpuinfo_x86 *c)
+{
+ char *vendor = NULL;
+
+ if (c->x86_vendor < sizeof(cpu_vendor_names)/sizeof(char *))
+ vendor = cpu_vendor_names[c->x86_vendor];
+ else if (c->cpuid_level >= 0)
+ vendor = c->x86_vendor_id;
+
+ if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
+ printk("%s ", vendor);
+
+ if (!c->x86_model_id[0])
+ printk("%d86", c->x86);
+ else
+ printk("%s", c->x86_model_id);
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ printk(" stepping %02x\n", c->x86_mask);
+ else
+ printk("\n");
+}
+
+/*
+ * Get CPU information for use by the procfs.
+ */
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+ /*
+ * These flag bits must match the definitions in <asm/cpufeature.h>.
+ * NULL means this bit is undefined or reserved; either way it doesn't
+ * have meaning as far as Linux is concerned. Note that it's important
+ * to realize there is a difference between this table and CPUID -- if
+ * applications want to get the raw CPUID data, they should access
+ * /dev/cpu/<cpu_nr>/cpuid instead.
+ */
+ static char *x86_cap_flags[] = {
+ /* Intel-defined */
+ "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
+ "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
+ "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
+ "fxsr", "sse", "sse2", "ss", NULL, "tm", "ia64", NULL,
+
+ /* AMD-defined */
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, "mmxext", NULL,
+ NULL, NULL, NULL, NULL, NULL, "lm", "3dnowext", "3dnow",
+
+ /* Transmeta-defined */
+ "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* Other (Linux-defined) */
+ "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ };
+ struct cpuinfo_x86 *c = v;
+ int i, n = c - cpu_data;
+ int fpu_exception;
+
+#ifdef CONFIG_SMP
+ if (!(cpu_online_map & (1<<n)))
+ return 0;
+#endif
+ seq_printf(m, "processor\t: %d\n"
+ "vendor_id\t: %s\n"
+ "cpu family\t: %d\n"
+ "model\t\t: %d\n"
+ "model name\t: %s\n",
+ n,
+ c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown",
+ c->x86,
+ c->x86_model,
+ c->x86_model_id[0] ? c->x86_model_id : "unknown");
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ seq_printf(m, "stepping\t: %d\n", c->x86_mask);
+ else
+ seq_printf(m, "stepping\t: unknown\n");
+
+ if ( test_bit(X86_FEATURE_TSC, &c->x86_capability) ) {
+ seq_printf(m, "cpu MHz\t\t: %lu.%03lu\n",
+ cpu_khz / 1000, (cpu_khz % 1000));
+ }
+
+ /* Cache size */
+ if (c->x86_cache_size >= 0)
+ seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
+
+ /* We use exception 16 if we have hardware math and we've either seen it or the CPU claims it is internal */
+ fpu_exception = c->hard_math && (ignore_irq13 || cpu_has_fpu);
+ seq_printf(m, "fdiv_bug\t: %s\n"
+ "hlt_bug\t\t: %s\n"
+ "f00f_bug\t: %s\n"
+ "coma_bug\t: %s\n"
+ "fpu\t\t: %s\n"
+ "fpu_exception\t: %s\n"
+ "cpuid level\t: %d\n"
+ "wp\t\t: %s\n"
+ "flags\t\t:",
+ c->fdiv_bug ? "yes" : "no",
+ c->hlt_works_ok ? "no" : "yes",
+ c->f00f_bug ? "yes" : "no",
+ c->coma_bug ? "yes" : "no",
+ c->hard_math ? "yes" : "no",
+ fpu_exception ? "yes" : "no",
+ c->cpuid_level,
+ c->wp_works_ok ? "yes" : "no");
+
+ for ( i = 0 ; i < 32*NCAPINTS ; i++ )
+ if ( test_bit(i, &c->x86_capability) &&
+ x86_cap_flags[i] != NULL )
+ seq_printf(m, " %s", x86_cap_flags[i]);
+
+ seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n",
+ c->loops_per_jiffy/(500000/HZ),
+ (c->loops_per_jiffy/(5000/HZ)) % 100);
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ return *pos < NR_CPUS ? cpu_data + *pos : NULL;
+}
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return c_start(m, pos);
+}
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+struct seq_operations cpuinfo_op = {
+ start: c_start,
+ next: c_next,
+ stop: c_stop,
+ show: show_cpuinfo,
+};
+
+unsigned long cpu_initialized __initdata = 0;
+
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ */
+void __init cpu_init (void)
+{
+ int nr = smp_processor_id();
+
+ if (test_and_set_bit(nr, &cpu_initialized)) {
+ printk(KERN_WARNING "CPU#%d already initialized!\n", nr);
+ for (;;) __sti();
+ }
+ printk(KERN_INFO "Initializing CPU#%d\n", nr);
+
+ /*
+ * set up and load the per-CPU TSS and LDT
+ */
+ atomic_inc(&init_mm.mm_count);
+ current->active_mm = &init_mm;
+ if(current->mm)
+ BUG();
+ enter_lazy_tlb(&init_mm, current, nr);
+
+ HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, current->thread.esp0, 0);
+
+ /* Force FPU initialization. */
+ current->flags &= ~PF_USEDFPU;
+ current->used_math = 0;
+ stts();
+}
+
+
+/******************************************************************************
+ * Time-to-die callback handling.
+ */
+
+static void time_to_die(int irq, void *unused, struct pt_regs *regs)
+{
+ extern void ctrl_alt_del(void);
+ ctrl_alt_del();
+}
+
+static int __init setup_death_event(void)
+{
+ (void)request_irq(_EVENT_DIE, time_to_die, 0, "die", NULL);
+ return 0;
+}
+
+__initcall(setup_death_event);
--- /dev/null
+/*
+ * linux/arch/i386/kernel/signal.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/tty.h>
+#include <linux/personality.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+
+#define DEBUG_SIG 0
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+int FASTCALL(do_signal(struct pt_regs *regs, sigset_t *oldset));
+
+int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from)
+{
+ if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
+ return -EFAULT;
+ if (from->si_code < 0)
+ return __copy_to_user(to, from, sizeof(siginfo_t));
+ else {
+ int err;
+
+ /* If you change siginfo_t structure, please be sure
+ this code is fixed accordingly.
+ It should never copy any pad contained in the structure
+ to avoid security leaks, but must copy the generic
+ 3 ints plus the relevant union member. */
+ err = __put_user(from->si_signo, &to->si_signo);
+ err |= __put_user(from->si_errno, &to->si_errno);
+ err |= __put_user((short)from->si_code, &to->si_code);
+ /* First 32bits of unions are always present. */
+ err |= __put_user(from->si_pid, &to->si_pid);
+ switch (from->si_code >> 16) {
+ case __SI_FAULT >> 16:
+ break;
+ case __SI_CHLD >> 16:
+ err |= __put_user(from->si_utime, &to->si_utime);
+ err |= __put_user(from->si_stime, &to->si_stime);
+ err |= __put_user(from->si_status, &to->si_status);
+ default:
+ err |= __put_user(from->si_uid, &to->si_uid);
+ break;
+ /* case __SI_RT: This is not generated by the kernel as of now. */
+ }
+ return err;
+ }
+}
+
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+asmlinkage int
+sys_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+ struct pt_regs * regs = (struct pt_regs *) &history0;
+ sigset_t saveset;
+
+ mask &= _BLOCKABLE;
+ spin_lock_irq(¤t->sigmask_lock);
+ saveset = current->blocked;
+ siginitset(¤t->blocked, mask);
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize)
+{
+ struct pt_regs * regs = (struct pt_regs *) &unewset;
+ sigset_t saveset, newset;
+
+ /* XXX: Don't preclude handling different sized sigset_t's. */
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&newset, unewset, sizeof(newset)))
+ return -EFAULT;
+ sigdelsetmask(&newset, ~_BLOCKABLE);
+
+ spin_lock_irq(¤t->sigmask_lock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_sigaction(int sig, const struct old_sigaction *act,
+ struct old_sigaction *oact)
+{
+ struct k_sigaction new_ka, old_ka;
+ int ret;
+
+ if (act) {
+ old_sigset_t mask;
+ if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
+ __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+ __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ return -EFAULT;
+ __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ __get_user(mask, &act->sa_mask);
+ siginitset(&new_ka.sa.sa_mask, mask);
+ }
+
+ ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+ if (!ret && oact) {
+ if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
+ __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+ __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ return -EFAULT;
+ __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ }
+
+ return ret;
+}
+
+asmlinkage int
+sys_sigaltstack(const stack_t *uss, stack_t *uoss)
+{
+ struct pt_regs *regs = (struct pt_regs *) &uss;
+ return do_sigaltstack(uss, uoss, regs->esp);
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+struct sigframe
+{
+ char *pretcode;
+ int sig;
+ struct sigcontext sc;
+ struct _fpstate fpstate;
+ unsigned long extramask[_NSIG_WORDS-1];
+ char retcode[8];
+};
+
+struct rt_sigframe
+{
+ char *pretcode;
+ int sig;
+ struct siginfo *pinfo;
+ void *puc;
+ struct siginfo info;
+ struct ucontext uc;
+ struct _fpstate fpstate;
+ char retcode[8];
+};
+
+static int
+restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc, int *peax)
+{
+ unsigned int err = 0;
+
+#define COPY(x) err |= __get_user(regs->x, &sc->x)
+
+#define COPY_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp; }
+
+#define COPY_SEG_STRICT(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp|3; }
+
+#define GET_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ loadsegment(seg,tmp); }
+
+ GET_SEG(gs);
+ GET_SEG(fs);
+ COPY_SEG(es);
+ COPY_SEG(ds);
+ COPY(edi);
+ COPY(esi);
+ COPY(ebp);
+ COPY(esp);
+ COPY(ebx);
+ COPY(edx);
+ COPY(ecx);
+ COPY(eip);
+ COPY_SEG_STRICT(cs);
+ COPY_SEG_STRICT(ss);
+
+ {
+ unsigned int tmpflags;
+ err |= __get_user(tmpflags, &sc->eflags);
+ regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5);
+ regs->orig_eax = -1; /* disable syscall checks */
+ }
+
+ {
+ struct _fpstate * buf;
+ err |= __get_user(buf, &sc->fpstate);
+ if (buf) {
+ if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
+ goto badframe;
+ err |= restore_i387(buf);
+ }
+ }
+
+ err |= __get_user(*peax, &sc->eax);
+ return err;
+
+badframe:
+ return 1;
+}
+
+asmlinkage int sys_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct sigframe *frame = (struct sigframe *)(regs->esp - 8);
+ sigset_t set;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__get_user(set.sig[0], &frame->sc.oldmask)
+ || (_NSIG_WORDS > 1
+ && __copy_from_user(&set.sig[1], &frame->extramask,
+ sizeof(frame->extramask))))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (restore_sigcontext(regs, &frame->sc, &eax))
+ goto badframe;
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct rt_sigframe *frame = (struct rt_sigframe *)(regs->esp - 4);
+ sigset_t set;
+ stack_t st;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax))
+ goto badframe;
+
+ if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
+ goto badframe;
+ /* It is more difficult to avoid calling this function than to
+ call it and ignore errors. */
+ do_sigaltstack(&st, NULL, regs->esp);
+
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+/*
+ * Set up a signal frame.
+ */
+
+static int
+setup_sigcontext(struct sigcontext *sc, struct _fpstate *fpstate,
+ struct pt_regs *regs, unsigned long mask)
+{
+ int tmp, err = 0;
+
+ tmp = 0;
+ __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int *)&sc->gs);
+ __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int *)&sc->fs);
+
+ err |= __put_user(regs->xes, (unsigned int *)&sc->es);
+ err |= __put_user(regs->xds, (unsigned int *)&sc->ds);
+ err |= __put_user(regs->edi, &sc->edi);
+ err |= __put_user(regs->esi, &sc->esi);
+ err |= __put_user(regs->ebp, &sc->ebp);
+ err |= __put_user(regs->esp, &sc->esp);
+ err |= __put_user(regs->ebx, &sc->ebx);
+ err |= __put_user(regs->edx, &sc->edx);
+ err |= __put_user(regs->ecx, &sc->ecx);
+ err |= __put_user(regs->eax, &sc->eax);
+ err |= __put_user(current->thread.trap_no, &sc->trapno);
+ err |= __put_user(current->thread.error_code, &sc->err);
+ err |= __put_user(regs->eip, &sc->eip);
+ err |= __put_user(regs->xcs, (unsigned int *)&sc->cs);
+ err |= __put_user(regs->eflags, &sc->eflags);
+ err |= __put_user(regs->esp, &sc->esp_at_signal);
+ err |= __put_user(regs->xss, (unsigned int *)&sc->ss);
+
+ tmp = save_i387(fpstate);
+ if (tmp < 0)
+ err = 1;
+ else
+ err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
+
+ /* non-iBCS2 extensions.. */
+ err |= __put_user(mask, &sc->oldmask);
+ err |= __put_user(current->thread.cr2, &sc->cr2);
+
+ return err;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
+{
+ unsigned long esp;
+
+ /* Default to using normal stack */
+ esp = regs->esp;
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ if (ka->sa.sa_flags & SA_ONSTACK) {
+ if (sas_ss_flags(esp) == 0)
+ esp = current->sas_ss_sp + current->sas_ss_size;
+ }
+
+ /* This is the legacy signal stack switching. */
+ else if ((regs->xss & 0xffff) != __USER_DS &&
+ !(ka->sa.sa_flags & SA_RESTORER) &&
+ ka->sa.sa_restorer) {
+ esp = (unsigned long) ka->sa.sa_restorer;
+ }
+
+ return (void *)((esp - frame_size) & -8ul);
+}
+
+static void setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct sigframe *frame;
+ int err = 0;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ err |= __put_user((current->exec_domain
+ && current->exec_domain->signal_invmap
+ && sig < 32
+ ? current->exec_domain->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ if (err)
+ goto give_sigsegv;
+
+ err |= setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+ if (err)
+ goto give_sigsegv;
+
+ if (_NSIG_WORDS > 1) {
+ err |= __copy_to_user(frame->extramask, &set->sig[1],
+ sizeof(frame->extramask));
+ }
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ err |= __put_user(frame->retcode, &frame->pretcode);
+ /* This is popl %eax ; movl $,%eax ; int $0x80 */
+ err |= __put_user(0xb858, (short *)(frame->retcode+0));
+ err |= __put_user(__NR_sigreturn, (int *)(frame->retcode+2));
+ err |= __put_user(0x80cd, (short *)(frame->retcode+6));
+ }
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+ regs->eflags &= ~TF_MASK;
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ if (sig == SIGSEGV)
+ ka->sa.sa_handler = SIG_DFL;
+ force_sig(SIGSEGV, current);
+}
+
+static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct rt_sigframe *frame;
+ int err = 0;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ err |= __put_user((current->exec_domain
+ && current->exec_domain->signal_invmap
+ && sig < 32
+ ? current->exec_domain->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ err |= __put_user(&frame->info, &frame->pinfo);
+ err |= __put_user(&frame->uc, &frame->puc);
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err)
+ goto give_sigsegv;
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(regs->esp),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ err |= __put_user(frame->retcode, &frame->pretcode);
+ /* This is movl $,%eax ; int $0x80 */
+ err |= __put_user(0xb8, (char *)(frame->retcode+0));
+ err |= __put_user(__NR_rt_sigreturn, (int *)(frame->retcode+1));
+ err |= __put_user(0x80cd, (short *)(frame->retcode+5));
+ }
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+ regs->eflags &= ~TF_MASK;
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ if (sig == SIGSEGV)
+ ka->sa.sa_handler = SIG_DFL;
+ force_sig(SIGSEGV, current);
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+
+static void
+handle_signal(unsigned long sig, struct k_sigaction *ka,
+ siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
+{
+ /* Are we from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* If so, check system call restarting.. */
+ switch (regs->eax) {
+ case -ERESTARTNOHAND:
+ regs->eax = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ka->sa.sa_flags & SA_RESTART)) {
+ regs->eax = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+
+ /* Set up the stack frame */
+ if (ka->sa.sa_flags & SA_SIGINFO)
+ setup_rt_frame(sig, ka, info, oldset, regs);
+ else
+ setup_frame(sig, ka, oldset, regs);
+
+ if (ka->sa.sa_flags & SA_ONESHOT)
+ ka->sa.sa_handler = SIG_DFL;
+
+ if (!(ka->sa.sa_flags & SA_NODEFER)) {
+ spin_lock_irq(¤t->sigmask_lock);
+ sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
+ sigaddset(¤t->blocked,sig);
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+ }
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int do_signal(struct pt_regs *regs, sigset_t *oldset)
+{
+ siginfo_t info;
+ struct k_sigaction *ka;
+
+ /*
+ * We want the common case to go fast, which
+ * is why we may in certain cases get here from
+ * kernel mode. Just return without doing anything
+ * if so.
+ */
+ if ((regs->xcs & 2) != 2)
+ return 1;
+
+ if (!oldset)
+ oldset = ¤t->blocked;
+
+ for (;;) {
+ unsigned long signr;
+
+ spin_lock_irq(¤t->sigmask_lock);
+ signr = dequeue_signal(¤t->blocked, &info);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (!signr)
+ break;
+
+ if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
+ /* Let the debugger run. */
+ current->exit_code = signr;
+ current->state = TASK_STOPPED;
+ notify_parent(current, SIGCHLD);
+ schedule();
+
+ /* We're back. Did the debugger cancel the sig? */
+ if (!(signr = current->exit_code))
+ continue;
+ current->exit_code = 0;
+
+ /* The debugger continued. Ignore SIGSTOP. */
+ if (signr == SIGSTOP)
+ continue;
+
+ /* Update the siginfo structure. Is this good? */
+ if (signr != info.si_signo) {
+ info.si_signo = signr;
+ info.si_errno = 0;
+ info.si_code = SI_USER;
+ info.si_pid = current->p_pptr->pid;
+ info.si_uid = current->p_pptr->uid;
+ }
+
+ /* If the (new) signal is now blocked, requeue it. */
+ if (sigismember(¤t->blocked, signr)) {
+ send_sig_info(signr, &info, current);
+ continue;
+ }
+ }
+
+ ka = ¤t->sig->action[signr-1];
+ if (ka->sa.sa_handler == SIG_IGN) {
+ if (signr != SIGCHLD)
+ continue;
+ /* Check for SIGCHLD: it's special. */
+ while (sys_wait4(-1, NULL, WNOHANG, NULL) > 0)
+ /* nothing */;
+ continue;
+ }
+
+ if (ka->sa.sa_handler == SIG_DFL) {
+ int exit_code = signr;
+
+ /* Init gets no signals it doesn't want. */
+ if (current->pid == 1)
+ continue;
+
+ switch (signr) {
+ case SIGCONT: case SIGCHLD: case SIGWINCH: case SIGURG:
+ continue;
+
+ case SIGTSTP: case SIGTTIN: case SIGTTOU:
+ if (is_orphaned_pgrp(current->pgrp))
+ continue;
+ /* FALLTHRU */
+
+ case SIGSTOP: {
+ struct signal_struct *sig;
+ current->state = TASK_STOPPED;
+ current->exit_code = signr;
+ sig = current->p_pptr->sig;
+ if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
+ notify_parent(current, SIGCHLD);
+ schedule();
+ continue;
+ }
+
+ case SIGQUIT: case SIGILL: case SIGTRAP:
+ case SIGABRT: case SIGFPE: case SIGSEGV:
+ case SIGBUS: case SIGSYS: case SIGXCPU: case SIGXFSZ:
+ if (do_coredump(signr, regs))
+ exit_code |= 0x80;
+ /* FALLTHRU */
+
+ default:
+ sig_exit(signr, exit_code, &info);
+ /* NOTREACHED */
+ }
+ }
+
+ /* Reenable any watchpoints before delivering the
+ * signal to user space. The processor register will
+ * have been cleared if the watchpoint triggered
+ * inside the kernel.
+ */
+ if ( current->thread.debugreg[7] != 0 )
+ HYPERVISOR_set_debugreg(7, current->thread.debugreg[7]);
+
+ /* Whee! Actually deliver the signal. */
+ handle_signal(signr, ka, &info, oldset, regs);
+ return 1;
+ }
+
+ /* Did we come from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* Restart the system call - no handlers present */
+ if (regs->eax == -ERESTARTNOHAND ||
+ regs->eax == -ERESTARTSYS ||
+ regs->eax == -ERESTARTNOINTR) {
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+ return 0;
+}
--- /dev/null
+/*
+ * linux/arch/i386/kernel/sys_i386.c
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/i386
+ * platform.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+
+#include <asm/uaccess.h>
+#include <asm/ipc.h>
+
+/*
+ * sys_pipe() is the normal C calling standard for creating
+ * a pipe. It's not the way Unix traditionally does this, though.
+ */
+asmlinkage int sys_pipe(unsigned long * fildes)
+{
+ int fd[2];
+ int error;
+
+ error = do_pipe(fd);
+ if (!error) {
+ if (copy_to_user(fildes, fd, 2*sizeof(int)))
+ error = -EFAULT;
+ }
+ return error;
+}
+
+/* common code for old and new mmaps */
+static inline long do_mmap2(
+ unsigned long addr, unsigned long len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ int error = -EBADF;
+ struct file * file = NULL;
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+ if (!(flags & MAP_ANONYMOUS)) {
+ file = fget(fd);
+ if (!file)
+ goto out;
+ }
+
+ down_write(¤t->mm->mmap_sem);
+ error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(¤t->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+out:
+ return error;
+}
+
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ return do_mmap2(addr, len, prot, flags, fd, pgoff);
+}
+
+/*
+ * Perform the select(nd, in, out, ex, tv) and mmap() system
+ * calls. Linux/i386 didn't use to be able to handle more than
+ * 4 system call parameters, so these system calls used a memory
+ * block for parameter passing..
+ */
+
+struct mmap_arg_struct {
+ unsigned long addr;
+ unsigned long len;
+ unsigned long prot;
+ unsigned long flags;
+ unsigned long fd;
+ unsigned long offset;
+};
+
+asmlinkage int old_mmap(struct mmap_arg_struct *arg)
+{
+ struct mmap_arg_struct a;
+ int err = -EFAULT;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ goto out;
+
+ err = -EINVAL;
+ if (a.offset & ~PAGE_MASK)
+ goto out;
+
+ err = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT);
+out:
+ return err;
+}
+
+
+extern asmlinkage int sys_select(int, fd_set *, fd_set *, fd_set *, struct timeval *);
+
+struct sel_arg_struct {
+ unsigned long n;
+ fd_set *inp, *outp, *exp;
+ struct timeval *tvp;
+};
+
+asmlinkage int old_select(struct sel_arg_struct *arg)
+{
+ struct sel_arg_struct a;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ return -EFAULT;
+ /* sys_select() does the appropriate kernel locking */
+ return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
+}
+
+/*
+ * sys_ipc() is the de-multiplexer for the SysV IPC calls..
+ *
+ * This is really horribly ugly.
+ */
+asmlinkage int sys_ipc (uint call, int first, int second,
+ int third, void *ptr, long fifth)
+{
+ int version, ret;
+
+ version = call >> 16; /* hack for backward compatibility */
+ call &= 0xffff;
+
+ switch (call) {
+ case SEMOP:
+ return sys_semop (first, (struct sembuf *)ptr, second);
+ case SEMGET:
+ return sys_semget (first, second, third);
+ case SEMCTL: {
+ union semun fourth;
+ if (!ptr)
+ return -EINVAL;
+ if (get_user(fourth.__pad, (void **) ptr))
+ return -EFAULT;
+ return sys_semctl (first, second, third, fourth);
+ }
+
+ case MSGSND:
+ return sys_msgsnd (first, (struct msgbuf *) ptr,
+ second, third);
+ case MSGRCV:
+ switch (version) {
+ case 0: {
+ struct ipc_kludge tmp;
+ if (!ptr)
+ return -EINVAL;
+
+ if (copy_from_user(&tmp,
+ (struct ipc_kludge *) ptr,
+ sizeof (tmp)))
+ return -EFAULT;
+ return sys_msgrcv (first, tmp.msgp, second,
+ tmp.msgtyp, third);
+ }
+ default:
+ return sys_msgrcv (first,
+ (struct msgbuf *) ptr,
+ second, fifth, third);
+ }
+ case MSGGET:
+ return sys_msgget ((key_t) first, second);
+ case MSGCTL:
+ return sys_msgctl (first, second, (struct msqid_ds *) ptr);
+
+ case SHMAT:
+ switch (version) {
+ default: {
+ ulong raddr;
+ ret = sys_shmat (first, (char *) ptr, second, &raddr);
+ if (ret)
+ return ret;
+ return put_user (raddr, (ulong *) third);
+ }
+ case 1: /* iBCS2 emulator entry point */
+ if (!segment_eq(get_fs(), get_ds()))
+ return -EINVAL;
+ return sys_shmat (first, (char *) ptr, second, (ulong *) third);
+ }
+ case SHMDT:
+ return sys_shmdt ((char *)ptr);
+ case SHMGET:
+ return sys_shmget (first, second, third);
+ case SHMCTL:
+ return sys_shmctl (first, second,
+ (struct shmid_ds *) ptr);
+ default:
+ return -EINVAL;
+ }
+}
+
+/*
+ * Old cruft
+ */
+asmlinkage int sys_uname(struct old_utsname * name)
+{
+ int err;
+ if (!name)
+ return -EFAULT;
+ down_read(&uts_sem);
+ err=copy_to_user(name, &system_utsname, sizeof (*name));
+ up_read(&uts_sem);
+ return err?-EFAULT:0;
+}
+
+asmlinkage int sys_olduname(struct oldold_utsname * name)
+{
+ int error;
+
+ if (!name)
+ return -EFAULT;
+ if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
+ return -EFAULT;
+
+ down_read(&uts_sem);
+
+ error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN);
+ error |= __put_user(0,name->sysname+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN);
+ error |= __put_user(0,name->nodename+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN);
+ error |= __put_user(0,name->release+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN);
+ error |= __put_user(0,name->version+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN);
+ error |= __put_user(0,name->machine+__OLD_UTS_LEN);
+
+ up_read(&uts_sem);
+
+ error = error ? -EFAULT : 0;
+
+ return error;
+}
+
+asmlinkage int sys_pause(void)
+{
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ return -ERESTARTNOHAND;
+}
+
--- /dev/null
+/* -*- Mode:C; c-basic-offset:4; tab-width:4 -*-
+ ****************************************************************************
+ * (C) 2002 - Rolf Neugebauer - Intel Research Cambridge
+ ****************************************************************************
+ *
+ * File: arch.xeno/time.c
+ * Author: Rolf Neugebauer
+ * Changes:
+ *
+ * Date: Nov 2002
+ *
+ * Environment: XenoLinux
+ * Description: Interface with Hypervisor to get correct notion of time
+ * Currently supports Systemtime and WallClock time.
+ *
+ * (This has hardly any resemblence with the Linux code but left the
+ * copyright notice anyway. Ignore the comments in the copyright notice.)
+ ****************************************************************************
+ * $Id: c-insert.c,v 1.7 2002/11/08 16:04:34 rn Exp $
+ ****************************************************************************
+ */
+
+/*
+ * linux/arch/i386/kernel/time.c
+ *
+ * Copyright (C) 1991, 1992, 1995 Linus Torvalds
+ *
+ * This file contains the PC-specific time handling details:
+ * reading the RTC at bootup, etc..
+ * 1994-07-02 Alan Modra
+ * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
+ * 1995-03-26 Markus Kuhn
+ * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
+ * precision CMOS clock update
+ * 1996-05-03 Ingo Molnar
+ * fixed time warps in do_[slow|fast]_gettimeoffset()
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * 1998-09-05 (Various)
+ * More robust do_fast_gettimeoffset() algorithm implemented
+ * (works with APM, Cyrix 6x86MX and Centaur C6),
+ * monotonic gettimeofday() with fast_get_timeoffset(),
+ * drift-proof precision TSC calibration on boot
+ * (C. Scott Ananian <cananian@alumni.princeton.edu>, Andrew D.
+ * Balsa <andrebalsa@altern.org>, Philip Gladstone <philip@raptor.com>;
+ * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@tu-harburg.de>).
+ * 1998-12-16 Andrea Arcangeli
+ * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
+ * because was not accounting lost_ticks.
+ * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli
+ * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ * serialize accesses to xtime/lost_ticks).
+ */
+
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/msr.h>
+#include <asm/delay.h>
+#include <asm/mpspec.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+
+#include <asm/div64.h>
+#include <asm/hypervisor.h>
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+
+#undef XENO_TIME_DEBUG /* adds sanity checks and periodic printouts */
+
+spinlock_t rtc_lock = SPIN_LOCK_UNLOCKED;
+extern rwlock_t xtime_lock;
+
+unsigned long cpu_khz; /* get this from Xen, used elsewhere */
+static spinlock_t hyp_stime_lock = SPIN_LOCK_UNLOCKED;
+static spinlock_t hyp_wctime_lock = SPIN_LOCK_UNLOCKED;
+
+static u32 st_scale_f;
+static u32 st_scale_i;
+static u32 shadow_st_pcc;
+static s64 shadow_st;
+
+/*
+ * System time.
+ * Although the rest of the Linux kernel doesn't know about this, we
+ * we use it to extrapolate passage of wallclock time.
+ * We need to read the values from the shared info page "atomically"
+ * and use the cycle counter value as the "version" number. Clashes
+ * should be very rare.
+ */
+static inline long long get_s_time(void)
+{
+ unsigned long flags;
+ u32 delta_tsc, low, pcc;
+ u64 delta;
+ s64 now;
+
+ spin_lock_irqsave(&hyp_stime_lock, flags);
+
+ while ((pcc = HYPERVISOR_shared_info->st_timestamp) != shadow_st_pcc)
+ {
+ barrier();
+ shadow_st_pcc = pcc;
+ shadow_st = HYPERVISOR_shared_info->system_time;
+ barrier();
+ }
+
+ now = shadow_st;
+ /* only use bottom 32bits of TSC. This should be sufficient */
+ rdtscl(low);
+ delta_tsc = low - pcc;
+ delta = ((u64)delta_tsc * st_scale_f);
+ delta >>= 32;
+ delta += ((u64)delta_tsc * st_scale_i);
+
+ spin_unlock_irqrestore(&hyp_time_lock, flags);
+
+ return now + delta;
+
+}
+#define NOW() ((long long)get_s_time())
+
+/*
+ * Wallclock time.
+ * Based on what the hypervisor tells us, extrapolated using system time.
+ * Again need to read a number of values from the shared page "atomically".
+ * this time using a version number.
+ */
+static u32 shadow_wc_version=0;
+static long shadow_tv_sec;
+static long shadow_tv_usec;
+static long long shadow_wc_timestamp;
+void do_gettimeofday(struct timeval *tv)
+{
+ unsigned long flags;
+ long usec, sec;
+ u32 version;
+ u64 now;
+
+ spin_lock_irqsave(&hyp_wctime_lock, flags);
+
+ while ((version = HYPERVISOR_shared_info->wc_version)!= shadow_wc_version)
+ {
+ barrier();
+ shadow_wc_version = version;
+ shadow_tv_sec = HYPERVISOR_shared_info->tv_sec;
+ shadow_tv_usec = HYPERVISOR_shared_info->tv_usec;
+ shadow_wc_timestamp = HYPERVISOR_shared_info->wc_timestamp;
+ barrier();
+ }
+
+ now = NOW();
+ usec = ((unsigned long)(now-shadow_wc_timestamp))/1000;
+ sec = shadow_tv_sec;
+ usec += shadow_tv_usec;
+
+ while ( usec >= 1000000 )
+ {
+ usec -= 1000000;
+ sec++;
+ }
+
+ tv->tv_sec = sec;
+ tv->tv_usec = usec;
+
+ spin_unlock_irqrestore(&hyp_time_lock, flags);
+
+#ifdef XENO_TIME_DEBUG
+ {
+ static long long old_now=0;
+ static long long wct=0, old_wct=0;
+
+ /* This debug code checks if time increase over two subsequent calls */
+ wct=(((long long)sec) * 1000000) + usec;
+ /* wall clock time going backwards */
+ if ((wct < old_wct) ) {
+ printk("Urgh1: wc diff=%6ld, usec = %ld (0x%lX)\n",
+ (long)(wct-old_wct), usec, usec);
+ printk(" st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
+ now-old_now, now, old_now);
+ }
+
+ /* system time going backwards */
+ if (now<=old_now) {
+ printk("Urgh2: st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
+ now-old_now, now, old_now);
+ }
+ old_wct = wct;
+ old_now = now;
+ }
+#endif
+
+}
+
+void do_settimeofday(struct timeval *tv)
+{
+/* XXX RN: should do something special here for dom0 */
+#if 0
+ write_lock_irq(&xtime_lock);
+ /*
+ * This is revolting. We need to set "xtime" correctly. However, the
+ * value in this location is the value at the most recent update of
+ * wall time. Discover what correction gettimeofday() would have
+ * made, and then undo it!
+ */
+ tv->tv_usec -= do_gettimeoffset();
+ tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ);
+
+ while ( tv->tv_usec < 0 )
+ {
+ tv->tv_usec += 1000000;
+ tv->tv_sec--;
+ }
+
+ xtime = *tv;
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+ write_unlock_irq(&xtime_lock);
+#endif
+}
+
+
+/*
+ * Timer ISR.
+ * Unlike normal Linux these don't come in at a fixed rate of HZ.
+ * In here we wrok out how often it should have been called and then call
+ * the architecture independent part (do_timer()) the appropriate number of
+ * times. A bit of a nasty hack, to keep the "other" notion of wallclock time
+ * happy.
+ */
+static long long us_per_tick=1000000/HZ;
+static long long last_irq;
+static inline void do_timer_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ struct timeval tv;
+ long long time, delta;
+
+#ifdef XENO_TIME_DEBUG
+ static u32 foo_count = 0;
+ foo_count++;
+ if (foo_count>= 1000) {
+ s64 n = NOW();
+ struct timeval tv;
+ do_gettimeofday(&tv);
+ printk("0x%08X%08X %ld:%ld\n",
+ (u32)(n>>32), (u32)n, tv.tv_sec, tv.tv_usec);
+ foo_count = 0;
+ }
+#endif
+ /*
+ * The next bit really sucks:
+ * Linux not only uses do_gettimeofday() to keep a notion of
+ * wallclock time, but also maintains the xtime struct and jiffies.
+ * (Even worse some userland code accesses this via the sys_time()
+ * system call)
+ * Unfortunately, xtime is maintain in the architecture independent
+ * part of the timer ISR (./kernel/timer.c sic!). So, although we have
+ * perfectly valid notion of wallclock time from the hypervisor we here
+ * fake missed timer interrupts so that the arch independent part of
+ * the Timer ISR updates jiffies for us *and* once the bh gets run
+ * updates xtime accordingly. Yuck!
+ */
+
+ /* work out the number of jiffies past and update them */
+ do_gettimeofday(&tv);
+ time = (((long long)tv.tv_sec) * 1000000) + tv.tv_usec;
+ delta = time - last_irq;
+ if (delta <= 0) {
+ printk ("Timer ISR: Time went backwards: %lld\n", delta);
+ return;
+ }
+ while (delta >= us_per_tick) {
+ do_timer(regs);
+ delta -= us_per_tick;
+ last_irq += us_per_tick;
+ }
+
+#if 0
+ if (!user_mode(regs))
+ x86_do_profile(regs->eip);
+#endif
+}
+
+static void timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+ write_lock(&xtime_lock);
+ do_timer_interrupt(irq, NULL, regs);
+ write_unlock(&xtime_lock);
+}
+
+static struct irqaction irq_timer = {
+ timer_interrupt,
+ SA_INTERRUPT,
+ 0,
+ "timer",
+ NULL,
+ NULL
+};
+
+void __init time_init(void)
+{
+ unsigned long long alarm;
+ u64 cpu_freq = HYPERVISOR_shared_info->cpu_freq;
+ u64 scale;
+
+ cpu_khz = (u32)cpu_freq/1000;
+ printk("Xen reported: %lu.%03lu MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
+
+ /*
+ * calculate systemtime scaling factor
+ * XXX RN: have to cast cpu_freq to u32 limits it to 4.29 GHz.
+ * Get a better do_div!
+ */
+ scale = 1000000000LL << 32;
+ do_div(scale,(u32)cpu_freq);
+ st_scale_f = scale & 0xffffffff;
+ st_scale_i = scale >> 32;
+ printk("System Time scale: %X %X\n",st_scale_i, st_scale_f);
+
+ do_gettimeofday(&xtime);
+ last_irq = (((long long)xtime.tv_sec) * 1000000) + xtime.tv_usec;
+
+ setup_irq(TIMER_IRQ, &irq_timer);
+
+ /*
+ * Start ticker. Note that timing runs of wall clock, not virtual
+ * 'domain' time. This means that clock sshould run at the correct
+ * rate. For things like scheduling, it's not clear whether it
+ * matters which sort of time we use.
+ * XXX RN: unimplemented.
+ */
+
+ rdtscll(alarm);
+#if 0
+ alarm += (1000/HZ)*HYPERVISOR_shared_info->ticks_per_ms;
+ HYPERVISOR_shared_info->wall_timeout = alarm;
+ HYPERVISOR_shared_info->domain_timeout = ~0ULL;
+#endif
+ clear_bit(_EVENT_TIMER, &HYPERVISOR_shared_info->events);
+}
--- /dev/null
+/*
+ * linux/arch/i386/traps.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * 'Traps.c' handles hardware traps and faults after we have saved some
+ * state in 'asm.s'.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/highmem.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+#include <asm/smp.h>
+#include <asm/pgalloc.h>
+
+#include <asm/hypervisor.h>
+
+#include <linux/irq.h>
+#include <linux/module.h>
+
+asmlinkage int system_call(void);
+
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void double_fault(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void alignment_check(void);
+asmlinkage void spurious_interrupt_bug(void);
+asmlinkage void machine_check(void);
+
+int kstack_depth_to_print = 24;
+
+
+/*
+ * If the address is either in the .text section of the
+ * kernel, or in the vmalloc'ed module regions, it *may*
+ * be the address of a calling routine
+ */
+
+#ifdef CONFIG_MODULES
+
+extern struct module *module_list;
+extern struct module kernel_module;
+
+static inline int kernel_text_address(unsigned long addr)
+{
+ int retval = 0;
+ struct module *mod;
+
+ if (addr >= (unsigned long) &_stext &&
+ addr <= (unsigned long) &_etext)
+ return 1;
+
+ for (mod = module_list; mod != &kernel_module; mod = mod->next) {
+ /* mod_bound tests for addr being inside the vmalloc'ed
+ * module area. Of course it'd be better to test only
+ * for the .text subset... */
+ if (mod_bound(addr, 0, mod)) {
+ retval = 1;
+ break;
+ }
+ }
+
+ return retval;
+}
+
+#else
+
+static inline int kernel_text_address(unsigned long addr)
+{
+ return (addr >= (unsigned long) &_stext &&
+ addr <= (unsigned long) &_etext);
+}
+
+#endif
+
+void show_trace(unsigned long * stack)
+{
+ int i;
+ unsigned long addr;
+
+ if (!stack)
+ stack = (unsigned long*)&stack;
+
+ printk("Call Trace: ");
+ i = 1;
+ while (((long) stack & (THREAD_SIZE-1)) != 0) {
+ addr = *stack++;
+ if (kernel_text_address(addr)) {
+ if (i && ((i % 6) == 0))
+ printk("\n ");
+ printk("[<%08lx>] ", addr);
+ i++;
+ }
+ }
+ printk("\n");
+}
+
+void show_trace_task(struct task_struct *tsk)
+{
+ unsigned long esp = tsk->thread.esp;
+
+ /* User space on another CPU? */
+ if ((esp ^ (unsigned long)tsk) & (PAGE_MASK<<1))
+ return;
+ show_trace((unsigned long *)esp);
+}
+
+void show_stack(unsigned long * esp)
+{
+ unsigned long *stack;
+ int i;
+
+ // debugging aid: "show_stack(NULL);" prints the
+ // back trace for this cpu.
+
+ if(esp==NULL)
+ esp=(unsigned long*)&esp;
+
+ stack = esp;
+ for(i=0; i < kstack_depth_to_print; i++) {
+ if (((long) stack & (THREAD_SIZE-1)) == 0)
+ break;
+ if (i && ((i % 8) == 0))
+ printk("\n ");
+ printk("%08lx ", *stack++);
+ }
+ printk("\n");
+ show_trace(esp);
+}
+
+void show_registers(struct pt_regs *regs)
+{
+ int i;
+ int in_kernel = 1;
+ unsigned long esp;
+ unsigned short ss;
+
+ esp = (unsigned long) (®s->esp);
+ ss = __KERNEL_DS;
+ if (regs->xcs & 2) {
+ in_kernel = 0;
+ esp = regs->esp;
+ ss = regs->xss & 0xffff;
+ }
+ printk("CPU: %d\nEIP: %04x:[<%08lx>] %s\nEFLAGS: %08lx\n",
+ smp_processor_id(), 0xffff & regs->xcs, regs->eip, print_tainted(), regs->eflags);
+ printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n",
+ regs->eax, regs->ebx, regs->ecx, regs->edx);
+ printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n",
+ regs->esi, regs->edi, regs->ebp, esp);
+ printk("ds: %04x es: %04x ss: %04x\n",
+ regs->xds & 0xffff, regs->xes & 0xffff, ss);
+ printk("Process %s (pid: %d, stackpage=%08lx)",
+ current->comm, current->pid, 4096+(unsigned long)current);
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (in_kernel) {
+
+ printk("\nStack: ");
+ show_stack((unsigned long*)esp);
+
+#if 0
+ printk("\nCode: ");
+ if(regs->eip < PAGE_OFFSET)
+ goto bad;
+
+ for(i=0;i<20;i++)
+ {
+ unsigned char c;
+ if(__get_user(c, &((unsigned char*)regs->eip)[i])) {
+bad:
+ printk(" Bad EIP value.");
+ break;
+ }
+ printk("%02x ", c);
+ }
+#endif
+ }
+ printk("\n");
+}
+
+spinlock_t die_lock = SPIN_LOCK_UNLOCKED;
+
+void die(const char * str, struct pt_regs * regs, long err)
+{
+ console_verbose();
+ spin_lock_irq(&die_lock);
+ bust_spinlocks(1);
+ printk("%s: %04lx\n", str, err & 0xffff);
+ show_registers(regs);
+ bust_spinlocks(0);
+ spin_unlock_irq(&die_lock);
+ do_exit(SIGSEGV);
+}
+
+static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
+{
+ if (!(2 & regs->xcs))
+ die(str, regs, err);
+}
+
+
+static void inline do_trap(int trapnr, int signr, char *str,
+ struct pt_regs * regs, long error_code,
+ siginfo_t *info)
+{
+ if (!(regs->xcs & 2))
+ goto kernel_trap;
+
+ /*trap_signal:*/ {
+ struct task_struct *tsk = current;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
+ if (info)
+ force_sig_info(signr, info, tsk);
+ else
+ force_sig(signr, tsk);
+ return;
+ }
+
+ kernel_trap: {
+ unsigned long fixup = search_exception_table(regs->eip);
+ if (fixup)
+ regs->eip = fixup;
+ else
+ die(str, regs, error_code);
+ return;
+ }
+}
+
+#define DO_ERROR(trapnr, signr, str, name) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ do_trap(trapnr, signr, str, regs, error_code, NULL); \
+}
+
+#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ siginfo_t info; \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void *)siaddr; \
+ do_trap(trapnr, signr, str, regs, error_code, &info); \
+}
+
+DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip)
+DO_ERROR( 3, SIGTRAP, "int3", int3)
+DO_ERROR( 4, SIGSEGV, "overflow", overflow)
+DO_ERROR( 5, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip)
+DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
+DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
+DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
+DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR(18, SIGBUS, "machine check", machine_check)
+
+asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
+{
+ if (!(regs->xcs & 2))
+ goto gp_in_kernel;
+
+ current->thread.error_code = error_code;
+ current->thread.trap_no = 13;
+ force_sig(SIGSEGV, current);
+ return;
+
+gp_in_kernel:
+ {
+ unsigned long fixup;
+ fixup = search_exception_table(regs->eip);
+ if (fixup) {
+ regs->eip = fixup;
+ return;
+ }
+ die("general protection fault", regs, error_code);
+ }
+}
+
+
+asmlinkage void do_debug(struct pt_regs * regs, long error_code)
+{
+ unsigned int condition;
+ struct task_struct *tsk = current;
+ siginfo_t info;
+
+ condition = HYPERVISOR_get_debugreg(6);
+
+ /* Mask out spurious debug traps due to lazy DR7 setting */
+ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
+ if (!tsk->thread.debugreg[7])
+ goto clear_dr7;
+ }
+
+ /* Save debug status register where ptrace can see it */
+ tsk->thread.debugreg[6] = condition;
+
+ /* Mask out spurious TF errors due to lazy TF clearing */
+ if (condition & DR_STEP) {
+ /*
+ * The TF error should be masked out only if the current
+ * process is not traced and if the TRAP flag has been set
+ * previously by a tracing process (condition detected by
+ * the PT_DTRACE flag); remember that the i386 TRAP flag
+ * can be modified by the process itself in user mode,
+ * allowing programs to debug themselves without the ptrace()
+ * interface.
+ */
+ if ((tsk->ptrace & (PT_DTRACE|PT_PTRACED)) == PT_DTRACE)
+ goto clear_TF;
+ }
+
+ /* Ok, finally something we can handle */
+ tsk->thread.trap_no = 1;
+ tsk->thread.error_code = error_code;
+ info.si_signo = SIGTRAP;
+ info.si_errno = 0;
+ info.si_code = TRAP_BRKPT;
+
+ /* If this is a kernel mode trap, save the user PC on entry to
+ * the kernel, that's what the debugger can make sense of.
+ */
+ info.si_addr = ((regs->xcs & 3) == 0) ? (void *)tsk->thread.eip :
+ (void *)regs->eip;
+ force_sig_info(SIGTRAP, &info, tsk);
+
+ /* Disable additional traps. They'll be re-enabled when
+ * the signal is delivered.
+ */
+ clear_dr7:
+ HYPERVISOR_set_debugreg(7, 0);
+ return;
+
+ clear_TF:
+ regs->eflags &= ~TF_MASK;
+ return;
+}
+
+
+/*
+ * Note that we play around with the 'TS' bit in an attempt to get
+ * the correct behaviour even in the presence of the asynchronous
+ * IRQ13 behaviour
+ */
+void math_error(void *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short cwd, swd;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 16;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't syncronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(task);
+ swd = get_fpu_swd(task);
+ switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ case 0x040: /* Stack Fault */
+ case 0x240: /* Stack Fault | Direction */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_coprocessor_error(struct pt_regs * regs, long error_code)
+{
+ ignore_irq13 = 1;
+ math_error((void *)regs->eip);
+}
+
+void simd_math_error(void *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short mxcsr;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 19;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ mxcsr = get_fpu_mxcsr(task);
+ switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_simd_coprocessor_error(struct pt_regs * regs,
+ long error_code)
+{
+ if (cpu_has_xmm) {
+ /* Handle SIMD FPU exceptions on PIII+ processors. */
+ ignore_irq13 = 1;
+ simd_math_error((void *)regs->eip);
+ } else {
+ die_if_kernel("cache flush denied", regs, error_code);
+ current->thread.trap_no = 19;
+ current->thread.error_code = error_code;
+ force_sig(SIGSEGV, current);
+ }
+}
+
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs,
+ long error_code)
+{
+}
+
+/*
+ * 'math_state_restore()' saves the current math information in the
+ * old math state array, and gets the new ones from the current task
+ *
+ * Careful.. There are problems with IBM-designed IRQ13 behaviour.
+ * Don't touch unless you *really* know how it works.
+ */
+asmlinkage void math_state_restore(struct pt_regs regs)
+{
+ if (current->used_math) {
+ restore_fpu(current);
+ } else {
+ init_fpu();
+ }
+ current->flags |= PF_USEDFPU; /* So we fnsave on switch_to() */
+}
+
+static trap_info_t trap_table[] = {
+ { 0, 0, __KERNEL_CS, (unsigned long)divide_error },
+ { 1, 0, __KERNEL_CS, (unsigned long)debug },
+ { 3, 3, __KERNEL_CS, (unsigned long)int3 },
+ { 4, 3, __KERNEL_CS, (unsigned long)overflow },
+ { 5, 3, __KERNEL_CS, (unsigned long)bounds },
+ { 6, 0, __KERNEL_CS, (unsigned long)invalid_op },
+ { 7, 0, __KERNEL_CS, (unsigned long)device_not_available },
+ { 8, 0, __KERNEL_CS, (unsigned long)double_fault },
+ { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun },
+ { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS },
+ { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present },
+ { 12, 0, __KERNEL_CS, (unsigned long)stack_segment },
+ { 13, 0, __KERNEL_CS, (unsigned long)general_protection },
+ { 14, 0, __KERNEL_CS, (unsigned long)page_fault },
+ { 15, 0, __KERNEL_CS, (unsigned long)spurious_interrupt_bug },
+ { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error },
+ { 17, 0, __KERNEL_CS, (unsigned long)alignment_check },
+ { 18, 0, __KERNEL_CS, (unsigned long)machine_check },
+ { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error },
+ { SYSCALL_VECTOR,
+ 3, __KERNEL_CS, (unsigned long)system_call },
+ { 0, 0, 0, 0 }
+};
+
+
+
+void __init trap_init(void)
+{
+ HYPERVISOR_set_trap_table(trap_table);
+ HYPERVISOR_set_fast_trap(SYSCALL_VECTOR);
+ cpu_init();
+}
--- /dev/null
+
+.S.o:
+ $(CC) $(AFLAGS) -c $< -o $*.o
+
+L_TARGET = lib.a
+
+obj-y = checksum.o old-checksum.o delay.o \
+ usercopy.o getuser.o \
+ memcpy.o strstr.o
+
+obj-$(CONFIG_X86_USE_3DNOW) += mmx.o
+obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
+obj-$(CONFIG_DEBUG_IOVIRT) += iodebug.o
+
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * IP/TCP/UDP checksumming routines
+ *
+ * Authors: Jorge Cwik, <jorge@laser.satlink.net>
+ * Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ * Tom May, <ftom@netcom.com>
+ * Pentium Pro/II routines:
+ * Alexander Kjeldaas <astor@guardian.no>
+ * Finn Arne Gangstad <finnag@guardian.no>
+ * Lots of code moved from tcp.c and ip.c; see those files
+ * for more names.
+ *
+ * Changes: Ingo Molnar, converted csum_partial_copy() to 2.1 exception
+ * handling.
+ * Andi Kleen, add zeroing on error
+ * converted to pure assembler
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <asm/errno.h>
+
+/*
+ * computes a partial checksum, e.g. for TCP/UDP fragments
+ */
+
+/*
+unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
+ */
+
+.text
+.align 4
+.globl csum_partial
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+ /*
+ * Experiments with Ethernet and SLIP connections show that buff
+ * is aligned on either a 2-byte or 4-byte boundary. We get at
+ * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
+ * Fortunately, it is easy to convert 2-byte alignment to 4-byte
+ * alignment for the unrolled loop.
+ */
+csum_partial:
+ pushl %esi
+ pushl %ebx
+ movl 20(%esp),%eax # Function arg: unsigned int sum
+ movl 16(%esp),%ecx # Function arg: int len
+ movl 12(%esp),%esi # Function arg: unsigned char *buff
+ testl $3, %esi # Check alignment.
+ jz 2f # Jump if alignment is ok.
+ testl $1, %esi # Check alignment.
+ jz 10f # Jump if alignment is boundary of 2bytes.
+
+ # buf is odd
+ dec %ecx
+ jl 8f
+ movzbl (%esi), %ebx
+ adcl %ebx, %eax
+ roll $8, %eax
+ inc %esi
+ testl $2, %esi
+ jz 2f
+10:
+ subl $2, %ecx # Alignment uses up two bytes.
+ jae 1f # Jump if we had at least two bytes.
+ addl $2, %ecx # ecx was < 2. Deal with it.
+ jmp 4f
+1: movw (%esi), %bx
+ addl $2, %esi
+ addw %bx, %ax
+ adcl $0, %eax
+2:
+ movl %ecx, %edx
+ shrl $5, %ecx
+ jz 2f
+ testl %esi, %esi
+1: movl (%esi), %ebx
+ adcl %ebx, %eax
+ movl 4(%esi), %ebx
+ adcl %ebx, %eax
+ movl 8(%esi), %ebx
+ adcl %ebx, %eax
+ movl 12(%esi), %ebx
+ adcl %ebx, %eax
+ movl 16(%esi), %ebx
+ adcl %ebx, %eax
+ movl 20(%esi), %ebx
+ adcl %ebx, %eax
+ movl 24(%esi), %ebx
+ adcl %ebx, %eax
+ movl 28(%esi), %ebx
+ adcl %ebx, %eax
+ lea 32(%esi), %esi
+ dec %ecx
+ jne 1b
+ adcl $0, %eax
+2: movl %edx, %ecx
+ andl $0x1c, %edx
+ je 4f
+ shrl $2, %edx # This clears CF
+3: adcl (%esi), %eax
+ lea 4(%esi), %esi
+ dec %edx
+ jne 3b
+ adcl $0, %eax
+4: andl $3, %ecx
+ jz 7f
+ cmpl $2, %ecx
+ jb 5f
+ movw (%esi),%cx
+ leal 2(%esi),%esi
+ je 6f
+ shll $16,%ecx
+5: movb (%esi),%cl
+6: addl %ecx,%eax
+ adcl $0, %eax
+7:
+ testl $1, 12(%esp)
+ jz 8f
+ roll $8, %eax
+8:
+ popl %ebx
+ popl %esi
+ ret
+
+#else
+
+/* Version for PentiumII/PPro */
+
+csum_partial:
+ pushl %esi
+ pushl %ebx
+ movl 20(%esp),%eax # Function arg: unsigned int sum
+ movl 16(%esp),%ecx # Function arg: int len
+ movl 12(%esp),%esi # Function arg: const unsigned char *buf
+
+ testl $3, %esi
+ jnz 25f
+10:
+ movl %ecx, %edx
+ movl %ecx, %ebx
+ andl $0x7c, %ebx
+ shrl $7, %ecx
+ addl %ebx,%esi
+ shrl $2, %ebx
+ negl %ebx
+ lea 45f(%ebx,%ebx,2), %ebx
+ testl %esi, %esi
+ jmp *%ebx
+
+ # Handle 2-byte-aligned regions
+20: addw (%esi), %ax
+ lea 2(%esi), %esi
+ adcl $0, %eax
+ jmp 10b
+25:
+ testl $1, %esi
+ jz 30f
+ # buf is odd
+ dec %ecx
+ jl 90f
+ movzbl (%esi), %ebx
+ addl %ebx, %eax
+ adcl $0, %eax
+ roll $8, %eax
+ inc %esi
+ testl $2, %esi
+ jz 10b
+
+30: subl $2, %ecx
+ ja 20b
+ je 32f
+ addl $2, %ecx
+ jz 80f
+ movzbl (%esi),%ebx # csumming 1 byte, 2-aligned
+ addl %ebx, %eax
+ adcl $0, %eax
+ jmp 80f
+32:
+ addw (%esi), %ax # csumming 2 bytes, 2-aligned
+ adcl $0, %eax
+ jmp 80f
+
+40:
+ addl -128(%esi), %eax
+ adcl -124(%esi), %eax
+ adcl -120(%esi), %eax
+ adcl -116(%esi), %eax
+ adcl -112(%esi), %eax
+ adcl -108(%esi), %eax
+ adcl -104(%esi), %eax
+ adcl -100(%esi), %eax
+ adcl -96(%esi), %eax
+ adcl -92(%esi), %eax
+ adcl -88(%esi), %eax
+ adcl -84(%esi), %eax
+ adcl -80(%esi), %eax
+ adcl -76(%esi), %eax
+ adcl -72(%esi), %eax
+ adcl -68(%esi), %eax
+ adcl -64(%esi), %eax
+ adcl -60(%esi), %eax
+ adcl -56(%esi), %eax
+ adcl -52(%esi), %eax
+ adcl -48(%esi), %eax
+ adcl -44(%esi), %eax
+ adcl -40(%esi), %eax
+ adcl -36(%esi), %eax
+ adcl -32(%esi), %eax
+ adcl -28(%esi), %eax
+ adcl -24(%esi), %eax
+ adcl -20(%esi), %eax
+ adcl -16(%esi), %eax
+ adcl -12(%esi), %eax
+ adcl -8(%esi), %eax
+ adcl -4(%esi), %eax
+45:
+ lea 128(%esi), %esi
+ adcl $0, %eax
+ dec %ecx
+ jge 40b
+ movl %edx, %ecx
+50: andl $3, %ecx
+ jz 80f
+
+ # Handle the last 1-3 bytes without jumping
+ notl %ecx # 1->2, 2->1, 3->0, higher bits are masked
+ movl $0xffffff,%ebx # by the shll and shrl instructions
+ shll $3,%ecx
+ shrl %cl,%ebx
+ andl -128(%esi),%ebx # esi is 4-aligned so should be ok
+ addl %ebx,%eax
+ adcl $0,%eax
+80:
+ testl $1, 12(%esp)
+ jz 90f
+ roll $8, %eax
+90:
+ popl %ebx
+ popl %esi
+ ret
+
+#endif
+
+/*
+unsigned int csum_partial_copy_generic (const char *src, char *dst,
+ int len, int sum, int *src_err_ptr, int *dst_err_ptr)
+ */
+
+/*
+ * Copy from ds while checksumming, otherwise like csum_partial
+ *
+ * The macros SRC and DST specify the type of access for the instruction.
+ * thus we can call a custom exception handler for all access types.
+ *
+ * FIXME: could someone double-check whether I haven't mixed up some SRC and
+ * DST definitions? It's damn hard to trigger all cases. I hope I got
+ * them all but there's no guarantee.
+ */
+
+#define SRC(y...) \
+ 9999: y; \
+ .section __ex_table, "a"; \
+ .long 9999b, 6001f ; \
+ .previous
+
+#define DST(y...) \
+ 9999: y; \
+ .section __ex_table, "a"; \
+ .long 9999b, 6002f ; \
+ .previous
+
+.align 4
+.globl csum_partial_copy_generic
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+#define ARGBASE 16
+#define FP 12
+
+csum_partial_copy_generic:
+ subl $4,%esp
+ pushl %edi
+ pushl %esi
+ pushl %ebx
+ movl ARGBASE+16(%esp),%eax # sum
+ movl ARGBASE+12(%esp),%ecx # len
+ movl ARGBASE+4(%esp),%esi # src
+ movl ARGBASE+8(%esp),%edi # dst
+
+ testl $2, %edi # Check alignment.
+ jz 2f # Jump if alignment is ok.
+ subl $2, %ecx # Alignment uses up two bytes.
+ jae 1f # Jump if we had at least two bytes.
+ addl $2, %ecx # ecx was < 2. Deal with it.
+ jmp 4f
+SRC(1: movw (%esi), %bx )
+ addl $2, %esi
+DST( movw %bx, (%edi) )
+ addl $2, %edi
+ addw %bx, %ax
+ adcl $0, %eax
+2:
+ movl %ecx, FP(%esp)
+ shrl $5, %ecx
+ jz 2f
+ testl %esi, %esi
+SRC(1: movl (%esi), %ebx )
+SRC( movl 4(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, (%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 4(%edi) )
+
+SRC( movl 8(%esi), %ebx )
+SRC( movl 12(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, 8(%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 12(%edi) )
+
+SRC( movl 16(%esi), %ebx )
+SRC( movl 20(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, 16(%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 20(%edi) )
+
+SRC( movl 24(%esi), %ebx )
+SRC( movl 28(%esi), %edx )
+ adcl %ebx, %eax
+DST( movl %ebx, 24(%edi) )
+ adcl %edx, %eax
+DST( movl %edx, 28(%edi) )
+
+ lea 32(%esi), %esi
+ lea 32(%edi), %edi
+ dec %ecx
+ jne 1b
+ adcl $0, %eax
+2: movl FP(%esp), %edx
+ movl %edx, %ecx
+ andl $0x1c, %edx
+ je 4f
+ shrl $2, %edx # This clears CF
+SRC(3: movl (%esi), %ebx )
+ adcl %ebx, %eax
+DST( movl %ebx, (%edi) )
+ lea 4(%esi), %esi
+ lea 4(%edi), %edi
+ dec %edx
+ jne 3b
+ adcl $0, %eax
+4: andl $3, %ecx
+ jz 7f
+ cmpl $2, %ecx
+ jb 5f
+SRC( movw (%esi), %cx )
+ leal 2(%esi), %esi
+DST( movw %cx, (%edi) )
+ leal 2(%edi), %edi
+ je 6f
+ shll $16,%ecx
+SRC(5: movb (%esi), %cl )
+DST( movb %cl, (%edi) )
+6: addl %ecx, %eax
+ adcl $0, %eax
+7:
+5000:
+
+# Exception handler:
+.section .fixup, "ax"
+
+6001:
+ movl ARGBASE+20(%esp), %ebx # src_err_ptr
+ movl $-EFAULT, (%ebx)
+
+ # zero the complete destination - computing the rest
+ # is too much work
+ movl ARGBASE+8(%esp), %edi # dst
+ movl ARGBASE+12(%esp), %ecx # len
+ xorl %eax,%eax
+ rep ; stosb
+
+ jmp 5000b
+
+6002:
+ movl ARGBASE+24(%esp), %ebx # dst_err_ptr
+ movl $-EFAULT,(%ebx)
+ jmp 5000b
+
+.previous
+
+ popl %ebx
+ popl %esi
+ popl %edi
+ popl %ecx # equivalent to addl $4,%esp
+ ret
+
+#else
+
+/* Version for PentiumII/PPro */
+
+#define ROUND1(x) \
+ SRC(movl x(%esi), %ebx ) ; \
+ addl %ebx, %eax ; \
+ DST(movl %ebx, x(%edi) ) ;
+
+#define ROUND(x) \
+ SRC(movl x(%esi), %ebx ) ; \
+ adcl %ebx, %eax ; \
+ DST(movl %ebx, x(%edi) ) ;
+
+#define ARGBASE 12
+
+csum_partial_copy_generic:
+ pushl %ebx
+ pushl %edi
+ pushl %esi
+ movl ARGBASE+4(%esp),%esi #src
+ movl ARGBASE+8(%esp),%edi #dst
+ movl ARGBASE+12(%esp),%ecx #len
+ movl ARGBASE+16(%esp),%eax #sum
+# movl %ecx, %edx
+ movl %ecx, %ebx
+ movl %esi, %edx
+ shrl $6, %ecx
+ andl $0x3c, %ebx
+ negl %ebx
+ subl %ebx, %esi
+ subl %ebx, %edi
+ lea -1(%esi),%edx
+ andl $-32,%edx
+ lea 3f(%ebx,%ebx), %ebx
+ testl %esi, %esi
+ jmp *%ebx
+1: addl $64,%esi
+ addl $64,%edi
+ SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
+ ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)
+ ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)
+ ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)
+ ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4)
+3: adcl $0,%eax
+ addl $64, %edx
+ dec %ecx
+ jge 1b
+4: movl ARGBASE+12(%esp),%edx #len
+ andl $3, %edx
+ jz 7f
+ cmpl $2, %edx
+ jb 5f
+SRC( movw (%esi), %dx )
+ leal 2(%esi), %esi
+DST( movw %dx, (%edi) )
+ leal 2(%edi), %edi
+ je 6f
+ shll $16,%edx
+5:
+SRC( movb (%esi), %dl )
+DST( movb %dl, (%edi) )
+6: addl %edx, %eax
+ adcl $0, %eax
+7:
+.section .fixup, "ax"
+6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr
+ movl $-EFAULT, (%ebx)
+ # zero the complete destination (computing the rest is too much work)
+ movl ARGBASE+8(%esp),%edi # dst
+ movl ARGBASE+12(%esp),%ecx # len
+ xorl %eax,%eax
+ rep; stosb
+ jmp 7b
+6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr
+ movl $-EFAULT, (%ebx)
+ jmp 7b
+.previous
+
+ popl %esi
+ popl %edi
+ popl %ebx
+ ret
+
+#undef ROUND
+#undef ROUND1
+
+#endif
--- /dev/null
+/*
+ * x86 version of "atomic_dec_and_lock()" using
+ * the atomic "cmpxchg" instruction.
+ *
+ * (For CPU's lacking cmpxchg, we use the slow
+ * generic version, and this one never even gets
+ * compiled).
+ */
+
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+
+int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
+{
+ int counter;
+ int newcount;
+
+repeat:
+ counter = atomic_read(atomic);
+ newcount = counter-1;
+
+ if (!newcount)
+ goto slow_path;
+
+ asm volatile("lock; cmpxchgl %1,%2"
+ :"=a" (newcount)
+ :"r" (newcount), "m" (atomic->counter), "0" (counter));
+
+ /* If the above failed, "eax" will have changed */
+ if (newcount != counter)
+ goto repeat;
+ return 0;
+
+slow_path:
+ spin_lock(lock);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ spin_unlock(lock);
+ return 0;
+}
--- /dev/null
+/*
+ * Precise Delay Loops for i386
+ *
+ * Copyright (C) 1993 Linus Torvalds
+ * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ * The __delay function must _NOT_ be inlined as its execution time
+ * depends wildly on alignment on many x86 processors. The additional
+ * jump magic is needed to get the timing stable on all the CPU's
+ * we have to worry about.
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <asm/processor.h>
+#include <asm/delay.h>
+
+#ifdef CONFIG_SMP
+#include <asm/smp.h>
+#endif
+
+void __delay(unsigned long loops)
+{
+ unsigned long bclock, now;
+
+ rdtscl(bclock);
+ do
+ {
+ rep_nop();
+ rdtscl(now);
+ } while ((now-bclock) < loops);
+}
+
+inline void __const_udelay(unsigned long xloops)
+{
+ int d0;
+ __asm__("mull %0"
+ :"=d" (xloops), "=&a" (d0)
+ :"1" (xloops),"0" (current_cpu_data.loops_per_jiffy));
+ __delay(xloops * HZ);
+}
+
+void __udelay(unsigned long usecs)
+{
+ __const_udelay(usecs * 0x000010c6); /* 2**32 / 1000000 */
+}
--- /dev/null
+/*
+ * __get_user functions.
+ *
+ * (C) Copyright 1998 Linus Torvalds
+ *
+ * These functions have a non-standard call interface
+ * to make them more efficient, especially as they
+ * return an error value in addition to the "real"
+ * return value.
+ */
+
+/*
+ * __get_user_X
+ *
+ * Inputs: %eax contains the address
+ *
+ * Outputs: %eax is error code (0 or -EFAULT)
+ * %edx contains zero-extended value
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+addr_limit = 12
+
+.text
+.align 4
+.globl __get_user_1
+__get_user_1:
+ movl %esp,%edx
+ andl $0xffffe000,%edx
+ cmpl addr_limit(%edx),%eax
+ jae bad_get_user
+1: movzbl (%eax),%edx
+ xorl %eax,%eax
+ ret
+
+.align 4
+.globl __get_user_2
+__get_user_2:
+ addl $1,%eax
+ movl %esp,%edx
+ jc bad_get_user
+ andl $0xffffe000,%edx
+ cmpl addr_limit(%edx),%eax
+ jae bad_get_user
+2: movzwl -1(%eax),%edx
+ xorl %eax,%eax
+ ret
+
+.align 4
+.globl __get_user_4
+__get_user_4:
+ addl $3,%eax
+ movl %esp,%edx
+ jc bad_get_user
+ andl $0xffffe000,%edx
+ cmpl addr_limit(%edx),%eax
+ jae bad_get_user
+3: movl -3(%eax),%edx
+ xorl %eax,%eax
+ ret
+
+bad_get_user:
+ xorl %edx,%edx
+ movl $-14,%eax
+ ret
+
+.section __ex_table,"a"
+ .long 1b,bad_get_user
+ .long 2b,bad_get_user
+ .long 3b,bad_get_user
+.previous
--- /dev/null
+#include <asm/io.h>
+
+void * __io_virt_debug(unsigned long x, const char *file, int line)
+{
+ if (x < PAGE_OFFSET) {
+ printk("io mapaddr 0x%05lx not valid at %s:%d!\n", x, file, line);
+ return __va(x);
+ }
+ return (void *)x;
+}
+
+unsigned long __io_phys_debug(unsigned long x, const char *file, int line)
+{
+ if (x < PAGE_OFFSET) {
+ printk("io mapaddr 0x%05lx not valid at %s:%d!\n", x, file, line);
+ return x;
+ }
+ return __pa(x);
+}
--- /dev/null
+#include <linux/config.h>
+#include <linux/string.h>
+
+#undef memcpy
+#undef memset
+
+void * memcpy(void * to, const void * from, size_t n)
+{
+#ifdef CONFIG_X86_USE_3DNOW
+ return __memcpy3d(to, from, n);
+#else
+ return __memcpy(to, from, n);
+#endif
+}
+
+void * memset(void * s, int c, size_t count)
+{
+ return __memset(s, c, count);
+}
--- /dev/null
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+
+#include <asm/i387.h>
+#include <asm/hardirq.h>
+
+
+/*
+ * MMX 3DNow! library helper functions
+ *
+ * To do:
+ * We can use MMX just for prefetch in IRQ's. This may be a win.
+ * (reported so on K6-III)
+ * We should use a better code neutral filler for the short jump
+ * leal ebx. [ebx] is apparently best for K6-2, but Cyrix ??
+ * We also want to clobber the filler register so we dont get any
+ * register forwarding stalls on the filler.
+ *
+ * Add *user handling. Checksums are not a win with MMX on any CPU
+ * tested so far for any MMX solution figured.
+ *
+ * 22/09/2000 - Arjan van de Ven
+ * Improved for non-egineering-sample Athlons
+ *
+ */
+
+void *_mmx_memcpy(void *to, const void *from, size_t len)
+{
+ void *p;
+ int i;
+
+ if (in_interrupt())
+ return __memcpy(to, from, len);
+
+ p = to;
+ i = len >> 6; /* len/64 */
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n" /* This set is 28 bytes */
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+
+ for(; i>5; i--)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movq 8(%0), %%mm1\n"
+ " movq 16(%0), %%mm2\n"
+ " movq 24(%0), %%mm3\n"
+ " movq %%mm0, (%1)\n"
+ " movq %%mm1, 8(%1)\n"
+ " movq %%mm2, 16(%1)\n"
+ " movq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm0\n"
+ " movq 40(%0), %%mm1\n"
+ " movq 48(%0), %%mm2\n"
+ " movq 56(%0), %%mm3\n"
+ " movq %%mm0, 32(%1)\n"
+ " movq %%mm1, 40(%1)\n"
+ " movq %%mm2, 48(%1)\n"
+ " movq %%mm3, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+
+ for(; i>0; i--)
+ {
+ __asm__ __volatile__ (
+ " movq (%0), %%mm0\n"
+ " movq 8(%0), %%mm1\n"
+ " movq 16(%0), %%mm2\n"
+ " movq 24(%0), %%mm3\n"
+ " movq %%mm0, (%1)\n"
+ " movq %%mm1, 8(%1)\n"
+ " movq %%mm2, 16(%1)\n"
+ " movq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm0\n"
+ " movq 40(%0), %%mm1\n"
+ " movq 48(%0), %%mm2\n"
+ " movq 56(%0), %%mm3\n"
+ " movq %%mm0, 32(%1)\n"
+ " movq %%mm1, 40(%1)\n"
+ " movq %%mm2, 48(%1)\n"
+ " movq %%mm3, 56(%1)\n"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ /*
+ * Now do the tail of the block
+ */
+ __memcpy(to, from, len&63);
+ kernel_fpu_end();
+ return p;
+}
+
+#ifdef CONFIG_MK7
+
+/*
+ * The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
+ * other MMX using processors do not.
+ */
+
+static void fast_clear_page(void *page)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ " pxor %%mm0, %%mm0\n" : :
+ );
+
+ for(i=0;i<4096/64;i++)
+ {
+ __asm__ __volatile__ (
+ " movntq %%mm0, (%0)\n"
+ " movntq %%mm0, 8(%0)\n"
+ " movntq %%mm0, 16(%0)\n"
+ " movntq %%mm0, 24(%0)\n"
+ " movntq %%mm0, 32(%0)\n"
+ " movntq %%mm0, 40(%0)\n"
+ " movntq %%mm0, 48(%0)\n"
+ " movntq %%mm0, 56(%0)\n"
+ : : "r" (page) : "memory");
+ page+=64;
+ }
+ /* since movntq is weakly-ordered, a "sfence" is needed to become
+ * ordered again.
+ */
+ __asm__ __volatile__ (
+ " sfence \n" : :
+ );
+ kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ /* maybe the prefetch stuff can go before the expensive fnsave...
+ * but that is for later. -AV
+ */
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n"
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+ for(i=0; i<(4096-320)/64; i++)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movntq %%mm0, (%1)\n"
+ " movq 8(%0), %%mm1\n"
+ " movntq %%mm1, 8(%1)\n"
+ " movq 16(%0), %%mm2\n"
+ " movntq %%mm2, 16(%1)\n"
+ " movq 24(%0), %%mm3\n"
+ " movntq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm4\n"
+ " movntq %%mm4, 32(%1)\n"
+ " movq 40(%0), %%mm5\n"
+ " movntq %%mm5, 40(%1)\n"
+ " movq 48(%0), %%mm6\n"
+ " movntq %%mm6, 48(%1)\n"
+ " movq 56(%0), %%mm7\n"
+ " movntq %%mm7, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ for(i=(4096-320)/64; i<4096/64; i++)
+ {
+ __asm__ __volatile__ (
+ "2: movq (%0), %%mm0\n"
+ " movntq %%mm0, (%1)\n"
+ " movq 8(%0), %%mm1\n"
+ " movntq %%mm1, 8(%1)\n"
+ " movq 16(%0), %%mm2\n"
+ " movntq %%mm2, 16(%1)\n"
+ " movq 24(%0), %%mm3\n"
+ " movntq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm4\n"
+ " movntq %%mm4, 32(%1)\n"
+ " movq 40(%0), %%mm5\n"
+ " movntq %%mm5, 40(%1)\n"
+ " movq 48(%0), %%mm6\n"
+ " movntq %%mm6, 48(%1)\n"
+ " movq 56(%0), %%mm7\n"
+ " movntq %%mm7, 56(%1)\n"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ /* since movntq is weakly-ordered, a "sfence" is needed to become
+ * ordered again.
+ */
+ __asm__ __volatile__ (
+ " sfence \n" : :
+ );
+ kernel_fpu_end();
+}
+
+#else
+
+/*
+ * Generic MMX implementation without K7 specific streaming
+ */
+
+static void fast_clear_page(void *page)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ " pxor %%mm0, %%mm0\n" : :
+ );
+
+ for(i=0;i<4096/128;i++)
+ {
+ __asm__ __volatile__ (
+ " movq %%mm0, (%0)\n"
+ " movq %%mm0, 8(%0)\n"
+ " movq %%mm0, 16(%0)\n"
+ " movq %%mm0, 24(%0)\n"
+ " movq %%mm0, 32(%0)\n"
+ " movq %%mm0, 40(%0)\n"
+ " movq %%mm0, 48(%0)\n"
+ " movq %%mm0, 56(%0)\n"
+ " movq %%mm0, 64(%0)\n"
+ " movq %%mm0, 72(%0)\n"
+ " movq %%mm0, 80(%0)\n"
+ " movq %%mm0, 88(%0)\n"
+ " movq %%mm0, 96(%0)\n"
+ " movq %%mm0, 104(%0)\n"
+ " movq %%mm0, 112(%0)\n"
+ " movq %%mm0, 120(%0)\n"
+ : : "r" (page) : "memory");
+ page+=128;
+ }
+
+ kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+ int i;
+
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n"
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+ for(i=0; i<4096/64; i++)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movq 8(%0), %%mm1\n"
+ " movq 16(%0), %%mm2\n"
+ " movq 24(%0), %%mm3\n"
+ " movq %%mm0, (%1)\n"
+ " movq %%mm1, 8(%1)\n"
+ " movq %%mm2, 16(%1)\n"
+ " movq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm0\n"
+ " movq 40(%0), %%mm1\n"
+ " movq 48(%0), %%mm2\n"
+ " movq 56(%0), %%mm3\n"
+ " movq %%mm0, 32(%1)\n"
+ " movq %%mm1, 40(%1)\n"
+ " movq %%mm2, 48(%1)\n"
+ " movq %%mm3, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ kernel_fpu_end();
+}
+
+
+#endif
+
+/*
+ * Favour MMX for page clear and copy.
+ */
+
+static void slow_zero_page(void * page)
+{
+ int d0, d1;
+ __asm__ __volatile__( \
+ "cld\n\t" \
+ "rep ; stosl" \
+ : "=&c" (d0), "=&D" (d1)
+ :"a" (0),"1" (page),"0" (1024)
+ :"memory");
+}
+
+void mmx_clear_page(void * page)
+{
+ if(in_interrupt())
+ slow_zero_page(page);
+ else
+ fast_clear_page(page);
+}
+
+static void slow_copy_page(void *to, void *from)
+{
+ int d0, d1, d2;
+ __asm__ __volatile__( \
+ "cld\n\t" \
+ "rep ; movsl" \
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2) \
+ : "0" (1024),"1" ((long) to),"2" ((long) from) \
+ : "memory");
+}
+
+
+void mmx_copy_page(void *to, void *from)
+{
+ if(in_interrupt())
+ slow_copy_page(to, from);
+ else
+ fast_copy_page(to, from);
+}
--- /dev/null
+/*
+ * FIXME: old compatibility stuff, will be removed soon.
+ */
+
+#include <net/checksum.h>
+
+unsigned int csum_partial_copy( const char *src, char *dst, int len, int sum)
+{
+ int src_err=0, dst_err=0;
+
+ sum = csum_partial_copy_generic ( src, dst, len, sum, &src_err, &dst_err);
+
+ if (src_err || dst_err)
+ printk("old csum_partial_copy_fromuser(), tell mingo to convert me.\n");
+
+ return sum;
+}
+
+
--- /dev/null
+#include <linux/string.h>
+
+char * strstr(const char * cs,const char * ct)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movl %6,%%edi\n\t"
+ "repne\n\t"
+ "scasb\n\t"
+ "notl %%ecx\n\t"
+ "decl %%ecx\n\t" /* NOTE! This also sets Z if searchstring='' */
+ "movl %%ecx,%%edx\n"
+ "1:\tmovl %6,%%edi\n\t"
+ "movl %%esi,%%eax\n\t"
+ "movl %%edx,%%ecx\n\t"
+ "repe\n\t"
+ "cmpsb\n\t"
+ "je 2f\n\t" /* also works for empty string, see above */
+ "xchgl %%eax,%%esi\n\t"
+ "incl %%esi\n\t"
+ "cmpb $0,-1(%%eax)\n\t"
+ "jne 1b\n\t"
+ "xorl %%eax,%%eax\n\t"
+ "2:"
+ :"=a" (__res), "=&c" (d0), "=&S" (d1)
+ :"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
+ :"dx", "di");
+return __res;
+}
+
--- /dev/null
+/*
+ * User address space access functions.
+ * The non inlined parts of asm-i386/uaccess.h are here.
+ *
+ * Copyright 1997 Andi Kleen <ak@muc.de>
+ * Copyright 1997 Linus Torvalds
+ */
+#include <linux/config.h>
+#include <asm/uaccess.h>
+#include <asm/mmx.h>
+
+#ifdef CONFIG_X86_USE_3DNOW_AND_WORKS
+
+unsigned long
+__generic_copy_to_user(void *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_WRITE, to, n))
+ {
+ if(n<512)
+ __copy_user(to,from,n);
+ else
+ mmx_copy_user(to,from,n);
+ }
+ return n;
+}
+
+unsigned long
+__generic_copy_from_user(void *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_READ, from, n))
+ {
+ if(n<512)
+ __copy_user_zeroing(to,from,n);
+ else
+ mmx_copy_user_zeroing(to, from, n);
+ }
+ else
+ memset(to, 0, n);
+ return n;
+}
+
+#else
+
+unsigned long
+__generic_copy_to_user(void *to, const void *from, unsigned long n)
+{
+ prefetch(from);
+ if (access_ok(VERIFY_WRITE, to, n))
+ __copy_user(to,from,n);
+ return n;
+}
+
+unsigned long
+__generic_copy_from_user(void *to, const void *from, unsigned long n)
+{
+ prefetchw(to);
+ if (access_ok(VERIFY_READ, from, n))
+ __copy_user_zeroing(to,from,n);
+ else
+ memset(to, 0, n);
+ return n;
+}
+
+#endif
+
+/*
+ * Copy a null terminated string from userspace.
+ */
+
+#define __do_strncpy_from_user(dst,src,count,res) \
+do { \
+ int __d0, __d1, __d2; \
+ __asm__ __volatile__( \
+ " testl %1,%1\n" \
+ " jz 2f\n" \
+ "0: lodsb\n" \
+ " stosb\n" \
+ " testb %%al,%%al\n" \
+ " jz 1f\n" \
+ " decl %1\n" \
+ " jnz 0b\n" \
+ "1: subl %1,%0\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl %5,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ ".previous" \
+ : "=d"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1), \
+ "=&D" (__d2) \
+ : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
+ : "memory"); \
+} while (0)
+
+long
+__strncpy_from_user(char *dst, const char *src, long count)
+{
+ long res;
+ __do_strncpy_from_user(dst, src, count, res);
+ return res;
+}
+
+long
+strncpy_from_user(char *dst, const char *src, long count)
+{
+ long res = -EFAULT;
+ if (access_ok(VERIFY_READ, src, 1))
+ __do_strncpy_from_user(dst, src, count, res);
+ return res;
+}
+
+
+/*
+ * Zero Userspace
+ */
+
+#define __do_clear_user(addr,size) \
+do { \
+ int __d0; \
+ __asm__ __volatile__( \
+ "0: rep; stosl\n" \
+ " movl %2,%0\n" \
+ "1: rep; stosb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: lea 0(%2,%0,4),%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,2b\n" \
+ ".previous" \
+ : "=&c"(size), "=&D" (__d0) \
+ : "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
+} while (0)
+
+unsigned long
+clear_user(void *to, unsigned long n)
+{
+ if (access_ok(VERIFY_WRITE, to, n))
+ __do_clear_user(to, n);
+ return n;
+}
+
+unsigned long
+__clear_user(void *to, unsigned long n)
+{
+ __do_clear_user(to, n);
+ return n;
+}
+
+/*
+ * Return the size of a string (including the ending 0)
+ *
+ * Return 0 on exception, a value greater than N if too long
+ */
+
+long strnlen_user(const char *s, long n)
+{
+ unsigned long mask = -__addr_ok(s);
+ unsigned long res, tmp;
+
+ __asm__ __volatile__(
+ " testl %0, %0\n"
+ " jz 3f\n"
+ " andl %0,%%ecx\n"
+ "0: repne; scasb\n"
+ " setne %%al\n"
+ " subl %%ecx,%0\n"
+ " addl %0,%%eax\n"
+ "1:\n"
+ ".section .fixup,\"ax\"\n"
+ "2: xorl %%eax,%%eax\n"
+ " jmp 1b\n"
+ "3: movb $1,%%al\n"
+ " jmp 1b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 0b,2b\n"
+ ".previous"
+ :"=r" (n), "=D" (s), "=a" (res), "=c" (tmp)
+ :"0" (n), "1" (s), "2" (0), "3" (mask)
+ :"cc");
+ return res & mask;
+}
--- /dev/null
+#
+# Makefile for the linux i386-specific parts of the memory manager.
+#
+# Note! Dependencies are done automagically by 'make dep', which also
+# removes any old dependencies. DON'T put your own dependencies here
+# unless it's something special (ie not a .c file).
+#
+# Note 2! The CFLAGS definition is now in the main makefile...
+
+O_TARGET := mm.o
+
+obj-y := init.o fault.o extable.o pageattr.o hypervisor.o get_unmapped_area.o mmu_context.o
+
+export-objs := pageattr.o
+
+include $(TOPDIR)/Rules.make
--- /dev/null
+/*
+ * linux/arch/i386/mm/extable.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <asm/uaccess.h>
+
+extern const struct exception_table_entry __start___ex_table[];
+extern const struct exception_table_entry __stop___ex_table[];
+
+static inline unsigned long
+search_one_table(const struct exception_table_entry *first,
+ const struct exception_table_entry *last,
+ unsigned long value)
+{
+ while (first <= last) {
+ const struct exception_table_entry *mid;
+ long diff;
+
+ mid = (last - first) / 2 + first;
+ diff = mid->insn - value;
+ if (diff == 0)
+ return mid->fixup;
+ else if (diff < 0)
+ first = mid+1;
+ else
+ last = mid-1;
+ }
+ return 0;
+}
+
+extern spinlock_t modlist_lock;
+
+unsigned long
+search_exception_table(unsigned long addr)
+{
+ unsigned long ret = 0;
+
+#ifndef CONFIG_MODULES
+ /* There is only the kernel to search. */
+ ret = search_one_table(__start___ex_table, __stop___ex_table-1, addr);
+ return ret;
+#else
+ unsigned long flags;
+ /* The kernel is the last "module" -- no need to treat it special. */
+ struct module *mp;
+
+ spin_lock_irqsave(&modlist_lock, flags);
+ for (mp = module_list; mp != NULL; mp = mp->next) {
+ if (mp->ex_table_start == NULL || !(mp->flags&(MOD_RUNNING|MOD_INITIALIZING)))
+ continue;
+ ret = search_one_table(mp->ex_table_start,
+ mp->ex_table_end - 1, addr);
+ if (ret)
+ break;
+ }
+ spin_unlock_irqrestore(&modlist_lock, flags);
+ return ret;
+#endif
+}
--- /dev/null
+/*
+ * linux/arch/i386/mm/fault.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h> /* For unblank_screen() */
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/hardirq.h>
+
+extern void die(const char *,struct pt_regs *,long);
+
+pgd_t *cur_pgd;
+
+/*
+ * Ugly, ugly, but the goto's result in better assembly..
+ */
+int __verify_write(const void * addr, unsigned long size)
+{
+ struct vm_area_struct * vma;
+ unsigned long start = (unsigned long) addr;
+
+ if (!size)
+ return 1;
+
+ vma = find_vma(current->mm, start);
+ if (!vma)
+ goto bad_area;
+ if (vma->vm_start > start)
+ goto check_stack;
+
+good_area:
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ size--;
+ size += start & ~PAGE_MASK;
+ size >>= PAGE_SHIFT;
+ start &= PAGE_MASK;
+
+ for (;;) {
+ survive:
+ {
+ int fault = handle_mm_fault(current->mm, vma, start, 1);
+ if (!fault)
+ goto bad_area;
+ if (fault < 0)
+ goto out_of_memory;
+ }
+ if (!size)
+ break;
+ size--;
+ start += PAGE_SIZE;
+ if (start < vma->vm_end)
+ continue;
+ vma = vma->vm_next;
+ if (!vma || vma->vm_start != start)
+ goto bad_area;
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;;
+ }
+ return 1;
+
+check_stack:
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (expand_stack(vma, start) == 0)
+ goto good_area;
+
+bad_area:
+ return 0;
+
+out_of_memory:
+ if (current->pid == 1) {
+ yield();
+ goto survive;
+ }
+ goto bad_area;
+}
+
+extern spinlock_t timerlist_lock;
+
+/*
+ * Unlock any spinlocks which will prevent us from getting the
+ * message out (timerlist_lock is acquired through the
+ * console unblank code)
+ */
+void bust_spinlocks(int yes)
+{
+ spin_lock_init(&timerlist_lock);
+ if (yes) {
+ oops_in_progress = 1;
+ } else {
+ int loglevel_save = console_loglevel;
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ oops_in_progress = 0;
+ /*
+ * OK, the message is on the console. Now we call printk()
+ * without oops_in_progress set so that printk will give klogd
+ * a poke. Hold onto your hats...
+ */
+ console_loglevel = 15; /* NMI oopser may have shut the console up */
+ printk(" ");
+ console_loglevel = loglevel_save;
+ }
+}
+
+/*
+ * This routine handles page faults. It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ *
+ * error_code:
+ * bit 0 == 0 means no page found, 1 means protection fault
+ * bit 1 == 0 means read, 1 means write
+ * bit 2 == 0 means kernel, 1 means user-mode
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs,
+ unsigned long error_code,
+ unsigned long address)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ unsigned long page;
+ unsigned long fixup;
+ int write;
+ siginfo_t info;
+
+ /* Set the "privileged fault" bit to something sane. */
+ error_code &= 3;
+ error_code |= (regs->xcs & 2) << 1;
+
+#if PT_UPDATE_DEBUG > 0
+ if ( (error_code == 0) && (address >= TASK_SIZE) )
+ {
+ unsigned long paddr = __pa(address);
+ int i;
+ for ( i = 0; i < pt_update_queue_idx; i++ )
+ {
+ if ( update_debug_queue[i].ptr == paddr )
+ {
+ printk("XXX now(EIP=%08lx:ptr=%08lx) "
+ "then(%s/%d:p/v=%08lx/%08lx)\n",
+ regs->eip, address,
+ update_debug_queue[i].file,
+ update_debug_queue[i].line,
+ update_debug_queue[i].ptr,
+ update_debug_queue[i].val);
+ }
+ }
+ }
+#endif
+
+ if ( flush_page_update_queue() != 0 ) return;
+
+ /*
+ * We fault-in kernel-space virtual memory on-demand. The
+ * 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ *
+ * This verifies that the fault happens in kernel space
+ * (error_code & 4) == 0, and that the fault was not a
+ * protection error (error_code & 1) == 0.
+ */
+ if (address >= TASK_SIZE && !(error_code & 5))
+ goto vmalloc_fault;
+
+ mm = tsk->mm;
+ info.si_code = SEGV_MAPERR;
+
+ /*
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+ if (in_interrupt() || !mm)
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+
+ vma = find_vma(mm, address);
+ if (!vma)
+ goto bad_area;
+ if (vma->vm_start <= address)
+ goto good_area;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (error_code & 4) {
+ /*
+ * accessing the stack below %esp is always a bug.
+ * The "+ 32" is there due to some instructions (like
+ * pusha) doing post-decrement on the stack and that
+ * doesn't show up until later..
+ */
+ if (address + 32 < regs->esp)
+ goto bad_area;
+ }
+ if (expand_stack(vma, address))
+ goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+ info.si_code = SEGV_ACCERR;
+ write = 0;
+ switch (error_code & 3) {
+ default: /* 3: write, present */
+ /* fall through */
+ case 2: /* write, not present */
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ write++;
+ break;
+ case 1: /* read, present */
+ goto bad_area;
+ case 0: /* read, not present */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto bad_area;
+ }
+
+ survive:
+ /*
+ * If for any reason at all we couldn't handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ switch (handle_mm_fault(mm, vma, address, write)) {
+ case 1:
+ tsk->min_flt++;
+ break;
+ case 2:
+ tsk->maj_flt++;
+ break;
+ case 0:
+ goto do_sigbus;
+ default:
+ goto out_of_memory;
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & 4) {
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ /* info.si_code has been set above */
+ info.si_addr = (void *)address;
+ force_sig_info(SIGSEGV, &info, tsk);
+ return;
+ }
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if ((fixup = search_exception_table(regs->eip)) != 0) {
+ regs->eip = fixup;
+ return;
+ }
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+ bust_spinlocks(1);
+
+ if (address < PAGE_SIZE)
+ printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
+ else
+ printk(KERN_ALERT "Unable to handle kernel paging request");
+ printk(" at virtual address %08lx\n",address);
+ printk(" printing eip:\n");
+ printk("%08lx\n", regs->eip);
+ page = ((unsigned long *) cur_pgd)[address >> 22];
+ printk(KERN_ALERT "*pde=%08lx(%08lx)\n", page, machine_to_phys(page));
+ if (page & 1) {
+ page &= PAGE_MASK;
+ address &= 0x003ff000;
+ page = machine_to_phys(page);
+ page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
+ printk(KERN_ALERT "*pte=%08lx(%08lx)\n", page,
+ machine_to_phys(page));
+ }
+ die("Oops", regs, error_code);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+ if (tsk->pid == 1) {
+ yield();
+ goto survive;
+ }
+ up_read(&mm->mmap_sem);
+ printk("VM: killing process %s\n", tsk->comm);
+ if (error_code & 4)
+ do_exit(SIGKILL);
+ goto no_context;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+
+ /*
+ * Send a sigbus, regardless of whether we were in kernel
+ * or user mode.
+ */
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void *)address;
+ force_sig_info(SIGBUS, &info, tsk);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & 4))
+ goto no_context;
+ return;
+
+vmalloc_fault:
+ {
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk" here. We might be inside
+ * an interrupt in the middle of a task switch..
+ */
+ int offset = __pgd_offset(address);
+ pgd_t *pgd, *pgd_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+
+ pgd = offset + cur_pgd;
+ pgd_k = init_mm.pgd + offset;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
+ pmd = pmd_offset(pgd, address);
+ pmd_k = pmd_offset(pgd_k, address);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+ XENO_flush_page_update_queue(); /* flush PMD update */
+
+ pte_k = pte_offset(pmd_k, address);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
--- /dev/null
+
+#include <linux/slab.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/swapctl.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/personality.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+
+/*
+static int direct_mapped(unsigned long addr)
+{
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if(node->addr == addr)
+ break;
+ curr = curr->next;
+ }
+
+ if(curr == direct_list)
+ return 0;
+
+ return 1;
+}
+*/
+/*
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct vm_area_struct *vma;
+
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(current->mm, addr);
+ if (TASK_SIZE - len >= addr &&
+ (!vma || addr + len <= vma->vm_start))
+ return addr;
+ }
+ addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);
+
+ for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
+ if (TASK_SIZE - len < addr)
+ return -ENOMEM;
+
+ if ((!vma || addr + len <= vma->vm_start) && !direct_mapped(addr))
+ return addr;
+
+ addr = vma->vm_end;
+ }
+}
+*/
+struct list_head *find_direct(struct list_head *list, unsigned long addr)
+{
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+ direct_mmap_node_t * node;
+
+ for ( curr = direct_list->next; curr != direct_list; curr = curr->next )
+ {
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if ( node->vm_start >= addr ) break;
+ }
+
+ return curr;
+}
+
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long
+addr, unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct vm_area_struct *vma;
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = ¤t->mm->context.direct_list;
+
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ if ( addr )
+ {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(current->mm, addr);
+ curr = find_direct(direct_list, addr);
+ node = list_entry(curr, direct_mmap_node_t, list);
+ if ( (TASK_SIZE - len >= addr) &&
+ (!vma || addr + len <= vma->vm_start) &&
+ ((curr == direct_list) || addr + len <= node->vm_start) )
+ return addr;
+ }
+
+ addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);
+
+
+ /* Find first VMA and direct_map nodes with vm_start > addr */
+ vma = find_vma(current->mm, addr);
+ curr = find_direct(direct_list, addr);
+ node = list_entry(curr, direct_mmap_node_t, list);
+
+ for ( ; ; )
+ {
+ if ( TASK_SIZE - len < addr ) return -ENOMEM;
+
+ if ( vma && ((curr == direct_list) || (vma->vm_start < node->vm_start)))
+ {
+ /* Do we fit before VMA node? */
+ if ( addr + len <= vma->vm_start ) return addr;
+ addr = vma->vm_end;
+ vma = vma->vm_next;
+ }
+ else if ( curr != direct_list )
+ {
+ /* Do we fit before direct_map node? */
+ if ( addr + len <= node->vm_start) return addr;
+ addr = node->vm_end;
+ curr = curr->next;
+ node = list_entry(curr, direct_mmap_node_t, list);
+ }
+ else
+ {
+ /* !vma && curr == direct_list */
+ return addr;
+ }
+ }
+}
--- /dev/null
+/******************************************************************************
+ * xeno/mm/hypervisor.c
+ *
+ * Update page tables via the hypervisor.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/hypervisor.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+#define QUEUE_SIZE 2048
+static page_update_request_t update_queue[QUEUE_SIZE];
+unsigned int pt_update_queue_idx = 0;
+#define idx pt_update_queue_idx
+
+#if PT_UPDATE_DEBUG > 0
+page_update_debug_t update_debug_queue[QUEUE_SIZE] = {{0}};
+#undef queue_l1_entry_update
+#undef queue_l2_entry_update
+static void DEBUG_allow_pt_reads(void)
+{
+ pte_t *pte;
+ page_update_request_t update;
+ int i;
+ for ( i = idx-1; i >= 0; i-- )
+ {
+ pte = update_debug_queue[i].ptep;
+ if ( pte == NULL ) continue;
+ update_debug_queue[i].ptep = NULL;
+ update.ptr = phys_to_machine(__pa(pte));
+ update.val = update_debug_queue[i].pteval;
+ HYPERVISOR_pt_update(&update, 1);
+ }
+}
+static void DEBUG_disallow_pt_read(unsigned long pa)
+{
+ pte_t *pte;
+ pmd_t *pmd;
+ pgd_t *pgd;
+ unsigned long pteval;
+ /*
+ * We may fault because of an already outstanding update.
+ * That's okay -- it'll get fixed up in the fault handler.
+ */
+ page_update_request_t update;
+ unsigned long va = (unsigned long)__va(pa);
+ pgd = pgd_offset_k(va);
+ pmd = pmd_offset(pgd, va);
+ pte = pte_offset(pmd, va);
+ update.ptr = phys_to_machine(__pa(pte));
+ pteval = *(unsigned long *)pte;
+ update.val = pteval & ~_PAGE_PRESENT;
+ HYPERVISOR_pt_update(&update, 1);
+ update_debug_queue[idx].ptep = pte;
+ update_debug_queue[idx].pteval = pteval;
+}
+#endif
+
+#if PT_UPDATE_DEBUG > 1
+#undef queue_pt_switch
+#undef queue_tlb_flush
+#undef queue_invlpg
+#undef queue_pgd_pin
+#undef queue_pgd_unpin
+#undef queue_pte_pin
+#undef queue_pte_unpin
+#endif
+
+
+/*
+ * This is the current pagetable base pointer, which is updated
+ * on context switch.
+ */
+unsigned long pt_baseptr;
+
+void _flush_page_update_queue(void)
+{
+ if ( idx == 0 ) return;
+#if PT_UPDATE_DEBUG > 1
+ printk("Flushing %d entries from pt update queue\n", idx);
+#endif
+#if PT_UPDATE_DEBUG > 0
+ DEBUG_allow_pt_reads();
+#endif
+ HYPERVISOR_pt_update(update_queue, idx);
+ idx = 0;
+}
+
+static void increment_index(void)
+{
+ if ( ++idx == QUEUE_SIZE ) _flush_page_update_queue();
+}
+
+void queue_l1_entry_update(unsigned long ptr, unsigned long val)
+{
+#if PT_UPDATE_DEBUG > 0
+ DEBUG_disallow_pt_read(ptr);
+#endif
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].val = val;
+ increment_index();
+}
+
+void queue_l2_entry_update(unsigned long ptr, unsigned long val)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].val = val;
+ increment_index();
+}
+
+void queue_pt_switch(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_NEW_BASEPTR;
+ increment_index();
+}
+
+void queue_tlb_flush(void)
+{
+ update_queue[idx].ptr = PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_TLB_FLUSH;
+ increment_index();
+}
+
+void queue_invlpg(unsigned long ptr)
+{
+ update_queue[idx].ptr = PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = ptr & PAGE_MASK;
+ update_queue[idx].val |= PGEXT_INVLPG;
+ increment_index();
+}
+
+void queue_pgd_pin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_PIN_L2_TABLE;
+ increment_index();
+}
+
+void queue_pgd_unpin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_UNPIN_TABLE;
+ increment_index();
+}
+
+void queue_pte_pin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_PIN_L1_TABLE;
+ increment_index();
+}
+
+void queue_pte_unpin(unsigned long ptr)
+{
+ update_queue[idx].ptr = phys_to_machine(ptr);
+ update_queue[idx].ptr |= PGREQ_EXTENDED_COMMAND;
+ update_queue[idx].val = PGEXT_UNPIN_TABLE;
+ increment_index();
+}
--- /dev/null
+/*
+ * linux/arch/i386/mm/init.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#ifdef CONFIG_BLK_DEV_INITRD
+#include <linux/blk.h>
+#endif
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/dma.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+
+mmu_gather_t mmu_gathers[NR_CPUS];
+unsigned long highstart_pfn, highend_pfn;
+static unsigned long totalram_pages;
+static unsigned long totalhigh_pages;
+
+int do_check_pgt_cache(int low, int high)
+{
+ int freed = 0;
+ if(pgtable_cache_size > high) {
+ do {
+ if (!QUICKLIST_EMPTY(pgd_quicklist)) {
+ free_pgd_slow(get_pgd_fast());
+ freed++;
+ }
+ if (!QUICKLIST_EMPTY(pte_quicklist)) {
+ pte_free_slow(pte_alloc_one_fast(NULL, 0));
+ freed++;
+ }
+ } while(pgtable_cache_size > low);
+ }
+ return freed;
+}
+
+void show_mem(void)
+{
+ int i, total = 0, reserved = 0;
+ int shared = 0, cached = 0;
+ int highmem = 0;
+
+ printk("Mem-info:\n");
+ show_free_areas();
+ printk("Free swap: %6dkB\n",nr_swap_pages<<(PAGE_SHIFT-10));
+ i = max_mapnr;
+ while (i-- > 0) {
+ total++;
+ if (PageHighMem(mem_map+i))
+ highmem++;
+ if (PageReserved(mem_map+i))
+ reserved++;
+ else if (PageSwapCache(mem_map+i))
+ cached++;
+ else if (page_count(mem_map+i))
+ shared += page_count(mem_map+i) - 1;
+ }
+ printk("%d pages of RAM\n", total);
+ printk("%d pages of HIGHMEM\n",highmem);
+ printk("%d reserved pages\n",reserved);
+ printk("%d pages shared\n",shared);
+ printk("%d pages swap cached\n",cached);
+ printk("%ld pages in page table cache\n",pgtable_cache_size);
+ show_buffers();
+}
+
+/* References to section boundaries */
+
+extern char _text, _etext, _edata, __bss_start, _end;
+extern char __init_begin, __init_end;
+
+static inline void set_pte_phys (unsigned long vaddr,
+ unsigned long phys, pgprot_t flags)
+{
+ pgprot_t prot;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = init_mm.pgd + __pgd_offset(vaddr);
+ if (pgd_none(*pgd)) {
+ printk("PAE BUG #00!\n");
+ return;
+ }
+ pmd = pmd_offset(pgd, vaddr);
+ if (pmd_none(*pmd)) {
+ printk("PAE BUG #01!\n");
+ return;
+ }
+ pte = pte_offset(pmd, vaddr);
+#if 0 // XXX Xen ?????
+ /* <phys,flags> stored as-is, to permit clearing entries */
+ set_pte(pte, mk_pte_phys(phys, flags));
+#endif
+ if (pte_val(*pte))
+ pte_ERROR(*pte);
+
+ pgprot_val(prot) = pgprot_val(PAGE_KERNEL) | pgprot_val(flags);
+
+ /* We queue directly, avoiding hidden phys->machine translation. */
+ queue_l1_entry_update(__pa(pte), phys | pgprot_val(prot));
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+void __set_fixmap (enum fixed_addresses idx, unsigned long phys,
+ pgprot_t flags)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ printk("Invalid __set_fixmap\n");
+ return;
+ }
+ set_pte_phys(address, phys, flags);
+}
+
+static void __init fixrange_init (unsigned long start,
+ unsigned long end, pgd_t *pgd_base)
+{
+ pgd_t *pgd, *kpgd;
+ pmd_t *pmd, *kpmd;
+ pte_t *pte, *kpte;
+ int i, j;
+ unsigned long vaddr;
+
+ vaddr = start;
+ i = __pgd_offset(vaddr);
+ j = __pmd_offset(vaddr);
+ pgd = pgd_base + i;
+
+ for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
+#if CONFIG_X86_PAE
+ if (pgd_none(*pgd)) {
+ pmd = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ set_pgd(pgd, __pgd(__pa(pmd) + 0x1));
+ if (pmd != pmd_offset(pgd, 0))
+ printk("PAE BUG #02!\n");
+ }
+ pmd = pmd_offset(pgd, vaddr);
+#else
+ pmd = (pmd_t *)pgd;
+#endif
+ for (; (j < PTRS_PER_PMD) && (vaddr != end); pmd++, j++) {
+ if (pmd_none(*pmd)) {
+ pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ clear_page(pte);
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ queue_l1_entry_update(__pa(kpte),
+ (*(unsigned long *)kpte)&~_PAGE_RW);
+
+ set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
+
+ // XXX Xen below reqd ?
+ //if (pte != pte_offset(pmd, 0))
+ // BUG();
+ }
+ vaddr += PMD_SIZE;
+ }
+ j = 0;
+ }
+
+ XENO_flush_page_update_queue();
+}
+
+
+static void __init zone_sizes_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+ unsigned int max_dma, high, low;
+
+ max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+ low = max_low_pfn;
+ high = highend_pfn;
+
+ if (low < max_dma)
+ zones_size[ZONE_DMA] = low;
+ else {
+ zones_size[ZONE_DMA] = max_dma;
+ zones_size[ZONE_NORMAL] = low - max_dma;
+#ifdef CONFIG_HIGHMEM
+ zones_size[ZONE_HIGHMEM] = high - low;
+#endif
+ }
+ free_area_init(zones_size);
+}
+
+/*
+ * paging_init() sets up the page tables - note that the first 8MB are
+ * already mapped by head.S.
+ *
+ * This routines also unmaps the page at virtual kernel address 0, so
+ * that we can trap those pesky NULL-reference errors in the kernel.
+ */
+void __init paging_init(void)
+{
+ unsigned long vaddr;
+
+ zone_sizes_init();
+
+ /*
+ * Fixed mappings, only the page table structure has to be created -
+ * mappings will be set by set_fixmap():
+ */
+ vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+ fixrange_init(vaddr, HYPERVISOR_VIRT_START, init_mm.pgd);
+
+ /*
+ * XXX We do this conversion early, so that all other page tables
+ * will automatically get this mapping.
+ */
+ set_fixmap(FIX_BLKRING_BASE, start_info.blk_ring);
+
+#ifdef CONFIG_HIGHMEM
+#error
+ kmap_init();
+#endif
+}
+
+static inline int page_is_ram (unsigned long pagenr)
+{
+ return 1;
+}
+
+#ifdef CONFIG_HIGHMEM
+void __init one_highpage_init(struct page *page, int pfn, int bad_ppro)
+{
+ if (!page_is_ram(pfn)) {
+ SetPageReserved(page);
+ return;
+ }
+
+ if (bad_ppro && page_kills_ppro(pfn)) {
+ SetPageReserved(page);
+ return;
+ }
+
+ ClearPageReserved(page);
+ set_bit(PG_highmem, &page->flags);
+ atomic_set(&page->count, 1);
+ __free_page(page);
+ totalhigh_pages++;
+}
+#endif /* CONFIG_HIGHMEM */
+
+static void __init set_max_mapnr_init(void)
+{
+#ifdef CONFIG_HIGHMEM
+ highmem_start_page = mem_map + highstart_pfn;
+ max_mapnr = num_physpages = highend_pfn;
+ num_mappedpages = max_low_pfn;
+#else
+ max_mapnr = num_mappedpages = num_physpages = max_low_pfn;
+#endif
+}
+
+static int __init free_pages_init(void)
+{
+ int bad_ppro, reservedpages, pfn;
+
+ /* this will put all low memory onto the freelists */
+ totalram_pages += free_all_bootmem();
+
+ reservedpages = 0;
+ for (pfn = 0; pfn < max_low_pfn; pfn++) {
+ /*
+ * Only count reserved RAM pages
+ */
+ if (page_is_ram(pfn) && PageReserved(mem_map+pfn))
+ reservedpages++;
+ }
+#ifdef CONFIG_HIGHMEM
+ for (pfn = highend_pfn-1; pfn >= highstart_pfn; pfn--)
+ one_highpage_init((struct page *) (mem_map + pfn), pfn, bad_ppro);
+ totalram_pages += totalhigh_pages;
+#endif
+ return reservedpages;
+}
+
+void __init mem_init(void)
+{
+ int codesize, reservedpages, datasize, initsize;
+
+ if (!mem_map)
+ BUG();
+
+ set_max_mapnr_init();
+
+ high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+
+ /* clear the zero-page */
+ memset(empty_zero_page, 0, PAGE_SIZE);
+
+ reservedpages = free_pages_init();
+
+ codesize = (unsigned long) &_etext - (unsigned long) &_text;
+ datasize = (unsigned long) &_edata - (unsigned long) &_etext;
+ initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
+
+ printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n",
+ (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+ max_mapnr << (PAGE_SHIFT-10),
+ codesize >> 10,
+ reservedpages << (PAGE_SHIFT-10),
+ datasize >> 10,
+ initsize >> 10,
+ (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
+ );
+
+ boot_cpu_data.wp_works_ok = 1;
+}
+
+void free_initmem(void)
+{
+ unsigned long addr;
+
+ addr = (unsigned long)(&__init_begin);
+ for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(addr));
+ set_page_count(virt_to_page(addr), 1);
+ free_page(addr);
+ totalram_pages++;
+ }
+ printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n", (&__init_end - &__init_begin) >> 10);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+ if (start < end)
+ printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+ for (; start < end; start += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(start));
+ set_page_count(virt_to_page(start), 1);
+ free_page(start);
+ totalram_pages++;
+ }
+}
+#endif
+
+void si_meminfo(struct sysinfo *val)
+{
+ val->totalram = totalram_pages;
+ val->sharedram = 0;
+ val->freeram = nr_free_pages();
+ val->bufferram = atomic_read(&buffermem_pages);
+ val->totalhigh = totalhigh_pages;
+ val->freehigh = nr_free_highpages();
+ val->mem_unit = PAGE_SIZE;
+ return;
+}
+
+#if defined(CONFIG_X86_PAE)
+struct kmem_cache_s *pae_pgd_cachep;
+void __init pgtable_cache_init(void)
+{
+ /*
+ * PAE pgds must be 16-byte aligned:
+ */
+ pae_pgd_cachep = kmem_cache_create("pae_pgd", 32, 0,
+ SLAB_HWCACHE_ALIGN | SLAB_MUST_HWCACHE_ALIGN, NULL, NULL);
+ if (!pae_pgd_cachep)
+ panic("init_pae(): Cannot alloc pae_pgd SLAB cache");
+}
+#endif /* CONFIG_X86_PAE */
--- /dev/null
+
+#include <linux/slab.h>
+#include <linux/list.h>
+
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+ INIT_LIST_HEAD(&mm->context.direct_list);
+ return 0;
+}
+
+/* just free all elements of list identifying directly mapped areas */
+void destroy_context(struct mm_struct *mm)
+{
+ direct_mmap_node_t * node;
+ struct list_head * curr;
+ struct list_head * direct_list = &mm->context.direct_list;
+
+ curr = direct_list->next;
+ while(curr != direct_list){
+ node = list_entry(curr, direct_mmap_node_t, list);
+ curr = curr->next;
+ list_del(&node->list);
+ kfree(node);
+ }
+
+}
--- /dev/null
+/*
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ * Thanks to Ben LaHaise for precious feedback.
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+
+/* Should move most of this stuff into the appropiate includes */
+#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
+#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
+
+static inline pte_t *lookup_address(unsigned long address)
+{
+ pmd_t *pmd;
+ pgd_t *pgd = pgd_offset(&init_mm, address);
+
+ if (pgd_none(*pgd))
+ return NULL;
+ if (pgd_val(*pgd) & _PAGE_PSE)
+ return (pte_t *)pgd;
+ pmd = pmd_offset(pgd, address);
+ if (pmd_none(*pmd))
+ return NULL;
+ if (pmd_val(*pmd) & _PAGE_PSE)
+ return (pte_t *)pmd;
+ return pte_offset(pmd, address);
+}
+
+static struct page *split_large_page(unsigned long address, pgprot_t prot)
+{
+ int i;
+ unsigned long addr;
+ struct page *base = alloc_pages(GFP_KERNEL, 0);
+ pte_t *pbase;
+ if (!base)
+ return NULL;
+ address = __pa(address);
+ addr = address & LARGE_PAGE_MASK;
+ pbase = (pte_t *)page_address(base);
+ for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
+ pbase[i] = mk_pte_phys(addr,
+ addr == address ? prot : PAGE_KERNEL);
+ }
+ return base;
+}
+
+static void flush_kernel_map(void * address)
+{
+ if (!test_bit(X86_FEATURE_SELFSNOOP, boot_cpu_data.x86_capability)) {
+ /* Could use CLFLUSH here if the CPU supports it (Hammer,P4) */
+ if (boot_cpu_data.x86_model >= 4)
+ asm volatile("wbinvd":::"memory");
+ }
+
+ /* Do global flush here to work around large page flushing errata
+ in some early Athlons */
+ __flush_tlb_all();
+}
+
+static void set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
+{
+ set_pte_atomic(kpte, pte); /* change init_mm */
+#ifndef CONFIG_X86_PAE
+ {
+ struct list_head *l;
+ spin_lock(&mmlist_lock);
+ list_for_each(l, &init_mm.mmlist) {
+ struct mm_struct *mm = list_entry(l, struct mm_struct, mmlist);
+ pmd_t *pmd = pmd_offset(pgd_offset(mm, address), address);
+ set_pte_atomic((pte_t *)pmd, pte);
+ }
+ spin_unlock(&mmlist_lock);
+ }
+#endif
+}
+
+/* no more special protections in this 2/4MB area - revert to a
+ large page again. */
+static inline void revert_page(struct page *kpte_page, unsigned long address)
+{
+ pte_t *linear = (pte_t *)
+ pmd_offset(pgd_offset(&init_mm, address), address);
+ set_pmd_pte(linear, address,
+ mk_pte_phys(__pa(address & LARGE_PAGE_MASK),
+ MAKE_GLOBAL(_KERNPG_TABLE|_PAGE_PSE)));
+}
+
+/*
+ * Change the page attributes of an page in the linear mapping.
+ *
+ * This should be used when a page is mapped with a different caching policy
+ * than write-back somewhere - some CPUs do not like it when mappings with
+ * different caching policies exist. This changes the page attributes of the
+ * in kernel linear mapping too.
+ *
+ * The caller needs to ensure that there are no conflicting mappings elsewhere.
+ * This function only deals with the kernel linear map.
+ * When page is in highmem it must never be kmap'ed.
+ */
+static int
+__change_page_attr(struct page *page, pgprot_t prot, struct page **oldpage)
+{
+ pte_t *kpte;
+ unsigned long address;
+ struct page *kpte_page;
+
+#ifdef CONFIG_HIGHMEM
+ if (page >= highmem_start_page)
+ BUG();
+#endif
+ address = (unsigned long)page_address(page);
+ kpte = lookup_address(address);
+ if (!kpte)
+ return -EINVAL;
+ kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK);
+ if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) {
+ if ((pte_val(*kpte) & _PAGE_PSE) == 0) {
+ pte_t old = *kpte;
+ pte_t standard = mk_pte(page, PAGE_KERNEL);
+
+ set_pte_atomic(kpte, mk_pte(page, prot));
+ if (pte_same(old,standard))
+ atomic_inc(&kpte_page->count);
+ } else {
+ struct page *split = split_large_page(address, prot);
+ if (!split)
+ return -ENOMEM;
+ atomic_inc(&kpte_page->count);
+ set_pmd_pte(kpte,address,mk_pte(split, PAGE_KERNEL));
+ }
+ } else if ((pte_val(*kpte) & _PAGE_PSE) == 0) {
+ set_pte_atomic(kpte, mk_pte(page, PAGE_KERNEL));
+ atomic_dec(&kpte_page->count);
+ }
+
+ if (cpu_has_pse && (atomic_read(&kpte_page->count) == 1)) {
+ *oldpage = kpte_page;
+ revert_page(kpte_page, address);
+ }
+ return 0;
+}
+
+int change_page_attr(struct page *page, int numpages, pgprot_t prot)
+{
+ int err = 0;
+ struct page *fpage;
+ int i;
+
+ down_write(&init_mm.mmap_sem);
+ for (i = 0; i < numpages; i++, page++) {
+ fpage = NULL;
+ err = __change_page_attr(page, prot, &fpage);
+ if (err)
+ break;
+ if (fpage || i == numpages-1) {
+ void *address = page_address(page);
+#ifdef CONFIG_SMP
+ smp_call_function(flush_kernel_map, address, 1, 1);
+#endif
+ flush_kernel_map(address);
+ if (fpage)
+ __free_page(fpage);
+ }
+ }
+ up_write(&init_mm.mmap_sem);
+ return err;
+}
+
+EXPORT_SYMBOL(change_page_attr);
--- /dev/null
+/* ld script to make i386 Linux kernel
+ * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
+ */
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+ENTRY(_start)
+SECTIONS
+{
+ . = 0xC0000000 + 0x000000;
+ _text = .; /* Text and read-only data */
+ .text : {
+ *(.text)
+ *(.fixup)
+ *(.gnu.warning)
+ } = 0x9090
+
+ _etext = .; /* End of text section */
+
+ .rodata : { *(.rodata) *(.rodata.*) }
+ .kstrtab : { *(.kstrtab) }
+
+ . = ALIGN(16); /* Exception table */
+ __start___ex_table = .;
+ __ex_table : { *(__ex_table) }
+ __stop___ex_table = .;
+
+ __start___ksymtab = .; /* Kernel symbol table */
+ __ksymtab : { *(__ksymtab) }
+ __stop___ksymtab = .;
+
+ .data : { /* Data */
+ *(.data)
+ CONSTRUCTORS
+ }
+
+ _edata = .; /* End of data section */
+
+ . = ALIGN(8192); /* init_task */
+ .data.init_task : { *(.data.init_task) }
+
+ . = ALIGN(4096); /* Init code and data */
+ __init_begin = .;
+ .text.init : { *(.text.init) }
+ .data.init : { *(.data.init) }
+ . = ALIGN(16);
+ __setup_start = .;
+ .setup.init : { *(.setup.init) }
+ __setup_end = .;
+ __initcall_start = .;
+ .initcall.init : { *(.initcall.init) }
+ __initcall_end = .;
+ . = ALIGN(4096);
+ __init_end = .;
+
+ . = ALIGN(4096);
+ .data.page_aligned : { *(.data.idt) }
+
+ . = ALIGN(32);
+ .data.cacheline_aligned : { *(.data.cacheline_aligned) }
+
+ __bss_start = .; /* BSS */
+ .bss : {
+ *(.bss)
+ }
+ _end = . ;
+
+ /* Sections to be discarded */
+ /DISCARD/ : {
+ *(.text.exit)
+ *(.data.exit)
+ *(.exitcall.exit)
+ }
+
+ /* Stabs debugging sections. */
+ .stab 0 : { *(.stab) }
+ .stabstr 0 : { *(.stabstr) }
+ .stab.excl 0 : { *(.stab.excl) }
+ .stab.exclstr 0 : { *(.stab.exclstr) }
+ .stab.index 0 : { *(.stab.index) }
+ .stab.indexstr 0 : { *(.stab.indexstr) }
+ .comment 0 : { *(.comment) }
+}
--- /dev/null
+#
+# Block device driver configuration
+#
+mainmenu_option next_comment
+comment 'Block devices'
+
+tristate 'Normal floppy disk support' CONFIG_BLK_DEV_FD
+if [ "$CONFIG_AMIGA" = "y" ]; then
+ tristate 'Amiga floppy support' CONFIG_AMIGA_FLOPPY
+fi
+if [ "$CONFIG_ATARI" = "y" ]; then
+ tristate 'Atari floppy support' CONFIG_ATARI_FLOPPY
+fi
+if [ "$CONFIG_MAC" = "y" ]; then
+ dep_bool 'Macintosh IIfx/Quadra 900/Quadra 950 floppy support (EXPERIMENTAL)' CONFIG_BLK_DEV_SWIM_IOP $CONFIG_EXPERIMENTAL
+fi
+if [ "$CONFIG_MCA" = "y" ]; then
+ tristate 'PS/2 ESDI hard disk support' CONFIG_BLK_DEV_PS2
+fi
+if [ "$CONFIG_ZORRO" = "y" ]; then
+ tristate 'Amiga Zorro II ramdisk support' CONFIG_AMIGA_Z2RAM
+fi
+if [ "$CONFIG_ATARI" = "y" ]; then
+ tristate 'Atari ACSI support' CONFIG_ATARI_ACSI
+ if [ "$CONFIG_ATARI_ACSI" != "n" ]; then
+ comment 'Some devices (e.g. CD jukebox) support multiple LUNs'
+ bool ' Probe all LUNs on each ACSI device' CONFIG_ACSI_MULTI_LUN
+ tristate ' Atari SLM laser printer support' CONFIG_ATARI_SLM
+ fi
+fi
+dep_tristate 'XT hard disk support' CONFIG_BLK_DEV_XD $CONFIG_ISA
+dep_tristate 'Parallel port IDE device support' CONFIG_PARIDE $CONFIG_PARPORT
+if [ "$CONFIG_PARIDE" = "y" -o "$CONFIG_PARIDE" = "m" ]; then
+ source drivers/block/paride/Config.in
+fi
+dep_tristate 'Compaq SMART2 support' CONFIG_BLK_CPQ_DA $CONFIG_PCI
+dep_tristate 'Compaq Smart Array 5xxx support' CONFIG_BLK_CPQ_CISS_DA $CONFIG_PCI
+dep_mbool ' SCSI tape drive support for Smart Array 5xxx' CONFIG_CISS_SCSI_TAPE $CONFIG_BLK_CPQ_CISS_DA $CONFIG_SCSI
+dep_tristate 'Mylex DAC960/DAC1100 PCI RAID Controller support' CONFIG_BLK_DEV_DAC960 $CONFIG_PCI
+dep_tristate 'Micro Memory MM5415 Battery Backed RAM support (EXPERIMENTAL)' CONFIG_BLK_DEV_UMEM $CONFIG_PCI $CONFIG_EXPERIMENTAL
+
+tristate 'Loopback device support' CONFIG_BLK_DEV_LOOP
+dep_tristate 'Network block device support' CONFIG_BLK_DEV_NBD $CONFIG_NET
+
+tristate 'RAM disk support' CONFIG_BLK_DEV_RAM
+if [ "$CONFIG_BLK_DEV_RAM" = "y" -o "$CONFIG_BLK_DEV_RAM" = "m" ]; then
+ int ' Default RAM disk size' CONFIG_BLK_DEV_RAM_SIZE 4096
+fi
+dep_bool ' Initial RAM disk (initrd) support' CONFIG_BLK_DEV_INITRD $CONFIG_BLK_DEV_RAM
+
+bool 'Per partition statistics in /proc/partitions' CONFIG_BLK_STATS
+
+bool 'XenoLinux virtual block device support' CONFIG_XENOLINUX_BLOCK
+
+endmenu
--- /dev/null
+/*
+ * linux/drivers/block/ll_rw_blk.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 1994, Karl Keyte: Added support for disk statistics
+ * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
+ * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> - July2000
+ */
+
+/*
+ * This handles all read/write requests to block devices
+ */
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/config.h>
+#include <linux/locks.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/init.h>
+#include <linux/smp_lock.h>
+#include <linux/completion.h>
+#include <linux/bootmem.h>
+
+#include <asm/system.h>
+#include <asm/io.h>
+#include <linux/blk.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+/*
+ * MAC Floppy IWM hooks
+ */
+
+#ifdef CONFIG_MAC_FLOPPY_IWM
+extern int mac_floppy_init(void);
+#endif
+
+/*
+ * For the allocated request tables
+ */
+static kmem_cache_t *request_cachep;
+
+/*
+ * The "disk" task queue is used to start the actual requests
+ * after a plug
+ */
+DECLARE_TASK_QUEUE(tq_disk);
+
+/*
+ * Protect the request list against multiple users..
+ *
+ * With this spinlock the Linux block IO subsystem is 100% SMP threaded
+ * from the IRQ event side, and almost 100% SMP threaded from the syscall
+ * side (we still have protect against block device array operations, and
+ * the do_request() side is casually still unsafe. The kernel lock protects
+ * this part currently.).
+ *
+ * there is a fair chance that things will work just OK if these functions
+ * are called with no global kernel lock held ...
+ */
+spinlock_t io_request_lock = SPIN_LOCK_UNLOCKED;
+
+/* This specifies how many sectors to read ahead on the disk. */
+
+int read_ahead[MAX_BLKDEV];
+
+/* blk_dev_struct is:
+ * *request_fn
+ * *current_request
+ */
+struct blk_dev_struct blk_dev[MAX_BLKDEV]; /* initialized by blk_dev_init() */
+
+/*
+ * blk_size contains the size of all block-devices in units of 1024 byte
+ * sectors:
+ *
+ * blk_size[MAJOR][MINOR]
+ *
+ * if (!blk_size[MAJOR]) then no minor size checking is done.
+ */
+int * blk_size[MAX_BLKDEV];
+
+/*
+ * blksize_size contains the size of all block-devices:
+ *
+ * blksize_size[MAJOR][MINOR]
+ *
+ * if (!blksize_size[MAJOR]) then 1024 bytes is assumed.
+ */
+int * blksize_size[MAX_BLKDEV];
+
+/*
+ * hardsect_size contains the size of the hardware sector of a device.
+ *
+ * hardsect_size[MAJOR][MINOR]
+ *
+ * if (!hardsect_size[MAJOR])
+ * then 512 bytes is assumed.
+ * else
+ * sector_size is hardsect_size[MAJOR][MINOR]
+ * This is currently set by some scsi devices and read by the msdos fs driver.
+ * Other uses may appear later.
+ */
+int * hardsect_size[MAX_BLKDEV];
+
+/*
+ * The following tunes the read-ahead algorithm in mm/filemap.c
+ */
+int * max_readahead[MAX_BLKDEV];
+
+/*
+ * Max number of sectors per request
+ */
+int * max_sectors[MAX_BLKDEV];
+
+unsigned long blk_max_low_pfn, blk_max_pfn;
+int blk_nohighio = 0;
+
+static inline int get_max_sectors(kdev_t dev)
+{
+ if (!max_sectors[MAJOR(dev)])
+ return MAX_SECTORS;
+ return max_sectors[MAJOR(dev)][MINOR(dev)];
+}
+
+inline request_queue_t *blk_get_queue(kdev_t dev)
+{
+ struct blk_dev_struct *bdev = blk_dev + MAJOR(dev);
+
+ if (bdev->queue)
+ return bdev->queue(dev);
+ else
+ return &blk_dev[MAJOR(dev)].request_queue;
+}
+
+static int __blk_cleanup_queue(struct request_list *list)
+{
+ struct list_head *head = &list->free;
+ struct request *rq;
+ int i = 0;
+
+ while (!list_empty(head)) {
+ rq = list_entry(head->next, struct request, queue);
+ list_del(&rq->queue);
+ kmem_cache_free(request_cachep, rq);
+ i++;
+ };
+
+ if (i != list->count)
+ printk("request list leak!\n");
+
+ list->count = 0;
+ return i;
+}
+
+/**
+ * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
+ * @q: the request queue to be released
+ *
+ * Description:
+ * blk_cleanup_queue is the pair to blk_init_queue(). It should
+ * be called when a request queue is being released; typically
+ * when a block device is being de-registered. Currently, its
+ * primary task it to free all the &struct request structures that
+ * were allocated to the queue.
+ * Caveat:
+ * Hopefully the low level driver will have finished any
+ * outstanding requests first...
+ **/
+void blk_cleanup_queue(request_queue_t * q)
+{
+ int count = q->nr_requests;
+
+ count -= __blk_cleanup_queue(&q->rq[READ]);
+ count -= __blk_cleanup_queue(&q->rq[WRITE]);
+
+ if (count)
+ printk("blk_cleanup_queue: leaked requests (%d)\n", count);
+
+ memset(q, 0, sizeof(*q));
+}
+
+/**
+ * blk_queue_headactive - indicate whether head of request queue may be active
+ * @q: The queue which this applies to.
+ * @active: A flag indication where the head of the queue is active.
+ *
+ * Description:
+ * The driver for a block device may choose to leave the currently active
+ * request on the request queue, removing it only when it has completed.
+ * The queue handling routines assume this by default for safety reasons
+ * and will not involve the head of the request queue in any merging or
+ * reordering of requests when the queue is unplugged (and thus may be
+ * working on this particular request).
+ *
+ * If a driver removes requests from the queue before processing them, then
+ * it may indicate that it does so, there by allowing the head of the queue
+ * to be involved in merging and reordering. This is done be calling
+ * blk_queue_headactive() with an @active flag of %0.
+ *
+ * If a driver processes several requests at once, it must remove them (or
+ * at least all but one of them) from the request queue.
+ *
+ * When a queue is plugged the head will be assumed to be inactive.
+ **/
+
+void blk_queue_headactive(request_queue_t * q, int active)
+{
+ q->head_active = active;
+}
+
+/**
+ * blk_queue_make_request - define an alternate make_request function for a device
+ * @q: the request queue for the device to be affected
+ * @mfn: the alternate make_request function
+ *
+ * Description:
+ * The normal way for &struct buffer_heads to be passed to a device
+ * driver is for them to be collected into requests on a request
+ * queue, and then to allow the device driver to select requests
+ * off that queue when it is ready. This works well for many block
+ * devices. However some block devices (typically virtual devices
+ * such as md or lvm) do not benefit from the processing on the
+ * request queue, and are served best by having the requests passed
+ * directly to them. This can be achieved by providing a function
+ * to blk_queue_make_request().
+ *
+ * Caveat:
+ * The driver that does this *must* be able to deal appropriately
+ * with buffers in "highmemory", either by calling bh_kmap() to get
+ * a kernel mapping, to by calling create_bounce() to create a
+ * buffer in normal memory.
+ **/
+
+void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
+{
+ q->make_request_fn = mfn;
+}
+
+/**
+ * blk_queue_bounce_limit - set bounce buffer limit for queue
+ * @q: the request queue for the device
+ * @dma_addr: bus address limit
+ *
+ * Description:
+ * Different hardware can have different requirements as to what pages
+ * it can do I/O directly to. A low level driver can call
+ * blk_queue_bounce_limit to have lower memory pages allocated as bounce
+ * buffers for doing I/O to pages residing above @page. By default
+ * the block layer sets this to the highest numbered "low" memory page.
+ **/
+void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr)
+{
+ unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
+ unsigned long mb = dma_addr >> 20;
+ static request_queue_t *old_q;
+
+ /*
+ * keep this for debugging for now...
+ */
+ if (dma_addr != BLK_BOUNCE_HIGH && q != old_q) {
+ old_q = q;
+ printk("blk: queue %p, ", q);
+ if (dma_addr == BLK_BOUNCE_ANY)
+ printk("no I/O memory limit\n");
+ else
+ printk("I/O limit %luMb (mask 0x%Lx)\n", mb,
+ (long long) dma_addr);
+ }
+
+ q->bounce_pfn = bounce_pfn;
+}
+
+
+/*
+ * can we merge the two segments, or do we need to start a new one?
+ */
+inline int blk_seg_merge_ok(struct buffer_head *bh, struct buffer_head *nxt)
+{
+ /*
+ * if bh and nxt are contigous and don't cross a 4g boundary, it's ok
+ */
+ if (BH_CONTIG(bh, nxt) && BH_PHYS_4G(bh, nxt))
+ return 1;
+
+ return 0;
+}
+
+static inline int ll_new_segment(request_queue_t *q, struct request *req, int max_segments)
+{
+ if (req->nr_segments < max_segments) {
+ req->nr_segments++;
+ return 1;
+ }
+ return 0;
+}
+
+static int ll_back_merge_fn(request_queue_t *q, struct request *req,
+ struct buffer_head *bh, int max_segments)
+{
+ if (blk_seg_merge_ok(req->bhtail, bh))
+ return 1;
+
+ return ll_new_segment(q, req, max_segments);
+}
+
+static int ll_front_merge_fn(request_queue_t *q, struct request *req,
+ struct buffer_head *bh, int max_segments)
+{
+ if (blk_seg_merge_ok(bh, req->bh))
+ return 1;
+
+ return ll_new_segment(q, req, max_segments);
+}
+
+static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
+ struct request *next, int max_segments)
+{
+ int total_segments = req->nr_segments + next->nr_segments;
+
+ if (blk_seg_merge_ok(req->bhtail, next->bh))
+ total_segments--;
+
+ if (total_segments > max_segments)
+ return 0;
+
+ req->nr_segments = total_segments;
+ return 1;
+}
+
+/*
+ * "plug" the device if there are no outstanding requests: this will
+ * force the transfer to start only after we have put all the requests
+ * on the list.
+ *
+ * This is called with interrupts off and no requests on the queue.
+ * (and with the request spinlock acquired)
+ */
+static void generic_plug_device(request_queue_t *q, kdev_t dev)
+{
+ /*
+ * no need to replug device
+ */
+ if (!list_empty(&q->queue_head) || q->plugged)
+ return;
+
+ q->plugged = 1;
+ queue_task(&q->plug_tq, &tq_disk);
+}
+
+/*
+ * remove the plug and let it rip..
+ */
+static inline void __generic_unplug_device(request_queue_t *q)
+{
+ if (q->plugged) {
+ q->plugged = 0;
+ if (!list_empty(&q->queue_head))
+ q->request_fn(q);
+ }
+}
+
+void generic_unplug_device(void *data)
+{
+ request_queue_t *q = (request_queue_t *) data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&io_request_lock, flags);
+ __generic_unplug_device(q);
+ spin_unlock_irqrestore(&io_request_lock, flags);
+}
+
+/** blk_grow_request_list
+ * @q: The &request_queue_t
+ * @nr_requests: how many requests are desired
+ *
+ * More free requests are added to the queue's free lists, bringing
+ * the total number of requests to @nr_requests.
+ *
+ * The requests are added equally to the request queue's read
+ * and write freelists.
+ *
+ * This function can sleep.
+ *
+ * Returns the (new) number of requests which the queue has available.
+ */
+int blk_grow_request_list(request_queue_t *q, int nr_requests)
+{
+ unsigned long flags;
+ /* Several broken drivers assume that this function doesn't sleep,
+ * this causes system hangs during boot.
+ * As a temporary fix, make the function non-blocking.
+ */
+ spin_lock_irqsave(&io_request_lock, flags);
+ while (q->nr_requests < nr_requests) {
+ struct request *rq;
+ int rw;
+
+ rq = kmem_cache_alloc(request_cachep, SLAB_ATOMIC);
+ if (rq == NULL)
+ break;
+ memset(rq, 0, sizeof(*rq));
+ rq->rq_status = RQ_INACTIVE;
+ rw = q->nr_requests & 1;
+ list_add(&rq->queue, &q->rq[rw].free);
+ q->rq[rw].count++;
+ q->nr_requests++;
+ }
+ q->batch_requests = q->nr_requests / 4;
+ if (q->batch_requests > 32)
+ q->batch_requests = 32;
+ spin_unlock_irqrestore(&io_request_lock, flags);
+ return q->nr_requests;
+}
+
+static void blk_init_free_list(request_queue_t *q)
+{
+ struct sysinfo si;
+ int megs; /* Total memory, in megabytes */
+ int nr_requests;
+
+ INIT_LIST_HEAD(&q->rq[READ].free);
+ INIT_LIST_HEAD(&q->rq[WRITE].free);
+ q->rq[READ].count = 0;
+ q->rq[WRITE].count = 0;
+ q->nr_requests = 0;
+
+ si_meminfo(&si);
+ megs = si.totalram >> (20 - PAGE_SHIFT);
+ nr_requests = 128;
+ if (megs < 32)
+ nr_requests /= 2;
+ blk_grow_request_list(q, nr_requests);
+
+ init_waitqueue_head(&q->wait_for_requests[0]);
+ init_waitqueue_head(&q->wait_for_requests[1]);
+ spin_lock_init(&q->queue_lock);
+}
+
+static int __make_request(request_queue_t * q, int rw, struct buffer_head * bh);
+
+/**
+ * blk_init_queue - prepare a request queue for use with a block device
+ * @q: The &request_queue_t to be initialised
+ * @rfn: The function to be called to process requests that have been
+ * placed on the queue.
+ *
+ * Description:
+ * If a block device wishes to use the standard request handling procedures,
+ * which sorts requests and coalesces adjacent requests, then it must
+ * call blk_init_queue(). The function @rfn will be called when there
+ * are requests on the queue that need to be processed. If the device
+ * supports plugging, then @rfn may not be called immediately when requests
+ * are available on the queue, but may be called at some time later instead.
+ * Plugged queues are generally unplugged when a buffer belonging to one
+ * of the requests on the queue is needed, or due to memory pressure.
+ *
+ * @rfn is not required, or even expected, to remove all requests off the
+ * queue, but only as many as it can handle at a time. If it does leave
+ * requests on the queue, it is responsible for arranging that the requests
+ * get dealt with eventually.
+ *
+ * A global spin lock $io_request_lock must be held while manipulating the
+ * requests on the request queue.
+ *
+ * The request on the head of the queue is by default assumed to be
+ * potentially active, and it is not considered for re-ordering or merging
+ * whenever the given queue is unplugged. This behaviour can be changed with
+ * blk_queue_headactive().
+ *
+ * Note:
+ * blk_init_queue() must be paired with a blk_cleanup_queue() call
+ * when the block device is deactivated (such as at module unload).
+ **/
+void blk_init_queue(request_queue_t * q, request_fn_proc * rfn)
+{
+ INIT_LIST_HEAD(&q->queue_head);
+ elevator_init(&q->elevator, ELEVATOR_LINUS);
+ blk_init_free_list(q);
+ q->request_fn = rfn;
+ q->back_merge_fn = ll_back_merge_fn;
+ q->front_merge_fn = ll_front_merge_fn;
+ q->merge_requests_fn = ll_merge_requests_fn;
+ q->make_request_fn = __make_request;
+ q->plug_tq.sync = 0;
+ q->plug_tq.routine = &generic_unplug_device;
+ q->plug_tq.data = q;
+ q->plugged = 0;
+ /*
+ * These booleans describe the queue properties. We set the
+ * default (and most common) values here. Other drivers can
+ * use the appropriate functions to alter the queue properties.
+ * as appropriate.
+ */
+ q->plug_device_fn = generic_plug_device;
+ q->head_active = 1;
+
+ blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
+}
+
+#define blkdev_free_rq(list) list_entry((list)->next, struct request, queue);
+/*
+ * Get a free request. io_request_lock must be held and interrupts
+ * disabled on the way in. Returns NULL if there are no free requests.
+ */
+static struct request *get_request(request_queue_t *q, int rw)
+{
+ struct request *rq = NULL;
+ struct request_list *rl = q->rq + rw;
+
+ if (!list_empty(&rl->free)) {
+ rq = blkdev_free_rq(&rl->free);
+ list_del(&rq->queue);
+ rl->count--;
+ rq->rq_status = RQ_ACTIVE;
+ rq->cmd = rw;
+ rq->special = NULL;
+ rq->q = q;
+ }
+
+ return rq;
+}
+
+/*
+ * Here's the request allocation design:
+ *
+ * 1: Blocking on request exhaustion is a key part of I/O throttling.
+ *
+ * 2: We want to be `fair' to all requesters. We must avoid starvation, and
+ * attempt to ensure that all requesters sleep for a similar duration. Hence
+ * no stealing requests when there are other processes waiting.
+ *
+ * 3: We also wish to support `batching' of requests. So when a process is
+ * woken, we want to allow it to allocate a decent number of requests
+ * before it blocks again, so they can be nicely merged (this only really
+ * matters if the process happens to be adding requests near the head of
+ * the queue).
+ *
+ * 4: We want to avoid scheduling storms. This isn't really important, because
+ * the system will be I/O bound anyway. But it's easy.
+ *
+ * There is tension between requirements 2 and 3. Once a task has woken,
+ * we don't want to allow it to sleep as soon as it takes its second request.
+ * But we don't want currently-running tasks to steal all the requests
+ * from the sleepers. We handle this with wakeup hysteresis around
+ * 0 .. batch_requests and with the assumption that request taking is much,
+ * much faster than request freeing.
+ *
+ * So here's what we do:
+ *
+ * a) A READA requester fails if free_requests < batch_requests
+ *
+ * We don't want READA requests to prevent sleepers from ever
+ * waking. Note that READA is used extremely rarely - a few
+ * filesystems use it for directory readahead.
+ *
+ * When a process wants a new request:
+ *
+ * b) If free_requests == 0, the requester sleeps in FIFO manner.
+ *
+ * b) If 0 < free_requests < batch_requests and there are waiters,
+ * we still take a request non-blockingly. This provides batching.
+ *
+ * c) If free_requests >= batch_requests, the caller is immediately
+ * granted a new request.
+ *
+ * When a request is released:
+ *
+ * d) If free_requests < batch_requests, do nothing.
+ *
+ * f) If free_requests >= batch_requests, wake up a single waiter.
+ *
+ * The net effect is that when a process is woken at the batch_requests level,
+ * it will be able to take approximately (batch_requests) requests before
+ * blocking again (at the tail of the queue).
+ *
+ * This all assumes that the rate of taking requests is much, much higher
+ * than the rate of releasing them. Which is very true.
+ *
+ * -akpm, Feb 2002.
+ */
+
+static struct request *__get_request_wait(request_queue_t *q, int rw)
+{
+ register struct request *rq;
+ DECLARE_WAITQUEUE(wait, current);
+
+ generic_unplug_device(q);
+ add_wait_queue_exclusive(&q->wait_for_requests[rw], &wait);
+ do {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (q->rq[rw].count == 0)
+ schedule();
+ spin_lock_irq(&io_request_lock);
+ rq = get_request(q, rw);
+ spin_unlock_irq(&io_request_lock);
+ } while (rq == NULL);
+ remove_wait_queue(&q->wait_for_requests[rw], &wait);
+ current->state = TASK_RUNNING;
+ return rq;
+}
+
+/* RO fail safe mechanism */
+
+static long ro_bits[MAX_BLKDEV][8];
+
+int is_read_only(kdev_t dev)
+{
+ int minor,major;
+
+ major = MAJOR(dev);
+ minor = MINOR(dev);
+ if (major < 0 || major >= MAX_BLKDEV) return 0;
+ return ro_bits[major][minor >> 5] & (1 << (minor & 31));
+}
+
+void set_device_ro(kdev_t dev,int flag)
+{
+ int minor,major;
+
+ major = MAJOR(dev);
+ minor = MINOR(dev);
+ if (major < 0 || major >= MAX_BLKDEV) return;
+ if (flag) ro_bits[major][minor >> 5] |= 1 << (minor & 31);
+ else ro_bits[major][minor >> 5] &= ~(1 << (minor & 31));
+}
+
+inline void drive_stat_acct (kdev_t dev, int rw,
+ unsigned long nr_sectors, int new_io)
+{
+ unsigned int major = MAJOR(dev);
+ unsigned int index;
+
+ index = disk_index(dev);
+ if ((index >= DK_MAX_DISK) || (major >= DK_MAX_MAJOR))
+ return;
+
+ kstat.dk_drive[major][index] += new_io;
+ if (rw == READ) {
+ kstat.dk_drive_rio[major][index] += new_io;
+ kstat.dk_drive_rblk[major][index] += nr_sectors;
+ } else if (rw == WRITE) {
+ kstat.dk_drive_wio[major][index] += new_io;
+ kstat.dk_drive_wblk[major][index] += nr_sectors;
+ } else
+ printk(KERN_ERR "drive_stat_acct: cmd not R/W?\n");
+}
+
+#ifdef CONFIG_BLK_STATS
+/*
+ * Return up to two hd_structs on which to do IO accounting for a given
+ * request.
+ *
+ * On a partitioned device, we want to account both against the partition
+ * and against the whole disk.
+ */
+static void locate_hd_struct(struct request *req,
+ struct hd_struct **hd1,
+ struct hd_struct **hd2)
+{
+ struct gendisk *gd;
+
+ *hd1 = NULL;
+ *hd2 = NULL;
+
+ gd = get_gendisk(req->rq_dev);
+ if (gd && gd->part) {
+ /* Mask out the partition bits: account for the entire disk */
+ int devnr = MINOR(req->rq_dev) >> gd->minor_shift;
+ int whole_minor = devnr << gd->minor_shift;
+
+ *hd1 = &gd->part[whole_minor];
+ if (whole_minor != MINOR(req->rq_dev))
+ *hd2= &gd->part[MINOR(req->rq_dev)];
+ }
+}
+
+/*
+ * Round off the performance stats on an hd_struct.
+ *
+ * The average IO queue length and utilisation statistics are maintained
+ * by observing the current state of the queue length and the amount of
+ * time it has been in this state for.
+ * Normally, that accounting is done on IO completion, but that can result
+ * in more than a second's worth of IO being accounted for within any one
+ * second, leading to >100% utilisation. To deal with that, we do a
+ * round-off before returning the results when reading /proc/partitions,
+ * accounting immediately for all queue usage up to the current jiffies and
+ * restarting the counters again.
+ */
+void disk_round_stats(struct hd_struct *hd)
+{
+ unsigned long now = jiffies;
+
+ hd->aveq += (hd->ios_in_flight * (jiffies - hd->last_queue_change));
+ hd->last_queue_change = now;
+
+ if (hd->ios_in_flight)
+ hd->io_ticks += (now - hd->last_idle_time);
+ hd->last_idle_time = now;
+}
+
+static inline void down_ios(struct hd_struct *hd)
+{
+ disk_round_stats(hd);
+ --hd->ios_in_flight;
+}
+
+static inline void up_ios(struct hd_struct *hd)
+{
+ disk_round_stats(hd);
+ ++hd->ios_in_flight;
+}
+
+static void account_io_start(struct hd_struct *hd, struct request *req,
+ int merge, int sectors)
+{
+ switch (req->cmd) {
+ case READ:
+ if (merge)
+ hd->rd_merges++;
+ hd->rd_sectors += sectors;
+ break;
+ case WRITE:
+ if (merge)
+ hd->wr_merges++;
+ hd->wr_sectors += sectors;
+ break;
+ }
+ if (!merge)
+ up_ios(hd);
+}
+
+static void account_io_end(struct hd_struct *hd, struct request *req)
+{
+ unsigned long duration = jiffies - req->start_time;
+ switch (req->cmd) {
+ case READ:
+ hd->rd_ticks += duration;
+ hd->rd_ios++;
+ break;
+ case WRITE:
+ hd->wr_ticks += duration;
+ hd->wr_ios++;
+ break;
+ }
+ down_ios(hd);
+}
+
+void req_new_io(struct request *req, int merge, int sectors)
+{
+ struct hd_struct *hd1, *hd2;
+
+ locate_hd_struct(req, &hd1, &hd2);
+ if (hd1)
+ account_io_start(hd1, req, merge, sectors);
+ if (hd2)
+ account_io_start(hd2, req, merge, sectors);
+}
+
+void req_merged_io(struct request *req)
+{
+ struct hd_struct *hd1, *hd2;
+
+ locate_hd_struct(req, &hd1, &hd2);
+ if (hd1)
+ down_ios(hd1);
+ if (hd2)
+ down_ios(hd2);
+}
+
+void req_finished_io(struct request *req)
+{
+ struct hd_struct *hd1, *hd2;
+
+ locate_hd_struct(req, &hd1, &hd2);
+ if (hd1)
+ account_io_end(hd1, req);
+ if (hd2)
+ account_io_end(hd2, req);
+}
+EXPORT_SYMBOL(req_finished_io);
+#endif /* CONFIG_BLK_STATS */
+
+/*
+ * add-request adds a request to the linked list.
+ * io_request_lock is held and interrupts disabled, as we muck with the
+ * request queue list.
+ *
+ * By this point, req->cmd is always either READ/WRITE, never READA,
+ * which is important for drive_stat_acct() above.
+ */
+static inline void add_request(request_queue_t * q, struct request * req,
+ struct list_head *insert_here)
+{
+ drive_stat_acct(req->rq_dev, req->cmd, req->nr_sectors, 1);
+
+ if (!q->plugged && q->head_active && insert_here == &q->queue_head) {
+ spin_unlock_irq(&io_request_lock);
+ printk("list_empty(&q->queue_head) is %d\n",
+ list_empty(&q->queue_head));
+ BUG();
+ }
+
+ /*
+ * elevator indicated where it wants this request to be
+ * inserted at elevator_merge time
+ */
+ list_add(&req->queue, insert_here);
+}
+
+/*
+ * Must be called with io_request_lock held and interrupts disabled
+ */
+void blkdev_release_request(struct request *req)
+{
+ request_queue_t *q = req->q;
+ int rw = req->cmd;
+
+ req->rq_status = RQ_INACTIVE;
+ req->q = NULL;
+
+ /*
+ * Request may not have originated from ll_rw_blk. if not,
+ * assume it has free buffers and check waiters
+ */
+ if (q) {
+ list_add(&req->queue, &q->rq[rw].free);
+ if (++q->rq[rw].count >= q->batch_requests &&
+ waitqueue_active(&q->wait_for_requests[rw]))
+ wake_up(&q->wait_for_requests[rw]);
+ }
+}
+
+/*
+ * Has to be called with the request spinlock acquired
+ */
+static void attempt_merge(request_queue_t * q,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ struct request *next;
+
+ next = blkdev_next_request(req);
+ if (req->sector + req->nr_sectors != next->sector)
+ return;
+ if (req->cmd != next->cmd
+ || req->rq_dev != next->rq_dev
+ || req->nr_sectors + next->nr_sectors > max_sectors
+ || next->waiting)
+ return;
+ /*
+ * If we are not allowed to merge these requests, then
+ * return. If we are allowed to merge, then the count
+ * will have been updated to the appropriate number,
+ * and we shouldn't do it here too.
+ */
+ if (!q->merge_requests_fn(q, req, next, max_segments))
+ return;
+
+ q->elevator.elevator_merge_req_fn(req, next);
+ req->bhtail->b_reqnext = next->bh;
+ req->bhtail = next->bhtail;
+ req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+ list_del(&next->queue);
+
+ /* One last thing: we have removed a request, so we now have one
+ less expected IO to complete for accounting purposes. */
+ req_merged_io(req);
+
+ blkdev_release_request(next);
+}
+
+static inline void attempt_back_merge(request_queue_t * q,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ if (&req->queue == q->queue_head.prev)
+ return;
+ attempt_merge(q, req, max_sectors, max_segments);
+}
+
+static inline void attempt_front_merge(request_queue_t * q,
+ struct list_head * head,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ struct list_head * prev;
+
+ prev = req->queue.prev;
+ if (head == prev)
+ return;
+ attempt_merge(q, blkdev_entry_to_request(prev), max_sectors, max_segments);
+}
+
+static int __make_request(request_queue_t * q, int rw,
+ struct buffer_head * bh)
+{
+ unsigned int sector, count;
+ int max_segments = MAX_SEGMENTS;
+ struct request * req, *freereq = NULL;
+ int rw_ahead, max_sectors, el_ret;
+ struct list_head *head, *insert_here;
+ int latency;
+ elevator_t *elevator = &q->elevator;
+
+ count = bh->b_size >> 9;
+ sector = bh->b_rsector;
+
+ rw_ahead = 0; /* normal case; gets changed below for READA */
+ switch (rw) {
+ case READA:
+#if 0 /* bread() misinterprets failed READA attempts as IO errors on SMP */
+ rw_ahead = 1;
+#endif
+ rw = READ; /* drop into READ */
+ case READ:
+ case WRITE:
+ latency = elevator_request_latency(elevator, rw);
+ break;
+ default:
+ BUG();
+ goto end_io;
+ }
+
+ /* We'd better have a real physical mapping!
+ Check this bit only if the buffer was dirty and just locked
+ down by us so at this point flushpage will block and
+ won't clear the mapped bit under us. */
+ if (!buffer_mapped(bh))
+ BUG();
+
+ /*
+ * Temporary solution - in 2.5 this will be done by the lowlevel
+ * driver. Create a bounce buffer if the buffer data points into
+ * high memory - keep the original buffer otherwise.
+ */
+ bh = blk_queue_bounce(q, rw, bh);
+
+/* look for a free request. */
+ /*
+ * Try to coalesce the new request with old requests
+ */
+ max_sectors = get_max_sectors(bh->b_rdev);
+
+again:
+ req = NULL;
+ head = &q->queue_head;
+ /*
+ * Now we acquire the request spinlock, we have to be mega careful
+ * not to schedule or do something nonatomic
+ */
+ spin_lock_irq(&io_request_lock);
+
+ insert_here = head->prev;
+ if (list_empty(head)) {
+ q->plug_device_fn(q, bh->b_rdev); /* is atomic */
+ goto get_rq;
+ } else if (q->head_active && !q->plugged)
+ head = head->next;
+
+ el_ret = elevator->elevator_merge_fn(q, &req, head, bh, rw,max_sectors);
+ switch (el_ret) {
+
+ case ELEVATOR_BACK_MERGE:
+ if (!q->back_merge_fn(q, req, bh, max_segments)) {
+ insert_here = &req->queue;
+ break;
+ }
+ req->bhtail->b_reqnext = bh;
+ req->bhtail = bh;
+ req->nr_sectors = req->hard_nr_sectors += count;
+ blk_started_io(count);
+ drive_stat_acct(req->rq_dev, req->cmd, count, 0);
+ req_new_io(req, 1, count);
+ attempt_back_merge(q, req, max_sectors, max_segments);
+ goto out;
+
+ case ELEVATOR_FRONT_MERGE:
+ if (!q->front_merge_fn(q, req, bh, max_segments)) {
+ insert_here = req->queue.prev;
+ break;
+ }
+ bh->b_reqnext = req->bh;
+ req->bh = bh;
+ /*
+ * may not be valid, but queues not having bounce
+ * enabled for highmem pages must not look at
+ * ->buffer anyway
+ */
+ req->buffer = bh->b_data;
+ req->current_nr_sectors = req->hard_cur_sectors = count;
+ req->sector = req->hard_sector = sector;
+ req->nr_sectors = req->hard_nr_sectors += count;
+ blk_started_io(count);
+ drive_stat_acct(req->rq_dev, req->cmd, count, 0);
+ req_new_io(req, 1, count);
+ attempt_front_merge(q, head, req, max_sectors, max_segments);
+ goto out;
+
+ /*
+ * elevator says don't/can't merge. get new request
+ */
+ case ELEVATOR_NO_MERGE:
+ /*
+ * use elevator hints as to where to insert the
+ * request. if no hints, just add it to the back
+ * of the queue
+ */
+ if (req)
+ insert_here = &req->queue;
+ break;
+
+ default:
+ printk("elevator returned crap (%d)\n", el_ret);
+ BUG();
+ }
+
+get_rq:
+ if (freereq) {
+ req = freereq;
+ freereq = NULL;
+ } else {
+ /*
+ * See description above __get_request_wait()
+ */
+ if (rw_ahead) {
+ if (q->rq[rw].count < q->batch_requests) {
+ spin_unlock_irq(&io_request_lock);
+ goto end_io;
+ }
+ req = get_request(q, rw);
+ if (req == NULL)
+ BUG();
+ } else {
+ req = get_request(q, rw);
+ if (req == NULL) {
+ spin_unlock_irq(&io_request_lock);
+ freereq = __get_request_wait(q, rw);
+ goto again;
+ }
+ }
+ }
+
+/* fill up the request-info, and add it to the queue */
+ req->elevator_sequence = latency;
+ req->cmd = rw;
+ req->errors = 0;
+ req->hard_sector = req->sector = sector;
+ req->hard_nr_sectors = req->nr_sectors = count;
+ req->current_nr_sectors = req->hard_cur_sectors = count;
+ req->nr_segments = 1; /* Always 1 for a new request. */
+ req->nr_hw_segments = 1; /* Always 1 for a new request. */
+ req->buffer = bh->b_data;
+ req->waiting = NULL;
+ req->bh = bh;
+ req->bhtail = bh;
+ req->rq_dev = bh->b_rdev;
+ req->start_time = jiffies;
+ req_new_io(req, 0, count);
+ blk_started_io(count);
+ add_request(q, req, insert_here);
+out:
+ if (freereq)
+ blkdev_release_request(freereq);
+ spin_unlock_irq(&io_request_lock);
+ return 0;
+end_io:
+ bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
+ return 0;
+}
+
+/**
+ * generic_make_request: hand a buffer head to it's device driver for I/O
+ * @rw: READ, WRITE, or READA - what sort of I/O is desired.
+ * @bh: The buffer head describing the location in memory and on the device.
+ *
+ * generic_make_request() is used to make I/O requests of block
+ * devices. It is passed a &struct buffer_head and a &rw value. The
+ * %READ and %WRITE options are (hopefully) obvious in meaning. The
+ * %READA value means that a read is required, but that the driver is
+ * free to fail the request if, for example, it cannot get needed
+ * resources immediately.
+ *
+ * generic_make_request() does not return any status. The
+ * success/failure status of the request, along with notification of
+ * completion, is delivered asynchronously through the bh->b_end_io
+ * function described (one day) else where.
+ *
+ * The caller of generic_make_request must make sure that b_page,
+ * b_addr, b_size are set to describe the memory buffer, that b_rdev
+ * and b_rsector are set to describe the device address, and the
+ * b_end_io and optionally b_private are set to describe how
+ * completion notification should be signaled. BH_Mapped should also
+ * be set (to confirm that b_dev and b_blocknr are valid).
+ *
+ * generic_make_request and the drivers it calls may use b_reqnext,
+ * and may change b_rdev and b_rsector. So the values of these fields
+ * should NOT be depended on after the call to generic_make_request.
+ * Because of this, the caller should record the device address
+ * information in b_dev and b_blocknr.
+ *
+ * Apart from those fields mentioned above, no other fields, and in
+ * particular, no other flags, are changed by generic_make_request or
+ * any lower level drivers.
+ * */
+void generic_make_request (int rw, struct buffer_head * bh)
+{
+ int major = MAJOR(bh->b_rdev);
+ int minorsize = 0;
+ request_queue_t *q;
+
+ if (!bh->b_end_io)
+ BUG();
+
+ /* Test device size, when known. */
+ if (blk_size[major])
+ minorsize = blk_size[major][MINOR(bh->b_rdev)];
+ if (minorsize) {
+ unsigned long maxsector = (minorsize << 1) + 1;
+ unsigned long sector = bh->b_rsector;
+ unsigned int count = bh->b_size >> 9;
+
+ if (maxsector < count || maxsector - count < sector) {
+ /* Yecch */
+ bh->b_state &= (1 << BH_Lock) | (1 << BH_Mapped);
+
+ /* This may well happen - the kernel calls bread()
+ without checking the size of the device, e.g.,
+ when mounting a device. */
+ printk(KERN_INFO
+ "attempt to access beyond end of device\n");
+ printk(KERN_INFO "%s: rw=%d, want=%ld, limit=%d\n",
+ kdevname(bh->b_rdev), rw,
+ (sector + count)>>1, minorsize);
+
+ /* Yecch again */
+ bh->b_end_io(bh, 0);
+ return;
+ }
+ }
+
+ /*
+ * Resolve the mapping until finished. (drivers are
+ * still free to implement/resolve their own stacking
+ * by explicitly returning 0)
+ */
+ /* NOTE: we don't repeat the blk_size check for each new device.
+ * Stacking drivers are expected to know what they are doing.
+ */
+ do {
+ q = blk_get_queue(bh->b_rdev);
+ if (!q) {
+ printk(KERN_ERR
+ "generic_make_request: Trying to access "
+ "nonexistent block-device %s (%ld)\n",
+ kdevname(bh->b_rdev), bh->b_rsector);
+ buffer_IO_error(bh);
+ break;
+ }
+ } while (q->make_request_fn(q, rw, bh));
+}
+
+
+/**
+ * submit_bh: submit a buffer_head to the block device later for I/O
+ * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
+ * @bh: The &struct buffer_head which describes the I/O
+ *
+ * submit_bh() is very similar in purpose to generic_make_request(), and
+ * uses that function to do most of the work.
+ *
+ * The extra functionality provided by submit_bh is to determine
+ * b_rsector from b_blocknr and b_size, and to set b_rdev from b_dev.
+ * This is is appropriate for IO requests that come from the buffer
+ * cache and page cache which (currently) always use aligned blocks.
+ */
+void submit_bh(int rw, struct buffer_head * bh)
+{
+ int count = bh->b_size >> 9;
+
+ if (!test_bit(BH_Lock, &bh->b_state))
+ BUG();
+
+ set_bit(BH_Req, &bh->b_state);
+ set_bit(BH_Launder, &bh->b_state);
+
+ /*
+ * First step, 'identity mapping' - RAID or LVM might
+ * further remap this.
+ */
+ bh->b_rdev = bh->b_dev;
+ bh->b_rsector = bh->b_blocknr * count;
+
+ generic_make_request(rw, bh);
+
+ switch (rw) {
+ case WRITE:
+ kstat.pgpgout += count;
+ break;
+ default:
+ kstat.pgpgin += count;
+ break;
+ }
+}
+
+/**
+ * ll_rw_block: low-level access to block devices
+ * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
+ * @nr: number of &struct buffer_heads in the array
+ * @bhs: array of pointers to &struct buffer_head
+ *
+ * ll_rw_block() takes an array of pointers to &struct buffer_heads,
+ * and requests an I/O operation on them, either a %READ or a %WRITE.
+ * The third %READA option is described in the documentation for
+ * generic_make_request() which ll_rw_block() calls.
+ *
+ * This function provides extra functionality that is not in
+ * generic_make_request() that is relevant to buffers in the buffer
+ * cache or page cache. In particular it drops any buffer that it
+ * cannot get a lock on (with the BH_Lock state bit), any buffer that
+ * appears to be clean when doing a write request, and any buffer that
+ * appears to be up-to-date when doing read request. Further it marks
+ * as clean buffers that are processed for writing (the buffer cache
+ * wont assume that they are actually clean until the buffer gets
+ * unlocked).
+ *
+ * ll_rw_block sets b_end_io to simple completion handler that marks
+ * the buffer up-to-date (if approriate), unlocks the buffer and wakes
+ * any waiters. As client that needs a more interesting completion
+ * routine should call submit_bh() (or generic_make_request())
+ * directly.
+ *
+ * Caveat:
+ * All of the buffers must be for the same device, and must also be
+ * of the current approved size for the device. */
+
+void ll_rw_block(int rw, int nr, struct buffer_head * bhs[])
+{
+ unsigned int major;
+ int correct_size;
+ int i;
+
+ if (!nr)
+ return;
+
+ major = MAJOR(bhs[0]->b_dev);
+
+ /* Determine correct block size for this device. */
+ correct_size = get_hardsect_size(bhs[0]->b_dev);
+
+ /* Verify requested block sizes. */
+ for (i = 0; i < nr; i++) {
+ struct buffer_head *bh = bhs[i];
+ if (bh->b_size % correct_size) {
+ printk(KERN_NOTICE "ll_rw_block: device %s: "
+ "only %d-char blocks implemented (%u)\n",
+ kdevname(bhs[0]->b_dev),
+ correct_size, bh->b_size);
+ goto sorry;
+ }
+ }
+
+ if ((rw & WRITE) && is_read_only(bhs[0]->b_dev)) {
+ printk(KERN_NOTICE "Can't write to read-only device %s\n",
+ kdevname(bhs[0]->b_dev));
+ goto sorry;
+ }
+
+ for (i = 0; i < nr; i++) {
+ struct buffer_head *bh = bhs[i];
+
+ /* Only one thread can actually submit the I/O. */
+ if (test_and_set_bit(BH_Lock, &bh->b_state))
+ continue;
+
+ /* We have the buffer lock */
+ atomic_inc(&bh->b_count);
+ bh->b_end_io = end_buffer_io_sync;
+
+ switch(rw) {
+ case WRITE:
+ if (!atomic_set_buffer_clean(bh))
+ /* Hmmph! Nothing to write */
+ goto end_io;
+ __mark_buffer_clean(bh);
+ break;
+
+ case READA:
+ case READ:
+ if (buffer_uptodate(bh))
+ /* Hmmph! Already have it */
+ goto end_io;
+ break;
+ default:
+ BUG();
+ end_io:
+ bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
+ continue;
+ }
+
+ submit_bh(rw, bh);
+ }
+ return;
+
+sorry:
+ /* Make sure we don't get infinite dirty retries.. */
+ for (i = 0; i < nr; i++)
+ mark_buffer_clean(bhs[i]);
+}
+
+#ifdef CONFIG_STRAM_SWAP
+extern int stram_device_init (void);
+#endif
+
+
+/**
+ * end_that_request_first - end I/O on one buffer.
+ * @req: the request being processed
+ * @uptodate: 0 for I/O error
+ * @name: the name printed for an I/O error
+ *
+ * Description:
+ * Ends I/O on the first buffer attached to @req, and sets it up
+ * for the next buffer_head (if any) in the cluster.
+ *
+ * Return:
+ * 0 - we are done with this request, call end_that_request_last()
+ * 1 - still buffers pending for this request
+ *
+ * Caveat:
+ * Drivers implementing their own end_request handling must call
+ * blk_finished_io() appropriately.
+ **/
+
+int end_that_request_first (struct request *req, int uptodate, char *name)
+{
+ struct buffer_head * bh;
+ int nsect;
+
+ req->errors = 0;
+ if (!uptodate)
+ printk("end_request: I/O error, dev %s (%s), sector %lu\n",
+ kdevname(req->rq_dev), name, req->sector);
+
+ if ((bh = req->bh) != NULL) {
+ nsect = bh->b_size >> 9;
+ blk_finished_io(nsect);
+ req->bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+ bh->b_end_io(bh, uptodate);
+ if ((bh = req->bh) != NULL) {
+ req->hard_sector += nsect;
+ req->hard_nr_sectors -= nsect;
+ req->sector = req->hard_sector;
+ req->nr_sectors = req->hard_nr_sectors;
+
+ req->current_nr_sectors = bh->b_size >> 9;
+ req->hard_cur_sectors = req->current_nr_sectors;
+ if (req->nr_sectors < req->current_nr_sectors) {
+ req->nr_sectors = req->current_nr_sectors;
+ printk("end_request: buffer-list destroyed\n");
+ }
+ req->buffer = bh->b_data;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+void end_that_request_last(struct request *req)
+{
+ if (req->waiting != NULL)
+ complete(req->waiting);
+ req_finished_io(req);
+
+ blkdev_release_request(req);
+}
+
+int __init blk_dev_init(void)
+{
+ struct blk_dev_struct *dev;
+
+ request_cachep = kmem_cache_create("blkdev_requests",
+ sizeof(struct request),
+ 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
+
+ if (!request_cachep)
+ panic("Can't create request pool slab cache\n");
+
+ for (dev = blk_dev + MAX_BLKDEV; dev-- != blk_dev;)
+ dev->queue = NULL;
+
+ memset(ro_bits,0,sizeof(ro_bits));
+ memset(max_readahead, 0, sizeof(max_readahead));
+ memset(max_sectors, 0, sizeof(max_sectors));
+
+ blk_max_low_pfn = max_low_pfn - 1;
+ blk_max_pfn = max_pfn - 1;
+
+#ifdef CONFIG_AMIGA_Z2RAM
+ z2_init();
+#endif
+#ifdef CONFIG_STRAM_SWAP
+ stram_device_init();
+#endif
+#ifdef CONFIG_ISP16_CDI
+ isp16_init();
+#endif
+#ifdef CONFIG_BLK_DEV_PS2
+ ps2esdi_init();
+#endif
+#ifdef CONFIG_BLK_DEV_XD
+ xd_init();
+#endif
+#ifdef CONFIG_BLK_DEV_MFM
+ mfm_init();
+#endif
+#ifdef CONFIG_PARIDE
+ { extern void paride_init(void); paride_init(); };
+#endif
+#ifdef CONFIG_MAC_FLOPPY
+ swim3_init();
+#endif
+#ifdef CONFIG_BLK_DEV_SWIM_IOP
+ swimiop_init();
+#endif
+#ifdef CONFIG_AMIGA_FLOPPY
+ amiga_floppy_init();
+#endif
+#ifdef CONFIG_ATARI_FLOPPY
+ atari_floppy_init();
+#endif
+#ifdef CONFIG_BLK_DEV_FD
+ floppy_init();
+#else
+#if defined(__i386__) && !defined(CONFIG_XENO) /* Do we even need this? */
+ outb_p(0xc, 0x3f2);
+#endif
+#endif
+#ifdef CONFIG_CDU31A
+ cdu31a_init();
+#endif
+#ifdef CONFIG_ATARI_ACSI
+ acsi_init();
+#endif
+#ifdef CONFIG_MCD
+ mcd_init();
+#endif
+#ifdef CONFIG_MCDX
+ mcdx_init();
+#endif
+#ifdef CONFIG_SBPCD
+ sbpcd_init();
+#endif
+#ifdef CONFIG_AZTCD
+ aztcd_init();
+#endif
+#ifdef CONFIG_CDU535
+ sony535_init();
+#endif
+#ifdef CONFIG_GSCD
+ gscd_init();
+#endif
+#ifdef CONFIG_CM206
+ cm206_init();
+#endif
+#ifdef CONFIG_OPTCD
+ optcd_init();
+#endif
+#ifdef CONFIG_SJCD
+ sjcd_init();
+#endif
+#ifdef CONFIG_APBLOCK
+ ap_init();
+#endif
+#ifdef CONFIG_DDV
+ ddv_init();
+#endif
+#ifdef CONFIG_MDISK
+ mdisk_init();
+#endif
+#ifdef CONFIG_DASD
+ dasd_init();
+#endif
+#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_BLOCK)
+ tapeblock_init();
+#endif
+#ifdef CONFIG_BLK_DEV_XPRAM
+ xpram_init();
+#endif
+
+#ifdef CONFIG_SUN_JSFLASH
+ jsfd_init();
+#endif
+
+#ifdef CONFIG_XENOLINUX_BLOCK
+ xlblk_init();
+#endif
+
+ return 0;
+};
+
+EXPORT_SYMBOL(io_request_lock);
+EXPORT_SYMBOL(end_that_request_first);
+EXPORT_SYMBOL(end_that_request_last);
+EXPORT_SYMBOL(blk_grow_request_list);
+EXPORT_SYMBOL(blk_init_queue);
+EXPORT_SYMBOL(blk_get_queue);
+EXPORT_SYMBOL(blk_cleanup_queue);
+EXPORT_SYMBOL(blk_queue_headactive);
+EXPORT_SYMBOL(blk_queue_make_request);
+EXPORT_SYMBOL(generic_make_request);
+EXPORT_SYMBOL(blkdev_release_request);
+EXPORT_SYMBOL(generic_unplug_device);
+EXPORT_SYMBOL(blk_queue_bounce_limit);
+EXPORT_SYMBOL(blk_max_low_pfn);
+EXPORT_SYMBOL(blk_max_pfn);
+EXPORT_SYMBOL(blk_seg_merge_ok);
+EXPORT_SYMBOL(blk_nohighio);
--- /dev/null
+/*
+ * linux/drivers/char/tty_io.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles
+ * or rs-channels. It also implements echoing, cooked mode etc.
+ *
+ * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0.
+ *
+ * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the
+ * tty_struct and tty_queue structures. Previously there was an array
+ * of 256 tty_struct's which was statically allocated, and the
+ * tty_queue structures were allocated at boot time. Both are now
+ * dynamically allocated only when the tty is open.
+ *
+ * Also restructured routines so that there is more of a separation
+ * between the high-level tty routines (tty_io.c and tty_ioctl.c) and
+ * the low-level tty routines (serial.c, pty.c, console.c). This
+ * makes for cleaner and more compact code. -TYT, 9/17/92
+ *
+ * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines
+ * which can be dynamically activated and de-activated by the line
+ * discipline handling modules (like SLIP).
+ *
+ * NOTE: pay no attention to the line discipline code (yet); its
+ * interface is still subject to change in this version...
+ * -- TYT, 1/31/92
+ *
+ * Added functionality to the OPOST tty handling. No delays, but all
+ * other bits should be there.
+ * -- Nick Holloway <alfie@dcs.warwick.ac.uk>, 27th May 1993.
+ *
+ * Rewrote canonical mode and added more termios flags.
+ * -- julian@uhunix.uhcc.hawaii.edu (J. Cowley), 13Jan94
+ *
+ * Reorganized FASYNC support so mouse code can share it.
+ * -- ctm@ardi.com, 9Sep95
+ *
+ * New TIOCLINUX variants added.
+ * -- mj@k332.feld.cvut.cz, 19-Nov-95
+ *
+ * Restrict vt switching via ioctl()
+ * -- grif@cs.ucr.edu, 5-Dec-95
+ *
+ * Move console and virtual terminal code to more appropriate files,
+ * implement CONFIG_VT and generalize console device interface.
+ * -- Marko Kohtala <Marko.Kohtala@hut.fi>, March 97
+ *
+ * Rewrote init_dev and release_dev to eliminate races.
+ * -- Bill Hawes <whawes@star.net>, June 97
+ *
+ * Added devfs support.
+ * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 13-Jan-1998
+ *
+ * Added support for a Unix98-style ptmx device.
+ * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998
+ *
+ * Reduced memory usage for older ARM systems
+ * -- Russell King <rmk@arm.linux.org.uk>
+ *
+ * Move do_SAK() into process context. Less stack use in devfs functions.
+ * alloc_tty_struct() always uses kmalloc() -- Andrew Morton <andrewm@uow.edu.eu> 17Mar01
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/major.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/fcntl.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <linux/devpts_fs.h>
+#include <linux/file.h>
+#include <linux/console.h>
+#include <linux/timer.h>
+#include <linux/ctype.h>
+#include <linux/kd.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+
+#include <linux/kbd_kern.h>
+#include <linux/vt_kern.h>
+#include <linux/selection.h>
+#include <linux/devfs_fs_kernel.h>
+
+#include <linux/kmod.h>
+
+#ifdef CONFIG_XENO
+extern void xeno_console_init(void);
+#endif
+
+#ifdef CONFIG_VT
+extern void con_init_devfs (void);
+#endif
+
+extern void disable_early_printk(void);
+
+#define CONSOLE_DEV MKDEV(TTY_MAJOR,0)
+#define TTY_DEV MKDEV(TTYAUX_MAJOR,0)
+#define SYSCONS_DEV MKDEV(TTYAUX_MAJOR,1)
+#define PTMX_DEV MKDEV(TTYAUX_MAJOR,2)
+
+#undef TTY_DEBUG_HANGUP
+
+#define TTY_PARANOIA_CHECK 1
+#define CHECK_TTY_COUNT 1
+
+struct termios tty_std_termios; /* for the benefit of tty drivers */
+struct tty_driver *tty_drivers; /* linked list of tty drivers */
+struct tty_ldisc ldiscs[NR_LDISCS]; /* line disc dispatch table */
+
+#ifdef CONFIG_UNIX98_PTYS
+extern struct tty_driver ptm_driver[]; /* Unix98 pty masters; for /dev/ptmx */
+extern struct tty_driver pts_driver[]; /* Unix98 pty slaves; for /dev/ptmx */
+#endif
+
+/*
+ * redirect is the pseudo-tty that console output
+ * is redirected to if asked by TIOCCONS.
+ */
+struct tty_struct * redirect;
+
+static void initialize_tty_struct(struct tty_struct *tty);
+
+static ssize_t tty_read(struct file *, char *, size_t, loff_t *);
+static ssize_t tty_write(struct file *, const char *, size_t, loff_t *);
+static unsigned int tty_poll(struct file *, poll_table *);
+static int tty_open(struct inode *, struct file *);
+static int tty_release(struct inode *, struct file *);
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg);
+static int tty_fasync(int fd, struct file * filp, int on);
+extern int vme_scc_init (void);
+extern long vme_scc_console_init(void);
+extern int serial167_init(void);
+extern long serial167_console_init(void);
+extern void console_8xx_init(void);
+extern int rs_8xx_init(void);
+extern void mac_scc_console_init(void);
+extern void hwc_console_init(void);
+extern void hwc_tty_init(void);
+extern void con3215_init(void);
+extern void tty3215_init(void);
+extern void tub3270_con_init(void);
+extern void tub3270_init(void);
+extern void rs285_console_init(void);
+extern void sa1100_rs_console_init(void);
+extern void sgi_serial_console_init(void);
+extern void sci_console_init(void);
+extern void tx3912_console_init(void);
+extern void tx3912_rs_init(void);
+extern void txx927_console_init(void);
+extern void sb1250_serial_console_init(void);
+
+#ifndef MIN
+#define MIN(a,b) ((a) < (b) ? (a) : (b))
+#endif
+#ifndef MAX
+#define MAX(a,b) ((a) < (b) ? (b) : (a))
+#endif
+
+static struct tty_struct *alloc_tty_struct(void)
+{
+ struct tty_struct *tty;
+
+ tty = kmalloc(sizeof(struct tty_struct), GFP_KERNEL);
+ if (tty)
+ memset(tty, 0, sizeof(struct tty_struct));
+ return tty;
+}
+
+static inline void free_tty_struct(struct tty_struct *tty)
+{
+ kfree(tty);
+}
+
+/*
+ * This routine returns the name of tty.
+ */
+static char *
+_tty_make_name(struct tty_struct *tty, const char *name, char *buf)
+{
+ int idx = (tty)?MINOR(tty->device) - tty->driver.minor_start:0;
+
+ if (!tty) /* Hmm. NULL pointer. That's fun. */
+ strcpy(buf, "NULL tty");
+ else
+ sprintf(buf, name,
+ idx + tty->driver.name_base);
+
+ return buf;
+}
+
+#define TTY_NUMBER(tty) (MINOR((tty)->device) - (tty)->driver.minor_start + \
+ (tty)->driver.name_base)
+
+char *tty_name(struct tty_struct *tty, char *buf)
+{
+ return _tty_make_name(tty, (tty)?tty->driver.name:NULL, buf);
+}
+
+inline int tty_paranoia_check(struct tty_struct *tty, kdev_t device,
+ const char *routine)
+{
+#ifdef TTY_PARANOIA_CHECK
+ static const char badmagic[] = KERN_WARNING
+ "Warning: bad magic number for tty struct (%s) in %s\n";
+ static const char badtty[] = KERN_WARNING
+ "Warning: null TTY for (%s) in %s\n";
+
+ if (!tty) {
+ printk(badtty, kdevname(device), routine);
+ return 1;
+ }
+ if (tty->magic != TTY_MAGIC) {
+ printk(badmagic, kdevname(device), routine);
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+static int check_tty_count(struct tty_struct *tty, const char *routine)
+{
+#ifdef CHECK_TTY_COUNT
+ struct list_head *p;
+ int count = 0;
+
+ file_list_lock();
+ for(p = tty->tty_files.next; p != &tty->tty_files; p = p->next) {
+ if(list_entry(p, struct file, f_list)->private_data == tty)
+ count++;
+ }
+ file_list_unlock();
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_SLAVE &&
+ tty->link && tty->link->count)
+ count++;
+ if (tty->count != count) {
+ printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) "
+ "!= #fd's(%d) in %s\n",
+ kdevname(tty->device), tty->count, count, routine);
+ return count;
+ }
+#endif
+ return 0;
+}
+
+int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc)
+{
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ return -EINVAL;
+
+ if (new_ldisc) {
+ ldiscs[disc] = *new_ldisc;
+ ldiscs[disc].flags |= LDISC_FLAG_DEFINED;
+ ldiscs[disc].num = disc;
+ } else
+ memset(&ldiscs[disc], 0, sizeof(struct tty_ldisc));
+
+ return 0;
+}
+
+EXPORT_SYMBOL(tty_register_ldisc);
+
+/* Set the discipline of a tty line. */
+static int tty_set_ldisc(struct tty_struct *tty, int ldisc)
+{
+ int retval = 0;
+ struct tty_ldisc o_ldisc;
+ char buf[64];
+
+ if ((ldisc < N_TTY) || (ldisc >= NR_LDISCS))
+ return -EINVAL;
+ /* Eduardo Blanco <ejbs@cs.cs.com.uy> */
+ /* Cyrus Durgin <cider@speakeasy.org> */
+ if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED)) {
+ char modname [20];
+ sprintf(modname, "tty-ldisc-%d", ldisc);
+ request_module (modname);
+ }
+ if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED))
+ return -EINVAL;
+
+ if (tty->ldisc.num == ldisc)
+ return 0; /* We are already in the desired discipline */
+ o_ldisc = tty->ldisc;
+
+ tty_wait_until_sent(tty, 0);
+
+ /* Shutdown the current discipline. */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+
+ /* Now set up the new line discipline. */
+ tty->ldisc = ldiscs[ldisc];
+ tty->termios->c_line = ldisc;
+ if (tty->ldisc.open)
+ retval = (tty->ldisc.open)(tty);
+ if (retval < 0) {
+ tty->ldisc = o_ldisc;
+ tty->termios->c_line = tty->ldisc.num;
+ if (tty->ldisc.open && (tty->ldisc.open(tty) < 0)) {
+ tty->ldisc = ldiscs[N_TTY];
+ tty->termios->c_line = N_TTY;
+ if (tty->ldisc.open) {
+ int r = tty->ldisc.open(tty);
+
+ if (r < 0)
+ panic("Couldn't open N_TTY ldisc for "
+ "%s --- error %d.",
+ tty_name(tty, buf), r);
+ }
+ }
+ }
+ if (tty->ldisc.num != o_ldisc.num && tty->driver.set_ldisc)
+ tty->driver.set_ldisc(tty);
+ return retval;
+}
+
+/*
+ * This routine returns a tty driver structure, given a device number
+ */
+struct tty_driver *get_tty_driver(kdev_t device)
+{
+ int major, minor;
+ struct tty_driver *p;
+
+ minor = MINOR(device);
+ major = MAJOR(device);
+
+ for (p = tty_drivers; p; p = p->next) {
+ if (p->major != major)
+ continue;
+ if (minor < p->minor_start)
+ continue;
+ if (minor >= p->minor_start + p->num)
+ continue;
+ return p;
+ }
+ return NULL;
+}
+
+/*
+ * If we try to write to, or set the state of, a terminal and we're
+ * not in the foreground, send a SIGTTOU. If the signal is blocked or
+ * ignored, go ahead and perform the operation. (POSIX 7.2)
+ */
+int tty_check_change(struct tty_struct * tty)
+{
+ if (current->tty != tty)
+ return 0;
+ if (tty->pgrp <= 0) {
+ printk(KERN_WARNING "tty_check_change: tty->pgrp <= 0!\n");
+ return 0;
+ }
+ if (current->pgrp == tty->pgrp)
+ return 0;
+ if (is_ignored(SIGTTOU))
+ return 0;
+ if (is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ (void) kill_pg(current->pgrp,SIGTTOU,1);
+ return -ERESTARTSYS;
+}
+
+static ssize_t hung_up_tty_read(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ /* Can't seek (pread) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+ return 0;
+}
+
+static ssize_t hung_up_tty_write(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ /* Can't seek (pwrite) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+ return -EIO;
+}
+
+/* No kernel lock held - none needed ;) */
+static unsigned int hung_up_tty_poll(struct file * filp, poll_table * wait)
+{
+ return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM;
+}
+
+static int hung_up_tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
+}
+
+static struct file_operations tty_fops = {
+ llseek: no_llseek,
+ read: tty_read,
+ write: tty_write,
+ poll: tty_poll,
+ ioctl: tty_ioctl,
+ open: tty_open,
+ release: tty_release,
+ fasync: tty_fasync,
+};
+
+static struct file_operations hung_up_tty_fops = {
+ llseek: no_llseek,
+ read: hung_up_tty_read,
+ write: hung_up_tty_write,
+ poll: hung_up_tty_poll,
+ ioctl: hung_up_tty_ioctl,
+ release: tty_release,
+};
+
+/*
+ * This can be called by the "eventd" kernel thread. That is process synchronous,
+ * but doesn't hold any locks, so we need to make sure we have the appropriate
+ * locks for what we're doing..
+ */
+void do_tty_hangup(void *data)
+{
+ struct tty_struct *tty = (struct tty_struct *) data;
+ struct file * cons_filp = NULL;
+ struct task_struct *p;
+ struct list_head *l;
+ int closecount = 0, n;
+
+ if (!tty)
+ return;
+
+ /* inuse_filps is protected by the single kernel lock */
+ lock_kernel();
+
+ check_tty_count(tty, "do_tty_hangup");
+ file_list_lock();
+ for (l = tty->tty_files.next; l != &tty->tty_files; l = l->next) {
+ struct file * filp = list_entry(l, struct file, f_list);
+ if (filp->f_dentry->d_inode->i_rdev == CONSOLE_DEV ||
+ filp->f_dentry->d_inode->i_rdev == SYSCONS_DEV) {
+ cons_filp = filp;
+ continue;
+ }
+ if (filp->f_op != &tty_fops)
+ continue;
+ closecount++;
+ tty_fasync(-1, filp, 0); /* can't block */
+ filp->f_op = &hung_up_tty_fops;
+ }
+ file_list_unlock();
+
+ /* FIXME! What are the locking issues here? This may me overdoing things.. */
+ {
+ unsigned long flags;
+
+ save_flags(flags); cli();
+ if (tty->ldisc.flush_buffer)
+ tty->ldisc.flush_buffer(tty);
+ if (tty->driver.flush_buffer)
+ tty->driver.flush_buffer(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+ tty->ldisc.write_wakeup)
+ (tty->ldisc.write_wakeup)(tty);
+ restore_flags(flags);
+ }
+
+ wake_up_interruptible(&tty->write_wait);
+ wake_up_interruptible(&tty->read_wait);
+
+ /*
+ * Shutdown the current line discipline, and reset it to
+ * N_TTY.
+ */
+ if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS)
+ *tty->termios = tty->driver.init_termios;
+ if (tty->ldisc.num != ldiscs[N_TTY].num) {
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ tty->ldisc = ldiscs[N_TTY];
+ tty->termios->c_line = N_TTY;
+ if (tty->ldisc.open) {
+ int i = (tty->ldisc.open)(tty);
+ if (i < 0)
+ printk(KERN_ERR "do_tty_hangup: N_TTY open: "
+ "error %d\n", -i);
+ }
+ }
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((tty->session > 0) && (p->session == tty->session) &&
+ p->leader) {
+ send_sig(SIGHUP,p,1);
+ send_sig(SIGCONT,p,1);
+ if (tty->pgrp > 0)
+ p->tty_old_pgrp = tty->pgrp;
+ }
+ if (p->tty == tty)
+ p->tty = NULL;
+ }
+ read_unlock(&tasklist_lock);
+
+ tty->flags = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+ tty->ctrl_status = 0;
+ /*
+ * If one of the devices matches a console pointer, we
+ * cannot just call hangup() because that will cause
+ * tty->count and state->count to go out of sync.
+ * So we just call close() the right number of times.
+ */
+ if (cons_filp) {
+ if (tty->driver.close)
+ for (n = 0; n < closecount; n++)
+ tty->driver.close(tty, cons_filp);
+ } else if (tty->driver.hangup)
+ (tty->driver.hangup)(tty);
+ unlock_kernel();
+}
+
+void tty_hangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s hangup...\n", tty_name(tty, buf));
+#endif
+ schedule_task(&tty->tq_hangup);
+}
+
+void tty_vhangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s vhangup...\n", tty_name(tty, buf));
+#endif
+ do_tty_hangup((void *) tty);
+}
+
+int tty_hung_up_p(struct file * filp)
+{
+ return (filp->f_op == &hung_up_tty_fops);
+}
+
+/*
+ * This function is typically called only by the session leader, when
+ * it wants to disassociate itself from its controlling tty.
+ *
+ * It performs the following functions:
+ * (1) Sends a SIGHUP and SIGCONT to the foreground process group
+ * (2) Clears the tty from being controlling the session
+ * (3) Clears the controlling tty for all processes in the
+ * session group.
+ *
+ * The argument on_exit is set to 1 if called when a process is
+ * exiting; it is 0 if called by the ioctl TIOCNOTTY.
+ */
+void disassociate_ctty(int on_exit)
+{
+ struct tty_struct *tty = current->tty;
+ struct task_struct *p;
+ int tty_pgrp = -1;
+
+ if (tty) {
+ tty_pgrp = tty->pgrp;
+ if (on_exit && tty->driver.type != TTY_DRIVER_TYPE_PTY)
+ tty_vhangup(tty);
+ } else {
+ if (current->tty_old_pgrp) {
+ kill_pg(current->tty_old_pgrp, SIGHUP, on_exit);
+ kill_pg(current->tty_old_pgrp, SIGCONT, on_exit);
+ }
+ return;
+ }
+ if (tty_pgrp > 0) {
+ kill_pg(tty_pgrp, SIGHUP, on_exit);
+ if (!on_exit)
+ kill_pg(tty_pgrp, SIGCONT, on_exit);
+ }
+
+ current->tty_old_pgrp = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p)
+ if (p->session == current->session)
+ p->tty = NULL;
+ read_unlock(&tasklist_lock);
+}
+
+void stop_tty(struct tty_struct *tty)
+{
+ if (tty->stopped)
+ return;
+ tty->stopped = 1;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_START;
+ tty->ctrl_status |= TIOCPKT_STOP;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver.stop)
+ (tty->driver.stop)(tty);
+}
+
+void start_tty(struct tty_struct *tty)
+{
+ if (!tty->stopped || tty->flow_stopped)
+ return;
+ tty->stopped = 0;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_STOP;
+ tty->ctrl_status |= TIOCPKT_START;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver.start)
+ (tty->driver.start)(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+ tty->ldisc.write_wakeup)
+ (tty->ldisc.write_wakeup)(tty);
+ wake_up_interruptible(&tty->write_wait);
+}
+
+static ssize_t tty_read(struct file * file, char * buf, size_t count,
+ loff_t *ppos)
+{
+ int i;
+ struct tty_struct * tty;
+ struct inode *inode;
+
+ /* Can't seek (pread) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+
+ tty = (struct tty_struct *)file->private_data;
+ inode = file->f_dentry->d_inode;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_read"))
+ return -EIO;
+ if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+
+ /* This check not only needs to be done before reading, but also
+ whenever read_chan() gets woken up after sleeping, so I've
+ moved it to there. This should only be done for the N_TTY
+ line discipline, anyway. Same goes for write_chan(). -- jlc. */
+#if 0
+ if ((inode->i_rdev != CONSOLE_DEV) && /* don't stop on /dev/console */
+ (tty->pgrp > 0) &&
+ (current->tty == tty) &&
+ (tty->pgrp != current->pgrp))
+ if (is_ignored(SIGTTIN) || is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ else {
+ (void) kill_pg(current->pgrp, SIGTTIN, 1);
+ return -ERESTARTSYS;
+ }
+#endif
+ lock_kernel();
+ if (tty->ldisc.read)
+ i = (tty->ldisc.read)(tty,file,buf,count);
+ else
+ i = -EIO;
+ unlock_kernel();
+ if (i > 0)
+ inode->i_atime = CURRENT_TIME;
+ return i;
+}
+
+/*
+ * Split writes up in sane blocksizes to avoid
+ * denial-of-service type attacks
+ */
+static inline ssize_t do_tty_write(
+ ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t),
+ struct tty_struct *tty,
+ struct file *file,
+ const unsigned char *buf,
+ size_t count)
+{
+ ssize_t ret = 0, written = 0;
+
+ if (file->f_flags & O_NONBLOCK) {
+ if (down_trylock(&tty->atomic_write))
+ return -EAGAIN;
+ }
+ else {
+ if (down_interruptible(&tty->atomic_write))
+ return -ERESTARTSYS;
+ }
+ if ( test_bit(TTY_NO_WRITE_SPLIT, &tty->flags) ) {
+ lock_kernel();
+ written = write(tty, file, buf, count);
+ unlock_kernel();
+ } else {
+ for (;;) {
+ unsigned long size = MAX(PAGE_SIZE*2,16384);
+ if (size > count)
+ size = count;
+ lock_kernel();
+ ret = write(tty, file, buf, size);
+ unlock_kernel();
+ if (ret <= 0)
+ break;
+ written += ret;
+ buf += ret;
+ count -= ret;
+ if (!count)
+ break;
+ ret = -ERESTARTSYS;
+ if (signal_pending(current))
+ break;
+ if (current->need_resched)
+ schedule();
+ }
+ }
+ if (written) {
+ file->f_dentry->d_inode->i_mtime = CURRENT_TIME;
+ ret = written;
+ }
+ up(&tty->atomic_write);
+ return ret;
+}
+
+
+static ssize_t tty_write(struct file * file, const char * buf, size_t count,
+ loff_t *ppos)
+{
+ int is_console;
+ struct tty_struct * tty;
+ struct inode *inode;
+
+ /* Can't seek (pwrite) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+
+ /*
+ * For now, we redirect writes from /dev/console as
+ * well as /dev/tty0.
+ */
+ inode = file->f_dentry->d_inode;
+ is_console = (inode->i_rdev == SYSCONS_DEV ||
+ inode->i_rdev == CONSOLE_DEV);
+
+ if (is_console && redirect)
+ tty = redirect;
+ else
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_write"))
+ return -EIO;
+ if (!tty || !tty->driver.write || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+#if 0
+ if (!is_console && L_TOSTOP(tty) && (tty->pgrp > 0) &&
+ (current->tty == tty) && (tty->pgrp != current->pgrp)) {
+ if (is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ if (!is_ignored(SIGTTOU)) {
+ (void) kill_pg(current->pgrp, SIGTTOU, 1);
+ return -ERESTARTSYS;
+ }
+ }
+#endif
+ if (!tty->ldisc.write)
+ return -EIO;
+ return do_tty_write(tty->ldisc.write, tty, file,
+ (const unsigned char *)buf, count);
+}
+
+/* Semaphore to protect creating and releasing a tty */
+static DECLARE_MUTEX(tty_sem);
+
+static void down_tty_sem(int index)
+{
+ down(&tty_sem);
+}
+
+static void up_tty_sem(int index)
+{
+ up(&tty_sem);
+}
+
+static void release_mem(struct tty_struct *tty, int idx);
+
+/*
+ * WSH 06/09/97: Rewritten to remove races and properly clean up after a
+ * failed open. The new code protects the open with a semaphore, so it's
+ * really quite straightforward. The semaphore locking can probably be
+ * relaxed for the (most common) case of reopening a tty.
+ */
+static int init_dev(kdev_t device, struct tty_struct **ret_tty)
+{
+ struct tty_struct *tty, *o_tty;
+ struct termios *tp, **tp_loc, *o_tp, **o_tp_loc;
+ struct termios *ltp, **ltp_loc, *o_ltp, **o_ltp_loc;
+ struct tty_driver *driver;
+ int retval=0;
+ int idx;
+
+ driver = get_tty_driver(device);
+ if (!driver)
+ return -ENODEV;
+
+ idx = MINOR(device) - driver->minor_start;
+
+ /*
+ * Check whether we need to acquire the tty semaphore to avoid
+ * race conditions. For now, play it safe.
+ */
+ down_tty_sem(idx);
+
+ /* check whether we're reopening an existing tty */
+ tty = driver->table[idx];
+ if (tty) goto fast_track;
+
+ /*
+ * First time open is complex, especially for PTY devices.
+ * This code guarantees that either everything succeeds and the
+ * TTY is ready for operation, or else the table slots are vacated
+ * and the allocated memory released. (Except that the termios
+ * and locked termios may be retained.)
+ */
+
+ o_tty = NULL;
+ tp = o_tp = NULL;
+ ltp = o_ltp = NULL;
+
+ tty = alloc_tty_struct();
+ if(!tty)
+ goto fail_no_mem;
+ initialize_tty_struct(tty);
+ tty->device = device;
+ tty->driver = *driver;
+
+ tp_loc = &driver->termios[idx];
+ if (!*tp_loc) {
+ tp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!tp)
+ goto free_mem_out;
+ *tp = driver->init_termios;
+ }
+
+ ltp_loc = &driver->termios_locked[idx];
+ if (!*ltp_loc) {
+ ltp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!ltp)
+ goto free_mem_out;
+ memset(ltp, 0, sizeof(struct termios));
+ }
+
+ if (driver->type == TTY_DRIVER_TYPE_PTY) {
+ o_tty = alloc_tty_struct();
+ if (!o_tty)
+ goto free_mem_out;
+ initialize_tty_struct(o_tty);
+ o_tty->device = (kdev_t) MKDEV(driver->other->major,
+ driver->other->minor_start + idx);
+ o_tty->driver = *driver->other;
+
+ o_tp_loc = &driver->other->termios[idx];
+ if (!*o_tp_loc) {
+ o_tp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_tp)
+ goto free_mem_out;
+ *o_tp = driver->other->init_termios;
+ }
+
+ o_ltp_loc = &driver->other->termios_locked[idx];
+ if (!*o_ltp_loc) {
+ o_ltp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_ltp)
+ goto free_mem_out;
+ memset(o_ltp, 0, sizeof(struct termios));
+ }
+
+ /*
+ * Everything allocated ... set up the o_tty structure.
+ */
+ driver->other->table[idx] = o_tty;
+ if (!*o_tp_loc)
+ *o_tp_loc = o_tp;
+ if (!*o_ltp_loc)
+ *o_ltp_loc = o_ltp;
+ o_tty->termios = *o_tp_loc;
+ o_tty->termios_locked = *o_ltp_loc;
+ (*driver->other->refcount)++;
+ if (driver->subtype == PTY_TYPE_MASTER)
+ o_tty->count++;
+
+ /* Establish the links in both directions */
+ tty->link = o_tty;
+ o_tty->link = tty;
+ }
+
+ /*
+ * All structures have been allocated, so now we install them.
+ * Failures after this point use release_mem to clean up, so
+ * there's no need to null out the local pointers.
+ */
+ driver->table[idx] = tty;
+
+ if (!*tp_loc)
+ *tp_loc = tp;
+ if (!*ltp_loc)
+ *ltp_loc = ltp;
+ tty->termios = *tp_loc;
+ tty->termios_locked = *ltp_loc;
+ (*driver->refcount)++;
+ tty->count++;
+
+ /*
+ * Structures all installed ... call the ldisc open routines.
+ * If we fail here just call release_mem to clean up. No need
+ * to decrement the use counts, as release_mem doesn't care.
+ */
+ if (tty->ldisc.open) {
+ retval = (tty->ldisc.open)(tty);
+ if (retval)
+ goto release_mem_out;
+ }
+ if (o_tty && o_tty->ldisc.open) {
+ retval = (o_tty->ldisc.open)(o_tty);
+ if (retval) {
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ goto release_mem_out;
+ }
+ }
+ goto success;
+
+ /*
+ * This fast open can be used if the tty is already open.
+ * No memory is allocated, and the only failures are from
+ * attempting to open a closing tty or attempting multiple
+ * opens on a pty master.
+ */
+fast_track:
+ if (test_bit(TTY_CLOSING, &tty->flags)) {
+ retval = -EIO;
+ goto end_init;
+ }
+ if (driver->type == TTY_DRIVER_TYPE_PTY &&
+ driver->subtype == PTY_TYPE_MASTER) {
+ /*
+ * special case for PTY masters: only one open permitted,
+ * and the slave side open count is incremented as well.
+ */
+ if (tty->count) {
+ retval = -EIO;
+ goto end_init;
+ }
+ tty->link->count++;
+ }
+ tty->count++;
+ tty->driver = *driver; /* N.B. why do this every time?? */
+
+success:
+ *ret_tty = tty;
+
+ /* All paths come through here to release the semaphore */
+end_init:
+ up_tty_sem(idx);
+ return retval;
+
+ /* Release locally allocated memory ... nothing placed in slots */
+free_mem_out:
+ if (o_tp)
+ kfree(o_tp);
+ if (o_tty)
+ free_tty_struct(o_tty);
+ if (ltp)
+ kfree(ltp);
+ if (tp)
+ kfree(tp);
+ free_tty_struct(tty);
+
+fail_no_mem:
+ retval = -ENOMEM;
+ goto end_init;
+
+ /* call the tty release_mem routine to clean out this slot */
+release_mem_out:
+ printk(KERN_INFO "init_dev: ldisc open failed, "
+ "clearing slot %d\n", idx);
+ release_mem(tty, idx);
+ goto end_init;
+}
+
+/*
+ * Releases memory associated with a tty structure, and clears out the
+ * driver table slots.
+ */
+static void release_mem(struct tty_struct *tty, int idx)
+{
+ struct tty_struct *o_tty;
+ struct termios *tp;
+
+ if ((o_tty = tty->link) != NULL) {
+ o_tty->driver.table[idx] = NULL;
+ if (o_tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = o_tty->driver.termios[idx];
+ o_tty->driver.termios[idx] = NULL;
+ kfree(tp);
+ }
+ o_tty->magic = 0;
+ (*o_tty->driver.refcount)--;
+ list_del(&o_tty->tty_files);
+ free_tty_struct(o_tty);
+ }
+
+ tty->driver.table[idx] = NULL;
+ if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = tty->driver.termios[idx];
+ tty->driver.termios[idx] = NULL;
+ kfree(tp);
+ }
+ tty->magic = 0;
+ (*tty->driver.refcount)--;
+ list_del(&tty->tty_files);
+ free_tty_struct(tty);
+}
+
+/*
+ * Even releasing the tty structures is a tricky business.. We have
+ * to be very careful that the structures are all released at the
+ * same time, as interrupts might otherwise get the wrong pointers.
+ *
+ * WSH 09/09/97: rewritten to avoid some nasty race conditions that could
+ * lead to double frees or releasing memory still in use.
+ */
+static void release_dev(struct file * filp)
+{
+ struct tty_struct *tty, *o_tty;
+ int pty_master, tty_closing, o_tty_closing, do_sleep;
+ int idx;
+ char buf[64];
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "release_dev"))
+ return;
+
+ check_tty_count(tty, "release_dev");
+
+ tty_fasync(-1, filp, 0);
+
+ idx = MINOR(tty->device) - tty->driver.minor_start;
+ pty_master = (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER);
+ o_tty = tty->link;
+
+#ifdef TTY_PARANOIA_CHECK
+ if (idx < 0 || idx >= tty->driver.num) {
+ printk(KERN_DEBUG "release_dev: bad idx when trying to "
+ "free (%s)\n", kdevname(tty->device));
+ return;
+ }
+ if (tty != tty->driver.table[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.table[%d] not tty "
+ "for (%s)\n", idx, kdevname(tty->device));
+ return;
+ }
+ if (tty->termios != tty->driver.termios[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios[%d] not termios "
+ "for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (tty->termios_locked != tty->driver.termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios_locked[%d] not "
+ "termios_locked for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+#endif
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "release_dev of %s (tty count=%d)...",
+ tty_name(tty, buf), tty->count);
+#endif
+
+#ifdef TTY_PARANOIA_CHECK
+ if (tty->driver.other) {
+ if (o_tty != tty->driver.other->table[idx]) {
+ printk(KERN_DEBUG "release_dev: other->table[%d] "
+ "not o_tty for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->termios != tty->driver.other->termios[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios[%d] "
+ "not o_termios for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->termios_locked !=
+ tty->driver.other->termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios_locked["
+ "%d] not o_termios_locked for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->link != tty) {
+ printk(KERN_DEBUG "release_dev: bad pty pointers\n");
+ return;
+ }
+ }
+#endif
+
+ if (tty->driver.close)
+ tty->driver.close(tty, filp);
+
+ /*
+ * Sanity check: if tty->count is going to zero, there shouldn't be
+ * any waiters on tty->read_wait or tty->write_wait. We test the
+ * wait queues and kick everyone out _before_ actually starting to
+ * close. This ensures that we won't block while releasing the tty
+ * structure.
+ *
+ * The test for the o_tty closing is necessary, since the master and
+ * slave sides may close in any order. If the slave side closes out
+ * first, its count will be one, since the master side holds an open.
+ * Thus this test wouldn't be triggered at the time the slave closes,
+ * so we do it now.
+ *
+ * Note that it's possible for the tty to be opened again while we're
+ * flushing out waiters. By recalculating the closing flags before
+ * each iteration we avoid any problems.
+ */
+ while (1) {
+ tty_closing = tty->count <= 1;
+ o_tty_closing = o_tty &&
+ (o_tty->count <= (pty_master ? 1 : 0));
+ do_sleep = 0;
+
+ if (tty_closing) {
+ if (waitqueue_active(&tty->read_wait)) {
+ wake_up(&tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&tty->write_wait)) {
+ wake_up(&tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (o_tty_closing) {
+ if (waitqueue_active(&o_tty->read_wait)) {
+ wake_up(&o_tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&o_tty->write_wait)) {
+ wake_up(&o_tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (!do_sleep)
+ break;
+
+ printk(KERN_WARNING "release_dev: %s: read/write wait queue "
+ "active!\n", tty_name(tty, buf));
+ schedule();
+ }
+
+ /*
+ * The closing flags are now consistent with the open counts on
+ * both sides, and we've completed the last operation that could
+ * block, so it's safe to proceed with closing.
+ */
+ if (pty_master) {
+ if (--o_tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad pty slave count "
+ "(%d) for %s\n",
+ o_tty->count, tty_name(o_tty, buf));
+ o_tty->count = 0;
+ }
+ }
+ if (--tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad tty->count (%d) for %s\n",
+ tty->count, tty_name(tty, buf));
+ tty->count = 0;
+ }
+
+ /*
+ * We've decremented tty->count, so we should zero out
+ * filp->private_data, to break the link between the tty and
+ * the file descriptor. Otherwise if filp_close() blocks before
+ * the file descriptor is removed from the inuse_filp
+ * list, check_tty_count() could observe a discrepancy and
+ * printk a warning message to the user.
+ */
+ filp->private_data = 0;
+
+ /*
+ * Perform some housekeeping before deciding whether to return.
+ *
+ * Set the TTY_CLOSING flag if this was the last open. In the
+ * case of a pty we may have to wait around for the other side
+ * to close, and TTY_CLOSING makes sure we can't be reopened.
+ */
+ if(tty_closing)
+ set_bit(TTY_CLOSING, &tty->flags);
+ if(o_tty_closing)
+ set_bit(TTY_CLOSING, &o_tty->flags);
+
+ /*
+ * If _either_ side is closing, make sure there aren't any
+ * processes that still think tty or o_tty is their controlling
+ * tty. Also, clear redirect if it points to either tty.
+ */
+ if (tty_closing || o_tty_closing) {
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if (p->tty == tty || (o_tty && p->tty == o_tty))
+ p->tty = NULL;
+ }
+ read_unlock(&tasklist_lock);
+
+ if (redirect == tty || (o_tty && redirect == o_tty))
+ redirect = NULL;
+ }
+
+ /* check whether both sides are closing ... */
+ if (!tty_closing || (o_tty && !o_tty_closing))
+ return;
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "freeing tty structure...");
+#endif
+
+ /*
+ * Shutdown the current line discipline, and reset it to N_TTY.
+ * N.B. why reset ldisc when we're releasing the memory??
+ */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ tty->ldisc = ldiscs[N_TTY];
+ tty->termios->c_line = N_TTY;
+ if (o_tty) {
+ if (o_tty->ldisc.close)
+ (o_tty->ldisc.close)(o_tty);
+ o_tty->ldisc = ldiscs[N_TTY];
+ }
+
+ /*
+ * Make sure that the tty's task queue isn't activated.
+ */
+ run_task_queue(&tq_timer);
+ flush_scheduled_tasks();
+
+ /*
+ * The release_mem function takes care of the details of clearing
+ * the slots and preserving the termios structure.
+ */
+ release_mem(tty, idx);
+}
+
+/*
+ * tty_open and tty_release keep up the tty count that contains the
+ * number of opens done on a tty. We cannot use the inode-count, as
+ * different inodes might point to the same tty.
+ *
+ * Open-counting is needed for pty masters, as well as for keeping
+ * track of serial lines: DTR is dropped when the last close happens.
+ * (This is not done solely through tty->count, now. - Ted 1/27/92)
+ *
+ * The termios state of a pty is reset on first open so that
+ * settings don't persist across reuse.
+ */
+static int tty_open(struct inode * inode, struct file * filp)
+{
+ struct tty_struct *tty;
+ int noctty, retval;
+ kdev_t device;
+ unsigned short saved_flags;
+ char buf[64];
+
+ saved_flags = filp->f_flags;
+retry_open:
+ noctty = filp->f_flags & O_NOCTTY;
+ device = inode->i_rdev;
+ if (device == TTY_DEV) {
+ if (!current->tty)
+ return -ENXIO;
+ device = current->tty->device;
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */
+ /* noctty = 1; */
+ }
+#ifdef CONFIG_VT
+ if (device == CONSOLE_DEV) {
+ extern int fg_console;
+ device = MKDEV(TTY_MAJOR, fg_console + 1);
+ noctty = 1;
+ }
+#endif
+ if (device == SYSCONS_DEV) {
+ struct console *c = console_drivers;
+ while(c && !c->device)
+ c = c->next;
+ if (!c)
+ return -ENODEV;
+ device = c->device(c);
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/console block */
+ noctty = 1;
+ }
+
+ if (device == PTMX_DEV) {
+#ifdef CONFIG_UNIX98_PTYS
+
+ /* find a free pty. */
+ int major, minor;
+ struct tty_driver *driver;
+
+ /* find a device that is not in use. */
+ retval = -1;
+ for ( major = 0 ; major < UNIX98_NR_MAJORS ; major++ ) {
+ driver = &ptm_driver[major];
+ for (minor = driver->minor_start ;
+ minor < driver->minor_start + driver->num ;
+ minor++) {
+ device = MKDEV(driver->major, minor);
+ if (!init_dev(device, &tty)) goto ptmx_found; /* ok! */
+ }
+ }
+ return -EIO; /* no free ptys */
+ ptmx_found:
+ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
+ minor -= driver->minor_start;
+ devpts_pty_new(driver->other->name_base + minor, MKDEV(driver->other->major, minor + driver->other->minor_start));
+ tty_register_devfs(&pts_driver[major], DEVFS_FL_DEFAULT,
+ pts_driver[major].minor_start + minor);
+ noctty = 1;
+ goto init_dev_done;
+
+#else /* CONFIG_UNIX_98_PTYS */
+
+ return -ENODEV;
+
+#endif /* CONFIG_UNIX_98_PTYS */
+ }
+
+ retval = init_dev(device, &tty);
+ if (retval)
+ return retval;
+
+#ifdef CONFIG_UNIX98_PTYS
+init_dev_done:
+#endif
+ filp->private_data = tty;
+ file_move(filp, &tty->tty_files);
+ check_tty_count(tty, "tty_open");
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER)
+ noctty = 1;
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "opening %s...", tty_name(tty, buf));
+#endif
+ if (tty->driver.open)
+ retval = tty->driver.open(tty, filp);
+ else
+ retval = -ENODEV;
+ filp->f_flags = saved_flags;
+
+ if (!retval && test_bit(TTY_EXCLUSIVE, &tty->flags) && !suser())
+ retval = -EBUSY;
+
+ if (retval) {
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "error %d in opening %s...", retval,
+ tty_name(tty, buf));
+#endif
+
+ release_dev(filp);
+ if (retval != -ERESTARTSYS)
+ return retval;
+ if (signal_pending(current))
+ return retval;
+ schedule();
+ /*
+ * Need to reset f_op in case a hangup happened.
+ */
+ filp->f_op = &tty_fops;
+ goto retry_open;
+ }
+ if (!noctty &&
+ current->leader &&
+ !current->tty &&
+ tty->session == 0) {
+ task_lock(current);
+ current->tty = tty;
+ task_unlock(current);
+ current->tty_old_pgrp = 0;
+ tty->session = current->session;
+ tty->pgrp = current->pgrp;
+ }
+ if ((tty->driver.type == TTY_DRIVER_TYPE_SERIAL) &&
+ (tty->driver.subtype == SERIAL_TYPE_CALLOUT) &&
+ (tty->count == 1)) {
+ static int nr_warns;
+ if (nr_warns < 5) {
+ printk(KERN_WARNING "tty_io.c: "
+ "process %d (%s) used obsolete /dev/%s - "
+ "update software to use /dev/ttyS%d\n",
+ current->pid, current->comm,
+ tty_name(tty, buf), TTY_NUMBER(tty));
+ nr_warns++;
+ }
+ }
+ return 0;
+}
+
+static int tty_release(struct inode * inode, struct file * filp)
+{
+ lock_kernel();
+ release_dev(filp);
+ unlock_kernel();
+ return 0;
+}
+
+/* No kernel lock held - fine */
+static unsigned int tty_poll(struct file * filp, poll_table * wait)
+{
+ struct tty_struct * tty;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_poll"))
+ return 0;
+
+ if (tty->ldisc.poll)
+ return (tty->ldisc.poll)(tty, filp, wait);
+ return 0;
+}
+
+static int tty_fasync(int fd, struct file * filp, int on)
+{
+ struct tty_struct * tty;
+ int retval;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_fasync"))
+ return 0;
+
+ retval = fasync_helper(fd, filp, on, &tty->fasync);
+ if (retval <= 0)
+ return retval;
+
+ if (on) {
+ if (!waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = 1;
+ if (filp->f_owner.pid == 0) {
+ filp->f_owner.pid = (-tty->pgrp) ? : current->pid;
+ filp->f_owner.uid = current->uid;
+ filp->f_owner.euid = current->euid;
+ }
+ } else {
+ if (!tty->fasync && !waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = N_TTY_BUF_SIZE;
+ }
+ return 0;
+}
+
+static int tiocsti(struct tty_struct *tty, char * arg)
+{
+ char ch, mbz = 0;
+
+ if ((current->tty != tty) && !suser())
+ return -EPERM;
+ if (get_user(ch, arg))
+ return -EFAULT;
+ tty->ldisc.receive_buf(tty, &ch, &mbz, 1);
+ return 0;
+}
+
+static int tiocgwinsz(struct tty_struct *tty, struct winsize * arg)
+{
+ if (copy_to_user(arg, &tty->winsize, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocswinsz(struct tty_struct *tty, struct tty_struct *real_tty,
+ struct winsize * arg)
+{
+ struct winsize tmp_ws;
+
+ if (copy_from_user(&tmp_ws, arg, sizeof(*arg)))
+ return -EFAULT;
+ if (!memcmp(&tmp_ws, &tty->winsize, sizeof(*arg)))
+ return 0;
+ if (tty->pgrp > 0)
+ kill_pg(tty->pgrp, SIGWINCH, 1);
+ if ((real_tty->pgrp != tty->pgrp) && (real_tty->pgrp > 0))
+ kill_pg(real_tty->pgrp, SIGWINCH, 1);
+ tty->winsize = tmp_ws;
+ real_tty->winsize = tmp_ws;
+ return 0;
+}
+
+static int tioccons(struct inode *inode,
+ struct tty_struct *tty, struct tty_struct *real_tty)
+{
+ if (inode->i_rdev == SYSCONS_DEV ||
+ inode->i_rdev == CONSOLE_DEV) {
+ if (!suser())
+ return -EPERM;
+ redirect = NULL;
+ return 0;
+ }
+ if (redirect)
+ return -EBUSY;
+ redirect = real_tty;
+ return 0;
+}
+
+
+static int fionbio(struct file *file, int *arg)
+{
+ int nonblock;
+
+ if (get_user(nonblock, arg))
+ return -EFAULT;
+
+ if (nonblock)
+ file->f_flags |= O_NONBLOCK;
+ else
+ file->f_flags &= ~O_NONBLOCK;
+ return 0;
+}
+
+static int tiocsctty(struct tty_struct *tty, int arg)
+{
+ if (current->leader &&
+ (current->session == tty->session))
+ return 0;
+ /*
+ * The process must be a session leader and
+ * not have a controlling tty already.
+ */
+ if (!current->leader || current->tty)
+ return -EPERM;
+ if (tty->session > 0) {
+ /*
+ * This tty is already the controlling
+ * tty for another session group!
+ */
+ if ((arg == 1) && suser()) {
+ /*
+ * Steal it away
+ */
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p)
+ if (p->tty == tty)
+ p->tty = NULL;
+ read_unlock(&tasklist_lock);
+ } else
+ return -EPERM;
+ }
+ task_lock(current);
+ current->tty = tty;
+ task_unlock(current);
+ current->tty_old_pgrp = 0;
+ tty->session = current->session;
+ tty->pgrp = current->pgrp;
+ return 0;
+}
+
+static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->tty != real_tty)
+ return -ENOTTY;
+ return put_user(real_tty->pgrp, arg);
+}
+
+static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
+{
+ pid_t pgrp;
+ int retval = tty_check_change(real_tty);
+
+ if (retval == -EIO)
+ return -ENOTTY;
+ if (retval)
+ return retval;
+ if (!current->tty ||
+ (current->tty != real_tty) ||
+ (real_tty->session != current->session))
+ return -ENOTTY;
+ if (get_user(pgrp, (pid_t *) arg))
+ return -EFAULT;
+ if (pgrp < 0)
+ return -EINVAL;
+ if (session_of_pgrp(pgrp) != current->session)
+ return -EPERM;
+ real_tty->pgrp = pgrp;
+ return 0;
+}
+
+static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->tty != real_tty)
+ return -ENOTTY;
+ if (real_tty->session <= 0)
+ return -ENOTTY;
+ return put_user(real_tty->session, arg);
+}
+
+static int tiocttygstruct(struct tty_struct *tty, struct tty_struct *arg)
+{
+ if (copy_to_user(arg, tty, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocsetd(struct tty_struct *tty, int *arg)
+{
+ int ldisc;
+
+ if (get_user(ldisc, arg))
+ return -EFAULT;
+ return tty_set_ldisc(tty, ldisc);
+}
+
+static int send_break(struct tty_struct *tty, int duration)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ tty->driver.break_ctl(tty, -1);
+ if (!signal_pending(current))
+ schedule_timeout(duration);
+ tty->driver.break_ctl(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ return 0;
+}
+
+static int tty_generic_brk(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg)
+{
+ if (cmd == TCSBRK && arg)
+ {
+ /* tcdrain case */
+ int retval = tty_check_change(tty);
+ if (retval)
+ return retval;
+ tty_wait_until_sent(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ return 0;
+}
+
+/*
+ * Split this up, as gcc can choke on it otherwise..
+ */
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ struct tty_struct *tty, *real_tty;
+ int retval;
+
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_ioctl"))
+ return -EINVAL;
+
+ real_tty = tty;
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER)
+ real_tty = tty->link;
+
+ /*
+ * Break handling by driver
+ */
+ if (!tty->driver.break_ctl) {
+ switch(cmd) {
+ case TIOCSBRK:
+ case TIOCCBRK:
+ if (tty->driver.ioctl)
+ return tty->driver.ioctl(tty, file, cmd, arg);
+ return -EINVAL;
+
+ /* These two ioctl's always return success; even if */
+ /* the driver doesn't support them. */
+ case TCSBRK:
+ case TCSBRKP:
+ retval = -ENOIOCTLCMD;
+ if (tty->driver.ioctl)
+ retval = tty->driver.ioctl(tty, file, cmd, arg);
+ /* Not driver handled */
+ if (retval == -ENOIOCTLCMD)
+ retval = tty_generic_brk(tty, file, cmd, arg);
+ return retval;
+ }
+ }
+
+ /*
+ * Factor out some common prep work
+ */
+ switch (cmd) {
+ case TIOCSETD:
+ case TIOCSBRK:
+ case TIOCCBRK:
+ case TCSBRK:
+ case TCSBRKP:
+ retval = tty_check_change(tty);
+ if (retval)
+ return retval;
+ if (cmd != TIOCCBRK) {
+ tty_wait_until_sent(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ break;
+ }
+
+ switch (cmd) {
+ case TIOCSTI:
+ return tiocsti(tty, (char *)arg);
+ case TIOCGWINSZ:
+ return tiocgwinsz(tty, (struct winsize *) arg);
+ case TIOCSWINSZ:
+ return tiocswinsz(tty, real_tty, (struct winsize *) arg);
+ case TIOCCONS:
+ return tioccons(inode, tty, real_tty);
+ case FIONBIO:
+ return fionbio(file, (int *) arg);
+ case TIOCEXCL:
+ set_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNXCL:
+ clear_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNOTTY:
+ if (current->tty != tty)
+ return -ENOTTY;
+ if (current->leader)
+ disassociate_ctty(0);
+ task_lock(current);
+ current->tty = NULL;
+ task_unlock(current);
+ return 0;
+ case TIOCSCTTY:
+ return tiocsctty(tty, arg);
+ case TIOCGPGRP:
+ return tiocgpgrp(tty, real_tty, (pid_t *) arg);
+ case TIOCSPGRP:
+ return tiocspgrp(tty, real_tty, (pid_t *) arg);
+ case TIOCGSID:
+ return tiocgsid(tty, real_tty, (pid_t *) arg);
+ case TIOCGETD:
+ return put_user(tty->ldisc.num, (int *) arg);
+ case TIOCSETD:
+ return tiocsetd(tty, (int *) arg);
+#ifdef CONFIG_VT
+ case TIOCLINUX:
+ return tioclinux(tty, arg);
+#endif
+ case TIOCTTYGSTRUCT:
+ return tiocttygstruct(tty, (struct tty_struct *) arg);
+
+ /*
+ * Break handling
+ */
+ case TIOCSBRK: /* Turn break on, unconditionally */
+ tty->driver.break_ctl(tty, -1);
+ return 0;
+
+ case TIOCCBRK: /* Turn break off, unconditionally */
+ tty->driver.break_ctl(tty, 0);
+ return 0;
+ case TCSBRK: /* SVID version: non-zero arg --> no break */
+ /*
+ * XXX is the above comment correct, or the
+ * code below correct? Is this ioctl used at
+ * all by anyone?
+ */
+ if (!arg)
+ return send_break(tty, HZ/4);
+ return 0;
+ case TCSBRKP: /* support for POSIX tcsendbreak() */
+ return send_break(tty, arg ? arg*(HZ/10) : HZ/4);
+ }
+ if (tty->driver.ioctl) {
+ int retval = (tty->driver.ioctl)(tty, file, cmd, arg);
+ if (retval != -ENOIOCTLCMD)
+ return retval;
+ }
+ if (tty->ldisc.ioctl) {
+ int retval = (tty->ldisc.ioctl)(tty, file, cmd, arg);
+ if (retval != -ENOIOCTLCMD)
+ return retval;
+ }
+ return -EINVAL;
+}
+
+
+/*
+ * This implements the "Secure Attention Key" --- the idea is to
+ * prevent trojan horses by killing all processes associated with this
+ * tty when the user hits the "Secure Attention Key". Required for
+ * super-paranoid applications --- see the Orange Book for more details.
+ *
+ * This code could be nicer; ideally it should send a HUP, wait a few
+ * seconds, then send a INT, and then a KILL signal. But you then
+ * have to coordinate with the init process, since all processes associated
+ * with the current tty must be dead before the new getty is allowed
+ * to spawn.
+ *
+ * Now, if it would be correct ;-/ The current code has a nasty hole -
+ * it doesn't catch files in flight. We may send the descriptor to ourselves
+ * via AF_UNIX socket, close it and later fetch from socket. FIXME.
+ *
+ * Nasty bug: do_SAK is being called in interrupt context. This can
+ * deadlock. We punt it up to process context. AKPM - 16Mar2001
+ */
+static void __do_SAK(void *arg)
+{
+#ifdef TTY_SOFT_SAK
+ tty_hangup(tty);
+#else
+ struct tty_struct *tty = arg;
+ struct task_struct *p;
+ int session;
+ int i;
+ struct file *filp;
+
+ if (!tty)
+ return;
+ session = tty->session;
+ if (tty->ldisc.flush_buffer)
+ tty->ldisc.flush_buffer(tty);
+ if (tty->driver.flush_buffer)
+ tty->driver.flush_buffer(tty);
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((p->tty == tty) ||
+ ((session > 0) && (p->session == session))) {
+ send_sig(SIGKILL, p, 1);
+ continue;
+ }
+ task_lock(p);
+ if (p->files) {
+ read_lock(&p->files->file_lock);
+ for (i=0; i < p->files->max_fds; i++) {
+ filp = fcheck_files(p->files, i);
+ if (filp && (filp->f_op == &tty_fops) &&
+ (filp->private_data == tty)) {
+ send_sig(SIGKILL, p, 1);
+ break;
+ }
+ }
+ read_unlock(&p->files->file_lock);
+ }
+ task_unlock(p);
+ }
+ read_unlock(&tasklist_lock);
+#endif
+}
+
+/*
+ * The tq handling here is a little racy - tty->SAK_tq may already be queued.
+ * But there's no mechanism to fix that without futzing with tqueue_lock.
+ * Fortunately we don't need to worry, because if ->SAK_tq is already queued,
+ * the values which we write to it will be identical to the values which it
+ * already has. --akpm
+ */
+void do_SAK(struct tty_struct *tty)
+{
+ if (!tty)
+ return;
+ PREPARE_TQUEUE(&tty->SAK_tq, __do_SAK, tty);
+ schedule_task(&tty->SAK_tq);
+}
+
+/*
+ * This routine is called out of the software interrupt to flush data
+ * from the flip buffer to the line discipline.
+ */
+static void flush_to_ldisc(void *private_)
+{
+ struct tty_struct *tty = (struct tty_struct *) private_;
+ unsigned char *cp;
+ char *fp;
+ int count;
+ unsigned long flags;
+
+ if (test_bit(TTY_DONT_FLIP, &tty->flags)) {
+ queue_task(&tty->flip.tqueue, &tq_timer);
+ return;
+ }
+ if (tty->flip.buf_num) {
+ cp = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ fp = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.buf_num = 0;
+
+ save_flags(flags); cli();
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ } else {
+ cp = tty->flip.char_buf;
+ fp = tty->flip.flag_buf;
+ tty->flip.buf_num = 1;
+
+ save_flags(flags); cli();
+ tty->flip.char_buf_ptr = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ }
+ count = tty->flip.count;
+ tty->flip.count = 0;
+ restore_flags(flags);
+
+ tty->ldisc.receive_buf(tty, cp, fp, count);
+}
+
+/*
+ * Routine which returns the baud rate of the tty
+ *
+ * Note that the baud_table needs to be kept in sync with the
+ * include/asm/termbits.h file.
+ */
+static int baud_table[] = {
+ 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800,
+ 9600, 19200, 38400, 57600, 115200, 230400, 460800,
+#ifdef __sparc__
+ 76800, 153600, 307200, 614400, 921600
+#else
+ 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000,
+ 2500000, 3000000, 3500000, 4000000
+#endif
+};
+
+static int n_baud_table = sizeof(baud_table)/sizeof(int);
+
+int tty_get_baud_rate(struct tty_struct *tty)
+{
+ unsigned int cflag, i;
+
+ cflag = tty->termios->c_cflag;
+
+ i = cflag & CBAUD;
+ if (i & CBAUDEX) {
+ i &= ~CBAUDEX;
+ if (i < 1 || i+15 >= n_baud_table)
+ tty->termios->c_cflag &= ~CBAUDEX;
+ else
+ i += 15;
+ }
+ if (i==15 && tty->alt_speed) {
+ if (!tty->warned) {
+ printk(KERN_WARNING "Use of setserial/setrocket to "
+ "set SPD_* flags is deprecated\n");
+ tty->warned = 1;
+ }
+ return(tty->alt_speed);
+ }
+
+ return baud_table[i];
+}
+
+void tty_flip_buffer_push(struct tty_struct *tty)
+{
+ if (tty->low_latency)
+ flush_to_ldisc((void *) tty);
+ else
+ queue_task(&tty->flip.tqueue, &tq_timer);
+}
+
+/*
+ * This subroutine initializes a tty structure.
+ */
+static void initialize_tty_struct(struct tty_struct *tty)
+{
+ memset(tty, 0, sizeof(struct tty_struct));
+ tty->magic = TTY_MAGIC;
+ tty->ldisc = ldiscs[N_TTY];
+ tty->pgrp = -1;
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ tty->flip.tqueue.routine = flush_to_ldisc;
+ tty->flip.tqueue.data = tty;
+ init_MUTEX(&tty->flip.pty_sem);
+ init_waitqueue_head(&tty->write_wait);
+ init_waitqueue_head(&tty->read_wait);
+ tty->tq_hangup.routine = do_tty_hangup;
+ tty->tq_hangup.data = tty;
+ sema_init(&tty->atomic_read, 1);
+ sema_init(&tty->atomic_write, 1);
+ spin_lock_init(&tty->read_lock);
+ INIT_LIST_HEAD(&tty->tty_files);
+ INIT_TQUEUE(&tty->SAK_tq, 0, 0);
+}
+
+/*
+ * The default put_char routine if the driver did not define one.
+ */
+void tty_default_put_char(struct tty_struct *tty, unsigned char ch)
+{
+ tty->driver.write(tty, 0, &ch, 1);
+}
+
+/*
+ * Register a tty device described by <driver>, with minor number <minor>.
+ */
+void tty_register_devfs (struct tty_driver *driver, unsigned int flags, unsigned minor)
+{
+#ifdef CONFIG_DEVFS_FS
+ umode_t mode = S_IFCHR | S_IRUSR | S_IWUSR;
+ kdev_t device = MKDEV (driver->major, minor);
+ int idx = minor - driver->minor_start;
+ char buf[32];
+
+ switch (device) {
+ case TTY_DEV:
+ case PTMX_DEV:
+ mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+ break;
+ default:
+ if (driver->major == PTY_MASTER_MAJOR)
+ mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+ break;
+ }
+ if ( (minor < driver->minor_start) ||
+ (minor >= driver->minor_start + driver->num) ) {
+ printk(KERN_ERR "Attempt to register invalid minor number "
+ "with devfs (%d:%d).\n", (int)driver->major,(int)minor);
+ return;
+ }
+# ifdef CONFIG_UNIX98_PTYS
+ if ( (driver->major >= UNIX98_PTY_SLAVE_MAJOR) &&
+ (driver->major < UNIX98_PTY_SLAVE_MAJOR + UNIX98_NR_MAJORS) )
+ flags |= DEVFS_FL_CURRENT_OWNER;
+# endif
+ sprintf(buf, driver->name, idx + driver->name_base);
+ devfs_register (NULL, buf, flags | DEVFS_FL_DEFAULT,
+ driver->major, minor, mode, &tty_fops, NULL);
+#endif /* CONFIG_DEVFS_FS */
+}
+
+void tty_unregister_devfs (struct tty_driver *driver, unsigned minor)
+{
+#ifdef CONFIG_DEVFS_FS
+ void * handle;
+ int idx = minor - driver->minor_start;
+ char buf[32];
+
+ sprintf(buf, driver->name, idx + driver->name_base);
+ handle = devfs_find_handle (NULL, buf, driver->major, minor,
+ DEVFS_SPECIAL_CHR, 0);
+ devfs_unregister (handle);
+#endif /* CONFIG_DEVFS_FS */
+}
+
+EXPORT_SYMBOL(tty_register_devfs);
+EXPORT_SYMBOL(tty_unregister_devfs);
+
+/*
+ * Called by a tty driver to register itself.
+ */
+int tty_register_driver(struct tty_driver *driver)
+{
+ int error;
+ int i;
+
+ if (driver->flags & TTY_DRIVER_INSTALLED)
+ return 0;
+
+ error = devfs_register_chrdev(driver->major, driver->name, &tty_fops);
+ if (error < 0)
+ return error;
+ else if(driver->major == 0)
+ driver->major = error;
+
+ if (!driver->put_char)
+ driver->put_char = tty_default_put_char;
+
+ driver->prev = 0;
+ driver->next = tty_drivers;
+ if (tty_drivers) tty_drivers->prev = driver;
+ tty_drivers = driver;
+
+ if ( !(driver->flags & TTY_DRIVER_NO_DEVFS) ) {
+ for(i = 0; i < driver->num; i++)
+ tty_register_devfs(driver, 0, driver->minor_start + i);
+ }
+ proc_tty_register_driver(driver);
+ return error;
+}
+
+/*
+ * Called by a tty driver to unregister itself.
+ */
+int tty_unregister_driver(struct tty_driver *driver)
+{
+ int retval;
+ struct tty_driver *p;
+ int i, found = 0;
+ struct termios *tp;
+ const char *othername = NULL;
+
+ if (*driver->refcount)
+ return -EBUSY;
+
+ for (p = tty_drivers; p; p = p->next) {
+ if (p == driver)
+ found++;
+ else if (p->major == driver->major)
+ othername = p->name;
+ }
+
+ if (!found)
+ return -ENOENT;
+
+ if (othername == NULL) {
+ retval = devfs_unregister_chrdev(driver->major, driver->name);
+ if (retval)
+ return retval;
+ } else
+ devfs_register_chrdev(driver->major, othername, &tty_fops);
+
+ if (driver->prev)
+ driver->prev->next = driver->next;
+ else
+ tty_drivers = driver->next;
+
+ if (driver->next)
+ driver->next->prev = driver->prev;
+
+ /*
+ * Free the termios and termios_locked structures because
+ * we don't want to get memory leaks when modular tty
+ * drivers are removed from the kernel.
+ */
+ for (i = 0; i < driver->num; i++) {
+ tp = driver->termios[i];
+ if (tp) {
+ driver->termios[i] = NULL;
+ kfree(tp);
+ }
+ tp = driver->termios_locked[i];
+ if (tp) {
+ driver->termios_locked[i] = NULL;
+ kfree(tp);
+ }
+ tty_unregister_devfs(driver, driver->minor_start + i);
+ }
+ proc_tty_unregister_driver(driver);
+ return 0;
+}
+
+
+/*
+ * Initialize the console device. This is called *early*, so
+ * we can't necessarily depend on lots of kernel help here.
+ * Just do some early initializations, and do the complex setup
+ * later.
+ */
+void __init console_init(void)
+{
+ /* Setup the default TTY line discipline. */
+ memset(ldiscs, 0, sizeof(ldiscs));
+ (void) tty_register_ldisc(N_TTY, &tty_ldisc_N_TTY);
+
+ /*
+ * Set up the standard termios. Individual tty drivers may
+ * deviate from this; this is used as a template.
+ */
+ memset(&tty_std_termios, 0, sizeof(struct termios));
+ memcpy(tty_std_termios.c_cc, INIT_C_CC, NCCS);
+ tty_std_termios.c_iflag = ICRNL | IXON;
+ tty_std_termios.c_oflag = OPOST | ONLCR;
+ tty_std_termios.c_cflag = B38400 | CS8 | CREAD | HUPCL;
+ tty_std_termios.c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK |
+ ECHOCTL | ECHOKE | IEXTEN;
+
+ /*
+ * set up the console device so that later boot sequences can
+ * inform about problems etc..
+ */
+#ifdef CONFIG_EARLY_PRINTK
+ disable_early_printk();
+#endif
+#ifdef CONFIG_VT
+ con_init();
+#endif
+#ifdef CONFIG_AU1000_SERIAL_CONSOLE
+ au1000_serial_console_init();
+#endif
+#ifdef CONFIG_SERIAL_CONSOLE
+#if (defined(CONFIG_8xx) || defined(CONFIG_8260))
+ console_8xx_init();
+#elif defined(CONFIG_MAC_SERIAL) && defined(CONFIG_SERIAL)
+ if (_machine == _MACH_Pmac)
+ mac_scc_console_init();
+ else
+ serial_console_init();
+#elif defined(CONFIG_MAC_SERIAL)
+ mac_scc_console_init();
+#elif defined(CONFIG_PARISC)
+ pdc_console_init();
+#elif defined(CONFIG_SERIAL)
+ serial_console_init();
+#endif /* CONFIG_8xx */
+#ifdef CONFIG_SGI_SERIAL
+ sgi_serial_console_init();
+#endif
+#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC)
+ vme_scc_console_init();
+#endif
+#if defined(CONFIG_SERIAL167)
+ serial167_console_init();
+#endif
+#if defined(CONFIG_SH_SCI)
+ sci_console_init();
+#endif
+#endif
+#ifdef CONFIG_TN3270_CONSOLE
+ tub3270_con_init();
+#endif
+#ifdef CONFIG_TN3215
+ con3215_init();
+#endif
+#ifdef CONFIG_HWC
+ hwc_console_init();
+#endif
+#ifdef CONFIG_STDIO_CONSOLE
+ stdio_console_init();
+#endif
+#ifdef CONFIG_SERIAL_21285_CONSOLE
+ rs285_console_init();
+#endif
+#ifdef CONFIG_SERIAL_SA1100_CONSOLE
+ sa1100_rs_console_init();
+#endif
+#ifdef CONFIG_ARC_CONSOLE
+ arc_console_init();
+#endif
+#ifdef CONFIG_SERIAL_AMBA_CONSOLE
+ ambauart_console_init();
+#endif
+#ifdef CONFIG_SERIAL_TX3912_CONSOLE
+ tx3912_console_init();
+#endif
+#ifdef CONFIG_TXX927_SERIAL_CONSOLE
+ txx927_console_init();
+#endif
+#ifdef CONFIG_SIBYTE_SB1250_DUART_CONSOLE
+ sb1250_serial_console_init();
+#endif
+}
+
+static struct tty_driver dev_tty_driver, dev_syscons_driver;
+#ifdef CONFIG_UNIX98_PTYS
+static struct tty_driver dev_ptmx_driver;
+#endif
+#ifdef CONFIG_VT
+static struct tty_driver dev_console_driver;
+#endif
+
+/*
+ * Ok, now we can initialize the rest of the tty devices and can count
+ * on memory allocations, interrupts etc..
+ */
+void __init tty_init(void)
+{
+ /*
+ * dev_tty_driver and dev_console_driver are actually magic
+ * devices which get redirected at open time. Nevertheless,
+ * we register them so that register_chrdev is called
+ * appropriately.
+ */
+ memset(&dev_tty_driver, 0, sizeof(struct tty_driver));
+ dev_tty_driver.magic = TTY_DRIVER_MAGIC;
+ dev_tty_driver.driver_name = "/dev/tty";
+ dev_tty_driver.name = dev_tty_driver.driver_name + 5;
+ dev_tty_driver.name_base = 0;
+ dev_tty_driver.major = TTYAUX_MAJOR;
+ dev_tty_driver.minor_start = 0;
+ dev_tty_driver.num = 1;
+ dev_tty_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_tty_driver.subtype = SYSTEM_TYPE_TTY;
+
+ if (tty_register_driver(&dev_tty_driver))
+ panic("Couldn't register /dev/tty driver\n");
+
+ dev_syscons_driver = dev_tty_driver;
+ dev_syscons_driver.driver_name = "/dev/console";
+ dev_syscons_driver.name = dev_syscons_driver.driver_name + 5;
+ dev_syscons_driver.major = TTYAUX_MAJOR;
+ dev_syscons_driver.minor_start = 1;
+ dev_syscons_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_syscons_driver.subtype = SYSTEM_TYPE_SYSCONS;
+
+ if (tty_register_driver(&dev_syscons_driver))
+ panic("Couldn't register /dev/console driver\n");
+
+ /* console calls tty_register_driver() before kmalloc() works.
+ * Thus, we can't devfs_register() then. Do so now, instead.
+ */
+#ifdef CONFIG_XENO
+ xeno_console_init();
+#endif
+#ifdef CONFIG_VT
+ con_init_devfs();
+#endif
+
+#ifdef CONFIG_UNIX98_PTYS
+ dev_ptmx_driver = dev_tty_driver;
+ dev_ptmx_driver.driver_name = "/dev/ptmx";
+ dev_ptmx_driver.name = dev_ptmx_driver.driver_name + 5;
+ dev_ptmx_driver.major= MAJOR(PTMX_DEV);
+ dev_ptmx_driver.minor_start = MINOR(PTMX_DEV);
+ dev_ptmx_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_ptmx_driver.subtype = SYSTEM_TYPE_SYSPTMX;
+
+ if (tty_register_driver(&dev_ptmx_driver))
+ panic("Couldn't register /dev/ptmx driver\n");
+#endif
+
+#ifdef CONFIG_VT
+ dev_console_driver = dev_tty_driver;
+ dev_console_driver.driver_name = "/dev/vc/0";
+ dev_console_driver.name = dev_console_driver.driver_name + 5;
+ dev_console_driver.major = TTY_MAJOR;
+ dev_console_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_console_driver.subtype = SYSTEM_TYPE_CONSOLE;
+
+ if (tty_register_driver(&dev_console_driver))
+ panic("Couldn't register /dev/tty0 driver\n");
+
+ kbd_init();
+#endif
+
+#ifdef CONFIG_ESPSERIAL /* init ESP before rs, so rs doesn't see the port */
+ espserial_init();
+#endif
+#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC)
+ vme_scc_init();
+#endif
+#ifdef CONFIG_SERIAL_TX3912
+ tx3912_rs_init();
+#endif
+#ifdef CONFIG_ROCKETPORT
+ rp_init();
+#endif
+#ifdef CONFIG_SERIAL167
+ serial167_init();
+#endif
+#ifdef CONFIG_CYCLADES
+ cy_init();
+#endif
+#ifdef CONFIG_STALLION
+ stl_init();
+#endif
+#ifdef CONFIG_ISTALLION
+ stli_init();
+#endif
+#ifdef CONFIG_DIGI
+ pcxe_init();
+#endif
+#ifdef CONFIG_DIGIEPCA
+ pc_init();
+#endif
+#ifdef CONFIG_SPECIALIX
+ specialix_init();
+#endif
+#if (defined(CONFIG_8xx) || defined(CONFIG_8260))
+ rs_8xx_init();
+#endif /* CONFIG_8xx */
+ pty_init();
+#ifdef CONFIG_MOXA_SMARTIO
+ mxser_init();
+#endif
+#ifdef CONFIG_MOXA_INTELLIO
+ moxa_init();
+#endif
+#ifdef CONFIG_VT
+ vcs_init();
+#endif
+#ifdef CONFIG_TN3270
+ tub3270_init();
+#endif
+#ifdef CONFIG_TN3215
+ tty3215_init();
+#endif
+#ifdef CONFIG_HWC
+ hwc_tty_init();
+#endif
+#ifdef CONFIG_A2232
+ a2232board_init();
+#endif
+}
--- /dev/null
+/*
+ * linux/fs/exec.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * #!-checking implemented by tytso.
+ */
+/*
+ * Demand-loading implemented 01.12.91 - no need to read anything but
+ * the header into memory. The inode of the executable is put into
+ * "current->executable", and page faults do the actual loading. Clean.
+ *
+ * Once more I can proudly say that linux stood up to being changed: it
+ * was less than 2 hours work to get demand-loading completely implemented.
+ *
+ * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead,
+ * current->executable is only used by the procfs. This allows a dispatch
+ * table to check for several different types of binary formats. We keep
+ * trying until we recognize the file or we run out of supported binary
+ * formats.
+ */
+
+#include <linux/config.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/mman.h>
+#include <linux/a.out.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+#include <linux/personality.h>
+#include <linux/swap.h>
+#include <linux/utsname.h>
+#define __NO_VERSION__
+#include <linux/module.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/mmu_context.h>
+
+#ifdef CONFIG_KMOD
+#include <linux/kmod.h>
+#endif
+
+int core_uses_pid;
+char core_pattern[65] = "core";
+/* The maximal length of core_pattern is also specified in sysctl.c */
+
+static struct linux_binfmt *formats;
+static rwlock_t binfmt_lock = RW_LOCK_UNLOCKED;
+
+int register_binfmt(struct linux_binfmt * fmt)
+{
+ struct linux_binfmt ** tmp = &formats;
+
+ if (!fmt)
+ return -EINVAL;
+ if (fmt->next)
+ return -EBUSY;
+ write_lock(&binfmt_lock);
+ while (*tmp) {
+ if (fmt == *tmp) {
+ write_unlock(&binfmt_lock);
+ return -EBUSY;
+ }
+ tmp = &(*tmp)->next;
+ }
+ fmt->next = formats;
+ formats = fmt;
+ write_unlock(&binfmt_lock);
+ return 0;
+}
+
+int unregister_binfmt(struct linux_binfmt * fmt)
+{
+ struct linux_binfmt ** tmp = &formats;
+
+ write_lock(&binfmt_lock);
+ while (*tmp) {
+ if (fmt == *tmp) {
+ *tmp = fmt->next;
+ write_unlock(&binfmt_lock);
+ return 0;
+ }
+ tmp = &(*tmp)->next;
+ }
+ write_unlock(&binfmt_lock);
+ return -EINVAL;
+}
+
+static inline void put_binfmt(struct linux_binfmt * fmt)
+{
+ if (fmt->module)
+ __MOD_DEC_USE_COUNT(fmt->module);
+}
+
+/*
+ * Note that a shared library must be both readable and executable due to
+ * security reasons.
+ *
+ * Also note that we take the address to load from from the file itself.
+ */
+asmlinkage long sys_uselib(const char * library)
+{
+ struct file * file;
+ struct nameidata nd;
+ int error;
+
+ error = user_path_walk(library, &nd);
+ if (error)
+ goto out;
+
+ error = -EINVAL;
+ if (!S_ISREG(nd.dentry->d_inode->i_mode))
+ goto exit;
+
+ error = permission(nd.dentry->d_inode, MAY_READ | MAY_EXEC);
+ if (error)
+ goto exit;
+
+ file = dentry_open(nd.dentry, nd.mnt, O_RDONLY);
+ error = PTR_ERR(file);
+ if (IS_ERR(file))
+ goto out;
+
+ error = -ENOEXEC;
+ if(file->f_op && file->f_op->read) {
+ struct linux_binfmt * fmt;
+
+ read_lock(&binfmt_lock);
+ for (fmt = formats ; fmt ; fmt = fmt->next) {
+ if (!fmt->load_shlib)
+ continue;
+ if (!try_inc_mod_count(fmt->module))
+ continue;
+ read_unlock(&binfmt_lock);
+ error = fmt->load_shlib(file);
+ read_lock(&binfmt_lock);
+ put_binfmt(fmt);
+ if (error != -ENOEXEC)
+ break;
+ }
+ read_unlock(&binfmt_lock);
+ }
+ fput(file);
+out:
+ return error;
+exit:
+ path_release(&nd);
+ goto out;
+}
+
+/*
+ * count() counts the number of arguments/envelopes
+ */
+static int count(char ** argv, int max)
+{
+ int i = 0;
+
+ if (argv != NULL) {
+ for (;;) {
+ char * p;
+
+ if (get_user(p, argv))
+ return -EFAULT;
+ if (!p)
+ break;
+ argv++;
+ if(++i > max)
+ return -E2BIG;
+ }
+ }
+ return i;
+}
+
+/*
+ * 'copy_strings()' copies argument/envelope strings from user
+ * memory to free pages in kernel mem. These are in a format ready
+ * to be put directly into the top of new user memory.
+ */
+int copy_strings(int argc,char ** argv, struct linux_binprm *bprm)
+{
+ struct page *kmapped_page = NULL;
+ char *kaddr = NULL;
+ int ret;
+
+ while (argc-- > 0) {
+ char *str;
+ int len;
+ unsigned long pos;
+
+ if (get_user(str, argv+argc) ||
+ !(len = strnlen_user(str, bprm->p))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (bprm->p < len) {
+ ret = -E2BIG;
+ goto out;
+ }
+
+ bprm->p -= len;
+ /* XXX: add architecture specific overflow check here. */
+ pos = bprm->p;
+
+ while (len > 0) {
+ int i, new, err;
+ int offset, bytes_to_copy;
+ struct page *page;
+
+ offset = pos % PAGE_SIZE;
+ i = pos/PAGE_SIZE;
+ page = bprm->page[i];
+ new = 0;
+ if (!page) {
+ page = alloc_page(GFP_HIGHUSER);
+ bprm->page[i] = page;
+ if (!page) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ new = 1;
+ }
+
+ if (page != kmapped_page) {
+ if (kmapped_page)
+ kunmap(kmapped_page);
+ kmapped_page = page;
+ kaddr = kmap(kmapped_page);
+ }
+ if (new && offset)
+ memset(kaddr, 0, offset);
+ bytes_to_copy = PAGE_SIZE - offset;
+ if (bytes_to_copy > len) {
+ bytes_to_copy = len;
+ if (new)
+ memset(kaddr+offset+len, 0,
+ PAGE_SIZE-offset-len);
+ }
+ err = copy_from_user(kaddr+offset, str, bytes_to_copy);
+ if (err) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ pos += bytes_to_copy;
+ str += bytes_to_copy;
+ len -= bytes_to_copy;
+ }
+ }
+ ret = 0;
+out:
+ if (kmapped_page)
+ kunmap(kmapped_page);
+ return ret;
+}
+
+/*
+ * Like copy_strings, but get argv and its values from kernel memory.
+ */
+int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm)
+{
+ int r;
+ mm_segment_t oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ r = copy_strings(argc, argv, bprm);
+ set_fs(oldfs);
+ return r;
+}
+
+/*
+ * This routine is used to map in a page into an address space: needed by
+ * execve() for the initial stack and environment pages.
+ *
+ * tsk->mmap_sem is held for writing.
+ */
+void put_dirty_page(struct task_struct * tsk, struct page *page, unsigned long address)
+{
+ pgd_t * pgd;
+ pmd_t * pmd;
+ pte_t * pte;
+
+ if (page_count(page) != 1)
+ printk(KERN_ERR "mem_map disagrees with %p at %08lx\n", page, address);
+ pgd = pgd_offset(tsk->mm, address);
+
+ spin_lock(&tsk->mm->page_table_lock);
+ pmd = pmd_alloc(tsk->mm, pgd, address);
+ if (!pmd)
+ goto out;
+ pte = pte_alloc(tsk->mm, pmd, address);
+ if (!pte)
+ goto out;
+ if (!pte_none(*pte))
+ goto out;
+ lru_cache_add(page);
+ flush_dcache_page(page);
+ flush_page_to_ram(page);
+ set_pte(pte, pte_mkdirty(pte_mkwrite(mk_pte(page, PAGE_COPY))));
+ XENO_flush_page_update_queue();
+ tsk->mm->rss++;
+ spin_unlock(&tsk->mm->page_table_lock);
+
+ /* no need for flush_tlb */
+ return;
+out:
+ spin_unlock(&tsk->mm->page_table_lock);
+ __free_page(page);
+ force_sig(SIGKILL, tsk);
+ return;
+}
+
+int setup_arg_pages(struct linux_binprm *bprm)
+{
+ unsigned long stack_base;
+ struct vm_area_struct *mpnt;
+ int i;
+
+ stack_base = STACK_TOP - MAX_ARG_PAGES*PAGE_SIZE;
+
+ bprm->p += stack_base;
+ if (bprm->loader)
+ bprm->loader += stack_base;
+ bprm->exec += stack_base;
+
+ mpnt = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!mpnt)
+ return -ENOMEM;
+
+ down_write(¤t->mm->mmap_sem);
+ {
+ mpnt->vm_mm = current->mm;
+ mpnt->vm_start = PAGE_MASK & (unsigned long) bprm->p;
+ mpnt->vm_end = STACK_TOP;
+ mpnt->vm_page_prot = PAGE_COPY;
+ mpnt->vm_flags = VM_STACK_FLAGS;
+ mpnt->vm_ops = NULL;
+ mpnt->vm_pgoff = 0;
+ mpnt->vm_file = NULL;
+ mpnt->vm_private_data = (void *) 0;
+ insert_vm_struct(current->mm, mpnt);
+ current->mm->total_vm = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
+ }
+
+ for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
+ struct page *page = bprm->page[i];
+ if (page) {
+ bprm->page[i] = NULL;
+ put_dirty_page(current,page,stack_base);
+ }
+ stack_base += PAGE_SIZE;
+ }
+ up_write(¤t->mm->mmap_sem);
+
+ return 0;
+}
+
+struct file *open_exec(const char *name)
+{
+ struct nameidata nd;
+ struct inode *inode;
+ struct file *file;
+ int err = 0;
+
+ err = path_lookup(name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, &nd);
+ file = ERR_PTR(err);
+ if (!err) {
+ inode = nd.dentry->d_inode;
+ file = ERR_PTR(-EACCES);
+ if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
+ S_ISREG(inode->i_mode)) {
+ int err = permission(inode, MAY_EXEC);
+ if (!err && !(inode->i_mode & 0111))
+ err = -EACCES;
+ file = ERR_PTR(err);
+ if (!err) {
+ file = dentry_open(nd.dentry, nd.mnt, O_RDONLY);
+ if (!IS_ERR(file)) {
+ err = deny_write_access(file);
+ if (err) {
+ fput(file);
+ file = ERR_PTR(err);
+ }
+ }
+out:
+ return file;
+ }
+ }
+ path_release(&nd);
+ }
+ goto out;
+}
+
+int kernel_read(struct file *file, unsigned long offset,
+ char * addr, unsigned long count)
+{
+ mm_segment_t old_fs;
+ loff_t pos = offset;
+ int result = -ENOSYS;
+
+ if (!file->f_op->read)
+ goto fail;
+ old_fs = get_fs();
+ set_fs(get_ds());
+ result = file->f_op->read(file, addr, count, &pos);
+ set_fs(old_fs);
+fail:
+ return result;
+}
+
+static int exec_mmap(void)
+{
+ struct mm_struct * mm, * old_mm;
+
+ old_mm = current->mm;
+ if (old_mm && atomic_read(&old_mm->mm_users) == 1) {
+ mm_release();
+ exit_mmap(old_mm);
+ return 0;
+ }
+
+ mm = mm_alloc();
+ if (mm) {
+ struct mm_struct *active_mm;
+
+ if (init_new_context(current, mm)) {
+ mmdrop(mm);
+ return -ENOMEM;
+ }
+
+ /* Add it to the list of mm's */
+ spin_lock(&mmlist_lock);
+ list_add(&mm->mmlist, &init_mm.mmlist);
+ mmlist_nr++;
+ spin_unlock(&mmlist_lock);
+
+ task_lock(current);
+ active_mm = current->active_mm;
+ current->mm = mm;
+ current->active_mm = mm;
+ task_unlock(current);
+ activate_mm(active_mm, mm);
+ mm_release();
+ if (old_mm) {
+ if (active_mm != old_mm) BUG();
+ mmput(old_mm);
+ return 0;
+ }
+ mmdrop(active_mm);
+ return 0;
+ }
+ return -ENOMEM;
+}
+
+/*
+ * This function makes sure the current process has its own signal table,
+ * so that flush_signal_handlers can later reset the handlers without
+ * disturbing other processes. (Other processes might share the signal
+ * table via the CLONE_SIGNAL option to clone().)
+ */
+
+static inline int make_private_signals(void)
+{
+ struct signal_struct * newsig;
+
+ if (atomic_read(¤t->sig->count) <= 1)
+ return 0;
+ newsig = kmem_cache_alloc(sigact_cachep, GFP_KERNEL);
+ if (newsig == NULL)
+ return -ENOMEM;
+ spin_lock_init(&newsig->siglock);
+ atomic_set(&newsig->count, 1);
+ memcpy(newsig->action, current->sig->action, sizeof(newsig->action));
+ spin_lock_irq(¤t->sigmask_lock);
+ current->sig = newsig;
+ spin_unlock_irq(¤t->sigmask_lock);
+ return 0;
+}
+
+/*
+ * If make_private_signals() made a copy of the signal table, decrement the
+ * refcount of the original table, and free it if necessary.
+ * We don't do that in make_private_signals() so that we can back off
+ * in flush_old_exec() if an error occurs after calling make_private_signals().
+ */
+
+static inline void release_old_signals(struct signal_struct * oldsig)
+{
+ if (current->sig == oldsig)
+ return;
+ if (atomic_dec_and_test(&oldsig->count))
+ kmem_cache_free(sigact_cachep, oldsig);
+}
+
+/*
+ * These functions flushes out all traces of the currently running executable
+ * so that a new one can be started
+ */
+
+static inline void flush_old_files(struct files_struct * files)
+{
+ long j = -1;
+
+ write_lock(&files->file_lock);
+ for (;;) {
+ unsigned long set, i;
+
+ j++;
+ i = j * __NFDBITS;
+ if (i >= files->max_fds || i >= files->max_fdset)
+ break;
+ set = files->close_on_exec->fds_bits[j];
+ if (!set)
+ continue;
+ files->close_on_exec->fds_bits[j] = 0;
+ write_unlock(&files->file_lock);
+ for ( ; set ; i++,set >>= 1) {
+ if (set & 1) {
+ sys_close(i);
+ }
+ }
+ write_lock(&files->file_lock);
+
+ }
+ write_unlock(&files->file_lock);
+}
+
+/*
+ * An execve() will automatically "de-thread" the process.
+ * Note: we don't have to hold the tasklist_lock to test
+ * whether we migth need to do this. If we're not part of
+ * a thread group, there is no way we can become one
+ * dynamically. And if we are, we only need to protect the
+ * unlink - even if we race with the last other thread exit,
+ * at worst the list_del_init() might end up being a no-op.
+ */
+static inline void de_thread(struct task_struct *tsk)
+{
+ if (!list_empty(&tsk->thread_group)) {
+ write_lock_irq(&tasklist_lock);
+ list_del_init(&tsk->thread_group);
+ write_unlock_irq(&tasklist_lock);
+ }
+
+ /* Minor oddity: this might stay the same. */
+ tsk->tgid = tsk->pid;
+}
+
+int flush_old_exec(struct linux_binprm * bprm)
+{
+ char * name;
+ int i, ch, retval;
+ struct signal_struct * oldsig;
+
+ /*
+ * Make sure we have a private signal table
+ */
+ oldsig = current->sig;
+ retval = make_private_signals();
+ if (retval) goto flush_failed;
+
+ /*
+ * Release all of the old mmap stuff
+ */
+ retval = exec_mmap();
+ if (retval) goto mmap_failed;
+
+ /* This is the point of no return */
+ release_old_signals(oldsig);
+
+ current->sas_ss_sp = current->sas_ss_size = 0;
+
+ if (current->euid == current->uid && current->egid == current->gid)
+ current->mm->dumpable = 1;
+ name = bprm->filename;
+ for (i=0; (ch = *(name++)) != '\0';) {
+ if (ch == '/')
+ i = 0;
+ else
+ if (i < 15)
+ current->comm[i++] = ch;
+ }
+ current->comm[i] = '\0';
+
+ flush_thread();
+
+ de_thread(current);
+
+ if (bprm->e_uid != current->euid || bprm->e_gid != current->egid ||
+ permission(bprm->file->f_dentry->d_inode,MAY_READ))
+ current->mm->dumpable = 0;
+
+ /* An exec changes our domain. We are no longer part of the thread
+ group */
+
+ current->self_exec_id++;
+
+ flush_signal_handlers(current);
+ flush_old_files(current->files);
+
+ return 0;
+
+mmap_failed:
+flush_failed:
+ spin_lock_irq(¤t->sigmask_lock);
+ if (current->sig != oldsig) {
+ kmem_cache_free(sigact_cachep, current->sig);
+ current->sig = oldsig;
+ }
+ spin_unlock_irq(¤t->sigmask_lock);
+ return retval;
+}
+
+/*
+ * We mustn't allow tracing of suid binaries, unless
+ * the tracer has the capability to trace anything..
+ */
+static inline int must_not_trace_exec(struct task_struct * p)
+{
+ return (p->ptrace & PT_PTRACED) && !(p->ptrace & PT_PTRACE_CAP);
+}
+
+/*
+ * Fill the binprm structure from the inode.
+ * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
+ */
+int prepare_binprm(struct linux_binprm *bprm)
+{
+ int mode;
+ struct inode * inode = bprm->file->f_dentry->d_inode;
+
+ mode = inode->i_mode;
+ /*
+ * Check execute perms again - if the caller has CAP_DAC_OVERRIDE,
+ * vfs_permission lets a non-executable through
+ */
+ if (!(mode & 0111)) /* with at least _one_ execute bit set */
+ return -EACCES;
+ if (bprm->file->f_op == NULL)
+ return -EACCES;
+
+ bprm->e_uid = current->euid;
+ bprm->e_gid = current->egid;
+
+ if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
+ /* Set-uid? */
+ if (mode & S_ISUID)
+ bprm->e_uid = inode->i_uid;
+
+ /* Set-gid? */
+ /*
+ * If setgid is set but no group execute bit then this
+ * is a candidate for mandatory locking, not a setgid
+ * executable.
+ */
+ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
+ bprm->e_gid = inode->i_gid;
+ }
+
+ /* We don't have VFS support for capabilities yet */
+ cap_clear(bprm->cap_inheritable);
+ cap_clear(bprm->cap_permitted);
+ cap_clear(bprm->cap_effective);
+
+ /* To support inheritance of root-permissions and suid-root
+ * executables under compatibility mode, we raise all three
+ * capability sets for the file.
+ *
+ * If only the real uid is 0, we only raise the inheritable
+ * and permitted sets of the executable file.
+ */
+
+ if (!issecure(SECURE_NOROOT)) {
+ if (bprm->e_uid == 0 || current->uid == 0) {
+ cap_set_full(bprm->cap_inheritable);
+ cap_set_full(bprm->cap_permitted);
+ }
+ if (bprm->e_uid == 0)
+ cap_set_full(bprm->cap_effective);
+ }
+
+ memset(bprm->buf,0,BINPRM_BUF_SIZE);
+ return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
+}
+
+/*
+ * This function is used to produce the new IDs and capabilities
+ * from the old ones and the file's capabilities.
+ *
+ * The formula used for evolving capabilities is:
+ *
+ * pI' = pI
+ * (***) pP' = (fP & X) | (fI & pI)
+ * pE' = pP' & fE [NB. fE is 0 or ~0]
+ *
+ * I=Inheritable, P=Permitted, E=Effective // p=process, f=file
+ * ' indicates post-exec(), and X is the global 'cap_bset'.
+ *
+ */
+
+void compute_creds(struct linux_binprm *bprm)
+{
+ kernel_cap_t new_permitted, working;
+ int do_unlock = 0;
+
+ new_permitted = cap_intersect(bprm->cap_permitted, cap_bset);
+ working = cap_intersect(bprm->cap_inheritable,
+ current->cap_inheritable);
+ new_permitted = cap_combine(new_permitted, working);
+
+ if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
+ !cap_issubset(new_permitted, current->cap_permitted)) {
+ current->mm->dumpable = 0;
+
+ lock_kernel();
+ if (must_not_trace_exec(current)
+ || atomic_read(¤t->fs->count) > 1
+ || atomic_read(¤t->files->count) > 1
+ || atomic_read(¤t->sig->count) > 1) {
+ if(!capable(CAP_SETUID)) {
+ bprm->e_uid = current->uid;
+ bprm->e_gid = current->gid;
+ }
+ if(!capable(CAP_SETPCAP)) {
+ new_permitted = cap_intersect(new_permitted,
+ current->cap_permitted);
+ }
+ }
+ do_unlock = 1;
+ }
+
+
+ /* For init, we want to retain the capabilities set
+ * in the init_task struct. Thus we skip the usual
+ * capability rules */
+ if (current->pid != 1) {
+ current->cap_permitted = new_permitted;
+ current->cap_effective =
+ cap_intersect(new_permitted, bprm->cap_effective);
+ }
+
+ /* AUD: Audit candidate if current->cap_effective is set */
+
+ current->suid = current->euid = current->fsuid = bprm->e_uid;
+ current->sgid = current->egid = current->fsgid = bprm->e_gid;
+
+ if(do_unlock)
+ unlock_kernel();
+ current->keep_capabilities = 0;
+}
+
+
+void remove_arg_zero(struct linux_binprm *bprm)
+{
+ if (bprm->argc) {
+ unsigned long offset;
+ char * kaddr;
+ struct page *page;
+
+ offset = bprm->p % PAGE_SIZE;
+ goto inside;
+
+ while (bprm->p++, *(kaddr+offset++)) {
+ if (offset != PAGE_SIZE)
+ continue;
+ offset = 0;
+ kunmap(page);
+inside:
+ page = bprm->page[bprm->p/PAGE_SIZE];
+ kaddr = kmap(page);
+ }
+ kunmap(page);
+ bprm->argc--;
+ }
+}
+
+/*
+ * cycle the list of binary formats handler, until one recognizes the image
+ */
+int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
+{
+ int try,retval=0;
+ struct linux_binfmt *fmt;
+#ifdef __alpha__
+ /* handle /sbin/loader.. */
+ {
+ struct exec * eh = (struct exec *) bprm->buf;
+
+ if (!bprm->loader && eh->fh.f_magic == 0x183 &&
+ (eh->fh.f_flags & 0x3000) == 0x3000)
+ {
+ struct file * file;
+ unsigned long loader;
+
+ allow_write_access(bprm->file);
+ fput(bprm->file);
+ bprm->file = NULL;
+
+ loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
+
+ file = open_exec("/sbin/loader");
+ retval = PTR_ERR(file);
+ if (IS_ERR(file))
+ return retval;
+
+ /* Remember if the application is TASO. */
+ bprm->sh_bang = eh->ah.entry < 0x100000000;
+
+ bprm->file = file;
+ bprm->loader = loader;
+ retval = prepare_binprm(bprm);
+ if (retval<0)
+ return retval;
+ /* should call search_binary_handler recursively here,
+ but it does not matter */
+ }
+ }
+#endif
+ /* kernel module loader fixup */
+ /* so we don't try to load run modprobe in kernel space. */
+ set_fs(USER_DS);
+ for (try=0; try<2; try++) {
+ read_lock(&binfmt_lock);
+ for (fmt = formats ; fmt ; fmt = fmt->next) {
+ int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
+ if (!fn)
+ continue;
+ if (!try_inc_mod_count(fmt->module))
+ continue;
+ read_unlock(&binfmt_lock);
+ retval = fn(bprm, regs);
+ if (retval >= 0) {
+ put_binfmt(fmt);
+ allow_write_access(bprm->file);
+ if (bprm->file)
+ fput(bprm->file);
+ bprm->file = NULL;
+ current->did_exec = 1;
+ return retval;
+ }
+ read_lock(&binfmt_lock);
+ put_binfmt(fmt);
+ if (retval != -ENOEXEC)
+ break;
+ if (!bprm->file) {
+ read_unlock(&binfmt_lock);
+ return retval;
+ }
+ }
+ read_unlock(&binfmt_lock);
+ if (retval != -ENOEXEC) {
+ break;
+#ifdef CONFIG_KMOD
+ }else{
+#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
+ char modname[20];
+ if (printable(bprm->buf[0]) &&
+ printable(bprm->buf[1]) &&
+ printable(bprm->buf[2]) &&
+ printable(bprm->buf[3]))
+ break; /* -ENOEXEC */
+ sprintf(modname, "binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
+ request_module(modname);
+#endif
+ }
+ }
+ return retval;
+}
+
+
+/*
+ * sys_execve() executes a new program.
+ */
+int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs)
+{
+ struct linux_binprm bprm;
+ struct file *file;
+ int retval;
+ int i;
+
+ file = open_exec(filename);
+
+ retval = PTR_ERR(file);
+ if (IS_ERR(file))
+ return retval;
+
+ bprm.p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
+ memset(bprm.page, 0, MAX_ARG_PAGES*sizeof(bprm.page[0]));
+
+ bprm.file = file;
+ bprm.filename = filename;
+ bprm.sh_bang = 0;
+ bprm.loader = 0;
+ bprm.exec = 0;
+ if ((bprm.argc = count(argv, bprm.p / sizeof(void *))) < 0) {
+ allow_write_access(file);
+ fput(file);
+ return bprm.argc;
+ }
+
+ if ((bprm.envc = count(envp, bprm.p / sizeof(void *))) < 0) {
+ allow_write_access(file);
+ fput(file);
+ return bprm.envc;
+ }
+
+ retval = prepare_binprm(&bprm);
+ if (retval < 0)
+ goto out;
+
+ retval = copy_strings_kernel(1, &bprm.filename, &bprm);
+ if (retval < 0)
+ goto out;
+
+ bprm.exec = bprm.p;
+ retval = copy_strings(bprm.envc, envp, &bprm);
+ if (retval < 0)
+ goto out;
+
+ retval = copy_strings(bprm.argc, argv, &bprm);
+ if (retval < 0)
+ goto out;
+
+ retval = search_binary_handler(&bprm,regs);
+ if (retval >= 0)
+ /* execve success */
+ return retval;
+
+out:
+ /* Something went wrong, return the inode and free the argument pages*/
+ allow_write_access(bprm.file);
+ if (bprm.file)
+ fput(bprm.file);
+
+ for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
+ struct page * page = bprm.page[i];
+ if (page)
+ __free_page(page);
+ }
+
+ return retval;
+}
+
+void set_binfmt(struct linux_binfmt *new)
+{
+ struct linux_binfmt *old = current->binfmt;
+ if (new && new->module)
+ __MOD_INC_USE_COUNT(new->module);
+ current->binfmt = new;
+ if (old && old->module)
+ __MOD_DEC_USE_COUNT(old->module);
+}
+
+#define CORENAME_MAX_SIZE 64
+
+/* format_corename will inspect the pattern parameter, and output a
+ * name into corename, which must have space for at least
+ * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
+ */
+void format_corename(char *corename, const char *pattern, long signr)
+{
+ const char *pat_ptr = pattern;
+ char *out_ptr = corename;
+ char *const out_end = corename + CORENAME_MAX_SIZE;
+ int rc;
+ int pid_in_pattern = 0;
+
+ /* Repeat as long as we have more pattern to process and more output
+ space */
+ while (*pat_ptr) {
+ if (*pat_ptr != '%') {
+ if (out_ptr == out_end)
+ goto out;
+ *out_ptr++ = *pat_ptr++;
+ } else {
+ switch (*++pat_ptr) {
+ case 0:
+ goto out;
+ /* Double percent, output one percent */
+ case '%':
+ if (out_ptr == out_end)
+ goto out;
+ *out_ptr++ = '%';
+ break;
+ /* pid */
+ case 'p':
+ pid_in_pattern = 1;
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%d", current->pid);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ /* uid */
+ case 'u':
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%d", current->uid);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ /* gid */
+ case 'g':
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%d", current->gid);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ /* signal that caused the coredump */
+ case 's':
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%ld", signr);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ /* UNIX time of coredump */
+ case 't': {
+ struct timeval tv;
+ do_gettimeofday(&tv);
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%ld", tv.tv_sec);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ }
+ /* hostname */
+ case 'h':
+ down_read(&uts_sem);
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%s", system_utsname.nodename);
+ up_read(&uts_sem);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ /* executable */
+ case 'e':
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ "%s", current->comm);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ break;
+ default:
+ break;
+ }
+ ++pat_ptr;
+ }
+ }
+ /* Backward compatibility with core_uses_pid:
+ *
+ * If core_pattern does not include a %p (as is the default)
+ * and core_uses_pid is set, then .%pid will be appended to
+ * the filename */
+ if (!pid_in_pattern
+ && (core_uses_pid || atomic_read(¤t->mm->mm_users) != 1)) {
+ rc = snprintf(out_ptr, out_end - out_ptr,
+ ".%d", current->pid);
+ if (rc > out_end - out_ptr)
+ goto out;
+ out_ptr += rc;
+ }
+ out:
+ *out_ptr = 0;
+}
+
+int do_coredump(long signr, struct pt_regs * regs)
+{
+ struct linux_binfmt * binfmt;
+ char corename[CORENAME_MAX_SIZE + 1];
+ struct file * file;
+ struct inode * inode;
+ int retval = 0;
+
+ lock_kernel();
+ binfmt = current->binfmt;
+ if (!binfmt || !binfmt->core_dump)
+ goto fail;
+ if (!current->mm->dumpable)
+ goto fail;
+ current->mm->dumpable = 0;
+ if (current->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump)
+ goto fail;
+
+ format_corename(corename, core_pattern, signr);
+ file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW, 0600);
+ if (IS_ERR(file))
+ goto fail;
+ inode = file->f_dentry->d_inode;
+ if (inode->i_nlink > 1)
+ goto close_fail; /* multiple links - don't dump */
+ if (d_unhashed(file->f_dentry))
+ goto close_fail;
+
+ if (!S_ISREG(inode->i_mode))
+ goto close_fail;
+ if (!file->f_op)
+ goto close_fail;
+ if (!file->f_op->write)
+ goto close_fail;
+ if (do_truncate(file->f_dentry, 0) != 0)
+ goto close_fail;
+
+ retval = binfmt->core_dump(signr, regs, file);
+
+close_fail:
+ filp_close(file, NULL);
+fail:
+ unlock_kernel();
+ return retval;
+}
--- /dev/null
+#ifndef __I386_A_OUT_H__
+#define __I386_A_OUT_H__
+
+struct exec
+{
+ unsigned long a_info; /* Use macros N_MAGIC, etc for access */
+ unsigned a_text; /* length of text, in bytes */
+ unsigned a_data; /* length of data, in bytes */
+ unsigned a_bss; /* length of uninitialized data area for file, in bytes */
+ unsigned a_syms; /* length of symbol table data in file, in bytes */
+ unsigned a_entry; /* start address */
+ unsigned a_trsize; /* length of relocation info for text, in bytes */
+ unsigned a_drsize; /* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a) ((a).a_trsize)
+#define N_DRSIZE(a) ((a).a_drsize)
+#define N_SYMSIZE(a) ((a).a_syms)
+
+#ifdef __KERNEL__
+
+#define STACK_TOP TASK_SIZE
+
+#endif
+
+#endif /* __A_OUT_GNU_H__ */
--- /dev/null
+#ifndef __ASM_APIC_H
+#define __ASM_APIC_H
+
+#include <linux/config.h>
+#include <linux/pm.h>
+#include <asm/apicdef.h>
+#include <asm/system.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#define APIC_DEBUG 0
+
+#if APIC_DEBUG
+#define Dprintk(x...) printk(x)
+#else
+#define Dprintk(x...)
+#endif
+
+/*
+ * Basic functions accessing APICs.
+ */
+
+static __inline void apic_write(unsigned long reg, unsigned long v)
+{
+ *((volatile unsigned long *)(APIC_BASE+reg)) = v;
+}
+
+static __inline void apic_write_atomic(unsigned long reg, unsigned long v)
+{
+ xchg((volatile unsigned long *)(APIC_BASE+reg), v);
+}
+
+static __inline unsigned long apic_read(unsigned long reg)
+{
+ return *((volatile unsigned long *)(APIC_BASE+reg));
+}
+
+static __inline__ void apic_wait_icr_idle(void)
+{
+ do { } while ( apic_read( APIC_ICR ) & APIC_ICR_BUSY );
+}
+
+#ifdef CONFIG_X86_GOOD_APIC
+# define FORCE_READ_AROUND_WRITE 0
+# define apic_read_around(x)
+# define apic_write_around(x,y) apic_write((x),(y))
+#else
+# define FORCE_READ_AROUND_WRITE 1
+# define apic_read_around(x) apic_read(x)
+# define apic_write_around(x,y) apic_write_atomic((x),(y))
+#endif
+
+static inline void ack_APIC_irq(void)
+{
+ /*
+ * ack_APIC_irq() actually gets compiled as a single instruction:
+ * - a single rmw on Pentium/82489DX
+ * - a single write on P6+ cores (CONFIG_X86_GOOD_APIC)
+ * ... yummie.
+ */
+
+ /* Docs say use 0 for future compatibility */
+ apic_write_around(APIC_EOI, 0);
+}
+
+extern int get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void connect_bsp_APIC (void);
+extern void disconnect_bsp_APIC (void);
+extern void disable_local_APIC (void);
+extern int verify_local_APIC (void);
+extern void cache_APIC_registers (void);
+extern void sync_Arb_IDs (void);
+extern void init_bsp_APIC (void);
+extern void setup_local_APIC (void);
+extern void init_apic_mappings (void);
+extern void smp_local_timer_interrupt (struct pt_regs * regs);
+extern void setup_APIC_clocks (void);
+extern void setup_apic_nmi_watchdog (void);
+extern inline void nmi_watchdog_tick (struct pt_regs * regs);
+extern int APIC_init_uniprocessor (void);
+extern void disable_APIC_timer(void);
+extern void enable_APIC_timer(void);
+
+extern struct pm_dev *apic_pm_register(pm_dev_t, unsigned long, pm_callback);
+extern void apic_pm_unregister(struct pm_dev*);
+
+extern unsigned int apic_timer_irqs [NR_CPUS];
+extern int check_nmi_watchdog (void);
+
+extern unsigned int nmi_watchdog;
+#define NMI_NONE 0
+#define NMI_IO_APIC 1
+#define NMI_LOCAL_APIC 2
+#define NMI_INVALID 3
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#endif /* __ASM_APIC_H */
--- /dev/null
+#ifndef __ASM_APICDEF_H
+#define __ASM_APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define APIC_DEFAULT_PHYS_BASE 0xfee00000
+
+#define APIC_ID 0x20
+#define APIC_ID_MASK (0x0F<<24)
+#define GET_APIC_ID(x) (((x)>>24)&0x0F)
+#define APIC_LVR 0x30
+#define APIC_LVR_MASK 0xFF00FF
+#define GET_APIC_VERSION(x) ((x)&0xFF)
+#define GET_APIC_MAXLVT(x) (((x)>>16)&0xFF)
+#define APIC_INTEGRATED(x) ((x)&0xF0)
+#define APIC_TASKPRI 0x80
+#define APIC_TPRI_MASK 0xFF
+#define APIC_ARBPRI 0x90
+#define APIC_ARBPRI_MASK 0xFF
+#define APIC_PROCPRI 0xA0
+#define APIC_EOI 0xB0
+#define APIC_EIO_ACK 0x0 /* Write this to the EOI register */
+#define APIC_RRR 0xC0
+#define APIC_LDR 0xD0
+#define APIC_LDR_MASK (0xFF<<24)
+#define GET_APIC_LOGICAL_ID(x) (((x)>>24)&0xFF)
+#define SET_APIC_LOGICAL_ID(x) (((x)<<24))
+#define APIC_ALL_CPUS 0xFF
+#define APIC_DFR 0xE0
+#define APIC_DFR_CLUSTER 0x0FFFFFFFul /* Clustered */
+#define APIC_DFR_FLAT 0xFFFFFFFFul /* Flat mode */
+#define APIC_SPIV 0xF0
+#define APIC_SPIV_FOCUS_DISABLED (1<<9)
+#define APIC_SPIV_APIC_ENABLED (1<<8)
+#define APIC_ISR 0x100
+#define APIC_TMR 0x180
+#define APIC_IRR 0x200
+#define APIC_ESR 0x280
+#define APIC_ESR_SEND_CS 0x00001
+#define APIC_ESR_RECV_CS 0x00002
+#define APIC_ESR_SEND_ACC 0x00004
+#define APIC_ESR_RECV_ACC 0x00008
+#define APIC_ESR_SENDILL 0x00020
+#define APIC_ESR_RECVILL 0x00040
+#define APIC_ESR_ILLREGA 0x00080
+#define APIC_ICR 0x300
+#define APIC_DEST_SELF 0x40000
+#define APIC_DEST_ALLINC 0x80000
+#define APIC_DEST_ALLBUT 0xC0000
+#define APIC_ICR_RR_MASK 0x30000
+#define APIC_ICR_RR_INVALID 0x00000
+#define APIC_ICR_RR_INPROG 0x10000
+#define APIC_ICR_RR_VALID 0x20000
+#define APIC_INT_LEVELTRIG 0x08000
+#define APIC_INT_ASSERT 0x04000
+#define APIC_ICR_BUSY 0x01000
+#define APIC_DEST_PHYSICAL 0x00000
+#define APIC_DEST_LOGICAL 0x00800
+#define APIC_DM_FIXED 0x00000
+#define APIC_DM_LOWEST 0x00100
+#define APIC_DM_SMI 0x00200
+#define APIC_DM_REMRD 0x00300
+#define APIC_DM_NMI 0x00400
+#define APIC_DM_INIT 0x00500
+#define APIC_DM_STARTUP 0x00600
+#define APIC_DM_EXTINT 0x00700
+#define APIC_VECTOR_MASK 0x000FF
+#define APIC_ICR2 0x310
+#define GET_APIC_DEST_FIELD(x) (((x)>>24)&0xFF)
+#define SET_APIC_DEST_FIELD(x) ((x)<<24)
+#define APIC_LVTT 0x320
+#define APIC_LVTPC 0x340
+#define APIC_LVT0 0x350
+#define APIC_LVT_TIMER_BASE_MASK (0x3<<18)
+#define GET_APIC_TIMER_BASE(x) (((x)>>18)&0x3)
+#define SET_APIC_TIMER_BASE(x) (((x)<<18))
+#define APIC_TIMER_BASE_CLKIN 0x0
+#define APIC_TIMER_BASE_TMBASE 0x1
+#define APIC_TIMER_BASE_DIV 0x2
+#define APIC_LVT_TIMER_PERIODIC (1<<17)
+#define APIC_LVT_MASKED (1<<16)
+#define APIC_LVT_LEVEL_TRIGGER (1<<15)
+#define APIC_LVT_REMOTE_IRR (1<<14)
+#define APIC_INPUT_POLARITY (1<<13)
+#define APIC_SEND_PENDING (1<<12)
+#define GET_APIC_DELIVERY_MODE(x) (((x)>>8)&0x7)
+#define SET_APIC_DELIVERY_MODE(x,y) (((x)&~0x700)|((y)<<8))
+#define APIC_MODE_FIXED 0x0
+#define APIC_MODE_NMI 0x4
+#define APIC_MODE_EXINT 0x7
+#define APIC_LVT1 0x360
+#define APIC_LVTERR 0x370
+#define APIC_TMICT 0x380
+#define APIC_TMCCT 0x390
+#define APIC_TDCR 0x3E0
+#define APIC_TDR_DIV_TMBASE (1<<2)
+#define APIC_TDR_DIV_1 0xB
+#define APIC_TDR_DIV_2 0x0
+#define APIC_TDR_DIV_4 0x1
+#define APIC_TDR_DIV_8 0x2
+#define APIC_TDR_DIV_16 0x3
+#define APIC_TDR_DIV_32 0x8
+#define APIC_TDR_DIV_64 0x9
+#define APIC_TDR_DIV_128 0xA
+
+#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+
+#ifdef CONFIG_X86_CLUSTERED_APIC
+#define MAX_IO_APICS 32
+#else
+#define MAX_IO_APICS 8
+#endif
+
+
+/*
+ * The broadcast ID is 0xF for old APICs and 0xFF for xAPICs. SAPICs
+ * don't broadcast (yet?), but if they did, they might use 0xFFFF.
+ */
+#define APIC_BROADCAST_ID_XAPIC (0xFF)
+#define APIC_BROADCAST_ID_APIC (0x0F)
+
+/*
+ * the local APIC register structure, memory mapped. Not terribly well
+ * tested, but we might eventually use this one in the future - the
+ * problem why we cannot use it right now is the P5 APIC, it has an
+ * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
+ */
+#define u32 unsigned int
+
+#define lapic ((volatile struct local_apic *)APIC_BASE)
+
+struct local_apic {
+
+/*000*/ struct { u32 __reserved[4]; } __reserved_01;
+
+/*010*/ struct { u32 __reserved[4]; } __reserved_02;
+
+/*020*/ struct { /* APIC ID Register */
+ u32 __reserved_1 : 24,
+ phys_apic_id : 4,
+ __reserved_2 : 4;
+ u32 __reserved[3];
+ } id;
+
+/*030*/ const
+ struct { /* APIC Version Register */
+ u32 version : 8,
+ __reserved_1 : 8,
+ max_lvt : 8,
+ __reserved_2 : 8;
+ u32 __reserved[3];
+ } version;
+
+/*040*/ struct { u32 __reserved[4]; } __reserved_03;
+
+/*050*/ struct { u32 __reserved[4]; } __reserved_04;
+
+/*060*/ struct { u32 __reserved[4]; } __reserved_05;
+
+/*070*/ struct { u32 __reserved[4]; } __reserved_06;
+
+/*080*/ struct { /* Task Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } tpr;
+
+/*090*/ const
+ struct { /* Arbitration Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } apr;
+
+/*0A0*/ const
+ struct { /* Processor Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } ppr;
+
+/*0B0*/ struct { /* End Of Interrupt Register */
+ u32 eoi;
+ u32 __reserved[3];
+ } eoi;
+
+/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
+
+/*0D0*/ struct { /* Logical Destination Register */
+ u32 __reserved_1 : 24,
+ logical_dest : 8;
+ u32 __reserved_2[3];
+ } ldr;
+
+/*0E0*/ struct { /* Destination Format Register */
+ u32 __reserved_1 : 28,
+ model : 4;
+ u32 __reserved_2[3];
+ } dfr;
+
+/*0F0*/ struct { /* Spurious Interrupt Vector Register */
+ u32 spurious_vector : 8,
+ apic_enabled : 1,
+ focus_cpu : 1,
+ __reserved_2 : 22;
+ u32 __reserved_3[3];
+ } svr;
+
+/*100*/ struct { /* In Service Register */
+/*170*/ u32 bitfield;
+ u32 __reserved[3];
+ } isr [8];
+
+/*180*/ struct { /* Trigger Mode Register */
+/*1F0*/ u32 bitfield;
+ u32 __reserved[3];
+ } tmr [8];
+
+/*200*/ struct { /* Interrupt Request Register */
+/*270*/ u32 bitfield;
+ u32 __reserved[3];
+ } irr [8];
+
+/*280*/ union { /* Error Status Register */
+ struct {
+ u32 send_cs_error : 1,
+ receive_cs_error : 1,
+ send_accept_error : 1,
+ receive_accept_error : 1,
+ __reserved_1 : 1,
+ send_illegal_vector : 1,
+ receive_illegal_vector : 1,
+ illegal_register_address : 1,
+ __reserved_2 : 24;
+ u32 __reserved_3[3];
+ } error_bits;
+ struct {
+ u32 errors;
+ u32 __reserved_3[3];
+ } all_errors;
+ } esr;
+
+/*290*/ struct { u32 __reserved[4]; } __reserved_08;
+
+/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
+
+/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
+
+/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
+
+/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
+
+/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
+
+/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
+
+/*300*/ struct { /* Interrupt Command Register 1 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ destination_mode : 1,
+ delivery_status : 1,
+ __reserved_1 : 1,
+ level : 1,
+ trigger : 1,
+ __reserved_2 : 2,
+ shorthand : 2,
+ __reserved_3 : 12;
+ u32 __reserved_4[3];
+ } icr1;
+
+/*310*/ struct { /* Interrupt Command Register 2 */
+ union {
+ u32 __reserved_1 : 24,
+ phys_dest : 4,
+ __reserved_2 : 4;
+ u32 __reserved_3 : 24,
+ logical_dest : 8;
+ } dest;
+ u32 __reserved_4[3];
+ } icr2;
+
+/*320*/ struct { /* LVT - Timer */
+ u32 vector : 8,
+ __reserved_1 : 4,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ timer_mode : 1,
+ __reserved_3 : 14;
+ u32 __reserved_4[3];
+ } lvt_timer;
+
+/*330*/ struct { u32 __reserved[4]; } __reserved_15;
+
+/*340*/ struct { /* LVT - Performance Counter */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_pc;
+
+/*350*/ struct { /* LVT - LINT0 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ polarity : 1,
+ remote_irr : 1,
+ trigger : 1,
+ mask : 1,
+ __reserved_2 : 15;
+ u32 __reserved_3[3];
+ } lvt_lint0;
+
+/*360*/ struct { /* LVT - LINT1 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ polarity : 1,
+ remote_irr : 1,
+ trigger : 1,
+ mask : 1,
+ __reserved_2 : 15;
+ u32 __reserved_3[3];
+ } lvt_lint1;
+
+/*370*/ struct { /* LVT - Error */
+ u32 vector : 8,
+ __reserved_1 : 4,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_error;
+
+/*380*/ struct { /* Timer Initial Count Register */
+ u32 initial_count;
+ u32 __reserved_2[3];
+ } timer_icr;
+
+/*390*/ const
+ struct { /* Timer Current Count Register */
+ u32 curr_count;
+ u32 __reserved_2[3];
+ } timer_ccr;
+
+/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
+
+/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
+
+/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
+
+/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
+
+/*3E0*/ struct { /* Timer Divide Configuration Register */
+ u32 divisor : 4,
+ __reserved_1 : 28;
+ u32 __reserved_2[3];
+ } timer_dcr;
+
+/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
+
+} __attribute__ ((packed));
+
+#undef u32
+
+#endif
--- /dev/null
+#ifndef __ARCH_I386_ATOMIC__
+#define __ARCH_I386_ATOMIC__
+
+#include <linux/config.h>
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK "lock ; "
+#else
+#define LOCK ""
+#endif
+
+/*
+ * Make sure gcc doesn't try to be clever and move things around
+ * on us. We need to use _exactly_ the address the user gave us,
+ * not some alias that contains the same information.
+ */
+typedef struct { volatile int counter; } atomic_t;
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+#define atomic_read(v) ((v)->counter)
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+#define atomic_set(v,i) (((v)->counter) = (i))
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v. Note that the guaranteed useful range
+ * of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_add(int i, atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "addl %1,%0"
+ :"=m" (v->counter)
+ :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub - subtract the atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_sub(int i, atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "subl %1,%0"
+ :"=m" (v->counter)
+ :"ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "subl %2,%0; sete %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"ir" (i), "m" (v->counter) : "memory");
+ return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_inc(atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "incl %0"
+ :"=m" (v->counter)
+ :"m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ void atomic_dec(atomic_t *v)
+{
+ __asm__ __volatile__(
+ LOCK "decl %0"
+ :"=m" (v->counter)
+ :"m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_dec_and_test(atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "decl %0; sete %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"m" (v->counter) : "memory");
+ return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_inc_and_test(atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "incl %0; sete %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"m" (v->counter) : "memory");
+ return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @v: pointer of type atomic_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero. Note that the guaranteed
+ * useful range of an atomic_t is only 24 bits.
+ */
+static __inline__ int atomic_add_negative(int i, atomic_t *v)
+{
+ unsigned char c;
+
+ __asm__ __volatile__(
+ LOCK "addl %2,%0; sets %1"
+ :"=m" (v->counter), "=qm" (c)
+ :"ir" (i), "m" (v->counter) : "memory");
+ return c;
+}
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr) \
+__asm__ __volatile__(LOCK "andl %0,%1" \
+: : "r" (~(mask)),"m" (*addr) : "memory")
+
+#define atomic_set_mask(mask, addr) \
+__asm__ __volatile__(LOCK "orl %0,%1" \
+: : "r" (mask),"m" (*addr) : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec() barrier()
+#define smp_mb__after_atomic_dec() barrier()
+#define smp_mb__before_atomic_inc() barrier()
+#define smp_mb__after_atomic_inc() barrier()
+
+#endif
--- /dev/null
+#ifndef _I386_BITOPS_H
+#define _I386_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#include <linux/config.h>
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX "lock ; "
+#else
+#define LOCK_PREFIX ""
+#endif
+
+#define ADDR (*(volatile long *) addr)
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered. See __set_bit()
+ * if you do not require the atomic guarantees.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __inline__ void set_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__( LOCK_PREFIX
+ "btsl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __inline__ void __set_bit(int nr, volatile void * addr)
+{
+ __asm__(
+ "btsl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered. However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static __inline__ void clear_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__( LOCK_PREFIX
+ "btrl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+#define smp_mb__before_clear_bit() barrier()
+#define smp_mb__after_clear_bit() barrier()
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __inline__ void __change_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__(
+ "btcl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __inline__ void change_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__( LOCK_PREFIX
+ "btcl %1,%0"
+ :"=m" (ADDR)
+ :"Ir" (nr));
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static __inline__ int test_and_set_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__( LOCK_PREFIX
+ "btsl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static __inline__ int __test_and_set_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__(
+ "btsl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr));
+ return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static __inline__ int test_and_clear_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__( LOCK_PREFIX
+ "btrl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static __inline__ int __test_and_clear_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__(
+ "btrl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr));
+ return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __inline__ int __test_and_change_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__(
+ "btcl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its new value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static __inline__ int test_and_change_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__( LOCK_PREFIX
+ "btcl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit),"=m" (ADDR)
+ :"Ir" (nr) : "memory");
+ return oldbit;
+}
+
+#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static int test_bit(int nr, const volatile void * addr);
+#endif
+
+static __inline__ int constant_test_bit(int nr, const volatile void * addr)
+{
+ return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
+}
+
+static __inline__ int variable_test_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__(
+ "btl %2,%1\n\tsbbl %0,%0"
+ :"=r" (oldbit)
+ :"m" (ADDR),"Ir" (nr));
+ return oldbit;
+}
+
+#define test_bit(nr,addr) \
+(__builtin_constant_p(nr) ? \
+ constant_test_bit((nr),(addr)) : \
+ variable_test_bit((nr),(addr)))
+
+/**
+ * find_first_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit-number of the first zero bit, not the number of the byte
+ * containing a bit.
+ */
+static __inline__ int find_first_zero_bit(void * addr, unsigned size)
+{
+ int d0, d1, d2;
+ int res;
+
+ if (!size)
+ return 0;
+ /* This looks at memory. Mark it volatile to tell gcc not to move it around */
+ __asm__ __volatile__(
+ "movl $-1,%%eax\n\t"
+ "xorl %%edx,%%edx\n\t"
+ "repe; scasl\n\t"
+ "je 1f\n\t"
+ "xorl -4(%%edi),%%eax\n\t"
+ "subl $4,%%edi\n\t"
+ "bsfl %%eax,%%edx\n"
+ "1:\tsubl %%ebx,%%edi\n\t"
+ "shll $3,%%edi\n\t"
+ "addl %%edi,%%edx"
+ :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
+ :"1" ((size + 31) >> 5), "2" (addr), "b" (addr));
+ return res;
+}
+
+/**
+ * find_next_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+static __inline__ int find_next_zero_bit (void * addr, int size, int offset)
+{
+ unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
+ int set = 0, bit = offset & 31, res;
+
+ if (bit) {
+ /*
+ * Look for zero in first byte
+ */
+ __asm__("bsfl %1,%0\n\t"
+ "jne 1f\n\t"
+ "movl $32, %0\n"
+ "1:"
+ : "=r" (set)
+ : "r" (~(*p >> bit)));
+ if (set < (32 - bit))
+ return set + offset;
+ set = 32 - bit;
+ p++;
+ }
+ /*
+ * No zero yet, search remaining full bytes for a zero
+ */
+ res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
+ return (offset + set + res);
+}
+
+/**
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static __inline__ unsigned long ffz(unsigned long word)
+{
+ __asm__("bsfl %1,%0"
+ :"=r" (word)
+ :"r" (~word));
+ return word;
+}
+
+#ifdef __KERNEL__
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz (man ffs).
+ */
+static __inline__ int ffs(int x)
+{
+ int r;
+
+ __asm__("bsfl %1,%0\n\t"
+ "jnz 1f\n\t"
+ "movl $-1,%0\n"
+ "1:" : "=r" (r) : "rm" (x));
+ return r+1;
+}
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+#define hweight32(x) generic_hweight32(x)
+#define hweight16(x) generic_hweight16(x)
+#define hweight8(x) generic_hweight8(x)
+
+#endif /* __KERNEL__ */
+
+#ifdef __KERNEL__
+
+#define ext2_set_bit __test_and_set_bit
+#define ext2_clear_bit __test_and_clear_bit
+#define ext2_test_bit test_bit
+#define ext2_find_first_zero_bit find_first_zero_bit
+#define ext2_find_next_zero_bit find_next_zero_bit
+
+/* Bitmap functions for the minix filesystem. */
+#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,addr)
+#define minix_set_bit(nr,addr) __set_bit(nr,addr)
+#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,addr)
+#define minix_test_bit(nr,addr) test_bit(nr,addr)
+#define minix_find_first_zero_bit(addr,size) find_first_zero_bit(addr,size)
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_BITOPS_H */
--- /dev/null
+#ifndef _LINUX_BOOT_H
+#define _LINUX_BOOT_H
+
+/* Don't touch these, unless you really know what you're doing. */
+#define DEF_INITSEG 0x9000
+#define DEF_SYSSEG 0x1000
+#define DEF_SETUPSEG 0x9020
+#define DEF_SYSSIZE 0x7F00
+
+/* Internal svga startup constants */
+#define NORMAL_VGA 0xffff /* 80x25 mode */
+#define EXTENDED_VGA 0xfffe /* 80x50 mode */
+#define ASK_VGA 0xfffd /* ask for it at bootup */
+
+#endif
--- /dev/null
+/*
+ * include/asm-i386/bugs.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Cyrix stuff, June 1998 by:
+ * - Rafael R. Reilova (moved everything from head.S),
+ * <rreilova@ececs.uc.edu>
+ * - Channing Corn (tests & fixes),
+ * - Andrew D. Balsa (code cleanup).
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ * void check_bugs(void);
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+
+
+static void __init check_fpu(void)
+{
+ boot_cpu_data.fdiv_bug = 0;
+}
+
+static void __init check_hlt(void)
+{
+ boot_cpu_data.hlt_works_ok = 1;
+}
+
+static void __init check_bugs(void)
+{
+ extern void __init boot_init_fpu(void);
+
+ identify_cpu(&boot_cpu_data);
+ boot_init_fpu();
+#ifndef CONFIG_SMP
+ printk("CPU: ");
+ print_cpu_info(&boot_cpu_data);
+#endif
+ check_fpu();
+ check_hlt();
+ system_utsname.machine[1] = '0' +
+ (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+}
--- /dev/null
+#ifndef _I386_BYTEORDER_H
+#define _I386_BYTEORDER_H
+
+#include <asm/types.h>
+
+#ifdef __GNUC__
+
+/* For avoiding bswap on i386 */
+#ifdef __KERNEL__
+#include <linux/config.h>
+#endif
+
+static __inline__ __const__ __u32 ___arch__swab32(__u32 x)
+{
+#ifdef CONFIG_X86_BSWAP
+ __asm__("bswap %0" : "=r" (x) : "0" (x));
+#else
+ __asm__("xchgb %b0,%h0\n\t" /* swap lower bytes */
+ "rorl $16,%0\n\t" /* swap words */
+ "xchgb %b0,%h0" /* swap higher bytes */
+ :"=q" (x)
+ : "0" (x));
+#endif
+ return x;
+}
+
+static __inline__ __const__ __u16 ___arch__swab16(__u16 x)
+{
+ __asm__("xchgb %b0,%h0" /* swap bytes */ \
+ : "=q" (x) \
+ : "0" (x)); \
+ return x;
+}
+
+#define __arch__swab32(x) ___arch__swab32(x)
+#define __arch__swab16(x) ___arch__swab16(x)
+
+#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
+# define __BYTEORDER_HAS_U64__
+# define __SWAB_64_THRU_32__
+#endif
+
+#endif /* __GNUC__ */
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _I386_BYTEORDER_H */
--- /dev/null
+/*
+ * include/asm-i386/cache.h
+ */
+#ifndef __ARCH_I386_CACHE_H
+#define __ARCH_I386_CACHE_H
+
+#include <linux/config.h>
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#endif
--- /dev/null
+#ifndef _I386_CHECKSUM_H
+#define _I386_CHECKSUM_H
+
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+asmlinkage unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums, and handles user-space pointer exceptions correctly, when needed.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+
+asmlinkage unsigned int csum_partial_copy_generic( const char *src, char *dst, int len, int sum,
+ int *src_err_ptr, int *dst_err_ptr);
+
+/*
+ * Note: when you get a NULL pointer exception here this means someone
+ * passed in an incorrect kernel address to one of these functions.
+ *
+ * If you use these functions directly please don't forget the
+ * verify_area().
+ */
+static __inline__
+unsigned int csum_partial_copy_nocheck ( const char *src, char *dst,
+ int len, int sum)
+{
+ return csum_partial_copy_generic ( src, dst, len, sum, NULL, NULL);
+}
+
+static __inline__
+unsigned int csum_partial_copy_from_user ( const char *src, char *dst,
+ int len, int sum, int *err_ptr)
+{
+ return csum_partial_copy_generic ( src, dst, len, sum, err_ptr, NULL);
+}
+
+/*
+ * These are the old (and unsafe) way of doing checksums, a warning message will be
+ * printed if they are used and an exeption occurs.
+ *
+ * these functions should go away after some time.
+ */
+
+#define csum_partial_copy_fromuser csum_partial_copy
+unsigned int csum_partial_copy( const char *src, char *dst, int len, int sum);
+
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.
+ *
+ * By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
+ * Arnt Gulbrandsen.
+ */
+static inline unsigned short ip_fast_csum(unsigned char * iph,
+ unsigned int ihl)
+{
+ unsigned int sum;
+
+ __asm__ __volatile__(
+ "movl (%1), %0 ;\n"
+ "subl $4, %2 ;\n"
+ "jbe 2f ;\n"
+ "addl 4(%1), %0 ;\n"
+ "adcl 8(%1), %0 ;\n"
+ "adcl 12(%1), %0 ;\n"
+"1: adcl 16(%1), %0 ;\n"
+ "lea 4(%1), %1 ;\n"
+ "decl %2 ;\n"
+ "jne 1b ;\n"
+ "adcl $0, %0 ;\n"
+ "movl %0, %2 ;\n"
+ "shrl $16, %0 ;\n"
+ "addw %w2, %w0 ;\n"
+ "adcl $0, %0 ;\n"
+ "notl %0 ;\n"
+"2: ;\n"
+ /* Since the input registers which are loaded with iph and ipl
+ are modified, we must also specify them as outputs, or gcc
+ will assume they contain their original values. */
+ : "=r" (sum), "=r" (iph), "=r" (ihl)
+ : "1" (iph), "2" (ihl));
+ return(sum);
+}
+
+/*
+ * Fold a partial checksum
+ */
+
+static inline unsigned int csum_fold(unsigned int sum)
+{
+ __asm__(
+ "addl %1, %0 ;\n"
+ "adcl $0xffff, %0 ;\n"
+ : "=r" (sum)
+ : "r" (sum << 16), "0" (sum & 0xffff0000)
+ );
+ return (~sum) >> 16;
+}
+
+static inline unsigned long csum_tcpudp_nofold(unsigned long saddr,
+ unsigned long daddr,
+ unsigned short len,
+ unsigned short proto,
+ unsigned int sum)
+{
+ __asm__(
+ "addl %1, %0 ;\n"
+ "adcl %2, %0 ;\n"
+ "adcl %3, %0 ;\n"
+ "adcl $0, %0 ;\n"
+ : "=r" (sum)
+ : "g" (daddr), "g"(saddr), "g"((ntohs(len)<<16)+proto*256), "0"(sum));
+ return sum;
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline unsigned short int csum_tcpudp_magic(unsigned long saddr,
+ unsigned long daddr,
+ unsigned short len,
+ unsigned short proto,
+ unsigned int sum)
+{
+ return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+
+static inline unsigned short ip_compute_csum(unsigned char * buff, int len)
+{
+ return csum_fold (csum_partial(buff, len, 0));
+}
+
+#define _HAVE_ARCH_IPV6_CSUM
+static __inline__ unsigned short int csum_ipv6_magic(struct in6_addr *saddr,
+ struct in6_addr *daddr,
+ __u32 len,
+ unsigned short proto,
+ unsigned int sum)
+{
+ __asm__(
+ "addl 0(%1), %0 ;\n"
+ "adcl 4(%1), %0 ;\n"
+ "adcl 8(%1), %0 ;\n"
+ "adcl 12(%1), %0 ;\n"
+ "adcl 0(%2), %0 ;\n"
+ "adcl 4(%2), %0 ;\n"
+ "adcl 8(%2), %0 ;\n"
+ "adcl 12(%2), %0 ;\n"
+ "adcl %3, %0 ;\n"
+ "adcl %4, %0 ;\n"
+ "adcl $0, %0 ;\n"
+ : "=&r" (sum)
+ : "r" (saddr), "r" (daddr),
+ "r"(htonl(len)), "r"(htonl(proto)), "0"(sum));
+
+ return csum_fold(sum);
+}
+
+/*
+ * Copy and checksum to user
+ */
+#define HAVE_CSUM_COPY_USER
+static __inline__ unsigned int csum_and_copy_to_user(const char *src, char *dst,
+ int len, int sum, int *err_ptr)
+{
+ if (access_ok(VERIFY_WRITE, dst, len))
+ return csum_partial_copy_generic(src, dst, len, sum, NULL, err_ptr);
+
+ if (len)
+ *err_ptr = -EFAULT;
+
+ return -1; /* invalid checksum */
+}
+
+#endif
--- /dev/null
+/*
+ * cpufeature.h
+ *
+ * Defines x86 CPU feature bits
+ */
+
+#ifndef __ASM_I386_CPUFEATURE_H
+#define __ASM_I386_CPUFEATURE_H
+
+/* Sample usage: CPU_FEATURE_P(cpu.x86_capability, FPU) */
+#define CPU_FEATURE_P(CAP, FEATURE) test_bit(CAP, X86_FEATURE_##FEATURE ##_BIT)
+
+#define NCAPINTS 4 /* Currently we have 4 32-bit words worth of info */
+
+/* Intel-defined CPU features, CPUID level 0x00000001, word 0 */
+#define X86_FEATURE_FPU (0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME (0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE (0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE (0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
+#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC (0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP (0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR (0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE (0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA (0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
+#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN (0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLSH (0*32+19) /* Supports the CLFLUSH instruction */
+#define X86_FEATURE_DTES (0*32+21) /* Debug Trace Store */
+#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
+ /* of FPU context), and CR4.OSFXSR available */
+#define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */
+#define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */
+#define X86_FEATURE_SELFSNOOP (0*32+27) /* CPU self snoop */
+#define X86_FEATURE_HT (0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC (0*32+29) /* Automatic clock control */
+#define X86_FEATURE_IA64 (0*32+30) /* IA-64 processor */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL (1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW (1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY (2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN (2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI (2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX (3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR (3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+#define cpu_has(c, bit) test_bit(bit, (c)->x86_capability)
+
+#endif /* __ASM_I386_CPUFEATURE_H */
+
+/*
+ * Local Variables:
+ * mode:c
+ * comment-column:42
+ * End:
+ */
--- /dev/null
+#ifndef _I386_CURRENT_H
+#define _I386_CURRENT_H
+
+struct task_struct;
+
+static inline struct task_struct * get_current(void)
+{
+ struct task_struct *current;
+ __asm__("andl %%esp,%0; ":"=r" (current) : "0" (~8191UL));
+ return current;
+ }
+
+#define current get_current()
+
+#endif /* !(_I386_CURRENT_H) */
--- /dev/null
+#ifndef _I386_DEBUGREG_H
+#define _I386_DEBUGREG_H
+
+
+/* Indicate the register numbers for a number of the specific
+ debug registers. Registers 0-3 contain the addresses we wish to trap on */
+#define DR_FIRSTADDR 0 /* u_debugreg[DR_FIRSTADDR] */
+#define DR_LASTADDR 3 /* u_debugreg[DR_LASTADDR] */
+
+#define DR_STATUS 6 /* u_debugreg[DR_STATUS] */
+#define DR_CONTROL 7 /* u_debugreg[DR_CONTROL] */
+
+/* Define a few things for the status register. We can use this to determine
+ which debugging register was responsible for the trap. The other bits
+ are either reserved or not of interest to us. */
+
+#define DR_TRAP0 (0x1) /* db0 */
+#define DR_TRAP1 (0x2) /* db1 */
+#define DR_TRAP2 (0x4) /* db2 */
+#define DR_TRAP3 (0x8) /* db3 */
+
+#define DR_STEP (0x4000) /* single-step */
+#define DR_SWITCH (0x8000) /* task switch */
+
+/* Now define a bunch of things for manipulating the control register.
+ The top two bytes of the control register consist of 4 fields of 4
+ bits - each field corresponds to one of the four debug registers,
+ and indicates what types of access we trap on, and how large the data
+ field is that we are looking at */
+
+#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
+#define DR_CONTROL_SIZE 4 /* 4 control bits per register */
+
+#define DR_RW_EXECUTE (0x0) /* Settings for the access types to trap on */
+#define DR_RW_WRITE (0x1)
+#define DR_RW_READ (0x3)
+
+#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
+#define DR_LEN_2 (0x4)
+#define DR_LEN_4 (0xC)
+
+/* The low byte to the control register determine which registers are
+ enabled. There are 4 fields of two bits. One bit is "local", meaning
+ that the processor will reset the bit after a task switch and the other
+ is global meaning that we have to explicitly reset the bit. With linux,
+ you can use either one, since we explicitly zero the register when we enter
+ kernel mode. */
+
+#define DR_LOCAL_ENABLE_SHIFT 0 /* Extra shift to the local enable bit */
+#define DR_GLOBAL_ENABLE_SHIFT 1 /* Extra shift to the global enable bit */
+#define DR_ENABLE_SIZE 2 /* 2 enable bits per register */
+
+#define DR_LOCAL_ENABLE_MASK (0x55) /* Set local bits for all 4 regs */
+#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
+
+/* The second byte to the control register has a few special things.
+ We can slow the instruction pipeline for instructions coming via the
+ gdt or the ldt if we want to. I am not sure why this is an advantage */
+
+#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
+#define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */
+#define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */
+
+#endif
--- /dev/null
+#ifndef _I386_DELAY_H
+#define _I386_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/i386/lib/delay.c
+ */
+
+extern void __bad_udelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __const_udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+#define udelay(n) (__builtin_constant_p(n) ? \
+ ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c6ul)) : \
+ __udelay(n))
+
+#endif /* defined(_I386_DELAY_H) */
--- /dev/null
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <asm/ldt.h>
+
+#define __LDT(_X) (0)
+
+#define clear_LDT() ((void)0)
+#define load_LDT(_mm) ((void)0)
+
+#endif
--- /dev/null
+#ifndef __I386_DIV64
+#define __I386_DIV64
+
+#define do_div(n,base) ({ \
+ unsigned long __upper, __low, __high, __mod; \
+ asm("":"=a" (__low), "=d" (__high):"A" (n)); \
+ __upper = __high; \
+ if (__high) { \
+ __upper = __high % (base); \
+ __high = __high / (base); \
+ } \
+ asm("divl %2":"=a" (__low), "=d" (__mod):"rm" (base), "0" (__low), "1" (__upper)); \
+ asm("":"=A" (n):"a" (__low),"d" (__high)); \
+ __mod; \
+})
+
+#endif
--- /dev/null
+/* $Id: dma.h,v 1.7 1992/12/14 00:29:34 root Exp root $
+ * linux/include/asm/dma.h: Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ */
+
+#ifndef _ASM_DMA_H
+#define _ASM_DMA_H
+
+#include <linux/config.h>
+#include <linux/spinlock.h> /* And spinlocks */
+#include <asm/io.h> /* need byte IO */
+#include <linux/delay.h>
+
+
+#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
+#define dma_outb outb_p
+#else
+#define dma_outb outb
+#endif
+
+#define dma_inb inb
+
+/*
+ * NOTES about DMA transfers:
+ *
+ * controller 1: channels 0-3, byte operations, ports 00-1F
+ * controller 2: channels 4-7, word operations, ports C0-DF
+ *
+ * - ALL registers are 8 bits only, regardless of transfer size
+ * - channel 4 is not used - cascades 1 into 2.
+ * - channels 0-3 are byte - addresses/counts are for physical bytes
+ * - channels 5-7 are word - addresses/counts are for physical words
+ * - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
+ * - transfer count loaded to registers is 1 less than actual count
+ * - controller 2 offsets are all even (2x offsets for controller 1)
+ * - page registers for 5-7 don't use data bit 0, represent 128K pages
+ * - page registers for 0-3 use bit 0, represent 64K pages
+ *
+ * DMA transfers are limited to the lower 16MB of _physical_ memory.
+ * Note that addresses loaded into registers must be _physical_ addresses,
+ * not logical addresses (which may differ if paging is active).
+ *
+ * Address mapping for channels 0-3:
+ *
+ * A23 ... A16 A15 ... A8 A7 ... A0 (Physical addresses)
+ * | ... | | ... | | ... |
+ * | ... | | ... | | ... |
+ * | ... | | ... | | ... |
+ * P7 ... P0 A7 ... A0 A7 ... A0
+ * | Page | Addr MSB | Addr LSB | (DMA registers)
+ *
+ * Address mapping for channels 5-7:
+ *
+ * A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0 (Physical addresses)
+ * | ... | \ \ ... \ \ \ ... \ \
+ * | ... | \ \ ... \ \ \ ... \ (not used)
+ * | ... | \ \ ... \ \ \ ... \
+ * P7 ... P1 (0) A7 A6 ... A0 A7 A6 ... A0
+ * | Page | Addr MSB | Addr LSB | (DMA registers)
+ *
+ * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
+ * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
+ * the hardware level, so odd-byte transfers aren't possible).
+ *
+ * Transfer count (_not # bytes_) is limited to 64K, represented as actual
+ * count - 1 : 64K => 0xFFFF, 1 => 0x0000. Thus, count is always 1 or more,
+ * and up to 128K bytes may be transferred on channels 5-7 in one operation.
+ *
+ */
+
+#define MAX_DMA_CHANNELS 8
+
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS (PAGE_OFFSET+0x1000000)
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE 0x00 /* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE 0xC0 /* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG 0x08 /* command register (w) */
+#define DMA1_STAT_REG 0x08 /* status register (r) */
+#define DMA1_REQ_REG 0x09 /* request register (w) */
+#define DMA1_MASK_REG 0x0A /* single-channel mask (w) */
+#define DMA1_MODE_REG 0x0B /* mode register (w) */
+#define DMA1_CLEAR_FF_REG 0x0C /* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG 0x0D /* Temporary Register (r) */
+#define DMA1_RESET_REG 0x0D /* Master Clear (w) */
+#define DMA1_CLR_MASK_REG 0x0E /* Clear Mask */
+#define DMA1_MASK_ALL_REG 0x0F /* all-channels mask (w) */
+
+#define DMA2_CMD_REG 0xD0 /* command register (w) */
+#define DMA2_STAT_REG 0xD0 /* status register (r) */
+#define DMA2_REQ_REG 0xD2 /* request register (w) */
+#define DMA2_MASK_REG 0xD4 /* single-channel mask (w) */
+#define DMA2_MODE_REG 0xD6 /* mode register (w) */
+#define DMA2_CLEAR_FF_REG 0xD8 /* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG 0xDA /* Temporary Register (r) */
+#define DMA2_RESET_REG 0xDA /* Master Clear (w) */
+#define DMA2_CLR_MASK_REG 0xDC /* Clear Mask */
+#define DMA2_MASK_ALL_REG 0xDE /* all-channels mask (w) */
+
+#define DMA_ADDR_0 0x00 /* DMA address registers */
+#define DMA_ADDR_1 0x02
+#define DMA_ADDR_2 0x04
+#define DMA_ADDR_3 0x06
+#define DMA_ADDR_4 0xC0
+#define DMA_ADDR_5 0xC4
+#define DMA_ADDR_6 0xC8
+#define DMA_ADDR_7 0xCC
+
+#define DMA_CNT_0 0x01 /* DMA count registers */
+#define DMA_CNT_1 0x03
+#define DMA_CNT_2 0x05
+#define DMA_CNT_3 0x07
+#define DMA_CNT_4 0xC2
+#define DMA_CNT_5 0xC6
+#define DMA_CNT_6 0xCA
+#define DMA_CNT_7 0xCE
+
+#define DMA_PAGE_0 0x87 /* DMA page registers */
+#define DMA_PAGE_1 0x83
+#define DMA_PAGE_2 0x81
+#define DMA_PAGE_3 0x82
+#define DMA_PAGE_5 0x8B
+#define DMA_PAGE_6 0x89
+#define DMA_PAGE_7 0x8A
+
+#define DMA_MODE_READ 0x44 /* I/O to memory, no autoinit, increment, single mode */
+#define DMA_MODE_WRITE 0x48 /* memory to I/O, no autoinit, increment, single mode */
+#define DMA_MODE_CASCADE 0xC0 /* pass thru DREQ->HRQ, DACK<-HLDA only */
+
+#define DMA_AUTOINIT 0x10
+
+
+extern spinlock_t dma_spin_lock;
+
+static __inline__ unsigned long claim_dma_lock(void)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&dma_spin_lock, flags);
+ return flags;
+}
+
+static __inline__ void release_dma_lock(unsigned long flags)
+{
+ spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* enable/disable a specific DMA channel */
+static __inline__ void enable_dma(unsigned int dmanr)
+{
+ if (dmanr<=3)
+ dma_outb(dmanr, DMA1_MASK_REG);
+ else
+ dma_outb(dmanr & 3, DMA2_MASK_REG);
+}
+
+static __inline__ void disable_dma(unsigned int dmanr)
+{
+ if (dmanr<=3)
+ dma_outb(dmanr | 4, DMA1_MASK_REG);
+ else
+ dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while holding the DMA lock ! ---
+ */
+static __inline__ void clear_dma_ff(unsigned int dmanr)
+{
+ if (dmanr<=3)
+ dma_outb(0, DMA1_CLEAR_FF_REG);
+ else
+ dma_outb(0, DMA2_CLEAR_FF_REG);
+}
+
+/* set mode (above) for a specific DMA channel */
+static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
+{
+ if (dmanr<=3)
+ dma_outb(mode | dmanr, DMA1_MODE_REG);
+ else
+ dma_outb(mode | (dmanr&3), DMA2_MODE_REG);
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
+{
+ switch(dmanr) {
+ case 0:
+ dma_outb(pagenr, DMA_PAGE_0);
+ break;
+ case 1:
+ dma_outb(pagenr, DMA_PAGE_1);
+ break;
+ case 2:
+ dma_outb(pagenr, DMA_PAGE_2);
+ break;
+ case 3:
+ dma_outb(pagenr, DMA_PAGE_3);
+ break;
+ case 5:
+ dma_outb(pagenr & 0xfe, DMA_PAGE_5);
+ break;
+ case 6:
+ dma_outb(pagenr & 0xfe, DMA_PAGE_6);
+ break;
+ case 7:
+ dma_outb(pagenr & 0xfe, DMA_PAGE_7);
+ break;
+ }
+}
+
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+ set_dma_page(dmanr, a>>16);
+ if (dmanr <= 3) {
+ dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+ dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
+ } else {
+ dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+ dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
+ }
+}
+
+
+/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+ count--;
+ if (dmanr <= 3) {
+ dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+ dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
+ } else {
+ dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+ dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
+ }
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static __inline__ int get_dma_residue(unsigned int dmanr)
+{
+ unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
+ : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
+
+ /* using short to get 16-bit wrap around */
+ unsigned short count;
+
+ count = 1 + dma_inb(io_port);
+ count += dma_inb(io_port) << 8;
+
+ return (dmanr<=3)? count : (count<<1);
+}
+
+
+/* These are in kernel/dma.c: */
+extern int request_dma(unsigned int dmanr, const char * device_id); /* reserve a DMA channel */
+extern void free_dma(unsigned int dmanr); /* release it again */
+
+/* From PCI */
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy (0)
+#endif
+
+#endif /* _ASM_DMA_H */
--- /dev/null
+#ifndef __ASMi386_ELF_H
+#define __ASMi386_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+#include <linux/utsname.h>
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+typedef struct user_fxsr_struct elf_fpxregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+ (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS ELFCLASS32
+#define ELF_DATA ELFDATA2LSB
+#define ELF_ARCH EM_386
+
+/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
+ contains a pointer to a function which might be registered using `atexit'.
+ This provides a mean for the dynamic linker to call DT_FINI functions for
+ shared libraries that have been loaded before the code runs.
+
+ A value of 0 tells we have no such handler.
+
+ We might as well make sure everything else is cleared too (except for %esp),
+ just to make things more deterministic.
+ */
+#define ELF_PLAT_INIT(_r) do { \
+ _r->ebx = 0; _r->ecx = 0; _r->edx = 0; \
+ _r->esi = 0; _r->edi = 0; _r->ebp = 0; \
+ _r->eax = 0; \
+} while (0)
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE 4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ use of this is to invoke "./ld.so someprog" to test out a new version of
+ the loader. We need to make sure that it is out of the way of the program
+ that it will "exec", and that there is sufficient room for the brk. */
+
+#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
+
+/* Wow, the "main" arch needs arch dependent functions too.. :) */
+
+/* regs is struct pt_regs, pr_reg is elf_gregset_t (which is
+ now struct_user_regs, they are different) */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) \
+ pr_reg[0] = regs->ebx; \
+ pr_reg[1] = regs->ecx; \
+ pr_reg[2] = regs->edx; \
+ pr_reg[3] = regs->esi; \
+ pr_reg[4] = regs->edi; \
+ pr_reg[5] = regs->ebp; \
+ pr_reg[6] = regs->eax; \
+ pr_reg[7] = regs->xds; \
+ pr_reg[8] = regs->xes; \
+ /* fake once used fs and gs selectors? */ \
+ pr_reg[9] = regs->xds; /* was fs and __fs */ \
+ pr_reg[10] = regs->xds; /* was gs and __gs */ \
+ pr_reg[11] = regs->orig_eax; \
+ pr_reg[12] = regs->eip; \
+ pr_reg[13] = regs->xcs; \
+ pr_reg[14] = regs->eflags; \
+ pr_reg[15] = regs->esp; \
+ pr_reg[16] = regs->xss;
+
+/* This yields a mask that user programs can use to figure out what
+ instruction set this CPU supports. This could be done in user space,
+ but it's not easy, and we've already done it here. */
+
+#define ELF_HWCAP (boot_cpu_data.x86_capability[0])
+
+/* This yields a string that ld.so will use to load implementation
+ specific libraries for optimization. This is more specific in
+ intent than poking at uname or /proc/cpuinfo.
+
+ For the moment, we have only optimizations for the Intel generations,
+ but that could change... */
+
+#define ELF_PLATFORM (system_utsname.machine)
+
+#ifdef __KERNEL__
+#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX)
+#endif
+
+#endif
--- /dev/null
+#ifndef _I386_ERRNO_H
+#define _I386_ERRNO_H
+
+#define EPERM 1 /* Operation not permitted */
+#define ENOENT 2 /* No such file or directory */
+#define ESRCH 3 /* No such process */
+#define EINTR 4 /* Interrupted system call */
+#define EIO 5 /* I/O error */
+#define ENXIO 6 /* No such device or address */
+#define E2BIG 7 /* Argument list too long */
+#define ENOEXEC 8 /* Exec format error */
+#define EBADF 9 /* Bad file number */
+#define ECHILD 10 /* No child processes */
+#define EAGAIN 11 /* Try again */
+#define ENOMEM 12 /* Out of memory */
+#define EACCES 13 /* Permission denied */
+#define EFAULT 14 /* Bad address */
+#define ENOTBLK 15 /* Block device required */
+#define EBUSY 16 /* Device or resource busy */
+#define EEXIST 17 /* File exists */
+#define EXDEV 18 /* Cross-device link */
+#define ENODEV 19 /* No such device */
+#define ENOTDIR 20 /* Not a directory */
+#define EISDIR 21 /* Is a directory */
+#define EINVAL 22 /* Invalid argument */
+#define ENFILE 23 /* File table overflow */
+#define EMFILE 24 /* Too many open files */
+#define ENOTTY 25 /* Not a typewriter */
+#define ETXTBSY 26 /* Text file busy */
+#define EFBIG 27 /* File too large */
+#define ENOSPC 28 /* No space left on device */
+#define ESPIPE 29 /* Illegal seek */
+#define EROFS 30 /* Read-only file system */
+#define EMLINK 31 /* Too many links */
+#define EPIPE 32 /* Broken pipe */
+#define EDOM 33 /* Math argument out of domain of func */
+#define ERANGE 34 /* Math result not representable */
+#define EDEADLK 35 /* Resource deadlock would occur */
+#define ENAMETOOLONG 36 /* File name too long */
+#define ENOLCK 37 /* No record locks available */
+#define ENOSYS 38 /* Function not implemented */
+#define ENOTEMPTY 39 /* Directory not empty */
+#define ELOOP 40 /* Too many symbolic links encountered */
+#define EWOULDBLOCK EAGAIN /* Operation would block */
+#define ENOMSG 42 /* No message of desired type */
+#define EIDRM 43 /* Identifier removed */
+#define ECHRNG 44 /* Channel number out of range */
+#define EL2NSYNC 45 /* Level 2 not synchronized */
+#define EL3HLT 46 /* Level 3 halted */
+#define EL3RST 47 /* Level 3 reset */
+#define ELNRNG 48 /* Link number out of range */
+#define EUNATCH 49 /* Protocol driver not attached */
+#define ENOCSI 50 /* No CSI structure available */
+#define EL2HLT 51 /* Level 2 halted */
+#define EBADE 52 /* Invalid exchange */
+#define EBADR 53 /* Invalid request descriptor */
+#define EXFULL 54 /* Exchange full */
+#define ENOANO 55 /* No anode */
+#define EBADRQC 56 /* Invalid request code */
+#define EBADSLT 57 /* Invalid slot */
+
+#define EDEADLOCK EDEADLK
+
+#define EBFONT 59 /* Bad font file format */
+#define ENOSTR 60 /* Device not a stream */
+#define ENODATA 61 /* No data available */
+#define ETIME 62 /* Timer expired */
+#define ENOSR 63 /* Out of streams resources */
+#define ENONET 64 /* Machine is not on the network */
+#define ENOPKG 65 /* Package not installed */
+#define EREMOTE 66 /* Object is remote */
+#define ENOLINK 67 /* Link has been severed */
+#define EADV 68 /* Advertise error */
+#define ESRMNT 69 /* Srmount error */
+#define ECOMM 70 /* Communication error on send */
+#define EPROTO 71 /* Protocol error */
+#define EMULTIHOP 72 /* Multihop attempted */
+#define EDOTDOT 73 /* RFS specific error */
+#define EBADMSG 74 /* Not a data message */
+#define EOVERFLOW 75 /* Value too large for defined data type */
+#define ENOTUNIQ 76 /* Name not unique on network */
+#define EBADFD 77 /* File descriptor in bad state */
+#define EREMCHG 78 /* Remote address changed */
+#define ELIBACC 79 /* Can not access a needed shared library */
+#define ELIBBAD 80 /* Accessing a corrupted shared library */
+#define ELIBSCN 81 /* .lib section in a.out corrupted */
+#define ELIBMAX 82 /* Attempting to link in too many shared libraries */
+#define ELIBEXEC 83 /* Cannot exec a shared library directly */
+#define EILSEQ 84 /* Illegal byte sequence */
+#define ERESTART 85 /* Interrupted system call should be restarted */
+#define ESTRPIPE 86 /* Streams pipe error */
+#define EUSERS 87 /* Too many users */
+#define ENOTSOCK 88 /* Socket operation on non-socket */
+#define EDESTADDRREQ 89 /* Destination address required */
+#define EMSGSIZE 90 /* Message too long */
+#define EPROTOTYPE 91 /* Protocol wrong type for socket */
+#define ENOPROTOOPT 92 /* Protocol not available */
+#define EPROTONOSUPPORT 93 /* Protocol not supported */
+#define ESOCKTNOSUPPORT 94 /* Socket type not supported */
+#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */
+#define EPFNOSUPPORT 96 /* Protocol family not supported */
+#define EAFNOSUPPORT 97 /* Address family not supported by protocol */
+#define EADDRINUSE 98 /* Address already in use */
+#define EADDRNOTAVAIL 99 /* Cannot assign requested address */
+#define ENETDOWN 100 /* Network is down */
+#define ENETUNREACH 101 /* Network is unreachable */
+#define ENETRESET 102 /* Network dropped connection because of reset */
+#define ECONNABORTED 103 /* Software caused connection abort */
+#define ECONNRESET 104 /* Connection reset by peer */
+#define ENOBUFS 105 /* No buffer space available */
+#define EISCONN 106 /* Transport endpoint is already connected */
+#define ENOTCONN 107 /* Transport endpoint is not connected */
+#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */
+#define ETOOMANYREFS 109 /* Too many references: cannot splice */
+#define ETIMEDOUT 110 /* Connection timed out */
+#define ECONNREFUSED 111 /* Connection refused */
+#define EHOSTDOWN 112 /* Host is down */
+#define EHOSTUNREACH 113 /* No route to host */
+#define EALREADY 114 /* Operation already in progress */
+#define EINPROGRESS 115 /* Operation now in progress */
+#define ESTALE 116 /* Stale NFS file handle */
+#define EUCLEAN 117 /* Structure needs cleaning */
+#define ENOTNAM 118 /* Not a XENIX named type file */
+#define ENAVAIL 119 /* No XENIX semaphores available */
+#define EISNAM 120 /* Is a named type file */
+#define EREMOTEIO 121 /* Remote I/O error */
+#define EDQUOT 122 /* Quota exceeded */
+
+#define ENOMEDIUM 123 /* No medium found */
+#define EMEDIUMTYPE 124 /* Wrong medium type */
+
+#endif
--- /dev/null
+#ifndef _I386_FCNTL_H
+#define _I386_FCNTL_H
+
+/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
+ located on an ext2 file system */
+#define O_ACCMODE 0003
+#define O_RDONLY 00
+#define O_WRONLY 01
+#define O_RDWR 02
+#define O_CREAT 0100 /* not fcntl */
+#define O_EXCL 0200 /* not fcntl */
+#define O_NOCTTY 0400 /* not fcntl */
+#define O_TRUNC 01000 /* not fcntl */
+#define O_APPEND 02000
+#define O_NONBLOCK 04000
+#define O_NDELAY O_NONBLOCK
+#define O_SYNC 010000
+#define FASYNC 020000 /* fcntl, for BSD compatibility */
+#define O_DIRECT 040000 /* direct disk access hint */
+#define O_LARGEFILE 0100000
+#define O_DIRECTORY 0200000 /* must be a directory */
+#define O_NOFOLLOW 0400000 /* don't follow links */
+
+#define F_DUPFD 0 /* dup */
+#define F_GETFD 1 /* get close_on_exec */
+#define F_SETFD 2 /* set/clear close_on_exec */
+#define F_GETFL 3 /* get file->f_flags */
+#define F_SETFL 4 /* set file->f_flags */
+#define F_GETLK 5
+#define F_SETLK 6
+#define F_SETLKW 7
+
+#define F_SETOWN 8 /* for sockets. */
+#define F_GETOWN 9 /* for sockets. */
+#define F_SETSIG 10 /* for sockets. */
+#define F_GETSIG 11 /* for sockets. */
+
+#define F_GETLK64 12 /* using 'struct flock64' */
+#define F_SETLK64 13
+#define F_SETLKW64 14
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC 1 /* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#define F_RDLCK 0
+#define F_WRLCK 1
+#define F_UNLCK 2
+
+/* for old implementation of bsd flock () */
+#define F_EXLCK 4 /* or 3 */
+#define F_SHLCK 8 /* or 4 */
+
+/* for leases */
+#define F_INPROGRESS 16
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH 1 /* shared lock */
+#define LOCK_EX 2 /* exclusive lock */
+#define LOCK_NB 4 /* or'd with one of the above to prevent
+ blocking */
+#define LOCK_UN 8 /* remove lock */
+
+#define LOCK_MAND 32 /* This is a mandatory flock */
+#define LOCK_READ 64 /* ... Which allows concurrent read operations */
+#define LOCK_WRITE 128 /* ... Which allows concurrent write operations */
+#define LOCK_RW 192 /* ... Which allows concurrent read & write ops */
+
+struct flock {
+ short l_type;
+ short l_whence;
+ off_t l_start;
+ off_t l_len;
+ pid_t l_pid;
+};
+
+struct flock64 {
+ short l_type;
+ short l_whence;
+ loff_t l_start;
+ loff_t l_len;
+ pid_t l_pid;
+};
+
+#define F_LINUX_SPECIFIC_BASE 1024
+
+#endif
--- /dev/null
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+enum fixed_addresses {
+#ifdef CONFIG_HIGHMEM_XXX
+ FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
+ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#endif
+ FIX_BLKRING_BASE,
+ __end_of_permanent_fixed_addresses,
+ __end_of_fixed_addresses
+};
+
+extern void __set_fixmap (enum fixed_addresses idx,
+ unsigned long phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+/*
+ * used by vmalloc.c.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap, and leave one page empty
+ * at the top of mem..
+ */
+#define FIXADDR_TOP (HYPERVISOR_VIRT_START - 2*PAGE_SIZE)
+#define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE)
+
+#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static inline unsigned long fix_to_virt(const unsigned int idx)
+{
+ /*
+ * this branch gets completely eliminated after inlining,
+ * except when someone tries to use fixaddr indices in an
+ * illegal way. (such as mixing up address types or using
+ * out-of-range indices).
+ *
+ * If it doesn't get removed, the linker will complain
+ * loudly with a reasonably clear error message..
+ */
+ if (idx >= __end_of_fixed_addresses)
+ __this_fixmap_does_not_exist();
+
+ return __fix_to_virt(idx);
+}
+
+#endif
--- /dev/null
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995
+ */
+#ifndef __ASM_I386_FLOPPY_H
+#define __ASM_I386_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma&1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port) inb_p(port)
+#define fd_outb(port,value) outb_p(port,value)
+
+#define fd_request_dma() CSW._request_dma(FLOPPY_DMA,"floppy")
+#define fd_free_dma() CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq() enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq() disable_irq(FLOPPY_IRQ)
+#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue() SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size) SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static void floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
+{
+ register unsigned char st;
+
+#undef TRACE_FLPY_INT
+#define NO_FLOPPY_ASSEMBLER
+
+#ifdef TRACE_FLPY_INT
+ static int calls=0;
+ static int bytes=0;
+ static int dma_wait=0;
+#endif
+ if(!doing_pdma) {
+ floppy_interrupt(irq, dev_id, regs);
+ return;
+ }
+
+#ifdef TRACE_FLPY_INT
+ if(!calls)
+ bytes = virtual_dma_count;
+#endif
+
+#ifndef NO_FLOPPY_ASSEMBLER
+ __asm__ (
+ "testl %1,%1"
+ "je 3f"
+"1: inb %w4,%b0"
+ "andb $160,%b0"
+ "cmpb $160,%b0"
+ "jne 2f"
+ "incw %w4"
+ "testl %3,%3"
+ "jne 4f"
+ "inb %w4,%b0"
+ "movb %0,(%2)"
+ "jmp 5f"
+"4: movb (%2),%0"
+ "outb %b0,%w4"
+"5: decw %w4"
+ "outb %0,$0x80"
+ "decl %1"
+ "incl %2"
+ "testl %1,%1"
+ "jne 1b"
+"3: inb %w4,%b0"
+"2: "
+ : "=a" ((char) st),
+ "=c" ((long) virtual_dma_count),
+ "=S" ((long) virtual_dma_addr)
+ : "b" ((long) virtual_dma_mode),
+ "d" ((short) virtual_dma_port+4),
+ "1" ((long) virtual_dma_count),
+ "2" ((long) virtual_dma_addr));
+#else
+ {
+ register int lcount;
+ register char *lptr;
+
+ st = 1;
+ for(lcount=virtual_dma_count, lptr=virtual_dma_addr;
+ lcount; lcount--, lptr++) {
+ st=inb(virtual_dma_port+4) & 0xa0 ;
+ if(st != 0xa0)
+ break;
+ if(virtual_dma_mode)
+ outb_p(*lptr, virtual_dma_port+5);
+ else
+ *lptr = inb_p(virtual_dma_port+5);
+ }
+ virtual_dma_count = lcount;
+ virtual_dma_addr = lptr;
+ st = inb(virtual_dma_port+4);
+ }
+#endif
+
+#ifdef TRACE_FLPY_INT
+ calls++;
+#endif
+ if(st == 0x20)
+ return;
+ if(!(st & 0x20)) {
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+#ifdef TRACE_FLPY_INT
+ printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+ virtual_dma_count, virtual_dma_residue, calls, bytes,
+ dma_wait);
+ calls = 0;
+ dma_wait=0;
+#endif
+ doing_pdma = 0;
+ floppy_interrupt(irq, dev_id, regs);
+ return;
+ }
+#ifdef TRACE_FLPY_INT
+ if(!virtual_dma_count)
+ dma_wait++;
+#endif
+}
+
+static void fd_disable_dma(void)
+{
+ if(! (can_use_virtual_dma & 1))
+ disable_dma(FLOPPY_DMA);
+ doing_pdma = 0;
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char * device_id)
+{
+ return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+ return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+ if(can_use_virtual_dma)
+ return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT,
+ "floppy", NULL);
+ else
+ return request_irq(FLOPPY_IRQ, floppy_interrupt,
+ SA_INTERRUPT|SA_SAMPLE_RANDOM,
+ "floppy", NULL);
+
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+ return __get_dma_pages(GFP_KERNEL,get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+ return (unsigned long) vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+ if((unsigned int) addr >= (unsigned int) high_memory)
+ return vfree((void *)addr);
+ else
+ free_pages(addr, get_order(size));
+}
+
+#define fd_dma_mem_free(addr, size) _fd_dma_mem_free(addr, size)
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+ if(can_use_virtual_dma == 2) {
+ if((unsigned int) addr >= (unsigned int) high_memory ||
+ virt_to_bus(addr) >= 0x1000000 ||
+ _CROSS_64KB(addr, size, 0))
+ use_virtual_dma = 1;
+ else
+ use_virtual_dma = 0;
+ } else {
+ use_virtual_dma = can_use_virtual_dma & 1;
+ }
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+ doing_pdma = 1;
+ virtual_dma_port = io;
+ virtual_dma_mode = (mode == DMA_MODE_WRITE);
+ virtual_dma_addr = addr;
+ virtual_dma_count = size;
+ virtual_dma_residue = 0;
+ return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+ if (CROSS_64KB(addr, size)) {
+ printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+ return -1;
+ }
+#endif
+ /* actual, physical DMA */
+ doing_pdma = 0;
+ clear_dma_ff(FLOPPY_DMA);
+ set_dma_mode(FLOPPY_DMA,mode);
+ set_dma_addr(FLOPPY_DMA,virt_to_bus(addr));
+ set_dma_count(FLOPPY_DMA,size);
+ enable_dma(FLOPPY_DMA);
+ return 0;
+}
+
+struct fd_routine_l {
+ int (*_request_dma)(unsigned int dmanr, const char * device_id);
+ void (*_free_dma)(unsigned int dmanr);
+ int (*_get_dma_residue)(unsigned int dummy);
+ unsigned long (*_dma_mem_alloc) (unsigned long size);
+ int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+ {
+ request_dma,
+ free_dma,
+ get_dma_residue,
+ dma_mem_alloc,
+ hard_dma_setup
+ },
+ {
+ vdma_request_dma,
+ vdma_nop,
+ vdma_get_dma_residue,
+ vdma_mem_alloc,
+ vdma_dma_setup
+ }
+};
+
+
+static int FDC1 = 0x3f0;
+static int FDC2 = -1;
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user. Paul G.
+ */
+#define FLOPPY0_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = (CMOS_READ(0x10) >> 4) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define FLOPPY1_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = CMOS_READ(0x10) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define FLOPPY_MOTOR_MASK 0xf0
+
+#define AUTO_DMA
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_I386_FLOPPY_H */
--- /dev/null
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+/* assembly code in softirq.h is sensitive to the offsets of these fields */
+typedef struct {
+ unsigned int __softirq_pending;
+ unsigned int __local_irq_count;
+ unsigned int __local_bh_count;
+ unsigned int __syscall_count;
+ struct task_struct * __ksoftirqd_task; /* waitqueue is too large */
+ unsigned int __nmi_count; /* arch dependent */
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */
+
+/*
+ * Are we in an interrupt context? Either doing bottom half
+ * or hardware interrupt processing?
+ */
+#define in_interrupt() ({ int __cpu = smp_processor_id(); \
+ (local_irq_count(__cpu) + local_bh_count(__cpu) != 0); })
+
+#define in_irq() (local_irq_count(smp_processor_id()) != 0)
+
+#ifndef CONFIG_SMP
+
+#define hardirq_trylock(cpu) (local_irq_count(cpu) == 0)
+#define hardirq_endlock(cpu) do { } while (0)
+
+#define irq_enter(cpu, irq) (local_irq_count(cpu)++)
+#define irq_exit(cpu, irq) (local_irq_count(cpu)--)
+
+#define synchronize_irq() barrier()
+
+#else
+
+#include <asm/atomic.h>
+#include <asm/smp.h>
+
+extern unsigned char global_irq_holder;
+extern unsigned volatile long global_irq_lock; /* long for set_bit -RR */
+
+static inline int irqs_running (void)
+{
+ int i;
+
+ for (i = 0; i < smp_num_cpus; i++)
+ if (local_irq_count(i))
+ return 1;
+ return 0;
+}
+
+static inline void release_irqlock(int cpu)
+{
+ /* if we didn't own the irq lock, just ignore.. */
+ if (global_irq_holder == (unsigned char) cpu) {
+ global_irq_holder = NO_PROC_ID;
+ clear_bit(0,&global_irq_lock);
+ }
+}
+
+static inline void irq_enter(int cpu, int irq)
+{
+ ++local_irq_count(cpu);
+
+ while (test_bit(0,&global_irq_lock)) {
+ cpu_relax();
+ }
+}
+
+static inline void irq_exit(int cpu, int irq)
+{
+ --local_irq_count(cpu);
+}
+
+static inline int hardirq_trylock(int cpu)
+{
+ return !local_irq_count(cpu) && !test_bit(0,&global_irq_lock);
+}
+
+#define hardirq_endlock(cpu) do { } while (0)
+
+extern void synchronize_irq(void);
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_HARDIRQ_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/hdreg.h
+ *
+ * Copyright (C) 1994-1996 Linus Torvalds & authors
+ */
+
+#ifndef __ASMi386_HDREG_H
+#define __ASMi386_HDREG_H
+
+//typedef unsigned short ide_ioreg_t;
+typedef unsigned long ide_ioreg_t;
+
+#endif /* __ASMi386_HDREG_H */
--- /dev/null
+#error "Highmem unsupported!"
+
--- /dev/null
+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ * linux/include/asm/hw_irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ */
+
+#include <linux/config.h>
+#include <linux/smp.h>
+#include <asm/atomic.h>
+#include <asm/irq.h>
+
+#define SYSCALL_VECTOR 0x80
+
+extern int irq_vector[NR_IRQS];
+
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+extern char _stext, _etext;
+
+extern unsigned long prof_cpu_mask;
+extern unsigned int * prof_buffer;
+extern unsigned long prof_len;
+extern unsigned long prof_shift;
+
+/*
+ * x86 profiling function, SMP safe. We might want to do this in
+ * assembly totally?
+ */
+static inline void x86_do_profile (unsigned long eip)
+{
+ if (!prof_buffer)
+ return;
+
+ /*
+ * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
+ * (default is all CPUs.)
+ */
+ if (!((1<<smp_processor_id()) & prof_cpu_mask))
+ return;
+
+ eip -= (unsigned long) &_stext;
+ eip >>= prof_shift;
+ /*
+ * Don't ignore out-of-bounds EIP values silently,
+ * put them into the last histogram slot, so if
+ * present, they will show up as a sharp peak.
+ */
+ if (eip > prof_len-1)
+ eip = prof_len-1;
+ atomic_inc((atomic_t *)&prof_buffer[eip]);
+}
+
+static inline void hw_resend_irq(struct hw_interrupt_type *h,
+ unsigned int i)
+{}
+
+#endif /* _ASM_HW_IRQ_H */
--- /dev/null
+/******************************************************************************
+ * block.h
+ *
+ * Block IO communication rings.
+ *
+ * These are the ring data structures for buffering messages between
+ * the hypervisor and guestos's.
+ *
+ */
+
+#ifndef __BLOCK_H__
+#define __BLOCK_H__
+
+#include <linux/kdev_t.h>
+
+/* the first four definitions match fs.h */
+#define XEN_BLOCK_READ 0
+#define XEN_BLOCK_WRITE 1
+#define XEN_BLOCK_READA 2 /* currently unused */
+#define XEN_BLOCK_SPECIAL 4 /* currently unused */
+#define XEN_BLOCK_PROBE 8 /* determine io configuration from hypervisor */
+#define XEN_BLOCK_DEBUG 16 /* debug */
+
+#define BLK_RING_SIZE 128
+#define BLK_RING_MAX_ENTRIES (BLK_RING_SIZE - 2)
+#define BLK_RING_INC(_i) (((_i)+1) & (BLK_RING_SIZE-1))
+#define BLK_RING_ADD(_i,_j) (((_i)+(_j)) & (BLK_RING_SIZE-1))
+
+typedef struct blk_ring_req_entry
+{
+ void * id; /* for guest os use */
+ int operation; /* XEN_BLOCK_READ or XEN_BLOCK_WRITE */
+ char * buffer;
+ unsigned long block_number; /* block number */
+ unsigned short block_size; /* block size */
+ kdev_t device;
+ unsigned long sector_number; /* real buffer location on disk */
+} blk_ring_req_entry_t;
+
+typedef struct blk_ring_resp_entry
+{
+ void *id;
+ unsigned long status;
+} blk_ring_resp_entry_t;
+
+typedef struct blk_ring_st
+{
+ unsigned int req_prod; /* Request producer. Updated by guest OS. */
+ unsigned int resp_prod; /* Response producer. Updated by Xen. */
+ union {
+ blk_ring_req_entry_t req;
+ blk_ring_resp_entry_t resp;
+ } ring[BLK_RING_SIZE];
+} blk_ring_t;
+
+#define MAX_XEN_DISK_COUNT 100
+
+#define XEN_DISK_IDE 1
+#define XEN_DISK_SCSI 2
+
+typedef struct xen_disk /* physical disk */
+{
+ int type; /* disk type */
+ unsigned long capacity;
+ unsigned char heads; /* hdreg.h::hd_geometry */
+ unsigned char sectors; /* hdreg.h::hd_geometry */
+ unsigned int cylinders; /* hdreg.h::hd_big_geometry */
+ unsigned long start; /* hdreg.h::hd_geometry */
+ void * gendisk; /* struct gendisk ptr */
+} xen_disk_t;
+
+typedef struct xen_disk_info
+{
+ int count; /* number of subsequent xen_disk_t structures to follow */
+ xen_disk_t disks[100];
+} xen_disk_info_t;
+
+#endif
--- /dev/null
+/******************************************************************************
+ * hypervisor-if.h
+ *
+ * Interface to Xeno hypervisor.
+ */
+
+#include "network.h"
+#include "block.h"
+
+#ifndef __HYPERVISOR_IF_H__
+#define __HYPERVISOR_IF_H__
+
+/*
+ * Virtual addresses beyond this are not modifiable by guest OSes.
+ * The machine->physical mapping table starts at this address, read-only
+ * to all domains except DOM0.
+ */
+#define HYPERVISOR_VIRT_START (0xFC000000UL)
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+typedef struct trap_info_st
+{
+ unsigned char vector; /* exception/interrupt vector */
+ unsigned char dpl; /* privilege level */
+ unsigned short cs; /* code selector */
+ unsigned long address; /* code address */
+} trap_info_t;
+
+
+typedef struct
+{
+/*
+ * PGREQ_XXX: specified in least-significant bits of 'ptr' field.
+ * All requests specify relevent PTE or PT address in 'ptr'.
+ * Normal requests specify update value in 'value'.
+ * Extended requests specify command in least 8 bits of 'value'.
+ */
+/* A normal page-table update request. */
+#define PGREQ_NORMAL 0
+/* Update an entry in the machine->physical mapping table. */
+#define PGREQ_MPT_UPDATE 1
+/* An extended command. */
+#define PGREQ_EXTENDED_COMMAND 2
+/* DOM0 can make entirely unchecked updates which do not affect refcnts. */
+#define PGREQ_UNCHECKED_UPDATE 3
+ unsigned long ptr, val; /* *ptr = val */
+/* Announce a new top-level page table. */
+#define PGEXT_PIN_L1_TABLE 0
+#define PGEXT_PIN_L2_TABLE 1
+#define PGEXT_PIN_L3_TABLE 2
+#define PGEXT_PIN_L4_TABLE 3
+#define PGEXT_UNPIN_TABLE 4
+#define PGEXT_NEW_BASEPTR 5
+#define PGEXT_TLB_FLUSH 6
+#define PGEXT_INVLPG 7
+#define PGEXT_CMD_MASK 255
+#define PGEXT_CMD_SHIFT 8
+} page_update_request_t;
+
+
+/*
+ * Segment descriptor tables.
+ */
+/* 8 entries, plus a TSS entry for each CPU (up to 32 CPUs). */
+#define FIRST_DOMAIN_GDT_ENTRY 40
+/* These are flat segments for domain bootstrap and fallback. */
+#define FLAT_RING1_CS 0x11
+#define FLAT_RING1_DS 0x19
+#define FLAT_RING3_CS 0x23
+#define FLAT_RING3_DS 0x2b
+
+
+/* EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5. */
+
+#define __HYPERVISOR_set_trap_table 0
+#define __HYPERVISOR_pt_update 1
+#define __HYPERVISOR_console_write 2
+#define __HYPERVISOR_set_gdt 3
+#define __HYPERVISOR_stack_and_ldt_switch 4
+#define __HYPERVISOR_net_update 5
+#define __HYPERVISOR_fpu_taskswitch 6
+#define __HYPERVISOR_sched_op 7
+#define __HYPERVISOR_exit 8
+#define __HYPERVISOR_dom0_op 9
+#define __HYPERVISOR_network_op 10
+#define __HYPERVISOR_block_io_op 11
+#define __HYPERVISOR_set_debugreg 12
+#define __HYPERVISOR_get_debugreg 13
+#define __HYPERVISOR_update_descriptor 14
+#define __HYPERVISOR_set_fast_trap 15
+
+#define TRAP_INSTR "int $0x82"
+
+
+/* Event message note:
+ *
+ * Here, as in the interrupts to the guestos, additional network interfaces
+ * are defined. These definitions server as placeholders for the event bits,
+ * however, in the code these events will allways be referred to as shifted
+ * offsets from the base NET events.
+ */
+
+/* Events that a guest OS may receive from the hypervisor. */
+#define EVENT_BLK_RESP 0x01 /* A block device response has been queued. */
+#define EVENT_TIMER 0x02 /* A timeout has been updated. */
+#define EVENT_DIE 0x04 /* OS is about to be killed. Clean up please! */
+#define EVENT_DEBUG 0x08 /* Request guest to dump debug info (gross!) */
+#define EVENT_NET_TX 0x10 /* There are packets for transmission. */
+#define EVENT_NET_RX 0x20 /* There are empty buffers for receive. */
+
+/* Bit offsets, as opposed to the above masks. */
+#define _EVENT_BLK_RESP 0
+#define _EVENT_TIMER 1
+#define _EVENT_DIE 2
+#define _EVENT_NET_TX 3
+#define _EVENT_NET_RX 4
+#define _EVENT_DEBUG 5
+
+
+/*
+ * NB. We expect that this struct is smaller than a page.
+ */
+typedef struct shared_info_st {
+
+ /* Bitmask of outstanding event notifications hypervisor -> guest OS. */
+ unsigned long events;
+ /*
+ * Hypervisor will only signal event delivery via the "callback
+ * exception" when this value is non-zero. Hypervisor clears this when
+ * notiying the guest OS -- this prevents unbounded reentrancy and
+ * stack overflow (in this way, acts as an interrupt-enable flag).
+ */
+ unsigned long events_enable;
+
+ /*
+ * Address for callbacks hypervisor -> guest OS.
+ * Stack frame looks like that of an interrupt.
+ * Code segment is the default flat selector.
+ * This handler will only be called when events_enable is non-zero.
+ */
+ unsigned long event_address;
+
+ /*
+ * Hypervisor uses this callback when it takes a fault on behalf of
+ * an application. This can happen when returning from interrupts for
+ * example: various faults can occur when reloading the segment
+ * registers, and executing 'iret'.
+ * This callback is provided with an extended stack frame, augmented
+ * with saved values for segment registers %ds and %es:
+ * %ds, %es, %eip, %cs, %eflags [, %oldesp, %oldss]
+ * Code segment is the default flat selector.
+ * FAULTS WHEN CALLING THIS HANDLER WILL TERMINATE THE DOMAIN!!!
+ */
+ unsigned long failsafe_address;
+
+ /*
+ * Time:
+ * The following abstractions are exposed: System Time, Wall Clock
+ * Time, Domain Virtual Time. Domains can access Cycle counter time
+ * directly.
+ * XXX RN: Need something to pass NTP scaling to GuestOS.
+ */
+
+ u64 cpu_freq; /* to calculate ticks -> real time */
+
+ /* System Time */
+ long long system_time; /* in ns */
+ unsigned long st_timestamp; /* cyclecounter at last update */
+
+ /* Wall Clock Time */
+ u32 wc_version; /* a version number for info below */
+ long tv_sec; /* essentially a struct timeval */
+ long tv_usec;
+ long long wc_timestamp; /* system time at last update */
+
+ /* Domain Virtual Time */
+ unsigned long long domain_time;
+
+ /*
+ * Timeout values:
+ * Allow a domain to specify a timeout value in system time and
+ * domain virtual time.
+ */
+ unsigned long long wall_timeout;
+ unsigned long long domain_timeout;
+
+} shared_info_t;
+
+/*
+ * NB. We expect that this struct is smaller than a page.
+ */
+typedef struct start_info_st {
+ unsigned long nr_pages; /* total pages allocated to this domain */
+ shared_info_t *shared_info; /* VIRTUAL address of shared info struct */
+ unsigned long pt_base; /* VIRTUAL address of page directory */
+ unsigned long mod_start; /* VIRTUAL address of pre-loaded module */
+ unsigned long mod_len; /* size (bytes) of pre-loaded module */
+ net_ring_t *net_rings; /* network rings (VIRTUAL ADDRESS) */
+ int num_net_rings;
+ unsigned long blk_ring; /* block io ring (MACHINE ADDRESS) */
+ unsigned char cmd_line[1]; /* variable-length */
+} start_info_t;
+
+/* For use in guest OSes. */
+extern shared_info_t *HYPERVISOR_shared_info;
+
+#endif /* __HYPERVISOR_IF_H__ */
--- /dev/null
+/******************************************************************************
+ * network.h
+ *
+ * ring data structures for buffering messages between hypervisor and
+ * guestos's. As it stands this is only used for network buffer exchange.
+ *
+ * This file also contains structures and interfaces for the per-domain
+ * routing/filtering tables in the hypervisor.
+ *
+ */
+
+#ifndef __RING_H__
+#define __RING_H__
+
+#include <linux/types.h>
+
+typedef struct tx_entry_st {
+ unsigned long addr; /* virtual address */
+ unsigned long size; /* in bytes */
+ int status; /* per descriptor status. */
+} tx_entry_t;
+
+typedef struct rx_entry_st {
+ unsigned long addr; /* virtual address */
+ unsigned long size; /* in bytes */
+ int status; /* per descriptor status. */
+} rx_entry_t;
+
+#define TX_RING_SIZE 256
+#define RX_RING_SIZE 256
+typedef struct net_ring_st {
+ /*
+ * Guest OS places packets into ring at tx_prod.
+ * Hypervisor removes at tx_cons.
+ * Ring is empty when tx_prod == tx_cons.
+ * Guest OS receives a DOMAIN_EVENT_NET_TX when tx_cons passes tx_event.
+ * Hypervisor may be prodded whenever tx_prod is updated, but this is
+ * only necessary when tx_cons == old_tx_prod (ie. transmitter stalled).
+ */
+ tx_entry_t *tx_ring;
+ unsigned int tx_prod, tx_cons, tx_event;
+
+ /*
+ * Guest OS places empty buffers into ring at rx_prod.
+ * Hypervisor fills buffers as rx_cons.
+ * Ring is empty when rx_prod == rx_cons.
+ * Guest OS receives a DOMAIN_EVENT_NET_RX when rx_cons passes rx_event.
+ * Hypervisor may be prodded whenever rx_prod is updated, but this is
+ * only necessary when rx_cons == old_rx_prod (ie. receiver stalled).
+ */
+ rx_entry_t *rx_ring;
+ unsigned int rx_prod, rx_cons, rx_event;
+} net_ring_t;
+
+/* Specify base of per-domain array. Get returned free slot in the array. */
+/*net_ring_t *create_net_vif(int domain);*/
+
+/* Packet routing/filtering code follows:
+ */
+
+#define NETWORK_ACTION_ACCEPT 0
+#define NETWORK_ACTION_COUNT 1
+
+#define NETWORK_PROTO_ANY 0
+#define NETWORK_PROTO_IP 1
+#define NETWORK_PROTO_TCP 2
+#define NETWORK_PROTO_UDP 3
+#define NETWORK_PROTO_ARP 4
+
+typedef struct net_rule_st
+{
+ u32 src_addr;
+ u32 dst_addr;
+ u16 src_port;
+ u16 dst_port;
+ u32 src_addr_mask;
+ u32 dst_addr_mask;
+ u16 src_port_mask;
+ u16 dst_port_mask;
+ u16 proto;
+
+ int src_interface;
+ int dst_interface;
+ u16 action;
+} net_rule_t;
+
+typedef struct vif_query_st
+{
+ unsigned int domain;
+ char *buf; // where to put the reply -- guest virtual address
+} vif_query_t;
+
+/* Network trap operations and associated structure.
+ * This presently just handles rule insertion and deletion, but will
+ * evenually have code to add and remove interfaces.
+ */
+
+#define NETWORK_OP_ADDRULE 0
+#define NETWORK_OP_DELETERULE 1
+#define NETWORK_OP_GETRULELIST 2
+#define NETWORK_OP_VIFQUERY 3
+
+typedef struct network_op_st
+{
+ unsigned long cmd;
+ union
+ {
+ net_rule_t net_rule;
+ vif_query_t vif_query;
+ }
+ u;
+} network_op_t;
+
+typedef struct net_rule_ent_st
+{
+ net_rule_t r;
+ struct net_rule_ent_st *next;
+} net_rule_ent_t;
+
+/* Drop a new rule down to the network tables. */
+int add_net_rule(net_rule_t *rule);
+
+
+/* Descriptor status values:
+ */
+
+#define RING_STATUS_OK 0 // Everything is gravy.
+#define RING_STATUS_ERR_CFU -1 // Copy from user problems.
+#define RING_STATUS_BAD_PAGE -2 // What they gave us was pure evil.
+
+#endif
--- /dev/null
+/******************************************************************************
+ * hypervisor.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002, K A Fraser
+ */
+
+#ifndef __HYPERVISOR_H__
+#define __HYPERVISOR_H__
+
+#include <asm/hypervisor-ifs/hypervisor-if.h>
+#include <asm/ptrace.h>
+
+/* arch/xeno/kernel/setup.c */
+union start_info_union
+{
+ start_info_t start_info;
+ char padding[512];
+};
+extern union start_info_union start_info_union;
+#define start_info (start_info_union.start_info)
+
+/* arch/xeno/kernel/hypervisor.c */
+void do_hypervisor_callback(struct pt_regs *regs);
+
+
+/* arch/xeno/mm/hypervisor.c */
+/*
+ * NB. ptr values should be PHYSICAL, not MACHINE. 'vals' should be already
+ * be MACHINE addresses.
+ */
+
+extern unsigned int pt_update_queue_idx;
+
+void queue_l1_entry_update(unsigned long ptr, unsigned long val);
+void queue_l2_entry_update(unsigned long ptr, unsigned long val);
+void queue_pt_switch(unsigned long ptr);
+void queue_tlb_flush(void);
+void queue_invlpg(unsigned long ptr);
+void queue_pgd_pin(unsigned long ptr);
+void queue_pgd_unpin(unsigned long ptr);
+void queue_pte_pin(unsigned long ptr);
+void queue_pte_unpin(unsigned long ptr);
+
+#define PT_UPDATE_DEBUG 0
+
+#if PT_UPDATE_DEBUG > 0
+typedef struct {
+ unsigned long ptr, val, pteval;
+ void *ptep;
+ int line; char *file;
+} page_update_debug_t;
+extern page_update_debug_t update_debug_queue[];
+#define queue_l1_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ queue_l1_entry_update((_p),(_v)); \
+})
+#define queue_l2_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ queue_l2_entry_update((_p),(_v)); \
+})
+#endif
+
+#if PT_UPDATE_DEBUG > 1
+#undef queue_l1_entry_update
+#undef queue_l2_entry_update
+#define queue_l1_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ printk("L1 %s %d: %08lx (%08lx -> %08lx)\n", __FILE__, __LINE__, \
+ phys_to_machine(_p), *(unsigned long *)__va(_p), \
+ (unsigned long)(_v)); \
+ queue_l1_entry_update((_p),(_v)); \
+})
+#define queue_l2_entry_update(_p,_v) ({ \
+ update_debug_queue[pt_update_queue_idx].ptr = (_p); \
+ update_debug_queue[pt_update_queue_idx].val = (_v); \
+ update_debug_queue[pt_update_queue_idx].line = __LINE__; \
+ update_debug_queue[pt_update_queue_idx].file = __FILE__; \
+ printk("L2 %s %d: %08lx (%08lx -> %08lx)\n", __FILE__, __LINE__, \
+ phys_to_machine(_p), *(unsigned long *)__va(_p), \
+ (unsigned long)(_v)); \
+ queue_l2_entry_update((_p),(_v)); \
+})
+#define queue_pt_switch(_p) ({ \
+ printk("PTSWITCH %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pt_switch(_p); \
+})
+#define queue_tlb_flush() ({ \
+ printk("TLB FLUSH %s %d\n", __FILE__, __LINE__); \
+ queue_tlb_flush(); \
+})
+#define queue_invlpg(_p) ({ \
+ printk("INVLPG %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_invlpg(_p); \
+})
+#define queue_pgd_pin(_p) ({ \
+ printk("PGD PIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pgd_pin(_p); \
+})
+#define queue_pgd_unpin(_p) ({ \
+ printk("PGD UNPIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pgd_unpin(_p); \
+})
+#define queue_pte_pin(_p) ({ \
+ printk("PTE PIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pte_pin(_p); \
+})
+#define queue_pte_unpin(_p) ({ \
+ printk("PTE UNPIN %s %d: %08lx\n", __FILE__, __LINE__, (_p)); \
+ queue_pte_unpin(_p); \
+})
+#endif
+
+void _flush_page_update_queue(void);
+static inline int flush_page_update_queue(void)
+{
+ unsigned int idx = pt_update_queue_idx;
+ if ( idx != 0 ) _flush_page_update_queue();
+ return idx;
+}
+#define XENO_flush_page_update_queue() (_flush_page_update_queue())
+
+
+/*
+ * Assembler stubs for hyper-calls.
+ */
+
+static inline int HYPERVISOR_set_trap_table(trap_info_t *table)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_trap_table),
+ "b" (table) );
+
+ return ret;
+}
+
+
+static inline int HYPERVISOR_pt_update(page_update_request_t *req, int count)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_pt_update),
+ "b" (req), "c" (count) );
+
+ return ret;
+}
+
+
+static inline int HYPERVISOR_console_write(const char *str, int count)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_console_write),
+ "b" (str), "c" (count) );
+
+
+ return ret;
+}
+
+static inline int HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_gdt),
+ "b" (frame_list), "c" (entries) );
+
+
+ return ret;
+}
+
+static inline int HYPERVISOR_stack_and_ldt_switch(
+ unsigned long ss, unsigned long esp, unsigned long ldts)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_stack_and_ldt_switch),
+ "b" (ss), "c" (esp), "d" (ldts) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_net_update(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_net_update) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_fpu_taskswitch(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_fpu_taskswitch) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_do_sched_op(void *sched_op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_sched_op),
+ "b" (sched_op) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_exit(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_exit) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_dom0_op(void *dom0_op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_dom0_op),
+ "b" (dom0_op) : "memory" );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_network_op(void *network_op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_network_op),
+ "b" (network_op) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_block_io_op(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_block_io_op) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_set_debugreg(int reg, unsigned long value)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_debugreg),
+ "b" (reg), "c" (value) );
+
+ return ret;
+}
+
+static inline unsigned long HYPERVISOR_get_debugreg(int reg)
+{
+ unsigned long ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_get_debugreg),
+ "b" (reg) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_update_descriptor(
+ unsigned long pa, unsigned long word1, unsigned long word2)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_gdt),
+ "b" (pa), "c" (word1), "d" (word2) );
+
+ return ret;
+}
+
+static inline int HYPERVISOR_set_fast_trap(int idx)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" (__HYPERVISOR_set_fast_trap),
+ "b" (idx) );
+
+ return ret;
+}
+
+#endif /* __HYPERVISOR_H__ */
--- /dev/null
+/*
+ * include/asm-i386/i387.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#ifndef __ASM_I386_I387_H
+#define __ASM_I386_I387_H
+
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+
+extern void init_fpu(void);
+/*
+ * FPU lazy state save handling...
+ */
+extern void save_init_fpu( struct task_struct *tsk );
+extern void restore_fpu( struct task_struct *tsk );
+
+extern void kernel_fpu_begin(void);
+#define kernel_fpu_end() stts()
+
+
+#define unlazy_fpu( tsk ) do { \
+ if ( tsk->flags & PF_USEDFPU ) \
+ save_init_fpu( tsk ); \
+} while (0)
+
+#define clear_fpu( tsk ) do { \
+ if ( tsk->flags & PF_USEDFPU ) { \
+ asm volatile("fwait"); \
+ tsk->flags &= ~PF_USEDFPU; \
+ stts(); \
+ } \
+} while (0)
+
+/*
+ * FPU state interaction...
+ */
+extern unsigned short get_fpu_cwd( struct task_struct *tsk );
+extern unsigned short get_fpu_swd( struct task_struct *tsk );
+extern unsigned short get_fpu_twd( struct task_struct *tsk );
+extern unsigned short get_fpu_mxcsr( struct task_struct *tsk );
+
+extern void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd );
+extern void set_fpu_swd( struct task_struct *tsk, unsigned short swd );
+extern void set_fpu_twd( struct task_struct *tsk, unsigned short twd );
+extern void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr );
+
+#define load_mxcsr( val ) do { \
+ unsigned long __mxcsr = ((unsigned long)(val) & 0xffbf); \
+ asm volatile( "ldmxcsr %0" : : "m" (__mxcsr) ); \
+} while (0)
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387( struct _fpstate *buf );
+extern int restore_i387( struct _fpstate *buf );
+
+/*
+ * ptrace request handers...
+ */
+extern int get_fpregs( struct user_i387_struct *buf,
+ struct task_struct *tsk );
+extern int set_fpregs( struct task_struct *tsk,
+ struct user_i387_struct *buf );
+
+extern int get_fpxregs( struct user_fxsr_struct *buf,
+ struct task_struct *tsk );
+extern int set_fpxregs( struct task_struct *tsk,
+ struct user_fxsr_struct *buf );
+extern void load_empty_fpu(struct task_struct *);
+
+/*
+ * FPU state for core dumps...
+ */
+extern int dump_fpu( struct pt_regs *regs,
+ struct user_i387_struct *fpu );
+extern int dump_extended_fpu( struct pt_regs *regs,
+ struct user_fxsr_struct *fpu );
+
+#endif /* __ASM_I386_I387_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/ide.h
+ *
+ * Copyright (C) 1994-1996 Linus Torvalds & authors
+ */
+
+/*
+ * This file contains the i386 architecture specific IDE code.
+ */
+
+#ifndef __ASMi386_IDE_H
+#define __ASMi386_IDE_H
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+
+#ifndef MAX_HWIFS
+# ifdef CONFIG_BLK_DEV_IDEPCI
+#define MAX_HWIFS 10
+# else
+#define MAX_HWIFS 6
+# endif
+#endif
+
+static __inline__ int ide_default_irq(ide_ioreg_t base)
+{
+ switch (base) {
+ case 0x1f0: return 14;
+ case 0x170: return 15;
+ case 0x1e8: return 11;
+ case 0x168: return 10;
+ case 0x1e0: return 8;
+ case 0x160: return 12;
+ default:
+ return 0;
+ }
+}
+
+static __inline__ ide_ioreg_t ide_default_io_base(int index)
+{
+ switch (index) {
+ case 0: return 0x1f0;
+ case 1: return 0x170;
+ case 2: return 0x1e8;
+ case 3: return 0x168;
+ case 4: return 0x1e0;
+ case 5: return 0x160;
+ default:
+ return 0;
+ }
+}
+
+static __inline__ void ide_init_hwif_ports(hw_regs_t *hw, ide_ioreg_t data_port, ide_ioreg_t ctrl_port, int *irq)
+{
+ ide_ioreg_t reg = data_port;
+ int i;
+
+ for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
+ hw->io_ports[i] = reg;
+ reg += 1;
+ }
+ if (ctrl_port) {
+ hw->io_ports[IDE_CONTROL_OFFSET] = ctrl_port;
+ } else {
+ hw->io_ports[IDE_CONTROL_OFFSET] = hw->io_ports[IDE_DATA_OFFSET] + 0x206;
+ }
+ if (irq != NULL)
+ *irq = 0;
+ hw->io_ports[IDE_IRQ_OFFSET] = 0;
+}
+
+static __inline__ void ide_init_default_hwifs(void)
+{
+#ifndef CONFIG_BLK_DEV_IDEPCI
+ hw_regs_t hw;
+ int index;
+
+ for(index = 0; index < MAX_HWIFS; index++) {
+ memset(&hw, 0, sizeof hw);
+ ide_init_hwif_ports(&hw, ide_default_io_base(index), 0, NULL);
+ hw.irq = ide_default_irq(ide_default_io_base(index));
+ ide_register_hw(&hw, NULL);
+ }
+#endif /* CONFIG_BLK_DEV_IDEPCI */
+}
+
+#include <asm-generic/ide_iops.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASMi386_IDE_H */
--- /dev/null
+#error "<asm/init.h> should never be used - use <linux/init.h> instead"
--- /dev/null
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ * Linus
+ */
+
+ /*
+ * Bit simplified and optimized by Jan Hubicka
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+ *
+ * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+ * isa_read[wl] and isa_write[wl] fixed
+ * - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ */
+
+#define IO_SPACE_LIMIT 0xffff
+
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */
+#define XQUAD_PORTIO_LEN 0x80000 /* Only remapping first 2 quads */
+
+#ifdef __KERNEL__
+
+#include <linux/vmalloc.h>
+
+/*
+ * Temporary debugging check to catch old code using
+ * unmapped ISA addresses. Will be removed in 2.4.
+ */
+#if CONFIG_DEBUG_IOVIRT
+ extern void *__io_virt_debug(unsigned long x, const char *file, int line);
+ extern unsigned long __io_phys_debug(unsigned long x, const char *file, int line);
+ #define __io_virt(x) __io_virt_debug((unsigned long)(x), __FILE__, __LINE__)
+//#define __io_phys(x) __io_phys_debug((unsigned long)(x), __FILE__, __LINE__)
+#else
+ #define __io_virt(x) ((void *)(x))
+//#define __io_phys(x) __pa(x)
+#endif
+
+/**
+ * virt_to_phys - map virtual addresses to physical
+ * @address: address to remap
+ *
+ * The returned physical address is the physical (CPU) mapping for
+ * the memory address given. It is only valid to use this function on
+ * addresses directly mapped or allocated via kmalloc.
+ *
+ * This function does not give bus mappings for DMA transfers. In
+ * almost all conceivable cases a device driver should not be using
+ * this function
+ */
+
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+ return __pa(address);
+}
+
+/**
+ * phys_to_virt - map physical address to virtual
+ * @address: address to remap
+ *
+ * The returned virtual address is a current CPU mapping for
+ * the memory address given. It is only valid to use this function on
+ * addresses that have a kernel mapping
+ *
+ * This function does not handle bus mappings for DMA transfers. In
+ * almost all conceivable cases a device driver should not be using
+ * this function
+ */
+
+static inline void * phys_to_virt(unsigned long address)
+{
+ return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#ifdef CONFIG_HIGHMEM64G
+#define page_to_phys(page) ((u64)(page - mem_map) << PAGE_SHIFT)
+#else
+#define page_to_phys(page) ((page - mem_map) << PAGE_SHIFT)
+#endif
+
+/*
+ * IO bus memory addresses are also 1:1 with the physical address
+ */
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+#define page_to_bus page_to_phys
+
+/*
+ * readX/writeX() are used to access memory mapped devices. On some
+ * architectures the memory mapped IO stuff needs to be accessed
+ * differently. On the x86 architecture, we just read/write the
+ * memory location directly.
+ */
+
+#define readb(addr) (*(volatile unsigned char *) __io_virt(addr))
+#define readw(addr) (*(volatile unsigned short *) __io_virt(addr))
+#define readl(addr) (*(volatile unsigned int *) __io_virt(addr))
+#define __raw_readb readb
+#define __raw_readw readw
+#define __raw_readl readl
+
+#define writeb(b,addr) (*(volatile unsigned char *) __io_virt(addr) = (b))
+#define writew(b,addr) (*(volatile unsigned short *) __io_virt(addr) = (b))
+#define writel(b,addr) (*(volatile unsigned int *) __io_virt(addr) = (b))
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+
+#define memset_io(a,b,c) __memset(__io_virt(a),(b),(c))
+#define memcpy_fromio(a,b,c) __memcpy((a),__io_virt(b),(c))
+#define memcpy_toio(a,b,c) __memcpy(__io_virt(a),(b),(c))
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char *)(PAGE_OFFSET))
+
+#define isa_readb(a) readb(__ISA_IO_base + (a))
+#define isa_readw(a) readw(__ISA_IO_base + (a))
+#define isa_readl(a) readl(__ISA_IO_base + (a))
+#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
+#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
+#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
+#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c))
+#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c))
+#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c))
+
+
+/*
+ * Again, i386 does not require mem IO specific function.
+ */
+
+#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),__io_virt(b),(c),(d))
+#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),__io_virt(__ISA_IO_base + (b)),(c),(d))
+
+/**
+ * check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the mmio address io_addr. This
+ * address should have been obtained by ioremap.
+ * Returns 1 on a match.
+ */
+
+static inline int check_signature(unsigned long io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/**
+ * isa_check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the ISA mmio address io_addr.
+ * Returns 1 on a match.
+ *
+ * This function is deprecated. New drivers should use ioremap and
+ * check_signature.
+ */
+
+
+static inline int isa_check_signature(unsigned long io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (isa_readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/*
+ * Cache management
+ *
+ * This needed for two cases
+ * 1. Out of order aware processors
+ * 2. Accidentally out of order processors (PPro errata #51)
+ */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void flush_write_buffers(void)
+{
+ __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
+}
+
+#define dma_cache_inv(_start,_size) flush_write_buffers()
+#define dma_cache_wback(_start,_size) flush_write_buffers()
+#define dma_cache_wback_inv(_start,_size) flush_write_buffers()
+
+#else
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size) do { } while (0)
+#define dma_cache_wback(_start,_size) do { } while (0)
+#define dma_cache_wback_inv(_start,_size) do { } while (0)
+#define flush_write_buffers()
+
+#endif
+
+#endif /* __KERNEL__ */
+
+#ifdef SLOW_IO_BY_JUMPING
+#define __SLOW_DOWN_IO "\njmp 1f\n1:\tjmp 1f\n1:"
+#else
+#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
+#endif
+
+#ifdef REALLY_SLOW_IO
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
+#else
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
+#endif
+
+#ifdef CONFIG_MULTIQUAD
+extern void *xquad_portio; /* Where the IO area was mapped */
+#endif /* CONFIG_MULTIQUAD */
+
+/*
+ * Talk about misusing macros..
+ */
+#define __OUT1(s,x) \
+static inline void out##s(unsigned x value, unsigned short port) {
+
+#define __OUT2(s,s1,s2) \
+__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"
+
+#if defined (CONFIG_MULTIQUAD) && !defined(STANDALONE)
+#define __OUTQ(s,ss,x) /* Do the equivalent of the portio op on quads */ \
+static inline void out##ss(unsigned x value, unsigned short port) { \
+ if (xquad_portio) \
+ write##s(value, (unsigned long) xquad_portio + port); \
+ else /* We're still in early boot, running on quad 0 */ \
+ out##ss##_local(value, port); \
+} \
+static inline void out##ss##_quad(unsigned x value, unsigned short port, int quad) { \
+ if (xquad_portio) \
+ write##s(value, (unsigned long) xquad_portio + (XQUAD_PORTIO_QUAD*quad)\
+ + port); \
+}
+
+#define __INQ(s,ss) /* Do the equivalent of the portio op on quads */ \
+static inline RETURN_TYPE in##ss(unsigned short port) { \
+ if (xquad_portio) \
+ return read##s((unsigned long) xquad_portio + port); \
+ else /* We're still in early boot, running on quad 0 */ \
+ return in##ss##_local(port); \
+} \
+static inline RETURN_TYPE in##ss##_quad(unsigned short port, int quad) { \
+ if (xquad_portio) \
+ return read##s((unsigned long) xquad_portio + (XQUAD_PORTIO_QUAD*quad)\
+ + port); \
+ else\
+ return 0;\
+}
+#endif /* CONFIG_MULTIQUAD && !STANDALONE */
+
+#if !defined(CONFIG_MULTIQUAD) || defined(STANDALONE)
+#define __OUT(s,s1,x) \
+__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));}
+#else
+/* Make the default portio routines operate on quad 0 */
+#define __OUT(s,s1,x) \
+__OUT1(s##_local,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p_local,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \
+__OUTQ(s,s,x) \
+__OUTQ(s,s##_p,x)
+#endif /* !CONFIG_MULTIQUAD || STANDALONE */
+
+#define __IN1(s) \
+static inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;
+
+#define __IN2(s,s1,s2) \
+__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"
+
+#if !defined(CONFIG_MULTIQUAD) || defined(STANDALONE)
+#define __IN(s,s1,i...) \
+__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; }
+#else
+/* Make the default portio routines operate on quad 0 */
+#define __IN(s,s1,i...) \
+__IN1(s##_local) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p_local) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__INQ(s,s) \
+__INQ(s,s##_p)
+#endif /* !CONFIG_MULTIQUAD || STANDALONE */
+
+#define __INS(s) \
+static inline void ins##s(unsigned short port, void * addr, unsigned long count) \
+{ __asm__ __volatile__ ("rep ; ins" #s \
+: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define __OUTS(s) \
+static inline void outs##s(unsigned short port, const void * addr, unsigned long count) \
+{ __asm__ __volatile__ ("rep ; outs" #s \
+: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define RETURN_TYPE unsigned char
+__IN(b,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned short
+__IN(w,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned int
+__IN(l,"")
+#undef RETURN_TYPE
+
+__OUT(b,"b",char)
+__OUT(w,"w",short)
+__OUT(l,,int)
+
+__INS(b)
+__INS(w)
+__INS(l)
+
+__OUTS(b)
+__OUTS(w)
+__OUTS(l)
+
+#endif
--- /dev/null
+#ifndef __ASM_IO_APIC_H
+#define __ASM_IO_APIC_H
+
+#include <linux/config.h>
+#include <asm/types.h>
+
+/*
+ * Intel IO-APIC support for SMP and UP systems.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
+ */
+
+#ifdef CONFIG_X86_IO_APIC
+
+#define APIC_MISMATCH_DEBUG
+
+#define IO_APIC_BASE(idx) \
+ ((volatile int *)(__fix_to_virt(FIX_IO_APIC_BASE_0 + idx) \
+ + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK)))
+
+/*
+ * The structure of the IO-APIC:
+ */
+struct IO_APIC_reg_00 {
+ __u32 __reserved_2 : 24,
+ ID : 4,
+ __reserved_1 : 4;
+} __attribute__ ((packed));
+
+struct IO_APIC_reg_01 {
+ __u32 version : 8,
+ __reserved_2 : 7,
+ PRQ : 1,
+ entries : 8,
+ __reserved_1 : 8;
+} __attribute__ ((packed));
+
+struct IO_APIC_reg_02 {
+ __u32 __reserved_2 : 24,
+ arbitration : 4,
+ __reserved_1 : 4;
+} __attribute__ ((packed));
+
+/*
+ * # of IO-APICs and # of IRQ routing registers
+ */
+extern int nr_ioapics;
+extern int nr_ioapic_registers[MAX_IO_APICS];
+
+enum ioapic_irq_destination_types {
+ dest_Fixed = 0,
+ dest_LowestPrio = 1,
+ dest_SMI = 2,
+ dest__reserved_1 = 3,
+ dest_NMI = 4,
+ dest_INIT = 5,
+ dest__reserved_2 = 6,
+ dest_ExtINT = 7
+};
+
+struct IO_APIC_route_entry {
+ __u32 vector : 8,
+ delivery_mode : 3, /* 000: FIXED
+ * 001: lowest prio
+ * 111: ExtINT
+ */
+ dest_mode : 1, /* 0: physical, 1: logical */
+ delivery_status : 1,
+ polarity : 1,
+ irr : 1,
+ trigger : 1, /* 0: edge, 1: level */
+ mask : 1, /* 0: enabled, 1: disabled */
+ __reserved_2 : 15;
+
+ union { struct { __u32
+ __reserved_1 : 24,
+ physical_dest : 4,
+ __reserved_2 : 4;
+ } physical;
+
+ struct { __u32
+ __reserved_1 : 24,
+ logical_dest : 8;
+ } logical;
+ } dest;
+
+} __attribute__ ((packed));
+
+/*
+ * MP-BIOS irq configuration table structures:
+ */
+
+/* I/O APIC entries */
+extern struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+
+/* # of MP IRQ source entries */
+extern int mp_irq_entries;
+
+/* MP IRQ source entries */
+extern struct mpc_config_intsrc *mp_irqs;
+
+/* non-0 if default (table-less) MP configuration */
+extern int mpc_default_type;
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+ *IO_APIC_BASE(apic) = reg;
+ return *(IO_APIC_BASE(apic)+4);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+ *IO_APIC_BASE(apic) = reg;
+ *(IO_APIC_BASE(apic)+4) = value;
+}
+
+/*
+ * Re-write a value: to be used for read-modify-write
+ * cycles where the read already set up the index register.
+ */
+static inline void io_apic_modify(unsigned int apic, unsigned int value)
+{
+ *(IO_APIC_BASE(apic)+4) = value;
+}
+
+/*
+ * Synchronize the IO-APIC and the CPU by doing
+ * a dummy read from the IO-APIC
+ */
+static inline void io_apic_sync(unsigned int apic)
+{
+ (void) *(IO_APIC_BASE(apic)+4);
+}
+
+/* 1 if "noapic" boot option passed */
+extern int skip_ioapic_setup;
+
+/*
+ * If we use the IO-APIC for IRQ routing, disable automatic
+ * assignment of PCI IRQ's.
+ */
+#define io_apic_assign_pci_irqs (mp_irq_entries && !skip_ioapic_setup)
+
+#else /* !CONFIG_X86_IO_APIC */
+#define io_apic_assign_pci_irqs 0
+#endif
+
+#endif
--- /dev/null
+/* $Id: ioctl.h,v 1.5 1993/07/19 21:53:50 root Exp root $
+ *
+ * linux/ioctl.h for Linux by H.H. Bergman.
+ */
+
+#ifndef _ASMI386_IOCTL_H
+#define _ASMI386_IOCTL_H
+
+/* ioctl command encoding: 32 bits total, command in lower 16 bits,
+ * size of the parameter structure in the lower 14 bits of the
+ * upper 16 bits.
+ * Encoding the size of the parameter structure in the ioctl request
+ * is useful for catching programs compiled with old versions
+ * and to avoid overwriting user space outside the user buffer area.
+ * The highest 2 bits are reserved for indicating the ``access mode''.
+ * NOTE: This limits the max parameter size to 16kB -1 !
+ */
+
+/*
+ * The following is for compatibility across the various Linux
+ * platforms. The i386 ioctl numbering scheme doesn't really enforce
+ * a type field. De facto, however, the top 8 bits of the lower 16
+ * bits are indeed used as a type field, so we might just as well make
+ * this explicit here. Please be sure to use the decoding macros
+ * below from now on.
+ */
+#define _IOC_NRBITS 8
+#define _IOC_TYPEBITS 8
+#define _IOC_SIZEBITS 14
+#define _IOC_DIRBITS 2
+
+#define _IOC_NRMASK ((1 << _IOC_NRBITS)-1)
+#define _IOC_TYPEMASK ((1 << _IOC_TYPEBITS)-1)
+#define _IOC_SIZEMASK ((1 << _IOC_SIZEBITS)-1)
+#define _IOC_DIRMASK ((1 << _IOC_DIRBITS)-1)
+
+#define _IOC_NRSHIFT 0
+#define _IOC_TYPESHIFT (_IOC_NRSHIFT+_IOC_NRBITS)
+#define _IOC_SIZESHIFT (_IOC_TYPESHIFT+_IOC_TYPEBITS)
+#define _IOC_DIRSHIFT (_IOC_SIZESHIFT+_IOC_SIZEBITS)
+
+/*
+ * Direction bits.
+ */
+#define _IOC_NONE 0U
+#define _IOC_WRITE 1U
+#define _IOC_READ 2U
+
+#define _IOC(dir,type,nr,size) \
+ (((dir) << _IOC_DIRSHIFT) | \
+ ((type) << _IOC_TYPESHIFT) | \
+ ((nr) << _IOC_NRSHIFT) | \
+ ((size) << _IOC_SIZESHIFT))
+
+/* used to create numbers */
+#define _IO(type,nr) _IOC(_IOC_NONE,(type),(nr),0)
+#define _IOR(type,nr,size) _IOC(_IOC_READ,(type),(nr),sizeof(size))
+#define _IOW(type,nr,size) _IOC(_IOC_WRITE,(type),(nr),sizeof(size))
+#define _IOWR(type,nr,size) _IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
+
+/* used to decode ioctl numbers.. */
+#define _IOC_DIR(nr) (((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
+#define _IOC_TYPE(nr) (((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
+#define _IOC_NR(nr) (((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
+#define _IOC_SIZE(nr) (((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
+
+/* ...and for the drivers/sound files... */
+
+#define IOC_IN (_IOC_WRITE << _IOC_DIRSHIFT)
+#define IOC_OUT (_IOC_READ << _IOC_DIRSHIFT)
+#define IOC_INOUT ((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
+#define IOCSIZE_MASK (_IOC_SIZEMASK << _IOC_SIZESHIFT)
+#define IOCSIZE_SHIFT (_IOC_SIZESHIFT)
+
+#endif /* _ASMI386_IOCTL_H */
--- /dev/null
+#ifndef __ARCH_I386_IOCTLS_H__
+#define __ARCH_I386_IOCTLS_H__
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS 0x5401
+#define TCSETS 0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
+#define TCSETSW 0x5403
+#define TCSETSF 0x5404
+#define TCGETA 0x5405
+#define TCSETA 0x5406
+#define TCSETAW 0x5407
+#define TCSETAF 0x5408
+#define TCSBRK 0x5409
+#define TCXONC 0x540A
+#define TCFLSH 0x540B
+#define TIOCEXCL 0x540C
+#define TIOCNXCL 0x540D
+#define TIOCSCTTY 0x540E
+#define TIOCGPGRP 0x540F
+#define TIOCSPGRP 0x5410
+#define TIOCOUTQ 0x5411
+#define TIOCSTI 0x5412
+#define TIOCGWINSZ 0x5413
+#define TIOCSWINSZ 0x5414
+#define TIOCMGET 0x5415
+#define TIOCMBIS 0x5416
+#define TIOCMBIC 0x5417
+#define TIOCMSET 0x5418
+#define TIOCGSOFTCAR 0x5419
+#define TIOCSSOFTCAR 0x541A
+#define FIONREAD 0x541B
+#define TIOCINQ FIONREAD
+#define TIOCLINUX 0x541C
+#define TIOCCONS 0x541D
+#define TIOCGSERIAL 0x541E
+#define TIOCSSERIAL 0x541F
+#define TIOCPKT 0x5420
+#define FIONBIO 0x5421
+#define TIOCNOTTY 0x5422
+#define TIOCSETD 0x5423
+#define TIOCGETD 0x5424
+#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */
+#define TIOCTTYGSTRUCT 0x5426 /* For debugging only */
+#define TIOCSBRK 0x5427 /* BSD compatibility */
+#define TIOCCBRK 0x5428 /* BSD compatibility */
+#define TIOCGSID 0x5429 /* Return the session ID of FD */
+#define TIOCGPTN _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK _IOW('T',0x31, int) /* Lock/unlock Pty */
+
+#define FIONCLEX 0x5450 /* these numbers need to be adjusted. */
+#define FIOCLEX 0x5451
+#define FIOASYNC 0x5452
+#define TIOCSERCONFIG 0x5453
+#define TIOCSERGWILD 0x5454
+#define TIOCSERSWILD 0x5455
+#define TIOCGLCKTRMIOS 0x5456
+#define TIOCSLCKTRMIOS 0x5457
+#define TIOCSERGSTRUCT 0x5458 /* For debugging only */
+#define TIOCSERGETLSR 0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */
+#define TIOCGHAYESESP 0x545E /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP 0x545F /* Set Hayes ESP configuration */
+
+/* Used for packet mode */
+#define TIOCPKT_DATA 0
+#define TIOCPKT_FLUSHREAD 1
+#define TIOCPKT_FLUSHWRITE 2
+#define TIOCPKT_STOP 4
+#define TIOCPKT_START 8
+#define TIOCPKT_NOSTOP 16
+#define TIOCPKT_DOSTOP 32
+
+#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */
+
+#endif
--- /dev/null
+#ifndef __i386_IPC_H__
+#define __i386_IPC_H__
+
+/*
+ * These are used to wrap system calls on x86.
+ *
+ * See arch/i386/kernel/sys_i386.c for ugly details..
+ */
+struct ipc_kludge {
+ struct msgbuf *msgp;
+ long msgtyp;
+};
+
+#define SEMOP 1
+#define SEMGET 2
+#define SEMCTL 3
+#define MSGSND 11
+#define MSGRCV 12
+#define MSGGET 13
+#define MSGCTL 14
+#define SHMAT 21
+#define SHMDT 22
+#define SHMGET 23
+#define SHMCTL 24
+
+/* Used by the DIPC package, try and avoid reusing it */
+#define DIPC 25
+
+#define IPCCALL(version,op) ((version)<<16 | (op))
+
+#endif
--- /dev/null
+#ifndef __i386_IPCBUF_H__
+#define __i386_IPCBUF_H__
+
+/*
+ * The ipc64_perm structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 32-bit mode_t and seq
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct ipc64_perm
+{
+ __kernel_key_t key;
+ __kernel_uid32_t uid;
+ __kernel_gid32_t gid;
+ __kernel_uid32_t cuid;
+ __kernel_gid32_t cgid;
+ __kernel_mode_t mode;
+ unsigned short __pad1;
+ unsigned short seq;
+ unsigned short __pad2;
+ unsigned long __unused1;
+ unsigned long __unused2;
+};
+
+#endif /* __i386_IPCBUF_H__ */
--- /dev/null
+#ifndef _ASM_IRQ_H
+#define _ASM_IRQ_H
+
+/*
+ * linux/include/asm/irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ */
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+#include <asm/ptrace.h>
+
+#define NET_TX_IRQ _EVENT_NET_TX
+#define NET_RX_IRQ _EVENT_NET_RX
+#define NET2_TX_IRQ _EVENT_NET2_TX
+#define NET2_RX_IRQ _EVENT_NET2_RX
+#define TIMER_IRQ _EVENT_TIMER
+
+#define NR_IRQS (sizeof(HYPERVISOR_shared_info->events) * 8)
+
+#define irq_cannonicalize(_irq) (_irq)
+
+extern void disable_irq(unsigned int);
+extern void disable_irq_nosync(unsigned int);
+extern void enable_irq(unsigned int);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#define ARCH_HAS_NMI_WATCHDOG /* See include/linux/nmi.h */
+#endif
+
+#endif /* _ASM_IRQ_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/keyboard.h
+ *
+ * Created 3 Nov 1996 by Geert Uytterhoeven
+ */
+
+/*
+ * This file contains the i386 architecture specific keyboard definitions
+ */
+
+#ifndef _I386_KEYBOARD_H
+#define _I386_KEYBOARD_H
+
+#ifdef __KERNEL__
+
+#include <linux/kernel.h>
+#include <linux/ioport.h>
+#include <linux/kd.h>
+#include <linux/pm.h>
+#include <asm/io.h>
+
+#define KEYBOARD_IRQ 1
+#define DISABLE_KBD_DURING_INTERRUPTS 0
+
+extern int pckbd_setkeycode(unsigned int scancode, unsigned int keycode);
+extern int pckbd_getkeycode(unsigned int scancode);
+extern int pckbd_translate(unsigned char scancode, unsigned char *keycode,
+ char raw_mode);
+extern char pckbd_unexpected_up(unsigned char keycode);
+extern void pckbd_leds(unsigned char leds);
+extern void pckbd_init_hw(void);
+extern int pckbd_pm_resume(struct pm_dev *, pm_request_t, void *);
+extern pm_callback pm_kbd_request_override;
+extern unsigned char pckbd_sysrq_xlate[128];
+
+#define kbd_setkeycode pckbd_setkeycode
+#define kbd_getkeycode pckbd_getkeycode
+#define kbd_translate pckbd_translate
+#define kbd_unexpected_up pckbd_unexpected_up
+#define kbd_leds pckbd_leds
+#define kbd_init_hw pckbd_init_hw
+#define kbd_sysrq_xlate pckbd_sysrq_xlate
+
+#define SYSRQ_KEY 0x54
+
+/* resource allocation */
+#define kbd_request_region()
+#define kbd_request_irq(handler) request_irq(KEYBOARD_IRQ, handler, 0, \
+ "keyboard", NULL)
+
+/* How to access the keyboard macros on this platform. */
+#define kbd_read_input() inb(KBD_DATA_REG)
+#define kbd_read_status() inb(KBD_STATUS_REG)
+#define kbd_write_output(val) outb(val, KBD_DATA_REG)
+#define kbd_write_command(val) outb(val, KBD_CNTL_REG)
+
+/* Some stoneage hardware needs delays after some operations. */
+#define kbd_pause() do { } while(0)
+
+/*
+ * Machine specific bits for the PS/2 driver
+ */
+
+#define AUX_IRQ 12
+
+#define aux_request_irq(hand, dev_id) \
+ request_irq(AUX_IRQ, hand, SA_SHIRQ, "PS/2 Mouse", dev_id)
+
+#define aux_free_irq(dev_id) free_irq(AUX_IRQ, dev_id)
+
+#endif /* __KERNEL__ */
+#endif /* _I386_KEYBOARD_H */
--- /dev/null
+#ifndef _ASM_KMAP_TYPES_H
+#define _ASM_KMAP_TYPES_H
+
+enum km_type {
+ KM_BOUNCE_READ,
+ KM_SKB_SUNRPC_DATA,
+ KM_SKB_DATA_SOFTIRQ,
+ KM_USER0,
+ KM_USER1,
+ KM_BH_IRQ,
+ KM_TYPE_NR
+};
+
+#endif
--- /dev/null
+/*
+ * ldt.h
+ *
+ * Definitions of structures used with the modify_ldt system call.
+ */
+#ifndef _LINUX_LDT_H
+#define _LINUX_LDT_H
+
+/* Maximum number of LDT entries supported. */
+#define LDT_ENTRIES 8192
+/* The size of each LDT entry. */
+#define LDT_ENTRY_SIZE 8
+
+#ifndef __ASSEMBLY__
+struct modify_ldt_ldt_s {
+ unsigned int entry_number;
+ unsigned long base_addr;
+ unsigned int limit;
+ unsigned int seg_32bit:1;
+ unsigned int contents:2;
+ unsigned int read_exec_only:1;
+ unsigned int limit_in_pages:1;
+ unsigned int seg_not_present:1;
+ unsigned int useable:1;
+};
+
+#define MODIFY_LDT_CONTENTS_DATA 0
+#define MODIFY_LDT_CONTENTS_STACK 1
+#define MODIFY_LDT_CONTENTS_CODE 2
+
+#endif /* !__ASSEMBLY__ */
+#endif
--- /dev/null
+/* $Id: linux_logo.h,v 1.8 1998/07/30 16:30:24 jj Exp $
+ * include/asm-i386/linux_logo.h: This is a linux logo
+ * to be displayed on boot.
+ *
+ * Copyright (C) 1996 Larry Ewing (lewing@isc.tamu.edu)
+ * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ *
+ * You can put anything here, but:
+ * LINUX_LOGO_COLORS has to be less than 224
+ * image size has to be 80x80
+ * values have to start from 0x20
+ * (i.e. RGB(linux_logo_red[0],
+ * linux_logo_green[0],
+ * linux_logo_blue[0]) is color 0x20)
+ * BW image has to be 80x80 as well, with MS bit
+ * on the left
+ * Serial_console ascii image can be any size,
+ * but should contain %s to display the version
+ */
+
+#include <linux/init.h>
+#include <linux/version.h>
+
+#define linux_logo_banner "Linux/ia32 version " UTS_RELEASE
+
+#include <linux/linux_logo.h>
+
--- /dev/null
+/*
+ * SMP locks primitives for building ix86 locks
+ * (not yet used).
+ *
+ * Alan Cox, alan@redhat.com, 1995
+ */
+
+/*
+ * This would be much easier but far less clear and easy
+ * to borrow for other processors if it was just assembler.
+ */
+
+static __inline__ void prim_spin_lock(struct spinlock *sp)
+{
+ int processor=smp_processor_id();
+
+ /*
+ * Grab the lock bit
+ */
+
+ while(lock_set_bit(0,&sp->lock))
+ {
+ /*
+ * Failed, but that's cos we own it!
+ */
+
+ if(sp->cpu==processor)
+ {
+ sp->users++;
+ return 0;
+ }
+ /*
+ * Spin in the cache S state if possible
+ */
+ while(sp->lock)
+ {
+ /*
+ * Wait for any invalidates to go off
+ */
+
+ if(smp_invalidate_needed&(1<<processor))
+ while(lock_clear_bit(processor,&smp_invalidate_needed))
+ local_flush_tlb();
+ sp->spins++;
+ }
+ /*
+ * Someone wrote the line, we go 'I' and get
+ * the cache entry. Now try to regrab
+ */
+ }
+ sp->users++;sp->cpu=processor;
+ return 1;
+}
+
+/*
+ * Release a spin lock
+ */
+
+static __inline__ int prim_spin_unlock(struct spinlock *sp)
+{
+ /* This is safe. The decrement is still guarded by the lock. A multilock would
+ not be safe this way */
+ if(!--sp->users)
+ {
+ sp->cpu= NO_PROC_ID;lock_clear_bit(0,&sp->lock);
+ return 1;
+ }
+ return 0;
+}
+
+
+/*
+ * Non blocking lock grab
+ */
+
+static __inline__ int prim_spin_lock_nb(struct spinlock *sp)
+{
+ if(lock_set_bit(0,&sp->lock))
+ return 0; /* Locked already */
+ sp->users++;
+ return 1; /* We got the lock */
+}
+
+
+/*
+ * These wrap the locking primitives up for usage
+ */
+
+static __inline__ void spinlock(struct spinlock *sp)
+{
+ if(sp->priority<current->lock_order)
+ panic("lock order violation: %s (%d)\n", sp->name, current->lock_order);
+ if(prim_spin_lock(sp))
+ {
+ /*
+ * We got a new lock. Update the priority chain
+ */
+ sp->oldpri=current->lock_order;
+ current->lock_order=sp->priority;
+ }
+}
+
+static __inline__ void spinunlock(struct spinlock *sp)
+{
+ int pri;
+ if(current->lock_order!=sp->priority)
+ panic("lock release order violation %s (%d)\n", sp->name, current->lock_order);
+ pri=sp->oldpri;
+ if(prim_spin_unlock(sp))
+ {
+ /*
+ * Update the debugging lock priority chain. We dumped
+ * our last right to the lock.
+ */
+ current->lock_order=sp->pri;
+ }
+}
+
+static __inline__ void spintestlock(struct spinlock *sp)
+{
+ /*
+ * We do no sanity checks, it's legal to optimistically
+ * get a lower lock.
+ */
+ prim_spin_lock_nb(sp);
+}
+
+static __inline__ void spintestunlock(struct spinlock *sp)
+{
+ /*
+ * A testlock doesn't update the lock chain so we
+ * must not update it on free
+ */
+ prim_spin_unlock(sp);
+}
--- /dev/null
+#ifndef _I386_MATH_EMU_H
+#define _I386_MATH_EMU_H
+
+#include <asm/sigcontext.h>
+
+int restore_i387_soft(void *s387, struct _fpstate *buf);
+int save_i387_soft(void *s387, struct _fpstate * buf);
+
+/* This structure matches the layout of the data saved to the stack
+ following a device-not-present interrupt, part of it saved
+ automatically by the 80386/80486.
+ */
+struct info {
+ long ___orig_eip;
+ long ___ebx;
+ long ___ecx;
+ long ___edx;
+ long ___esi;
+ long ___edi;
+ long ___ebp;
+ long ___eax;
+ long ___ds;
+ long ___es;
+ long ___orig_eax;
+ long ___eip;
+ long ___cs;
+ long ___eflags;
+ long ___esp;
+ long ___ss;
+ long ___vm86_es; /* This and the following only in vm86 mode */
+ long ___vm86_ds;
+ long ___vm86_fs;
+ long ___vm86_gs;
+};
+#endif
--- /dev/null
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+#include <asm/io.h>
+
+#ifndef RTC_PORT
+#define RTC_PORT(x) (0x70 + (x))
+#define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */
+#endif
+
+/*
+ * The yet supported machines all access the RTC index register via
+ * an ISA port access but the way to access the date register differs ...
+ */
+#define CMOS_READ(addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+inb_p(RTC_PORT(1)); \
+})
+#define CMOS_WRITE(val, addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+outb_p((val),RTC_PORT(1)); \
+})
+
+#define RTC_IRQ 8
+
+#endif /* _ASM_MC146818RTC_H */
--- /dev/null
+#ifndef MCA_DMA_H
+#define MCA_DMA_H
+
+#include <asm/io.h>
+#include <linux/ioport.h>
+
+/*
+ * Microchannel specific DMA stuff. DMA on an MCA machine is fairly similar to
+ * standard PC dma, but it certainly has its quirks. DMA register addresses
+ * are in a different place and there are some added functions. Most of this
+ * should be pretty obvious on inspection. Note that the user must divide
+ * count by 2 when using 16-bit dma; that is not handled by these functions.
+ *
+ * Ramen Noodles are yummy.
+ *
+ * 1998 Tymm Twillman <tymm@computer.org>
+ */
+
+/*
+ * Registers that are used by the DMA controller; FN is the function register
+ * (tell the controller what to do) and EXE is the execution register (how
+ * to do it)
+ */
+
+#define MCA_DMA_REG_FN 0x18
+#define MCA_DMA_REG_EXE 0x1A
+
+/*
+ * Functions that the DMA controller can do
+ */
+
+#define MCA_DMA_FN_SET_IO 0x00
+#define MCA_DMA_FN_SET_ADDR 0x20
+#define MCA_DMA_FN_GET_ADDR 0x30
+#define MCA_DMA_FN_SET_COUNT 0x40
+#define MCA_DMA_FN_GET_COUNT 0x50
+#define MCA_DMA_FN_GET_STATUS 0x60
+#define MCA_DMA_FN_SET_MODE 0x70
+#define MCA_DMA_FN_SET_ARBUS 0x80
+#define MCA_DMA_FN_MASK 0x90
+#define MCA_DMA_FN_RESET_MASK 0xA0
+#define MCA_DMA_FN_MASTER_CLEAR 0xD0
+
+/*
+ * Modes (used by setting MCA_DMA_FN_MODE in the function register)
+ *
+ * Note that the MODE_READ is read from memory (write to device), and
+ * MODE_WRITE is vice-versa.
+ */
+
+#define MCA_DMA_MODE_XFER 0x04 /* read by default */
+#define MCA_DMA_MODE_READ 0x04 /* same as XFER */
+#define MCA_DMA_MODE_WRITE 0x08 /* OR with MODE_XFER to use */
+#define MCA_DMA_MODE_IO 0x01 /* DMA from IO register */
+#define MCA_DMA_MODE_16 0x40 /* 16 bit xfers */
+
+
+/**
+ * mca_enable_dma - channel to enable DMA on
+ * @dmanr: DMA channel
+ *
+ * Enable the MCA bus DMA on a channel. This can be called from
+ * IRQ context.
+ */
+
+static __inline__ void mca_enable_dma(unsigned int dmanr)
+{
+ outb(MCA_DMA_FN_RESET_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ * mca_disble_dma - channel to disable DMA on
+ * @dmanr: DMA channel
+ *
+ * Enable the MCA bus DMA on a channel. This can be called from
+ * IRQ context.
+ */
+
+static __inline__ void mca_disable_dma(unsigned int dmanr)
+{
+ outb(MCA_DMA_FN_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ * mca_set_dma_addr - load a 24bit DMA address
+ * @dmanr: DMA channel
+ * @a: 24bit bus address
+ *
+ * Load the address register in the DMA controller. This has a 24bit
+ * limitation (16Mb).
+ */
+
+static __inline__ void mca_set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+ outb(MCA_DMA_FN_SET_ADDR | dmanr, MCA_DMA_REG_FN);
+ outb(a & 0xff, MCA_DMA_REG_EXE);
+ outb((a >> 8) & 0xff, MCA_DMA_REG_EXE);
+ outb((a >> 16) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ * mca_get_dma_addr - load a 24bit DMA address
+ * @dmanr: DMA channel
+ *
+ * Read the address register in the DMA controller. This has a 24bit
+ * limitation (16Mb). The return is a bus address.
+ */
+
+static __inline__ unsigned int mca_get_dma_addr(unsigned int dmanr)
+{
+ unsigned int addr;
+
+ outb(MCA_DMA_FN_GET_ADDR | dmanr, MCA_DMA_REG_FN);
+ addr = inb(MCA_DMA_REG_EXE);
+ addr |= inb(MCA_DMA_REG_EXE) << 8;
+ addr |= inb(MCA_DMA_REG_EXE) << 16;
+
+ return addr;
+}
+
+/**
+ * mca_set_dma_count - load a 16bit transfer count
+ * @dmanr: DMA channel
+ * @count: count
+ *
+ * Set the DMA count for this channel. This can be up to 64Kbytes.
+ * Setting a count of zero will not do what you expect.
+ */
+
+static __inline__ void mca_set_dma_count(unsigned int dmanr, unsigned int count)
+{
+ count--; /* transfers one more than count -- correct for this */
+
+ outb(MCA_DMA_FN_SET_COUNT | dmanr, MCA_DMA_REG_FN);
+ outb(count & 0xff, MCA_DMA_REG_EXE);
+ outb((count >> 8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ * mca_get_dma_residue - get the remaining bytes to transfer
+ * @dmanr: DMA channel
+ *
+ * This function returns the number of bytes left to transfer
+ * on this DMA channel.
+ */
+
+static __inline__ unsigned int mca_get_dma_residue(unsigned int dmanr)
+{
+ unsigned short count;
+
+ outb(MCA_DMA_FN_GET_COUNT | dmanr, MCA_DMA_REG_FN);
+ count = 1 + inb(MCA_DMA_REG_EXE);
+ count += inb(MCA_DMA_REG_EXE) << 8;
+
+ return count;
+}
+
+/**
+ * mca_set_dma_io - set the port for an I/O transfer
+ * @dmanr: DMA channel
+ * @io_addr: an I/O port number
+ *
+ * Unlike the ISA bus DMA controllers the DMA on MCA bus can transfer
+ * with an I/O port target.
+ */
+
+static __inline__ void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
+{
+ /*
+ * DMA from a port address -- set the io address
+ */
+
+ outb(MCA_DMA_FN_SET_IO | dmanr, MCA_DMA_REG_FN);
+ outb(io_addr & 0xff, MCA_DMA_REG_EXE);
+ outb((io_addr >> 8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ * mca_set_dma_mode - set the DMA mode
+ * @dmanr: DMA channel
+ * @mode: mode to set
+ *
+ * The DMA controller supports several modes. The mode values you can
+ * set are :
+ *
+ * %MCA_DMA_MODE_READ when reading from the DMA device.
+ *
+ * %MCA_DMA_MODE_WRITE to writing to the DMA device.
+ *
+ * %MCA_DMA_MODE_IO to do DMA to or from an I/O port.
+ *
+ * %MCA_DMA_MODE_16 to do 16bit transfers.
+ *
+ */
+
+static __inline__ void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
+{
+ outb(MCA_DMA_FN_SET_MODE | dmanr, MCA_DMA_REG_FN);
+ outb(mode, MCA_DMA_REG_EXE);
+}
+
+#endif /* MCA_DMA_H */
--- /dev/null
+#ifndef __I386_MMAN_H__
+#define __I386_MMAN_H__
+
+#define PROT_READ 0x1 /* page can be read */
+#define PROT_WRITE 0x2 /* page can be written */
+#define PROT_EXEC 0x4 /* page can be executed */
+#define PROT_NONE 0x0 /* page can not be accessed */
+
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_TYPE 0x0f /* Mask for type of mapping */
+#define MAP_FIXED 0x10 /* Interpret addr exactly */
+#define MAP_ANONYMOUS 0x20 /* don't use a file */
+
+#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
+#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
+#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
+#define MAP_LOCKED 0x2000 /* pages are locked */
+#define MAP_NORESERVE 0x4000 /* don't check for reservations */
+
+#define MS_ASYNC 1 /* sync memory asynchronously */
+#define MS_INVALIDATE 2 /* invalidate the caches */
+#define MS_SYNC 4 /* synchronous memory sync */
+
+#define MCL_CURRENT 1 /* lock all current mappings */
+#define MCL_FUTURE 2 /* lock all future mappings */
+
+#define MADV_NORMAL 0x0 /* default page-in behavior */
+#define MADV_RANDOM 0x1 /* page-in minimum required */
+#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
+#define MADV_WILLNEED 0x3 /* pre-fault pages */
+#define MADV_DONTNEED 0x4 /* discard these pages */
+
+/* compatibility flags */
+#define MAP_ANON MAP_ANONYMOUS
+#define MAP_FILE 0
+
+#endif /* __I386_MMAN_H__ */
--- /dev/null
+#ifndef __i386_MMU_H
+#define __i386_MMU_H
+
+#include <linux/list.h>
+
+/* describes dirrectly mapped vma nodes */
+typedef struct {
+ struct list_head list;
+ unsigned long vm_start;
+ unsigned long vm_end;
+} direct_mmap_node_t;
+
+/*
+ * The i386 doesn't have a mmu context, but
+ * we put the segment information here.
+ */
+typedef struct {
+ void *segments;
+ unsigned long cpuvalid;
+ struct list_head direct_list;
+} mm_context_t;
+
+#endif
--- /dev/null
+#ifndef __I386_MMU_CONTEXT_H
+#define __I386_MMU_CONTEXT_H
+
+#include <linux/config.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+
+/*
+ * possibly do the LDT unload here?
+ */
+
+extern int init_new_context(struct task_struct *tsk, struct mm_struct *);
+extern void destroy_context(struct mm_struct *);
+
+//#define destroy_context(mm) do { } while(0)
+//#define init_new_context(tsk,mm) 0
+
+#ifdef CONFIG_SMP
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk, unsigned cpu)
+{
+ if(cpu_tlbstate[cpu].state == TLBSTATE_OK)
+ cpu_tlbstate[cpu].state = TLBSTATE_LAZY;
+}
+#else
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk, unsigned cpu)
+{
+}
+#endif
+
+extern pgd_t *cur_pgd;
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk, unsigned cpu)
+{
+ if (prev != next) {
+ /* stop flush ipis for the previous mm */
+ clear_bit(cpu, &prev->cpu_vm_mask);
+ /*
+ * Re-load LDT if necessary
+ */
+ if (prev->context.segments != next->context.segments)
+ load_LDT(next);
+#ifdef CONFIG_SMP
+ cpu_tlbstate[cpu].state = TLBSTATE_OK;
+ cpu_tlbstate[cpu].active_mm = next;
+#endif
+ set_bit(cpu, &next->cpu_vm_mask);
+ set_bit(cpu, &next->context.cpuvalid);
+ /* Re-load page tables */
+ cur_pgd = next->pgd;
+ queue_pt_switch(__pa(cur_pgd));
+ XENO_flush_page_update_queue();
+ }
+#ifdef CONFIG_SMP
+ else {
+ cpu_tlbstate[cpu].state = TLBSTATE_OK;
+ if(cpu_tlbstate[cpu].active_mm != next)
+ out_of_line_bug();
+ if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) {
+ /* We were in lazy tlb mode and leave_mm disabled
+ * tlb flush IPI delivery. We must reload %cr3.
+ */
+ load_cr3(next->pgd);
+ }
+ if (!test_and_set_bit(cpu, &next->context.cpuvalid))
+ load_LDT(next);
+ }
+#endif
+}
+
+#define activate_mm(prev, next) \
+ switch_mm((prev),(next),NULL,smp_processor_id())
+
+#endif
--- /dev/null
+#ifndef _ASM_MMX_H
+#define _ASM_MMX_H
+
+/*
+ * MMX 3Dnow! helper operations
+ */
+
+#include <linux/types.h>
+
+extern void *_mmx_memcpy(void *to, const void *from, size_t size);
+extern void mmx_clear_page(void *page);
+extern void mmx_copy_page(void *to, void *from);
+
+#endif
--- /dev/null
+#ifndef _ASM_I386_MODULE_H
+#define _ASM_I386_MODULE_H
+/*
+ * This file contains the i386 architecture specific module code.
+ */
+
+#define module_map(x) vmalloc(x)
+#define module_unmap(x) vfree(x)
+#define module_arch_init(x) (0)
+#define arch_init_modules(x) do { } while (0)
+
+#endif /* _ASM_I386_MODULE_H */
--- /dev/null
+#ifndef __ASM_MPSPEC_H
+#define __ASM_MPSPEC_H
+
+/*
+ * Structure definitions for SMP machines following the
+ * Intel Multiprocessing Specification 1.1 and 1.4.
+ */
+
+/*
+ * This tag identifies where the SMP configuration
+ * information is.
+ */
+
+#define SMP_MAGIC_IDENT (('_'<<24)|('P'<<16)|('M'<<8)|'_')
+
+/*
+ * a maximum of 16 APICs with the current APIC ID architecture.
+ * xAPICs can have up to 256. SAPICs have 16 ID bits.
+ */
+#ifdef CONFIG_X86_CLUSTERED_APIC
+#define MAX_APICS 256
+#else
+#define MAX_APICS 16
+#endif
+
+#define MAX_MPC_ENTRY 1024
+
+struct intel_mp_floating
+{
+ char mpf_signature[4]; /* "_MP_" */
+ unsigned long mpf_physptr; /* Configuration table address */
+ unsigned char mpf_length; /* Our length (paragraphs) */
+ unsigned char mpf_specification;/* Specification version */
+ unsigned char mpf_checksum; /* Checksum (makes sum 0) */
+ unsigned char mpf_feature1; /* Standard or configuration ? */
+ unsigned char mpf_feature2; /* Bit7 set for IMCR|PIC */
+ unsigned char mpf_feature3; /* Unused (0) */
+ unsigned char mpf_feature4; /* Unused (0) */
+ unsigned char mpf_feature5; /* Unused (0) */
+};
+
+struct mp_config_table
+{
+ char mpc_signature[4];
+#define MPC_SIGNATURE "PCMP"
+ unsigned short mpc_length; /* Size of table */
+ char mpc_spec; /* 0x01 */
+ char mpc_checksum;
+ char mpc_oem[8];
+ char mpc_productid[12];
+ unsigned long mpc_oemptr; /* 0 if not present */
+ unsigned short mpc_oemsize; /* 0 if not present */
+ unsigned short mpc_oemcount;
+ unsigned long mpc_lapic; /* APIC address */
+ unsigned long reserved;
+};
+
+/* Followed by entries */
+
+#define MP_PROCESSOR 0
+#define MP_BUS 1
+#define MP_IOAPIC 2
+#define MP_INTSRC 3
+#define MP_LINTSRC 4
+#define MP_TRANSLATION 192 /* Used by IBM NUMA-Q to describe node locality */
+
+struct mpc_config_processor
+{
+ unsigned char mpc_type;
+ unsigned char mpc_apicid; /* Local APIC number */
+ unsigned char mpc_apicver; /* Its versions */
+ unsigned char mpc_cpuflag;
+#define CPU_ENABLED 1 /* Processor is available */
+#define CPU_BOOTPROCESSOR 2 /* Processor is the BP */
+ unsigned long mpc_cpufeature;
+#define CPU_STEPPING_MASK 0x0F
+#define CPU_MODEL_MASK 0xF0
+#define CPU_FAMILY_MASK 0xF00
+ unsigned long mpc_featureflag; /* CPUID feature value */
+ unsigned long mpc_reserved[2];
+};
+
+struct mpc_config_bus
+{
+ unsigned char mpc_type;
+ unsigned char mpc_busid;
+ unsigned char mpc_bustype[6] __attribute((packed));
+};
+
+/* List of Bus Type string values, Intel MP Spec. */
+#define BUSTYPE_EISA "EISA"
+#define BUSTYPE_ISA "ISA"
+#define BUSTYPE_INTERN "INTERN" /* Internal BUS */
+#define BUSTYPE_MCA "MCA"
+#define BUSTYPE_VL "VL" /* Local bus */
+#define BUSTYPE_PCI "PCI"
+#define BUSTYPE_PCMCIA "PCMCIA"
+#define BUSTYPE_CBUS "CBUS"
+#define BUSTYPE_CBUSII "CBUSII"
+#define BUSTYPE_FUTURE "FUTURE"
+#define BUSTYPE_MBI "MBI"
+#define BUSTYPE_MBII "MBII"
+#define BUSTYPE_MPI "MPI"
+#define BUSTYPE_MPSA "MPSA"
+#define BUSTYPE_NUBUS "NUBUS"
+#define BUSTYPE_TC "TC"
+#define BUSTYPE_VME "VME"
+#define BUSTYPE_XPRESS "XPRESS"
+
+struct mpc_config_ioapic
+{
+ unsigned char mpc_type;
+ unsigned char mpc_apicid;
+ unsigned char mpc_apicver;
+ unsigned char mpc_flags;
+#define MPC_APIC_USABLE 0x01
+ unsigned long mpc_apicaddr;
+};
+
+struct mpc_config_intsrc
+{
+ unsigned char mpc_type;
+ unsigned char mpc_irqtype;
+ unsigned short mpc_irqflag;
+ unsigned char mpc_srcbus;
+ unsigned char mpc_srcbusirq;
+ unsigned char mpc_dstapic;
+ unsigned char mpc_dstirq;
+};
+
+enum mp_irq_source_types {
+ mp_INT = 0,
+ mp_NMI = 1,
+ mp_SMI = 2,
+ mp_ExtINT = 3
+};
+
+#define MP_IRQDIR_DEFAULT 0
+#define MP_IRQDIR_HIGH 1
+#define MP_IRQDIR_LOW 3
+
+
+struct mpc_config_lintsrc
+{
+ unsigned char mpc_type;
+ unsigned char mpc_irqtype;
+ unsigned short mpc_irqflag;
+ unsigned char mpc_srcbusid;
+ unsigned char mpc_srcbusirq;
+ unsigned char mpc_destapic;
+#define MP_APIC_ALL 0xFF
+ unsigned char mpc_destapiclint;
+};
+
+struct mp_config_oemtable
+{
+ char oem_signature[4];
+#define MPC_OEM_SIGNATURE "_OEM"
+ unsigned short oem_length; /* Size of table */
+ char oem_rev; /* 0x01 */
+ char oem_checksum;
+ char mpc_oem[8];
+};
+
+struct mpc_config_translation
+{
+ unsigned char mpc_type;
+ unsigned char trans_len;
+ unsigned char trans_type;
+ unsigned char trans_quad;
+ unsigned char trans_global;
+ unsigned char trans_local;
+ unsigned short trans_reserved;
+};
+
+/*
+ * Default configurations
+ *
+ * 1 2 CPU ISA 82489DX
+ * 2 2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
+ * 3 2 CPU EISA 82489DX
+ * 4 2 CPU MCA 82489DX
+ * 5 2 CPU ISA+PCI
+ * 6 2 CPU EISA+PCI
+ * 7 2 CPU MCA+PCI
+ */
+
+#ifdef CONFIG_MULTIQUAD
+#define MAX_IRQ_SOURCES 512
+#else /* !CONFIG_MULTIQUAD */
+#define MAX_IRQ_SOURCES 256
+#endif /* CONFIG_MULTIQUAD */
+
+#define MAX_MP_BUSSES 32
+enum mp_bustype {
+ MP_BUS_ISA = 1,
+ MP_BUS_EISA,
+ MP_BUS_PCI,
+ MP_BUS_MCA
+};
+extern int *mp_bus_id_to_type;
+extern int *mp_bus_id_to_node;
+extern int *mp_bus_id_to_local;
+extern int *mp_bus_id_to_pci_bus;
+extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+
+extern unsigned int boot_cpu_physical_apicid;
+extern unsigned long phys_cpu_present_map;
+extern int smp_found_config;
+extern void find_smp_config (void);
+extern void get_smp_config (void);
+extern int nr_ioapics;
+extern int apic_version [MAX_APICS];
+extern int mp_irq_entries;
+extern struct mpc_config_intsrc *mp_irqs;
+extern int mpc_default_type;
+extern int mp_current_pci_id;
+extern unsigned long mp_lapic_addr;
+extern int pic_mode;
+extern int using_apic_timer;
+
+#endif
+
--- /dev/null
+#ifndef _I386_MSGBUF_H
+#define _I386_MSGBUF_H
+
+/*
+ * The msqid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct msqid64_ds {
+ struct ipc64_perm msg_perm;
+ __kernel_time_t msg_stime; /* last msgsnd time */
+ unsigned long __unused1;
+ __kernel_time_t msg_rtime; /* last msgrcv time */
+ unsigned long __unused2;
+ __kernel_time_t msg_ctime; /* last change time */
+ unsigned long __unused3;
+ unsigned long msg_cbytes; /* current number of bytes on queue */
+ unsigned long msg_qnum; /* number of messages in queue */
+ unsigned long msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+
+#endif /* _I386_MSGBUF_H */
--- /dev/null
+#ifndef __ASM_MSR_H
+#define __ASM_MSR_H
+
+/*
+ * Access to machine-specific registers (available on 586 and better only)
+ * Note: the rd* operations modify the parameters directly (without using
+ * pointer indirection), this allows gcc to optimize better
+ */
+
+#define rdmsr(msr,val1,val2) \
+ __asm__ __volatile__("rdmsr" \
+ : "=a" (val1), "=d" (val2) \
+ : "c" (msr))
+
+#define wrmsr(msr,val1,val2) \
+ __asm__ __volatile__("wrmsr" \
+ : /* no outputs */ \
+ : "c" (msr), "a" (val1), "d" (val2))
+
+#define rdtsc(low,high) \
+ __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))
+
+#define rdtscl(low) \
+ __asm__ __volatile__("rdtsc" : "=a" (low) : : "edx")
+
+#define rdtscll(val) \
+ __asm__ __volatile__("rdtsc" : "=A" (val))
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+#define rdpmc(counter,low,high) \
+ __asm__ __volatile__("rdpmc" \
+ : "=a" (low), "=d" (high) \
+ : "c" (counter))
+
+/* symbolic names for some interesting MSRs */
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR 0
+#define MSR_IA32_P5_MC_TYPE 1
+#define MSR_IA32_PLATFORM_ID 0x17
+#define MSR_IA32_EBL_CR_POWERON 0x2a
+
+#define MSR_IA32_APICBASE 0x1b
+#define MSR_IA32_APICBASE_BSP (1<<8)
+#define MSR_IA32_APICBASE_ENABLE (1<<11)
+#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+
+#define MSR_IA32_UCODE_WRITE 0x79
+#define MSR_IA32_UCODE_REV 0x8b
+
+#define MSR_IA32_BBL_CR_CTL 0x119
+
+#define MSR_IA32_MCG_CAP 0x179
+#define MSR_IA32_MCG_STATUS 0x17a
+#define MSR_IA32_MCG_CTL 0x17b
+
+#define MSR_IA32_THERM_CONTROL 0x19a
+#define MSR_IA32_THERM_INTERRUPT 0x19b
+#define MSR_IA32_THERM_STATUS 0x19c
+#define MSR_IA32_MISC_ENABLE 0x1a0
+
+#define MSR_IA32_DEBUGCTLMSR 0x1d9
+#define MSR_IA32_LASTBRANCHFROMIP 0x1db
+#define MSR_IA32_LASTBRANCHTOIP 0x1dc
+#define MSR_IA32_LASTINTFROMIP 0x1dd
+#define MSR_IA32_LASTINTTOIP 0x1de
+
+#define MSR_IA32_MC0_CTL 0x400
+#define MSR_IA32_MC0_STATUS 0x401
+#define MSR_IA32_MC0_ADDR 0x402
+#define MSR_IA32_MC0_MISC 0x403
+
+#define MSR_P6_PERFCTR0 0xc1
+#define MSR_P6_PERFCTR1 0xc2
+#define MSR_P6_EVNTSEL0 0x186
+#define MSR_P6_EVNTSEL1 0x187
+
+/* AMD Defined MSRs */
+#define MSR_K6_EFER 0xC0000080
+#define MSR_K6_STAR 0xC0000081
+#define MSR_K6_WHCR 0xC0000082
+#define MSR_K6_UWCCR 0xC0000085
+#define MSR_K6_EPMR 0xC0000086
+#define MSR_K6_PSOR 0xC0000087
+#define MSR_K6_PFIR 0xC0000088
+
+#define MSR_K7_EVNTSEL0 0xC0010000
+#define MSR_K7_PERFCTR0 0xC0010004
+#define MSR_K7_HWCR 0xC0010015
+#define MSR_K7_CLK_CTL 0xC001001b
+#define MSR_K7_FID_VID_CTL 0xC0010041
+#define MSR_K7_VID_STATUS 0xC0010042
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1 0x107
+#define MSR_IDT_FCR2 0x108
+#define MSR_IDT_FCR3 0x109
+#define MSR_IDT_FCR4 0x10a
+
+#define MSR_IDT_MCR0 0x110
+#define MSR_IDT_MCR1 0x111
+#define MSR_IDT_MCR2 0x112
+#define MSR_IDT_MCR3 0x113
+#define MSR_IDT_MCR4 0x114
+#define MSR_IDT_MCR5 0x115
+#define MSR_IDT_MCR6 0x116
+#define MSR_IDT_MCR7 0x117
+#define MSR_IDT_MCR_CTRL 0x120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR 0x1107
+#define MSR_VIA_LONGHAUL 0x110a
+#define MSR_VIA_BCR2 0x1147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL 0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS 0x80868011
+#define MSR_TMTA_LRTI_READOUT 0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a
+
+#endif /* __ASM_MSR_H */
--- /dev/null
+/* Generic MTRR (Memory Type Range Register) ioctls.
+
+ Copyright (C) 1997-1999 Richard Gooch
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Library General Public
+ License as published by the Free Software Foundation; either
+ version 2 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Library General Public License for more details.
+
+ You should have received a copy of the GNU Library General Public
+ License along with this library; if not, write to the Free
+ Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ Richard Gooch may be reached by email at rgooch@atnf.csiro.au
+ The postal address is:
+ Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
+*/
+#ifndef _LINUX_MTRR_H
+#define _LINUX_MTRR_H
+
+#include <linux/config.h>
+#include <linux/ioctl.h>
+
+#define MTRR_IOCTL_BASE 'M'
+
+struct mtrr_sentry
+{
+ unsigned long base; /* Base address */
+ unsigned long size; /* Size of region */
+ unsigned int type; /* Type of region */
+};
+
+struct mtrr_gentry
+{
+ unsigned int regnum; /* Register number */
+ unsigned long base; /* Base address */
+ unsigned long size; /* Size of region */
+ unsigned int type; /* Type of region */
+};
+
+/* These are the various ioctls */
+#define MTRRIOC_ADD_ENTRY _IOW(MTRR_IOCTL_BASE, 0, struct mtrr_sentry)
+#define MTRRIOC_SET_ENTRY _IOW(MTRR_IOCTL_BASE, 1, struct mtrr_sentry)
+#define MTRRIOC_DEL_ENTRY _IOW(MTRR_IOCTL_BASE, 2, struct mtrr_sentry)
+#define MTRRIOC_GET_ENTRY _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
+#define MTRRIOC_KILL_ENTRY _IOW(MTRR_IOCTL_BASE, 4, struct mtrr_sentry)
+#define MTRRIOC_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 5, struct mtrr_sentry)
+#define MTRRIOC_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 6, struct mtrr_sentry)
+#define MTRRIOC_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 7, struct mtrr_sentry)
+#define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
+#define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry)
+
+/* These are the region types */
+#define MTRR_TYPE_UNCACHABLE 0
+#define MTRR_TYPE_WRCOMB 1
+/*#define MTRR_TYPE_ 2*/
+/*#define MTRR_TYPE_ 3*/
+#define MTRR_TYPE_WRTHROUGH 4
+#define MTRR_TYPE_WRPROT 5
+#define MTRR_TYPE_WRBACK 6
+#define MTRR_NUM_TYPES 7
+
+#ifdef MTRR_NEED_STRINGS
+static char *mtrr_strings[MTRR_NUM_TYPES] =
+{
+ "uncachable", /* 0 */
+ "write-combining", /* 1 */
+ "?", /* 2 */
+ "?", /* 3 */
+ "write-through", /* 4 */
+ "write-protect", /* 5 */
+ "write-back", /* 6 */
+};
+#endif
+
+#ifdef __KERNEL__
+
+/* The following functions are for use by other drivers */
+# ifdef CONFIG_MTRR
+extern int mtrr_add (unsigned long base, unsigned long size,
+ unsigned int type, char increment);
+extern int mtrr_add_page (unsigned long base, unsigned long size,
+ unsigned int type, char increment);
+extern int mtrr_del (int reg, unsigned long base, unsigned long size);
+extern int mtrr_del_page (int reg, unsigned long base, unsigned long size);
+extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
+# else
+static __inline__ int mtrr_add (unsigned long base, unsigned long size,
+ unsigned int type, char increment)
+{
+ return -ENODEV;
+}
+static __inline__ int mtrr_add_page (unsigned long base, unsigned long size,
+ unsigned int type, char increment)
+{
+ return -ENODEV;
+}
+static __inline__ int mtrr_del (int reg, unsigned long base,
+ unsigned long size)
+{
+ return -ENODEV;
+}
+static __inline__ int mtrr_del_page (int reg, unsigned long base,
+ unsigned long size)
+{
+ return -ENODEV;
+}
+
+static __inline__ void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) {;}
+
+# endif
+
+/* The following functions are for initialisation: don't use them! */
+extern int mtrr_init (void);
+# if defined(CONFIG_SMP) && defined(CONFIG_MTRR)
+extern void mtrr_init_boot_cpu (void);
+extern void mtrr_init_secondary_cpu (void);
+# endif
+
+#endif
+
+#endif /* _LINUX_MTRR_H */
--- /dev/null
+/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $
+ * linux/include/asm-i386/namei.h
+ *
+ * Included from linux/fs/namei.c
+ */
+
+#ifndef __I386_NAMEI_H
+#define __I386_NAMEI_H
+
+/* This dummy routine maybe changed to something useful
+ * for /usr/gnemul/ emulation stuff.
+ * Look at asm-sparc/namei.h for details.
+ */
+
+#define __emul_prefix() NULL
+
+#endif /* __I386_NAMEI_H */
--- /dev/null
+#ifndef _I386_PAGE_H
+#define _I386_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1UL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+#define clear_page(page) mmx_clear_page((void *)(page))
+#define copy_page(to,from) mmx_copy_page(to,from)
+
+#else
+
+/*
+ * On older X86 processors its not a win to use MMX here it seems.
+ * Maybe the K6-III ?
+ */
+
+#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE)
+
+#endif
+
+#define clear_user_page(page, vaddr) clear_page(page)
+#define copy_user_page(to, from, vaddr) copy_page(to, from)
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+extern unsigned long *phys_to_machine_mapping;
+#define pfn_to_mfn(_pfn) (phys_to_machine_mapping[(_pfn)])
+#define mfn_to_pfn(_mfn) (machine_to_phys_mapping[(_mfn)])
+static inline unsigned long phys_to_machine(unsigned long phys)
+{
+ unsigned long machine = pfn_to_mfn(phys >> PAGE_SHIFT);
+ machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK);
+ return machine;
+}
+static inline unsigned long machine_to_phys(unsigned long machine)
+{
+ unsigned long phys = mfn_to_pfn(machine >> PAGE_SHIFT);
+ phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK);
+ return phys;
+}
+
+/*
+ * These are used to make use of C type-checking..
+ */
+#if CONFIG_X86_PAE
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long long pmd; } pmd_t;
+typedef struct { unsigned long long pgd; } pgd_t;
+#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
+#else
+typedef struct { unsigned long pte_low; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pgd; } pgd_t;
+static inline unsigned long pte_val(pte_t x)
+{
+ unsigned long ret = x.pte_low;
+ if ( (ret & 1) ) ret = machine_to_phys(ret);
+ return ret;
+}
+#endif
+#define PTE_MASK PAGE_MASK
+
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+static inline unsigned long pmd_val(pmd_t x)
+{
+ unsigned long ret = x.pmd;
+ if ( (ret & 1) ) ret = machine_to_phys(ret);
+ return ret;
+}
+#define pgd_val(x) ({ BUG(); (unsigned long)0; })
+#define pgprot_val(x) ((x).pgprot)
+
+static inline pte_t __pte(unsigned long x)
+{
+ if ( (x & 1) ) x = phys_to_machine(x);
+ return ((pte_t) { (x) });
+}
+static inline pmd_t __pmd(unsigned long x)
+{
+ if ( (x & 1) ) x = phys_to_machine(x);
+ return ((pmd_t) { (x) });
+}
+#define __pgd(x) ({ BUG(); (pgprot_t) { 0 }; })
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#endif /* !__ASSEMBLY__ */
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/*
+ * This handles the memory map.. We could make this a config
+ * option, but too many people screw it up, and too few need
+ * it.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB.
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+
+#define __PAGE_OFFSET (0xC0000000)
+
+/*
+ * This much address space is reserved for vmalloc() and iomap()
+ * as well as fixmap mappings.
+ */
+#define __VMALLOC_RESERVE (128 << 20)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Tell the user there is some problem. Beep too, so we can
+ * see^H^H^Hhear bugs in early bootup as well!
+ * The offending file and line are encoded after the "officially
+ * undefined" opcode for parsing in the trap handler.
+ */
+
+#if 1 /* Set to zero for a slightly smaller kernel */
+#define BUG() \
+ __asm__ __volatile__( "ud2\n" \
+ "\t.word %c0\n" \
+ "\t.long %c1\n" \
+ : : "i" (__LINE__), "i" (__FILE__))
+#else
+#define BUG() __asm__ __volatile__("ud2\n")
+#endif
+
+#define PAGE_BUG(page) do { \
+ BUG(); \
+} while (0)
+
+/* Pure 2^n version of get_order */
+static __inline__ int get_order(unsigned long size)
+{
+ int order;
+
+ size = (size-1) >> (PAGE_SHIFT-1);
+ order = -1;
+ do {
+ size >>= 1;
+ order++;
+ } while (size);
+ return order;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET)
+#define VMALLOC_RESERVE ((unsigned long)__VMALLOC_RESERVE)
+#define __MAXMEM (-__PAGE_OFFSET-__VMALLOC_RESERVE)
+#define MAXMEM ((unsigned long)(-PAGE_OFFSET-VMALLOC_RESERVE))
+#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET)
+#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
+#define virt_to_page(kaddr) (mem_map + (__pa(kaddr) >> PAGE_SHIFT))
+#define VALID_PAGE(page) ((page - mem_map) < max_mapnr)
+
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_PAGE_H */
--- /dev/null
+#ifndef _ASMi386_PARAM_H
+#define _ASMi386_PARAM_H
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE 4096
+
+#ifndef NGROUPS
+#define NGROUPS 32
+#endif
+
+#ifndef NOGROUP
+#define NOGROUP (-1)
+#endif
+
+#define MAXHOSTNAMELEN 64 /* max length of hostname */
+
+#ifdef __KERNEL__
+# define CLOCKS_PER_SEC 100 /* frequency at which times() counts */
+#endif
+
+#endif
--- /dev/null
+/*
+ * parport.h: ia32-specific parport initialisation
+ *
+ * Copyright (C) 1999, 2000 Tim Waugh <tim@cyberelk.demon.co.uk>
+ *
+ * This file should only be included by drivers/parport/parport_pc.c.
+ */
+
+#ifndef _ASM_I386_PARPORT_H
+#define _ASM_I386_PARPORT_H 1
+
+static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
+static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
+{
+ return parport_pc_find_isa_ports (autoirq, autodma);
+}
+
+#endif /* !(_ASM_I386_PARPORT_H) */
--- /dev/null
+#ifndef _I386_PGALLOC_H
+#define _I386_PGALLOC_H
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <asm/hypervisor.h>
+#include <linux/threads.h>
+
+/*
+ * Quick lists are aligned so that least significant bits of array pointer
+ * are all zero when list is empty, and all one when list is full.
+ */
+#define QUICKLIST_ENTRIES 256
+#define QUICKLIST_EMPTY(_l) !((unsigned long)(_l) & ((QUICKLIST_ENTRIES*4)-1))
+#define QUICKLIST_FULL(_l) QUICKLIST_EMPTY((_l)+1)
+#define pgd_quicklist (current_cpu_data.pgd_quick)
+#define pmd_quicklist (current_cpu_data.pmd_quick)
+#define pte_quicklist (current_cpu_data.pte_quick)
+#define pgtable_cache_size (current_cpu_data.pgtable_cache_sz)
+
+#define pmd_populate(mm, pmd, pte) \
+ do { \
+ set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \
+ XENO_flush_page_update_queue(); \
+ } while ( 0 )
+
+/*
+ * Allocate and free page tables.
+ */
+
+#if defined (CONFIG_X86_PAE)
+
+#error "no PAE support as yet"
+
+/*
+ * We can't include <linux/slab.h> here, thus these uglinesses.
+ */
+struct kmem_cache_s;
+
+extern struct kmem_cache_s *pae_pgd_cachep;
+extern void *kmem_cache_alloc(struct kmem_cache_s *, int);
+extern void kmem_cache_free(struct kmem_cache_s *, void *);
+
+
+static inline pgd_t *get_pgd_slow(void)
+{
+ int i;
+ pgd_t *pgd = kmem_cache_alloc(pae_pgd_cachep, GFP_KERNEL);
+
+ if (pgd) {
+ for (i = 0; i < USER_PTRS_PER_PGD; i++) {
+ unsigned long pmd = __get_free_page(GFP_KERNEL);
+ if (!pmd)
+ goto out_oom;
+ clear_page(pmd);
+ set_pgd(pgd + i, __pgd(1 + __pa(pmd)));
+ }
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ swapper_pg_dir + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ }
+ return pgd;
+out_oom:
+ for (i--; i >= 0; i--)
+ free_page((unsigned long)__va(pgd_val(pgd[i])-1));
+ kmem_cache_free(pae_pgd_cachep, pgd);
+ return NULL;
+}
+
+#else
+
+static inline pgd_t *get_pgd_slow(void)
+{
+ pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+
+ if (pgd) {
+ memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ kpgd = pgd_offset_k((unsigned long)pgd);
+ kpmd = pmd_offset(kpgd, (unsigned long)pgd);
+ kpte = pte_offset(kpmd, (unsigned long)pgd);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)&~_PAGE_RW);
+ queue_pgd_pin(__pa(pgd));
+
+ }
+ return pgd;
+}
+
+#endif /* CONFIG_X86_PAE */
+
+static inline pgd_t *get_pgd_fast(void)
+{
+ unsigned long ret;
+
+ if ( !QUICKLIST_EMPTY(pgd_quicklist) ) {
+ ret = *(--pgd_quicklist);
+ pgtable_cache_size--;
+
+ } else
+ ret = (unsigned long)get_pgd_slow();
+ return (pgd_t *)ret;
+}
+
+static inline void free_pgd_slow(pgd_t *pgd)
+{
+#if defined(CONFIG_X86_PAE)
+#error
+ int i;
+
+ for (i = 0; i < USER_PTRS_PER_PGD; i++)
+ free_page((unsigned long)__va(pgd_val(pgd[i])-1));
+ kmem_cache_free(pae_pgd_cachep, pgd);
+#else
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+ queue_pgd_unpin(__pa(pgd));
+ kpgd = pgd_offset_k((unsigned long)pgd);
+ kpmd = pmd_offset(kpgd, (unsigned long)pgd);
+ kpte = pte_offset(kpmd, (unsigned long)pgd);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)|_PAGE_RW);
+ free_page((unsigned long)pgd);
+#endif
+}
+
+static inline void free_pgd_fast(pgd_t *pgd)
+{
+ if ( !QUICKLIST_FULL(pgd_quicklist) ) {
+ *(pgd_quicklist++) = (unsigned long)pgd;
+ pgtable_cache_size++;
+ } else
+ free_pgd_slow(pgd);
+}
+
+static inline pte_t *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ pte_t *pte;
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+
+ pte = (pte_t *) __get_free_page(GFP_KERNEL);
+ if (pte)
+ {
+ clear_page(pte);
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)&~_PAGE_RW);
+ queue_pte_pin(__pa(pte));
+ }
+ return pte;
+
+}
+
+static inline pte_t *pte_alloc_one_fast(struct mm_struct *mm,
+ unsigned long address)
+{
+ unsigned long ret = 0;
+ if ( !QUICKLIST_EMPTY(pte_quicklist) ) {
+ ret = *(--pte_quicklist);
+ pgtable_cache_size--;
+ }
+ return (pte_t *)ret;
+}
+
+static __inline__ void pte_free_slow(pte_t *pte)
+{
+ pgd_t *kpgd;
+ pmd_t *kpmd;
+ pte_t *kpte;
+ queue_pte_unpin(__pa(pte));
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ queue_l1_entry_update(__pa(kpte), (*(unsigned long *)kpte)|_PAGE_RW);
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free_fast(pte_t *pte)
+{
+ if ( !QUICKLIST_FULL(pte_quicklist) ) {
+ *(pte_quicklist++) = (unsigned long)pte;
+ pgtable_cache_size++;
+ } else
+ pte_free_slow(pte);
+}
+
+#define pte_free(pte) pte_free_fast(pte)
+#define pgd_free(pgd) free_pgd_fast(pgd)
+#define pgd_alloc(mm) get_pgd_fast()
+
+/*
+ * allocating and freeing a pmd is trivial: the 1-entry pmd is
+ * inside the pgd, so has no extra memory associated with it.
+ * (In the PAE case we free the pmds as part of the pgd.)
+ */
+
+#define pmd_alloc_one_fast(mm, addr) ({ BUG(); ((pmd_t *)1); })
+#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
+#define pmd_free_slow(x) do { } while (0)
+#define pmd_free_fast(x) do { } while (0)
+#define pmd_free(x) do { } while (0)
+#define pgd_populate(mm, pmd, pte) BUG()
+
+extern int do_check_pgt_cache(int, int);
+
+/*
+ * TLB flushing:
+ *
+ * - flush_tlb() flushes the current mm struct TLBs
+ * - flush_tlb_all() flushes all processes TLBs
+ * - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ * - flush_tlb_page(vma, vmaddr) flushes one page
+ * - flush_tlb_range(mm, start, end) flushes a range of pages
+ * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *
+ * ..but the i386 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ */
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ if (mm == current->active_mm) queue_tlb_flush();
+ XENO_flush_page_update_queue();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ if (vma->vm_mm == current->active_mm) queue_invlpg(addr);
+ XENO_flush_page_update_queue();
+}
+
+static inline void flush_tlb_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ if (mm == current->active_mm) queue_tlb_flush();
+ XENO_flush_page_update_queue();
+}
+
+#else
+#error no guestos SMP support yet...
+#include <asm/smp.h>
+
+#define local_flush_tlb() \
+ __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb() flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct mm_struct * mm, unsigned long start, unsigned long end)
+{
+ flush_tlb_mm(mm);
+}
+
+#define TLBSTATE_OK 1
+#define TLBSTATE_LAZY 2
+
+struct tlb_state
+{
+ struct mm_struct *active_mm;
+ int state;
+};
+extern struct tlb_state cpu_tlbstate[NR_CPUS];
+
+#endif /* CONFIG_SMP */
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ /* i386 does not keep any page table caches in TLB */
+ XENO_flush_page_update_queue();
+}
+
+#endif /* _I386_PGALLOC_H */
--- /dev/null
+#ifndef _I386_PGTABLE_2LEVEL_H
+#define _I386_PGTABLE_2LEVEL_H
+
+/*
+ * traditional i386 two-level paging structure:
+ */
+
+#define PGDIR_SHIFT 22
+#define PTRS_PER_PGD 1024
+
+/*
+ * the i386 is two-level, so we don't really have any
+ * PMD directory physically.
+ */
+#define PMD_SHIFT 22
+#define PTRS_PER_PMD 1
+
+#define PTRS_PER_PTE 1024
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pgd is never bad, and a pmd always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+#define pgd_clear(xp) do { } while (0)
+
+#define set_pte(pteptr, pteval) queue_l1_entry_update(__pa(pteptr), (pteval).pte_low)
+#define set_pte_atomic(pteptr, pteval) queue_l1_entry_update(__pa(pteptr), (pteval).pte_low)
+#define set_pmd(pmdptr, pmdval) queue_l2_entry_update(__pa(pmdptr), (pmdval).pmd)
+#define set_pgd(pgdptr, pgdval) ((void)0)
+
+#define pgd_page(pgd) \
+((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
+
+static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
+{
+ return (pmd_t *) dir;
+}
+
+/*
+ * A note on implementation of this atomic 'get-and-clear' operation.
+ * This is actually very simple because XenoLinux can only run on a single
+ * processor. Therefore, we cannot race other processors setting the 'accessed'
+ * or 'dirty' bits on a page-table entry.
+ * Even if pages are shared between domains, that is not a problem because
+ * each domain will have separate page tables, with their own versions of
+ * accessed & dirty state.
+ */
+static inline pte_t ptep_get_and_clear(pte_t *xp)
+{
+ pte_t pte = *xp;
+ queue_l1_entry_update(__pa(xp), 0);
+ return pte;
+}
+
+#define pte_same(a, b) ((a).pte_low == (b).pte_low)
+#define pte_page(x) (mem_map+((unsigned long)((pte_val(x) >> PAGE_SHIFT))))
+#define pte_none(x) (!(x).pte_low)
+#define __mk_pte(page_nr,pgprot) __pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+
+#endif /* _I386_PGTABLE_2LEVEL_H */
--- /dev/null
+#ifndef _I386_PGTABLE_3LEVEL_H
+#define _I386_PGTABLE_3LEVEL_H
+
+#error "PAE unsupported"
+
+/*
+ * Intel Physical Address Extension (PAE) Mode - three-level page
+ * tables on PPro+ CPUs.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT 30
+#define PTRS_PER_PGD 4
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT 21
+#define PTRS_PER_PMD 512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE 512
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
+
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+
+/* Rules for using set_pte: the pte being assigned *must* be
+ * either not present or in a state where the hardware will
+ * not attempt to update the pte. In places where this is
+ * not possible, use pte_get_and_clear to obtain the old pte
+ * value and then use set_pte to update it. -ben
+ */
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+ ptep->pte_high = pte.pte_high;
+ smp_wmb();
+ ptep->pte_low = pte.pte_low;
+}
+#define set_pmd(pmdptr,pmdval) \
+ set_64bit((unsigned long long *)(pmdptr),pmd_val(pmdval))
+#define set_pgd(pgdptr,pgdval) \
+ set_64bit((unsigned long long *)(pgdptr),pgd_val(pgdval))
+#define set_pte_atomic(pteptr,pteval) \
+ set_64bit((unsigned long long *)(pteptr),pte_val(pteval))
+
+
+/*
+ * Pentium-II erratum A13: in PAE mode we explicitly have to flush
+ * the TLB via cr3 if the top-level pgd is changed...
+ * We do not let the generic code free and clear pgd entries due to
+ * this erratum.
+ */
+static inline void pgd_clear (pgd_t * pgd) { }
+
+#define pgd_page(pgd) \
+((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(dir, address) ((pmd_t *) pgd_page(*(dir)) + \
+ __pmd_offset(address))
+
+static inline pte_t ptep_get_and_clear(pte_t *ptep)
+{
+ pte_t res;
+
+ /* xchg acts as a barrier before the setting of the high bits */
+ res.pte_low = xchg(&ptep->pte_low, 0);
+ res.pte_high = ptep->pte_high;
+ ptep->pte_high = 0;
+
+ return res;
+}
+
+static inline int pte_same(pte_t a, pte_t b)
+{
+ return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
+}
+
+#define pte_page(x) (mem_map+(((x).pte_low >> PAGE_SHIFT) | ((x).pte_high << (32 - PAGE_SHIFT))))
+#define pte_none(x) (!(x).pte_low && !(x).pte_high)
+
+static inline pte_t __mk_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+ pte_t pte;
+
+ pte.pte_high = page_nr >> (32 - PAGE_SHIFT);
+ pte.pte_low = (page_nr << PAGE_SHIFT) | pgprot_val(pgprot);
+ return pte;
+}
+
+#endif /* _I386_PGTABLE_3LEVEL_H */
--- /dev/null
+#ifndef _I386_PGTABLE_H
+#define _I386_PGTABLE_H
+
+#include <linux/config.h>
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/hypervisor.h>
+#include <linux/threads.h>
+#include <asm/fixmap.h>
+
+#ifndef _I386_BITOPS_H
+#include <asm/bitops.h>
+#endif
+
+#define swapper_pg_dir 0
+extern void paging_init(void);
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all() do { } while (0)
+#define flush_cache_mm(mm) do { } while (0)
+#define flush_cache_range(mm, start, end) do { } while (0)
+#define flush_cache_page(vma, vmaddr) do { } while (0)
+#define flush_page_to_ram(page) do { } while (0)
+#define flush_dcache_page(page) do { } while (0)
+#define flush_icache_range(start, end) do { } while (0)
+#define flush_icache_page(vma,pg) do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
+
+extern unsigned long pgkern_mask;
+
+#define __flush_tlb() ({ queue_tlb_flush(); XENO_flush_page_update_queue(); })
+#define __flush_tlb_global() __flush_tlb()
+#define __flush_tlb_all() __flush_tlb_global()
+#define __flush_tlb_one(addr) ({ queue_invlpg(addr); XENO_flush_page_update_queue(); })
+#define __flush_tlb_single(addr) ({ queue_invlpg(addr); XENO_flush_page_update_queue(); })
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[1024];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifndef __ASSEMBLY__
+#if CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+
+/*
+ * Need to initialise the X86 PAE caches
+ */
+extern void pgtable_cache_init(void);
+
+#else
+# include <asm/pgtable-2level.h>
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init() do { } while (0)
+
+#endif
+#endif
+
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_PGD_NR 0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define TWOLEVEL_PGDIR_SHIFT 22
+#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
+#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
+
+
+#ifndef __ASSEMBLY__
+/* 4MB is just a nice "safety zone". Also, we align to a fresh pde. */
+#define VMALLOC_OFFSET (4*1024*1024)
+#define VMALLOC_START (((unsigned long) high_memory + 2*VMALLOC_OFFSET-1) & \
+ ~(VMALLOC_OFFSET-1))
+#define VMALLOC_VMADDR(x) ((unsigned long)(x))
+#define VMALLOC_END (FIXADDR_START - 2*PAGE_SIZE)
+
+#define _PAGE_BIT_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+
+#define _PAGE_PRESENT 0x001
+#define _PAGE_RW 0x002
+#define _PAGE_USER 0x004
+#define _PAGE_PWT 0x008
+#define _PAGE_PCD 0x010
+#define _PAGE_ACCESSED 0x020
+#define _PAGE_DIRTY 0x040
+#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
+
+#define _PAGE_PROTNONE 0x080 /* If not present */
+
+#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+
+#define __PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_NOCACHE \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_RO \
+ (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+#if 0
+#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
+#else
+#define MAKE_GLOBAL(x) __pgprot(x)
+#endif
+
+#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+
+/*
+ * The i386 can't do page protection for execute, and considers that
+ * the same are read. Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY
+#define __P101 PAGE_READONLY
+#define __P110 PAGE_COPY
+#define __P111 PAGE_COPY
+
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY
+#define __S101 PAGE_READONLY
+#define __S110 PAGE_SHARED
+#define __S111 PAGE_SHARED
+
+#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+#define pte_clear(xp) queue_l1_entry_update(__pa(xp), 0)
+
+#define pmd_none(x) (!(x).pmd)
+#define pmd_present(x) ((x).pmd & _PAGE_PRESENT)
+#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
+#define pmd_bad(x) (((x).pmd & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
+static inline int pte_exec(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
+static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; }
+
+static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; }
+static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; }
+
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ int ret = pteval & _PAGE_DIRTY;
+ if ( ret ) queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_DIRTY);
+ return ret;
+}
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ int ret = pteval & _PAGE_ACCESSED;
+ if ( ret ) queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_ACCESSED);
+ return ret;
+}
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ if ( (pteval & _PAGE_RW) )
+ queue_l1_entry_update(__pa(ptep), pteval & ~_PAGE_RW);
+}
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ unsigned long pteval = *(unsigned long *)ptep;
+ if ( !(pteval & _PAGE_DIRTY) )
+ queue_l1_entry_update(__pa(ptep), pteval | _PAGE_DIRTY);
+}
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot) __mk_pte((page) - mem_map, (pgprot))
+
+/* This takes a physical page address that is used by the remapping functions */
+#define mk_pte_phys(physpage, pgprot) __mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ pte.pte_low &= _PAGE_CHG_MASK;
+ pte.pte_low |= pgprot_val(newprot);
+ return pte;
+}
+
+#define page_pte(page) page_pte_prot(page, __pgprot(0))
+
+#define pmd_page(pmd) \
+((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/* to find an entry in a page-table-directory. */
+#define pgd_index(address) ((address >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+
+#define __pgd_offset(address) pgd_index(address)
+
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+#define __pmd_offset(address) \
+ (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/* Find an entry in the third-level page table.. */
+#define __pte_offset(address) \
+ ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset(dir, address) ((pte_t *) pmd_page(*(dir)) + \
+ __pte_offset(address))
+
+/*
+ * The i386 doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ */
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+
+/* Encode and de-code a swap entry */
+#define SWP_TYPE(x) (((x).val >> 1) & 0x3f)
+#define SWP_OFFSET(x) ((x).val >> 8)
+#define SWP_ENTRY(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#define pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low })
+#define swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+struct page;
+int change_page_attr(struct page *, int, pgprot_t prot);
+
+#endif /* !__ASSEMBLY__ */
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+#define PageSkip(page) (0)
+#define kern_addr_valid(addr) (1)
+
+#define io_remap_page_range remap_page_range
+
+#endif /* _I386_PGTABLE_H */
--- /dev/null
+#ifndef __i386_POLL_H
+#define __i386_POLL_H
+
+/* These are specified by iBCS2 */
+#define POLLIN 0x0001
+#define POLLPRI 0x0002
+#define POLLOUT 0x0004
+#define POLLERR 0x0008
+#define POLLHUP 0x0010
+#define POLLNVAL 0x0020
+
+/* The rest seem to be more-or-less nonstandard. Check them! */
+#define POLLRDNORM 0x0040
+#define POLLRDBAND 0x0080
+#define POLLWRNORM 0x0100
+#define POLLWRBAND 0x0200
+#define POLLMSG 0x0400
+
+struct pollfd {
+ int fd;
+ short events;
+ short revents;
+};
+
+#endif
--- /dev/null
+#ifndef __ARCH_I386_POSIX_TYPES_H
+#define __ARCH_I386_POSIX_TYPES_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc. Also, we cannot
+ * assume GCC is being used.
+ */
+
+typedef unsigned short __kernel_dev_t;
+typedef unsigned long __kernel_ino_t;
+typedef unsigned short __kernel_mode_t;
+typedef unsigned short __kernel_nlink_t;
+typedef long __kernel_off_t;
+typedef int __kernel_pid_t;
+typedef unsigned short __kernel_ipc_pid_t;
+typedef unsigned short __kernel_uid_t;
+typedef unsigned short __kernel_gid_t;
+typedef unsigned int __kernel_size_t;
+typedef int __kernel_ssize_t;
+typedef int __kernel_ptrdiff_t;
+typedef long __kernel_time_t;
+typedef long __kernel_suseconds_t;
+typedef long __kernel_clock_t;
+typedef int __kernel_daddr_t;
+typedef char * __kernel_caddr_t;
+typedef unsigned short __kernel_uid16_t;
+typedef unsigned short __kernel_gid16_t;
+typedef unsigned int __kernel_uid32_t;
+typedef unsigned int __kernel_gid32_t;
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+
+#ifdef __GNUC__
+typedef long long __kernel_loff_t;
+#endif
+
+typedef struct {
+#if defined(__KERNEL__) || defined(__USE_ALL)
+ int val[2];
+#else /* !defined(__KERNEL__) && !defined(__USE_ALL) */
+ int __val[2];
+#endif /* !defined(__KERNEL__) && !defined(__USE_ALL) */
+} __kernel_fsid_t;
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#undef __FD_SET
+#define __FD_SET(fd,fdsetp) \
+ __asm__ __volatile__("btsl %1,%0": \
+ "=m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
+
+#undef __FD_CLR
+#define __FD_CLR(fd,fdsetp) \
+ __asm__ __volatile__("btrl %1,%0": \
+ "=m" (*(__kernel_fd_set *) (fdsetp)):"r" ((int) (fd)))
+
+#undef __FD_ISSET
+#define __FD_ISSET(fd,fdsetp) (__extension__ ({ \
+ unsigned char __result; \
+ __asm__ __volatile__("btl %1,%2 ; setb %0" \
+ :"=q" (__result) :"r" ((int) (fd)), \
+ "m" (*(__kernel_fd_set *) (fdsetp))); \
+ __result; }))
+
+#undef __FD_ZERO
+#define __FD_ZERO(fdsetp) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__("cld ; rep ; stosl" \
+ :"=m" (*(__kernel_fd_set *) (fdsetp)), \
+ "=&c" (__d0), "=&D" (__d1) \
+ :"a" (0), "1" (__FDSET_LONGS), \
+ "2" ((__kernel_fd_set *) (fdsetp)) : "memory"); \
+} while (0)
+
+#endif /* defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) */
+
+#endif
--- /dev/null
+/*
+ * include/asm-i386/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_I386_PROCESSOR_H
+#define __ASM_I386_PROCESSOR_H
+
+#include <asm/math_emu.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <linux/cache.h>
+#include <linux/config.h>
+#include <linux/threads.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
+
+/*
+ * CPU type and hardware bug flags. Kept separately for each CPU.
+ * Members of this structure are referenced in head.S, so think twice
+ * before touching them. [mj]
+ */
+
+struct cpuinfo_x86 {
+ __u8 x86; /* CPU family */
+ __u8 x86_vendor; /* CPU vendor */
+ __u8 x86_model;
+ __u8 x86_mask;
+ char wp_works_ok; /* It doesn't on 386's */
+ char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */
+ char hard_math;
+ char rfu;
+ int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */
+ __u32 x86_capability[NCAPINTS];
+ char x86_vendor_id[16];
+ char x86_model_id[64];
+ int x86_cache_size; /* in KB - valid for CPUS which support this
+ call */
+ int fdiv_bug;
+ int f00f_bug;
+ int coma_bug;
+ unsigned long loops_per_jiffy;
+ unsigned long *pgd_quick;
+ unsigned long *pmd_quick;
+ unsigned long *pte_quick;
+ unsigned long pgtable_cache_sz;
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_RISE 6
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_NSC 8
+#define X86_VENDOR_UNKNOWN 0xff
+
+/*
+ * capabilities of CPUs
+ */
+
+extern struct cpuinfo_x86 boot_cpu_data;
+extern struct tss_struct init_tss[NR_CPUS];
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+#define cpu_has_pge (test_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability))
+#define cpu_has_pse (test_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability))
+#define cpu_has_pae (test_bit(X86_FEATURE_PAE, boot_cpu_data.x86_capability))
+#define cpu_has_tsc (test_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability))
+#define cpu_has_de (test_bit(X86_FEATURE_DE, boot_cpu_data.x86_capability))
+#define cpu_has_vme (test_bit(X86_FEATURE_VME, boot_cpu_data.x86_capability))
+#define cpu_has_fxsr (test_bit(X86_FEATURE_FXSR, boot_cpu_data.x86_capability))
+#define cpu_has_xmm (test_bit(X86_FEATURE_XMM, boot_cpu_data.x86_capability))
+#define cpu_has_fpu (test_bit(X86_FEATURE_FPU, boot_cpu_data.x86_capability))
+#define cpu_has_apic (test_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability))
+
+extern char ignore_irq13;
+
+extern void identify_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT 0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */
+
+/*
+ * Generic CPUID function
+ */
+static inline void cpuid(int op, int *eax, int *ebx, int *ecx, int *edx)
+{
+ __asm__("cpuid"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (op));
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+ unsigned int eax;
+
+ __asm__("cpuid"
+ : "=a" (eax)
+ : "0" (op)
+ : "bx", "cx", "dx");
+ return eax;
+}
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+ unsigned int eax, ebx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=b" (ebx)
+ : "0" (op)
+ : "cx", "dx" );
+ return ebx;
+}
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+ unsigned int eax, ecx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=c" (ecx)
+ : "0" (op)
+ : "bx", "dx" );
+ return ecx;
+}
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+ unsigned int eax, edx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=d" (edx)
+ : "0" (op)
+ : "bx", "cx");
+ return edx;
+}
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME 0x0001 /* enable vm86 extensions */
+#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE 0x0008 /* enable debugging extensions */
+#define X86_CR4_PSE 0x0010 /* enable page size extensions */
+#define X86_CR4_PAE 0x0020 /* enable physical address extensions */
+#define X86_CR4_MCE 0x0040 /* Machine check enable */
+#define X86_CR4_PGE 0x0080 /* enable global pages */
+#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */
+#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */
+
+#define load_cr3(pgdir) \
+ asm volatile("movl %0,%%cr3": :"r" (__pa(pgdir)));
+
+extern unsigned long mmu_cr4_features;
+
+#include <asm/hypervisor.h>
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+ HYPERVISOR_console_write("No set_in_cr4", 13);
+}
+
+static inline void clear_in_cr4 (unsigned long mask)
+{
+ HYPERVISOR_console_write("No clear_in_cr4", 15);
+}
+
+/*
+ * Cyrix CPU configuration register indexes
+ */
+#define CX86_CCR0 0xc0
+#define CX86_CCR1 0xc1
+#define CX86_CCR2 0xc2
+#define CX86_CCR3 0xc3
+#define CX86_CCR4 0xe8
+#define CX86_CCR5 0xe9
+#define CX86_CCR6 0xea
+#define CX86_CCR7 0xeb
+#define CX86_DIR0 0xfe
+#define CX86_DIR1 0xff
+#define CX86_ARR_BASE 0xc4
+#define CX86_RCR_BASE 0xdc
+
+/*
+ * Cyrix CPU indexed register access macros
+ */
+
+#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86(reg, data) do { \
+ outb((reg), 0x22); \
+ outb((data), 0x23); \
+} while (0)
+
+/*
+ * Bus types (default is ISA, but people can check others with these..)
+ */
+#ifdef CONFIG_EISA
+extern int EISA_bus;
+#else
+#define EISA_bus (0)
+#endif
+extern int MCA_bus;
+
+/* from system description table in BIOS. Mostly for MCA use, but
+others may find it useful. */
+extern unsigned int machine_id;
+extern unsigned int machine_submodel_id;
+extern unsigned int BIOS_revision;
+extern unsigned int mca_pentium_flag;
+
+/*
+ * User space process size: 3GB (default).
+ */
+#define TASK_SIZE (PAGE_OFFSET)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE (TASK_SIZE / 3)
+
+/*
+ * Size of io_bitmap in longwords: 32 is ports 0-0x3ff.
+ */
+#define IO_BITMAP_SIZE 32
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+
+struct i387_fsave_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ long status; /* software status information */
+};
+
+struct i387_fxsave_struct {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long mxcsr;
+ long reserved;
+ long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+ long padding[56];
+} __attribute__ ((aligned (16)));
+
+struct i387_soft_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ unsigned char ftop, changed, lookahead, no_update, rm, alimit;
+ struct info *info;
+ unsigned long entry_eip;
+};
+
+union i387_union {
+ struct i387_fsave_struct fsave;
+ struct i387_fxsave_struct fxsave;
+ struct i387_soft_struct soft;
+};
+
+typedef struct {
+ unsigned long seg;
+} mm_segment_t;
+
+struct tss_struct {
+ unsigned short back_link,__blh;
+ unsigned long esp0;
+ unsigned short ss0,__ss0h;
+ unsigned long esp1;
+ unsigned short ss1,__ss1h;
+ unsigned long esp2;
+ unsigned short ss2,__ss2h;
+ unsigned long __cr3;
+ unsigned long eip;
+ unsigned long eflags;
+ unsigned long eax,ecx,edx,ebx;
+ unsigned long esp;
+ unsigned long ebp;
+ unsigned long esi;
+ unsigned long edi;
+ unsigned short es, __esh;
+ unsigned short cs, __csh;
+ unsigned short ss, __ssh;
+ unsigned short ds, __dsh;
+ unsigned short fs, __fsh;
+ unsigned short gs, __gsh;
+ unsigned short ldt, __ldth;
+ unsigned short trace, bitmap;
+ unsigned long io_bitmap[IO_BITMAP_SIZE+1];
+ /*
+ * pads the TSS to be cacheline-aligned (size is 0x100)
+ */
+ unsigned long __cacheline_filler[5];
+};
+
+struct thread_struct {
+ unsigned long esp0;
+ unsigned long eip;
+ unsigned long esp;
+ unsigned long fs;
+ unsigned long gs;
+/* Hardware debugging registers */
+ unsigned long debugreg[8]; /* %%db0-7 debug registers */
+/* fault info */
+ unsigned long cr2, trap_no, error_code;
+/* floating point info */
+ union i387_union i387;
+/* virtual 86 mode info */
+ struct vm86_struct * vm86_info;
+ unsigned long screen_bitmap;
+ unsigned long v86flags, v86mask, saved_esp0;
+};
+
+#define INIT_THREAD { 0 }
+
+#define INIT_TSS { \
+ 0,0, /* back_link, __blh */ \
+ sizeof(init_stack) + (long) &init_stack, /* esp0 */ \
+ __KERNEL_DS, 0, /* ss0 */ \
+ 0,0,0,0,0,0, /* stack1, stack2 */ \
+ 0, /* cr3 */ \
+ 0,0, /* eip,eflags */ \
+ 0,0,0,0, /* eax,ecx,edx,ebx */ \
+ 0,0,0,0, /* esp,ebp,esi,edi */ \
+ 0,0,0,0,0,0, /* es,cs,ss */ \
+ 0,0,0,0,0,0, /* ds,fs,gs */ \
+ __LDT(0),0, /* ldt */ \
+ 0, INVALID_IO_BITMAP_OFFSET, /* tace, bitmap */ \
+ {~0, } /* ioperm */ \
+}
+
+#define start_thread(regs, new_eip, new_esp) do { \
+ __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \
+ set_fs(USER_DS); \
+ regs->xds = __USER_DS; \
+ regs->xes = __USER_DS; \
+ regs->xss = __USER_DS; \
+ regs->xcs = __USER_CS; \
+ regs->eip = new_eip; \
+ regs->esp = new_esp; \
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+/* Copy and release all segment info associated with a VM */
+extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
+extern void release_segments(struct mm_struct * mm);
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+static inline unsigned long thread_saved_pc(struct thread_struct *t)
+{
+ return ((unsigned long *)t->esp)[3];
+}
+
+unsigned long get_wchan(struct task_struct *p);
+#define KSTK_EIP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1019])
+#define KSTK_ESP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1022])
+
+#define THREAD_SIZE (2*PAGE_SIZE)
+#define alloc_task_struct() ((struct task_struct *) __get_free_pages(GFP_KERNEL,1))
+#define free_task_struct(p) free_pages((unsigned long) (p), 1)
+#define get_task_struct(tsk) atomic_inc(&virt_to_page(tsk)->count)
+
+#define init_task (init_task_union.task)
+#define init_stack (init_task_union.stack)
+
+struct microcode {
+ unsigned int hdrver;
+ unsigned int rev;
+ unsigned int date;
+ unsigned int sig;
+ unsigned int cksum;
+ unsigned int ldrver;
+ unsigned int pf;
+ unsigned int reserved[5];
+ unsigned int bits[500];
+};
+
+/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
+#define MICROCODE_IOCFREE _IO('6',0)
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+ __asm__ __volatile__("rep;nop");
+}
+
+#define cpu_relax() rep_nop()
+
+/* Prefetch instructions for Pentium III and AMD Athlon */
+#ifdef CONFIG_MPENTIUMIII
+
+#define ARCH_HAS_PREFETCH
+extern inline void prefetch(const void *x)
+{
+ __asm__ __volatile__ ("prefetchnta (%0)" : : "r"(x));
+}
+
+#elif CONFIG_X86_USE_3DNOW
+
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+extern inline void prefetch(const void *x)
+{
+ __asm__ __volatile__ ("prefetch (%0)" : : "r"(x));
+}
+
+extern inline void prefetchw(const void *x)
+{
+ __asm__ __volatile__ ("prefetchw (%0)" : : "r"(x));
+}
+#define spin_lock_prefetch(x) prefetchw(x)
+
+#endif
+
+#define TF_MASK 0x100
+
+#endif /* __ASM_I386_PROCESSOR_H */
--- /dev/null
+#ifndef _I386_PTRACE_H
+#define _I386_PTRACE_H
+
+#define EBX 0
+#define ECX 1
+#define EDX 2
+#define ESI 3
+#define EDI 4
+#define EBP 5
+#define EAX 6
+#define DS 7
+#define ES 8
+#define FS 9
+#define GS 10
+#define ORIG_EAX 11
+#define EIP 12
+#define CS 13
+#define EFL 14
+#define UESP 15
+#define SS 16
+#define FRAME_SIZE 17
+
+/* this struct defines the way the registers are stored on the
+ stack during a system call. */
+
+struct pt_regs {
+ long ebx;
+ long ecx;
+ long edx;
+ long esi;
+ long edi;
+ long ebp;
+ long eax;
+ int xds;
+ int xes;
+ long orig_eax;
+ long eip;
+ int xcs;
+ long eflags;
+ long esp;
+ int xss;
+};
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS 12
+#define PTRACE_SETREGS 13
+#define PTRACE_GETFPREGS 14
+#define PTRACE_SETFPREGS 15
+#define PTRACE_GETFPXREGS 18
+#define PTRACE_SETFPXREGS 19
+
+#define PTRACE_SETOPTIONS 21
+
+/* options set using PTRACE_SETOPTIONS */
+#define PTRACE_O_TRACESYSGOOD 0x00000001
+
+#ifdef __KERNEL__
+#define user_mode(regs) ((regs) && (3 & (regs)->xcs))
+#define instruction_pointer(regs) ((regs) ? (regs)->eip : NULL)
+extern void show_regs(struct pt_regs *);
+#endif
+
+#endif
--- /dev/null
+#ifndef _I386_RESOURCE_H
+#define _I386_RESOURCE_H
+
+/*
+ * Resource limits
+ */
+
+#define RLIMIT_CPU 0 /* CPU time in ms */
+#define RLIMIT_FSIZE 1 /* Maximum filesize */
+#define RLIMIT_DATA 2 /* max data size */
+#define RLIMIT_STACK 3 /* max stack size */
+#define RLIMIT_CORE 4 /* max core file size */
+#define RLIMIT_RSS 5 /* max resident set size */
+#define RLIMIT_NPROC 6 /* max number of processes */
+#define RLIMIT_NOFILE 7 /* max number of open files */
+#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */
+#define RLIMIT_AS 9 /* address space limit */
+#define RLIMIT_LOCKS 10 /* maximum file locks held */
+
+#define RLIM_NLIMITS 11
+
+/*
+ * SuS says limits have to be unsigned.
+ * Which makes a ton more sense anyway.
+ */
+#define RLIM_INFINITY (~0UL)
+
+#ifdef __KERNEL__
+
+#define INIT_RLIMITS \
+{ \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { _STK_LIM, RLIM_INFINITY }, \
+ { 0, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { 0, 0 }, \
+ { INR_OPEN, INR_OPEN }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+ { RLIM_INFINITY, RLIM_INFINITY }, \
+}
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+/* include/asm-i386/rwlock.h
+ *
+ * Helpers used by both rw spinlocks and rw semaphores.
+ *
+ * Based in part on code from semaphore.h and
+ * spinlock.h Copyright 1996 Linus Torvalds.
+ *
+ * Copyright 1999 Red Hat, Inc.
+ *
+ * Written by Benjamin LaHaise.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_I386_RWLOCK_H
+#define _ASM_I386_RWLOCK_H
+
+#define RW_LOCK_BIAS 0x01000000
+#define RW_LOCK_BIAS_STR "0x01000000"
+
+#define __build_read_lock_ptr(rw, helper) \
+ asm volatile(LOCK "subl $1,(%0)\n\t" \
+ "js 2f\n" \
+ "1:\n" \
+ LOCK_SECTION_START("") \
+ "2:\tcall " helper "\n\t" \
+ "jmp 1b\n" \
+ LOCK_SECTION_END \
+ ::"a" (rw) : "memory")
+
+#define __build_read_lock_const(rw, helper) \
+ asm volatile(LOCK "subl $1,%0\n\t" \
+ "js 2f\n" \
+ "1:\n" \
+ LOCK_SECTION_START("") \
+ "2:\tpushl %%eax\n\t" \
+ "leal %0,%%eax\n\t" \
+ "call " helper "\n\t" \
+ "popl %%eax\n\t" \
+ "jmp 1b\n" \
+ LOCK_SECTION_END \
+ :"=m" (*(volatile int *)rw) : : "memory")
+
+#define __build_read_lock(rw, helper) do { \
+ if (__builtin_constant_p(rw)) \
+ __build_read_lock_const(rw, helper); \
+ else \
+ __build_read_lock_ptr(rw, helper); \
+ } while (0)
+
+#define __build_write_lock_ptr(rw, helper) \
+ asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+ "jnz 2f\n" \
+ "1:\n" \
+ LOCK_SECTION_START("") \
+ "2:\tcall " helper "\n\t" \
+ "jmp 1b\n" \
+ LOCK_SECTION_END \
+ ::"a" (rw) : "memory")
+
+#define __build_write_lock_const(rw, helper) \
+ asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+ "jnz 2f\n" \
+ "1:\n" \
+ LOCK_SECTION_START("") \
+ "2:\tpushl %%eax\n\t" \
+ "leal %0,%%eax\n\t" \
+ "call " helper "\n\t" \
+ "popl %%eax\n\t" \
+ "jmp 1b\n" \
+ LOCK_SECTION_END \
+ :"=m" (*(volatile int *)rw) : : "memory")
+
+#define __build_write_lock(rw, helper) do { \
+ if (__builtin_constant_p(rw)) \
+ __build_write_lock_const(rw, helper); \
+ else \
+ __build_write_lock_ptr(rw, helper); \
+ } while (0)
+
+#endif
--- /dev/null
+/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ *
+ * Derived from asm-i386/semaphore.h
+ *
+ * Trylock by Brian Watson (Brian.J.Watson@compaq.com).
+ *
+ *
+ * The MSW of the count is the negated number of active writers and waiting
+ * lockers, and the LSW is the total number of active locks
+ *
+ * The lock count is initialized to 0 (no active and no waiting lockers).
+ *
+ * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
+ * uncontended lock. This can be determined because XADD returns the old value.
+ * Readers increment by 1 and see a positive value when uncontended, negative
+ * if there are writers (and maybe) readers waiting (in which case it goes to
+ * sleep).
+ *
+ * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
+ * be extended to 65534 by manually checking the whole MSW rather than relying
+ * on the S flag.
+ *
+ * The value of ACTIVE_BIAS supports up to 65535 active processes.
+ *
+ * This should be totally fair - if anything is waiting, a process that wants a
+ * lock will go to the back of the queue. When the currently active lock is
+ * released, if there's a writer at the front of the queue, then that and only
+ * that will be woken up; if there's a bunch of consequtive readers at the
+ * front, then they'll all be woken up, but no other readers will be.
+ */
+
+#ifndef _I386_RWSEM_H
+#define _I386_RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error please dont include asm/rwsem.h directly, use linux/rwsem.h instead
+#endif
+
+#ifdef __KERNEL__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+struct rwsem_waiter;
+
+extern struct rw_semaphore *FASTCALL(rwsem_down_read_failed(struct rw_semaphore *sem));
+extern struct rw_semaphore *FASTCALL(rwsem_down_write_failed(struct rw_semaphore *sem));
+extern struct rw_semaphore *FASTCALL(rwsem_wake(struct rw_semaphore *));
+
+/*
+ * the semaphore definition
+ */
+struct rw_semaphore {
+ signed long count;
+#define RWSEM_UNLOCKED_VALUE 0x00000000
+#define RWSEM_ACTIVE_BIAS 0x00000001
+#define RWSEM_ACTIVE_MASK 0x0000ffff
+#define RWSEM_WAITING_BIAS (-0x00010000)
+#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+ spinlock_t wait_lock;
+ struct list_head wait_list;
+#if RWSEM_DEBUG
+ int debug;
+#endif
+};
+
+/*
+ * initialisation
+ */
+#if RWSEM_DEBUG
+#define __RWSEM_DEBUG_INIT , 0
+#else
+#define __RWSEM_DEBUG_INIT /* */
+#endif
+
+#define __RWSEM_INITIALIZER(name) \
+{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, LIST_HEAD_INIT((name).wait_list) \
+ __RWSEM_DEBUG_INIT }
+
+#define DECLARE_RWSEM(name) \
+ struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+static inline void init_rwsem(struct rw_semaphore *sem)
+{
+ sem->count = RWSEM_UNLOCKED_VALUE;
+ spin_lock_init(&sem->wait_lock);
+ INIT_LIST_HEAD(&sem->wait_list);
+#if RWSEM_DEBUG
+ sem->debug = 0;
+#endif
+}
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+ __asm__ __volatile__(
+ "# beginning down_read\n\t"
+LOCK_PREFIX " incl (%%eax)\n\t" /* adds 0x00000001, returns the old value */
+ " js 2f\n\t" /* jump if we weren't granted the lock */
+ "1:\n\t"
+ LOCK_SECTION_START("")
+ "2:\n\t"
+ " pushl %%ecx\n\t"
+ " pushl %%edx\n\t"
+ " call rwsem_down_read_failed\n\t"
+ " popl %%edx\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ LOCK_SECTION_END
+ "# ending down_read\n\t"
+ : "+m"(sem->count)
+ : "a"(sem)
+ : "memory", "cc");
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+ __s32 result, tmp;
+ __asm__ __volatile__(
+ "# beginning __down_read_trylock\n\t"
+ " movl %0,%1\n\t"
+ "1:\n\t"
+ " movl %1,%2\n\t"
+ " addl %3,%2\n\t"
+ " jle 2f\n\t"
+LOCK_PREFIX " cmpxchgl %2,%0\n\t"
+ " jnz 1b\n\t"
+ "2:\n\t"
+ "# ending __down_read_trylock\n\t"
+ : "+m"(sem->count), "=&a"(result), "=&r"(tmp)
+ : "i"(RWSEM_ACTIVE_READ_BIAS)
+ : "memory", "cc");
+ return result>=0 ? 1 : 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+ int tmp;
+
+ tmp = RWSEM_ACTIVE_WRITE_BIAS;
+ __asm__ __volatile__(
+ "# beginning down_write\n\t"
+LOCK_PREFIX " xadd %0,(%%eax)\n\t" /* subtract 0x0000ffff, returns the old value */
+ " testl %0,%0\n\t" /* was the count 0 before? */
+ " jnz 2f\n\t" /* jump if we weren't granted the lock */
+ "1:\n\t"
+ LOCK_SECTION_START("")
+ "2:\n\t"
+ " pushl %%ecx\n\t"
+ " call rwsem_down_write_failed\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ LOCK_SECTION_END
+ "# ending down_write"
+ : "+d"(tmp), "+m"(sem->count)
+ : "a"(sem)
+ : "memory", "cc");
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+ signed long ret = cmpxchg(&sem->count,
+ RWSEM_UNLOCKED_VALUE,
+ RWSEM_ACTIVE_WRITE_BIAS);
+ if (ret == RWSEM_UNLOCKED_VALUE)
+ return 1;
+ return 0;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+ __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
+ __asm__ __volatile__(
+ "# beginning __up_read\n\t"
+LOCK_PREFIX " xadd %%edx,(%%eax)\n\t" /* subtracts 1, returns the old value */
+ " js 2f\n\t" /* jump if the lock is being waited upon */
+ "1:\n\t"
+ LOCK_SECTION_START("")
+ "2:\n\t"
+ " decw %%dx\n\t" /* do nothing if still outstanding active readers */
+ " jnz 1b\n\t"
+ " pushl %%ecx\n\t"
+ " call rwsem_wake\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ LOCK_SECTION_END
+ "# ending __up_read\n"
+ : "+m"(sem->count), "+d"(tmp)
+ : "a"(sem)
+ : "memory", "cc");
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+ __asm__ __volatile__(
+ "# beginning __up_write\n\t"
+ " movl %2,%%edx\n\t"
+LOCK_PREFIX " xaddl %%edx,(%%eax)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */
+ " jnz 2f\n\t" /* jump if the lock is being waited upon */
+ "1:\n\t"
+ LOCK_SECTION_START("")
+ "2:\n\t"
+ " decw %%dx\n\t" /* did the active count reduce to 0? */
+ " jnz 1b\n\t" /* jump back if not */
+ " pushl %%ecx\n\t"
+ " call rwsem_wake\n\t"
+ " popl %%ecx\n\t"
+ " jmp 1b\n"
+ LOCK_SECTION_END
+ "# ending __up_write\n"
+ : "+m"(sem->count)
+ : "a"(sem), "i"(-RWSEM_ACTIVE_WRITE_BIAS)
+ : "memory", "cc", "edx");
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+{
+ __asm__ __volatile__(
+LOCK_PREFIX "addl %1,%0"
+ :"=m"(sem->count)
+ :"ir"(delta), "m"(sem->count));
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+ int tmp = delta;
+
+ __asm__ __volatile__(
+LOCK_PREFIX "xadd %0,(%2)"
+ : "+r"(tmp), "=m"(sem->count)
+ : "r"(sem), "m"(sem->count)
+ : "memory");
+
+ return tmp+delta;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _I386_RWSEM_H */
--- /dev/null
+#ifndef _I386_SCATTERLIST_H
+#define _I386_SCATTERLIST_H
+
+/*
+ * Drivers must set either ->address or (preferred) ->page and ->offset
+ * to indicate where data must be transferred to/from.
+ *
+ * Using ->page is recommended since it handles highmem data as well as
+ * low mem. ->address is restricted to data which has a virtual mapping, and
+ * it will go away in the future. Updating to ->page can be automated very
+ * easily -- something like
+ *
+ * sg->address = some_ptr;
+ *
+ * can be rewritten as
+ *
+ * sg->page = virt_to_page(some_ptr);
+ * sg->offset = (unsigned long) some_ptr & ~PAGE_MASK;
+ *
+ * and that's it. There's no excuse for not highmem enabling YOUR driver. /jens
+ */
+struct scatterlist {
+ char * address; /* Location data is to be transferred to, NULL for
+ * highmem page */
+ struct page * page; /* Location for highmem page, if any */
+ unsigned int offset;/* for highmem, page offset */
+
+ dma_addr_t dma_address;
+ unsigned int length;
+};
+
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+
+#endif /* !(_I386_SCATTERLIST_H) */
--- /dev/null
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+#define __KERNEL_CS 0x11
+#define __KERNEL_DS 0x19
+
+#define __USER_CS 0x23
+#define __USER_DS 0x2B
+
+#endif
--- /dev/null
+#ifndef _I386_SEMAPHORE_H
+#define _I386_SEMAPHORE_H
+
+#include <linux/linkage.h>
+
+#ifdef __KERNEL__
+
+/*
+ * SMP- and interrupt-safe semaphores..
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ *
+ * Modified 1996-12-23 by Dave Grothe <dave@gcom.com> to fix bugs in
+ * the original code and to make semaphore waits
+ * interruptible so that processes waiting on
+ * semaphores can be killed.
+ * Modified 1999-02-14 by Andrea Arcangeli, split the sched.c helper
+ * functions in asm/sempahore-helper.h while fixing a
+ * potential and subtle race discovered by Ulrich Schmid
+ * in down_interruptible(). Since I started to play here I
+ * also implemented the `trylock' semaphore operation.
+ * 1999-07-02 Artur Skawina <skawina@geocities.com>
+ * Optimized "0(ecx)" -> "(ecx)" (the assembler does not
+ * do this). Changed calling sequences from push/jmp to
+ * traditional call/ret.
+ * Modified 2001-01-01 Andreas Franck <afranck@gmx.de>
+ * Some hacks to ensure compatibility with recent
+ * GCC snapshots, to avoid stack corruption when compiling
+ * with -fomit-frame-pointer. It's not sure if this will
+ * be fixed in GCC, as our previous implementation was a
+ * bit dubious.
+ *
+ * If you would like to see an analysis of this implementation, please
+ * ftp to gcom.com and download the file
+ * /pub/linux/src/semaphore/semaphore-2.0.24.tar.gz.
+ *
+ */
+
+#include <asm/system.h>
+#include <asm/atomic.h>
+#include <linux/wait.h>
+#include <linux/rwsem.h>
+
+struct semaphore {
+ atomic_t count;
+ int sleepers;
+ wait_queue_head_t wait;
+#if WAITQUEUE_DEBUG
+ long __magic;
+#endif
+};
+
+#if WAITQUEUE_DEBUG
+# define __SEM_DEBUG_INIT(name) \
+ , (int)&(name).__magic
+#else
+# define __SEM_DEBUG_INIT(name)
+#endif
+
+#define __SEMAPHORE_INITIALIZER(name,count) \
+{ ATOMIC_INIT(count), 0, __WAIT_QUEUE_HEAD_INITIALIZER((name).wait) \
+ __SEM_DEBUG_INIT(name) }
+
+#define __MUTEX_INITIALIZER(name) \
+ __SEMAPHORE_INITIALIZER(name,1)
+
+#define __DECLARE_SEMAPHORE_GENERIC(name,count) \
+ struct semaphore name = __SEMAPHORE_INITIALIZER(name,count)
+
+#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name,1)
+#define DECLARE_MUTEX_LOCKED(name) __DECLARE_SEMAPHORE_GENERIC(name,0)
+
+static inline void sema_init (struct semaphore *sem, int val)
+{
+/*
+ * *sem = (struct semaphore)__SEMAPHORE_INITIALIZER((*sem),val);
+ *
+ * i'd rather use the more flexible initialization above, but sadly
+ * GCC 2.7.2.3 emits a bogus warning. EGCS doesnt. Oh well.
+ */
+ atomic_set(&sem->count, val);
+ sem->sleepers = 0;
+ init_waitqueue_head(&sem->wait);
+#if WAITQUEUE_DEBUG
+ sem->__magic = (int)&sem->__magic;
+#endif
+}
+
+static inline void init_MUTEX (struct semaphore *sem)
+{
+ sema_init(sem, 1);
+}
+
+static inline void init_MUTEX_LOCKED (struct semaphore *sem)
+{
+ sema_init(sem, 0);
+}
+
+asmlinkage void __down_failed(void /* special register calling convention */);
+asmlinkage int __down_failed_interruptible(void /* params in registers */);
+asmlinkage int __down_failed_trylock(void /* params in registers */);
+asmlinkage void __up_wakeup(void /* special register calling convention */);
+
+asmlinkage void __down(struct semaphore * sem);
+asmlinkage int __down_interruptible(struct semaphore * sem);
+asmlinkage int __down_trylock(struct semaphore * sem);
+asmlinkage void __up(struct semaphore * sem);
+
+/*
+ * This is ugly, but we want the default case to fall through.
+ * "__down_failed" is a special asm handler that calls the C
+ * routine that actually waits. See arch/i386/kernel/semaphore.c
+ */
+static inline void down(struct semaphore * sem)
+{
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+
+ __asm__ __volatile__(
+ "# atomic down operation\n\t"
+ LOCK "decl %0\n\t" /* --sem->count */
+ "js 2f\n"
+ "1:\n"
+ LOCK_SECTION_START("")
+ "2:\tcall __down_failed\n\t"
+ "jmp 1b\n"
+ LOCK_SECTION_END
+ :"=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+}
+
+/*
+ * Interruptible try to acquire a semaphore. If we obtained
+ * it, return zero. If we were interrupted, returns -EINTR
+ */
+static inline int down_interruptible(struct semaphore * sem)
+{
+ int result;
+
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+
+ __asm__ __volatile__(
+ "# atomic interruptible down operation\n\t"
+ LOCK "decl %1\n\t" /* --sem->count */
+ "js 2f\n\t"
+ "xorl %0,%0\n"
+ "1:\n"
+ LOCK_SECTION_START("")
+ "2:\tcall __down_failed_interruptible\n\t"
+ "jmp 1b\n"
+ LOCK_SECTION_END
+ :"=a" (result), "=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+ return result;
+}
+
+/*
+ * Non-blockingly attempt to down() a semaphore.
+ * Returns zero if we acquired it
+ */
+static inline int down_trylock(struct semaphore * sem)
+{
+ int result;
+
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+
+ __asm__ __volatile__(
+ "# atomic interruptible down operation\n\t"
+ LOCK "decl %1\n\t" /* --sem->count */
+ "js 2f\n\t"
+ "xorl %0,%0\n"
+ "1:\n"
+ LOCK_SECTION_START("")
+ "2:\tcall __down_failed_trylock\n\t"
+ "jmp 1b\n"
+ LOCK_SECTION_END
+ :"=a" (result), "=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+ return result;
+}
+
+/*
+ * Note! This is subtle. We jump to wake people up only if
+ * the semaphore was negative (== somebody was waiting on it).
+ * The default case (no contention) will result in NO
+ * jumps for both down() and up().
+ */
+static inline void up(struct semaphore * sem)
+{
+#if WAITQUEUE_DEBUG
+ CHECK_MAGIC(sem->__magic);
+#endif
+ __asm__ __volatile__(
+ "# atomic up operation\n\t"
+ LOCK "incl %0\n\t" /* ++sem->count */
+ "jle 2f\n"
+ "1:\n"
+ LOCK_SECTION_START("")
+ "2:\tcall __up_wakeup\n\t"
+ "jmp 1b\n"
+ LOCK_SECTION_END
+ ".subsection 0\n"
+ :"=m" (sem->count)
+ :"c" (sem)
+ :"memory");
+}
+
+static inline int sem_getcount(struct semaphore *sem)
+{
+ return atomic_read(&sem->count);
+}
+
+#endif
+#endif
--- /dev/null
+#ifndef _I386_SEMBUF_H
+#define _I386_SEMBUF_H
+
+/*
+ * The semid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct semid64_ds {
+ struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
+ __kernel_time_t sem_otime; /* last semop time */
+ unsigned long __unused1;
+ __kernel_time_t sem_ctime; /* last change time */
+ unsigned long __unused2;
+ unsigned long sem_nsems; /* no. of semaphores in array */
+ unsigned long __unused3;
+ unsigned long __unused4;
+};
+
+#endif /* _I386_SEMBUF_H */
--- /dev/null
+/*
+ * include/asm-i386/serial.h
+ */
+
+#include <linux/config.h>
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ *
+ * It'd be nice if someone built a serial card with a 24.576 MHz
+ * clock, since the 16550A is capable of handling a top speed of 1.5
+ * megabits/second; but this requires the faster clock.
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+/* Standard COM flags (except for COM4, because of the 8514 problem) */
+#ifdef CONFIG_SERIAL_DETECT_IRQ
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+#else
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
+#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+#endif
+
+#ifdef CONFIG_SERIAL_MANY_PORTS
+#define FOURPORT_FLAGS ASYNC_FOURPORT
+#define ACCENT_FLAGS 0
+#define BOCA_FLAGS 0
+#define HUB6_FLAGS 0
+#define RS_TABLE_SIZE 64
+#else
+#define RS_TABLE_SIZE
+#endif
+
+#define MCA_COM_FLAGS (STD_COM_FLAGS|ASYNC_BOOT_ONLYMCA)
+
+/*
+ * The following define the access methods for the HUB6 card. All
+ * access is through two ports for all 24 possible chips. The card is
+ * selected through the high 2 bits, the port on that card with the
+ * "middle" 3 bits, and the register on that port with the bottom
+ * 3 bits.
+ *
+ * While the access port and interrupt is configurable, the default
+ * port locations are 0x302 for the port control register, and 0x303
+ * for the data read/write register. Normally, the interrupt is at irq3
+ * but can be anything from 3 to 7 inclusive. Note that using 3 will
+ * require disabling com2.
+ */
+
+#define C_P(card,port) (((card)<<6|(port)<<3) + 1)
+
+#define STD_SERIAL_PORT_DEFNS \
+ /* UART CLK PORT IRQ FLAGS */ \
+ { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS }, /* ttyS0 */ \
+ { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS }, /* ttyS1 */ \
+ { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS }, /* ttyS2 */ \
+ { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */
+
+/*
+ * HCDP_SERIAL_PORT_DEFNS should be placed in exactly the same slot
+ * in rs_table as defined by HCDP_SERIAL_CONSOLE_PORT in
+ * include/linux/serial.h
+ */
+#define HCDP_SERIAL_PORT_DEFNS \
+ { 0, BASE_BAUD, -1, 0, STD_COM_FLAGS}, /* ttySx device
+ in comments sucks.
+ You add an entry
+ and you get to edit
+ boatloads of these
+ comments. Not worth
+ it */
+
+
+#ifdef CONFIG_SERIAL_MANY_PORTS
+#define EXTRA_SERIAL_PORT_DEFNS \
+ { 0, BASE_BAUD, 0x1A0, 9, FOURPORT_FLAGS }, /* ttyS4 */ \
+ { 0, BASE_BAUD, 0x1A8, 9, FOURPORT_FLAGS }, /* ttyS5 */ \
+ { 0, BASE_BAUD, 0x1B0, 9, FOURPORT_FLAGS }, /* ttyS6 */ \
+ { 0, BASE_BAUD, 0x1B8, 9, FOURPORT_FLAGS }, /* ttyS7 */ \
+ { 0, BASE_BAUD, 0x2A0, 5, FOURPORT_FLAGS }, /* ttyS8 */ \
+ { 0, BASE_BAUD, 0x2A8, 5, FOURPORT_FLAGS }, /* ttyS9 */ \
+ { 0, BASE_BAUD, 0x2B0, 5, FOURPORT_FLAGS }, /* ttyS10 */ \
+ { 0, BASE_BAUD, 0x2B8, 5, FOURPORT_FLAGS }, /* ttyS11 */ \
+ { 0, BASE_BAUD, 0x330, 4, ACCENT_FLAGS }, /* ttyS12 */ \
+ { 0, BASE_BAUD, 0x338, 4, ACCENT_FLAGS }, /* ttyS13 */ \
+ { 0, BASE_BAUD, 0x000, 0, 0 }, /* ttyS14 (spare) */ \
+ { 0, BASE_BAUD, 0x000, 0, 0 }, /* ttyS15 (spare) */ \
+ { 0, BASE_BAUD, 0x100, 12, BOCA_FLAGS }, /* ttyS16 */ \
+ { 0, BASE_BAUD, 0x108, 12, BOCA_FLAGS }, /* ttyS17 */ \
+ { 0, BASE_BAUD, 0x110, 12, BOCA_FLAGS }, /* ttyS18 */ \
+ { 0, BASE_BAUD, 0x118, 12, BOCA_FLAGS }, /* ttyS19 */ \
+ { 0, BASE_BAUD, 0x120, 12, BOCA_FLAGS }, /* ttyS20 */ \
+ { 0, BASE_BAUD, 0x128, 12, BOCA_FLAGS }, /* ttyS21 */ \
+ { 0, BASE_BAUD, 0x130, 12, BOCA_FLAGS }, /* ttyS22 */ \
+ { 0, BASE_BAUD, 0x138, 12, BOCA_FLAGS }, /* ttyS23 */ \
+ { 0, BASE_BAUD, 0x140, 12, BOCA_FLAGS }, /* ttyS24 */ \
+ { 0, BASE_BAUD, 0x148, 12, BOCA_FLAGS }, /* ttyS25 */ \
+ { 0, BASE_BAUD, 0x150, 12, BOCA_FLAGS }, /* ttyS26 */ \
+ { 0, BASE_BAUD, 0x158, 12, BOCA_FLAGS }, /* ttyS27 */ \
+ { 0, BASE_BAUD, 0x160, 12, BOCA_FLAGS }, /* ttyS28 */ \
+ { 0, BASE_BAUD, 0x168, 12, BOCA_FLAGS }, /* ttyS29 */ \
+ { 0, BASE_BAUD, 0x170, 12, BOCA_FLAGS }, /* ttyS30 */ \
+ { 0, BASE_BAUD, 0x178, 12, BOCA_FLAGS }, /* ttyS31 */
+#else
+#define EXTRA_SERIAL_PORT_DEFNS
+#endif
+
+/* You can have up to four HUB6's in the system, but I've only
+ * included two cards here for a total of twelve ports.
+ */
+#if (defined(CONFIG_HUB6) && defined(CONFIG_SERIAL_MANY_PORTS))
+#define HUB6_SERIAL_PORT_DFNS \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,0) }, /* ttyS32 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,1) }, /* ttyS33 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,2) }, /* ttyS34 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,3) }, /* ttyS35 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,4) }, /* ttyS36 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(0,5) }, /* ttyS37 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,0) }, /* ttyS38 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,1) }, /* ttyS39 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,2) }, /* ttyS40 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,3) }, /* ttyS41 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,4) }, /* ttyS42 */ \
+ { 0, BASE_BAUD, 0x302, 3, HUB6_FLAGS, C_P(1,5) }, /* ttyS43 */
+#else
+#define HUB6_SERIAL_PORT_DFNS
+#endif
+
+#ifdef CONFIG_MCA
+#define MCA_SERIAL_PORT_DFNS \
+ { 0, BASE_BAUD, 0x3220, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x3228, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x4220, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x4228, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x5220, 3, MCA_COM_FLAGS }, \
+ { 0, BASE_BAUD, 0x5228, 3, MCA_COM_FLAGS },
+#else
+#define MCA_SERIAL_PORT_DFNS
+#endif
+
+#define SERIAL_PORT_DFNS \
+ STD_SERIAL_PORT_DEFNS \
+ HCDP_SERIAL_PORT_DEFNS \
+ EXTRA_SERIAL_PORT_DEFNS \
+ HUB6_SERIAL_PORT_DFNS \
+ MCA_SERIAL_PORT_DFNS
+
--- /dev/null
+/*
+ * Just a place holder. We don't want to have to test x86 before
+ * we include stuff
+ */
+
+#ifndef _i386_SETUP_H
+#define _i386_SETUP_H
+
+
+#endif /* _i386_SETUP_H */
--- /dev/null
+#ifndef _I386_SHMBUF_H
+#define _I386_SHMBUF_H
+
+/*
+ * The shmid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct shmid64_ds {
+ struct ipc64_perm shm_perm; /* operation perms */
+ size_t shm_segsz; /* size of segment (bytes) */
+ __kernel_time_t shm_atime; /* last attach time */
+ unsigned long __unused1;
+ __kernel_time_t shm_dtime; /* last detach time */
+ unsigned long __unused2;
+ __kernel_time_t shm_ctime; /* last change time */
+ unsigned long __unused3;
+ __kernel_pid_t shm_cpid; /* pid of creator */
+ __kernel_pid_t shm_lpid; /* pid of last operator */
+ unsigned long shm_nattch; /* no. of current attaches */
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+
+struct shminfo64 {
+ unsigned long shmmax;
+ unsigned long shmmin;
+ unsigned long shmmni;
+ unsigned long shmseg;
+ unsigned long shmall;
+ unsigned long __unused1;
+ unsigned long __unused2;
+ unsigned long __unused3;
+ unsigned long __unused4;
+};
+
+#endif /* _I386_SHMBUF_H */
--- /dev/null
+#ifndef _ASMI386_SHMPARAM_H
+#define _ASMI386_SHMPARAM_H
+
+#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */
+
+#endif /* _ASMI386_SHMPARAM_H */
--- /dev/null
+#ifndef _ASMi386_SIGCONTEXT_H
+#define _ASMi386_SIGCONTEXT_H
+
+/*
+ * As documented in the iBCS2 standard..
+ *
+ * The first part of "struct _fpstate" is just the normal i387
+ * hardware setup, the extra "status" word is used to save the
+ * coprocessor status word before entering the handler.
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * The FPU state data structure has had to grow to accomodate the
+ * extended FPU state required by the Streaming SIMD Extensions.
+ * There is no documented standard to accomplish this at the moment.
+ */
+struct _fpreg {
+ unsigned short significand[4];
+ unsigned short exponent;
+};
+
+struct _fpxreg {
+ unsigned short significand[4];
+ unsigned short exponent;
+ unsigned short padding[3];
+};
+
+struct _xmmreg {
+ unsigned long element[4];
+};
+
+struct _fpstate {
+ /* Regular FPU environment */
+ unsigned long cw;
+ unsigned long sw;
+ unsigned long tag;
+ unsigned long ipoff;
+ unsigned long cssel;
+ unsigned long dataoff;
+ unsigned long datasel;
+ struct _fpreg _st[8];
+ unsigned short status;
+ unsigned short magic; /* 0xffff = regular FPU data only */
+
+ /* FXSR FPU environment */
+ unsigned long _fxsr_env[6]; /* FXSR FPU env is ignored */
+ unsigned long mxcsr;
+ unsigned long reserved;
+ struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */
+ struct _xmmreg _xmm[8];
+ unsigned long padding[56];
+};
+
+#define X86_FXSR_MAGIC 0x0000
+
+struct sigcontext {
+ unsigned short gs, __gsh;
+ unsigned short fs, __fsh;
+ unsigned short es, __esh;
+ unsigned short ds, __dsh;
+ unsigned long edi;
+ unsigned long esi;
+ unsigned long ebp;
+ unsigned long esp;
+ unsigned long ebx;
+ unsigned long edx;
+ unsigned long ecx;
+ unsigned long eax;
+ unsigned long trapno;
+ unsigned long err;
+ unsigned long eip;
+ unsigned short cs, __csh;
+ unsigned long eflags;
+ unsigned long esp_at_signal;
+ unsigned short ss, __ssh;
+ struct _fpstate * fpstate;
+ unsigned long oldmask;
+ unsigned long cr2;
+};
+
+
+#endif
--- /dev/null
+#ifndef _I386_SIGINFO_H
+#define _I386_SIGINFO_H
+
+#include <linux/types.h>
+
+/* XXX: This structure was copied from the Alpha; is there an iBCS version? */
+
+typedef union sigval {
+ int sival_int;
+ void *sival_ptr;
+} sigval_t;
+
+#define SI_MAX_SIZE 128
+#define SI_PAD_SIZE ((SI_MAX_SIZE/sizeof(int)) - 3)
+
+typedef struct siginfo {
+ int si_signo;
+ int si_errno;
+ int si_code;
+
+ union {
+ int _pad[SI_PAD_SIZE];
+
+ /* kill() */
+ struct {
+ pid_t _pid; /* sender's pid */
+ uid_t _uid; /* sender's uid */
+ } _kill;
+
+ /* POSIX.1b timers */
+ struct {
+ unsigned int _timer1;
+ unsigned int _timer2;
+ } _timer;
+
+ /* POSIX.1b signals */
+ struct {
+ pid_t _pid; /* sender's pid */
+ uid_t _uid; /* sender's uid */
+ sigval_t _sigval;
+ } _rt;
+
+ /* SIGCHLD */
+ struct {
+ pid_t _pid; /* which child */
+ uid_t _uid; /* sender's uid */
+ int _status; /* exit code */
+ clock_t _utime;
+ clock_t _stime;
+ } _sigchld;
+
+ /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+ struct {
+ void *_addr; /* faulting insn/memory ref. */
+ } _sigfault;
+
+ /* SIGPOLL */
+ struct {
+ int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
+ int _fd;
+ } _sigpoll;
+ } _sifields;
+} siginfo_t;
+
+/*
+ * How these fields are to be accessed.
+ */
+#define si_pid _sifields._kill._pid
+#define si_uid _sifields._kill._uid
+#define si_status _sifields._sigchld._status
+#define si_utime _sifields._sigchld._utime
+#define si_stime _sifields._sigchld._stime
+#define si_value _sifields._rt._sigval
+#define si_int _sifields._rt._sigval.sival_int
+#define si_ptr _sifields._rt._sigval.sival_ptr
+#define si_addr _sifields._sigfault._addr
+#define si_band _sifields._sigpoll._band
+#define si_fd _sifields._sigpoll._fd
+
+#ifdef __KERNEL__
+#define __SI_MASK 0xffff0000
+#define __SI_KILL (0 << 16)
+#define __SI_TIMER (1 << 16)
+#define __SI_POLL (2 << 16)
+#define __SI_FAULT (3 << 16)
+#define __SI_CHLD (4 << 16)
+#define __SI_RT (5 << 16)
+#define __SI_CODE(T,N) ((T) << 16 | ((N) & 0xffff))
+#else
+#define __SI_KILL 0
+#define __SI_TIMER 0
+#define __SI_POLL 0
+#define __SI_FAULT 0
+#define __SI_CHLD 0
+#define __SI_RT 0
+#define __SI_CODE(T,N) (N)
+#endif
+
+/*
+ * si_code values
+ * Digital reserves positive values for kernel-generated signals.
+ */
+#define SI_USER 0 /* sent by kill, sigsend, raise */
+#define SI_KERNEL 0x80 /* sent by the kernel from somewhere */
+#define SI_QUEUE -1 /* sent by sigqueue */
+#define SI_TIMER __SI_CODE(__SI_TIMER,-2) /* sent by timer expiration */
+#define SI_MESGQ -3 /* sent by real time mesq state change */
+#define SI_ASYNCIO -4 /* sent by AIO completion */
+#define SI_SIGIO -5 /* sent by queued SIGIO */
+#define SI_TKILL -6 /* sent by tkill system call */
+
+#define SI_FROMUSER(siptr) ((siptr)->si_code <= 0)
+#define SI_FROMKERNEL(siptr) ((siptr)->si_code > 0)
+
+/*
+ * SIGILL si_codes
+ */
+#define ILL_ILLOPC (__SI_FAULT|1) /* illegal opcode */
+#define ILL_ILLOPN (__SI_FAULT|2) /* illegal operand */
+#define ILL_ILLADR (__SI_FAULT|3) /* illegal addressing mode */
+#define ILL_ILLTRP (__SI_FAULT|4) /* illegal trap */
+#define ILL_PRVOPC (__SI_FAULT|5) /* privileged opcode */
+#define ILL_PRVREG (__SI_FAULT|6) /* privileged register */
+#define ILL_COPROC (__SI_FAULT|7) /* coprocessor error */
+#define ILL_BADSTK (__SI_FAULT|8) /* internal stack error */
+#define NSIGILL 8
+
+/*
+ * SIGFPE si_codes
+ */
+#define FPE_INTDIV (__SI_FAULT|1) /* integer divide by zero */
+#define FPE_INTOVF (__SI_FAULT|2) /* integer overflow */
+#define FPE_FLTDIV (__SI_FAULT|3) /* floating point divide by zero */
+#define FPE_FLTOVF (__SI_FAULT|4) /* floating point overflow */
+#define FPE_FLTUND (__SI_FAULT|5) /* floating point underflow */
+#define FPE_FLTRES (__SI_FAULT|6) /* floating point inexact result */
+#define FPE_FLTINV (__SI_FAULT|7) /* floating point invalid operation */
+#define FPE_FLTSUB (__SI_FAULT|8) /* subscript out of range */
+#define NSIGFPE 8
+
+/*
+ * SIGSEGV si_codes
+ */
+#define SEGV_MAPERR (__SI_FAULT|1) /* address not mapped to object */
+#define SEGV_ACCERR (__SI_FAULT|2) /* invalid permissions for mapped object */
+#define NSIGSEGV 2
+
+/*
+ * SIGBUS si_codes
+ */
+#define BUS_ADRALN (__SI_FAULT|1) /* invalid address alignment */
+#define BUS_ADRERR (__SI_FAULT|2) /* non-existant physical address */
+#define BUS_OBJERR (__SI_FAULT|3) /* object specific hardware error */
+#define NSIGBUS 3
+
+/*
+ * SIGTRAP si_codes
+ */
+#define TRAP_BRKPT (__SI_FAULT|1) /* process breakpoint */
+#define TRAP_TRACE (__SI_FAULT|2) /* process trace trap */
+#define NSIGTRAP 2
+
+/*
+ * SIGCHLD si_codes
+ */
+#define CLD_EXITED (__SI_CHLD|1) /* child has exited */
+#define CLD_KILLED (__SI_CHLD|2) /* child was killed */
+#define CLD_DUMPED (__SI_CHLD|3) /* child terminated abnormally */
+#define CLD_TRAPPED (__SI_CHLD|4) /* traced child has trapped */
+#define CLD_STOPPED (__SI_CHLD|5) /* child has stopped */
+#define CLD_CONTINUED (__SI_CHLD|6) /* stopped child has continued */
+#define NSIGCHLD 6
+
+/*
+ * SIGPOLL si_codes
+ */
+#define POLL_IN (__SI_POLL|1) /* data input available */
+#define POLL_OUT (__SI_POLL|2) /* output buffers available */
+#define POLL_MSG (__SI_POLL|3) /* input message available */
+#define POLL_ERR (__SI_POLL|4) /* i/o error */
+#define POLL_PRI (__SI_POLL|5) /* high priority input available */
+#define POLL_HUP (__SI_POLL|6) /* device disconnected */
+#define NSIGPOLL 6
+
+/*
+ * sigevent definitions
+ *
+ * It seems likely that SIGEV_THREAD will have to be handled from
+ * userspace, libpthread transmuting it to SIGEV_SIGNAL, which the
+ * thread manager then catches and does the appropriate nonsense.
+ * However, everything is written out here so as to not get lost.
+ */
+#define SIGEV_SIGNAL 0 /* notify via signal */
+#define SIGEV_NONE 1 /* other notification: meaningless */
+#define SIGEV_THREAD 2 /* deliver via thread creation */
+
+#define SIGEV_MAX_SIZE 64
+#define SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3)
+
+typedef struct sigevent {
+ sigval_t sigev_value;
+ int sigev_signo;
+ int sigev_notify;
+ union {
+ int _pad[SIGEV_PAD_SIZE];
+
+ struct {
+ void (*_function)(sigval_t);
+ void *_attribute; /* really pthread_attr_t */
+ } _sigev_thread;
+ } _sigev_un;
+} sigevent_t;
+
+#define sigev_notify_function _sigev_un._sigev_thread._function
+#define sigev_notify_attributes _sigev_un._sigev_thread._attribute
+
+#ifdef __KERNEL__
+#include <linux/string.h>
+
+static inline void copy_siginfo(siginfo_t *to, siginfo_t *from)
+{
+ if (from->si_code < 0)
+ memcpy(to, from, sizeof(siginfo_t));
+ else
+ /* _sigchld is currently the largest know union member */
+ memcpy(to, from, 3*sizeof(int) + sizeof(from->_sifields._sigchld));
+}
+
+extern int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from);
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef _ASMi386_SIGNAL_H
+#define _ASMi386_SIGNAL_H
+
+#include <linux/types.h>
+
+/* Avoid too many header ordering problems. */
+struct siginfo;
+
+#ifdef __KERNEL__
+/* Most things should be clean enough to redefine this at will, if care
+ is taken to make libc match. */
+
+#define _NSIG 64
+#define _NSIG_BPW 32
+#define _NSIG_WORDS (_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t; /* at least 32 bits */
+
+typedef struct {
+ unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+#else
+/* Here we must cater to libcs that poke about in kernel headers. */
+
+#define NSIG 32
+typedef unsigned long sigset_t;
+
+#endif /* __KERNEL__ */
+
+#define SIGHUP 1
+#define SIGINT 2
+#define SIGQUIT 3
+#define SIGILL 4
+#define SIGTRAP 5
+#define SIGABRT 6
+#define SIGIOT 6
+#define SIGBUS 7
+#define SIGFPE 8
+#define SIGKILL 9
+#define SIGUSR1 10
+#define SIGSEGV 11
+#define SIGUSR2 12
+#define SIGPIPE 13
+#define SIGALRM 14
+#define SIGTERM 15
+#define SIGSTKFLT 16
+#define SIGCHLD 17
+#define SIGCONT 18
+#define SIGSTOP 19
+#define SIGTSTP 20
+#define SIGTTIN 21
+#define SIGTTOU 22
+#define SIGURG 23
+#define SIGXCPU 24
+#define SIGXFSZ 25
+#define SIGVTALRM 26
+#define SIGPROF 27
+#define SIGWINCH 28
+#define SIGIO 29
+#define SIGPOLL SIGIO
+/*
+#define SIGLOST 29
+*/
+#define SIGPWR 30
+#define SIGSYS 31
+#define SIGUNUSED 31
+
+/* These should not be considered constants from userland. */
+#define SIGRTMIN 32
+#define SIGRTMAX (_NSIG-1)
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_INTERRUPT is a no-op, but left due to historical reasons. Use the
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_NOCLDSTOP 0x00000001
+#define SA_NOCLDWAIT 0x00000002 /* not supported yet */
+#define SA_SIGINFO 0x00000004
+#define SA_ONSTACK 0x08000000
+#define SA_RESTART 0x10000000
+#define SA_NODEFER 0x40000000
+#define SA_RESETHAND 0x80000000
+
+#define SA_NOMASK SA_NODEFER
+#define SA_ONESHOT SA_RESETHAND
+#define SA_INTERRUPT 0x20000000 /* dummy -- ignored */
+
+#define SA_RESTORER 0x04000000
+
+/*
+ * sigaltstack controls
+ */
+#define SS_ONSTACK 1
+#define SS_DISABLE 2
+
+#define MINSIGSTKSZ 2048
+#define SIGSTKSZ 8192
+
+#ifdef __KERNEL__
+
+/*
+ * These values of sa_flags are used only by the kernel as part of the
+ * irq handling routines.
+ *
+ * SA_INTERRUPT is also used by the irq handling routines.
+ * SA_SHIRQ is for shared interrupt support on PCI and EISA.
+ */
+#define SA_PROBE SA_ONESHOT
+#define SA_SAMPLE_RANDOM SA_RESTART
+#define SA_SHIRQ 0x04000000
+#endif
+
+#define SIG_BLOCK 0 /* for blocking signals */
+#define SIG_UNBLOCK 1 /* for unblocking signals */
+#define SIG_SETMASK 2 /* for setting the signal mask */
+
+/* Type of a signal handler. */
+typedef void (*__sighandler_t)(int);
+
+#define SIG_DFL ((__sighandler_t)0) /* default signal handling */
+#define SIG_IGN ((__sighandler_t)1) /* ignore signal */
+#define SIG_ERR ((__sighandler_t)-1) /* error return from signal */
+
+#ifdef __KERNEL__
+struct old_sigaction {
+ __sighandler_t sa_handler;
+ old_sigset_t sa_mask;
+ unsigned long sa_flags;
+ void (*sa_restorer)(void);
+};
+
+struct sigaction {
+ __sighandler_t sa_handler;
+ unsigned long sa_flags;
+ void (*sa_restorer)(void);
+ sigset_t sa_mask; /* mask last for extensibility */
+};
+
+struct k_sigaction {
+ struct sigaction sa;
+};
+#else
+/* Here we must cater to libcs that poke about in kernel headers. */
+
+struct sigaction {
+ union {
+ __sighandler_t _sa_handler;
+ void (*_sa_sigaction)(int, struct siginfo *, void *);
+ } _u;
+ sigset_t sa_mask;
+ unsigned long sa_flags;
+ void (*sa_restorer)(void);
+};
+
+#define sa_handler _u._sa_handler
+#define sa_sigaction _u._sa_sigaction
+
+#endif /* __KERNEL__ */
+
+typedef struct sigaltstack {
+ void *ss_sp;
+ int ss_flags;
+ size_t ss_size;
+} stack_t;
+
+#ifdef __KERNEL__
+#include <asm/sigcontext.h>
+
+#define __HAVE_ARCH_SIG_BITOPS
+
+static __inline__ void sigaddset(sigset_t *set, int _sig)
+{
+ __asm__("btsl %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static __inline__ void sigdelset(sigset_t *set, int _sig)
+{
+ __asm__("btrl %1,%0" : "=m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static __inline__ int __const_sigismember(sigset_t *set, int _sig)
+{
+ unsigned long sig = _sig - 1;
+ return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
+}
+
+static __inline__ int __gen_sigismember(sigset_t *set, int _sig)
+{
+ int ret;
+ __asm__("btl %2,%1\n\tsbbl %0,%0"
+ : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+ return ret;
+}
+
+#define sigismember(set,sig) \
+ (__builtin_constant_p(sig) ? \
+ __const_sigismember((set),(sig)) : \
+ __gen_sigismember((set),(sig)))
+
+#define sigmask(sig) (1UL << ((sig) - 1))
+
+static __inline__ int sigfindinword(unsigned long word)
+{
+ __asm__("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc");
+ return word;
+}
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifndef __ASSEMBLY__
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/ptrace.h>
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#ifndef __ASSEMBLY__
+#include <asm/bitops.h>
+#include <asm/mpspec.h>
+#ifdef CONFIG_X86_IO_APIC
+#include <asm/io_apic.h>
+#endif
+#include <asm/apic.h>
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+#ifndef __ASSEMBLY__
+
+/*
+ * Private routines/data
+ */
+
+extern void smp_alloc_memory(void);
+extern unsigned long phys_cpu_present_map;
+extern unsigned long cpu_online_map;
+extern volatile unsigned long smp_invalidate_needed;
+extern int pic_mode;
+extern int smp_num_siblings;
+extern int cpu_sibling_map[];
+
+extern void smp_flush_tlb(void);
+extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs);
+extern void smp_send_reschedule(int cpu);
+extern void smp_invalidate_rcv(void); /* Process an NMI */
+extern void (*mtrr_hook) (void);
+extern void zap_low_mappings (void);
+
+/*
+ * On x86 all CPUs are mapped 1:1 to the APIC space.
+ * This simplifies scheduling and IPI sending and
+ * compresses data structures.
+ */
+static inline int cpu_logical_map(int cpu)
+{
+ return cpu;
+}
+static inline int cpu_number_map(int cpu)
+{
+ return cpu;
+}
+
+/*
+ * Some lowlevel functions might want to know about
+ * the real APIC ID <-> CPU # mapping.
+ */
+#define MAX_APICID 256
+extern volatile int cpu_to_physical_apicid[NR_CPUS];
+extern volatile int physical_apicid_to_cpu[MAX_APICID];
+extern volatile int cpu_to_logical_apicid[NR_CPUS];
+extern volatile int logical_apicid_to_cpu[MAX_APICID];
+
+/*
+ * General functions that each host system must provide.
+ */
+
+extern void smp_boot_cpus(void);
+extern void smp_store_cpu_info(int id); /* Store per CPU info (like the initial udelay numbers */
+
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+
+#define smp_processor_id() (current->processor)
+
+#endif /* !__ASSEMBLY__ */
+
+#define NO_PROC_ID 0xFF /* No processor magic marker */
+
+/*
+ * This magic constant controls our willingness to transfer
+ * a process across CPUs. Such a transfer incurs misses on the L1
+ * cache, and on a P6 or P5 with multiple L2 caches L2 hits. My
+ * gut feeling is this will vary by board in value. For a board
+ * with separate L2 cache it probably depends also on the RSS, and
+ * for a board with shared L2 cache it ought to decay fast as other
+ * processes are run.
+ */
+
+#define PROC_CHANGE_PENALTY 15 /* Schedule penalty */
+
+#endif
+#endif
--- /dev/null
+#ifndef __ASM_SMPLOCK_H
+#define __ASM_SMPLOCK_H
+
+/*
+ * <asm/smplock.h>
+ *
+ * i386 SMP lock implementation
+ */
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <asm/current.h>
+
+extern spinlock_cacheline_t kernel_flag_cacheline;
+#define kernel_flag kernel_flag_cacheline.lock
+
+#define kernel_locked() spin_is_locked(&kernel_flag)
+
+/*
+ * Release global kernel lock and global interrupt lock
+ */
+#define release_kernel_lock(task, cpu) \
+do { \
+ if (task->lock_depth >= 0) \
+ spin_unlock(&kernel_flag); \
+ release_irqlock(cpu); \
+ __sti(); \
+} while (0)
+
+/*
+ * Re-acquire the kernel lock
+ */
+#define reacquire_kernel_lock(task) \
+do { \
+ if (task->lock_depth >= 0) \
+ spin_lock(&kernel_flag); \
+} while (0)
+
+
+/*
+ * Getting the big kernel lock.
+ *
+ * This cannot happen asynchronously,
+ * so we only need to worry about other
+ * CPU's.
+ */
+static __inline__ void lock_kernel(void)
+{
+#if 1
+ if (!++current->lock_depth)
+ spin_lock(&kernel_flag);
+#else
+ __asm__ __volatile__(
+ "incl %1\n\t"
+ "jne 9f"
+ spin_lock_string
+ "\n9:"
+ :"=m" (__dummy_lock(&kernel_flag)),
+ "=m" (current->lock_depth));
+#endif
+}
+
+static __inline__ void unlock_kernel(void)
+{
+ if (current->lock_depth < 0)
+ out_of_line_bug();
+#if 1
+ if (--current->lock_depth < 0)
+ spin_unlock(&kernel_flag);
+#else
+ __asm__ __volatile__(
+ "decl %1\n\t"
+ "jns 9f\n\t"
+ spin_unlock_string
+ "\n9:"
+ :"=m" (__dummy_lock(&kernel_flag)),
+ "=m" (current->lock_depth));
+#endif
+}
+
+#endif /* __ASM_SMPLOCK_H */
--- /dev/null
+#ifndef _ASM_SOCKET_H
+#define _ASM_SOCKET_H
+
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET 1
+
+#define SO_DEBUG 1
+#define SO_REUSEADDR 2
+#define SO_TYPE 3
+#define SO_ERROR 4
+#define SO_DONTROUTE 5
+#define SO_BROADCAST 6
+#define SO_SNDBUF 7
+#define SO_RCVBUF 8
+#define SO_KEEPALIVE 9
+#define SO_OOBINLINE 10
+#define SO_NO_CHECK 11
+#define SO_PRIORITY 12
+#define SO_LINGER 13
+#define SO_BSDCOMPAT 14
+/* To add :#define SO_REUSEPORT 15 */
+#define SO_PASSCRED 16
+#define SO_PEERCRED 17
+#define SO_RCVLOWAT 18
+#define SO_SNDLOWAT 19
+#define SO_RCVTIMEO 20
+#define SO_SNDTIMEO 21
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION 22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
+#define SO_SECURITY_ENCRYPTION_NETWORK 24
+
+#define SO_BINDTODEVICE 25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER 26
+#define SO_DETACH_FILTER 27
+
+#define SO_PEERNAME 28
+#define SO_TIMESTAMP 29
+#define SCM_TIMESTAMP SO_TIMESTAMP
+
+#define SO_ACCEPTCONN 30
+
+/* Nasty libc5 fixup - bletch */
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+/* Socket types. */
+#define SOCK_STREAM 1 /* stream (connection) socket */
+#define SOCK_DGRAM 2 /* datagram (conn.less) socket */
+#define SOCK_RAW 3 /* raw socket */
+#define SOCK_RDM 4 /* reliably-delivered message */
+#define SOCK_SEQPACKET 5 /* sequential packet socket */
+#define SOCK_PACKET 10 /* linux specific way of */
+ /* getting packets at the dev */
+ /* level. For writing rarp and */
+ /* other similar things on the */
+ /* user level. */
+#define SOCK_MAX (SOCK_PACKET+1)
+#endif
+
+#endif /* _ASM_SOCKET_H */
--- /dev/null
+#ifndef __ARCH_I386_SOCKIOS__
+#define __ARCH_I386_SOCKIOS__
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN 0x8901
+#define SIOCSPGRP 0x8902
+#define FIOGETOWN 0x8903
+#define SIOCGPGRP 0x8904
+#define SIOCATMARK 0x8905
+#define SIOCGSTAMP 0x8906 /* Get stamp */
+
+#endif
--- /dev/null
+#ifndef __ASM_SOFTIRQ_H
+#define __ASM_SOFTIRQ_H
+
+#include <asm/atomic.h>
+#include <asm/hardirq.h>
+
+#define __cpu_bh_enable(cpu) \
+ do { barrier(); local_bh_count(cpu)--; } while (0)
+#define cpu_bh_disable(cpu) \
+ do { local_bh_count(cpu)++; barrier(); } while (0)
+
+#define local_bh_disable() cpu_bh_disable(smp_processor_id())
+#define __local_bh_enable() __cpu_bh_enable(smp_processor_id())
+
+#define in_softirq() (local_bh_count(smp_processor_id()) != 0)
+
+/*
+ * NOTE: this assembly code assumes:
+ *
+ * (char *)&local_bh_count - 8 == (char *)&softirq_pending
+ *
+ * If you change the offsets in irq_stat then you have to
+ * update this code as well.
+ */
+#define local_bh_enable() \
+do { \
+ unsigned int *ptr = &local_bh_count(smp_processor_id()); \
+ \
+ barrier(); \
+ if (!--*ptr) \
+ __asm__ __volatile__ ( \
+ "cmpl $0, -8(%0);" \
+ "jnz 2f;" \
+ "1:;" \
+ \
+ LOCK_SECTION_START("") \
+ "2: pushl %%eax; pushl %%ecx; pushl %%edx;" \
+ "call %c1;" \
+ "popl %%edx; popl %%ecx; popl %%eax;" \
+ "jmp 1b;" \
+ LOCK_SECTION_END \
+ \
+ : /* no output */ \
+ : "r" (ptr), "i" (do_softirq) \
+ /* no registers clobbered */ ); \
+} while (0)
+
+#endif /* __ASM_SOFTIRQ_H */
--- /dev/null
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <linux/config.h>
+
+extern int printk(const char * fmt, ...)
+ __attribute__ ((format (printf, 1, 2)));
+
+/* It seems that people are forgetting to
+ * initialize their spinlocks properly, tsk tsk.
+ * Remember to turn this off in 2.4. -ben
+ */
+#if defined(CONFIG_DEBUG_SPINLOCK)
+#define SPINLOCK_DEBUG 1
+#else
+#define SPINLOCK_DEBUG 0
+#endif
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ */
+
+typedef struct {
+ volatile unsigned int lock;
+#if SPINLOCK_DEBUG
+ unsigned magic;
+#endif
+} spinlock_t;
+
+#define SPINLOCK_MAGIC 0xdead4ead
+
+#if SPINLOCK_DEBUG
+#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC
+#else
+#define SPINLOCK_MAGIC_INIT /* */
+#endif
+
+#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT }
+
+#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0)
+
+/*
+ * Simple spin lock operations. There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * We make no fairness assumptions. They have a cost.
+ */
+
+#define spin_is_locked(x) (*(volatile signed char *)(&(x)->lock) <= 0)
+#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x))
+
+#define spin_lock_string \
+ "\n1:\t" \
+ "lock ; decb %0\n\t" \
+ "js 2f\n" \
+ LOCK_SECTION_START("") \
+ "2:\t" \
+ "cmpb $0,%0\n\t" \
+ "rep;nop\n\t" \
+ "jle 2b\n\t" \
+ "jmp 1b\n" \
+ LOCK_SECTION_END
+
+/*
+ * This works. Despite all the confusion.
+ * (except on PPro SMP or if we are using OOSTORE)
+ * (PPro errata 66, 92)
+ */
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define spin_unlock_string \
+ "movb $1,%0" \
+ :"=m" (lock->lock) : : "memory"
+
+
+static inline void spin_unlock(spinlock_t *lock)
+{
+#if SPINLOCK_DEBUG
+ if (lock->magic != SPINLOCK_MAGIC)
+ BUG();
+ if (!spin_is_locked(lock))
+ BUG();
+#endif
+ __asm__ __volatile__(
+ spin_unlock_string
+ );
+}
+
+#else
+
+#define spin_unlock_string \
+ "xchgb %b0, %1" \
+ :"=q" (oldval), "=m" (lock->lock) \
+ :"0" (oldval) : "memory"
+
+static inline void spin_unlock(spinlock_t *lock)
+{
+ char oldval = 1;
+#if SPINLOCK_DEBUG
+ if (lock->magic != SPINLOCK_MAGIC)
+ BUG();
+ if (!spin_is_locked(lock))
+ BUG();
+#endif
+ __asm__ __volatile__(
+ spin_unlock_string
+ );
+}
+
+#endif
+
+static inline int spin_trylock(spinlock_t *lock)
+{
+ char oldval;
+ __asm__ __volatile__(
+ "xchgb %b0,%1"
+ :"=q" (oldval), "=m" (lock->lock)
+ :"0" (0) : "memory");
+ return oldval > 0;
+}
+
+static inline void spin_lock(spinlock_t *lock)
+{
+#if SPINLOCK_DEBUG
+ __label__ here;
+here:
+ if (lock->magic != SPINLOCK_MAGIC) {
+printk("eip: %p\n", &&here);
+ BUG();
+ }
+#endif
+ __asm__ __volatile__(
+ spin_lock_string
+ :"=m" (lock->lock) : : "memory");
+}
+
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts
+ * but no interrupt writers. For those circumstances we
+ * can "mix" irq-safe locks - any writer needs to get a
+ * irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ */
+typedef struct {
+ volatile unsigned int lock;
+#if SPINLOCK_DEBUG
+ unsigned magic;
+#endif
+} rwlock_t;
+
+#define RWLOCK_MAGIC 0xdeaf1eed
+
+#if SPINLOCK_DEBUG
+#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC
+#else
+#define RWLOCK_MAGIC_INIT /* */
+#endif
+
+#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT }
+
+#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0)
+
+/*
+ * On x86, we implement read-write locks as a 32-bit counter
+ * with the high bit (sign) being the "contended" bit.
+ *
+ * The inline assembly is non-obvious. Think about it.
+ *
+ * Changed to use the same technique as rw semaphores. See
+ * semaphore.h for details. -ben
+ */
+/* the spinlock helpers are in arch/i386/kernel/semaphore.c */
+
+static inline void read_lock(rwlock_t *rw)
+{
+#if SPINLOCK_DEBUG
+ if (rw->magic != RWLOCK_MAGIC)
+ BUG();
+#endif
+ __build_read_lock(rw, "__read_lock_failed");
+}
+
+static inline void write_lock(rwlock_t *rw)
+{
+#if SPINLOCK_DEBUG
+ if (rw->magic != RWLOCK_MAGIC)
+ BUG();
+#endif
+ __build_write_lock(rw, "__write_lock_failed");
+}
+
+#define read_unlock(rw) asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory")
+#define write_unlock(rw) asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory")
+
+static inline int write_trylock(rwlock_t *lock)
+{
+ atomic_t *count = (atomic_t *)lock;
+ if (atomic_sub_and_test(RW_LOCK_BIAS, count))
+ return 1;
+ atomic_add(RW_LOCK_BIAS, count);
+ return 0;
+}
+
+#endif /* __ASM_SPINLOCK_H */
--- /dev/null
+#ifndef _I386_STAT_H
+#define _I386_STAT_H
+
+struct __old_kernel_stat {
+ unsigned short st_dev;
+ unsigned short st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+ unsigned short st_rdev;
+ unsigned long st_size;
+ unsigned long st_atime;
+ unsigned long st_mtime;
+ unsigned long st_ctime;
+};
+
+struct stat {
+ unsigned short st_dev;
+ unsigned short __pad1;
+ unsigned long st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+ unsigned short st_rdev;
+ unsigned short __pad2;
+ unsigned long st_size;
+ unsigned long st_blksize;
+ unsigned long st_blocks;
+ unsigned long st_atime;
+ unsigned long __unused1;
+ unsigned long st_mtime;
+ unsigned long __unused2;
+ unsigned long st_ctime;
+ unsigned long __unused3;
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+
+/* This matches struct stat64 in glibc2.1, hence the absolutely
+ * insane amounts of padding around dev_t's.
+ */
+struct stat64 {
+ unsigned short st_dev;
+ unsigned char __pad0[10];
+
+#define STAT64_HAS_BROKEN_ST_INO 1
+ unsigned long __st_ino;
+
+ unsigned int st_mode;
+ unsigned int st_nlink;
+
+ unsigned long st_uid;
+ unsigned long st_gid;
+
+ unsigned short st_rdev;
+ unsigned char __pad3[10];
+
+ long long st_size;
+ unsigned long st_blksize;
+
+ unsigned long st_blocks; /* Number 512-byte blocks allocated. */
+ unsigned long __pad4; /* future possible st_blocks high bits */
+
+ unsigned long st_atime;
+ unsigned long __pad5;
+
+ unsigned long st_mtime;
+ unsigned long __pad6;
+
+ unsigned long st_ctime;
+ unsigned long __pad7; /* will be high 32 bits of ctime someday */
+
+ unsigned long long st_ino;
+};
+
+#endif
--- /dev/null
+#ifndef _I386_STATFS_H
+#define _I386_STATFS_H
+
+#ifndef __KERNEL_STRICT_NAMES
+
+#include <linux/types.h>
+
+typedef __kernel_fsid_t fsid_t;
+
+#endif
+
+struct statfs {
+ long f_type;
+ long f_bsize;
+ long f_blocks;
+ long f_bfree;
+ long f_bavail;
+ long f_files;
+ long f_ffree;
+ __kernel_fsid_t f_fsid;
+ long f_namelen;
+ long f_spare[6];
+};
+
+#endif
--- /dev/null
+#ifndef _I386_STRING_I486_H_
+#define _I386_STRING_I486_H_
+
+/*
+ * This string-include defines all string functions as inline
+ * functions. Use gcc. It also assumes ds=es=data space, this should be
+ * normal. Most of the string-functions are rather heavily hand-optimized,
+ * see especially strtok,strstr,str[c]spn. They should work, but are not
+ * very easy to understand. Everything is done entirely within the register
+ * set, making the functions fast and clean.
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Revised and optimized for i486/pentium
+ * 1994/03/15 by Alberto Vignani/Davide Parodi @crf.it
+ *
+ * Split into 2 CPU specific files by Alan Cox to keep #ifdef noise down.
+ *
+ * 1999/10/5 Proper register args for newer GCCs and minor bugs
+ * fixed - Petko Manolov (petkan@spct.net)
+ * 1999/10/14 3DNow memscpy() added - Petkan
+ * 2000/05/09 extern changed to static in function definitions
+ * and a few cleanups - Petkan
+ */
+
+#define __HAVE_ARCH_STRCPY
+static inline char * strcpy(char * dest,const char *src)
+{
+register char *tmp= (char *)dest;
+register char dummy;
+__asm__ __volatile__(
+ "\n1:\t"
+ "movb (%0),%2\n\t"
+ "incl %0\n\t"
+ "movb %2,(%1)\n\t"
+ "incl %1\n\t"
+ "testb %2,%2\n\t"
+ "jne 1b"
+ :"=r" (src), "=r" (tmp), "=q" (dummy)
+ :"0" (src), "1" (tmp)
+ :"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCPY
+static inline char * strncpy(char * dest,const char *src,size_t count)
+{
+register char *tmp= (char *)dest;
+register char dummy;
+if (count) {
+__asm__ __volatile__(
+ "\n1:\t"
+ "movb (%0),%2\n\t"
+ "incl %0\n\t"
+ "movb %2,(%1)\n\t"
+ "incl %1\n\t"
+ "decl %3\n\t"
+ "je 3f\n\t"
+ "testb %2,%2\n\t"
+ "jne 1b\n\t"
+ "2:\tmovb %2,(%1)\n\t"
+ "incl %1\n\t"
+ "decl %3\n\t"
+ "jne 2b\n\t"
+ "3:"
+ :"=r" (src), "=r" (tmp), "=q" (dummy), "=r" (count)
+ :"0" (src), "1" (tmp), "3" (count)
+ :"memory");
+ } /* if (count) */
+return dest;
+}
+
+#define __HAVE_ARCH_STRCAT
+static inline char * strcat(char * dest,const char * src)
+{
+register char *tmp = (char *)(dest-1);
+register char dummy;
+__asm__ __volatile__(
+ "\n1:\tincl %1\n\t"
+ "cmpb $0,(%1)\n\t"
+ "jne 1b\n"
+ "2:\tmovb (%2),%b0\n\t"
+ "incl %2\n\t"
+ "movb %b0,(%1)\n\t"
+ "incl %1\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 2b\n"
+ :"=q" (dummy), "=r" (tmp), "=r" (src)
+ :"1" (tmp), "2" (src)
+ :"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCAT
+static inline char * strncat(char * dest,const char * src,size_t count)
+{
+register char *tmp = (char *)(dest-1);
+register char dummy;
+__asm__ __volatile__(
+ "\n1:\tincl %1\n\t"
+ "cmpb $0,(%1)\n\t"
+ "jne 1b\n"
+ "2:\tdecl %3\n\t"
+ "js 3f\n\t"
+ "movb (%2),%b0\n\t"
+ "incl %2\n\t"
+ "movb %b0,(%1)\n\t"
+ "incl %1\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 2b\n"
+ "3:\txorb %0,%0\n\t"
+ "movb %b0,(%1)\n\t"
+ :"=q" (dummy), "=r" (tmp), "=r" (src), "=r" (count)
+ :"1" (tmp), "2" (src), "3" (count)
+ :"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRCMP
+static inline int strcmp(const char * cs,const char * ct)
+{
+register int __res;
+__asm__ __volatile__(
+ "\n1:\tmovb (%1),%b0\n\t"
+ "incl %1\n\t"
+ "cmpb %b0,(%2)\n\t"
+ "jne 2f\n\t"
+ "incl %2\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 1b\n\t"
+ "xorl %0,%0\n\t"
+ "jmp 3f\n"
+ "2:\tmovl $1,%0\n\t"
+ "jb 3f\n\t"
+ "negl %0\n"
+ "3:"
+ :"=q" (__res), "=r" (cs), "=r" (ct)
+ :"1" (cs), "2" (ct)
+ : "memory" );
+return __res;
+}
+
+#define __HAVE_ARCH_STRNCMP
+static inline int strncmp(const char * cs,const char * ct,size_t count)
+{
+register int __res;
+__asm__ __volatile__(
+ "\n1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "movb (%1),%b0\n\t"
+ "incl %1\n\t"
+ "cmpb %b0,(%2)\n\t"
+ "jne 3f\n\t"
+ "incl %2\n\t"
+ "testb %b0,%b0\n\t"
+ "jne 1b\n"
+ "2:\txorl %0,%0\n\t"
+ "jmp 4f\n"
+ "3:\tmovl $1,%0\n\t"
+ "jb 4f\n\t"
+ "negl %0\n"
+ "4:"
+ :"=q" (__res), "=r" (cs), "=r" (ct), "=r" (count)
+ :"1" (cs), "2" (ct), "3" (count));
+return __res;
+}
+
+#define __HAVE_ARCH_STRCHR
+static inline char * strchr(const char * s, int c)
+{
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tmovb (%1),%%al\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "je 2f\n\t"
+ "incl %1\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "xorl %1,%1\n"
+ "2:\tmovl %1,%0\n\t"
+ :"=a" (__res), "=r" (s)
+ :"0" (c), "1" (s));
+return __res;
+}
+
+#define __HAVE_ARCH_STRRCHR
+static inline char * strrchr(const char * s, int c)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "jne 2f\n\t"
+ "leal -1(%%esi),%0\n"
+ "2:\ttestb %%al,%%al\n\t"
+ "jne 1b"
+ :"=d" (__res), "=&S" (d0), "=&a" (d1)
+ :"0" (0), "1" (s), "2" (c));
+return __res;
+}
+
+
+#define __HAVE_ARCH_STRCSPN
+static inline size_t strcspn(const char * cs, const char * ct)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movl %6,%%edi\n\t"
+ "repne\n\t"
+ "scasb\n\t"
+ "notl %%ecx\n\t"
+ "decl %%ecx\n\t"
+ "movl %%ecx,%%edx\n"
+ "1:\tlodsb\n\t"
+ "testb %%al,%%al\n\t"
+ "je 2f\n\t"
+ "movl %6,%%edi\n\t"
+ "movl %%edx,%%ecx\n\t"
+ "repne\n\t"
+ "scasb\n\t"
+ "jne 1b\n"
+ "2:\tdecl %0"
+ :"=S" (__res), "=&a" (d0), "=&c" (d1)
+ :"0" (cs), "1" (0), "2" (0xffffffff), "g" (ct)
+ :"dx", "di");
+return __res-cs;
+}
+
+
+#define __HAVE_ARCH_STRLEN
+static inline size_t strlen(const char * s)
+{
+/*
+ * slightly slower on a 486, but with better chances of
+ * register allocation
+ */
+register char dummy, *tmp= (char *)s;
+__asm__ __volatile__(
+ "\n1:\t"
+ "movb\t(%0),%1\n\t"
+ "incl\t%0\n\t"
+ "testb\t%1,%1\n\t"
+ "jne\t1b"
+ :"=r" (tmp),"=q" (dummy)
+ :"0" (s)
+ : "memory" );
+return (tmp-s-1);
+}
+
+/* Added by Gertjan van Wingerde to make minix and sysv module work */
+#define __HAVE_ARCH_STRNLEN
+static inline size_t strnlen(const char * s, size_t count)
+{
+int d0;
+register int __res;
+__asm__ __volatile__(
+ "movl %3,%0\n\t"
+ "jmp 2f\n"
+ "1:\tcmpb $0,(%0)\n\t"
+ "je 3f\n\t"
+ "incl %0\n"
+ "2:\tdecl %2\n\t"
+ "cmpl $-1,%2\n\t"
+ "jne 1b\n"
+ "3:\tsubl %3,%0"
+ :"=a" (__res), "=&d" (d0)
+ :"1" (count), "c" (s));
+return __res;
+}
+/* end of additional stuff */
+
+
+/*
+ * These ought to get tweaked to do some cache priming.
+ */
+
+static inline void * __memcpy_by4(void * to, const void * from, size_t n)
+{
+register void *tmp = (void *)to;
+register int dummy1,dummy2;
+__asm__ __volatile__ (
+ "\n1:\tmovl (%2),%0\n\t"
+ "addl $4,%2\n\t"
+ "movl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %3\n\t"
+ "jnz 1b"
+ :"=r" (dummy1), "=r" (tmp), "=r" (from), "=r" (dummy2)
+ :"1" (tmp), "2" (from), "3" (n/4)
+ :"memory");
+return (to);
+}
+
+static inline void * __memcpy_by2(void * to, const void * from, size_t n)
+{
+register void *tmp = (void *)to;
+register int dummy1,dummy2;
+__asm__ __volatile__ (
+ "shrl $1,%3\n\t"
+ "jz 2f\n" /* only a word */
+ "1:\tmovl (%2),%0\n\t"
+ "addl $4,%2\n\t"
+ "movl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %3\n\t"
+ "jnz 1b\n"
+ "2:\tmovw (%2),%w0\n\t"
+ "movw %w0,(%1)"
+ :"=r" (dummy1), "=r" (tmp), "=r" (from), "=r" (dummy2)
+ :"1" (tmp), "2" (from), "3" (n/2)
+ :"memory");
+return (to);
+}
+
+static inline void * __memcpy_g(void * to, const void * from, size_t n)
+{
+int d0, d1, d2;
+register void *tmp = (void *)to;
+__asm__ __volatile__ (
+ "shrl $1,%%ecx\n\t"
+ "jnc 1f\n\t"
+ "movsb\n"
+ "1:\tshrl $1,%%ecx\n\t"
+ "jnc 2f\n\t"
+ "movsw\n"
+ "2:\trep\n\t"
+ "movsl"
+ :"=&c" (d0), "=&D" (d1), "=&S" (d2)
+ :"0" (n), "1" ((long) tmp), "2" ((long) from)
+ :"memory");
+return (to);
+}
+
+#define __memcpy_c(d,s,count) \
+((count%4==0) ? \
+ __memcpy_by4((d),(s),(count)) : \
+ ((count%2==0) ? \
+ __memcpy_by2((d),(s),(count)) : \
+ __memcpy_g((d),(s),(count))))
+
+#define __memcpy(d,s,count) \
+(__builtin_constant_p(count) ? \
+ __memcpy_c((d),(s),(count)) : \
+ __memcpy_g((d),(s),(count)))
+
+#define __HAVE_ARCH_MEMCPY
+
+#include <linux/config.h>
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+/*
+** This CPU favours 3DNow strongly (eg AMD K6-II, K6-III, Athlon)
+*/
+
+static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+{
+ if (len < 512)
+ return __memcpy_c(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+static inline void *__memcpy3d(void *to, const void *from, size_t len)
+{
+ if(len < 512)
+ return __memcpy_g(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+#define memcpy(d, s, count) \
+(__builtin_constant_p(count) ? \
+ __constant_memcpy3d((d),(s),(count)) : \
+ __memcpy3d((d),(s),(count)))
+
+#else /* CONFIG_X86_USE_3DNOW */
+
+/*
+** Generic routines
+*/
+
+
+#define memcpy(d, s, count) __memcpy(d, s, count)
+
+#endif /* CONFIG_X86_USE_3DNOW */
+
+
+extern void __struct_cpy_bug( void );
+
+#define struct_cpy(x,y) \
+({ \
+ if (sizeof(*(x)) != sizeof(*(y))) \
+ __struct_cpy_bug; \
+ memcpy(x, y, sizeof(*(x))); \
+})
+
+
+#define __HAVE_ARCH_MEMMOVE
+static inline void * memmove(void * dest,const void * src, size_t n)
+{
+int d0, d1, d2;
+register void *tmp = (void *)dest;
+if (dest<src)
+__asm__ __volatile__ (
+ "rep\n\t"
+ "movsb"
+ :"=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n), "1" (src), "2" (tmp)
+ :"memory");
+else
+__asm__ __volatile__ (
+ "std\n\t"
+ "rep\n\t"
+ "movsb\n\t"
+ "cld"
+ :"=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n), "1" (n-1+(const char *)src), "2" (n-1+(char *)tmp)
+ :"memory");
+return dest;
+}
+
+
+#define __HAVE_ARCH_MEMCMP
+static inline int memcmp(const void * cs,const void * ct,size_t count)
+{
+int d0, d1, d2;
+register int __res;
+__asm__ __volatile__(
+ "repe\n\t"
+ "cmpsb\n\t"
+ "je 1f\n\t"
+ "sbbl %0,%0\n\t"
+ "orb $1,%b0\n"
+ "1:"
+ :"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+ :"0" (0), "1" (cs), "2" (ct), "3" (count));
+return __res;
+}
+
+
+#define __HAVE_ARCH_MEMCHR
+static inline void * memchr(const void * cs,int c,size_t count)
+{
+int d0;
+register void * __res;
+if (!count)
+ return NULL;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "je 1f\n\t"
+ "movl $1,%0\n"
+ "1:\tdecl %0"
+ :"=D" (__res), "=&c" (d0)
+ :"a" (c), "0" (cs), "1" (count));
+return __res;
+}
+
+#define __memset_cc(s,c,count) \
+((count%4==0) ? \
+ __memset_cc_by4((s),(c),(count)) : \
+ ((count%2==0) ? \
+ __memset_cc_by2((s),(c),(count)) : \
+ __memset_cg((s),(c),(count))))
+
+#define __memset_gc(s,c,count) \
+((count%4==0) ? \
+ __memset_gc_by4((s),(c),(count)) : \
+ ((count%2==0) ? \
+ __memset_gc_by2((s),(c),(count)) : \
+ __memset_gg((s),(c),(count))))
+
+#define __HAVE_ARCH_MEMSET
+#define memset(s,c,count) \
+(__builtin_constant_p(c) ? \
+ (__builtin_constant_p(count) ? \
+ __memset_cc((s),(c),(count)) : \
+ __memset_cg((s),(c),(count))) : \
+ (__builtin_constant_p(count) ? \
+ __memset_gc((s),(c),(count)) : \
+ __memset_gg((s),(c),(count))))
+
+static inline void * __memset_cc_by4(void * s, char c, size_t count)
+{
+/*
+ * register char *tmp = s;
+ */
+register char *tmp = (char *)s;
+register int dummy;
+__asm__ __volatile__ (
+ "\n1:\tmovl %2,(%0)\n\t"
+ "addl $4,%0\n\t"
+ "decl %1\n\t"
+ "jnz 1b"
+ :"=r" (tmp), "=r" (dummy)
+ :"q" (0x01010101UL * (unsigned char) c), "0" (tmp), "1" (count/4)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_cc_by2(void * s, char c, size_t count)
+{
+register void *tmp = (void *)s;
+register int dummy;
+__asm__ __volatile__ (
+ "shrl $1,%1\n\t" /* may be divisible also by 4 */
+ "jz 2f\n"
+ "\n1:\tmovl %2,(%0)\n\t"
+ "addl $4,%0\n\t"
+ "decl %1\n\t"
+ "jnz 1b\n"
+ "2:\tmovw %w2,(%0)"
+ :"=r" (tmp), "=r" (dummy)
+ :"q" (0x01010101UL * (unsigned char) c), "0" (tmp), "1" (count/2)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_gc_by4(void * s, char c, size_t count)
+{
+register void *tmp = (void *)s;
+register int dummy;
+__asm__ __volatile__ (
+ "movb %b0,%h0\n"
+ "pushw %w0\n\t"
+ "shll $16,%0\n\t"
+ "popw %w0\n"
+ "1:\tmovl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %2\n\t"
+ "jnz 1b\n"
+ :"=q" (c), "=r" (tmp), "=r" (dummy)
+ :"0" ((unsigned) c), "1" (tmp), "2" (count/4)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_gc_by2(void * s, char c, size_t count)
+{
+register void *tmp = (void *)s;
+register int dummy1,dummy2;
+__asm__ __volatile__ (
+ "movb %b0,%h0\n\t"
+ "shrl $1,%2\n\t" /* may be divisible also by 4 */
+ "jz 2f\n\t"
+ "pushw %w0\n\t"
+ "shll $16,%0\n\t"
+ "popw %w0\n"
+ "1:\tmovl %0,(%1)\n\t"
+ "addl $4,%1\n\t"
+ "decl %2\n\t"
+ "jnz 1b\n"
+ "2:\tmovw %w0,(%1)"
+ :"=q" (dummy1), "=r" (tmp), "=r" (dummy2)
+ :"0" ((unsigned) c), "1" (tmp), "2" (count/2)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_cg(void * s, char c, size_t count)
+{
+int d0, d1;
+register void *tmp = (void *)s;
+__asm__ __volatile__ (
+ "shrl $1,%%ecx\n\t"
+ "rep\n\t"
+ "stosw\n\t"
+ "jnc 1f\n\t"
+ "movb %%al,(%%edi)\n"
+ "1:"
+ :"=&c" (d0), "=&D" (d1)
+ :"a" (0x0101U * (unsigned char) c), "0" (count), "1" (tmp)
+ :"memory");
+return s;
+}
+
+static inline void * __memset_gg(void * s,char c,size_t count)
+{
+int d0, d1, d2;
+register void *tmp = (void *)s;
+__asm__ __volatile__ (
+ "movb %%al,%%ah\n\t"
+ "shrl $1,%%ecx\n\t"
+ "rep\n\t"
+ "stosw\n\t"
+ "jnc 1f\n\t"
+ "movb %%al,(%%edi)\n"
+ "1:"
+ :"=&c" (d0), "=&D" (d1), "=&D" (d2)
+ :"0" (count), "1" (tmp), "2" (c)
+ :"memory");
+return s;
+}
+
+
+/*
+ * find the first occurrence of byte 'c', or 1 past the area if none
+ */
+#define __HAVE_ARCH_MEMSCAN
+static inline void * memscan(void * addr, int c, size_t size)
+{
+ if (!size)
+ return addr;
+ __asm__("repnz; scasb
+ jnz 1f
+ dec %%edi
+1: "
+ : "=D" (addr), "=c" (size)
+ : "0" (addr), "1" (size), "a" (c));
+ return addr;
+}
+
+#endif
--- /dev/null
+#ifndef _I386_STRING_H_
+#define _I386_STRING_H_
+
+#ifdef __KERNEL__
+#include <linux/config.h>
+/*
+ * On a 486 or Pentium, we are better off not using the
+ * byte string operations. But on a 386 or a PPro the
+ * byte string ops are faster than doing it by hand
+ * (MUCH faster on a Pentium).
+ *
+ * Also, the byte strings actually work correctly. Forget
+ * the i486 routines for now as they may be broken..
+ */
+#if FIXED_486_STRING && defined(CONFIG_X86_USE_STRING_486)
+#include <asm/string-486.h>
+#else
+
+/*
+ * This string-include defines all string functions as inline
+ * functions. Use gcc. It also assumes ds=es=data space, this should be
+ * normal. Most of the string-functions are rather heavily hand-optimized,
+ * see especially strtok,strstr,str[c]spn. They should work, but are not
+ * very easy to understand. Everything is done entirely within the register
+ * set, making the functions fast and clean. String instructions have been
+ * used through-out, making for "slightly" unclear code :-)
+ *
+ * NO Copyright (C) 1991, 1992 Linus Torvalds,
+ * consider these trivial functions to be PD.
+ */
+
+#define __HAVE_ARCH_STRCPY
+static inline char * strcpy(char * dest,const char *src)
+{
+int d0, d1, d2;
+__asm__ __volatile__(
+ "1:\tlodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2)
+ :"0" (src),"1" (dest) : "memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCPY
+static inline char * strncpy(char * dest,const char *src,size_t count)
+{
+int d0, d1, d2, d3;
+__asm__ __volatile__(
+ "1:\tdecl %2\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "rep\n\t"
+ "stosb\n"
+ "2:"
+ : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
+ :"0" (src),"1" (dest),"2" (count) : "memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRCAT
+static inline char * strcat(char * dest,const char * src)
+{
+int d0, d1, d2, d3;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "decl %1\n"
+ "1:\tlodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+ : "0" (src), "1" (dest), "2" (0), "3" (0xffffffff):"memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRNCAT
+static inline char * strncat(char * dest,const char * src,size_t count)
+{
+int d0, d1, d2, d3;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "decl %1\n\t"
+ "movl %8,%3\n"
+ "1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n"
+ "2:\txorl %2,%2\n\t"
+ "stosb"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+ : "0" (src),"1" (dest),"2" (0),"3" (0xffffffff), "g" (count)
+ : "memory");
+return dest;
+}
+
+#define __HAVE_ARCH_STRCMP
+static inline int strcmp(const char * cs,const char * ct)
+{
+int d0, d1;
+register int __res;
+__asm__ __volatile__(
+ "1:\tlodsb\n\t"
+ "scasb\n\t"
+ "jne 2f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "xorl %%eax,%%eax\n\t"
+ "jmp 3f\n"
+ "2:\tsbbl %%eax,%%eax\n\t"
+ "orb $1,%%al\n"
+ "3:"
+ :"=a" (__res), "=&S" (d0), "=&D" (d1)
+ :"1" (cs),"2" (ct));
+return __res;
+}
+
+#define __HAVE_ARCH_STRNCMP
+static inline int strncmp(const char * cs,const char * ct,size_t count)
+{
+register int __res;
+int d0, d1, d2;
+__asm__ __volatile__(
+ "1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "scasb\n\t"
+ "jne 3f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n"
+ "2:\txorl %%eax,%%eax\n\t"
+ "jmp 4f\n"
+ "3:\tsbbl %%eax,%%eax\n\t"
+ "orb $1,%%al\n"
+ "4:"
+ :"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+ :"1" (cs),"2" (ct),"3" (count));
+return __res;
+}
+
+#define __HAVE_ARCH_STRCHR
+static inline char * strchr(const char * s, int c)
+{
+int d0;
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "je 2f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "movl $1,%1\n"
+ "2:\tmovl %1,%0\n\t"
+ "decl %0"
+ :"=a" (__res), "=&S" (d0) : "1" (s),"0" (c));
+return __res;
+}
+
+#define __HAVE_ARCH_STRRCHR
+static inline char * strrchr(const char * s, int c)
+{
+int d0, d1;
+register char * __res;
+__asm__ __volatile__(
+ "movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "jne 2f\n\t"
+ "leal -1(%%esi),%0\n"
+ "2:\ttestb %%al,%%al\n\t"
+ "jne 1b"
+ :"=g" (__res), "=&S" (d0), "=&a" (d1) :"0" (0),"1" (s),"2" (c));
+return __res;
+}
+
+#define __HAVE_ARCH_STRLEN
+static inline size_t strlen(const char * s)
+{
+int d0;
+register int __res;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "notl %0\n\t"
+ "decl %0"
+ :"=c" (__res), "=&D" (d0) :"1" (s),"a" (0), "0" (0xffffffff));
+return __res;
+}
+
+static inline void * __memcpy(void * to, const void * from, size_t n)
+{
+int d0, d1, d2;
+__asm__ __volatile__(
+ "rep ; movsl\n\t"
+ "testb $2,%b4\n\t"
+ "je 1f\n\t"
+ "movsw\n"
+ "1:\ttestb $1,%b4\n\t"
+ "je 2f\n\t"
+ "movsb\n"
+ "2:"
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+ :"0" (n/4), "q" (n),"1" ((long) to),"2" ((long) from)
+ : "memory");
+return (to);
+}
+
+/*
+ * This looks horribly ugly, but the compiler can optimize it totally,
+ * as the count is constant.
+ */
+static inline void * __constant_memcpy(void * to, const void * from, size_t n)
+{
+ switch (n) {
+ case 0:
+ return to;
+ case 1:
+ *(unsigned char *)to = *(const unsigned char *)from;
+ return to;
+ case 2:
+ *(unsigned short *)to = *(const unsigned short *)from;
+ return to;
+ case 3:
+ *(unsigned short *)to = *(const unsigned short *)from;
+ *(2+(unsigned char *)to) = *(2+(const unsigned char *)from);
+ return to;
+ case 4:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ return to;
+ case 6: /* for Ethernet addresses */
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(2+(unsigned short *)to) = *(2+(const unsigned short *)from);
+ return to;
+ case 8:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ return to;
+ case 12:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
+ return to;
+ case 16:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
+ *(3+(unsigned long *)to) = *(3+(const unsigned long *)from);
+ return to;
+ case 20:
+ *(unsigned long *)to = *(const unsigned long *)from;
+ *(1+(unsigned long *)to) = *(1+(const unsigned long *)from);
+ *(2+(unsigned long *)to) = *(2+(const unsigned long *)from);
+ *(3+(unsigned long *)to) = *(3+(const unsigned long *)from);
+ *(4+(unsigned long *)to) = *(4+(const unsigned long *)from);
+ return to;
+ }
+#define COMMON(x) \
+__asm__ __volatile__( \
+ "rep ; movsl" \
+ x \
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2) \
+ : "0" (n/4),"1" ((long) to),"2" ((long) from) \
+ : "memory");
+{
+ int d0, d1, d2;
+ switch (n % 4) {
+ case 0: COMMON(""); return to;
+ case 1: COMMON("\n\tmovsb"); return to;
+ case 2: COMMON("\n\tmovsw"); return to;
+ default: COMMON("\n\tmovsw\n\tmovsb"); return to;
+ }
+}
+
+#undef COMMON
+}
+
+#define __HAVE_ARCH_MEMCPY
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+/*
+ * This CPU favours 3DNow strongly (eg AMD Athlon)
+ */
+
+static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+{
+ if (len < 512)
+ return __constant_memcpy(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
+{
+ if (len < 512)
+ return __memcpy(to, from, len);
+ return _mmx_memcpy(to, from, len);
+}
+
+#define memcpy(t, f, n) \
+(__builtin_constant_p(n) ? \
+ __constant_memcpy3d((t),(f),(n)) : \
+ __memcpy3d((t),(f),(n)))
+
+#else
+
+/*
+ * No 3D Now!
+ */
+
+#define memcpy(t, f, n) \
+(__builtin_constant_p(n) ? \
+ __constant_memcpy((t),(f),(n)) : \
+ __memcpy((t),(f),(n)))
+
+#endif
+
+/*
+ * struct_cpy(x,y), copy structure *x into (matching structure) *y.
+ *
+ * We get link-time errors if the structure sizes do not match.
+ * There is no runtime overhead, it's all optimized away at
+ * compile time.
+ */
+extern void __struct_cpy_bug (void);
+
+#define struct_cpy(x,y) \
+({ \
+ if (sizeof(*(x)) != sizeof(*(y))) \
+ __struct_cpy_bug; \
+ memcpy(x, y, sizeof(*(x))); \
+})
+
+#define __HAVE_ARCH_MEMMOVE
+static inline void * memmove(void * dest,const void * src, size_t n)
+{
+int d0, d1, d2;
+if (dest<src)
+__asm__ __volatile__(
+ "rep\n\t"
+ "movsb"
+ : "=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n),"1" (src),"2" (dest)
+ : "memory");
+else
+__asm__ __volatile__(
+ "std\n\t"
+ "rep\n\t"
+ "movsb\n\t"
+ "cld"
+ : "=&c" (d0), "=&S" (d1), "=&D" (d2)
+ :"0" (n),
+ "1" (n-1+(const char *)src),
+ "2" (n-1+(char *)dest)
+ :"memory");
+return dest;
+}
+
+#define memcmp __builtin_memcmp
+
+#define __HAVE_ARCH_MEMCHR
+static inline void * memchr(const void * cs,int c,size_t count)
+{
+int d0;
+register void * __res;
+if (!count)
+ return NULL;
+__asm__ __volatile__(
+ "repne\n\t"
+ "scasb\n\t"
+ "je 1f\n\t"
+ "movl $1,%0\n"
+ "1:\tdecl %0"
+ :"=D" (__res), "=&c" (d0) : "a" (c),"0" (cs),"1" (count));
+return __res;
+}
+
+static inline void * __memset_generic(void * s, char c,size_t count)
+{
+int d0, d1;
+__asm__ __volatile__(
+ "rep\n\t"
+ "stosb"
+ : "=&c" (d0), "=&D" (d1)
+ :"a" (c),"1" (s),"0" (count)
+ :"memory");
+return s;
+}
+
+/* we might want to write optimized versions of these later */
+#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
+
+/*
+ * memset(x,0,y) is a reasonably common thing to do, so we want to fill
+ * things 32 bits at a time even when we don't know the size of the
+ * area at compile-time..
+ */
+static inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
+{
+int d0, d1;
+__asm__ __volatile__(
+ "rep ; stosl\n\t"
+ "testb $2,%b3\n\t"
+ "je 1f\n\t"
+ "stosw\n"
+ "1:\ttestb $1,%b3\n\t"
+ "je 2f\n\t"
+ "stosb\n"
+ "2:"
+ : "=&c" (d0), "=&D" (d1)
+ :"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
+ :"memory");
+return (s);
+}
+
+/* Added by Gertjan van Wingerde to make minix and sysv module work */
+#define __HAVE_ARCH_STRNLEN
+static inline size_t strnlen(const char * s, size_t count)
+{
+int d0;
+register int __res;
+__asm__ __volatile__(
+ "movl %2,%0\n\t"
+ "jmp 2f\n"
+ "1:\tcmpb $0,(%0)\n\t"
+ "je 3f\n\t"
+ "incl %0\n"
+ "2:\tdecl %1\n\t"
+ "cmpl $-1,%1\n\t"
+ "jne 1b\n"
+ "3:\tsubl %2,%0"
+ :"=a" (__res), "=&d" (d0)
+ :"c" (s),"1" (count));
+return __res;
+}
+/* end of additional stuff */
+
+#define __HAVE_ARCH_STRSTR
+
+extern char *strstr(const char *cs, const char *ct);
+
+/*
+ * This looks horribly ugly, but the compiler can optimize it totally,
+ * as we by now know that both pattern and count is constant..
+ */
+static inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
+{
+ switch (count) {
+ case 0:
+ return s;
+ case 1:
+ *(unsigned char *)s = pattern;
+ return s;
+ case 2:
+ *(unsigned short *)s = pattern;
+ return s;
+ case 3:
+ *(unsigned short *)s = pattern;
+ *(2+(unsigned char *)s) = pattern;
+ return s;
+ case 4:
+ *(unsigned long *)s = pattern;
+ return s;
+ }
+#define COMMON(x) \
+__asm__ __volatile__( \
+ "rep ; stosl" \
+ x \
+ : "=&c" (d0), "=&D" (d1) \
+ : "a" (pattern),"0" (count/4),"1" ((long) s) \
+ : "memory")
+{
+ int d0, d1;
+ switch (count % 4) {
+ case 0: COMMON(""); return s;
+ case 1: COMMON("\n\tstosb"); return s;
+ case 2: COMMON("\n\tstosw"); return s;
+ default: COMMON("\n\tstosw\n\tstosb"); return s;
+ }
+}
+
+#undef COMMON
+}
+
+#define __constant_c_x_memset(s, c, count) \
+(__builtin_constant_p(count) ? \
+ __constant_c_and_count_memset((s),(c),(count)) : \
+ __constant_c_memset((s),(c),(count)))
+
+#define __memset(s, c, count) \
+(__builtin_constant_p(count) ? \
+ __constant_count_memset((s),(c),(count)) : \
+ __memset_generic((s),(c),(count)))
+
+#define __HAVE_ARCH_MEMSET
+#define memset(s, c, count) \
+(__builtin_constant_p(c) ? \
+ __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
+ __memset((s),(c),(count)))
+
+/*
+ * find the first occurrence of byte 'c', or 1 past the area if none
+ */
+#define __HAVE_ARCH_MEMSCAN
+static inline void * memscan(void * addr, int c, size_t size)
+{
+ if (!size)
+ return addr;
+ __asm__("repnz; scasb\n\t"
+ "jnz 1f\n\t"
+ "dec %%edi\n"
+ "1:"
+ : "=D" (addr), "=c" (size)
+ : "0" (addr), "1" (size), "a" (c));
+ return addr;
+}
+
+#endif /* CONFIG_X86_USE_STRING_486 */
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/segment.h>
+#include <asm/hypervisor.h>
+#include <linux/bitops.h> /* for LOCK_PREFIX */
+
+#ifdef __KERNEL__
+
+struct task_struct; /* one of the stranger aspects of C forward declarations.. */
+extern void FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
+
+#define prepare_to_switch() do { } while(0)
+#define switch_to(prev,next,last) do { \
+ asm volatile("pushl %%esi\n\t" \
+ "pushl %%edi\n\t" \
+ "pushl %%ebp\n\t" \
+ "movl %%esp,%0\n\t" /* save ESP */ \
+ "movl %3,%%esp\n\t" /* restore ESP */ \
+ "movl $1f,%1\n\t" /* save EIP */ \
+ "pushl %4\n\t" /* restore EIP */ \
+ "jmp __switch_to\n" \
+ "1:\t" \
+ "popl %%ebp\n\t" \
+ "popl %%edi\n\t" \
+ "popl %%esi\n\t" \
+ :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \
+ "=b" (last) \
+ :"m" (next->thread.esp),"m" (next->thread.eip), \
+ "a" (prev), "d" (next), \
+ "b" (prev)); \
+} while (0)
+
+#define _set_base(addr,base) do { unsigned long __pr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %%dl,%2\n\t" \
+ "movb %%dh,%3" \
+ :"=&d" (__pr) \
+ :"m" (*((addr)+2)), \
+ "m" (*((addr)+4)), \
+ "m" (*((addr)+7)), \
+ "0" (base) \
+ ); } while(0)
+
+#define _set_limit(addr,limit) do { unsigned long __lr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %2,%%dh\n\t" \
+ "andb $0xf0,%%dh\n\t" \
+ "orb %%dh,%%dl\n\t" \
+ "movb %%dl,%2" \
+ :"=&d" (__lr) \
+ :"m" (*(addr)), \
+ "m" (*((addr)+6)), \
+ "0" (limit) \
+ ); } while(0)
+
+#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
+#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 )
+
+static inline unsigned long _get_base(char * addr)
+{
+ unsigned long __base;
+ __asm__("movb %3,%%dh\n\t"
+ "movb %2,%%dl\n\t"
+ "shll $16,%%edx\n\t"
+ "movw %1,%%dx"
+ :"=&d" (__base)
+ :"m" (*((addr)+2)),
+ "m" (*((addr)+4)),
+ "m" (*((addr)+7)));
+ return __base;
+}
+
+#define get_base(ldt) _get_base( ((char *)&(ldt)) )
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value) \
+ asm volatile("\n" \
+ "1:\t" \
+ "movl %0,%%" #seg "\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3:\t" \
+ "pushl $0\n\t" \
+ "popl %%" #seg "\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,3b\n" \
+ ".previous" \
+ : :"m" (*(unsigned int *)&(value)))
+
+#define clts() ((void)0)
+#define read_cr0() ({ \
+ unsigned int __dummy; \
+ __asm__( \
+ "movl %%cr0,%0\n\t" \
+ :"=r" (__dummy)); \
+ __dummy; \
+})
+#define write_cr0(x) \
+ __asm__("movl %0,%%cr0": :"r" (x));
+
+#define read_cr4() ({ \
+ unsigned int __dummy; \
+ __asm__( \
+ "movl %%cr4,%0\n\t" \
+ :"=r" (__dummy)); \
+ __dummy; \
+})
+#define write_cr4(x) \
+ __asm__("movl %0,%%cr4": :"r" (x));
+#define stts() (HYPERVISOR_fpu_taskswitch())
+
+#endif /* __KERNEL__ */
+
+#define wbinvd() \
+ __asm__ __volatile__ ("wbinvd": : :"memory");
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+ unsigned long __limit;
+ __asm__("lsll %1,%0"
+ :"=r" (__limit):"r" (segment));
+ return __limit+1;
+}
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+
+/*
+ * The semantics of XCHGCMP8B are a bit strange, this is why
+ * there is a loop and the loading of %%eax and %%edx has to
+ * be inside. This inlines well in most cases, the cached
+ * cost is around ~38 cycles. (in the future we might want
+ * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
+ * might have an implicit FPU-save as a cost, so it's not
+ * clear which path to go.)
+ *
+ * chmxchg8b must be used with the lock prefix here to allow
+ * the instruction to be executed atomically, see page 3-102
+ * of the instruction set reference 24319102.pdf. We need
+ * the reader side to see the coherent 64bit value.
+ */
+static inline void __set_64bit (unsigned long long * ptr,
+ unsigned int low, unsigned int high)
+{
+ __asm__ __volatile__ (
+ "\n1:\t"
+ "movl (%0), %%eax\n\t"
+ "movl 4(%0), %%edx\n\t"
+ "lock cmpxchg8b (%0)\n\t"
+ "jnz 1b"
+ : /* no outputs */
+ : "D"(ptr),
+ "b"(low),
+ "c"(high)
+ : "ax","dx","memory");
+}
+
+static inline void __set_64bit_constant (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
+}
+#define ll_low(x) *(((unsigned int*)&(x))+0)
+#define ll_high(x) *(((unsigned int*)&(x))+1)
+
+static inline void __set_64bit_var (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,ll_low(value), ll_high(value));
+}
+
+#define set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit_constant(ptr, value) : \
+ __set_64bit_var(ptr, value) )
+
+#define _set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
+ __set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ * but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("xchgb %b0,%1"
+ :"=q" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 2:
+ __asm__ __volatile__("xchgw %w0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 4:
+ __asm__ __volatile__("xchgl %0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ }
+ return x;
+}
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ unsigned long prev;
+ switch (size) {
+ case 1:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 2:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 4:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
+
+#else
+/* Compiling for a 386 proper. Is it worth implementing via cli/sti? */
+#endif
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * For now, "wmb()" doesn't actually do anything, as all
+ * Intel CPU's follow what Intel calls a *Processor Order*,
+ * in which all writes are seen in the program order even
+ * outside the CPU.
+ *
+ * I expect future Intel CPU's to have a weaker ordering,
+ * but I'd also expect them to finally get their act together
+ * and add some real memory barriers if so.
+ *
+ * Some non intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+
+#define mb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
+#define rmb() mb()
+
+#ifdef CONFIG_X86_OOSTORE
+#define wmb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
+#else
+#define wmb() __asm__ __volatile__ ("": : :"memory")
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#endif
+
+#define set_mb(var, value) do { xchg(&var, value); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+/* interrupt control.. */
+#define __save_flags(x) ((x) = HYPERVISOR_shared_info->events_enable); barrier()
+#define __restore_flags(x) \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ _shared->events_enable = (x); \
+ barrier(); \
+ if ( _shared->events && (x) ) do_hypervisor_callback(NULL); \
+} while (0)
+#define __cli() (HYPERVISOR_shared_info->events_enable = 0); barrier()
+#define __sti() \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ _shared->events_enable = 1; \
+ barrier(); \
+ if ( _shared->events ) do_hypervisor_callback(NULL); \
+} while (0)
+#define safe_halt() ((void)0)
+
+#define __save_and_cli(x) do { __save_flags(x); __cli(); } while(0);
+#define __save_and_sti(x) do { __save_flags(x); __sti(); } while(0);
+
+/* For spinlocks etc */
+//XXX#define local_irq_set(x) __save_and_sti(x)
+#define local_irq_save(x) ((x) = HYPERVISOR_shared_info->events_enable); (HYPERVISOR_shared_info->events_enable = 0); barrier()
+#define local_irq_restore(x) __restore_flags(x)
+#define local_irq_disable() __cli()
+#define local_irq_enable() __sti()
+
+
+#ifdef CONFIG_SMP
+#error no SMP
+extern void __global_cli(void);
+extern void __global_sti(void);
+extern unsigned long __global_save_flags(void);
+extern void __global_restore_flags(unsigned long);
+#define cli() __global_cli()
+#define sti() __global_sti()
+#define save_flags(x) ((x)=__global_save_flags())
+#define restore_flags(x) __global_restore_flags(x)
+#define save_and_cli(x) do { save_flags(x); cli(); } while(0);
+#define save_and_sti(x) do { save_flags(x); sti(); } while(0);
+
+#else
+
+#define cli() __cli()
+#define sti() __sti()
+#define save_flags(x) __save_flags(x)
+#define restore_flags(x) __restore_flags(x)
+#define save_and_cli(x) __save_and_cli(x)
+#define save_and_sti(x) __save_and_sti(x)
+
+#endif
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+extern unsigned long dmi_broken;
+extern int is_sony_vaio_laptop;
+
+#define BROKEN_ACPI_Sx 0x0001
+#define BROKEN_INIT_AFTER_S1 0x0002
+
+#endif
--- /dev/null
+#ifndef __ARCH_I386_TERMBITS_H__
+#define __ARCH_I386_TERMBITS_H__
+
+#include <linux/posix_types.h>
+
+typedef unsigned char cc_t;
+typedef unsigned int speed_t;
+typedef unsigned int tcflag_t;
+
+#define NCCS 19
+struct termios {
+ tcflag_t c_iflag; /* input mode flags */
+ tcflag_t c_oflag; /* output mode flags */
+ tcflag_t c_cflag; /* control mode flags */
+ tcflag_t c_lflag; /* local mode flags */
+ cc_t c_line; /* line discipline */
+ cc_t c_cc[NCCS]; /* control characters */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+/* c_iflag bits */
+#define IGNBRK 0000001
+#define BRKINT 0000002
+#define IGNPAR 0000004
+#define PARMRK 0000010
+#define INPCK 0000020
+#define ISTRIP 0000040
+#define INLCR 0000100
+#define IGNCR 0000200
+#define ICRNL 0000400
+#define IUCLC 0001000
+#define IXON 0002000
+#define IXANY 0004000
+#define IXOFF 0010000
+#define IMAXBEL 0020000
+
+/* c_oflag bits */
+#define OPOST 0000001
+#define OLCUC 0000002
+#define ONLCR 0000004
+#define OCRNL 0000010
+#define ONOCR 0000020
+#define ONLRET 0000040
+#define OFILL 0000100
+#define OFDEL 0000200
+#define NLDLY 0000400
+#define NL0 0000000
+#define NL1 0000400
+#define CRDLY 0003000
+#define CR0 0000000
+#define CR1 0001000
+#define CR2 0002000
+#define CR3 0003000
+#define TABDLY 0014000
+#define TAB0 0000000
+#define TAB1 0004000
+#define TAB2 0010000
+#define TAB3 0014000
+#define XTABS 0014000
+#define BSDLY 0020000
+#define BS0 0000000
+#define BS1 0020000
+#define VTDLY 0040000
+#define VT0 0000000
+#define VT1 0040000
+#define FFDLY 0100000
+#define FF0 0000000
+#define FF1 0100000
+
+/* c_cflag bit meaning */
+#define CBAUD 0010017
+#define B0 0000000 /* hang up */
+#define B50 0000001
+#define B75 0000002
+#define B110 0000003
+#define B134 0000004
+#define B150 0000005
+#define B200 0000006
+#define B300 0000007
+#define B600 0000010
+#define B1200 0000011
+#define B1800 0000012
+#define B2400 0000013
+#define B4800 0000014
+#define B9600 0000015
+#define B19200 0000016
+#define B38400 0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE 0000060
+#define CS5 0000000
+#define CS6 0000020
+#define CS7 0000040
+#define CS8 0000060
+#define CSTOPB 0000100
+#define CREAD 0000200
+#define PARENB 0000400
+#define PARODD 0001000
+#define HUPCL 0002000
+#define CLOCAL 0004000
+#define CBAUDEX 0010000
+#define B57600 0010001
+#define B115200 0010002
+#define B230400 0010003
+#define B460800 0010004
+#define B500000 0010005
+#define B576000 0010006
+#define B921600 0010007
+#define B1000000 0010010
+#define B1152000 0010011
+#define B1500000 0010012
+#define B2000000 0010013
+#define B2500000 0010014
+#define B3000000 0010015
+#define B3500000 0010016
+#define B4000000 0010017
+#define CIBAUD 002003600000 /* input baud rate (not used) */
+#define CMSPAR 010000000000 /* mark or space (stick) parity */
+#define CRTSCTS 020000000000 /* flow control */
+
+/* c_lflag bits */
+#define ISIG 0000001
+#define ICANON 0000002
+#define XCASE 0000004
+#define ECHO 0000010
+#define ECHOE 0000020
+#define ECHOK 0000040
+#define ECHONL 0000100
+#define NOFLSH 0000200
+#define TOSTOP 0000400
+#define ECHOCTL 0001000
+#define ECHOPRT 0002000
+#define ECHOKE 0004000
+#define FLUSHO 0010000
+#define PENDIN 0040000
+#define IEXTEN 0100000
+
+/* tcflow() and TCXONC use these */
+#define TCOOFF 0
+#define TCOON 1
+#define TCIOFF 2
+#define TCION 3
+
+/* tcflush() and TCFLSH use these */
+#define TCIFLUSH 0
+#define TCOFLUSH 1
+#define TCIOFLUSH 2
+
+/* tcsetattr uses these */
+#define TCSANOW 0
+#define TCSADRAIN 1
+#define TCSAFLUSH 2
+
+#endif
--- /dev/null
+#ifndef _I386_TERMIOS_H
+#define _I386_TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+ unsigned short ws_row;
+ unsigned short ws_col;
+ unsigned short ws_xpixel;
+ unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+ unsigned short c_iflag; /* input mode flags */
+ unsigned short c_oflag; /* output mode flags */
+ unsigned short c_cflag; /* control mode flags */
+ unsigned short c_lflag; /* local mode flags */
+ unsigned char c_line; /* line discipline */
+ unsigned char c_cc[NCC]; /* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE 0x001
+#define TIOCM_DTR 0x002
+#define TIOCM_RTS 0x004
+#define TIOCM_ST 0x008
+#define TIOCM_SR 0x010
+#define TIOCM_CTS 0x020
+#define TIOCM_CAR 0x040
+#define TIOCM_RNG 0x080
+#define TIOCM_DSR 0x100
+#define TIOCM_CD TIOCM_CAR
+#define TIOCM_RI TIOCM_RNG
+#define TIOCM_OUT1 0x2000
+#define TIOCM_OUT2 0x4000
+#define TIOCM_LOOP 0x8000
+
+#define TIOCM_MODEM_BITS TIOCM_OUT2 /* IRDA support */
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
+/* line disciplines */
+#define N_TTY 0
+#define N_SLIP 1
+#define N_MOUSE 2
+#define N_PPP 3
+#define N_STRIP 4
+#define N_AX25 5
+#define N_X25 6 /* X.25 async */
+#define N_6PACK 7
+#define N_MASC 8 /* Reserved for Mobitex module <kaz@cafe.net> */
+#define N_R3964 9 /* Reserved for Simatic R3964 module */
+#define N_PROFIBUS_FDL 10 /* Reserved for Profibus <Dave@mvhi.com> */
+#define N_IRDA 11 /* Linux IR - http://irda.sourceforge.net/ */
+#define N_SMSBLOCK 12 /* SMS block mode - for talking to GSM data cards about SMS messages */
+#define N_HDLC 13 /* synchronous HDLC */
+#define N_SYNC_PPP 14 /* synchronous PPP */
+#define N_HCI 15 /* Bluetooth HCI UART */
+
+#ifdef __KERNEL__
+
+/* intr=^C quit=^\ erase=del kill=^U
+ eof=^D vtime=\0 vmin=\1 sxtc=\0
+ start=^Q stop=^S susp=^Z eol=\0
+ reprint=^R discard=^U werase=^W lnext=^V
+ eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+ unsigned short __tmp; \
+ get_user(__tmp,&(termio)->x); \
+ *(unsigned short *) &(termios)->x = __tmp; \
+}
+
+#define user_termio_to_kernel_termios(termios, termio) \
+({ \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
+ SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
+ copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
+})
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+#define kernel_termios_to_user_termio(termio, termios) \
+({ \
+ put_user((termios)->c_iflag, &(termio)->c_iflag); \
+ put_user((termios)->c_oflag, &(termio)->c_oflag); \
+ put_user((termios)->c_cflag, &(termio)->c_cflag); \
+ put_user((termios)->c_lflag, &(termio)->c_lflag); \
+ put_user((termios)->c_line, &(termio)->c_line); \
+ copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
+})
+
+#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios))
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_TERMIOS_H */
--- /dev/null
+/*
+ * linux/include/asm-i386/timex.h
+ *
+ * i386 architecture timex specifications
+ */
+#ifndef _ASMi386_TIMEX_H
+#define _ASMi386_TIMEX_H
+
+#include <linux/config.h>
+#include <asm/msr.h>
+
+#ifdef CONFIG_MELAN
+# define CLOCK_TICK_RATE 1189200 /* AMD Elan has different frequency! */
+#else
+# define CLOCK_TICK_RATE 1193180 /* Underlying HZ */
+#endif
+
+#define CLOCK_TICK_FACTOR 20 /* Factor of both 1000000 and CLOCK_TICK_RATE */
+#define FINETUNE ((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \
+ (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \
+ << (SHIFT_SCALE-SHIFT_HZ)) / HZ)
+
+/*
+ * Standard way to access the cycle counter on i586+ CPUs.
+ * Currently only used on SMP.
+ *
+ * If you really have a SMP machine with i486 chips or older,
+ * compile for that, and this will just always return zero.
+ * That's ok, it just means that the nicer scheduling heuristics
+ * won't work for you.
+ *
+ * We only use the low 32 bits, and we'd simply better make sure
+ * that we reschedule before that wraps. Scheduling at least every
+ * four billion cycles just basically sounds like a good idea,
+ * regardless of how fast the machine is.
+ */
+typedef unsigned long long cycles_t;
+
+extern cycles_t cacheflush_time;
+
+static inline cycles_t get_cycles (void)
+{
+#ifndef CONFIG_X86_TSC
+ return 0;
+#else
+ unsigned long long ret;
+
+ rdtscll(ret);
+ return ret;
+#endif
+}
+
+extern unsigned long cpu_khz;
+
+#define vxtime_lock() do {} while (0)
+#define vxtime_unlock() do {} while (0)
+
+#endif
--- /dev/null
+#include <asm-generic/tlb.h>
--- /dev/null
+#ifndef _I386_TYPES_H
+#define _I386_TYPES_H
+
+typedef unsigned short umode_t;
+
+/*
+ * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
+ * header files exported to user space
+ */
+
+typedef __signed__ char __s8;
+typedef unsigned char __u8;
+
+typedef __signed__ short __s16;
+typedef unsigned short __u16;
+
+typedef __signed__ int __s32;
+typedef unsigned int __u32;
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+typedef __signed__ long long __s64;
+typedef unsigned long long __u64;
+#endif
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+#define BITS_PER_LONG 32
+
+/* DMA addresses come in generic and 64-bit flavours. */
+
+#ifdef CONFIG_HIGHMEM64G
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+typedef u64 dma64_addr_t;
+
+#endif /* __KERNEL__ */
+
+#endif
--- /dev/null
+#ifndef __i386_UACCESS_H
+#define __i386_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/prefetch.h>
+#include <asm/page.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not. If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) })
+
+
+#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF)
+#define USER_DS MAKE_MM_SEG(PAGE_OFFSET)
+
+#define get_ds() (KERNEL_DS)
+#define get_fs() (current->addr_limit)
+#define set_fs(x) (current->addr_limit = (x))
+
+#define segment_eq(a,b) ((a).seg == (b).seg)
+
+extern int __verify_write(const void *, unsigned long);
+
+#define __addr_ok(addr) ((unsigned long)(addr) < (current->addr_limit.seg))
+
+/*
+ * Uhhuh, this needs 33-bit arithmetic. We have a carry..
+ */
+#define __range_ok(addr,size) ({ \
+ unsigned long flag,sum; \
+ asm("addl %3,%1 ; sbbl %0,%0; cmpl %1,%4; sbbl $0,%0" \
+ :"=&r" (flag), "=r" (sum) \
+ :"1" (addr),"g" ((int)(size)),"g" (current->addr_limit.seg)); \
+ flag; })
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+#define access_ok(type,addr,size) (__range_ok(addr,size) == 0)
+
+#else
+
+#define access_ok(type,addr,size) ( (__range_ok(addr,size) == 0) && \
+ ((type) == VERIFY_READ || boot_cpu_data.wp_works_ok || \
+ segment_eq(get_fs(),KERNEL_DS) || \
+ __verify_write((void *)(addr),(size))))
+
+#endif
+
+static inline int verify_area(int type, const void * addr, unsigned long size)
+{
+ return access_ok(type,addr,size) ? 0 : -EFAULT;
+}
+
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+ unsigned long insn, fixup;
+};
+
+/* Returns 0 if exception not found and fixup otherwise. */
+extern unsigned long search_exception_table(unsigned long);
+
+
+/*
+ * These are the main single-value transfer routines. They automatically
+ * use the right size if we just have the right pointer type.
+ *
+ * This gets kind of ugly. We want to return _two_ values in "get_user()"
+ * and yet we don't want to do any pointers, because that is too much
+ * of a performance impact. Thus we have a few rather ugly macros here,
+ * and hide all the uglyness from the user.
+ *
+ * The "__xxx" versions of the user access functions are versions that
+ * do not verify the address space, that must have been done previously
+ * with a separate "access_ok()" call (this is used when we do multiple
+ * accesses to the same area of user memory).
+ */
+
+extern void __get_user_1(void);
+extern void __get_user_2(void);
+extern void __get_user_4(void);
+
+#define __get_user_x(size,ret,x,ptr) \
+ __asm__ __volatile__("call __get_user_" #size \
+ :"=a" (ret),"=d" (x) \
+ :"0" (ptr))
+
+/* Careful: we have to cast the result to the type of the pointer for sign reasons */
+#define get_user(x,ptr) \
+({ int __ret_gu,__val_gu; \
+ switch(sizeof (*(ptr))) { \
+ case 1: __get_user_x(1,__ret_gu,__val_gu,ptr); break; \
+ case 2: __get_user_x(2,__ret_gu,__val_gu,ptr); break; \
+ case 4: __get_user_x(4,__ret_gu,__val_gu,ptr); break; \
+ default: __get_user_x(X,__ret_gu,__val_gu,ptr); break; \
+ } \
+ (x) = (__typeof__(*(ptr)))__val_gu; \
+ __ret_gu; \
+})
+
+extern void __put_user_1(void);
+extern void __put_user_2(void);
+extern void __put_user_4(void);
+extern void __put_user_8(void);
+
+extern void __put_user_bad(void);
+
+#define put_user(x,ptr) \
+ __put_user_check((__typeof__(*(ptr)))(x),(ptr),sizeof(*(ptr)))
+
+#define __get_user(x,ptr) \
+ __get_user_nocheck((x),(ptr),sizeof(*(ptr)))
+#define __put_user(x,ptr) \
+ __put_user_nocheck((__typeof__(*(ptr)))(x),(ptr),sizeof(*(ptr)))
+
+#define __put_user_nocheck(x,ptr,size) \
+({ \
+ long __pu_err; \
+ __put_user_size((x),(ptr),(size),__pu_err); \
+ __pu_err; \
+})
+
+
+#define __put_user_check(x,ptr,size) \
+({ \
+ long __pu_err = -EFAULT; \
+ __typeof__(*(ptr)) *__pu_addr = (ptr); \
+ if (access_ok(VERIFY_WRITE,__pu_addr,size)) \
+ __put_user_size((x),__pu_addr,(size),__pu_err); \
+ __pu_err; \
+})
+
+#define __put_user_u64(x, addr, err) \
+ __asm__ __volatile__( \
+ "1: movl %%eax,0(%2)\n" \
+ "2: movl %%edx,4(%2)\n" \
+ "3:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "4: movl %3,%0\n" \
+ " jmp 3b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,4b\n" \
+ " .long 2b,4b\n" \
+ ".previous" \
+ : "=r"(err) \
+ : "A" (x), "r" (addr), "i"(-EFAULT), "0"(err))
+
+#define __put_user_size(x,ptr,size,retval) \
+do { \
+ retval = 0; \
+ switch (size) { \
+ case 1: __put_user_asm(x,ptr,retval,"b","b","iq"); break; \
+ case 2: __put_user_asm(x,ptr,retval,"w","w","ir"); break; \
+ case 4: __put_user_asm(x,ptr,retval,"l","","ir"); break; \
+ case 8: __put_user_u64(x,ptr,retval); break; \
+ default: __put_user_bad(); \
+ } \
+} while (0)
+
+struct __large_struct { unsigned long buf[100]; };
+#define __m(x) (*(struct __large_struct *)(x))
+
+/*
+ * Tell gcc we read from memory instead of writing: this is because
+ * we do not write to any memory gcc knows about, so there are no
+ * aliasing issues.
+ */
+#define __put_user_asm(x, addr, err, itype, rtype, ltype) \
+ __asm__ __volatile__( \
+ "1: mov"itype" %"rtype"1,%2\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl %3,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,3b\n" \
+ ".previous" \
+ : "=r"(err) \
+ : ltype (x), "m"(__m(addr)), "i"(-EFAULT), "0"(err))
+
+
+#define __get_user_nocheck(x,ptr,size) \
+({ \
+ long __gu_err, __gu_val; \
+ __get_user_size(__gu_val,(ptr),(size),__gu_err); \
+ (x) = (__typeof__(*(ptr)))__gu_val; \
+ __gu_err; \
+})
+
+extern long __get_user_bad(void);
+
+#define __get_user_size(x,ptr,size,retval) \
+do { \
+ retval = 0; \
+ switch (size) { \
+ case 1: __get_user_asm(x,ptr,retval,"b","b","=q"); break; \
+ case 2: __get_user_asm(x,ptr,retval,"w","w","=r"); break; \
+ case 4: __get_user_asm(x,ptr,retval,"l","","=r"); break; \
+ default: (x) = __get_user_bad(); \
+ } \
+} while (0)
+
+#define __get_user_asm(x, addr, err, itype, rtype, ltype) \
+ __asm__ __volatile__( \
+ "1: mov"itype" %2,%"rtype"1\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl %3,%0\n" \
+ " xor"itype" %"rtype"1,%"rtype"1\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 1b,3b\n" \
+ ".previous" \
+ : "=r"(err), ltype (x) \
+ : "m"(__m(addr)), "i"(-EFAULT), "0"(err))
+
+
+/*
+ * Copy To/From Userspace
+ */
+
+/* Generic arbitrary sized copy. */
+#define __copy_user(to,from,size) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ " movl %3,%0\n" \
+ "1: rep; movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: lea 0(%3,%0,4),%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,2b\n" \
+ ".previous" \
+ : "=&c"(size), "=&D" (__d0), "=&S" (__d1) \
+ : "r"(size & 3), "0"(size / 4), "1"(to), "2"(from) \
+ : "memory"); \
+} while (0)
+
+#define __copy_user_zeroing(to,from,size) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ " movl %3,%0\n" \
+ "1: rep; movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: lea 0(%3,%0,4),%0\n" \
+ "4: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosb\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=&c"(size), "=&D" (__d0), "=&S" (__d1) \
+ : "r"(size & 3), "0"(size / 4), "1"(to), "2"(from) \
+ : "memory"); \
+} while (0)
+
+/* We let the __ versions of copy_from/to_user inline, because they're often
+ * used in fast paths and have only a small space overhead.
+ */
+static inline unsigned long
+__generic_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __copy_user_zeroing(to,from,n);
+ return n;
+}
+
+static inline unsigned long
+__generic_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __copy_user(to,from,n);
+ return n;
+}
+
+
+/* Optimize just a little bit when we know the size of the move. */
+#define __constant_copy_user(to, from, size) \
+do { \
+ int __d0, __d1; \
+ switch (size & 3) { \
+ default: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "2: shl $2,%0\n" \
+ " jmp 1b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,2b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 1: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: shl $2,%0\n" \
+ "4: incl %0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 2: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: shl $2,%0\n" \
+ "4: addl $2,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 3: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2: movsb\n" \
+ "3:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "4: shl $2,%0\n" \
+ "5: addl $2,%0\n" \
+ "6: incl %0\n" \
+ " jmp 3b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,4b\n" \
+ " .long 1b,5b\n" \
+ " .long 2b,6b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+/* Optimize just a little bit when we know the size of the move. */
+#define __constant_copy_user_zeroing(to, from, size) \
+do { \
+ int __d0, __d1; \
+ switch (size & 3) { \
+ default: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "2: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " jmp 1b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,2b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 1: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsb\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " incl %0\n" \
+ " jmp 2b\n" \
+ "4: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " incl %0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 2: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " stosw\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " addl $2,%0\n" \
+ " jmp 2b\n" \
+ "4: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosw\n" \
+ " popl %%eax\n" \
+ " addl $2,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,3b\n" \
+ " .long 1b,4b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ case 3: \
+ __asm__ __volatile__( \
+ "0: rep; movsl\n" \
+ "1: movsw\n" \
+ "2: movsb\n" \
+ "3:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "4: pushl %0\n" \
+ " pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " rep; stosl\n" \
+ " stosw\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " popl %0\n" \
+ " shl $2,%0\n" \
+ " addl $3,%0\n" \
+ " jmp 2b\n" \
+ "5: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosw\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " addl $3,%0\n" \
+ " jmp 2b\n" \
+ "6: pushl %%eax\n" \
+ " xorl %%eax,%%eax\n" \
+ " stosb\n" \
+ " popl %%eax\n" \
+ " incl %0\n" \
+ " jmp 3b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n" \
+ " .align 4\n" \
+ " .long 0b,4b\n" \
+ " .long 1b,5b\n" \
+ " .long 2b,6b\n" \
+ ".previous" \
+ : "=c"(size), "=&S" (__d0), "=&D" (__d1)\
+ : "1"(from), "2"(to), "0"(size/4) \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+unsigned long __generic_copy_to_user(void *, const void *, unsigned long);
+unsigned long __generic_copy_from_user(void *, const void *, unsigned long);
+
+static inline unsigned long
+__constant_copy_to_user(void *to, const void *from, unsigned long n)
+{
+ prefetch(from);
+ if (access_ok(VERIFY_WRITE, to, n))
+ __constant_copy_user(to,from,n);
+ return n;
+}
+
+static inline unsigned long
+__constant_copy_from_user(void *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_READ, from, n))
+ __constant_copy_user_zeroing(to,from,n);
+ else
+ memset(to, 0, n);
+ return n;
+}
+
+static inline unsigned long
+__constant_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __constant_copy_user(to,from,n);
+ return n;
+}
+
+static inline unsigned long
+__constant_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
+{
+ __constant_copy_user_zeroing(to,from,n);
+ return n;
+}
+
+#define copy_to_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_to_user((to),(from),(n)) : \
+ __generic_copy_to_user((to),(from),(n)))
+
+#define copy_from_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_from_user((to),(from),(n)) : \
+ __generic_copy_from_user((to),(from),(n)))
+
+#define __copy_to_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_to_user_nocheck((to),(from),(n)) : \
+ __generic_copy_to_user_nocheck((to),(from),(n)))
+
+#define __copy_from_user(to,from,n) \
+ (__builtin_constant_p(n) ? \
+ __constant_copy_from_user_nocheck((to),(from),(n)) : \
+ __generic_copy_from_user_nocheck((to),(from),(n)))
+
+long strncpy_from_user(char *dst, const char *src, long count);
+long __strncpy_from_user(char *dst, const char *src, long count);
+#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
+long strnlen_user(const char *str, long n);
+unsigned long clear_user(void *mem, unsigned long len);
+unsigned long __clear_user(void *mem, unsigned long len);
+
+#endif /* __i386_UACCESS_H */
--- /dev/null
+#ifndef _ASMi386_UCONTEXT_H
+#define _ASMi386_UCONTEXT_H
+
+struct ucontext {
+ unsigned long uc_flags;
+ struct ucontext *uc_link;
+ stack_t uc_stack;
+ struct sigcontext uc_mcontext;
+ sigset_t uc_sigmask; /* mask last for extensibility */
+};
+
+#endif /* !_ASMi386_UCONTEXT_H */
--- /dev/null
+#ifndef __I386_UNALIGNED_H
+#define __I386_UNALIGNED_H
+
+/*
+ * The i386 can do unaligned accesses itself.
+ *
+ * The strange macros are there to make sure these can't
+ * be misused in a way that makes them not work on other
+ * architectures where unaligned accesses aren't as simple.
+ */
+
+/**
+ * get_unaligned - get value from possibly mis-aligned location
+ * @ptr: pointer to value
+ *
+ * This macro should be used for accessing values larger in size than
+ * single bytes at locations that are expected to be improperly aligned,
+ * e.g. retrieving a u16 value from a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define get_unaligned(ptr) (*(ptr))
+
+/**
+ * put_unaligned - put value to a possibly mis-aligned location
+ * @val: value to place
+ * @ptr: pointer to location
+ *
+ * This macro should be used for placing values larger in size than
+ * single bytes at locations that are expected to be improperly aligned,
+ * e.g. writing a u16 value to a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+
+#endif
--- /dev/null
+#ifndef _ASM_I386_UNISTD_H_
+#define _ASM_I386_UNISTD_H_
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_exit 1
+#define __NR_fork 2
+#define __NR_read 3
+#define __NR_write 4
+#define __NR_open 5
+#define __NR_close 6
+#define __NR_waitpid 7
+#define __NR_creat 8
+#define __NR_link 9
+#define __NR_unlink 10
+#define __NR_execve 11
+#define __NR_chdir 12
+#define __NR_time 13
+#define __NR_mknod 14
+#define __NR_chmod 15
+#define __NR_lchown 16
+#define __NR_break 17
+#define __NR_oldstat 18
+#define __NR_lseek 19
+#define __NR_getpid 20
+#define __NR_mount 21
+#define __NR_umount 22
+#define __NR_setuid 23
+#define __NR_getuid 24
+#define __NR_stime 25
+#define __NR_ptrace 26
+#define __NR_alarm 27
+#define __NR_oldfstat 28
+#define __NR_pause 29
+#define __NR_utime 30
+#define __NR_stty 31
+#define __NR_gtty 32
+#define __NR_access 33
+#define __NR_nice 34
+#define __NR_ftime 35
+#define __NR_sync 36
+#define __NR_kill 37
+#define __NR_rename 38
+#define __NR_mkdir 39
+#define __NR_rmdir 40
+#define __NR_dup 41
+#define __NR_pipe 42
+#define __NR_times 43
+#define __NR_prof 44
+#define __NR_brk 45
+#define __NR_setgid 46
+#define __NR_getgid 47
+#define __NR_signal 48
+#define __NR_geteuid 49
+#define __NR_getegid 50
+#define __NR_acct 51
+#define __NR_umount2 52
+#define __NR_lock 53
+#define __NR_ioctl 54
+#define __NR_fcntl 55
+#define __NR_mpx 56
+#define __NR_setpgid 57
+#define __NR_ulimit 58
+#define __NR_oldolduname 59
+#define __NR_umask 60
+#define __NR_chroot 61
+#define __NR_ustat 62
+#define __NR_dup2 63
+#define __NR_getppid 64
+#define __NR_getpgrp 65
+#define __NR_setsid 66
+#define __NR_sigaction 67
+#define __NR_sgetmask 68
+#define __NR_ssetmask 69
+#define __NR_setreuid 70
+#define __NR_setregid 71
+#define __NR_sigsuspend 72
+#define __NR_sigpending 73
+#define __NR_sethostname 74
+#define __NR_setrlimit 75
+#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */
+#define __NR_getrusage 77
+#define __NR_gettimeofday 78
+#define __NR_settimeofday 79
+#define __NR_getgroups 80
+#define __NR_setgroups 81
+#define __NR_select 82
+#define __NR_symlink 83
+#define __NR_oldlstat 84
+#define __NR_readlink 85
+#define __NR_uselib 86
+#define __NR_swapon 87
+#define __NR_reboot 88
+#define __NR_readdir 89
+#define __NR_mmap 90
+#define __NR_munmap 91
+#define __NR_truncate 92
+#define __NR_ftruncate 93
+#define __NR_fchmod 94
+#define __NR_fchown 95
+#define __NR_getpriority 96
+#define __NR_setpriority 97
+#define __NR_profil 98
+#define __NR_statfs 99
+#define __NR_fstatfs 100
+#define __NR_ioperm 101
+#define __NR_socketcall 102
+#define __NR_syslog 103
+#define __NR_setitimer 104
+#define __NR_getitimer 105
+#define __NR_stat 106
+#define __NR_lstat 107
+#define __NR_fstat 108
+#define __NR_olduname 109
+#define __NR_iopl 110
+#define __NR_vhangup 111
+#define __NR_idle 112
+#define __NR_vm86old 113
+#define __NR_wait4 114
+#define __NR_swapoff 115
+#define __NR_sysinfo 116
+#define __NR_ipc 117
+#define __NR_fsync 118
+#define __NR_sigreturn 119
+#define __NR_clone 120
+#define __NR_setdomainname 121
+#define __NR_uname 122
+#define __NR_modify_ldt 123
+#define __NR_adjtimex 124
+#define __NR_mprotect 125
+#define __NR_sigprocmask 126
+#define __NR_create_module 127
+#define __NR_init_module 128
+#define __NR_delete_module 129
+#define __NR_get_kernel_syms 130
+#define __NR_quotactl 131
+#define __NR_getpgid 132
+#define __NR_fchdir 133
+#define __NR_bdflush 134
+#define __NR_sysfs 135
+#define __NR_personality 136
+#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
+#define __NR_setfsuid 138
+#define __NR_setfsgid 139
+#define __NR__llseek 140
+#define __NR_getdents 141
+#define __NR__newselect 142
+#define __NR_flock 143
+#define __NR_msync 144
+#define __NR_readv 145
+#define __NR_writev 146
+#define __NR_getsid 147
+#define __NR_fdatasync 148
+#define __NR__sysctl 149
+#define __NR_mlock 150
+#define __NR_munlock 151
+#define __NR_mlockall 152
+#define __NR_munlockall 153
+#define __NR_sched_setparam 154
+#define __NR_sched_getparam 155
+#define __NR_sched_setscheduler 156
+#define __NR_sched_getscheduler 157
+#define __NR_sched_yield 158
+#define __NR_sched_get_priority_max 159
+#define __NR_sched_get_priority_min 160
+#define __NR_sched_rr_get_interval 161
+#define __NR_nanosleep 162
+#define __NR_mremap 163
+#define __NR_setresuid 164
+#define __NR_getresuid 165
+#define __NR_vm86 166
+#define __NR_query_module 167
+#define __NR_poll 168
+#define __NR_nfsservctl 169
+#define __NR_setresgid 170
+#define __NR_getresgid 171
+#define __NR_prctl 172
+#define __NR_rt_sigreturn 173
+#define __NR_rt_sigaction 174
+#define __NR_rt_sigprocmask 175
+#define __NR_rt_sigpending 176
+#define __NR_rt_sigtimedwait 177
+#define __NR_rt_sigqueueinfo 178
+#define __NR_rt_sigsuspend 179
+#define __NR_pread 180
+#define __NR_pwrite 181
+#define __NR_chown 182
+#define __NR_getcwd 183
+#define __NR_capget 184
+#define __NR_capset 185
+#define __NR_sigaltstack 186
+#define __NR_sendfile 187
+#define __NR_getpmsg 188 /* some people actually want streams */
+#define __NR_putpmsg 189 /* some people actually want streams */
+#define __NR_vfork 190
+#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
+#define __NR_mmap2 192
+#define __NR_truncate64 193
+#define __NR_ftruncate64 194
+#define __NR_stat64 195
+#define __NR_lstat64 196
+#define __NR_fstat64 197
+#define __NR_lchown32 198
+#define __NR_getuid32 199
+#define __NR_getgid32 200
+#define __NR_geteuid32 201
+#define __NR_getegid32 202
+#define __NR_setreuid32 203
+#define __NR_setregid32 204
+#define __NR_getgroups32 205
+#define __NR_setgroups32 206
+#define __NR_fchown32 207
+#define __NR_setresuid32 208
+#define __NR_getresuid32 209
+#define __NR_setresgid32 210
+#define __NR_getresgid32 211
+#define __NR_chown32 212
+#define __NR_setuid32 213
+#define __NR_setgid32 214
+#define __NR_setfsuid32 215
+#define __NR_setfsgid32 216
+#define __NR_pivot_root 217
+#define __NR_mincore 218
+#define __NR_madvise 219
+#define __NR_madvise1 219 /* delete when C lib stub is removed */
+#define __NR_getdents64 220
+#define __NR_fcntl64 221
+#define __NR_security 223 /* syscall for security modules */
+#define __NR_gettid 224
+#define __NR_readahead 225
+#define __NR_setxattr 226
+#define __NR_lsetxattr 227
+#define __NR_fsetxattr 228
+#define __NR_getxattr 229
+#define __NR_lgetxattr 230
+#define __NR_fgetxattr 231
+#define __NR_listxattr 232
+#define __NR_llistxattr 233
+#define __NR_flistxattr 234
+#define __NR_removexattr 235
+#define __NR_lremovexattr 236
+#define __NR_fremovexattr 237
+#define __NR_tkill 238
+#define __NR_sendfile64 239
+#define __NR_futex 240
+#define __NR_sched_setaffinity 241
+#define __NR_sched_getaffinity 242
+#define __NR_set_thread_area 243
+#define __NR_get_thread_area 244
+#define __NR_io_setup 245
+#define __NR_io_destroy 246
+#define __NR_io_getevents 247
+#define __NR_io_submit 248
+#define __NR_io_cancel 249
+#define __NR_alloc_hugepages 250
+#define __NR_free_hugepages 251
+#define __NR_exit_group 252
+
+/* user-visible error numbers are in the range -1 - -124: see <asm-i386/errno.h> */
+
+#define __syscall_return(type, res) \
+do { \
+ if ((unsigned long)(res) >= (unsigned long)(-125)) { \
+ errno = -(res); \
+ res = -1; \
+ } \
+ return (type) (res); \
+} while (0)
+
+/* XXX - _foo needs to be __foo, while __NR_bar could be _NR_bar. */
+#define _syscall0(type,name) \
+type name(void) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name)); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall1(type,name,type1,arg1) \
+type name(type1 arg1) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall2(type,name,type1,arg1,type2,arg2) \
+type name(type1 arg1,type2 arg2) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \
+type name(type1 arg1,type2 arg2,type3 arg3) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
+type name (type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3)),"S" ((long)(arg4))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
+ type5,arg5) \
+type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5) \
+{ \
+long __res; \
+__asm__ volatile ("int $0x80" \
+ : "=a" (__res) \
+ : "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5))); \
+__syscall_return(type,__res); \
+}
+
+#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
+ type5,arg5,type6,arg6) \
+type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5,type6 arg6) \
+{ \
+long __res; \
+__asm__ volatile ("push %%ebp ; movl %%eax,%%ebp ; movl %1,%%eax ; int $0x80 ; pop %%ebp" \
+ : "=a" (__res) \
+ : "i" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+ "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)), \
+ "0" ((long)(arg6))); \
+__syscall_return(type,__res); \
+}
+
+#ifdef __KERNEL_SYSCALLS__
+
+/*
+ * we need this inline - forking from kernel space will result
+ * in NO COPY ON WRITE (!!!), until an execve is executed. This
+ * is no problem, but for the stack. This is handled by not letting
+ * main() use the stack at all after fork(). Thus, no function
+ * calls - which means inline code for fork too, as otherwise we
+ * would use the stack upon exit from 'fork()'.
+ *
+ * Actually only pause and fork are needed inline, so that there
+ * won't be any messing with the stack from main(), but we define
+ * some others too.
+ */
+#define __NR__exit __NR_exit
+static inline _syscall0(int,pause)
+static inline _syscall0(int,sync)
+static inline _syscall0(pid_t,setsid)
+static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count)
+static inline _syscall3(int,read,int,fd,char *,buf,off_t,count)
+static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count)
+static inline _syscall1(int,dup,int,fd)
+static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp)
+static inline _syscall3(int,open,const char *,file,int,flag,int,mode)
+static inline _syscall1(int,close,int,fd)
+static inline _syscall1(int,_exit,int,exitcode)
+static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options)
+static inline _syscall1(int,delete_module,const char *,name)
+
+static inline pid_t wait(int * wait_stat)
+{
+ return waitpid(-1,wait_stat,0);
+}
+
+#endif
+
+#endif /* _ASM_I386_UNISTD_H_ */
--- /dev/null
+#ifndef _I386_USER_H
+#define _I386_USER_H
+
+#include <asm/page.h>
+#include <linux/ptrace.h>
+/* Core file format: The core file is written in such a way that gdb
+ can understand it and provide useful information to the user (under
+ linux we use the 'trad-core' bfd). There are quite a number of
+ obstacles to being able to view the contents of the floating point
+ registers, and until these are solved you will not be able to view the
+ contents of them. Actually, you can read in the core file and look at
+ the contents of the user struct to find out what the floating point
+ registers contain.
+ The actual file contents are as follows:
+ UPAGE: 1 page consisting of a user struct that tells gdb what is present
+ in the file. Directly after this is a copy of the task_struct, which
+ is currently not used by gdb, but it may come in useful at some point.
+ All of the registers are stored as part of the upage. The upage should
+ always be only one page.
+ DATA: The data area is stored. We use current->end_text to
+ current->brk to pick up all of the user variables, plus any memory
+ that may have been malloced. No attempt is made to determine if a page
+ is demand-zero or if a page is totally unused, we just cover the entire
+ range. All of the addresses are rounded in such a way that an integral
+ number of pages is written.
+ STACK: We need the stack information in order to get a meaningful
+ backtrace. We need to write the data from (esp) to
+ current->start_stack, so we round each of these off in order to be able
+ to write an integer number of pages.
+ The minimum core file size is 3 pages, or 12288 bytes.
+*/
+
+/*
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
+ * interacting with the FXSR-format floating point environment. Floating
+ * point data can be accessed in the regular format in the usual manner,
+ * and both the standard and SIMD floating point data can be accessed via
+ * the new ptrace requests. In either case, changes to the FPU environment
+ * will be reflected in the task's state as expected.
+ */
+
+struct user_i387_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+};
+
+struct user_fxsr_struct {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long mxcsr;
+ long reserved;
+ long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+ long padding[56];
+};
+
+/*
+ * This is the old layout of "struct pt_regs", and
+ * is still the layout used by user mode (the new
+ * pt_regs doesn't have all registers as the kernel
+ * doesn't use the extra segment registers)
+ */
+struct user_regs_struct {
+ long ebx, ecx, edx, esi, edi, ebp, eax;
+ unsigned short ds, __ds, es, __es;
+ unsigned short fs, __fs, gs, __gs;
+ long orig_eax, eip;
+ unsigned short cs, __cs;
+ long eflags, esp;
+ unsigned short ss, __ss;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+ this will be used by gdb to figure out where the data and stack segments
+ are within the file, and what virtual addresses to use. */
+struct user{
+/* We start with the registers, to mimic the way that "memory" is returned
+ from the ptrace(3,...) function. */
+ struct user_regs_struct regs; /* Where the registers are actually stored */
+/* ptrace does not yet supply these. Someday.... */
+ int u_fpvalid; /* True if math co-processor being used. */
+ /* for this mess. Not yet used. */
+ struct user_i387_struct i387; /* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+ unsigned long int u_tsize; /* Text segment size (pages). */
+ unsigned long int u_dsize; /* Data segment size (pages). */
+ unsigned long int u_ssize; /* Stack segment size (pages). */
+ unsigned long start_code; /* Starting virtual address of text. */
+ unsigned long start_stack; /* Starting virtual address of stack area.
+ This is actually the bottom of the stack,
+ the top of the stack is always found in the
+ esp register. */
+ long int signal; /* Signal that caused the core dump. */
+ int reserved; /* No longer used */
+ struct user_pt_regs * u_ar0; /* Used by gdb to help find the values for */
+ /* the registers. */
+ struct user_i387_struct* u_fpstate; /* Math Co-processor pointer. */
+ unsigned long magic; /* To uniquely identify a core file */
+ char u_comm[32]; /* User command that was responsible */
+ int u_debugreg[8];
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif /* _I386_USER_H */
--- /dev/null
+/*
+ * Access to VGA videoram
+ *
+ * (c) 1998 Martin Mares <mj@ucw.cz>
+ */
+
+#ifndef _LINUX_ASM_VGA_H_
+#define _LINUX_ASM_VGA_H_
+
+/*
+ * On the PC, we can just recalculate addresses and then
+ * access the videoram directly without any black magic.
+ */
+
+#define VGA_MAP_MEM(x) (unsigned long)phys_to_virt(x)
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x,y) (*(y) = (x))
+
+#endif
--- /dev/null
+/*
+ * include/asm-i386/xor.h
+ *
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * High-speed RAID5 checksumming functions utilizing MMX instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+#define FPU_SAVE \
+ do { \
+ if (!(current->flags & PF_USEDFPU)) \
+ __asm__ __volatile__ (" clts;\n"); \
+ __asm__ __volatile__ ("fsave %0; fwait": "=m"(fpu_save[0])); \
+ } while (0)
+
+#define FPU_RESTORE \
+ do { \
+ __asm__ __volatile__ ("frstor %0": : "m"(fpu_save[0])); \
+ if (!(current->flags & PF_USEDFPU)) \
+ stts(); \
+ } while (0)
+
+#define LD(x,y) " movq 8*("#x")(%1), %%mm"#y" ;\n"
+#define ST(x,y) " movq %%mm"#y", 8*("#x")(%1) ;\n"
+#define XO1(x,y) " pxor 8*("#x")(%2), %%mm"#y" ;\n"
+#define XO2(x,y) " pxor 8*("#x")(%3), %%mm"#y" ;\n"
+#define XO3(x,y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
+#define XO4(x,y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
+
+
+static void
+xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ ST(i,0) \
+ XO1(i+1,1) \
+ ST(i+1,1) \
+ XO1(i+2,2) \
+ ST(i+2,2) \
+ XO1(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ ST(i,0) \
+ XO2(i+1,1) \
+ ST(i+1,1) \
+ XO2(i+2,2) \
+ ST(i+2,2) \
+ XO2(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ ST(i,0) \
+ XO3(i+1,1) \
+ ST(i+1,1) \
+ XO3(i+2,2) \
+ ST(i+2,2) \
+ XO3(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " addl $128, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+
+static void
+xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ /* need to save/restore p4/p5 manually otherwise gcc's 10 argument
+ limit gets exceeded (+ counts as two arguments) */
+ __asm__ __volatile__ (
+ " pushl %4\n"
+ " pushl %5\n"
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ ST(i,0) \
+ XO4(i+1,1) \
+ ST(i+1,1) \
+ XO4(i+2,2) \
+ ST(i+2,2) \
+ XO4(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " addl $128, %4 ;\n"
+ " addl $128, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ " popl %5\n"
+ " popl %4\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ : "r" (p4), "r" (p5)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+#undef LD
+#undef XO1
+#undef XO2
+#undef XO3
+#undef XO4
+#undef ST
+#undef BLOCK
+
+static void
+xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ :
+ : "memory" );
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor (%4), %%mm0 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " pxor 8(%4), %%mm1 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " pxor 16(%4), %%mm2 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 24(%4), %%mm3 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " pxor 32(%4), %%mm4 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " pxor 40(%4), %%mm5 ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%4), %%mm6 ;\n"
+ " pxor 56(%4), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " addl $64, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ /* need to save p4/p5 manually to not exceed gcc's 10 argument limit */
+ __asm__ __volatile__ (
+ " pushl %4\n"
+ " pushl %5\n"
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " pxor (%4), %%mm0 ;\n"
+ " pxor 8(%4), %%mm1 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " pxor (%5), %%mm0 ;\n"
+ " pxor 8(%5), %%mm1 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 16(%4), %%mm2 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " pxor 16(%5), %%mm2 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 24(%4), %%mm3 ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 24(%5), %%mm3 ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%4), %%mm4 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " pxor 32(%5), %%mm4 ;\n"
+ " pxor 40(%4), %%mm5 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " pxor 40(%5), %%mm5 ;\n"
+ " pxor 48(%4), %%mm6 ;\n"
+ " pxor 56(%4), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%5), %%mm6 ;\n"
+ " pxor 56(%5), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " addl $64, %4 ;\n"
+ " addl $64, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ " popl %5\n"
+ " popl %4\n"
+ : "+g" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ : "r" (p4), "r" (p5)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static struct xor_block_template xor_block_pII_mmx = {
+ name: "pII_mmx",
+ do_2: xor_pII_mmx_2,
+ do_3: xor_pII_mmx_3,
+ do_4: xor_pII_mmx_4,
+ do_5: xor_pII_mmx_5,
+};
+
+static struct xor_block_template xor_block_p5_mmx = {
+ name: "p5_mmx",
+ do_2: xor_p5_mmx_2,
+ do_3: xor_p5_mmx_3,
+ do_4: xor_p5_mmx_4,
+ do_5: xor_p5_mmx_5,
+};
+
+#undef FPU_SAVE
+#undef FPU_RESTORE
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+#define XMMS_SAVE \
+ __asm__ __volatile__ ( \
+ "movl %%cr0,%0 ;\n\t" \
+ "clts ;\n\t" \
+ "movups %%xmm0,(%1) ;\n\t" \
+ "movups %%xmm1,0x10(%1) ;\n\t" \
+ "movups %%xmm2,0x20(%1) ;\n\t" \
+ "movups %%xmm3,0x30(%1) ;\n\t" \
+ : "=&r" (cr0) \
+ : "r" (xmm_save) \
+ : "memory")
+
+#define XMMS_RESTORE \
+ __asm__ __volatile__ ( \
+ "sfence ;\n\t" \
+ "movups (%1),%%xmm0 ;\n\t" \
+ "movups 0x10(%1),%%xmm1 ;\n\t" \
+ "movups 0x20(%1),%%xmm2 ;\n\t" \
+ "movups 0x30(%1),%%xmm3 ;\n\t" \
+ "movl %0,%%cr0 ;\n\t" \
+ : \
+ : "r" (cr0), "r" (xmm_save) \
+ : "memory")
+
+#define ALIGN16 __attribute__((aligned(16)))
+
+#define OFFS(x) "16*("#x")"
+#define PF_OFFS(x) "256+16*("#x")"
+#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n"
+#define LD(x,y) " movaps "OFFS(x)"(%1), %%xmm"#y" ;\n"
+#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%1) ;\n"
+#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n"
+#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n"
+#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n"
+#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n"
+#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n"
+#define XO1(x,y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n"
+#define XO2(x,y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n"
+#define XO3(x,y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n"
+#define XO4(x,y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n"
+#define XO5(x,y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2)
+ :
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r"(p2), "+r"(p3)
+ :
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " addl $256, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+ :
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ /* need to save p4/p5 manually to not exceed gcc's 10 argument limit */
+ __asm__ __volatile__ (
+ " pushl %4\n"
+ " pushl %5\n"
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ PF4(i) \
+ PF4(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ XO4(i+1,1) \
+ XO4(i+2,2) \
+ XO4(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " addl $256, %4 ;\n"
+ " addl $256, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ " popl %5\n"
+ " popl %4\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ : "r" (p4), "r" (p5)
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_pIII_sse = {
+ name: "pIII_sse",
+ do_2: xor_sse_2,
+ do_3: xor_sse_3,
+ do_4: xor_sse_4,
+ do_5: xor_sse_5,
+};
+
+/* Also try the generic routines. */
+#include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES \
+ do { \
+ xor_speed(&xor_block_8regs); \
+ xor_speed(&xor_block_32regs); \
+ if (cpu_has_xmm) \
+ xor_speed(&xor_block_pIII_sse); \
+ if (md_cpu_has_mmx()) { \
+ xor_speed(&xor_block_pII_mmx); \
+ xor_speed(&xor_block_p5_mmx); \
+ } \
+ } while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+ We may also be able to load into the L1 only depending on how the cpu
+ deals with a load to a line that is being prefetched. */
+#define XOR_SELECT_TEMPLATE(FASTEST) \
+ (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
--- /dev/null
+#ifndef _BLK_H
+#define _BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/locks.h>
+#include <linux/config.h>
+#include <linux/spinlock.h>
+
+/*
+ * Spinlock for protecting the request queue which
+ * is mucked around with in interrupts on potentially
+ * multiple CPU's..
+ */
+extern spinlock_t io_request_lock;
+
+/*
+ * Initialization functions.
+ */
+extern int isp16_init(void);
+extern int cdu31a_init(void);
+extern int acsi_init(void);
+extern int mcd_init(void);
+extern int mcdx_init(void);
+extern int sbpcd_init(void);
+extern int aztcd_init(void);
+extern int sony535_init(void);
+extern int gscd_init(void);
+extern int cm206_init(void);
+extern int optcd_init(void);
+extern int sjcd_init(void);
+extern int cdi_init(void);
+extern int hd_init(void);
+extern int ide_init(void);
+extern int xd_init(void);
+extern int mfm_init(void);
+extern int loop_init(void);
+extern int md_init(void);
+extern int ap_init(void);
+extern int ddv_init(void);
+extern int z2_init(void);
+extern int swim3_init(void);
+extern int swimiop_init(void);
+extern int amiga_floppy_init(void);
+extern int atari_floppy_init(void);
+extern int ez_init(void);
+extern int bpcd_init(void);
+extern int ps2esdi_init(void);
+extern int jsfd_init(void);
+extern int viodasd_init(void);
+extern int viocd_init(void);
+extern int xlblk_init(void);
+
+#if defined(CONFIG_ARCH_S390)
+extern int dasd_init(void);
+extern int xpram_init(void);
+extern int tapeblock_init(void);
+#endif /* CONFIG_ARCH_S390 */
+
+extern void set_device_ro(kdev_t dev,int flag);
+void add_blkdev_randomness(int major);
+
+extern int floppy_init(void);
+extern int rd_doload; /* 1 = load ramdisk, 0 = don't load */
+extern int rd_prompt; /* 1 = prompt for ramdisk, 0 = don't prompt */
+extern int rd_image_start; /* starting block # of image */
+
+#ifdef CONFIG_BLK_DEV_INITRD
+
+#define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */
+
+extern unsigned long initrd_start,initrd_end;
+extern int initrd_below_start_ok; /* 1 if it is not an error if initrd_start < memory_start */
+void initrd_init(void);
+
+#endif
+
+
+/*
+ * end_request() and friends. Must be called with the request queue spinlock
+ * acquired. All functions called within end_request() _must_be_ atomic.
+ *
+ * Several drivers define their own end_request and call
+ * end_that_request_first() and end_that_request_last()
+ * for parts of the original function. This prevents
+ * code duplication in drivers.
+ */
+
+static inline void blkdev_dequeue_request(struct request * req)
+{
+ list_del(&req->queue);
+}
+
+int end_that_request_first(struct request *req, int uptodate, char *name);
+void end_that_request_last(struct request *req);
+
+#if defined(MAJOR_NR) || defined(IDE_DRIVER)
+
+#undef DEVICE_ON
+#undef DEVICE_OFF
+
+/*
+ * Add entries as needed.
+ */
+
+#ifdef IDE_DRIVER
+
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+#define DEVICE_NAME "ide"
+
+#elif (MAJOR_NR == RAMDISK_MAJOR)
+
+/* ram disk */
+#define DEVICE_NAME "ramdisk"
+#define DEVICE_NR(device) (MINOR(device))
+#define DEVICE_NO_RANDOM
+
+#elif (MAJOR_NR == Z2RAM_MAJOR)
+
+/* Zorro II Ram */
+#define DEVICE_NAME "Z2RAM"
+#define DEVICE_REQUEST do_z2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == FLOPPY_MAJOR)
+
+static void floppy_off(unsigned int nr);
+
+#define DEVICE_NAME "floppy"
+#define DEVICE_INTR do_floppy
+#define DEVICE_REQUEST do_fd_request
+#define DEVICE_NR(device) ( (MINOR(device) & 3) | ((MINOR(device) & 0x80 ) >> 5 ))
+#define DEVICE_OFF(device) floppy_off(DEVICE_NR(device))
+
+#elif (MAJOR_NR == HD_MAJOR)
+
+/* Hard disk: timeout is 6 seconds. */
+#define DEVICE_NAME "hard disk"
+#define DEVICE_INTR do_hd
+#define TIMEOUT_VALUE (6*HZ)
+#define DEVICE_REQUEST do_hd_request
+#define DEVICE_NR(device) (MINOR(device)>>6)
+
+#elif (SCSI_DISK_MAJOR(MAJOR_NR))
+
+#define DEVICE_NAME "scsidisk"
+#define TIMEOUT_VALUE (2*HZ)
+#define DEVICE_NR(device) (((MAJOR(device) & SD_MAJOR_MASK) << (8 - 4)) + (MINOR(device) >> 4))
+
+/* Kludge to use the same number for both char and block major numbers */
+#elif (MAJOR_NR == MD_MAJOR) && defined(MD_DRIVER)
+
+#define DEVICE_NAME "Multiple devices driver"
+#define DEVICE_REQUEST do_md_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SCSI_TAPE_MAJOR)
+
+#define DEVICE_NAME "scsitape"
+#define DEVICE_INTR do_st
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+
+#elif (MAJOR_NR == OSST_MAJOR)
+
+#define DEVICE_NAME "onstream"
+#define DEVICE_INTR do_osst
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+#define DEVICE_ON(device)
+#define DEVICE_OFF(device)
+
+#elif (MAJOR_NR == SCSI_CDROM_MAJOR)
+
+#define DEVICE_NAME "CD-ROM"
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == XT_DISK_MAJOR)
+
+#define DEVICE_NAME "xt disk"
+#define DEVICE_REQUEST do_xd_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == PS2ESDI_MAJOR)
+
+#define DEVICE_NAME "PS/2 ESDI"
+#define DEVICE_REQUEST do_ps2esdi_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == CDU31A_CDROM_MAJOR)
+
+#define DEVICE_NAME "CDU31A"
+#define DEVICE_REQUEST do_cdu31a_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == ACSI_MAJOR) && (defined(CONFIG_ATARI_ACSI) || defined(CONFIG_ATARI_ACSI_MODULE))
+
+#define DEVICE_NAME "ACSI"
+#define DEVICE_INTR do_acsi
+#define DEVICE_REQUEST do_acsi_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#elif (MAJOR_NR == MITSUMI_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcd */
+#define DEVICE_REQUEST do_mcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MITSUMI_X_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcdx */
+#define DEVICE_REQUEST do_mcdx_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #1"
+#define DEVICE_REQUEST do_sbpcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM2_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #2"
+#define DEVICE_REQUEST do_sbpcd2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM3_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #3"
+#define DEVICE_REQUEST do_sbpcd3_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM4_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #4"
+#define DEVICE_REQUEST do_sbpcd4_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == AZTECH_CDROM_MAJOR)
+
+#define DEVICE_NAME "Aztech CD-ROM"
+#define DEVICE_REQUEST do_aztcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CDU535_CDROM_MAJOR)
+
+#define DEVICE_NAME "SONY-CDU535"
+#define DEVICE_INTR do_cdu535
+#define DEVICE_REQUEST do_cdu535_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == GOLDSTAR_CDROM_MAJOR)
+
+#define DEVICE_NAME "Goldstar R420"
+#define DEVICE_REQUEST do_gscd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CM206_CDROM_MAJOR)
+#define DEVICE_NAME "Philips/LMS CD-ROM cm206"
+#define DEVICE_REQUEST do_cm206_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == OPTICS_CDROM_MAJOR)
+
+#define DEVICE_NAME "DOLPHIN 8000AT CD-ROM"
+#define DEVICE_REQUEST do_optcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SANYO_CDROM_MAJOR)
+
+#define DEVICE_NAME "Sanyo H94A CD-ROM"
+#define DEVICE_REQUEST do_sjcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == APBLOCK_MAJOR)
+
+#define DEVICE_NAME "apblock"
+#define DEVICE_REQUEST ap_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DDV_MAJOR)
+
+#define DEVICE_NAME "ddv"
+#define DEVICE_REQUEST ddv_request
+#define DEVICE_NR(device) (MINOR(device)>>PARTN_BITS)
+
+#elif (MAJOR_NR == MFM_ACORN_MAJOR)
+
+#define DEVICE_NAME "mfm disk"
+#define DEVICE_INTR do_mfm
+#define DEVICE_REQUEST do_mfm_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == NBD_MAJOR)
+
+#define DEVICE_NAME "nbd"
+#define DEVICE_REQUEST do_nbd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MDISK_MAJOR)
+
+#define DEVICE_NAME "mdisk"
+#define DEVICE_REQUEST mdisk_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DASD_MAJOR)
+
+#define DEVICE_NAME "dasd"
+#define DEVICE_REQUEST do_dasd_request
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+
+#elif (MAJOR_NR == I2O_MAJOR)
+
+#define DEVICE_NAME "I2O block"
+#define DEVICE_REQUEST i2ob_request
+#define DEVICE_NR(device) (MINOR(device)>>4)
+
+#elif (MAJOR_NR == COMPAQ_SMART2_MAJOR)
+
+#define DEVICE_NAME "ida"
+#define TIMEOUT_VALUE (25*HZ)
+#define DEVICE_REQUEST do_ida_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#elif (MAJOR_NR == XLBLK_MAJOR)
+
+#define DEVICE_NAME "xeno disk"
+#define DEVICE_REQUEST do_xlblk_request
+/* #define DEVICE_INTR */
+#define DEVICE_NR(device) (MINOR(device))
+
+#endif /* MAJOR_NR == whatever */
+
+/* provide DEVICE_xxx defaults, if not explicitly defined
+ * above in the MAJOR_NR==xxx if-elif tree */
+#ifndef DEVICE_ON
+#define DEVICE_ON(device) do {} while (0)
+#endif
+#ifndef DEVICE_OFF
+#define DEVICE_OFF(device) do {} while (0)
+#endif
+
+#if (MAJOR_NR != SCSI_TAPE_MAJOR) && (MAJOR_NR != OSST_MAJOR)
+#if !defined(IDE_DRIVER)
+
+#ifndef CURRENT
+#define CURRENT blkdev_entry_next_request(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+#ifndef QUEUE_EMPTY
+#define QUEUE_EMPTY list_empty(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+
+#ifndef DEVICE_NAME
+#define DEVICE_NAME "unknown"
+#endif
+
+#define CURRENT_DEV DEVICE_NR(CURRENT->rq_dev)
+
+#ifdef DEVICE_INTR
+static void (*DEVICE_INTR)(void) = NULL;
+#endif
+
+#define SET_INTR(x) (DEVICE_INTR = (x))
+
+#ifdef DEVICE_REQUEST
+static void (DEVICE_REQUEST)(request_queue_t *);
+#endif
+
+#ifdef DEVICE_INTR
+#define CLEAR_INTR SET_INTR(NULL)
+#else
+#define CLEAR_INTR
+#endif
+
+#define INIT_REQUEST \
+ if (QUEUE_EMPTY) {\
+ CLEAR_INTR; \
+ return; \
+ } \
+ if (MAJOR(CURRENT->rq_dev) != MAJOR_NR) \
+ panic(DEVICE_NAME ": request list destroyed"); \
+ if (CURRENT->bh) { \
+ if (!buffer_locked(CURRENT->bh)) \
+ panic(DEVICE_NAME ": block not locked"); \
+ }
+
+#endif /* !defined(IDE_DRIVER) */
+
+
+#ifndef LOCAL_END_REQUEST /* If we have our own end_request, we do not want to include this mess */
+
+#if ! SCSI_BLK_MAJOR(MAJOR_NR) && (MAJOR_NR != COMPAQ_SMART2_MAJOR)
+
+static inline void end_request(int uptodate) {
+ struct request *req = CURRENT;
+
+ if (end_that_request_first(req, uptodate, DEVICE_NAME))
+ return;
+
+#ifndef DEVICE_NO_RANDOM
+ add_blkdev_randomness(MAJOR(req->rq_dev));
+#endif
+ DEVICE_OFF(req->rq_dev);
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+}
+
+#endif /* ! SCSI_BLK_MAJOR(MAJOR_NR) */
+#endif /* LOCAL_END_REQUEST */
+
+#endif /* (MAJOR_NR != SCSI_TAPE_MAJOR) */
+#endif /* defined(MAJOR_NR) || defined(IDE_DRIVER) */
+
+#endif /* _BLK_H */
--- /dev/null
+#ifndef _LINUX_MAJOR_H
+#define _LINUX_MAJOR_H
+
+/*
+ * This file has definitions for major device numbers.
+ * For the device number assignments, see Documentation/devices.txt.
+ */
+
+/* limits */
+
+/*
+ * Important: Don't change this to 256. Major number 255 is and must be
+ * reserved for future expansion into a larger dev_t space.
+ */
+#define MAX_CHRDEV 255
+#define MAX_BLKDEV 255
+
+#define UNNAMED_MAJOR 0
+#define MEM_MAJOR 1
+#define RAMDISK_MAJOR 1
+#define FLOPPY_MAJOR 2
+#define PTY_MASTER_MAJOR 2
+#define IDE0_MAJOR 3
+#define PTY_SLAVE_MAJOR 3
+#define HD_MAJOR IDE0_MAJOR
+#define TTY_MAJOR 4
+#define TTYAUX_MAJOR 5
+#define LP_MAJOR 6
+#define VCS_MAJOR 7
+#define LOOP_MAJOR 7
+#define SCSI_DISK0_MAJOR 8
+#define SCSI_TAPE_MAJOR 9
+#define MD_MAJOR 9
+#define MISC_MAJOR 10
+#define SCSI_CDROM_MAJOR 11
+#define MUX_MAJOR 11 /* PA-RISC only */
+#define QIC02_TAPE_MAJOR 12
+#define XT_DISK_MAJOR 13
+#define SOUND_MAJOR 14
+#define CDU31A_CDROM_MAJOR 15
+#define JOYSTICK_MAJOR 15
+#define GOLDSTAR_CDROM_MAJOR 16
+#define OPTICS_CDROM_MAJOR 17
+#define SANYO_CDROM_MAJOR 18
+#define CYCLADES_MAJOR 19
+#define CYCLADESAUX_MAJOR 20
+#define MITSUMI_X_CDROM_MAJOR 20
+#define MFM_ACORN_MAJOR 21 /* ARM Linux /dev/mfm */
+#define SCSI_GENERIC_MAJOR 21
+#define Z8530_MAJOR 34
+#define DIGI_MAJOR 23
+#define IDE1_MAJOR 22
+#define DIGICU_MAJOR 22
+#define MITSUMI_CDROM_MAJOR 23
+#define CDU535_CDROM_MAJOR 24
+#define STL_SERIALMAJOR 24
+#define MATSUSHITA_CDROM_MAJOR 25
+#define STL_CALLOUTMAJOR 25
+#define MATSUSHITA_CDROM2_MAJOR 26
+#define QIC117_TAPE_MAJOR 27
+#define MATSUSHITA_CDROM3_MAJOR 27
+#define MATSUSHITA_CDROM4_MAJOR 28
+#define STL_SIOMEMMAJOR 28
+#define ACSI_MAJOR 28
+#define AZTECH_CDROM_MAJOR 29
+#define GRAPHDEV_MAJOR 29 /* SparcLinux & Linux/68k /dev/fb */
+#define SHMIQ_MAJOR 85 /* Linux/mips, SGI /dev/shmiq */
+#define CM206_CDROM_MAJOR 32
+#define IDE2_MAJOR 33
+#define IDE3_MAJOR 34
+#define XPRAM_MAJOR 35 /* expanded storage on S/390 = "slow ram" */
+ /* proposed by Peter */
+#define NETLINK_MAJOR 36
+#define PS2ESDI_MAJOR 36
+#define IDETAPE_MAJOR 37
+#define Z2RAM_MAJOR 37
+#define APBLOCK_MAJOR 38 /* AP1000 Block device */
+#define DDV_MAJOR 39 /* AP1000 DDV block device */
+#define NBD_MAJOR 43 /* Network block device */
+#define RISCOM8_NORMAL_MAJOR 48
+#define DAC960_MAJOR 48 /* 48..55 */
+#define RISCOM8_CALLOUT_MAJOR 49
+#define MKISS_MAJOR 55
+#define DSP56K_MAJOR 55 /* DSP56001 processor device */
+
+#define IDE4_MAJOR 56
+#define IDE5_MAJOR 57
+
+#define LVM_BLK_MAJOR 58 /* Logical Volume Manager */
+
+#define SCSI_DISK1_MAJOR 65
+#define SCSI_DISK2_MAJOR 66
+#define SCSI_DISK3_MAJOR 67
+#define SCSI_DISK4_MAJOR 68
+#define SCSI_DISK5_MAJOR 69
+#define SCSI_DISK6_MAJOR 70
+#define SCSI_DISK7_MAJOR 71
+
+
+#define COMPAQ_SMART2_MAJOR 72
+#define COMPAQ_SMART2_MAJOR1 73
+#define COMPAQ_SMART2_MAJOR2 74
+#define COMPAQ_SMART2_MAJOR3 75
+#define COMPAQ_SMART2_MAJOR4 76
+#define COMPAQ_SMART2_MAJOR5 77
+#define COMPAQ_SMART2_MAJOR6 78
+#define COMPAQ_SMART2_MAJOR7 79
+
+#define SPECIALIX_NORMAL_MAJOR 75
+#define SPECIALIX_CALLOUT_MAJOR 76
+
+#define COMPAQ_CISS_MAJOR 104
+#define COMPAQ_CISS_MAJOR1 105
+#define COMPAQ_CISS_MAJOR2 106
+#define COMPAQ_CISS_MAJOR3 107
+#define COMPAQ_CISS_MAJOR4 108
+#define COMPAQ_CISS_MAJOR5 109
+#define COMPAQ_CISS_MAJOR6 110
+#define COMPAQ_CISS_MAJOR7 111
+
+#define ATARAID_MAJOR 114
+
+#define DASD_MAJOR 94 /* Official assignations from Peter */
+
+#define MDISK_MAJOR 95 /* Official assignations from Peter */
+
+#define I2O_MAJOR 80 /* 80->87 */
+
+#define IDE6_MAJOR 88
+#define IDE7_MAJOR 89
+#define IDE8_MAJOR 90
+#define IDE9_MAJOR 91
+
+#define UBD_MAJOR 98
+
+#define AURORA_MAJOR 79
+
+#define JSFD_MAJOR 99
+
+#define PHONE_MAJOR 100
+
+#define LVM_CHAR_MAJOR 109 /* Logical Volume Manager */
+
+#define UMEM_MAJOR 116 /* http://www.umem.com/ Battery Backed RAM */
+
+#define UMEM_MAJOR 116 /* http://www.umem.com/ Battery Backed RAM */
+
+#define XLBLK_MAJOR 123 /* XenoLinux Block Device */
+
+#define RTF_MAJOR 150
+#define RAW_MAJOR 162
+
+#define USB_ACM_MAJOR 166
+#define USB_ACM_AUX_MAJOR 167
+#define USB_CHAR_MAJOR 180
+
+#define UNIX98_PTY_MASTER_MAJOR 128
+#define UNIX98_PTY_MAJOR_COUNT 8
+#define UNIX98_PTY_SLAVE_MAJOR (UNIX98_PTY_MASTER_MAJOR+UNIX98_PTY_MAJOR_COUNT)
+
+#define VXVM_MAJOR 199 /* VERITAS volume i/o driver */
+#define VXSPEC_MAJOR 200 /* VERITAS volume config driver */
+#define VXDMP_MAJOR 201 /* VERITAS volume multipath driver */
+
+#define MSR_MAJOR 202
+#define CPUID_MAJOR 203
+
+#define OSST_MAJOR 206 /* OnStream-SCx0 SCSI tape */
+
+#define IBM_TTY3270_MAJOR 227 /* Official allocations now */
+#define IBM_FS3270_MAJOR 228
+
+/*
+ * Tests for SCSI devices.
+ */
+
+#define SCSI_DISK_MAJOR(M) ((M) == SCSI_DISK0_MAJOR || \
+ ((M) >= SCSI_DISK1_MAJOR && (M) <= SCSI_DISK7_MAJOR))
+
+#define SCSI_BLK_MAJOR(M) \
+ (SCSI_DISK_MAJOR(M) \
+ || (M) == SCSI_CDROM_MAJOR)
+
+static __inline__ int scsi_blk_major(int m) {
+ return SCSI_BLK_MAJOR(m);
+}
+
+/*
+ * Tests for IDE devices
+ */
+#define IDE_DISK_MAJOR(M) ((M) == IDE0_MAJOR || (M) == IDE1_MAJOR || \
+ (M) == IDE2_MAJOR || (M) == IDE3_MAJOR || \
+ (M) == IDE4_MAJOR || (M) == IDE5_MAJOR || \
+ (M) == IDE6_MAJOR || (M) == IDE7_MAJOR || \
+ (M) == IDE8_MAJOR || (M) == IDE9_MAJOR)
+
+static __inline__ int ide_blk_major(int m)
+{
+ return IDE_DISK_MAJOR(m);
+}
+
+#endif
--- /dev/null
+/*
+ * linux/include/linux/sunrpc/debug.h
+ *
+ * Debugging support for sunrpc module
+ *
+ * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LINUX_SUNRPC_DEBUG_H_
+#define _LINUX_SUNRPC_DEBUG_H_
+
+#include <linux/config.h>
+
+#include <linux/timer.h>
+#include <linux/tqueue.h>
+
+/*
+ * Enable RPC debugging/profiling.
+ */
+/*#ifdef CONFIG_SYSCTL*/
+/*#define RPC_DEBUG*/
+/*#endif*/
+/* #define RPC_PROFILE */
+
+/*
+ * RPC debug facilities
+ */
+#define RPCDBG_XPRT 0x0001
+#define RPCDBG_CALL 0x0002
+#define RPCDBG_DEBUG 0x0004
+#define RPCDBG_NFS 0x0008
+#define RPCDBG_AUTH 0x0010
+#define RPCDBG_PMAP 0x0020
+#define RPCDBG_SCHED 0x0040
+#define RPCDBG_SVCSOCK 0x0100
+#define RPCDBG_SVCDSP 0x0200
+#define RPCDBG_MISC 0x0400
+#define RPCDBG_ALL 0x7fff
+
+#ifdef __KERNEL__
+
+/*
+ * Debugging macros etc
+ */
+#ifdef RPC_DEBUG
+extern unsigned int rpc_debug;
+extern unsigned int nfs_debug;
+extern unsigned int nfsd_debug;
+extern unsigned int nlm_debug;
+#endif
+
+#define dprintk(args...) dfprintk(FACILITY, ## args)
+
+#undef ifdebug
+#ifdef RPC_DEBUG
+# define ifdebug(fac) if (rpc_debug & RPCDBG_##fac)
+# define dfprintk(fac, args...) do { ifdebug(fac) printk(args); } while(0)
+# define RPC_IFDEBUG(x) x
+#else
+# define dfprintk(fac, args...) do ; while (0)
+# define RPC_IFDEBUG(x)
+#endif
+
+#ifdef RPC_PROFILE
+# define pprintk(args...) printk(## args)
+#else
+# define pprintk(args...) do ; while (0)
+#endif
+
+/*
+ * Sysctl interface for RPC debugging
+ */
+#ifdef RPC_DEBUG
+void rpc_register_sysctl(void);
+void rpc_unregister_sysctl(void);
+#endif
+
+#endif /* __KERNEL__ */
+
+/*
+ * Declarations for the sysctl debug interface, which allows to read or
+ * change the debug flags for rpc, nfs, nfsd, and lockd. Since the sunrpc
+ * module currently registers its sysctl table dynamically, the sysctl path
+ * for module FOO is <CTL_SUNRPC, CTL_FOODEBUG>.
+ */
+#define CTL_SUNRPC 7249 /* arbitrary and hopefully unused */
+
+enum {
+ CTL_RPCDEBUG = 1,
+ CTL_NFSDEBUG,
+ CTL_NFSDDEBUG,
+ CTL_NLMDEBUG,
+};
+
+#endif /* _LINUX_SUNRPC_DEBUG_H_ */
--- /dev/null
+#define __KERNEL_SYSCALLS__
+#include <linux/config.h>
+#include <linux/slab.h>
+#include <linux/devfs_fs_kernel.h>
+#include <linux/unistd.h>
+#include <linux/ctype.h>
+#include <linux/blk.h>
+#include <linux/fd.h>
+#include <linux/tty.h>
+#include <linux/init.h>
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/nfs_mount.h>
+#include <linux/minix_fs.h>
+#include <linux/ext2_fs.h>
+#include <linux/romfs_fs.h>
+
+#define BUILD_CRAMDISK
+
+extern int get_filesystem_list(char * buf);
+
+extern asmlinkage long sys_mount(char *dev_name, char *dir_name, char *type,
+ unsigned long flags, void *data);
+extern asmlinkage long sys_mkdir(const char *name, int mode);
+extern asmlinkage long sys_chdir(const char *name);
+extern asmlinkage long sys_fchdir(int fd);
+extern asmlinkage long sys_chroot(const char *name);
+extern asmlinkage long sys_unlink(const char *name);
+extern asmlinkage long sys_symlink(const char *old, const char *new);
+extern asmlinkage long sys_mknod(const char *name, int mode, dev_t dev);
+extern asmlinkage long sys_umount(char *name, int flags);
+extern asmlinkage long sys_ioctl(int fd, int cmd, unsigned long arg);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+unsigned int real_root_dev; /* do_proc_dointvec cannot handle kdev_t */
+static int __initdata mount_initrd = 1;
+
+static int __init no_initrd(char *str)
+{
+ mount_initrd = 0;
+ return 1;
+}
+
+__setup("noinitrd", no_initrd);
+#else
+static int __initdata mount_initrd = 0;
+#endif
+
+int __initdata rd_doload; /* 1 = load RAM disk, 0 = don't load */
+
+int root_mountflags = MS_RDONLY | MS_VERBOSE;
+static char root_device_name[64];
+
+/* this is initialized in init/main.c */
+kdev_t ROOT_DEV;
+
+static int do_devfs = 0;
+
+static int __init load_ramdisk(char *str)
+{
+ rd_doload = simple_strtol(str,NULL,0) & 3;
+ return 1;
+}
+__setup("load_ramdisk=", load_ramdisk);
+
+static int __init readonly(char *str)
+{
+ if (*str)
+ return 0;
+ root_mountflags |= MS_RDONLY;
+ return 1;
+}
+
+static int __init readwrite(char *str)
+{
+ if (*str)
+ return 0;
+ root_mountflags &= ~MS_RDONLY;
+ return 1;
+}
+
+__setup("ro", readonly);
+__setup("rw", readwrite);
+
+static struct dev_name_struct {
+ const char *name;
+ const int num;
+} root_dev_names[] __initdata = {
+ { "nfs", 0x00ff },
+ { "hda", 0x0300 },
+ { "hdb", 0x0340 },
+ { "loop", 0x0700 },
+ { "hdc", 0x1600 },
+ { "hdd", 0x1640 },
+ { "hde", 0x2100 },
+ { "hdf", 0x2140 },
+ { "hdg", 0x2200 },
+ { "hdh", 0x2240 },
+ { "hdi", 0x3800 },
+ { "hdj", 0x3840 },
+ { "hdk", 0x3900 },
+ { "hdl", 0x3940 },
+ { "hdm", 0x5800 },
+ { "hdn", 0x5840 },
+ { "hdo", 0x5900 },
+ { "hdp", 0x5940 },
+ { "hdq", 0x5A00 },
+ { "hdr", 0x5A40 },
+ { "hds", 0x5B00 },
+ { "hdt", 0x5B40 },
+ { "sda", 0x0800 },
+ { "sdb", 0x0810 },
+ { "sdc", 0x0820 },
+ { "sdd", 0x0830 },
+ { "sde", 0x0840 },
+ { "sdf", 0x0850 },
+ { "sdg", 0x0860 },
+ { "sdh", 0x0870 },
+ { "sdi", 0x0880 },
+ { "sdj", 0x0890 },
+ { "sdk", 0x08a0 },
+ { "sdl", 0x08b0 },
+ { "sdm", 0x08c0 },
+ { "sdn", 0x08d0 },
+ { "sdo", 0x08e0 },
+ { "sdp", 0x08f0 },
+ { "ada", 0x1c00 },
+ { "adb", 0x1c10 },
+ { "adc", 0x1c20 },
+ { "add", 0x1c30 },
+ { "ade", 0x1c40 },
+ { "fd", 0x0200 },
+ { "md", 0x0900 },
+ { "xda", 0x0d00 },
+ { "xdb", 0x0d40 },
+ { "ram", 0x0100 },
+ { "scd", 0x0b00 },
+ { "mcd", 0x1700 },
+ { "cdu535", 0x1800 },
+ { "sonycd", 0x1800 },
+ { "aztcd", 0x1d00 },
+ { "cm206cd", 0x2000 },
+ { "gscd", 0x1000 },
+ { "sbpcd", 0x1900 },
+ { "eda", 0x2400 },
+ { "edb", 0x2440 },
+ { "pda", 0x2d00 },
+ { "pdb", 0x2d10 },
+ { "pdc", 0x2d20 },
+ { "pdd", 0x2d30 },
+ { "pcd", 0x2e00 },
+ { "pf", 0x2f00 },
+ { "apblock", APBLOCK_MAJOR << 8},
+ { "ddv", DDV_MAJOR << 8},
+ { "jsfd", JSFD_MAJOR << 8},
+#if defined(CONFIG_ARCH_S390)
+ { "dasda", (DASD_MAJOR << MINORBITS) },
+ { "dasdb", (DASD_MAJOR << MINORBITS) + (1 << 2) },
+ { "dasdc", (DASD_MAJOR << MINORBITS) + (2 << 2) },
+ { "dasdd", (DASD_MAJOR << MINORBITS) + (3 << 2) },
+ { "dasde", (DASD_MAJOR << MINORBITS) + (4 << 2) },
+ { "dasdf", (DASD_MAJOR << MINORBITS) + (5 << 2) },
+ { "dasdg", (DASD_MAJOR << MINORBITS) + (6 << 2) },
+ { "dasdh", (DASD_MAJOR << MINORBITS) + (7 << 2) },
+#endif
+#if defined(CONFIG_BLK_CPQ_DA) || defined(CONFIG_BLK_CPQ_DA_MODULE)
+ { "ida/c0d0p",0x4800 },
+ { "ida/c0d1p",0x4810 },
+ { "ida/c0d2p",0x4820 },
+ { "ida/c0d3p",0x4830 },
+ { "ida/c0d4p",0x4840 },
+ { "ida/c0d5p",0x4850 },
+ { "ida/c0d6p",0x4860 },
+ { "ida/c0d7p",0x4870 },
+ { "ida/c0d8p",0x4880 },
+ { "ida/c0d9p",0x4890 },
+ { "ida/c0d10p",0x48A0 },
+ { "ida/c0d11p",0x48B0 },
+ { "ida/c0d12p",0x48C0 },
+ { "ida/c0d13p",0x48D0 },
+ { "ida/c0d14p",0x48E0 },
+ { "ida/c0d15p",0x48F0 },
+ { "ida/c1d0p",0x4900 },
+ { "ida/c2d0p",0x4A00 },
+ { "ida/c3d0p",0x4B00 },
+ { "ida/c4d0p",0x4C00 },
+ { "ida/c5d0p",0x4D00 },
+ { "ida/c6d0p",0x4E00 },
+ { "ida/c7d0p",0x4F00 },
+#endif
+#if defined(CONFIG_BLK_CPQ_CISS_DA) || defined(CONFIG_BLK_CPQ_CISS_DA_MODULE)
+ { "cciss/c0d0p",0x6800 },
+ { "cciss/c0d1p",0x6810 },
+ { "cciss/c0d2p",0x6820 },
+ { "cciss/c0d3p",0x6830 },
+ { "cciss/c0d4p",0x6840 },
+ { "cciss/c0d5p",0x6850 },
+ { "cciss/c0d6p",0x6860 },
+ { "cciss/c0d7p",0x6870 },
+ { "cciss/c0d8p",0x6880 },
+ { "cciss/c0d9p",0x6890 },
+ { "cciss/c0d10p",0x68A0 },
+ { "cciss/c0d11p",0x68B0 },
+ { "cciss/c0d12p",0x68C0 },
+ { "cciss/c0d13p",0x68D0 },
+ { "cciss/c0d14p",0x68E0 },
+ { "cciss/c0d15p",0x68F0 },
+ { "cciss/c1d0p",0x6900 },
+ { "cciss/c2d0p",0x6A00 },
+ { "cciss/c3d0p",0x6B00 },
+ { "cciss/c4d0p",0x6C00 },
+ { "cciss/c5d0p",0x6D00 },
+ { "cciss/c6d0p",0x6E00 },
+ { "cciss/c7d0p",0x6F00 },
+#endif
+ { "ataraid/d0p",0x7200 },
+ { "ataraid/d1p",0x7210 },
+ { "ataraid/d2p",0x7220 },
+ { "ataraid/d3p",0x7230 },
+ { "ataraid/d4p",0x7240 },
+ { "ataraid/d5p",0x7250 },
+ { "ataraid/d6p",0x7260 },
+ { "ataraid/d7p",0x7270 },
+ { "ataraid/d8p",0x7280 },
+ { "ataraid/d9p",0x7290 },
+ { "ataraid/d10p",0x72A0 },
+ { "ataraid/d11p",0x72B0 },
+ { "ataraid/d12p",0x72C0 },
+ { "ataraid/d13p",0x72D0 },
+ { "ataraid/d14p",0x72E0 },
+ { "ataraid/d15p",0x72F0 },
+#if defined(CONFIG_XENOLINUX_BLOCK)
+ { "xhda", 0x7B00 },
+ { "xhdb", 0x7C00 },
+ { "xhdc", 0x7D00 },
+ { "xhdd", 0x7E00 },
+#endif
+ { "nftla", 0x5d00 },
+ { "nftlb", 0x5d10 },
+ { "nftlc", 0x5d20 },
+ { "nftld", 0x5d30 },
+ { "ftla", 0x2c00 },
+ { "ftlb", 0x2c08 },
+ { "ftlc", 0x2c10 },
+ { "ftld", 0x2c18 },
+ { "mtdblock", 0x1f00 },
+ { NULL, 0 }
+};
+
+kdev_t __init name_to_kdev_t(char *line)
+{
+ int base = 0, offs;
+ char *end;
+
+ if (strncmp(line,"/dev/",5) == 0) {
+ struct dev_name_struct *dev = root_dev_names;
+ line += 5;
+ do {
+ int len = strlen(dev->name);
+ if (strncmp(line,dev->name,len) == 0) {
+ line += len;
+ base = dev->num;
+ break;
+ }
+ dev++;
+ } while (dev->name);
+ }
+ offs = simple_strtoul(line, &end, base?10:16);
+ if (*end)
+ offs = 0;
+ return to_kdev_t(base + offs);
+}
+
+static int __init root_dev_setup(char *line)
+{
+ int i;
+ char ch;
+
+ ROOT_DEV = name_to_kdev_t(line);
+ memset (root_device_name, 0, sizeof root_device_name);
+ if (strncmp (line, "/dev/", 5) == 0) line += 5;
+ for (i = 0; i < sizeof root_device_name - 1; ++i)
+ {
+ ch = line[i];
+ if ( isspace (ch) || (ch == ',') || (ch == '\0') ) break;
+ root_device_name[i] = ch;
+ }
+ return 1;
+}
+
+__setup("root=", root_dev_setup);
+
+static char * __initdata root_mount_data;
+static int __init root_data_setup(char *str)
+{
+ root_mount_data = str;
+ return 1;
+}
+
+static char * __initdata root_fs_names;
+static int __init fs_names_setup(char *str)
+{
+ root_fs_names = str;
+ return 1;
+}
+
+__setup("rootflags=", root_data_setup);
+__setup("rootfstype=", fs_names_setup);
+
+static void __init get_fs_names(char *page)
+{
+ char *s = page;
+
+ if (root_fs_names) {
+ strcpy(page, root_fs_names);
+ while (*s++) {
+ if (s[-1] == ',')
+ s[-1] = '\0';
+ }
+ } else {
+ int len = get_filesystem_list(page);
+ char *p, *next;
+
+ page[len] = '\0';
+ for (p = page-1; p; p = next) {
+ next = strchr(++p, '\n');
+ if (*p++ != '\t')
+ continue;
+ while ((*s++ = *p++) != '\n')
+ ;
+ s[-1] = '\0';
+ }
+ }
+ *s = '\0';
+}
+static void __init mount_block_root(char *name, int flags)
+{
+ char *fs_names = __getname();
+ char *p;
+
+ get_fs_names(fs_names);
+retry:
+ for (p = fs_names; *p; p += strlen(p)+1) {
+ int err = sys_mount(name, "/root", p, flags, root_mount_data);
+ switch (err) {
+ case 0:
+ goto out;
+ case -EACCES:
+ flags |= MS_RDONLY;
+ goto retry;
+ case -EINVAL:
+ continue;
+ }
+ /*
+ * Allow the user to distinguish between failed open
+ * and bad superblock on root device.
+ */
+ printk ("VFS: Cannot open root device \"%s\" or %s\n",
+ root_device_name, kdevname (ROOT_DEV));
+ printk ("Please append a correct \"root=\" boot option\n");
+ panic("VFS: Unable to mount root fs on %s",
+ kdevname(ROOT_DEV));
+ }
+ panic("VFS: Unable to mount root fs on %s", kdevname(ROOT_DEV));
+out:
+ putname(fs_names);
+ sys_chdir("/root");
+ ROOT_DEV = current->fs->pwdmnt->mnt_sb->s_dev;
+ printk("VFS: Mounted root (%s filesystem)%s.\n",
+ current->fs->pwdmnt->mnt_sb->s_type->name,
+ (current->fs->pwdmnt->mnt_sb->s_flags & MS_RDONLY) ? " readonly" : "");
+}
+
+#ifdef CONFIG_ROOT_NFS
+static int __init mount_nfs_root(void)
+{
+ void *data = nfs_root_data();
+
+ if (data && sys_mount("/dev/root","/root","nfs",root_mountflags,data) == 0)
+ return 1;
+ return 0;
+}
+#endif
+
+static int __init create_dev(char *name, kdev_t dev, char *devfs_name)
+{
+ void *handle;
+ char path[64];
+ int n;
+
+ sys_unlink(name);
+ if (!do_devfs)
+ return sys_mknod(name, S_IFBLK|0600, kdev_t_to_nr(dev));
+
+ handle = devfs_find_handle(NULL, dev ? NULL : devfs_name,
+ MAJOR(dev), MINOR(dev), DEVFS_SPECIAL_BLK, 1);
+ if (!handle)
+ return -1;
+ n = devfs_generate_path(handle, path + 5, sizeof (path) - 5);
+ if (n < 0)
+ return -1;
+ return sys_symlink(path + n + 5, name);
+}
+
+#if defined(CONFIG_BLK_DEV_RAM) || defined(CONFIG_BLK_DEV_FD)
+static void __init change_floppy(char *fmt, ...)
+{
+ struct termios termios;
+ char buf[80];
+ char c;
+ int fd;
+ va_list args;
+ va_start(args, fmt);
+ vsprintf(buf, fmt, args);
+ va_end(args);
+ fd = open("/dev/root", O_RDWR | O_NDELAY, 0);
+ if (fd >= 0) {
+ sys_ioctl(fd, FDEJECT, 0);
+ close(fd);
+ }
+ printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf);
+ fd = open("/dev/console", O_RDWR, 0);
+ if (fd >= 0) {
+ sys_ioctl(fd, TCGETS, (long)&termios);
+ termios.c_lflag &= ~ICANON;
+ sys_ioctl(fd, TCSETSF, (long)&termios);
+ read(fd, &c, 1);
+ termios.c_lflag |= ICANON;
+ sys_ioctl(fd, TCSETSF, (long)&termios);
+ close(fd);
+ }
+}
+#endif
+
+#ifdef CONFIG_BLK_DEV_RAM
+
+int __initdata rd_prompt = 1; /* 1 = prompt for RAM disk, 0 = don't prompt */
+
+static int __init prompt_ramdisk(char *str)
+{
+ rd_prompt = simple_strtol(str,NULL,0) & 1;
+ return 1;
+}
+__setup("prompt_ramdisk=", prompt_ramdisk);
+
+int __initdata rd_image_start; /* starting block # of image */
+
+static int __init ramdisk_start_setup(char *str)
+{
+ rd_image_start = simple_strtol(str,NULL,0);
+ return 1;
+}
+__setup("ramdisk_start=", ramdisk_start_setup);
+
+static int __init crd_load(int in_fd, int out_fd);
+
+/*
+ * This routine tries to find a RAM disk image to load, and returns the
+ * number of blocks to read for a non-compressed image, 0 if the image
+ * is a compressed image, and -1 if an image with the right magic
+ * numbers could not be found.
+ *
+ * We currently check for the following magic numbers:
+ * minix
+ * ext2
+ * romfs
+ * gzip
+ */
+static int __init
+identify_ramdisk_image(int fd, int start_block)
+{
+ const int size = 512;
+ struct minix_super_block *minixsb;
+ struct ext2_super_block *ext2sb;
+ struct romfs_super_block *romfsb;
+ int nblocks = -1;
+ unsigned char *buf;
+
+ buf = kmalloc(size, GFP_KERNEL);
+ if (buf == 0)
+ return -1;
+
+ minixsb = (struct minix_super_block *) buf;
+ ext2sb = (struct ext2_super_block *) buf;
+ romfsb = (struct romfs_super_block *) buf;
+ memset(buf, 0xe5, size);
+
+ /*
+ * Read block 0 to test for gzipped kernel
+ */
+ lseek(fd, start_block * BLOCK_SIZE, 0);
+ read(fd, buf, size);
+
+ /*
+ * If it matches the gzip magic numbers, return -1
+ */
+ if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) {
+ printk(KERN_NOTICE
+ "RAMDISK: Compressed image found at block %d\n",
+ start_block);
+ nblocks = 0;
+ goto done;
+ }
+
+ /* romfs is at block zero too */
+ if (romfsb->word0 == ROMSB_WORD0 &&
+ romfsb->word1 == ROMSB_WORD1) {
+ printk(KERN_NOTICE
+ "RAMDISK: romfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ /*
+ * Read block 1 to test for minix and ext2 superblock
+ */
+ lseek(fd, (start_block+1) * BLOCK_SIZE, 0);
+ read(fd, buf, size);
+
+ /* Try minix */
+ if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
+ minixsb->s_magic == MINIX_SUPER_MAGIC2) {
+ printk(KERN_NOTICE
+ "RAMDISK: Minix filesystem found at block %d\n",
+ start_block);
+ nblocks = minixsb->s_nzones << minixsb->s_log_zone_size;
+ goto done;
+ }
+
+ /* Try ext2 */
+ if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) {
+ printk(KERN_NOTICE
+ "RAMDISK: ext2 filesystem found at block %d\n",
+ start_block);
+ nblocks = le32_to_cpu(ext2sb->s_blocks_count);
+ goto done;
+ }
+
+ printk(KERN_NOTICE
+ "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
+ start_block);
+
+done:
+ lseek(fd, start_block * BLOCK_SIZE, 0);
+ kfree(buf);
+ return nblocks;
+}
+#endif
+
+static int __init rd_load_image(char *from)
+{
+ int res = 0;
+
+#ifdef CONFIG_BLK_DEV_RAM
+ int in_fd, out_fd;
+ unsigned long rd_blocks, devblocks;
+ int nblocks, i;
+ char *buf;
+ unsigned short rotate = 0;
+#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES)
+ char rotator[4] = { '|' , '/' , '-' , '\\' };
+#endif
+
+ out_fd = open("/dev/ram", O_RDWR, 0);
+ if (out_fd < 0)
+ goto out;
+
+ in_fd = open(from, O_RDONLY, 0);
+ if (in_fd < 0)
+ goto noclose_input;
+
+ nblocks = identify_ramdisk_image(in_fd, rd_image_start);
+ if (nblocks < 0)
+ goto done;
+
+ if (nblocks == 0) {
+#ifdef BUILD_CRAMDISK
+ if (crd_load(in_fd, out_fd) == 0)
+ goto successful_load;
+#else
+ printk(KERN_NOTICE
+ "RAMDISK: Kernel does not support compressed "
+ "RAM disk images\n");
+#endif
+ goto done;
+ }
+
+ /*
+ * NOTE NOTE: nblocks suppose that the blocksize is BLOCK_SIZE, so
+ * rd_load_image will work only with filesystem BLOCK_SIZE wide!
+ * So make sure to use 1k blocksize while generating ext2fs
+ * ramdisk-images.
+ */
+ if (sys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0)
+ rd_blocks = 0;
+ else
+ rd_blocks >>= 1;
+
+ if (nblocks > rd_blocks) {
+ printk("RAMDISK: image too big! (%d/%lu blocks)\n",
+ nblocks, rd_blocks);
+ goto done;
+ }
+
+ /*
+ * OK, time to copy in the data
+ */
+ buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
+ if (buf == 0) {
+ printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
+ goto done;
+ }
+
+ if (sys_ioctl(in_fd, BLKGETSIZE, (unsigned long)&devblocks) < 0)
+ devblocks = 0;
+ else
+ devblocks >>= 1;
+
+ if (strcmp(from, "/dev/initrd") == 0)
+ devblocks = nblocks;
+
+ if (devblocks == 0) {
+ printk(KERN_ERR "RAMDISK: could not determine device size\n");
+ goto done;
+ }
+
+ printk(KERN_NOTICE "RAMDISK: Loading %d blocks [%ld disk%s] into ram disk... ",
+ nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
+ for (i=0; i < nblocks; i++) {
+ if (i && (i % devblocks == 0)) {
+ printk("done disk #%ld.\n", i/devblocks);
+ rotate = 0;
+ if (close(in_fd)) {
+ printk("Error closing the disk.\n");
+ goto noclose_input;
+ }
+ change_floppy("disk #%d", i/devblocks+1);
+ in_fd = open(from, O_RDONLY, 0);
+ if (in_fd < 0) {
+ printk("Error opening disk.\n");
+ goto noclose_input;
+ }
+ printk("Loading disk #%ld... ", i/devblocks+1);
+ }
+ read(in_fd, buf, BLOCK_SIZE);
+ write(out_fd, buf, BLOCK_SIZE);
+#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES)
+ if (!(i % 16)) {
+ printk("%c\b", rotator[rotate & 0x3]);
+ rotate++;
+ }
+#endif
+ }
+ printk("done.\n");
+ kfree(buf);
+
+successful_load:
+ res = 1;
+done:
+ close(in_fd);
+noclose_input:
+ close(out_fd);
+out:
+ sys_unlink("/dev/ram");
+#endif
+ return res;
+}
+
+static int __init rd_load_disk(int n)
+{
+#ifdef CONFIG_BLK_DEV_RAM
+ if (rd_prompt)
+ change_floppy("root floppy disk to be loaded into RAM disk");
+ create_dev("/dev/ram", MKDEV(RAMDISK_MAJOR, n), NULL);
+#endif
+ return rd_load_image("/dev/root");
+}
+
+#ifdef CONFIG_DEVFS_FS
+
+static void __init convert_name(char *prefix, char *name, char *p, int part)
+{
+ int host, bus, target, lun;
+ char dest[64];
+ char src[64];
+ char *base = p - 1;
+
+ /* Decode "c#b#t#u#" */
+ if (*p++ != 'c')
+ return;
+ host = simple_strtol(p, &p, 10);
+ if (*p++ != 'b')
+ return;
+ bus = simple_strtol(p, &p, 10);
+ if (*p++ != 't')
+ return;
+ target = simple_strtol(p, &p, 10);
+ if (*p++ != 'u')
+ return;
+ lun = simple_strtol(p, &p, 10);
+ if (!part)
+ sprintf(dest, "%s/host%d/bus%d/target%d/lun%d",
+ prefix, host, bus, target, lun);
+ else if (*p++ == 'p')
+ sprintf(dest, "%s/host%d/bus%d/target%d/lun%d/part%s",
+ prefix, host, bus, target, lun, p);
+ else
+ sprintf(dest, "%s/host%d/bus%d/target%d/lun%d/disc",
+ prefix, host, bus, target, lun);
+ *base = '\0';
+ sprintf(src, "/dev/%s", name);
+ sys_mkdir(src, 0755);
+ *base = '/';
+ sprintf(src, "/dev/%s", name);
+ sys_symlink(dest, src);
+}
+
+static void __init devfs_make_root(char *name)
+{
+
+ if (!strncmp(name, "sd/", 3))
+ convert_name("../scsi", name, name+3, 1);
+ else if (!strncmp(name, "sr/", 3))
+ convert_name("../scsi", name, name+3, 0);
+ else if (!strncmp(name, "ide/hd/", 7))
+ convert_name("..", name, name + 7, 1);
+ else if (!strncmp(name, "ide/cd/", 7))
+ convert_name("..", name, name + 7, 0);
+}
+#else
+static void __init devfs_make_root(char *name)
+{
+}
+#endif
+
+static void __init mount_root(void)
+{
+#ifdef CONFIG_ROOT_NFS
+ if (MAJOR(ROOT_DEV) == UNNAMED_MAJOR) {
+ if (mount_nfs_root()) {
+ sys_chdir("/root");
+ ROOT_DEV = current->fs->pwdmnt->mnt_sb->s_dev;
+ printk("VFS: Mounted root (nfs filesystem).\n");
+ return;
+ }
+ printk(KERN_ERR "VFS: Unable to mount root fs via NFS, trying floppy.\n");
+ ROOT_DEV = MKDEV(FLOPPY_MAJOR, 0);
+ }
+#endif
+printk("root_device_name = %s\n",root_device_name);
+ devfs_make_root(root_device_name);
+ create_dev("/dev/root", ROOT_DEV, root_device_name);
+#ifdef CONFIG_BLK_DEV_FD
+ if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
+ /* rd_doload is 2 for a dual initrd/ramload setup */
+ if (rd_doload==2) {
+ if (rd_load_disk(1)) {
+ ROOT_DEV = MKDEV(RAMDISK_MAJOR, 1);
+ create_dev("/dev/root", ROOT_DEV, NULL);
+ }
+ } else
+ change_floppy("root floppy");
+ }
+#endif
+ mount_block_root("/dev/root", root_mountflags);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static int old_fd, root_fd;
+static int do_linuxrc(void * shell)
+{
+ static char *argv[] = { "linuxrc", NULL, };
+ extern char * envp_init[];
+
+ close(old_fd);
+ close(root_fd);
+ close(0);
+ close(1);
+ close(2);
+ setsid();
+ (void) open("/dev/console",O_RDWR,0);
+ (void) dup(0);
+ (void) dup(0);
+ return execve(shell, argv, envp_init);
+}
+
+#endif
+
+static void __init handle_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ int ram0 = kdev_t_to_nr(MKDEV(RAMDISK_MAJOR,0));
+ int error;
+ int i, pid;
+
+ create_dev("/dev/root.old", ram0, NULL);
+ /* mount initrd on rootfs' /root */
+ mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
+ sys_mkdir("/old", 0700);
+ root_fd = open("/", 0, 0);
+ old_fd = open("/old", 0, 0);
+ /* move initrd over / and chdir/chroot in initrd root */
+ sys_chdir("/root");
+ sys_mount(".", "/", NULL, MS_MOVE, NULL);
+ sys_chroot(".");
+ mount_devfs_fs ();
+
+ pid = kernel_thread(do_linuxrc, "/linuxrc", SIGCHLD);
+ if (pid > 0) {
+ while (pid != wait(&i))
+ yield();
+ }
+
+ /* move initrd to rootfs' /old */
+ sys_fchdir(old_fd);
+ sys_mount("/", ".", NULL, MS_MOVE, NULL);
+ /* switch root and cwd back to / of rootfs */
+ sys_fchdir(root_fd);
+ sys_chroot(".");
+ sys_umount("/old/dev", 0);
+
+ if (real_root_dev == ram0) {
+ sys_chdir("/old");
+ return;
+ }
+
+ ROOT_DEV = real_root_dev;
+ mount_root();
+
+ printk(KERN_NOTICE "Trying to move old root to /initrd ... ");
+ error = sys_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
+ if (!error)
+ printk("okay\n");
+ else {
+ int fd = open("/dev/root.old", O_RDWR, 0);
+ printk("failed\n");
+ printk(KERN_NOTICE "Unmounting old root\n");
+ sys_umount("/old", MNT_DETACH);
+ printk(KERN_NOTICE "Trying to free ramdisk memory ... ");
+ if (fd < 0) {
+ error = fd;
+ } else {
+ error = sys_ioctl(fd, BLKFLSBUF, 0);
+ close(fd);
+ }
+ printk(!error ? "okay\n" : "failed\n");
+ }
+#endif
+}
+
+static int __init initrd_load(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ create_dev("/dev/ram", MKDEV(RAMDISK_MAJOR, 0), NULL);
+ create_dev("/dev/initrd", MKDEV(RAMDISK_MAJOR, INITRD_MINOR), NULL);
+#endif
+ return rd_load_image("/dev/initrd");
+}
+
+/*
+ * Prepare the namespace - decide what/where to mount, load ramdisks, etc.
+ */
+void prepare_namespace(void)
+{
+ int is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
+#ifdef CONFIG_ALL_PPC
+ extern void arch_discover_root(void);
+ arch_discover_root();
+#endif /* CONFIG_ALL_PPC */
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (!initrd_start)
+ mount_initrd = 0;
+ real_root_dev = ROOT_DEV;
+#endif
+ sys_mkdir("/dev", 0700);
+ sys_mkdir("/root", 0700);
+ sys_mknod("/dev/console", S_IFCHR|0600, MKDEV(TTYAUX_MAJOR, 1));
+#ifdef CONFIG_DEVFS_FS
+ sys_mount("devfs", "/dev", "devfs", 0, NULL);
+ do_devfs = 1;
+#endif
+
+ create_dev("/dev/root", ROOT_DEV, NULL);
+ if (mount_initrd) {
+ if (initrd_load() && ROOT_DEV != MKDEV(RAMDISK_MAJOR, 0)) {
+ handle_initrd();
+ goto out;
+ }
+ } else if (is_floppy && rd_doload && rd_load_disk(0))
+ ROOT_DEV = MKDEV(RAMDISK_MAJOR, 0);
+ mount_root();
+out:
+ sys_umount("/dev", 0);
+ sys_mount(".", "/", NULL, MS_MOVE, NULL);
+ sys_chroot(".");
+ mount_devfs_fs ();
+}
+
+#if defined(BUILD_CRAMDISK) && defined(CONFIG_BLK_DEV_RAM)
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args) args
+
+#ifndef memzero
+#define memzero(s, n) memset ((s), 0, (n))
+#endif
+
+typedef unsigned char uch;
+typedef unsigned short ush;
+typedef unsigned long ulg;
+
+#define INBUFSIZ 4096
+#define WSIZE 0x8000 /* window size--must be a power of two, and */
+ /* at least 32K for zip's deflate method */
+
+static uch *inbuf;
+static uch *window;
+
+static unsigned insize; /* valid bytes in inbuf */
+static unsigned inptr; /* index of next byte to be processed in inbuf */
+static unsigned outcnt; /* bytes in output buffer */
+static int exit_code;
+static long bytes_out;
+static int crd_infd, crd_outfd;
+
+#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+
+/* Diagnostic functions (stubbed out) */
+#define Assert(cond,msg)
+#define Trace(x)
+#define Tracev(x)
+#define Tracevv(x)
+#define Tracec(c,x)
+#define Tracecv(c,x)
+
+#define STATIC static
+
+static int fill_inbuf(void);
+static void flush_window(void);
+static void *malloc(int size);
+static void free(void *where);
+static void error(char *m);
+static void gzip_mark(void **);
+static void gzip_release(void **);
+
+#include "../lib/inflate.c"
+
+static void __init *malloc(int size)
+{
+ return kmalloc(size, GFP_KERNEL);
+}
+
+static void __init free(void *where)
+{
+ kfree(where);
+}
+
+static void __init gzip_mark(void **ptr)
+{
+}
+
+static void __init gzip_release(void **ptr)
+{
+}
+
+
+/* ===========================================================================
+ * Fill the input buffer. This is called only when the buffer is empty
+ * and at least one byte is really needed.
+ */
+static int __init fill_inbuf(void)
+{
+ if (exit_code) return -1;
+
+ insize = read(crd_infd, inbuf, INBUFSIZ);
+ if (insize == 0) return -1;
+
+ inptr = 1;
+
+ return inbuf[0];
+}
+
+/* ===========================================================================
+ * Write the output window window[0..outcnt-1] and update crc and bytes_out.
+ * (Used for the decompressed data only.)
+ */
+static void __init flush_window(void)
+{
+ ulg c = crc; /* temporary variable */
+ unsigned n;
+ uch *in, ch;
+
+ write(crd_outfd, window, outcnt);
+ in = window;
+ for (n = 0; n < outcnt; n++) {
+ ch = *in++;
+ c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
+ }
+ crc = c;
+ bytes_out += (ulg)outcnt;
+ outcnt = 0;
+}
+
+static void __init error(char *x)
+{
+ printk(KERN_ERR "%s", x);
+ exit_code = 1;
+}
+
+static int __init crd_load(int in_fd, int out_fd)
+{
+ int result;
+
+ insize = 0; /* valid bytes in inbuf */
+ inptr = 0; /* index of next byte to be processed in inbuf */
+ outcnt = 0; /* bytes in output buffer */
+ exit_code = 0;
+ bytes_out = 0;
+ crc = (ulg)0xffffffffL; /* shift register contents */
+
+ crd_infd = in_fd;
+ crd_outfd = out_fd;
+ inbuf = kmalloc(INBUFSIZ, GFP_KERNEL);
+ if (inbuf == 0) {
+ printk(KERN_ERR "RAMDISK: Couldn't allocate gzip buffer\n");
+ return -1;
+ }
+ window = kmalloc(WSIZE, GFP_KERNEL);
+ if (window == 0) {
+ printk(KERN_ERR "RAMDISK: Couldn't allocate gzip window\n");
+ kfree(inbuf);
+ return -1;
+ }
+ makecrc();
+ result = gunzip();
+ kfree(inbuf);
+ kfree(window);
+ return result;
+}
+
+#endif /* BUILD_CRAMDISK && CONFIG_BLK_DEV_RAM */
--- /dev/null
+/*
+ * linux/kernel/panic.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * This function is used through-out the kernel (including mm and fs)
+ * to indicate a major problem.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/sysrq.h>
+#include <linux/interrupt.h>
+
+asmlinkage void sys_sync(void); /* it's really int */
+
+int panic_timeout;
+
+struct notifier_block *panic_notifier_list;
+
+static int __init panic_setup(char *str)
+{
+ panic_timeout = simple_strtoul(str, NULL, 0);
+ return 1;
+}
+
+__setup("panic=", panic_setup);
+
+/**
+ * panic - halt the system
+ * @fmt: The text string to print
+ *
+ * Display a message, then perform cleanups. Functions in the panic
+ * notifier list are called after the filesystem cache is flushed (when possible).
+ *
+ * This function never returns.
+ */
+
+NORET_TYPE void panic(const char * fmt, ...)
+{
+ static char buf[1024];
+ va_list args;
+#if defined(CONFIG_ARCH_S390)
+ unsigned long caller = (unsigned long) __builtin_return_address(0);
+#endif
+
+ bust_spinlocks(1);
+ va_start(args, fmt);
+ vsprintf(buf, fmt, args);
+ va_end(args);
+ printk(KERN_EMERG "Kernel panic: %s\n",buf);
+ if (in_interrupt())
+ printk(KERN_EMERG "In interrupt handler - not syncing\n");
+ else if (!current->pid)
+ printk(KERN_EMERG "In idle task - not syncing\n");
+ else
+ sys_sync();
+ bust_spinlocks(0);
+
+#ifdef CONFIG_SMP
+ smp_send_stop();
+#endif
+
+ notifier_call_chain(&panic_notifier_list, 0, NULL);
+
+ if (panic_timeout > 0)
+ {
+ /*
+ * Delay timeout seconds before rebooting the machine.
+ * We can't use the "normal" timers since we just panicked..
+ */
+ printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
+ mdelay(panic_timeout*1000);
+ /*
+ * Should we run the reboot notifier. For the moment Im
+ * choosing not too. It might crash, be corrupt or do
+ * more harm than good for other reasons.
+ */
+ machine_restart(NULL);
+ }
+#ifdef __sparc__
+ {
+ extern int stop_a_enabled;
+ /* Make sure the user can actually press L1-A */
+ stop_a_enabled = 1;
+ printk("Press L1-A to return to the boot prom\n");
+ }
+#endif
+#if defined(CONFIG_ARCH_S390)
+ disabled_wait(caller);
+#endif
+ sti();
+ for(;;) {
+#if defined(CONFIG_X86) && defined(CONFIG_VT)
+ extern void panic_blink(void);
+ panic_blink();
+#endif
+ CHECK_EMERGENCY_SYNC
+#if defined(CONFIG_XENO)
+ HYPERVISOR_exit();
+#endif
+ }
+}
+
+/**
+ * print_tainted - return a string to represent the kernel taint state.
+ *
+ * The string is overwritten by the next call to print_taint().
+ */
+
+const char *print_tainted()
+{
+ static char buf[20];
+ if (tainted) {
+ snprintf(buf, sizeof(buf), "Tainted: %c%c",
+ tainted & 1 ? 'P' : 'G',
+ tainted & 2 ? 'F' : ' ');
+ }
+ else
+ snprintf(buf, sizeof(buf), "Not tainted");
+ return(buf);
+}
+
+int tainted = 0;
+
+/*
+ * A BUG() call in an inline function in a header should be avoided,
+ * because it can seriously bloat the kernel. So here we have
+ * helper functions.
+ * We lose the BUG()-time file-and-line info this way, but it's
+ * usually not very useful from an inline anyway. The backtrace
+ * tells us what we want to know.
+ */
+
+void __out_of_line_bug(int line)
+{
+ printk("kernel BUG in header file at line %d\n", line);
+
+ BUG();
+
+ /* Satisfy __attribute__((noreturn)) */
+ for ( ; ; )
+ ;
+}
--- /dev/null
+/*
+ * linux/mm/memory.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ */
+
+/*
+ * demand-loading started 01.12.91 - seems it is high on the list of
+ * things wanted, and it should be easy to implement. - Linus
+ */
+
+/*
+ * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
+ * pages started 02.12.91, seems to work. - Linus.
+ *
+ * Tested sharing by executing about 30 /bin/sh: under the old kernel it
+ * would have taken more than the 6M I have free, but it worked well as
+ * far as I could see.
+ *
+ * Also corrected some "invalidate()"s - I wasn't doing enough of them.
+ */
+
+/*
+ * Real VM (paging to/from disk) started 18.12.91. Much more work and
+ * thought has to go into this. Oh, well..
+ * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
+ * Found it. Everything seems to work now.
+ * 20.12.91 - Ok, making the swap-device changeable like the root.
+ */
+
+/*
+ * 05.04.94 - Multi-page memory management added for v1.1.
+ * Idea by Alex Bligh (alex@cconcepts.co.uk)
+ *
+ * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
+ * (Gerhard.Wichert@pdb.siemens.de)
+ */
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/module.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+
+unsigned long max_mapnr;
+unsigned long num_physpages;
+unsigned long num_mappedpages;
+void * high_memory;
+struct page *highmem_start_page;
+
+/*
+ * We special-case the C-O-W ZERO_PAGE, because it's such
+ * a common occurrence (no need to read the page to know
+ * that it's zero - better for the cache and memory subsystem).
+ */
+static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address)
+{
+ if (from == ZERO_PAGE(address)) {
+ clear_user_highpage(to, address);
+ return;
+ }
+ copy_user_highpage(to, from, address);
+}
+
+mem_map_t * mem_map;
+
+/*
+ * Called by TLB shootdown
+ */
+void __free_pte(pte_t pte)
+{
+ struct page *page = pte_page(pte);
+ if ((!VALID_PAGE(page)) || PageReserved(page))
+ return;
+ if (pte_dirty(pte))
+ set_page_dirty(page);
+ free_page_and_swap_cache(page);
+}
+
+
+/*
+ * Note: this doesn't free the actual pages themselves. That
+ * has been handled earlier when unmapping all the memory regions.
+ */
+static inline void free_one_pmd(pmd_t * dir)
+{
+ pte_t * pte;
+
+ if (pmd_none(*dir))
+ return;
+ if (pmd_bad(*dir)) {
+ pmd_ERROR(*dir);
+ pmd_clear(dir);
+ return;
+ }
+ pte = pte_offset(dir, 0);
+ pmd_clear(dir);
+ pte_free(pte);
+}
+
+static inline void free_one_pgd(pgd_t * dir)
+{
+ int j;
+ pmd_t * pmd;
+
+ if (pgd_none(*dir))
+ return;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return;
+ }
+ pmd = pmd_offset(dir, 0);
+ pgd_clear(dir);
+ for (j = 0; j < PTRS_PER_PMD ; j++) {
+ prefetchw(pmd+j+(PREFETCH_STRIDE/16));
+ free_one_pmd(pmd+j);
+ }
+ pmd_free(pmd);
+}
+
+/* Low and high watermarks for page table cache.
+ The system should try to have pgt_water[0] <= cache elements <= pgt_water[1]
+ */
+int pgt_cache_water[2] = { 25, 50 };
+
+/* Returns the number of pages freed */
+int check_pgt_cache(void)
+{
+ return do_check_pgt_cache(pgt_cache_water[0], pgt_cache_water[1]);
+}
+
+
+/*
+ * This function clears all user-level page tables of a process - this
+ * is needed by execve(), so that old pages aren't in the way.
+ */
+void clear_page_tables(struct mm_struct *mm, unsigned long first, int nr)
+{
+ pgd_t * page_dir = mm->pgd;
+
+ spin_lock(&mm->page_table_lock);
+ page_dir += first;
+ do {
+ free_one_pgd(page_dir);
+ page_dir++;
+ } while (--nr);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+
+ /* keep the page table cache within bounds */
+ check_pgt_cache();
+}
+
+#define PTE_TABLE_MASK ((PTRS_PER_PTE-1) * sizeof(pte_t))
+#define PMD_TABLE_MASK ((PTRS_PER_PMD-1) * sizeof(pmd_t))
+
+/*
+ * copy one vm_area from one task to the other. Assumes the page tables
+ * already present in the new task to be cleared in the whole range
+ * covered by this vma.
+ *
+ * 08Jan98 Merged into one routine from several inline routines to reduce
+ * variable count and make things faster. -jj
+ *
+ * dst->page_table_lock is held on entry and exit,
+ * but may be dropped within pmd_alloc() and pte_alloc().
+ */
+int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
+ struct vm_area_struct *vma)
+{
+ pgd_t * src_pgd, * dst_pgd;
+ unsigned long address = vma->vm_start;
+ unsigned long end = vma->vm_end;
+ unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+
+ src_pgd = pgd_offset(src, address)-1;
+ dst_pgd = pgd_offset(dst, address)-1;
+
+ for (;;) {
+ pmd_t * src_pmd, * dst_pmd;
+
+ src_pgd++; dst_pgd++;
+
+ /* copy_pmd_range */
+
+ if (pgd_none(*src_pgd))
+ goto skip_copy_pmd_range;
+ if (pgd_bad(*src_pgd)) {
+ pgd_ERROR(*src_pgd);
+ pgd_clear(src_pgd);
+skip_copy_pmd_range: address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ if (!address || (address >= end))
+ goto out;
+ continue;
+ }
+
+ src_pmd = pmd_offset(src_pgd, address);
+ dst_pmd = pmd_alloc(dst, dst_pgd, address);
+ if (!dst_pmd)
+ goto nomem;
+
+ do {
+ pte_t * src_pte, * dst_pte;
+
+ /* copy_pte_range */
+
+ if (pmd_none(*src_pmd))
+ goto skip_copy_pte_range;
+ if (pmd_bad(*src_pmd)) {
+ pmd_ERROR(*src_pmd);
+ pmd_clear(src_pmd);
+skip_copy_pte_range: address = (address + PMD_SIZE) & PMD_MASK;
+ if (address >= end)
+ goto out;
+ goto cont_copy_pmd_range;
+ }
+
+ src_pte = pte_offset(src_pmd, address);
+ dst_pte = pte_alloc(dst, dst_pmd, address);
+ if (!dst_pte)
+ goto nomem;
+
+ spin_lock(&src->page_table_lock);
+ do {
+ pte_t pte = *src_pte;
+ struct page *ptepage;
+
+ /* copy_one_pte */
+
+ if (pte_none(pte))
+ goto cont_copy_pte_range_noset;
+ if (!pte_present(pte)) {
+ swap_duplicate(pte_to_swp_entry(pte));
+ goto cont_copy_pte_range;
+ }
+ ptepage = pte_page(pte);
+ if ((!VALID_PAGE(ptepage)) ||
+ PageReserved(ptepage))
+ goto cont_copy_pte_range;
+
+ /* If it's a COW mapping, write protect it both in the parent and the child */
+ if (cow && pte_write(pte)) {
+ /* XENO modification: modified ordering here to avoid RaW hazard. */
+ pte = *src_pte;
+ pte = pte_wrprotect(pte);
+ ptep_set_wrprotect(src_pte);
+ }
+
+ /* If it's a shared mapping, mark it clean in the child */
+ if (vma->vm_flags & VM_SHARED)
+ pte = pte_mkclean(pte);
+ pte = pte_mkold(pte);
+ get_page(ptepage);
+ dst->rss++;
+
+cont_copy_pte_range: set_pte(dst_pte, pte);
+cont_copy_pte_range_noset: address += PAGE_SIZE;
+ if (address >= end)
+ goto out_unlock;
+ src_pte++;
+ dst_pte++;
+ } while ((unsigned long)src_pte & PTE_TABLE_MASK);
+ spin_unlock(&src->page_table_lock);
+
+cont_copy_pmd_range: src_pmd++;
+ dst_pmd++;
+ } while ((unsigned long)src_pmd & PMD_TABLE_MASK);
+ }
+out_unlock:
+ spin_unlock(&src->page_table_lock);
+out:
+ return 0;
+nomem:
+ return -ENOMEM;
+}
+
+/*
+ * Return indicates whether a page was freed so caller can adjust rss
+ */
+static inline void forget_pte(pte_t page)
+{
+ if (!pte_none(page)) {
+ printk("forget_pte: old mapping existed!\n");
+ BUG();
+ }
+}
+
+static inline int zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address, unsigned long size)
+{
+ unsigned long offset;
+ pte_t * ptep;
+ int freed = 0;
+
+ if (pmd_none(*pmd))
+ return 0;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return 0;
+ }
+ ptep = pte_offset(pmd, address);
+ offset = address & ~PMD_MASK;
+ if (offset + size > PMD_SIZE)
+ size = PMD_SIZE - offset;
+ size &= PAGE_MASK;
+ for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
+ pte_t pte = *ptep;
+ if (pte_none(pte))
+ continue;
+ if (pte_present(pte)) {
+ struct page *page = pte_page(pte);
+ if (VALID_PAGE(page) && !PageReserved(page))
+ freed ++;
+ /* This will eventually call __free_pte on the pte. */
+ tlb_remove_page(tlb, ptep, address + offset);
+ } else {
+ free_swap_and_cache(pte_to_swp_entry(pte));
+ pte_clear(ptep);
+ }
+ }
+
+ return freed;
+}
+
+static inline int zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir, unsigned long address, unsigned long size)
+{
+ pmd_t * pmd;
+ unsigned long end;
+ int freed;
+
+ if (pgd_none(*dir))
+ return 0;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return 0;
+ }
+ pmd = pmd_offset(dir, address);
+ end = address + size;
+ if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
+ end = ((address + PGDIR_SIZE) & PGDIR_MASK);
+ freed = 0;
+ do {
+ freed += zap_pte_range(tlb, pmd, address, end - address);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address < end);
+ return freed;
+}
+
+/*
+ * remove user pages in a given range.
+ */
+void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
+{
+ mmu_gather_t *tlb;
+ pgd_t * dir;
+ unsigned long start = address, end = address + size;
+ int freed = 0;
+
+ dir = pgd_offset(mm, address);
+
+ /*
+ * This is a long-lived spinlock. That's fine.
+ * There's no contention, because the page table
+ * lock only protects against kswapd anyway, and
+ * even if kswapd happened to be looking at this
+ * process we _want_ it to get stuck.
+ */
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ flush_cache_range(mm, address, end);
+ tlb = tlb_gather_mmu(mm);
+
+ do {
+ freed += zap_pmd_range(tlb, dir, address, end - address);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+
+ /* this will flush any remaining tlb entries */
+ tlb_finish_mmu(tlb, start, end);
+
+ /*
+ * Update rss for the mm_struct (not necessarily current->mm)
+ * Notice that rss is an unsigned long.
+ */
+ if (mm->rss > freed)
+ mm->rss -= freed;
+ else
+ mm->rss = 0;
+ spin_unlock(&mm->page_table_lock);
+}
+
+/*
+ * Do a quick page-table lookup for a single page.
+ */
+static struct page * follow_page(struct mm_struct *mm, unsigned long address, int write)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
+
+ pgd = pgd_offset(mm, address);
+ if (pgd_none(*pgd) || pgd_bad(*pgd))
+ goto out;
+
+ pmd = pmd_offset(pgd, address);
+ if (pmd_none(*pmd) || pmd_bad(*pmd))
+ goto out;
+
+ ptep = pte_offset(pmd, address);
+ if (!ptep)
+ goto out;
+
+ pte = *ptep;
+ if (pte_present(pte)) {
+ if (!write ||
+ (pte_write(pte) && pte_dirty(pte)))
+ return pte_page(pte);
+ }
+
+out:
+ return 0;
+}
+
+/*
+ * Given a physical address, is there a useful struct page pointing to
+ * it? This may become more complex in the future if we start dealing
+ * with IO-aperture pages in kiobufs.
+ */
+
+static inline struct page * get_page_map(struct page *page)
+{
+ if (!VALID_PAGE(page))
+ return 0;
+ return page;
+}
+
+/*
+ * Please read Documentation/cachetlb.txt before using this function,
+ * accessing foreign memory spaces can cause cache coherency problems.
+ *
+ * Accessing a VM_IO area is even more dangerous, therefore the function
+ * fails if pages is != NULL and a VM_IO area is found.
+ */
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
+ int len, int write, int force, struct page **pages, struct vm_area_struct **vmas)
+{
+ int i;
+ unsigned int flags;
+
+ /*
+ * Require read or write permissions.
+ * If 'force' is set, we only require the "MAY" flags.
+ */
+ flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+ i = 0;
+
+ do {
+ struct vm_area_struct * vma;
+
+ vma = find_extend_vma(mm, start);
+
+ if ( !vma || (pages && vma->vm_flags & VM_IO) || !(flags & vma->vm_flags) )
+ return i ? : -EFAULT;
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ struct page *map;
+ while (!(map = follow_page(mm, start, write))) {
+ spin_unlock(&mm->page_table_lock);
+ switch (handle_mm_fault(mm, vma, start, write)) {
+ case 1:
+ tsk->min_flt++;
+ break;
+ case 2:
+ tsk->maj_flt++;
+ break;
+ case 0:
+ if (i) return i;
+ return -EFAULT;
+ default:
+ if (i) return i;
+ return -ENOMEM;
+ }
+ spin_lock(&mm->page_table_lock);
+ }
+ if (pages) {
+ pages[i] = get_page_map(map);
+ /* FIXME: call the correct function,
+ * depending on the type of the found page
+ */
+ if (!pages[i])
+ goto bad_page;
+ page_cache_get(pages[i]);
+ }
+ if (vmas)
+ vmas[i] = vma;
+ i++;
+ start += PAGE_SIZE;
+ len--;
+ } while(len && start < vma->vm_end);
+ spin_unlock(&mm->page_table_lock);
+ } while(len);
+out:
+ return i;
+
+ /*
+ * We found an invalid page in the VMA. Release all we have
+ * so far and fail.
+ */
+bad_page:
+ spin_unlock(&mm->page_table_lock);
+ while (i--)
+ page_cache_release(pages[i]);
+ i = -EFAULT;
+ goto out;
+}
+
+EXPORT_SYMBOL(get_user_pages);
+
+/*
+ * Force in an entire range of pages from the current process's user VA,
+ * and pin them in physical memory.
+ */
+#define dprintk(x...)
+
+int map_user_kiobuf(int rw, struct kiobuf *iobuf, unsigned long va, size_t len)
+{
+ int pgcount, err;
+ struct mm_struct * mm;
+
+ /* Make sure the iobuf is not already mapped somewhere. */
+ if (iobuf->nr_pages)
+ return -EINVAL;
+
+ mm = current->mm;
+ dprintk ("map_user_kiobuf: begin\n");
+
+ pgcount = (va + len + PAGE_SIZE - 1)/PAGE_SIZE - va/PAGE_SIZE;
+ /* mapping 0 bytes is not permitted */
+ if (!pgcount) BUG();
+ err = expand_kiobuf(iobuf, pgcount);
+ if (err)
+ return err;
+
+ iobuf->locked = 0;
+ iobuf->offset = va & (PAGE_SIZE-1);
+ iobuf->length = len;
+
+ /* Try to fault in all of the necessary pages */
+ down_read(&mm->mmap_sem);
+ /* rw==READ means read from disk, write into memory area */
+ err = get_user_pages(current, mm, va, pgcount,
+ (rw==READ), 0, iobuf->maplist, NULL);
+ up_read(&mm->mmap_sem);
+ if (err < 0) {
+ unmap_kiobuf(iobuf);
+ dprintk ("map_user_kiobuf: end %d\n", err);
+ return err;
+ }
+ iobuf->nr_pages = err;
+ while (pgcount--) {
+ /* FIXME: flush superflous for rw==READ,
+ * probably wrong function for rw==WRITE
+ */
+ flush_dcache_page(iobuf->maplist[pgcount]);
+ }
+ dprintk ("map_user_kiobuf: end OK\n");
+ return 0;
+}
+
+/*
+ * Mark all of the pages in a kiobuf as dirty
+ *
+ * We need to be able to deal with short reads from disk: if an IO error
+ * occurs, the number of bytes read into memory may be less than the
+ * size of the kiobuf, so we have to stop marking pages dirty once the
+ * requested byte count has been reached.
+ *
+ * Must be called from process context - set_page_dirty() takes VFS locks.
+ */
+
+void mark_dirty_kiobuf(struct kiobuf *iobuf, int bytes)
+{
+ int index, offset, remaining;
+ struct page *page;
+
+ index = iobuf->offset >> PAGE_SHIFT;
+ offset = iobuf->offset & ~PAGE_MASK;
+ remaining = bytes;
+ if (remaining > iobuf->length)
+ remaining = iobuf->length;
+
+ while (remaining > 0 && index < iobuf->nr_pages) {
+ page = iobuf->maplist[index];
+
+ if (!PageReserved(page))
+ set_page_dirty(page);
+
+ remaining -= (PAGE_SIZE - offset);
+ offset = 0;
+ index++;
+ }
+}
+
+/*
+ * Unmap all of the pages referenced by a kiobuf. We release the pages,
+ * and unlock them if they were locked.
+ */
+
+void unmap_kiobuf (struct kiobuf *iobuf)
+{
+ int i;
+ struct page *map;
+
+ for (i = 0; i < iobuf->nr_pages; i++) {
+ map = iobuf->maplist[i];
+ if (map) {
+ if (iobuf->locked)
+ UnlockPage(map);
+ /* FIXME: cache flush missing for rw==READ
+ * FIXME: call the correct reference counting function
+ */
+ page_cache_release(map);
+ }
+ }
+
+ iobuf->nr_pages = 0;
+ iobuf->locked = 0;
+}
+
+
+/*
+ * Lock down all of the pages of a kiovec for IO.
+ *
+ * If any page is mapped twice in the kiovec, we return the error -EINVAL.
+ *
+ * The optional wait parameter causes the lock call to block until all
+ * pages can be locked if set. If wait==0, the lock operation is
+ * aborted if any locked pages are found and -EAGAIN is returned.
+ */
+
+int lock_kiovec(int nr, struct kiobuf *iovec[], int wait)
+{
+ struct kiobuf *iobuf;
+ int i, j;
+ struct page *page, **ppage;
+ int doublepage = 0;
+ int repeat = 0;
+
+ repeat:
+
+ for (i = 0; i < nr; i++) {
+ iobuf = iovec[i];
+
+ if (iobuf->locked)
+ continue;
+
+ ppage = iobuf->maplist;
+ for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
+ page = *ppage;
+ if (!page)
+ continue;
+
+ if (TryLockPage(page)) {
+ while (j--) {
+ struct page *tmp = *--ppage;
+ if (tmp)
+ UnlockPage(tmp);
+ }
+ goto retry;
+ }
+ }
+ iobuf->locked = 1;
+ }
+
+ return 0;
+
+ retry:
+
+ /*
+ * We couldn't lock one of the pages. Undo the locking so far,
+ * wait on the page we got to, and try again.
+ */
+
+ unlock_kiovec(nr, iovec);
+ if (!wait)
+ return -EAGAIN;
+
+ /*
+ * Did the release also unlock the page we got stuck on?
+ */
+ if (!PageLocked(page)) {
+ /*
+ * If so, we may well have the page mapped twice
+ * in the IO address range. Bad news. Of
+ * course, it _might_ just be a coincidence,
+ * but if it happens more than once, chances
+ * are we have a double-mapped page.
+ */
+ if (++doublepage >= 3)
+ return -EINVAL;
+
+ /* Try again... */
+ wait_on_page(page);
+ }
+
+ if (++repeat < 16)
+ goto repeat;
+ return -EAGAIN;
+}
+
+/*
+ * Unlock all of the pages of a kiovec after IO.
+ */
+
+int unlock_kiovec(int nr, struct kiobuf *iovec[])
+{
+ struct kiobuf *iobuf;
+ int i, j;
+ struct page *page, **ppage;
+
+ for (i = 0; i < nr; i++) {
+ iobuf = iovec[i];
+
+ if (!iobuf->locked)
+ continue;
+ iobuf->locked = 0;
+
+ ppage = iobuf->maplist;
+ for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
+ page = *ppage;
+ if (!page)
+ continue;
+ UnlockPage(page);
+ }
+ }
+ return 0;
+}
+
+static inline void zeromap_pte_range(pte_t * pte, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address), prot));
+ pte_t oldpage = ptep_get_and_clear(pte);
+ set_pte(pte, zero_pte);
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ zeromap_pte_range(pte, address, end - address, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int zeromap_page_range(unsigned long address, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = address;
+ unsigned long end = address + size;
+ struct mm_struct *mm = current->mm;
+
+ dir = pgd_offset(mm, address);
+ flush_cache_range(mm, beg, end);
+ if (address >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, address);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = zeromap_pmd_range(mm, pmd, address, end - address, prot);
+ if (error)
+ break;
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * maps a range of physical memory into the requested pages. the old
+ * mappings are removed. any references to nonexistent pages results
+ * in null mappings (currently treated as "copy-on-access")
+ */
+static inline void remap_pte_range(pte_t * pte, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ struct page *page;
+ pte_t oldpage;
+ oldpage = ptep_get_and_clear(pte);
+
+ page = virt_to_page(__va(phys_addr));
+ if ((!VALID_PAGE(page)) || PageReserved(page))
+ set_pte(pte, mk_pte_phys(phys_addr, prot));
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ phys_addr += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ phys_addr -= address;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ remap_pte_range(pte, address, end - address, address + phys_addr, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+/* Note: this is only safe if the mm semaphore is held when called. */
+int remap_page_range(unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = from;
+ unsigned long end = from + size;
+ struct mm_struct *mm = current->mm;
+
+ phys_addr -= from;
+ dir = pgd_offset(mm, from);
+ flush_cache_range(mm, beg, end);
+ if (from >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, from);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = remap_pmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
+ if (error)
+ break;
+ from = (from + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (from && (from < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * Establish a new mapping:
+ * - flush the old one
+ * - update the page tables
+ * - inform the TLB about the new one
+ *
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void establish_pte(struct vm_area_struct * vma, unsigned long address, pte_t *page_table, pte_t entry)
+{
+ set_pte(page_table, entry);
+ flush_tlb_page(vma, address);
+ update_mmu_cache(vma, address, entry);
+}
+
+/*
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address,
+ pte_t *page_table)
+{
+ flush_page_to_ram(new_page);
+ flush_cache_page(vma, address);
+ establish_pte(vma, address, page_table, pte_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot))));
+}
+
+/*
+ * This routine handles present pages, when users try to write
+ * to a shared page. It is done by copying the page to a new address
+ * and decrementing the shared-page counter for the old page.
+ *
+ * Goto-purists beware: the only reason for goto's here is that it results
+ * in better assembly code.. The "default" path will see no jumps at all.
+ *
+ * Note that this routine assumes that the protection checks have been
+ * done by the caller (the low-level page fault routine in most cases).
+ * Thus we can safely just mark it writable once we've done any necessary
+ * COW.
+ *
+ * We also mark the page dirty at this point even though the page will
+ * change only once the write actually happens. This avoids a few races,
+ * and potentially makes it more efficient.
+ *
+ * We hold the mm semaphore and the page_table_lock on entry and exit
+ * with the page_table_lock released.
+ */
+static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, pte_t *page_table, pte_t pte)
+{
+ struct page *old_page, *new_page;
+
+ old_page = pte_page(pte);
+ if (!VALID_PAGE(old_page))
+ goto bad_wp_page;
+
+ if (!TryLockPage(old_page)) {
+ int reuse = can_share_swap_page(old_page);
+ unlock_page(old_page);
+ if (reuse) {
+ flush_cache_page(vma, address);
+ establish_pte(vma, address, page_table, pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
+ spin_unlock(&mm->page_table_lock);
+ return 1; /* Minor fault */
+ }
+ }
+
+ /*
+ * Ok, we need to copy. Oh, well..
+ */
+ page_cache_get(old_page);
+ spin_unlock(&mm->page_table_lock);
+
+ new_page = alloc_page(GFP_HIGHUSER);
+ if (!new_page)
+ goto no_mem;
+ copy_cow_page(old_page,new_page,address);
+
+ /*
+ * Re-check the pte - we dropped the lock
+ */
+ spin_lock(&mm->page_table_lock);
+ if (pte_same(*page_table, pte)) {
+ if (PageReserved(old_page))
+ ++mm->rss;
+ break_cow(vma, new_page, address, page_table);
+ lru_cache_add(new_page);
+
+ /* Free the old page.. */
+ new_page = old_page;
+ }
+ spin_unlock(&mm->page_table_lock);
+ page_cache_release(new_page);
+ page_cache_release(old_page);
+ return 1; /* Minor fault */
+
+bad_wp_page:
+ spin_unlock(&mm->page_table_lock);
+ printk("do_wp_page: bogus page at address %08lx (page 0x%lx)\n",address,(unsigned long)old_page);
+ return -1;
+no_mem:
+ page_cache_release(old_page);
+ return -1;
+}
+
+static void vmtruncate_list(struct vm_area_struct *mpnt, unsigned long pgoff)
+{
+ do {
+ struct mm_struct *mm = mpnt->vm_mm;
+ unsigned long start = mpnt->vm_start;
+ unsigned long end = mpnt->vm_end;
+ unsigned long len = end - start;
+ unsigned long diff;
+
+ /* mapping wholly truncated? */
+ if (mpnt->vm_pgoff >= pgoff) {
+ zap_page_range(mm, start, len);
+ continue;
+ }
+
+ /* mapping wholly unaffected? */
+ len = len >> PAGE_SHIFT;
+ diff = pgoff - mpnt->vm_pgoff;
+ if (diff >= len)
+ continue;
+
+ /* Ok, partially affected.. */
+ start += diff << PAGE_SHIFT;
+ len = (len - diff) << PAGE_SHIFT;
+ zap_page_range(mm, start, len);
+ } while ((mpnt = mpnt->vm_next_share) != NULL);
+}
+
+/*
+ * Handle all mappings that got truncated by a "truncate()"
+ * system call.
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page. Ugly, but necessary.
+ */
+int vmtruncate(struct inode * inode, loff_t offset)
+{
+ unsigned long pgoff;
+ struct address_space *mapping = inode->i_mapping;
+ unsigned long limit;
+
+ if (inode->i_size < offset)
+ goto do_expand;
+ inode->i_size = offset;
+ spin_lock(&mapping->i_shared_lock);
+ if (!mapping->i_mmap && !mapping->i_mmap_shared)
+ goto out_unlock;
+
+ pgoff = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ if (mapping->i_mmap != NULL)
+ vmtruncate_list(mapping->i_mmap, pgoff);
+ if (mapping->i_mmap_shared != NULL)
+ vmtruncate_list(mapping->i_mmap_shared, pgoff);
+
+out_unlock:
+ spin_unlock(&mapping->i_shared_lock);
+ truncate_inode_pages(mapping, offset);
+ goto out_truncate;
+
+do_expand:
+ limit = current->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY && offset > limit)
+ goto out_sig;
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out;
+ inode->i_size = offset;
+
+out_truncate:
+ if (inode->i_op && inode->i_op->truncate) {
+ lock_kernel();
+ inode->i_op->truncate(inode);
+ unlock_kernel();
+ }
+ return 0;
+out_sig:
+ send_sig(SIGXFSZ, current, 0);
+out:
+ return -EFBIG;
+}
+
+/*
+ * Primitive swap readahead code. We simply read an aligned block of
+ * (1 << page_cluster) entries in the swap area. This method is chosen
+ * because it doesn't cost us any seek time. We also make sure to queue
+ * the 'original' request together with the readahead ones...
+ */
+void swapin_readahead(swp_entry_t entry)
+{
+ int i, num;
+ struct page *new_page;
+ unsigned long offset;
+
+ /*
+ * Get the number of handles we should do readahead io to.
+ */
+ num = valid_swaphandles(entry, &offset);
+ for (i = 0; i < num; offset++, i++) {
+ /* Ok, do the async read-ahead now */
+ new_page = read_swap_cache_async(SWP_ENTRY(SWP_TYPE(entry), offset));
+ if (!new_page)
+ break;
+ page_cache_release(new_page);
+ }
+ return;
+}
+
+/*
+ * We hold the mm semaphore and the page_table_lock on entry and
+ * should release the pagetable lock on exit..
+ */
+static int do_swap_page(struct mm_struct * mm,
+ struct vm_area_struct * vma, unsigned long address,
+ pte_t * page_table, pte_t orig_pte, int write_access)
+{
+ struct page *page;
+ swp_entry_t entry = pte_to_swp_entry(orig_pte);
+ pte_t pte;
+ int ret = 1;
+
+ spin_unlock(&mm->page_table_lock);
+ page = lookup_swap_cache(entry);
+ if (!page) {
+ swapin_readahead(entry);
+ page = read_swap_cache_async(entry);
+ if (!page) {
+ /*
+ * Back out if somebody else faulted in this pte while
+ * we released the page table lock.
+ */
+ int retval;
+ spin_lock(&mm->page_table_lock);
+ retval = pte_same(*page_table, orig_pte) ? -1 : 1;
+ spin_unlock(&mm->page_table_lock);
+ return retval;
+ }
+
+ /* Had to read the page from swap area: Major fault */
+ ret = 2;
+ }
+
+ mark_page_accessed(page);
+
+ lock_page(page);
+
+ /*
+ * Back out if somebody else faulted in this pte while we
+ * released the page table lock.
+ */
+ spin_lock(&mm->page_table_lock);
+ if (!pte_same(*page_table, orig_pte)) {
+ spin_unlock(&mm->page_table_lock);
+ unlock_page(page);
+ page_cache_release(page);
+ return 1;
+ }
+
+ /* The page isn't present yet, go ahead with the fault. */
+
+ swap_free(entry);
+ if (vm_swap_full())
+ remove_exclusive_swap_page(page);
+
+ mm->rss++;
+ pte = mk_pte(page, vma->vm_page_prot);
+ if (write_access && can_share_swap_page(page))
+ pte = pte_mkdirty(pte_mkwrite(pte));
+ unlock_page(page);
+
+ flush_page_to_ram(page);
+ flush_icache_page(vma, page);
+ set_pte(page_table, pte);
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, address, pte);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return ret;
+}
+
+/*
+ * We are called with the MM semaphore and page_table_lock
+ * spinlock held to protect against concurrent faults in
+ * multithreaded programs.
+ */
+static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, int write_access, unsigned long addr)
+{
+ pte_t entry;
+
+ /* Read-only mapping of ZERO_PAGE. */
+ entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
+
+ /* ..except if it's a write access */
+ if (write_access) {
+ struct page *page;
+
+ /* Allocate our own private page. */
+ spin_unlock(&mm->page_table_lock);
+
+ page = alloc_page(GFP_HIGHUSER);
+ if (!page)
+ goto no_mem;
+ clear_user_highpage(page, addr);
+
+ spin_lock(&mm->page_table_lock);
+ if (!pte_none(*page_table)) {
+ page_cache_release(page);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+ }
+ mm->rss++;
+ flush_page_to_ram(page);
+ entry = pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
+ lru_cache_add(page);
+ mark_page_accessed(page);
+ }
+
+ set_pte(page_table, entry);
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, addr, entry);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return 1; /* Minor fault */
+
+no_mem:
+ return -1;
+}
+
+/*
+ * do_no_page() tries to create a new page mapping. It aggressively
+ * tries to share with existing pages, but makes a separate copy if
+ * the "write_access" parameter is true in order to avoid the next
+ * page fault.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * This is called with the MM semaphore held and the page table
+ * spinlock held. Exit with the spinlock released.
+ */
+static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access, pte_t *page_table)
+{
+ struct page * new_page;
+ pte_t entry;
+
+ if (!vma->vm_ops || !vma->vm_ops->nopage)
+ return do_anonymous_page(mm, vma, page_table, write_access, address);
+ spin_unlock(&mm->page_table_lock);
+
+ new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
+
+ if (new_page == NULL) /* no page was available -- SIGBUS */
+ return 0;
+ if (new_page == NOPAGE_OOM)
+ return -1;
+
+ /*
+ * Should we do an early C-O-W break?
+ */
+ if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ struct page * page = alloc_page(GFP_HIGHUSER);
+ if (!page) {
+ page_cache_release(new_page);
+ return -1;
+ }
+ copy_user_highpage(page, new_page, address);
+ page_cache_release(new_page);
+ lru_cache_add(page);
+ new_page = page;
+ }
+
+ spin_lock(&mm->page_table_lock);
+ /*
+ * This silly early PAGE_DIRTY setting removes a race
+ * due to the bad i386 page protection. But it's valid
+ * for other architectures too.
+ *
+ * Note that if write_access is true, we either now have
+ * an exclusive copy of the page, or this is a shared mapping,
+ * so we can make it writable and dirty to avoid having to
+ * handle that later.
+ */
+ /* Only go through if we didn't race with anybody else... */
+ if (pte_none(*page_table)) {
+ ++mm->rss;
+ flush_page_to_ram(new_page);
+ flush_icache_page(vma, new_page);
+ entry = mk_pte(new_page, vma->vm_page_prot);
+ if (write_access)
+ entry = pte_mkwrite(pte_mkdirty(entry));
+ set_pte(page_table, entry);
+ } else {
+ /* One of our sibling threads was faster, back out. */
+ page_cache_release(new_page);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+ }
+
+ /* no need to invalidate: a not-present page shouldn't be cached */
+ update_mmu_cache(vma, address, entry);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return 2; /* Major fault */
+}
+
+/*
+ * These routines also need to handle stuff like marking pages dirty
+ * and/or accessed for architectures that don't do it in hardware (most
+ * RISC architectures). The early dirtying is also good on the i386.
+ *
+ * There is also a hook called "update_mmu_cache()" that architectures
+ * with external mmu caches can use to update those (ie the Sparc or
+ * PowerPC hashed page tables that act as extended TLBs).
+ *
+ * Note the "page_table_lock". It is to protect against kswapd removing
+ * pages from under us. Note that kswapd only ever _removes_ pages, never
+ * adds them. As such, once we have noticed that the page is not present,
+ * we can drop the lock early.
+ *
+ * The adding of pages is protected by the MM semaphore (which we hold),
+ * so we don't need to worry about a page being suddenly been added into
+ * our VM.
+ *
+ * We enter with the pagetable spinlock held, we are supposed to
+ * release it when done.
+ */
+static inline int handle_pte_fault(struct mm_struct *mm,
+ struct vm_area_struct * vma, unsigned long address,
+ int write_access, pte_t * pte)
+{
+ pte_t entry;
+
+ entry = *pte;
+ if (!pte_present(entry)) {
+ /*
+ * If it truly wasn't present, we know that kswapd
+ * and the PTE updates will not touch it later. So
+ * drop the lock.
+ */
+ if (pte_none(entry))
+ return do_no_page(mm, vma, address, write_access, pte);
+ return do_swap_page(mm, vma, address, pte, entry, write_access);
+ }
+
+ if (write_access) {
+ if (!pte_write(entry))
+ return do_wp_page(mm, vma, address, pte, entry);
+
+ entry = pte_mkdirty(entry);
+ }
+ entry = pte_mkyoung(entry);
+ establish_pte(vma, address, pte, entry);
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+}
+
+/*
+ * By the time we get here, we already hold the mm semaphore
+ */
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+
+ current->state = TASK_RUNNING;
+ pgd = pgd_offset(mm, address);
+
+ /*
+ * We need the page table lock to synchronize with kswapd
+ * and the SMP-safe atomic PTE updates.
+ */
+ spin_lock(&mm->page_table_lock);
+ pmd = pmd_alloc(mm, pgd, address);
+
+ if (pmd) {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (pte)
+ return handle_pte_fault(mm, vma, address, write_access, pte);
+ }
+ spin_unlock(&mm->page_table_lock);
+ return -1;
+}
+
+/*
+ * Allocate page middle directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ *
+ * On a two-level page table, this ends up actually being entirely
+ * optimized away.
+ */
+pmd_t *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ pmd_t *new;
+
+ /* "fast" allocation can happen without dropping the lock.. */
+ new = pmd_alloc_one_fast(mm, address);
+ if (!new) {
+ spin_unlock(&mm->page_table_lock);
+ new = pmd_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (!pgd_none(*pgd)) {
+ pmd_free(new);
+ goto out;
+ }
+ }
+ pgd_populate(mm, pgd, new);
+out:
+ return pmd_offset(pgd, address);
+}
+
+/*
+ * Allocate the page table directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ */
+pte_t *pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+{
+ if (pmd_none(*pmd)) {
+ pte_t *new;
+
+ /* "fast" allocation can happen without dropping the lock.. */
+ new = pte_alloc_one_fast(mm, address);
+ if (!new) {
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ new = pte_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (!pmd_none(*pmd)) {
+ pte_free(new);
+ goto out;
+ }
+ }
+ pmd_populate(mm, pmd, new);
+ }
+out:
+ return pte_offset(pmd, address);
+}
+
+int make_pages_present(unsigned long addr, unsigned long end)
+{
+ int ret, len, write;
+ struct vm_area_struct * vma;
+
+ vma = find_vma(current->mm, addr);
+ write = (vma->vm_flags & VM_WRITE) != 0;
+ if (addr >= end)
+ BUG();
+ if (end > vma->vm_end)
+ BUG();
+ len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
+ ret = get_user_pages(current, current->mm, addr,
+ len, write, 0, NULL, NULL);
+ return ret == len ? 0 : -1;
+}
+
+struct page * vmalloc_to_page(void * vmalloc_addr)
+{
+ unsigned long addr = (unsigned long) vmalloc_addr;
+ struct page *page = NULL;
+ pmd_t *pmd;
+ pte_t *pte;
+ pgd_t *pgd;
+
+ pgd = pgd_offset_k(addr);
+ if (!pgd_none(*pgd)) {
+ pmd = pmd_offset(pgd, addr);
+ if (!pmd_none(*pmd)) {
+ pte = pte_offset(pmd, addr);
+ if (pte_present(*pte)) {
+ page = pte_page(*pte);
+ }
+ }
+ }
+ return page;
+}
--- /dev/null
+/*
+ * linux/mm/remap.c
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ */
+
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+
+extern int vm_enough_memory(long pages);
+
+static inline pte_t *get_one_pte(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t * pgd;
+ pmd_t * pmd;
+ pte_t * pte = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ if (pgd_none(*pgd))
+ goto end;
+ if (pgd_bad(*pgd)) {
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+ goto end;
+ }
+
+ pmd = pmd_offset(pgd, addr);
+ if (pmd_none(*pmd))
+ goto end;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ goto end;
+ }
+
+ pte = pte_offset(pmd, addr);
+ if (pte_none(*pte))
+ pte = NULL;
+end:
+ return pte;
+}
+
+static inline pte_t *alloc_one_pte(struct mm_struct *mm, unsigned long addr)
+{
+ pmd_t * pmd;
+ pte_t * pte = NULL;
+
+ pmd = pmd_alloc(mm, pgd_offset(mm, addr), addr);
+ if (pmd)
+ pte = pte_alloc(mm, pmd, addr);
+ return pte;
+}
+
+static inline int copy_one_pte(struct mm_struct *mm, pte_t * src, pte_t * dst)
+{
+ int error = 0;
+ pte_t pte;
+
+ if (!pte_none(*src)) {
+ pte = ptep_get_and_clear(src);
+ if (!dst) {
+ /* No dest? We must put it back. */
+ dst = src;
+ error++;
+ }
+ set_pte(dst, pte);
+ }
+ return error;
+}
+
+static int move_one_page(struct mm_struct *mm, unsigned long old_addr, unsigned long new_addr)
+{
+ int error = 0;
+ pte_t * src;
+
+ spin_lock(&mm->page_table_lock);
+ src = get_one_pte(mm, old_addr);
+ if (src)
+ error = copy_one_pte(mm, src, alloc_one_pte(mm, new_addr));
+ spin_unlock(&mm->page_table_lock);
+ return error;
+}
+
+static int move_page_tables(struct mm_struct * mm,
+ unsigned long new_addr, unsigned long old_addr, unsigned long len)
+{
+ unsigned long offset = len;
+
+ flush_cache_range(mm, old_addr, old_addr + len);
+
+ /*
+ * This is not the clever way to do this, but we're taking the
+ * easy way out on the assumption that most remappings will be
+ * only a few pages.. This also makes error recovery easier.
+ */
+ while (offset) {
+ offset -= PAGE_SIZE;
+ if (move_one_page(mm, old_addr + offset, new_addr + offset))
+ goto oops_we_failed;
+ }
+ flush_tlb_range(mm, old_addr, old_addr + len);
+ return 0;
+
+ /*
+ * Ok, the move failed because we didn't have enough pages for
+ * the new page table tree. This is unlikely, but we have to
+ * take the possibility into account. In that case we just move
+ * all the pages back (this will work, because we still have
+ * the old page tables)
+ */
+oops_we_failed:
+ XENO_flush_page_update_queue();
+ flush_cache_range(mm, new_addr, new_addr + len);
+ while ((offset += PAGE_SIZE) < len)
+ move_one_page(mm, new_addr + offset, old_addr + offset);
+ XENO_flush_page_update_queue();
+ zap_page_range(mm, new_addr, len);
+ return -1;
+}
+
+static inline unsigned long move_vma(struct vm_area_struct * vma,
+ unsigned long addr, unsigned long old_len, unsigned long new_len,
+ unsigned long new_addr)
+{
+ struct mm_struct * mm = vma->vm_mm;
+ struct vm_area_struct * new_vma, * next, * prev;
+ int allocated_vma;
+
+ new_vma = NULL;
+ next = find_vma_prev(mm, new_addr, &prev);
+ if (next) {
+ if (prev && prev->vm_end == new_addr &&
+ can_vma_merge(prev, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = new_addr + new_len;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = prev;
+ if (next != prev->vm_next)
+ BUG();
+ if (prev->vm_end == next->vm_start && can_vma_merge(next, prev->vm_flags)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = next->vm_end;
+ __vma_unlink(mm, next, prev);
+ spin_unlock(&mm->page_table_lock);
+
+ mm->map_count--;
+ kmem_cache_free(vm_area_cachep, next);
+ }
+ } else if (next->vm_start == new_addr + new_len &&
+ can_vma_merge(next, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ next->vm_start = new_addr;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = next;
+ }
+ } else {
+ prev = find_vma(mm, new_addr-1);
+ if (prev && prev->vm_end == new_addr &&
+ can_vma_merge(prev, vma->vm_flags) && !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = new_addr + new_len;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = prev;
+ }
+ }
+
+ allocated_vma = 0;
+ if (!new_vma) {
+ new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!new_vma)
+ goto out;
+ allocated_vma = 1;
+ }
+
+ if (!move_page_tables(current->mm, new_addr, addr, old_len)) {
+ if (allocated_vma) {
+ *new_vma = *vma;
+ new_vma->vm_start = new_addr;
+ new_vma->vm_end = new_addr+new_len;
+ new_vma->vm_pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
+ new_vma->vm_raend = 0;
+ if (new_vma->vm_file)
+ get_file(new_vma->vm_file);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ insert_vm_struct(current->mm, new_vma);
+ }
+ do_munmap(current->mm, addr, old_len);
+ current->mm->total_vm += new_len >> PAGE_SHIFT;
+ if (new_vma->vm_flags & VM_LOCKED) {
+ current->mm->locked_vm += new_len >> PAGE_SHIFT;
+ make_pages_present(new_vma->vm_start,
+ new_vma->vm_end);
+ }
+ return new_addr;
+ }
+ if (allocated_vma)
+ kmem_cache_free(vm_area_cachep, new_vma);
+ out:
+ return -ENOMEM;
+}
+
+/*
+ * Expand (or shrink) an existing mapping, potentially moving it at the
+ * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
+ *
+ * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
+ * This option implies MREMAP_MAYMOVE.
+ */
+unsigned long do_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr)
+{
+ struct vm_area_struct *vma;
+ unsigned long ret = -EINVAL;
+
+ if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
+ goto out;
+
+ if (addr & ~PAGE_MASK)
+ goto out;
+
+ old_len = PAGE_ALIGN(old_len);
+ new_len = PAGE_ALIGN(new_len);
+
+ /* new_addr is only valid if MREMAP_FIXED is specified */
+ if (flags & MREMAP_FIXED) {
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+ if (!(flags & MREMAP_MAYMOVE))
+ goto out;
+
+ if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
+ goto out;
+
+ /* Check if the location we're moving into overlaps the
+ * old location at all, and fail if it does.
+ */
+ if ((new_addr <= addr) && (new_addr+new_len) > addr)
+ goto out;
+
+ if ((addr <= new_addr) && (addr+old_len) > new_addr)
+ goto out;
+
+ do_munmap(current->mm, new_addr, new_len);
+ }
+
+ /*
+ * Always allow a shrinking remap: that just unmaps
+ * the unnecessary pages..
+ */
+ ret = addr;
+ if (old_len >= new_len) {
+ do_munmap(current->mm, addr+new_len, old_len - new_len);
+ if (!(flags & MREMAP_FIXED) || (new_addr == addr))
+ goto out;
+ }
+
+ /*
+ * Ok, we need to grow.. or relocate.
+ */
+ ret = -EFAULT;
+ vma = find_vma(current->mm, addr);
+ if (!vma || vma->vm_start > addr)
+ goto out;
+ /* We can't remap across vm area boundaries */
+ if (old_len > vma->vm_end - addr)
+ goto out;
+ if (vma->vm_flags & VM_DONTEXPAND) {
+ if (new_len > old_len)
+ goto out;
+ }
+ if (vma->vm_flags & VM_LOCKED) {
+ unsigned long locked = current->mm->locked_vm << PAGE_SHIFT;
+ locked += new_len - old_len;
+ ret = -EAGAIN;
+ if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ goto out;
+ }
+ ret = -ENOMEM;
+ if ((current->mm->total_vm << PAGE_SHIFT) + (new_len - old_len)
+ > current->rlim[RLIMIT_AS].rlim_cur)
+ goto out;
+ /* Private writable mapping? Check memory availability.. */
+ if ((vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
+ !(flags & MAP_NORESERVE) &&
+ !vm_enough_memory((new_len - old_len) >> PAGE_SHIFT))
+ goto out;
+
+ /* old_len exactly to the end of the area..
+ * And we're not relocating the area.
+ */
+ if (old_len == vma->vm_end - addr &&
+ !((flags & MREMAP_FIXED) && (addr != new_addr)) &&
+ (old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
+ unsigned long max_addr = TASK_SIZE;
+ if (vma->vm_next)
+ max_addr = vma->vm_next->vm_start;
+ /* can we just expand the current mapping? */
+ if (max_addr - addr >= new_len) {
+ int pages = (new_len - old_len) >> PAGE_SHIFT;
+ spin_lock(&vma->vm_mm->page_table_lock);
+ vma->vm_end = addr + new_len;
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ current->mm->total_vm += pages;
+ if (vma->vm_flags & VM_LOCKED) {
+ current->mm->locked_vm += pages;
+ make_pages_present(addr + old_len,
+ addr + new_len);
+ }
+ ret = addr;
+ goto out;
+ }
+ }
+
+ /*
+ * We weren't able to just expand or shrink the area,
+ * we need to create a new one and move it..
+ */
+ ret = -ENOMEM;
+ if (flags & MREMAP_MAYMOVE) {
+ if (!(flags & MREMAP_FIXED)) {
+ unsigned long map_flags = 0;
+ if (vma->vm_flags & VM_SHARED)
+ map_flags |= MAP_SHARED;
+
+ new_addr = get_unmapped_area(vma->vm_file, 0, new_len, vma->vm_pgoff, map_flags);
+ ret = new_addr;
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+ }
+ ret = move_vma(vma, addr, old_len, new_len, new_addr);
+ }
+out:
+ return ret;
+}
+
+asmlinkage unsigned long sys_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr)
+{
+ unsigned long ret;
+
+ down_write(¤t->mm->mmap_sem);
+ ret = do_mremap(addr, old_len, new_len, flags, new_addr);
+ up_write(¤t->mm->mmap_sem);
+ return ret;
+}
--- /dev/null
+/*
+ * linux/mm/swapfile.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ * Swap reorganised 29.12.95, Stephen Tweedie
+ */
+
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel_stat.h>
+#include <linux/swap.h>
+#include <linux/swapctl.h>
+#include <linux/blkdev.h> /* for blk_size */
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <linux/shm.h>
+
+#include <asm/pgtable.h>
+
+spinlock_t swaplock = SPIN_LOCK_UNLOCKED;
+unsigned int nr_swapfiles;
+int total_swap_pages;
+static int swap_overflow;
+
+static const char Bad_file[] = "Bad swap file entry ";
+static const char Unused_file[] = "Unused swap file entry ";
+static const char Bad_offset[] = "Bad swap offset entry ";
+static const char Unused_offset[] = "Unused swap offset entry ";
+
+struct swap_list_t swap_list = {-1, -1};
+
+struct swap_info_struct swap_info[MAX_SWAPFILES];
+
+#define SWAPFILE_CLUSTER 256
+
+static inline int scan_swap_map(struct swap_info_struct *si)
+{
+ unsigned long offset;
+ /*
+ * We try to cluster swap pages by allocating them
+ * sequentially in swap. Once we've allocated
+ * SWAPFILE_CLUSTER pages this way, however, we resort to
+ * first-free allocation, starting a new cluster. This
+ * prevents us from scattering swap pages all over the entire
+ * swap partition, so that we reduce overall disk seek times
+ * between swap pages. -- sct */
+ if (si->cluster_nr) {
+ while (si->cluster_next <= si->highest_bit) {
+ offset = si->cluster_next++;
+ if (si->swap_map[offset])
+ continue;
+ si->cluster_nr--;
+ goto got_page;
+ }
+ }
+ si->cluster_nr = SWAPFILE_CLUSTER;
+
+ /* try to find an empty (even not aligned) cluster. */
+ offset = si->lowest_bit;
+ check_next_cluster:
+ if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
+ {
+ int nr;
+ for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
+ if (si->swap_map[nr])
+ {
+ offset = nr+1;
+ goto check_next_cluster;
+ }
+ /* We found a completly empty cluster, so start
+ * using it.
+ */
+ goto got_page;
+ }
+ /* No luck, so now go finegrined as usual. -Andrea */
+ for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) {
+ if (si->swap_map[offset])
+ continue;
+ si->lowest_bit = offset+1;
+ got_page:
+ if (offset == si->lowest_bit)
+ si->lowest_bit++;
+ if (offset == si->highest_bit)
+ si->highest_bit--;
+ if (si->lowest_bit > si->highest_bit) {
+ si->lowest_bit = si->max;
+ si->highest_bit = 0;
+ }
+ si->swap_map[offset] = 1;
+ nr_swap_pages--;
+ si->cluster_next = offset+1;
+ return offset;
+ }
+ si->lowest_bit = si->max;
+ si->highest_bit = 0;
+ return 0;
+}
+
+swp_entry_t get_swap_page(void)
+{
+ struct swap_info_struct * p;
+ unsigned long offset;
+ swp_entry_t entry;
+ int type, wrapped = 0;
+
+ entry.val = 0; /* Out of memory */
+ swap_list_lock();
+ type = swap_list.next;
+ if (type < 0)
+ goto out;
+ if (nr_swap_pages <= 0)
+ goto out;
+
+ while (1) {
+ p = &swap_info[type];
+ if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
+ swap_device_lock(p);
+ offset = scan_swap_map(p);
+ swap_device_unlock(p);
+ if (offset) {
+ entry = SWP_ENTRY(type,offset);
+ type = swap_info[type].next;
+ if (type < 0 ||
+ p->prio != swap_info[type].prio) {
+ swap_list.next = swap_list.head;
+ } else {
+ swap_list.next = type;
+ }
+ goto out;
+ }
+ }
+ type = p->next;
+ if (!wrapped) {
+ if (type < 0 || p->prio != swap_info[type].prio) {
+ type = swap_list.head;
+ wrapped = 1;
+ }
+ } else
+ if (type < 0)
+ goto out; /* out of swap space */
+ }
+out:
+ swap_list_unlock();
+ return entry;
+}
+
+static struct swap_info_struct * swap_info_get(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+ unsigned long offset, type;
+
+ if (!entry.val)
+ goto out;
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles)
+ goto bad_nofile;
+ p = & swap_info[type];
+ if (!(p->flags & SWP_USED))
+ goto bad_device;
+ offset = SWP_OFFSET(entry);
+ if (offset >= p->max)
+ goto bad_offset;
+ if (!p->swap_map[offset])
+ goto bad_free;
+ swap_list_lock();
+ if (p->prio > swap_info[swap_list.next].prio)
+ swap_list.next = type;
+ swap_device_lock(p);
+ return p;
+
+bad_free:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
+ goto out;
+bad_offset:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
+ goto out;
+bad_device:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
+ goto out;
+bad_nofile:
+ printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
+out:
+ return NULL;
+}
+
+static void swap_info_put(struct swap_info_struct * p)
+{
+ swap_device_unlock(p);
+ swap_list_unlock();
+}
+
+static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
+{
+ int count = p->swap_map[offset];
+
+ if (count < SWAP_MAP_MAX) {
+ count--;
+ p->swap_map[offset] = count;
+ if (!count) {
+ if (offset < p->lowest_bit)
+ p->lowest_bit = offset;
+ if (offset > p->highest_bit)
+ p->highest_bit = offset;
+ nr_swap_pages++;
+ }
+ }
+ return count;
+}
+
+/*
+ * Caller has made sure that the swapdevice corresponding to entry
+ * is still around or has not been recycled.
+ */
+void swap_free(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+
+ p = swap_info_get(entry);
+ if (p) {
+ swap_entry_free(p, SWP_OFFSET(entry));
+ swap_info_put(p);
+ }
+}
+
+/*
+ * Check if we're the only user of a swap page,
+ * when the page is locked.
+ */
+static int exclusive_swap_page(struct page *page)
+{
+ int retval = 0;
+ struct swap_info_struct * p;
+ swp_entry_t entry;
+
+ entry.val = page->index;
+ p = swap_info_get(entry);
+ if (p) {
+ /* Is the only swap cache user the cache itself? */
+ if (p->swap_map[SWP_OFFSET(entry)] == 1) {
+ /* Recheck the page count with the pagecache lock held.. */
+ spin_lock(&pagecache_lock);
+ if (page_count(page) - !!page->buffers == 2)
+ retval = 1;
+ spin_unlock(&pagecache_lock);
+ }
+ swap_info_put(p);
+ }
+ return retval;
+}
+
+/*
+ * We can use this swap cache entry directly
+ * if there are no other references to it.
+ *
+ * Here "exclusive_swap_page()" does the real
+ * work, but we opportunistically check whether
+ * we need to get all the locks first..
+ */
+int can_share_swap_page(struct page *page)
+{
+ int retval = 0;
+
+ if (!PageLocked(page))
+ BUG();
+ switch (page_count(page)) {
+ case 3:
+ if (!page->buffers)
+ break;
+ /* Fallthrough */
+ case 2:
+ if (!PageSwapCache(page))
+ break;
+ retval = exclusive_swap_page(page);
+ break;
+ case 1:
+ if (PageReserved(page))
+ break;
+ retval = 1;
+ }
+ return retval;
+}
+
+/*
+ * Work out if there are any other processes sharing this
+ * swap cache page. Free it if you can. Return success.
+ */
+int remove_exclusive_swap_page(struct page *page)
+{
+ int retval;
+ struct swap_info_struct * p;
+ swp_entry_t entry;
+
+ if (!PageLocked(page))
+ BUG();
+ if (!PageSwapCache(page))
+ return 0;
+ if (page_count(page) - !!page->buffers != 2) /* 2: us + cache */
+ return 0;
+
+ entry.val = page->index;
+ p = swap_info_get(entry);
+ if (!p)
+ return 0;
+
+ /* Is the only swap cache user the cache itself? */
+ retval = 0;
+ if (p->swap_map[SWP_OFFSET(entry)] == 1) {
+ /* Recheck the page count with the pagecache lock held.. */
+ spin_lock(&pagecache_lock);
+ if (page_count(page) - !!page->buffers == 2) {
+ __delete_from_swap_cache(page);
+ SetPageDirty(page);
+ retval = 1;
+ }
+ spin_unlock(&pagecache_lock);
+ }
+ swap_info_put(p);
+
+ if (retval) {
+ block_flushpage(page, 0);
+ swap_free(entry);
+ page_cache_release(page);
+ }
+
+ return retval;
+}
+
+/*
+ * Free the swap entry like above, but also try to
+ * free the page cache entry if it is the last user.
+ */
+void free_swap_and_cache(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+ struct page *page = NULL;
+
+ p = swap_info_get(entry);
+ if (p) {
+ if (swap_entry_free(p, SWP_OFFSET(entry)) == 1)
+ page = find_trylock_page(&swapper_space, entry.val);
+ swap_info_put(p);
+ }
+ if (page) {
+ page_cache_get(page);
+ /* Only cache user (+us), or swap space full? Free it! */
+ if (page_count(page) - !!page->buffers == 2 || vm_swap_full()) {
+ delete_from_swap_cache(page);
+ SetPageDirty(page);
+ }
+ UnlockPage(page);
+ page_cache_release(page);
+ }
+}
+
+/*
+ * The swap entry has been read in advance, and we return 1 to indicate
+ * that the page has been used or is no longer needed.
+ *
+ * Always set the resulting pte to be nowrite (the same as COW pages
+ * after one process has exited). We don't know just how many PTEs will
+ * share this swap entry, so be cautious and let do_wp_page work out
+ * what to do if a write is requested later.
+ */
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static inline void unuse_pte(struct vm_area_struct * vma, unsigned long address,
+ pte_t *dir, swp_entry_t entry, struct page* page)
+{
+ pte_t pte = *dir;
+
+ if (likely(pte_to_swp_entry(pte).val != entry.val))
+ return;
+ if (unlikely(pte_none(pte) || pte_present(pte)))
+ return;
+ get_page(page);
+ set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
+ swap_free(entry);
+ ++vma->vm_mm->rss;
+}
+
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static inline void unuse_pmd(struct vm_area_struct * vma, pmd_t *dir,
+ unsigned long address, unsigned long size, unsigned long offset,
+ swp_entry_t entry, struct page* page)
+{
+ pte_t * pte;
+ unsigned long end;
+
+ if (pmd_none(*dir))
+ return;
+ if (pmd_bad(*dir)) {
+ pmd_ERROR(*dir);
+ pmd_clear(dir);
+ return;
+ }
+ pte = pte_offset(dir, address);
+ offset += address & PMD_MASK;
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ unuse_pte(vma, offset+address-vma->vm_start, pte, entry, page);
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static inline void unuse_pgd(struct vm_area_struct * vma, pgd_t *dir,
+ unsigned long address, unsigned long size,
+ swp_entry_t entry, struct page* page)
+{
+ pmd_t * pmd;
+ unsigned long offset, end;
+
+ if (pgd_none(*dir))
+ return;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return;
+ }
+ pmd = pmd_offset(dir, address);
+ offset = address & PGDIR_MASK;
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ if (address >= end)
+ BUG();
+ do {
+ unuse_pmd(vma, pmd, address, end - address, offset, entry,
+ page);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+}
+
+/* mmlist_lock and vma->vm_mm->page_table_lock are held */
+static void unuse_vma(struct vm_area_struct * vma, pgd_t *pgdir,
+ swp_entry_t entry, struct page* page)
+{
+ unsigned long start = vma->vm_start, end = vma->vm_end;
+
+ if (start >= end)
+ BUG();
+ do {
+ unuse_pgd(vma, pgdir, start, end - start, entry, page);
+ start = (start + PGDIR_SIZE) & PGDIR_MASK;
+ pgdir++;
+ } while (start && (start < end));
+}
+
+static void unuse_process(struct mm_struct * mm,
+ swp_entry_t entry, struct page* page)
+{
+ struct vm_area_struct* vma;
+
+ /*
+ * Go through process' page directory.
+ */
+ spin_lock(&mm->page_table_lock);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ pgd_t * pgd = pgd_offset(mm, vma->vm_start);
+ unuse_vma(vma, pgd, entry, page);
+ }
+ XENO_flush_page_update_queue();
+ spin_unlock(&mm->page_table_lock);
+ return;
+}
+
+/*
+ * Scan swap_map from current position to next entry still in use.
+ * Recycle to start on reaching the end, returning 0 when empty.
+ */
+static int find_next_to_unuse(struct swap_info_struct *si, int prev)
+{
+ int max = si->max;
+ int i = prev;
+ int count;
+
+ /*
+ * No need for swap_device_lock(si) here: we're just looking
+ * for whether an entry is in use, not modifying it; false
+ * hits are okay, and sys_swapoff() has already prevented new
+ * allocations from this area (while holding swap_list_lock()).
+ */
+ for (;;) {
+ if (++i >= max) {
+ if (!prev) {
+ i = 0;
+ break;
+ }
+ /*
+ * No entries in use at top of swap_map,
+ * loop back to start and recheck there.
+ */
+ max = prev + 1;
+ prev = 0;
+ i = 1;
+ }
+ count = si->swap_map[i];
+ if (count && count != SWAP_MAP_BAD)
+ break;
+ }
+ return i;
+}
+
+/*
+ * We completely avoid races by reading each swap page in advance,
+ * and then search for the process using it. All the necessary
+ * page table adjustments can then be made atomically.
+ */
+static int try_to_unuse(unsigned int type)
+{
+ struct swap_info_struct * si = &swap_info[type];
+ struct mm_struct *start_mm;
+ unsigned short *swap_map;
+ unsigned short swcount;
+ struct page *page;
+ swp_entry_t entry;
+ int i = 0;
+ int retval = 0;
+ int reset_overflow = 0;
+
+ /*
+ * When searching mms for an entry, a good strategy is to
+ * start at the first mm we freed the previous entry from
+ * (though actually we don't notice whether we or coincidence
+ * freed the entry). Initialize this start_mm with a hold.
+ *
+ * A simpler strategy would be to start at the last mm we
+ * freed the previous entry from; but that would take less
+ * advantage of mmlist ordering (now preserved by swap_out()),
+ * which clusters forked address spaces together, most recent
+ * child immediately after parent. If we race with dup_mmap(),
+ * we very much want to resolve parent before child, otherwise
+ * we may miss some entries: using last mm would invert that.
+ */
+ start_mm = &init_mm;
+ atomic_inc(&init_mm.mm_users);
+
+ /*
+ * Keep on scanning until all entries have gone. Usually,
+ * one pass through swap_map is enough, but not necessarily:
+ * mmput() removes mm from mmlist before exit_mmap() and its
+ * zap_page_range(). That's not too bad, those entries are
+ * on their way out, and handled faster there than here.
+ * do_munmap() behaves similarly, taking the range out of mm's
+ * vma list before zap_page_range(). But unfortunately, when
+ * unmapping a part of a vma, it takes the whole out first,
+ * then reinserts what's left after (might even reschedule if
+ * open() method called) - so swap entries may be invisible
+ * to swapoff for a while, then reappear - but that is rare.
+ */
+ while ((i = find_next_to_unuse(si, i))) {
+ /*
+ * Get a page for the entry, using the existing swap
+ * cache page if there is one. Otherwise, get a clean
+ * page and read the swap into it.
+ */
+ swap_map = &si->swap_map[i];
+ entry = SWP_ENTRY(type, i);
+ page = read_swap_cache_async(entry);
+ if (!page) {
+ /*
+ * Either swap_duplicate() failed because entry
+ * has been freed independently, and will not be
+ * reused since sys_swapoff() already disabled
+ * allocation from here, or alloc_page() failed.
+ */
+ if (!*swap_map)
+ continue;
+ retval = -ENOMEM;
+ break;
+ }
+
+ /*
+ * Don't hold on to start_mm if it looks like exiting.
+ */
+ if (atomic_read(&start_mm->mm_users) == 1) {
+ mmput(start_mm);
+ start_mm = &init_mm;
+ atomic_inc(&init_mm.mm_users);
+ }
+
+ /*
+ * Wait for and lock page. When do_swap_page races with
+ * try_to_unuse, do_swap_page can handle the fault much
+ * faster than try_to_unuse can locate the entry. This
+ * apparently redundant "wait_on_page" lets try_to_unuse
+ * defer to do_swap_page in such a case - in some tests,
+ * do_swap_page and try_to_unuse repeatedly compete.
+ */
+ wait_on_page(page);
+ lock_page(page);
+
+ /*
+ * Remove all references to entry, without blocking.
+ * Whenever we reach init_mm, there's no address space
+ * to search, but use it as a reminder to search shmem.
+ */
+ swcount = *swap_map;
+ if (swcount > 1) {
+ flush_page_to_ram(page);
+ if (start_mm == &init_mm)
+ shmem_unuse(entry, page);
+ else
+ unuse_process(start_mm, entry, page);
+ }
+ if (*swap_map > 1) {
+ int set_start_mm = (*swap_map >= swcount);
+ struct list_head *p = &start_mm->mmlist;
+ struct mm_struct *new_start_mm = start_mm;
+ struct mm_struct *mm;
+
+ spin_lock(&mmlist_lock);
+ while (*swap_map > 1 &&
+ (p = p->next) != &start_mm->mmlist) {
+ mm = list_entry(p, struct mm_struct, mmlist);
+ swcount = *swap_map;
+ if (mm == &init_mm) {
+ set_start_mm = 1;
+ shmem_unuse(entry, page);
+ } else
+ unuse_process(mm, entry, page);
+ if (set_start_mm && *swap_map < swcount) {
+ new_start_mm = mm;
+ set_start_mm = 0;
+ }
+ }
+ atomic_inc(&new_start_mm->mm_users);
+ spin_unlock(&mmlist_lock);
+ mmput(start_mm);
+ start_mm = new_start_mm;
+ }
+
+ /*
+ * How could swap count reach 0x7fff when the maximum
+ * pid is 0x7fff, and there's no way to repeat a swap
+ * page within an mm (except in shmem, where it's the
+ * shared object which takes the reference count)?
+ * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
+ *
+ * If that's wrong, then we should worry more about
+ * exit_mmap() and do_munmap() cases described above:
+ * we might be resetting SWAP_MAP_MAX too early here.
+ * We know "Undead"s can happen, they're okay, so don't
+ * report them; but do report if we reset SWAP_MAP_MAX.
+ */
+ if (*swap_map == SWAP_MAP_MAX) {
+ swap_list_lock();
+ swap_device_lock(si);
+ nr_swap_pages++;
+ *swap_map = 1;
+ swap_device_unlock(si);
+ swap_list_unlock();
+ reset_overflow = 1;
+ }
+
+ /*
+ * If a reference remains (rare), we would like to leave
+ * the page in the swap cache; but try_to_swap_out could
+ * then re-duplicate the entry once we drop page lock,
+ * so we might loop indefinitely; also, that page could
+ * not be swapped out to other storage meanwhile. So:
+ * delete from cache even if there's another reference,
+ * after ensuring that the data has been saved to disk -
+ * since if the reference remains (rarer), it will be
+ * read from disk into another page. Splitting into two
+ * pages would be incorrect if swap supported "shared
+ * private" pages, but they are handled by tmpfs files.
+ * Note shmem_unuse already deleted its from swap cache.
+ */
+ if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
+ rw_swap_page(WRITE, page);
+ lock_page(page);
+ }
+ if (PageSwapCache(page))
+ delete_from_swap_cache(page);
+
+ /*
+ * So we could skip searching mms once swap count went
+ * to 1, we did not mark any present ptes as dirty: must
+ * mark page dirty so try_to_swap_out will preserve it.
+ */
+ SetPageDirty(page);
+ UnlockPage(page);
+ page_cache_release(page);
+
+ /*
+ * Make sure that we aren't completely killing
+ * interactive performance. Interruptible check on
+ * signal_pending() would be nice, but changes the spec?
+ */
+ if (current->need_resched)
+ schedule();
+ }
+
+ mmput(start_mm);
+ if (reset_overflow) {
+ printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
+ swap_overflow = 0;
+ }
+ return retval;
+}
+
+asmlinkage long sys_swapoff(const char * specialfile)
+{
+ struct swap_info_struct * p = NULL;
+ unsigned short *swap_map;
+ struct nameidata nd;
+ int i, type, prev;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = user_path_walk(specialfile, &nd);
+ if (err)
+ goto out;
+
+ lock_kernel();
+ prev = -1;
+ swap_list_lock();
+ for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
+ p = swap_info + type;
+ if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
+ if (p->swap_file == nd.dentry)
+ break;
+ }
+ prev = type;
+ }
+ err = -EINVAL;
+ if (type < 0) {
+ swap_list_unlock();
+ goto out_dput;
+ }
+
+ if (prev < 0) {
+ swap_list.head = p->next;
+ } else {
+ swap_info[prev].next = p->next;
+ }
+ if (type == swap_list.next) {
+ /* just pick something that's safe... */
+ swap_list.next = swap_list.head;
+ }
+ nr_swap_pages -= p->pages;
+ total_swap_pages -= p->pages;
+ p->flags = SWP_USED;
+ swap_list_unlock();
+ unlock_kernel();
+ err = try_to_unuse(type);
+ lock_kernel();
+ if (err) {
+ /* re-insert swap space back into swap_list */
+ swap_list_lock();
+ for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
+ if (p->prio >= swap_info[i].prio)
+ break;
+ p->next = i;
+ if (prev < 0)
+ swap_list.head = swap_list.next = p - swap_info;
+ else
+ swap_info[prev].next = p - swap_info;
+ nr_swap_pages += p->pages;
+ total_swap_pages += p->pages;
+ p->flags = SWP_WRITEOK;
+ swap_list_unlock();
+ goto out_dput;
+ }
+ if (p->swap_device)
+ blkdev_put(p->swap_file->d_inode->i_bdev, BDEV_SWAP);
+ path_release(&nd);
+
+ swap_list_lock();
+ swap_device_lock(p);
+ nd.mnt = p->swap_vfsmnt;
+ nd.dentry = p->swap_file;
+ p->swap_vfsmnt = NULL;
+ p->swap_file = NULL;
+ p->swap_device = 0;
+ p->max = 0;
+ swap_map = p->swap_map;
+ p->swap_map = NULL;
+ p->flags = 0;
+ swap_device_unlock(p);
+ swap_list_unlock();
+ vfree(swap_map);
+ err = 0;
+
+out_dput:
+ unlock_kernel();
+ path_release(&nd);
+out:
+ return err;
+}
+
+int get_swaparea_info(char *buf)
+{
+ char * page = (char *) __get_free_page(GFP_KERNEL);
+ struct swap_info_struct *ptr = swap_info;
+ int i, j, len = 0, usedswap;
+
+ if (!page)
+ return -ENOMEM;
+
+ len += sprintf(buf, "Filename\t\t\tType\t\tSize\tUsed\tPriority\n");
+ for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
+ if ((ptr->flags & SWP_USED) && ptr->swap_map) {
+ char * path = d_path(ptr->swap_file, ptr->swap_vfsmnt,
+ page, PAGE_SIZE);
+
+ len += sprintf(buf + len, "%-31s ", path);
+
+ if (!ptr->swap_device)
+ len += sprintf(buf + len, "file\t\t");
+ else
+ len += sprintf(buf + len, "partition\t");
+
+ usedswap = 0;
+ for (j = 0; j < ptr->max; ++j)
+ switch (ptr->swap_map[j]) {
+ case SWAP_MAP_BAD:
+ case 0:
+ continue;
+ default:
+ usedswap++;
+ }
+ len += sprintf(buf + len, "%d\t%d\t%d\n", ptr->pages << (PAGE_SHIFT - 10),
+ usedswap << (PAGE_SHIFT - 10), ptr->prio);
+ }
+ }
+ free_page((unsigned long) page);
+ return len;
+}
+
+int is_swap_partition(kdev_t dev) {
+ struct swap_info_struct *ptr = swap_info;
+ int i;
+
+ for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
+ if (ptr->flags & SWP_USED)
+ if (ptr->swap_device == dev)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
+ *
+ * The swapon system call
+ */
+asmlinkage long sys_swapon(const char * specialfile, int swap_flags)
+{
+ struct swap_info_struct * p;
+ struct nameidata nd;
+ struct inode * swap_inode;
+ unsigned int type;
+ int i, j, prev;
+ int error;
+ static int least_priority = 0;
+ union swap_header *swap_header = 0;
+ int swap_header_version;
+ int nr_good_pages = 0;
+ unsigned long maxpages = 1;
+ int swapfilesize;
+ struct block_device *bdev = NULL;
+ unsigned short *swap_map;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ lock_kernel();
+ swap_list_lock();
+ p = swap_info;
+ for (type = 0 ; type < nr_swapfiles ; type++,p++)
+ if (!(p->flags & SWP_USED))
+ break;
+ error = -EPERM;
+ if (type >= MAX_SWAPFILES) {
+ swap_list_unlock();
+ goto out;
+ }
+ if (type >= nr_swapfiles)
+ nr_swapfiles = type+1;
+ p->flags = SWP_USED;
+ p->swap_file = NULL;
+ p->swap_vfsmnt = NULL;
+ p->swap_device = 0;
+ p->swap_map = NULL;
+ p->lowest_bit = 0;
+ p->highest_bit = 0;
+ p->cluster_nr = 0;
+ p->sdev_lock = SPIN_LOCK_UNLOCKED;
+ p->next = -1;
+ if (swap_flags & SWAP_FLAG_PREFER) {
+ p->prio =
+ (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
+ } else {
+ p->prio = --least_priority;
+ }
+ swap_list_unlock();
+ error = user_path_walk(specialfile, &nd);
+ if (error)
+ goto bad_swap_2;
+
+ p->swap_file = nd.dentry;
+ p->swap_vfsmnt = nd.mnt;
+ swap_inode = nd.dentry->d_inode;
+ error = -EINVAL;
+
+ if (S_ISBLK(swap_inode->i_mode)) {
+ kdev_t dev = swap_inode->i_rdev;
+ struct block_device_operations *bdops;
+ devfs_handle_t de;
+
+ p->swap_device = dev;
+ set_blocksize(dev, PAGE_SIZE);
+
+ bd_acquire(swap_inode);
+ bdev = swap_inode->i_bdev;
+ de = devfs_get_handle_from_inode(swap_inode);
+ bdops = devfs_get_ops(de); /* Increments module use count */
+ if (bdops) bdev->bd_op = bdops;
+
+ error = blkdev_get(bdev, FMODE_READ|FMODE_WRITE, 0, BDEV_SWAP);
+ devfs_put_ops(de);/*Decrement module use count now we're safe*/
+ if (error)
+ goto bad_swap_2;
+ set_blocksize(dev, PAGE_SIZE);
+ error = -ENODEV;
+ if (!dev || (blk_size[MAJOR(dev)] &&
+ !blk_size[MAJOR(dev)][MINOR(dev)]))
+ goto bad_swap;
+ swapfilesize = 0;
+ if (blk_size[MAJOR(dev)])
+ swapfilesize = blk_size[MAJOR(dev)][MINOR(dev)]
+ >> (PAGE_SHIFT - 10);
+ } else if (S_ISREG(swap_inode->i_mode))
+ swapfilesize = swap_inode->i_size >> PAGE_SHIFT;
+ else
+ goto bad_swap;
+
+ error = -EBUSY;
+ for (i = 0 ; i < nr_swapfiles ; i++) {
+ struct swap_info_struct *q = &swap_info[i];
+ if (i == type || !q->swap_file)
+ continue;
+ if (swap_inode->i_mapping == q->swap_file->d_inode->i_mapping)
+ goto bad_swap;
+ }
+
+ swap_header = (void *) __get_free_page(GFP_USER);
+ if (!swap_header) {
+ printk("Unable to start swapping: out of memory :-)\n");
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+
+ lock_page(virt_to_page(swap_header));
+ rw_swap_page_nolock(READ, SWP_ENTRY(type,0), (char *) swap_header);
+
+ if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
+ swap_header_version = 1;
+ else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
+ swap_header_version = 2;
+ else {
+ printk("Unable to find swap-space signature\n");
+ error = -EINVAL;
+ goto bad_swap;
+ }
+
+ switch (swap_header_version) {
+ case 1:
+ memset(((char *) swap_header)+PAGE_SIZE-10,0,10);
+ j = 0;
+ p->lowest_bit = 0;
+ p->highest_bit = 0;
+ for (i = 1 ; i < 8*PAGE_SIZE ; i++) {
+ if (test_bit(i,(char *) swap_header)) {
+ if (!p->lowest_bit)
+ p->lowest_bit = i;
+ p->highest_bit = i;
+ maxpages = i+1;
+ j++;
+ }
+ }
+ nr_good_pages = j;
+ p->swap_map = vmalloc(maxpages * sizeof(short));
+ if (!p->swap_map) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+ for (i = 1 ; i < maxpages ; i++) {
+ if (test_bit(i,(char *) swap_header))
+ p->swap_map[i] = 0;
+ else
+ p->swap_map[i] = SWAP_MAP_BAD;
+ }
+ break;
+
+ case 2:
+ /* Check the swap header's sub-version and the size of
+ the swap file and bad block lists */
+ if (swap_header->info.version != 1) {
+ printk(KERN_WARNING
+ "Unable to handle swap header version %d\n",
+ swap_header->info.version);
+ error = -EINVAL;
+ goto bad_swap;
+ }
+
+ p->lowest_bit = 1;
+ maxpages = SWP_OFFSET(SWP_ENTRY(0,~0UL)) - 1;
+ if (maxpages > swap_header->info.last_page)
+ maxpages = swap_header->info.last_page;
+ p->highest_bit = maxpages - 1;
+
+ error = -EINVAL;
+ if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+ goto bad_swap;
+
+ /* OK, set up the swap map and apply the bad block list */
+ if (!(p->swap_map = vmalloc(maxpages * sizeof(short)))) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
+
+ error = 0;
+ memset(p->swap_map, 0, maxpages * sizeof(short));
+ for (i=0; i<swap_header->info.nr_badpages; i++) {
+ int page = swap_header->info.badpages[i];
+ if (page <= 0 || page >= swap_header->info.last_page)
+ error = -EINVAL;
+ else
+ p->swap_map[page] = SWAP_MAP_BAD;
+ }
+ nr_good_pages = swap_header->info.last_page -
+ swap_header->info.nr_badpages -
+ 1 /* header page */;
+ if (error)
+ goto bad_swap;
+ }
+
+ if (swapfilesize && maxpages > swapfilesize) {
+ printk(KERN_WARNING
+ "Swap area shorter than signature indicates\n");
+ error = -EINVAL;
+ goto bad_swap;
+ }
+ if (!nr_good_pages) {
+ printk(KERN_WARNING "Empty swap-file\n");
+ error = -EINVAL;
+ goto bad_swap;
+ }
+ p->swap_map[0] = SWAP_MAP_BAD;
+ swap_list_lock();
+ swap_device_lock(p);
+ p->max = maxpages;
+ p->flags = SWP_WRITEOK;
+ p->pages = nr_good_pages;
+ nr_swap_pages += nr_good_pages;
+ total_swap_pages += nr_good_pages;
+ printk(KERN_INFO "Adding Swap: %dk swap-space (priority %d)\n",
+ nr_good_pages<<(PAGE_SHIFT-10), p->prio);
+
+ /* insert swap space into swap_list: */
+ prev = -1;
+ for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
+ if (p->prio >= swap_info[i].prio) {
+ break;
+ }
+ prev = i;
+ }
+ p->next = i;
+ if (prev < 0) {
+ swap_list.head = swap_list.next = p - swap_info;
+ } else {
+ swap_info[prev].next = p - swap_info;
+ }
+ swap_device_unlock(p);
+ swap_list_unlock();
+ error = 0;
+ goto out;
+bad_swap:
+ if (bdev)
+ blkdev_put(bdev, BDEV_SWAP);
+bad_swap_2:
+ swap_list_lock();
+ swap_map = p->swap_map;
+ nd.mnt = p->swap_vfsmnt;
+ nd.dentry = p->swap_file;
+ p->swap_device = 0;
+ p->swap_file = NULL;
+ p->swap_vfsmnt = NULL;
+ p->swap_map = NULL;
+ p->flags = 0;
+ if (!(swap_flags & SWAP_FLAG_PREFER))
+ ++least_priority;
+ swap_list_unlock();
+ if (swap_map)
+ vfree(swap_map);
+ path_release(&nd);
+out:
+ if (swap_header)
+ free_page((long) swap_header);
+ unlock_kernel();
+ return error;
+}
+
+void si_swapinfo(struct sysinfo *val)
+{
+ unsigned int i;
+ unsigned long nr_to_be_unused = 0;
+
+ swap_list_lock();
+ for (i = 0; i < nr_swapfiles; i++) {
+ unsigned int j;
+ if (swap_info[i].flags != SWP_USED)
+ continue;
+ for (j = 0; j < swap_info[i].max; ++j) {
+ switch (swap_info[i].swap_map[j]) {
+ case 0:
+ case SWAP_MAP_BAD:
+ continue;
+ default:
+ nr_to_be_unused++;
+ }
+ }
+ }
+ val->freeswap = nr_swap_pages + nr_to_be_unused;
+ val->totalswap = total_swap_pages + nr_to_be_unused;
+ swap_list_unlock();
+}
+
+/*
+ * Verify that a swap entry is valid and increment its swap map count.
+ *
+ * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
+ * "permanent", but will be reclaimed by the next swapoff.
+ */
+int swap_duplicate(swp_entry_t entry)
+{
+ struct swap_info_struct * p;
+ unsigned long offset, type;
+ int result = 0;
+
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles)
+ goto bad_file;
+ p = type + swap_info;
+ offset = SWP_OFFSET(entry);
+
+ swap_device_lock(p);
+ if (offset < p->max && p->swap_map[offset]) {
+ if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
+ p->swap_map[offset]++;
+ result = 1;
+ } else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
+ if (swap_overflow++ < 5)
+ printk(KERN_WARNING "swap_dup: swap entry overflow\n");
+ p->swap_map[offset] = SWAP_MAP_MAX;
+ result = 1;
+ }
+ }
+ swap_device_unlock(p);
+out:
+ return result;
+
+bad_file:
+ printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
+ goto out;
+}
+
+/*
+ * Prior swap_duplicate protects against swap device deletion.
+ */
+void get_swaphandle_info(swp_entry_t entry, unsigned long *offset,
+ kdev_t *dev, struct inode **swapf)
+{
+ unsigned long type;
+ struct swap_info_struct *p;
+
+ type = SWP_TYPE(entry);
+ if (type >= nr_swapfiles) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Bad_file, entry.val);
+ return;
+ }
+
+ p = &swap_info[type];
+ *offset = SWP_OFFSET(entry);
+ if (*offset >= p->max && *offset != 0) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Bad_offset, entry.val);
+ return;
+ }
+ if (p->swap_map && !p->swap_map[*offset]) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Unused_offset, entry.val);
+ return;
+ }
+ if (!(p->flags & SWP_USED)) {
+ printk(KERN_ERR "rw_swap_page: %s%08lx\n", Unused_file, entry.val);
+ return;
+ }
+
+ if (p->swap_device) {
+ *dev = p->swap_device;
+ } else if (p->swap_file) {
+ *swapf = p->swap_file->d_inode;
+ } else {
+ printk(KERN_ERR "rw_swap_page: no swap file or device\n");
+ }
+ return;
+}
+
+/*
+ * swap_device_lock prevents swap_map being freed. Don't grab an extra
+ * reference on the swaphandle, it doesn't matter if it becomes unused.
+ */
+int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
+{
+ int ret = 0, i = 1 << page_cluster;
+ unsigned long toff;
+ struct swap_info_struct *swapdev = SWP_TYPE(entry) + swap_info;
+
+ if (!page_cluster) /* no readahead */
+ return 0;
+ toff = (SWP_OFFSET(entry) >> page_cluster) << page_cluster;
+ if (!toff) /* first page is swap header */
+ toff++, i--;
+ *offset = toff;
+
+ swap_device_lock(swapdev);
+ do {
+ /* Don't read-ahead past the end of the swap area */
+ if (toff >= swapdev->max)
+ break;
+ /* Don't read in free or bad pages */
+ if (!swapdev->swap_map[toff])
+ break;
+ if (swapdev->swap_map[toff] == SWAP_MAP_BAD)
+ break;
+ toff++;
+ ret++;
+ } while (--i);
+ swap_device_unlock(swapdev);
+ return ret;
+}
projects / xen.git / commitdiff