From 966524933a019a56ee1ca8f9e920b116314f1eb4 Mon Sep 17 00:00:00 2001 From: "rneugeba@wyvis.research.intel-research.net" Date: Tue, 15 Mar 2005 14:50:10 +0000 Subject: [PATCH] bitkeeper revision 1.1245 (4236f622mMlu4s1f6bmCbV2qW4kvjw) added 2.4 batch mode Signed-off-by: michael.fetterman@cl.cam.ac.uk --- .rootkeys | 3 + .../arch/xen/i386/mm/fault.c | 6 + linux-2.6.10-xen-sparse/fs/exec.c | 1432 ++++++++++++++ .../include/asm-xen/asm-i386/pgtable-2level.h | 8 +- linux-2.6.10-xen-sparse/mm/highmem.c | 607 ++++++ linux-2.6.10-xen-sparse/mm/memory.c | 44 + linux-2.6.10-xen-sparse/mm/swapfile.c | 1711 +++++++++++++++++ 7 files changed, 3810 insertions(+), 1 deletion(-) create mode 100644 linux-2.6.10-xen-sparse/fs/exec.c create mode 100644 linux-2.6.10-xen-sparse/mm/highmem.c create mode 100644 linux-2.6.10-xen-sparse/mm/swapfile.c diff --git a/.rootkeys b/.rootkeys index e4a6475151..08be4b8690 100644 --- a/.rootkeys +++ b/.rootkeys @@ -230,6 +230,7 @@ 41ee5e8bglvqKvZSY5uJ5JGQejEwyQ linux-2.6.10-xen-sparse/drivers/xen/usbback/usbback.c 41ee5e8ckZ9xVNvu9NHIZDK7JqApmQ linux-2.6.10-xen-sparse/drivers/xen/usbfront/usbfront.c 41ee5e8ck9scpGirfqEZRARbGDyTXA linux-2.6.10-xen-sparse/drivers/xen/usbfront/xhci.h +4236f620IqJ4VZVDPfMJzrpFrio8Sw linux-2.6.10-xen-sparse/fs/exec.c 412f47e4RKD-R5IS5gEXvcT8L4v8gA linux-2.6.10-xen-sparse/include/asm-generic/pgtable.h 40f56239YAjS52QG2FIAQpHDZAdGHg linux-2.6.10-xen-sparse/include/asm-xen/asm-i386/desc.h 4107adf1E5O4ztGHNGMzCCNhcvqNow linux-2.6.10-xen-sparse/include/asm-xen/asm-i386/dma-mapping.h @@ -274,8 +275,10 @@ 4124f66f4NaKNa0xPiGGykn9QaZk3w linux-2.6.10-xen-sparse/include/linux/skbuff.h 419dfc6awx7w88wk6cG9P3mPidX6LQ linux-2.6.10-xen-sparse/kernel/irq/manage.c 40f56a0ddHCSs3501MY4hRf22tctOw linux-2.6.10-xen-sparse/mkbuildtree +4236f620IaM-42pgVYuNGF4cFrttbw linux-2.6.10-xen-sparse/mm/highmem.c 412f46c0LJuKAgSPGoC0Z1DEkLfuLA linux-2.6.10-xen-sparse/mm/memory.c 410a94a4KT6I6X0LVc7djB39tRDp4g linux-2.6.10-xen-sparse/mm/page_alloc.c +4236f620F2ZXlYSPUkwtN85tZMqDFQ linux-2.6.10-xen-sparse/mm/swapfile.c 41505c572m-s9ATiO1LiD1GPznTTIg linux-2.6.10-xen-sparse/net/core/skbuff.c 413cb1e4zst25MDYjg63Y-NGC5_pLg netbsd-2.0-xen-sparse/Makefile 413cb1e5c_Mkxf_X0zimEhTKI_l4DA netbsd-2.0-xen-sparse/mkbuildtree diff --git a/linux-2.6.10-xen-sparse/arch/xen/i386/mm/fault.c b/linux-2.6.10-xen-sparse/arch/xen/i386/mm/fault.c index 416b2be163..f5c7c16c68 100644 --- a/linux-2.6.10-xen-sparse/arch/xen/i386/mm/fault.c +++ b/linux-2.6.10-xen-sparse/arch/xen/i386/mm/fault.c @@ -231,6 +231,12 @@ fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code, error_code |= (regs->xcs & 2) << 1; if (regs->eflags & X86_EFLAGS_VM) error_code |= 4; + +#ifdef CONFIG_XEN_BATCH_MODE2 + /* ensure all updates have completed */ + flush_page_update_queue(); +#endif + if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, SIGSEGV) == NOTIFY_STOP) diff --git a/linux-2.6.10-xen-sparse/fs/exec.c b/linux-2.6.10-xen-sparse/fs/exec.c new file mode 100644 index 0000000000..6e8586561a --- /dev/null +++ b/linux-2.6.10-xen-sparse/fs/exec.c @@ -0,0 +1,1432 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifdef CONFIG_KMOD +#include +#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; +} + +EXPORT_SYMBOL(register_binfmt); + +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; +} + +EXPORT_SYMBOL(unregister_binfmt); + +static inline void put_binfmt(struct linux_binfmt * fmt) +{ + module_put(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 __user * library) +{ + struct file * file; + struct nameidata nd; + int error; + + nd.intent.open.flags = FMODE_READ; + error = __user_walk(library, LOOKUP_FOLLOW|LOOKUP_OPEN, &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, &nd); + 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) { + struct linux_binfmt * fmt; + + read_lock(&binfmt_lock); + for (fmt = formats ; fmt ; fmt = fmt->next) { + if (!fmt->load_shlib) + continue; + if (!try_module_get(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 strings in array ARGV. + */ +static int count(char __user * __user * argv, int max) +{ + int i = 0; + + if (argv != NULL) { + for (;;) { + char __user * p; + + if (get_user(p, argv)) + return -EFAULT; + if (!p) + break; + argv++; + if(++i > max) + return -E2BIG; + } + } + return i; +} + +/* + * 'copy_strings()' copies argument/environment 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 __user * __user * argv, struct linux_binprm *bprm) +{ + struct page *kmapped_page = NULL; + char *kaddr = NULL; + int ret; + + while (argc-- > 0) { + char __user *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, (char __user * __user *)argv, bprm); + set_fs(oldfs); + return r; +} + +EXPORT_SYMBOL(copy_strings_kernel); + +#ifdef CONFIG_MMU +/* + * This routine is used to map in a page into an address space: needed by + * execve() for the initial stack and environment pages. + * + * vma->vm_mm->mmap_sem is held for writing. + */ +void install_arg_page(struct vm_area_struct *vma, + struct page *page, unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + pgd_t * pgd; + pmd_t * pmd; + pte_t * pte; + + if (unlikely(anon_vma_prepare(vma))) + goto out_sig; + + flush_dcache_page(page); + pgd = pgd_offset(mm, address); + + spin_lock(&mm->page_table_lock); + pmd = pmd_alloc(mm, pgd, address); + if (!pmd) + goto out; + pte = pte_alloc_map(mm, pmd, address); + if (!pte) + goto out; + if (!pte_none(*pte)) { + pte_unmap(pte); + goto out; + } + mm->rss++; + lru_cache_add_active(page); + set_pte(pte, pte_mkdirty(pte_mkwrite(mk_pte( + page, vma->vm_page_prot)))); +#ifdef CONFIG_XEN_BATCH_MODE2 + XEN_flush_page_update_queue(); +#endif + page_add_anon_rmap(page, vma, address); + pte_unmap(pte); + spin_unlock(&mm->page_table_lock); + + /* no need for flush_tlb */ + return; +out: + spin_unlock(&mm->page_table_lock); +out_sig: + __free_page(page); + force_sig(SIGKILL, current); +} + +int setup_arg_pages(struct linux_binprm *bprm, int executable_stack) +{ + unsigned long stack_base; + struct vm_area_struct *mpnt; + struct mm_struct *mm = current->mm; + int i, ret; + long arg_size; + +#ifdef CONFIG_STACK_GROWSUP + /* Move the argument and environment strings to the bottom of the + * stack space. + */ + int offset, j; + char *to, *from; + + /* Start by shifting all the pages down */ + i = 0; + for (j = 0; j < MAX_ARG_PAGES; j++) { + struct page *page = bprm->page[j]; + if (!page) + continue; + bprm->page[i++] = page; + } + + /* Now move them within their pages */ + offset = bprm->p % PAGE_SIZE; + to = kmap(bprm->page[0]); + for (j = 1; j < i; j++) { + memmove(to, to + offset, PAGE_SIZE - offset); + from = kmap(bprm->page[j]); + memcpy(to + PAGE_SIZE - offset, from, offset); + kunmap(bprm->page[j - 1]); + to = from; + } + memmove(to, to + offset, PAGE_SIZE - offset); + kunmap(bprm->page[j - 1]); + + /* Adjust bprm->p to point to the end of the strings. */ + bprm->p = PAGE_SIZE * i - offset; + + /* Limit stack size to 1GB */ + stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max; + if (stack_base > (1 << 30)) + stack_base = 1 << 30; + stack_base = PAGE_ALIGN(STACK_TOP - stack_base); + + mm->arg_start = stack_base; + arg_size = i << PAGE_SHIFT; + + /* zero pages that were copied above */ + while (i < MAX_ARG_PAGES) + bprm->page[i++] = NULL; +#else + stack_base = STACK_TOP - MAX_ARG_PAGES * PAGE_SIZE; + mm->arg_start = bprm->p + stack_base; + arg_size = STACK_TOP - (PAGE_MASK & (unsigned long) mm->arg_start); +#endif + + 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; + + if (security_vm_enough_memory(arg_size >> PAGE_SHIFT)) { + kmem_cache_free(vm_area_cachep, mpnt); + return -ENOMEM; + } + + memset(mpnt, 0, sizeof(*mpnt)); + + down_write(&mm->mmap_sem); + { + mpnt->vm_mm = mm; +#ifdef CONFIG_STACK_GROWSUP + mpnt->vm_start = stack_base; + mpnt->vm_end = PAGE_MASK & + (PAGE_SIZE - 1 + (unsigned long) bprm->p); +#else + mpnt->vm_start = PAGE_MASK & (unsigned long) bprm->p; + mpnt->vm_end = STACK_TOP; +#endif + /* Adjust stack execute permissions; explicitly enable + * for EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X + * and leave alone (arch default) otherwise. */ + if (unlikely(executable_stack == EXSTACK_ENABLE_X)) + mpnt->vm_flags = VM_STACK_FLAGS | VM_EXEC; + else if (executable_stack == EXSTACK_DISABLE_X) + mpnt->vm_flags = VM_STACK_FLAGS & ~VM_EXEC; + else + mpnt->vm_flags = VM_STACK_FLAGS; + mpnt->vm_flags |= mm->def_flags; + mpnt->vm_page_prot = protection_map[mpnt->vm_flags & 0x7]; + if ((ret = insert_vm_struct(mm, mpnt))) { + up_write(&mm->mmap_sem); + kmem_cache_free(vm_area_cachep, mpnt); + return ret; + } + mm->stack_vm = mm->total_vm = vma_pages(mpnt); + } + + for (i = 0 ; i < MAX_ARG_PAGES ; i++) { + struct page *page = bprm->page[i]; + if (page) { + bprm->page[i] = NULL; + install_arg_page(mpnt, page, stack_base); + } + stack_base += PAGE_SIZE; + } + up_write(&mm->mmap_sem); + + return 0; +} + +EXPORT_SYMBOL(setup_arg_pages); + +#define free_arg_pages(bprm) do { } while (0) + +#else + +static inline void free_arg_pages(struct linux_binprm *bprm) +{ + int i; + + for (i = 0; i < MAX_ARG_PAGES; i++) { + if (bprm->page[i]) + __free_page(bprm->page[i]); + bprm->page[i] = NULL; + } +} + +#endif /* CONFIG_MMU */ + +struct file *open_exec(const char *name) +{ + struct nameidata nd; + int err; + struct file *file; + + nd.intent.open.flags = FMODE_READ; + err = path_lookup(name, LOOKUP_FOLLOW|LOOKUP_OPEN, &nd); + file = ERR_PTR(err); + + if (!err) { + struct inode *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, &nd); + 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; +} + +EXPORT_SYMBOL(open_exec); + +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; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + result = vfs_read(file, (void __user *)addr, count, &pos); + set_fs(old_fs); + return result; +} + +EXPORT_SYMBOL(kernel_read); + +static int exec_mmap(struct mm_struct *mm) +{ + struct task_struct *tsk; + struct mm_struct * old_mm, *active_mm; + + /* Notify parent that we're no longer interested in the old VM */ + tsk = current; + old_mm = current->mm; + mm_release(tsk, old_mm); + + task_lock(tsk); + active_mm = tsk->active_mm; + tsk->mm = mm; + tsk->active_mm = mm; + activate_mm(active_mm, mm); + task_unlock(tsk); + arch_pick_mmap_layout(mm); + if (old_mm) { + if (active_mm != old_mm) BUG(); + mmput(old_mm); + return 0; + } + mmdrop(active_mm); + return 0; +} + +/* + * 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_SIGHAND option to clone().) + */ +static inline int de_thread(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct sighand_struct *newsighand, *oldsighand = tsk->sighand; + spinlock_t *lock = &oldsighand->siglock; + int count; + + /* + * If we don't share sighandlers, then we aren't sharing anything + * and we can just re-use it all. + */ + if (atomic_read(&oldsighand->count) <= 1) { + BUG_ON(atomic_read(&sig->count) != 1); + exit_itimers(sig); + return 0; + } + + newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); + if (!newsighand) + return -ENOMEM; + + if (thread_group_empty(current)) + goto no_thread_group; + + /* + * Kill all other threads in the thread group. + * We must hold tasklist_lock to call zap_other_threads. + */ + read_lock(&tasklist_lock); + spin_lock_irq(lock); + if (sig->group_exit) { + /* + * Another group action in progress, just + * return so that the signal is processed. + */ + spin_unlock_irq(lock); + read_unlock(&tasklist_lock); + kmem_cache_free(sighand_cachep, newsighand); + return -EAGAIN; + } + sig->group_exit = 1; + zap_other_threads(current); + read_unlock(&tasklist_lock); + + /* + * Account for the thread group leader hanging around: + */ + count = 2; + if (current->pid == current->tgid) + count = 1; + while (atomic_read(&sig->count) > count) { + sig->group_exit_task = current; + sig->notify_count = count; + __set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock_irq(lock); + schedule(); + spin_lock_irq(lock); + } + sig->group_exit_task = NULL; + sig->notify_count = 0; + spin_unlock_irq(lock); + + /* + * At this point all other threads have exited, all we have to + * do is to wait for the thread group leader to become inactive, + * and to assume its PID: + */ + if (current->pid != current->tgid) { + struct task_struct *leader = current->group_leader, *parent; + struct dentry *proc_dentry1, *proc_dentry2; + unsigned long exit_state, ptrace; + + /* + * Wait for the thread group leader to be a zombie. + * It should already be zombie at this point, most + * of the time. + */ + while (leader->exit_state != EXIT_ZOMBIE) + yield(); + + spin_lock(&leader->proc_lock); + spin_lock(¤t->proc_lock); + proc_dentry1 = proc_pid_unhash(current); + proc_dentry2 = proc_pid_unhash(leader); + write_lock_irq(&tasklist_lock); + + if (leader->tgid != current->tgid) + BUG(); + if (current->pid == current->tgid) + BUG(); + /* + * An exec() starts a new thread group with the + * TGID of the previous thread group. Rehash the + * two threads with a switched PID, and release + * the former thread group leader: + */ + ptrace = leader->ptrace; + parent = leader->parent; + + ptrace_unlink(current); + ptrace_unlink(leader); + remove_parent(current); + remove_parent(leader); + + switch_exec_pids(leader, current); + + current->parent = current->real_parent = leader->real_parent; + leader->parent = leader->real_parent = child_reaper; + current->group_leader = current; + leader->group_leader = leader; + + add_parent(current, current->parent); + add_parent(leader, leader->parent); + if (ptrace) { + current->ptrace = ptrace; + __ptrace_link(current, parent); + } + + list_del(¤t->tasks); + list_add_tail(¤t->tasks, &init_task.tasks); + current->exit_signal = SIGCHLD; + exit_state = leader->exit_state; + + write_unlock_irq(&tasklist_lock); + spin_unlock(&leader->proc_lock); + spin_unlock(¤t->proc_lock); + proc_pid_flush(proc_dentry1); + proc_pid_flush(proc_dentry2); + + if (exit_state != EXIT_ZOMBIE) + BUG(); + release_task(leader); + } + + /* + * Now there are really no other threads at all, + * so it's safe to stop telling them to kill themselves. + */ + sig->group_exit = 0; + +no_thread_group: + BUG_ON(atomic_read(&sig->count) != 1); + exit_itimers(sig); + + if (atomic_read(&oldsighand->count) == 1) { + /* + * Now that we nuked the rest of the thread group, + * it turns out we are not sharing sighand any more either. + * So we can just keep it. + */ + kmem_cache_free(sighand_cachep, newsighand); + } else { + /* + * Move our state over to newsighand and switch it in. + */ + spin_lock_init(&newsighand->siglock); + atomic_set(&newsighand->count, 1); + memcpy(newsighand->action, oldsighand->action, + sizeof(newsighand->action)); + + write_lock_irq(&tasklist_lock); + spin_lock(&oldsighand->siglock); + spin_lock(&newsighand->siglock); + + current->sighand = newsighand; + recalc_sigpending(); + + spin_unlock(&newsighand->siglock); + spin_unlock(&oldsighand->siglock); + write_unlock_irq(&tasklist_lock); + + if (atomic_dec_and_test(&oldsighand->count)) + kmem_cache_free(sighand_cachep, oldsighand); + } + + if (!thread_group_empty(current)) + BUG(); + if (current->tgid != current->pid) + BUG(); + return 0; +} + +/* + * 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; + + spin_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; + spin_unlock(&files->file_lock); + for ( ; set ; i++,set >>= 1) { + if (set & 1) { + sys_close(i); + } + } + spin_lock(&files->file_lock); + + } + spin_unlock(&files->file_lock); +} + +void get_task_comm(char *buf, struct task_struct *tsk) +{ + /* buf must be at least sizeof(tsk->comm) in size */ + task_lock(tsk); + memcpy(buf, tsk->comm, sizeof(tsk->comm)); + task_unlock(tsk); +} + +void set_task_comm(struct task_struct *tsk, char *buf) +{ + task_lock(tsk); + strlcpy(tsk->comm, buf, sizeof(tsk->comm)); + task_unlock(tsk); +} + +int flush_old_exec(struct linux_binprm * bprm) +{ + char * name; + int i, ch, retval; + struct files_struct *files; + char tcomm[sizeof(current->comm)]; + + /* + * Make sure we have a private signal table and that + * we are unassociated from the previous thread group. + */ + retval = de_thread(current); + if (retval) + goto out; + + /* + * Make sure we have private file handles. Ask the + * fork helper to do the work for us and the exit + * helper to do the cleanup of the old one. + */ + files = current->files; /* refcounted so safe to hold */ + retval = unshare_files(); + if (retval) + goto out; + /* + * Release all of the old mmap stuff + */ + retval = exec_mmap(bprm->mm); + if (retval) + goto mmap_failed; + + bprm->mm = NULL; /* We're using it now */ + + /* This is the point of no return */ + steal_locks(files); + put_files_struct(files); + + 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 < (sizeof(tcomm) - 1)) + tcomm[i++] = ch; + } + tcomm[i] = '\0'; + set_task_comm(current, tcomm); + + flush_thread(); + + if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || + permission(bprm->file->f_dentry->d_inode,MAY_READ, NULL) || + (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) { + suid_keys(current); + 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, 0); + flush_old_files(current->files); + + return 0; + +mmap_failed: + put_files_struct(current->files); + current->files = files; +out: + return retval; +} + +EXPORT_SYMBOL(flush_old_exec); + +/* + * 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; + int retval; + + mode = inode->i_mode; + /* + * Check execute perms again - if the caller has CAP_DAC_OVERRIDE, + * generic_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) { + current->personality &= ~PER_CLEAR_ON_SETID; + 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)) { + current->personality &= ~PER_CLEAR_ON_SETID; + bprm->e_gid = inode->i_gid; + } + } + + /* fill in binprm security blob */ + retval = security_bprm_set(bprm); + if (retval) + return retval; + + memset(bprm->buf,0,BINPRM_BUF_SIZE); + return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE); +} + +EXPORT_SYMBOL(prepare_binprm); + +static inline int unsafe_exec(struct task_struct *p) +{ + int unsafe = 0; + if (p->ptrace & PT_PTRACED) { + if (p->ptrace & PT_PTRACE_CAP) + unsafe |= LSM_UNSAFE_PTRACE_CAP; + else + unsafe |= LSM_UNSAFE_PTRACE; + } + if (atomic_read(&p->fs->count) > 1 || + atomic_read(&p->files->count) > 1 || + atomic_read(&p->sighand->count) > 1) + unsafe |= LSM_UNSAFE_SHARE; + + return unsafe; +} + +void compute_creds(struct linux_binprm *bprm) +{ + int unsafe; + + if (bprm->e_uid != current->uid) + suid_keys(current); + exec_keys(current); + + task_lock(current); + unsafe = unsafe_exec(current); + security_bprm_apply_creds(bprm, unsafe); + task_unlock(current); +} + +EXPORT_SYMBOL(compute_creds); + +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_atomic(kaddr, KM_USER0); +inside: + page = bprm->page[bprm->p/PAGE_SIZE]; + kaddr = kmap_atomic(page, KM_USER0); + } + kunmap_atomic(kaddr, KM_USER0); + bprm->argc--; + } +} + +EXPORT_SYMBOL(remove_arg_zero); + +/* + * 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; + 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 < 0x100000000UL; + + 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 + retval = security_bprm_check(bprm); + if (retval) + return retval; + + /* kernel module loader fixup */ + /* so we don't try to load run modprobe in kernel space. */ + set_fs(USER_DS); + retval = -ENOENT; + 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_module_get(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 || bprm->mm == NULL) + break; + if (!bprm->file) { + read_unlock(&binfmt_lock); + return retval; + } + } + read_unlock(&binfmt_lock); + if (retval != -ENOEXEC || bprm->mm == NULL) { + break; +#ifdef CONFIG_KMOD + }else{ +#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) + if (printable(bprm->buf[0]) && + printable(bprm->buf[1]) && + printable(bprm->buf[2]) && + printable(bprm->buf[3])) + break; /* -ENOEXEC */ + request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2])); +#endif + } + } + return retval; +} + +EXPORT_SYMBOL(search_binary_handler); + +/* + * sys_execve() executes a new program. + */ +int do_execve(char * filename, + char __user *__user *argv, + char __user *__user *envp, + struct pt_regs * regs) +{ + struct linux_binprm *bprm; + struct file *file; + int retval; + int i; + + retval = -ENOMEM; + bprm = kmalloc(sizeof(*bprm), GFP_KERNEL); + if (!bprm) + goto out_ret; + memset(bprm, 0, sizeof(*bprm)); + + file = open_exec(filename); + retval = PTR_ERR(file); + if (IS_ERR(file)) + goto out_kfree; + + sched_exec(); + + bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *); + + bprm->file = file; + bprm->filename = filename; + bprm->interp = filename; + bprm->mm = mm_alloc(); + retval = -ENOMEM; + if (!bprm->mm) + goto out_file; + + retval = init_new_context(current, bprm->mm); + if (retval < 0) + goto out_mm; + + bprm->argc = count(argv, bprm->p / sizeof(void *)); + if ((retval = bprm->argc) < 0) + goto out_mm; + + bprm->envc = count(envp, bprm->p / sizeof(void *)); + if ((retval = bprm->envc) < 0) + goto out_mm; + + retval = security_bprm_alloc(bprm); + if (retval) + goto out; + + 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) { + free_arg_pages(bprm); + + /* execve success */ + security_bprm_free(bprm); + kfree(bprm); + return retval; + } + +out: + /* Something went wrong, return the inode and free the argument pages*/ + for (i = 0 ; i < MAX_ARG_PAGES ; i++) { + struct page * page = bprm->page[i]; + if (page) + __free_page(page); + } + + if (bprm->security) + security_bprm_free(bprm); + +out_mm: + if (bprm->mm) + mmdrop(bprm->mm); + +out_file: + if (bprm->file) { + allow_write_access(bprm->file); + fput(bprm->file); + } + +out_kfree: + kfree(bprm); + +out_ret: + return retval; +} + +int set_binfmt(struct linux_binfmt *new) +{ + struct linux_binfmt *old = current->binfmt; + + if (new) { + if (!try_module_get(new->module)) + return -1; + } + current->binfmt = new; + if (old) + module_put(old->module); + return 0; +} + +EXPORT_SYMBOL(set_binfmt); + +#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. + */ +static 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->tgid); + 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, + "%lu", 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->tgid); + if (rc > out_end - out_ptr) + goto out; + out_ptr += rc; + } + out: + *out_ptr = 0; +} + +static void zap_threads (struct mm_struct *mm) +{ + struct task_struct *g, *p; + struct task_struct *tsk = current; + struct completion *vfork_done = tsk->vfork_done; + + /* + * Make sure nobody is waiting for us to release the VM, + * otherwise we can deadlock when we wait on each other + */ + if (vfork_done) { + tsk->vfork_done = NULL; + complete(vfork_done); + } + + read_lock(&tasklist_lock); + do_each_thread(g,p) + if (mm == p->mm && p != tsk) { + force_sig_specific(SIGKILL, p); + mm->core_waiters++; + } + while_each_thread(g,p); + + read_unlock(&tasklist_lock); +} + +static void coredump_wait(struct mm_struct *mm) +{ + DECLARE_COMPLETION(startup_done); + + mm->core_waiters++; /* let other threads block */ + mm->core_startup_done = &startup_done; + + /* give other threads a chance to run: */ + yield(); + + zap_threads(mm); + if (--mm->core_waiters) { + up_write(&mm->mmap_sem); + wait_for_completion(&startup_done); + } else + up_write(&mm->mmap_sem); + BUG_ON(mm->core_waiters); +} + +int do_coredump(long signr, int exit_code, struct pt_regs * regs) +{ + char corename[CORENAME_MAX_SIZE + 1]; + struct mm_struct *mm = current->mm; + struct linux_binfmt * binfmt; + struct inode * inode; + struct file * file; + int retval = 0; + + binfmt = current->binfmt; + if (!binfmt || !binfmt->core_dump) + goto fail; + down_write(&mm->mmap_sem); + if (!mm->dumpable) { + up_write(&mm->mmap_sem); + goto fail; + } + mm->dumpable = 0; + init_completion(&mm->core_done); + current->signal->group_exit = 1; + current->signal->group_exit_code = exit_code; + coredump_wait(mm); + + if (current->signal->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump) + goto fail_unlock; + + /* + * lock_kernel() because format_corename() is controlled by sysctl, which + * uses lock_kernel() + */ + lock_kernel(); + format_corename(corename, core_pattern, signr); + unlock_kernel(); + file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE, 0600); + if (IS_ERR(file)) + goto fail_unlock; + 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); + + if (retval) + current->signal->group_exit_code |= 0x80; +close_fail: + filp_close(file, NULL); +fail_unlock: + complete_all(&mm->core_done); +fail: + return retval; +} diff --git a/linux-2.6.10-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h b/linux-2.6.10-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h index 8c1a53ee75..483c255f07 100644 --- a/linux-2.6.10-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h +++ b/linux-2.6.10-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h @@ -39,10 +39,16 @@ do { \ #if defined(CONFIG_XEN_DEBUG_NO_MMU_BATCHING) #define set_pte(pteptr, pteval)\ set_pte_batched(pteptr, pteval) -#elif defined(CONFIG_XEN_BATCH_MODE) + +#elif defined(CONFIG_XEN_BATCH_MODE1) #define set_pte(pteptr, pteval)({\ set_pte_batched(pteptr, pteval);\ _flush_page_update_queue();}) + +#elif defined(CONFIG_XEN_BATCH_MODE2) +#define set_pte(pteptr, pteval)\ + set_pte_batched(pteptr, pteval) + #else #define set_pte(pteptr, pteval) (*(pteptr) = pteval) #endif diff --git a/linux-2.6.10-xen-sparse/mm/highmem.c b/linux-2.6.10-xen-sparse/mm/highmem.c new file mode 100644 index 0000000000..bf9fbdc5c5 --- /dev/null +++ b/linux-2.6.10-xen-sparse/mm/highmem.c @@ -0,0 +1,607 @@ +/* + * High memory handling common code and variables. + * + * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de + * Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de + * + * + * Redesigned the x86 32-bit VM architecture to deal with + * 64-bit physical space. With current x86 CPUs this + * means up to 64 Gigabytes physical RAM. + * + * Rewrote high memory support to move the page cache into + * high memory. Implemented permanent (schedulable) kmaps + * based on Linus' idea. + * + * Copyright (C) 1999 Ingo Molnar + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static mempool_t *page_pool, *isa_page_pool; + +static void *page_pool_alloc(int gfp_mask, void *data) +{ + int gfp = gfp_mask | (int) (long) data; + + return alloc_page(gfp); +} + +static void page_pool_free(void *page, void *data) +{ + __free_page(page); +} + +/* + * Virtual_count is not a pure "count". + * 0 means that it is not mapped, and has not been mapped + * since a TLB flush - it is usable. + * 1 means that there are no users, but it has been mapped + * since the last TLB flush - so we can't use it. + * n means that there are (n-1) current users of it. + */ +#ifdef CONFIG_HIGHMEM +static int pkmap_count[LAST_PKMAP]; +static unsigned int last_pkmap_nr; +static spinlock_t kmap_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED; + +pte_t * pkmap_page_table; + +static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); + +static void flush_all_zero_pkmaps(void) +{ + int i; + + flush_cache_kmaps(); + + for (i = 0; i < LAST_PKMAP; i++) { + struct page *page; + + /* + * zero means we don't have anything to do, + * >1 means that it is still in use. Only + * a count of 1 means that it is free but + * needs to be unmapped + */ + if (pkmap_count[i] != 1) + continue; + pkmap_count[i] = 0; + + /* sanity check */ + if (pte_none(pkmap_page_table[i])) + BUG(); + + /* + * Don't need an atomic fetch-and-clear op here; + * no-one has the page mapped, and cannot get at + * its virtual address (and hence PTE) without first + * getting the kmap_lock (which is held here). + * So no dangers, even with speculative execution. + */ + page = pte_page(pkmap_page_table[i]); + pte_clear(&pkmap_page_table[i]); + + set_page_address(page, NULL); + } + flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP)); +} + +static inline unsigned long map_new_virtual(struct page *page) +{ + unsigned long vaddr; + int count; + +start: + count = LAST_PKMAP; + /* Find an empty entry */ + for (;;) { + last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK; + if (!last_pkmap_nr) { + flush_all_zero_pkmaps(); + count = LAST_PKMAP; + } + if (!pkmap_count[last_pkmap_nr]) + break; /* Found a usable entry */ + if (--count) + continue; + + /* + * Sleep for somebody else to unmap their entries + */ + { + DECLARE_WAITQUEUE(wait, current); + + __set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue(&pkmap_map_wait, &wait); + spin_unlock(&kmap_lock); + schedule(); + remove_wait_queue(&pkmap_map_wait, &wait); + spin_lock(&kmap_lock); + + /* Somebody else might have mapped it while we slept */ + if (page_address(page)) + return (unsigned long)page_address(page); + + /* Re-start */ + goto start; + } + } + vaddr = PKMAP_ADDR(last_pkmap_nr); + set_pte(&(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot)); +#ifdef CONFIG_XEN_BATCH_MODE2 + XEN_flush_page_update_queue(); +#endif + pkmap_count[last_pkmap_nr] = 1; + set_page_address(page, (void *)vaddr); + + return vaddr; +} + +void fastcall *kmap_high(struct page *page) +{ + unsigned long vaddr; + + /* + * For highmem pages, we can't trust "virtual" until + * after we have the lock. + * + * We cannot call this from interrupts, as it may block + */ + spin_lock(&kmap_lock); + vaddr = (unsigned long)page_address(page); + if (!vaddr) + vaddr = map_new_virtual(page); + pkmap_count[PKMAP_NR(vaddr)]++; + if (pkmap_count[PKMAP_NR(vaddr)] < 2) + BUG(); + spin_unlock(&kmap_lock); + return (void*) vaddr; +} + +EXPORT_SYMBOL(kmap_high); + +void fastcall kunmap_high(struct page *page) +{ + unsigned long vaddr; + unsigned long nr; + int need_wakeup; + + spin_lock(&kmap_lock); + vaddr = (unsigned long)page_address(page); + if (!vaddr) + BUG(); + nr = PKMAP_NR(vaddr); + + /* + * A count must never go down to zero + * without a TLB flush! + */ + need_wakeup = 0; + switch (--pkmap_count[nr]) { + case 0: + BUG(); + case 1: + /* + * Avoid an unnecessary wake_up() function call. + * The common case is pkmap_count[] == 1, but + * no waiters. + * The tasks queued in the wait-queue are guarded + * by both the lock in the wait-queue-head and by + * the kmap_lock. As the kmap_lock is held here, + * no need for the wait-queue-head's lock. Simply + * test if the queue is empty. + */ + need_wakeup = waitqueue_active(&pkmap_map_wait); + } + spin_unlock(&kmap_lock); + + /* do wake-up, if needed, race-free outside of the spin lock */ + if (need_wakeup) + wake_up(&pkmap_map_wait); +} + +EXPORT_SYMBOL(kunmap_high); + +#define POOL_SIZE 64 + +static __init int init_emergency_pool(void) +{ + struct sysinfo i; + si_meminfo(&i); + si_swapinfo(&i); + + if (!i.totalhigh) + return 0; + + page_pool = mempool_create(POOL_SIZE, page_pool_alloc, page_pool_free, NULL); + if (!page_pool) + BUG(); + printk("highmem bounce pool size: %d pages\n", POOL_SIZE); + + return 0; +} + +__initcall(init_emergency_pool); + +/* + * highmem version, map in to vec + */ +static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) +{ + unsigned long flags; + unsigned char *vto; + + local_irq_save(flags); + vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ); + memcpy(vto + to->bv_offset, vfrom, to->bv_len); + kunmap_atomic(vto, KM_BOUNCE_READ); + local_irq_restore(flags); +} + +#else /* CONFIG_HIGHMEM */ + +#define bounce_copy_vec(to, vfrom) \ + memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len) + +#endif + +#define ISA_POOL_SIZE 16 + +/* + * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA + * as the max address, so check if the pool has already been created. + */ +int init_emergency_isa_pool(void) +{ + if (isa_page_pool) + return 0; + + isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc, page_pool_free, (void *) __GFP_DMA); + if (!isa_page_pool) + BUG(); + + printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE); + return 0; +} + +/* + * Simple bounce buffer support for highmem pages. Depending on the + * queue gfp mask set, *to may or may not be a highmem page. kmap it + * always, it will do the Right Thing + */ +static void copy_to_high_bio_irq(struct bio *to, struct bio *from) +{ + unsigned char *vfrom; + struct bio_vec *tovec, *fromvec; + int i; + + __bio_for_each_segment(tovec, to, i, 0) { + fromvec = from->bi_io_vec + i; + + /* + * not bounced + */ + if (tovec->bv_page == fromvec->bv_page) + continue; + + /* + * fromvec->bv_offset and fromvec->bv_len might have been + * modified by the block layer, so use the original copy, + * bounce_copy_vec already uses tovec->bv_len + */ + vfrom = page_address(fromvec->bv_page) + tovec->bv_offset; + + flush_dcache_page(tovec->bv_page); + bounce_copy_vec(tovec, vfrom); + } +} + +static void bounce_end_io(struct bio *bio, mempool_t *pool, int err) +{ + struct bio *bio_orig = bio->bi_private; + struct bio_vec *bvec, *org_vec; + int i; + + if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags)) + set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags); + + /* + * free up bounce indirect pages used + */ + __bio_for_each_segment(bvec, bio, i, 0) { + org_vec = bio_orig->bi_io_vec + i; + if (bvec->bv_page == org_vec->bv_page) + continue; + + mempool_free(bvec->bv_page, pool); + } + + bio_endio(bio_orig, bio_orig->bi_size, err); + bio_put(bio); +} + +static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done,int err) +{ + if (bio->bi_size) + return 1; + + bounce_end_io(bio, page_pool, err); + return 0; +} + +static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + bounce_end_io(bio, isa_page_pool, err); + return 0; +} + +static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err) +{ + struct bio *bio_orig = bio->bi_private; + + if (test_bit(BIO_UPTODATE, &bio->bi_flags)) + copy_to_high_bio_irq(bio_orig, bio); + + bounce_end_io(bio, pool, err); +} + +static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + __bounce_end_io_read(bio, page_pool, err); + return 0; +} + +static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + __bounce_end_io_read(bio, isa_page_pool, err); + return 0; +} + +static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig, + mempool_t *pool) +{ + struct page *page; + struct bio *bio = NULL; + int i, rw = bio_data_dir(*bio_orig); + struct bio_vec *to, *from; + + bio_for_each_segment(from, *bio_orig, i) { + page = from->bv_page; + + /* + * is destination page below bounce pfn? + */ + if (page_to_pfn(page) < q->bounce_pfn) + continue; + + /* + * irk, bounce it + */ + if (!bio) + bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt); + + to = bio->bi_io_vec + i; + + to->bv_page = mempool_alloc(pool, q->bounce_gfp); + to->bv_len = from->bv_len; + to->bv_offset = from->bv_offset; + + if (rw == WRITE) { + char *vto, *vfrom; + + flush_dcache_page(from->bv_page); + vto = page_address(to->bv_page) + to->bv_offset; + vfrom = kmap(from->bv_page) + from->bv_offset; + memcpy(vto, vfrom, to->bv_len); + kunmap(from->bv_page); + } + } + + /* + * no pages bounced + */ + if (!bio) + return; + + /* + * at least one page was bounced, fill in possible non-highmem + * pages + */ + bio_for_each_segment(from, *bio_orig, i) { + to = bio_iovec_idx(bio, i); + if (!to->bv_page) { + to->bv_page = from->bv_page; + to->bv_len = from->bv_len; + to->bv_offset = from->bv_offset; + } + } + + bio->bi_bdev = (*bio_orig)->bi_bdev; + bio->bi_flags |= (1 << BIO_BOUNCED); + bio->bi_sector = (*bio_orig)->bi_sector; + bio->bi_rw = (*bio_orig)->bi_rw; + + bio->bi_vcnt = (*bio_orig)->bi_vcnt; + bio->bi_idx = (*bio_orig)->bi_idx; + bio->bi_size = (*bio_orig)->bi_size; + + if (pool == page_pool) { + bio->bi_end_io = bounce_end_io_write; + if (rw == READ) + bio->bi_end_io = bounce_end_io_read; + } else { + bio->bi_end_io = bounce_end_io_write_isa; + if (rw == READ) + bio->bi_end_io = bounce_end_io_read_isa; + } + + bio->bi_private = *bio_orig; + *bio_orig = bio; +} + +void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig) +{ + mempool_t *pool; + + /* + * for non-isa bounce case, just check if the bounce pfn is equal + * to or bigger than the highest pfn in the system -- in that case, + * don't waste time iterating over bio segments + */ + if (!(q->bounce_gfp & GFP_DMA)) { + if (q->bounce_pfn >= blk_max_pfn) + return; + pool = page_pool; + } else { + BUG_ON(!isa_page_pool); + pool = isa_page_pool; + } + + /* + * slow path + */ + __blk_queue_bounce(q, bio_orig, pool); +} + +EXPORT_SYMBOL(blk_queue_bounce); + +#if defined(HASHED_PAGE_VIRTUAL) + +#define PA_HASH_ORDER 7 + +/* + * Describes one page->virtual association + */ +struct page_address_map { + struct page *page; + void *virtual; + struct list_head list; +}; + +/* + * page_address_map freelist, allocated from page_address_maps. + */ +static struct list_head page_address_pool; /* freelist */ +static spinlock_t pool_lock; /* protects page_address_pool */ + +/* + * Hash table bucket + */ +static struct page_address_slot { + struct list_head lh; /* List of page_address_maps */ + spinlock_t lock; /* Protect this bucket's list */ +} ____cacheline_aligned_in_smp page_address_htable[1<lock, flags); + if (!list_empty(&pas->lh)) { + struct page_address_map *pam; + + list_for_each_entry(pam, &pas->lh, list) { + if (pam->page == page) { + ret = pam->virtual; + goto done; + } + } + } +done: + spin_unlock_irqrestore(&pas->lock, flags); + return ret; +} + +EXPORT_SYMBOL(page_address); + +void set_page_address(struct page *page, void *virtual) +{ + unsigned long flags; + struct page_address_slot *pas; + struct page_address_map *pam; + + BUG_ON(!PageHighMem(page)); + + pas = page_slot(page); + if (virtual) { /* Add */ + BUG_ON(list_empty(&page_address_pool)); + + spin_lock_irqsave(&pool_lock, flags); + pam = list_entry(page_address_pool.next, + struct page_address_map, list); + list_del(&pam->list); + spin_unlock_irqrestore(&pool_lock, flags); + + pam->page = page; + pam->virtual = virtual; + + spin_lock_irqsave(&pas->lock, flags); + list_add_tail(&pam->list, &pas->lh); + spin_unlock_irqrestore(&pas->lock, flags); + } else { /* Remove */ + spin_lock_irqsave(&pas->lock, flags); + list_for_each_entry(pam, &pas->lh, list) { + if (pam->page == page) { + list_del(&pam->list); + spin_unlock_irqrestore(&pas->lock, flags); + spin_lock_irqsave(&pool_lock, flags); + list_add_tail(&pam->list, &page_address_pool); + spin_unlock_irqrestore(&pool_lock, flags); + goto done; + } + } + spin_unlock_irqrestore(&pas->lock, flags); + } +done: + return; +} + +static struct page_address_map page_address_maps[LAST_PKMAP]; + +void __init page_address_init(void) +{ + int i; + + INIT_LIST_HEAD(&page_address_pool); + for (i = 0; i < ARRAY_SIZE(page_address_maps); i++) + list_add(&page_address_maps[i].list, &page_address_pool); + for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) { + INIT_LIST_HEAD(&page_address_htable[i].lh); + spin_lock_init(&page_address_htable[i].lock); + } + spin_lock_init(&pool_lock); +} + +#endif /* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */ diff --git a/linux-2.6.10-xen-sparse/mm/memory.c b/linux-2.6.10-xen-sparse/mm/memory.c index 67ad006621..29a56f125a 100644 --- a/linux-2.6.10-xen-sparse/mm/memory.c +++ b/linux-2.6.10-xen-sparse/mm/memory.c @@ -152,6 +152,10 @@ void clear_page_tables(struct mmu_gather *tlb, unsigned long first, int nr) free_one_pgd(tlb, page_dir); page_dir++; } while (--nr); +#ifdef CONFIG_XEN_BATCH_MODE2 + XEN_flush_page_update_queue(); +#endif + } pte_t fastcall * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address) @@ -326,8 +330,15 @@ skip_copy_pte_range: * in the parent and the child */ if (cow) { +#ifdef CONFIG_XEN_BATCH_MODE2 +/* XEN modification: modified ordering here to avoid RaW hazard. */ + pte = *src_pte; + pte = pte_wrprotect(pte); + ptep_set_wrprotect(src_pte); +#else ptep_set_wrprotect(src_pte); pte = *src_pte; +#endif } /* @@ -1451,7 +1462,20 @@ static int do_swap_page(struct mm_struct * mm, unlock_page(page); flush_icache_page(vma, page); + +#ifdef CONFIG_XEN_BATCH_MODE2 + if ( likely(vma->vm_mm == current->mm) ) { + XEN_flush_page_update_queue(); + HYPERVISOR_update_va_mapping(address, pte, 0); + } else { + set_pte(page_table, pte); + XEN_flush_page_update_queue(); + } +#else set_pte(page_table, pte); +#endif + + page_add_anon_rmap(page, vma, address); if (write_access) { @@ -1516,7 +1540,17 @@ do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, page_add_anon_rmap(page, vma, addr); } +#ifdef CONFIG_XEN_BATCH_MODE2 + if ( likely(vma->vm_mm == current->mm) ) { + XEN_flush_page_update_queue(); + HYPERVISOR_update_va_mapping(addr, entry, 0); + } else { + set_pte(page_table, entry); + XEN_flush_page_update_queue(); + } +#else ptep_establish_new(vma, addr, page_table, entry); +#endif pte_unmap(page_table); /* No need to invalidate - it was non-present before */ @@ -1621,7 +1655,17 @@ retry: entry = mk_pte(new_page, vma->vm_page_prot); if (write_access) entry = maybe_mkwrite(pte_mkdirty(entry), vma); +#ifdef CONFIG_XEN_BATCH_MODE2 + if ( likely(vma->vm_mm == current->mm) ) { + XEN_flush_page_update_queue(); + HYPERVISOR_update_va_mapping(address, entry, 0); + } else { + set_pte(page_table, entry); + XEN_flush_page_update_queue(); + } +#else ptep_establish_new(vma, address, page_table, entry); +#endif if (anon) { lru_cache_add_active(new_page); page_add_anon_rmap(new_page, vma, address); diff --git a/linux-2.6.10-xen-sparse/mm/swapfile.c b/linux-2.6.10-xen-sparse/mm/swapfile.c new file mode 100644 index 0000000000..788e2424ac --- /dev/null +++ b/linux-2.6.10-xen-sparse/mm/swapfile.c @@ -0,0 +1,1711 @@ +/* + * linux/mm/swapfile.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * Swap reorganised 29.12.95, Stephen Tweedie + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +spinlock_t swaplock = SPIN_LOCK_UNLOCKED; +unsigned int nr_swapfiles; +long total_swap_pages; +static int swap_overflow; + +EXPORT_SYMBOL(total_swap_pages); + +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]; + +static DECLARE_MUTEX(swapon_sem); + +/* + * We need this because the bdev->unplug_fn can sleep and we cannot + * hold swap_list_lock while calling the unplug_fn. And swap_list_lock + * cannot be turned into a semaphore. + */ +static DECLARE_RWSEM(swap_unplug_sem); + +#define SWAPFILE_CLUSTER 256 + +void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) +{ + swp_entry_t entry; + + down_read(&swap_unplug_sem); + entry.val = page->private; + if (PageSwapCache(page)) { + struct block_device *bdev = swap_info[swp_type(entry)].bdev; + struct backing_dev_info *bdi; + + /* + * If the page is removed from swapcache from under us (with a + * racy try_to_unuse/swapoff) we need an additional reference + * count to avoid reading garbage from page->private above. If + * the WARN_ON triggers during a swapoff it maybe the race + * condition and it's harmless. However if it triggers without + * swapoff it signals a problem. + */ + WARN_ON(page_count(page) <= 1); + + bdi = bdev->bd_inode->i_mapping->backing_dev_info; + bdi->unplug_io_fn(bdi, page); + } + up_read(&swap_unplug_sem); +} + +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) + { + unsigned long 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; + si->inuse_pages++; + 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_ACTIVE) == SWP_ACTIVE) { + 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++; + p->inuse_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->private; + 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 swapcache lock held.. */ + spin_lock_irq(&swapper_space.tree_lock); + if (page_count(page) == 2) + retval = 1; + spin_unlock_irq(&swapper_space.tree_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 (!PagePrivate(page)) + 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; + + BUG_ON(PagePrivate(page)); + BUG_ON(!PageLocked(page)); + + if (!PageSwapCache(page)) + return 0; + if (PageWriteback(page)) + return 0; + if (page_count(page) != 2) /* 2: us + cache */ + return 0; + + entry.val = page->private; + 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 swapcache lock held.. */ + spin_lock_irq(&swapper_space.tree_lock); + if ((page_count(page) == 2) && !PageWriteback(page)) { + __delete_from_swap_cache(page); + SetPageDirty(page); + retval = 1; + } + spin_unlock_irq(&swapper_space.tree_lock); + } + swap_info_put(p); + + if (retval) { + 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) { + spin_lock_irq(&swapper_space.tree_lock); + page = radix_tree_lookup(&swapper_space.page_tree, + entry.val); + if (page && TestSetPageLocked(page)) + page = NULL; + spin_unlock_irq(&swapper_space.tree_lock); + } + swap_info_put(p); + } + if (page) { + int one_user; + + BUG_ON(PagePrivate(page)); + page_cache_get(page); + one_user = (page_count(page) == 2); + /* Only cache user (+us), or swap space full? Free it! */ + if (!PageWriteback(page) && (one_user || vm_swap_full())) { + delete_from_swap_cache(page); + SetPageDirty(page); + } + unlock_page(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. + */ +/* vma->vm_mm->page_table_lock is held */ +static void +unuse_pte(struct vm_area_struct *vma, unsigned long address, pte_t *dir, + swp_entry_t entry, struct page *page) +{ + vma->vm_mm->rss++; + get_page(page); + set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot))); + page_add_anon_rmap(page, vma, address); + swap_free(entry); +} + +/* vma->vm_mm->page_table_lock is held */ +static unsigned long 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; + pte_t swp_pte = swp_entry_to_pte(entry); + + if (pmd_none(*dir)) + return 0; + if (pmd_bad(*dir)) { + pmd_ERROR(*dir); + pmd_clear(dir); + return 0; + } + pte = pte_offset_map(dir, address); + offset += address & PMD_MASK; + address &= ~PMD_MASK; + end = address + size; + if (end > PMD_SIZE) + end = PMD_SIZE; + do { + /* + * swapoff spends a _lot_ of time in this loop! + * Test inline before going to call unuse_pte. + */ + if (unlikely(pte_same(*pte, swp_pte))) { + unuse_pte(vma, offset + address, pte, entry, page); + pte_unmap(pte); + + /* + * Move the page to the active list so it is not + * immediately swapped out again after swapon. + */ + activate_page(page); + + /* add 1 since address may be 0 */ + return 1 + offset + address; + } + address += PAGE_SIZE; + pte++; + } while (address && (address < end)); + pte_unmap(pte - 1); + return 0; +} + +/* vma->vm_mm->page_table_lock is held */ +static unsigned long 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; + unsigned long foundaddr; + + if (pgd_none(*dir)) + return 0; + if (pgd_bad(*dir)) { + pgd_ERROR(*dir); + pgd_clear(dir); + return 0; + } + 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 { + foundaddr = unuse_pmd(vma, pmd, address, end - address, + offset, entry, page); + if (foundaddr) + return foundaddr; + address = (address + PMD_SIZE) & PMD_MASK; + pmd++; + } while (address && (address < end)); + return 0; +} + +/* vma->vm_mm->page_table_lock is held */ +static unsigned long unuse_vma(struct vm_area_struct * vma, + swp_entry_t entry, struct page *page) +{ + pgd_t *pgdir; + unsigned long start, end; + unsigned long foundaddr; + + if (page->mapping) { + start = page_address_in_vma(page, vma); + if (start == -EFAULT) + return 0; + else + end = start + PAGE_SIZE; + } else { + start = vma->vm_start; + end = vma->vm_end; + } + pgdir = pgd_offset(vma->vm_mm, start); + do { + foundaddr = unuse_pgd(vma, pgdir, start, end - start, + entry, page); + if (foundaddr) + return foundaddr; + start = (start + PGDIR_SIZE) & PGDIR_MASK; + pgdir++; + } while (start && (start < end)); + return 0; +} + +static int unuse_process(struct mm_struct * mm, + swp_entry_t entry, struct page* page) +{ + struct vm_area_struct* vma; + unsigned long foundaddr = 0; + + /* + * Go through process' page directory. + */ + if (!down_read_trylock(&mm->mmap_sem)) { + /* + * Our reference to the page stops try_to_unmap_one from + * unmapping its ptes, so swapoff can make progress. + */ + unlock_page(page); + down_read(&mm->mmap_sem); + lock_page(page); + } + spin_lock(&mm->page_table_lock); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma->anon_vma) { + foundaddr = unuse_vma(vma, entry, page); + if (foundaddr) + break; + } + } +#ifdef CONFIG_XEN_BATCH_MODE2 + XEN_flush_page_update_queue(); +#endif + spin_unlock(&mm->page_table_lock); + up_read(&mm->mmap_sem); + /* + * Currently unuse_process cannot fail, but leave error handling + * at call sites for now, since we change it from time to time. + */ + return 0; +} + +/* + * 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; + int shmem; + + /* + * 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, which clusters forked mms + * together, child after parent. If we race with dup_mmap(), we + * prefer to resolve parent before child, lest we miss entries + * duplicated after we scanned child: using last mm would invert + * that. Though it's only a serious concern when an overflowed + * swap count is reset from SWAP_MAP_MAX, preventing a rescan. + */ + 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: + * there are races when an instance of an entry might be missed. + */ + while ((i = find_next_to_unuse(si, i)) != 0) { + if (signal_pending(current)) { + retval = -EINTR; + break; + } + + /* + * 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, NULL, 0); + 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_locked" 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_locked(page); + wait_on_page_writeback(page); + lock_page(page); + wait_on_page_writeback(page); + + /* + * Remove all references to entry. + * Whenever we reach init_mm, there's no address space + * to search, but use it as a reminder to search shmem. + */ + shmem = 0; + swcount = *swap_map; + if (swcount > 1) { + if (start_mm == &init_mm) + shmem = shmem_unuse(entry, page); + else + retval = 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 *prev_mm = start_mm; + struct mm_struct *mm; + + atomic_inc(&new_start_mm->mm_users); + atomic_inc(&prev_mm->mm_users); + spin_lock(&mmlist_lock); + while (*swap_map > 1 && !retval && + (p = p->next) != &start_mm->mmlist) { + mm = list_entry(p, struct mm_struct, mmlist); + if (atomic_inc_return(&mm->mm_users) == 1) { + atomic_dec(&mm->mm_users); + continue; + } + spin_unlock(&mmlist_lock); + mmput(prev_mm); + prev_mm = mm; + + cond_resched(); + + swcount = *swap_map; + if (swcount <= 1) + ; + else if (mm == &init_mm) { + set_start_mm = 1; + shmem = shmem_unuse(entry, page); + } else + retval = unuse_process(mm, entry, page); + if (set_start_mm && *swap_map < swcount) { + mmput(new_start_mm); + atomic_inc(&mm->mm_users); + new_start_mm = mm; + set_start_mm = 0; + } + spin_lock(&mmlist_lock); + } + spin_unlock(&mmlist_lock); + mmput(prev_mm); + mmput(start_mm); + start_mm = new_start_mm; + } + if (retval) { + unlock_page(page); + page_cache_release(page); + break; + } + + /* + * 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_device_lock(si); + *swap_map = 1; + swap_device_unlock(si); + reset_overflow = 1; + } + + /* + * If a reference remains (rare), we would like to leave + * the page in the swap cache; but try_to_unmap 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 a swappage from + * the swap cache, unless the move to filepage failed: + * in which case it left swappage in cache, lowered its + * swap count to pass quickly through the loops above, + * and now we must reincrement count to try again later. + */ + if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + }; + + swap_writepage(page, &wbc); + lock_page(page); + wait_on_page_writeback(page); + } + if (PageSwapCache(page)) { + if (shmem) + swap_duplicate(entry); + else + 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 shrink_list will preserve it. + */ + SetPageDirty(page); + unlock_page(page); + page_cache_release(page); + + /* + * Make sure that we aren't completely killing + * interactive performance. + */ + cond_resched(); + } + + mmput(start_mm); + if (reset_overflow) { + printk(KERN_WARNING "swapoff: cleared swap entry overflow\n"); + swap_overflow = 0; + } + return retval; +} + +/* + * After a successful try_to_unuse, if no swap is now in use, we know we + * can empty the mmlist. swap_list_lock must be held on entry and exit. + * Note that mmlist_lock nests inside swap_list_lock, and an mm must be + * added to the mmlist just after page_duplicate - before would be racy. + */ +static void drain_mmlist(void) +{ + struct list_head *p, *next; + unsigned int i; + + for (i = 0; i < nr_swapfiles; i++) + if (swap_info[i].inuse_pages) + return; + spin_lock(&mmlist_lock); + list_for_each_safe(p, next, &init_mm.mmlist) + list_del_init(p); + spin_unlock(&mmlist_lock); +} + +/* + * Use this swapdev's extent info to locate the (PAGE_SIZE) block which + * corresponds to page offset `offset'. + */ +sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) +{ + struct swap_extent *se = sis->curr_swap_extent; + struct swap_extent *start_se = se; + + for ( ; ; ) { + struct list_head *lh; + + if (se->start_page <= offset && + offset < (se->start_page + se->nr_pages)) { + return se->start_block + (offset - se->start_page); + } + lh = se->list.prev; + if (lh == &sis->extent_list) + lh = lh->prev; + se = list_entry(lh, struct swap_extent, list); + sis->curr_swap_extent = se; + BUG_ON(se == start_se); /* It *must* be present */ + } +} + +/* + * Free all of a swapdev's extent information + */ +static void destroy_swap_extents(struct swap_info_struct *sis) +{ + while (!list_empty(&sis->extent_list)) { + struct swap_extent *se; + + se = list_entry(sis->extent_list.next, + struct swap_extent, list); + list_del(&se->list); + kfree(se); + } + sis->nr_extents = 0; +} + +/* + * Add a block range (and the corresponding page range) into this swapdev's + * extent list. The extent list is kept sorted in block order. + * + * This function rather assumes that it is called in ascending sector_t order. + * It doesn't look for extent coalescing opportunities. + */ +static int +add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, + unsigned long nr_pages, sector_t start_block) +{ + struct swap_extent *se; + struct swap_extent *new_se; + struct list_head *lh; + + lh = sis->extent_list.next; /* The highest-addressed block */ + while (lh != &sis->extent_list) { + se = list_entry(lh, struct swap_extent, list); + if (se->start_block + se->nr_pages == start_block && + se->start_page + se->nr_pages == start_page) { + /* Merge it */ + se->nr_pages += nr_pages; + return 0; + } + lh = lh->next; + } + + /* + * No merge. Insert a new extent, preserving ordering. + */ + new_se = kmalloc(sizeof(*se), GFP_KERNEL); + if (new_se == NULL) + return -ENOMEM; + new_se->start_page = start_page; + new_se->nr_pages = nr_pages; + new_se->start_block = start_block; + + lh = sis->extent_list.prev; /* The lowest block */ + while (lh != &sis->extent_list) { + se = list_entry(lh, struct swap_extent, list); + if (se->start_block > start_block) + break; + lh = lh->prev; + } + list_add_tail(&new_se->list, lh); + sis->nr_extents++; + return 0; +} + +/* + * A `swap extent' is a simple thing which maps a contiguous range of pages + * onto a contiguous range of disk blocks. An ordered list of swap extents + * is built at swapon time and is then used at swap_writepage/swap_readpage + * time for locating where on disk a page belongs. + * + * If the swapfile is an S_ISBLK block device, a single extent is installed. + * This is done so that the main operating code can treat S_ISBLK and S_ISREG + * swap files identically. + * + * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap + * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK + * swapfiles are handled *identically* after swapon time. + * + * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks + * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If + * some stray blocks are found which do not fall within the PAGE_SIZE alignment + * requirements, they are simply tossed out - we will never use those blocks + * for swapping. + * + * For S_ISREG swapfiles we hold i_sem across the life of the swapon. This + * prevents root from shooting her foot off by ftruncating an in-use swapfile, + * which will scribble on the fs. + * + * The amount of disk space which a single swap extent represents varies. + * Typically it is in the 1-4 megabyte range. So we can have hundreds of + * extents in the list. To avoid much list walking, we cache the previous + * search location in `curr_swap_extent', and start new searches from there. + * This is extremely effective. The average number of iterations in + * map_swap_page() has been measured at about 0.3 per page. - akpm. + */ +static int setup_swap_extents(struct swap_info_struct *sis) +{ + struct inode *inode; + unsigned blocks_per_page; + unsigned long page_no; + unsigned blkbits; + sector_t probe_block; + sector_t last_block; + int ret; + + inode = sis->swap_file->f_mapping->host; + if (S_ISBLK(inode->i_mode)) { + ret = add_swap_extent(sis, 0, sis->max, 0); + goto done; + } + + blkbits = inode->i_blkbits; + blocks_per_page = PAGE_SIZE >> blkbits; + + /* + * Map all the blocks into the extent list. This code doesn't try + * to be very smart. + */ + probe_block = 0; + page_no = 0; + last_block = i_size_read(inode) >> blkbits; + while ((probe_block + blocks_per_page) <= last_block && + page_no < sis->max) { + unsigned block_in_page; + sector_t first_block; + + first_block = bmap(inode, probe_block); + if (first_block == 0) + goto bad_bmap; + + /* + * It must be PAGE_SIZE aligned on-disk + */ + if (first_block & (blocks_per_page - 1)) { + probe_block++; + goto reprobe; + } + + for (block_in_page = 1; block_in_page < blocks_per_page; + block_in_page++) { + sector_t block; + + block = bmap(inode, probe_block + block_in_page); + if (block == 0) + goto bad_bmap; + if (block != first_block + block_in_page) { + /* Discontiguity */ + probe_block++; + goto reprobe; + } + } + + /* + * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks + */ + ret = add_swap_extent(sis, page_no, 1, + first_block >> (PAGE_SHIFT - blkbits)); + if (ret) + goto out; + page_no++; + probe_block += blocks_per_page; +reprobe: + continue; + } + ret = 0; + if (page_no == 0) + ret = -EINVAL; + sis->max = page_no; + sis->highest_bit = page_no - 1; +done: + sis->curr_swap_extent = list_entry(sis->extent_list.prev, + struct swap_extent, list); + goto out; +bad_bmap: + printk(KERN_ERR "swapon: swapfile has holes\n"); + ret = -EINVAL; +out: + return ret; +} + +#if 0 /* We don't need this yet */ +#include +int page_queue_congested(struct page *page) +{ + struct backing_dev_info *bdi; + + BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */ + + if (PageSwapCache(page)) { + swp_entry_t entry = { .val = page->private }; + struct swap_info_struct *sis; + + sis = get_swap_info_struct(swp_type(entry)); + bdi = sis->bdev->bd_inode->i_mapping->backing_dev_info; + } else + bdi = page->mapping->backing_dev_info; + return bdi_write_congested(bdi); +} +#endif + +asmlinkage long sys_swapoff(const char __user * specialfile) +{ + struct swap_info_struct * p = NULL; + unsigned short *swap_map; + struct file *swap_file, *victim; + struct address_space *mapping; + struct inode *inode; + char * pathname; + int i, type, prev; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + pathname = getname(specialfile); + err = PTR_ERR(pathname); + if (IS_ERR(pathname)) + goto out; + + victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0); + putname(pathname); + err = PTR_ERR(victim); + if (IS_ERR(victim)) + goto out; + + mapping = victim->f_mapping; + 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_ACTIVE) == SWP_ACTIVE) { + if (p->swap_file->f_mapping == mapping) + break; + } + prev = type; + } + if (type < 0) { + err = -EINVAL; + swap_list_unlock(); + goto out_dput; + } + if (!security_vm_enough_memory(p->pages)) + vm_unacct_memory(p->pages); + else { + err = -ENOMEM; + 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_WRITEOK; + swap_list_unlock(); + current->flags |= PF_SWAPOFF; + err = try_to_unuse(type); + current->flags &= ~PF_SWAPOFF; + + /* wait for any unplug function to finish */ + down_write(&swap_unplug_sem); + up_write(&swap_unplug_sem); + + 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; + } + down(&swapon_sem); + swap_list_lock(); + drain_mmlist(); + swap_device_lock(p); + swap_file = p->swap_file; + p->swap_file = NULL; + p->max = 0; + swap_map = p->swap_map; + p->swap_map = NULL; + p->flags = 0; + destroy_swap_extents(p); + swap_device_unlock(p); + swap_list_unlock(); + up(&swapon_sem); + vfree(swap_map); + inode = mapping->host; + if (S_ISBLK(inode->i_mode)) { + struct block_device *bdev = I_BDEV(inode); + set_blocksize(bdev, p->old_block_size); + bd_release(bdev); + } else { + down(&inode->i_sem); + inode->i_flags &= ~S_SWAPFILE; + up(&inode->i_sem); + } + filp_close(swap_file, NULL); + err = 0; + +out_dput: + filp_close(victim, NULL); +out: + return err; +} + +#ifdef CONFIG_PROC_FS +/* iterator */ +static void *swap_start(struct seq_file *swap, loff_t *pos) +{ + struct swap_info_struct *ptr = swap_info; + int i; + loff_t l = *pos; + + down(&swapon_sem); + + for (i = 0; i < nr_swapfiles; i++, ptr++) { + if (!(ptr->flags & SWP_USED) || !ptr->swap_map) + continue; + if (!l--) + return ptr; + } + + return NULL; +} + +static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) +{ + struct swap_info_struct *ptr = v; + struct swap_info_struct *endptr = swap_info + nr_swapfiles; + + for (++ptr; ptr < endptr; ptr++) { + if (!(ptr->flags & SWP_USED) || !ptr->swap_map) + continue; + ++*pos; + return ptr; + } + + return NULL; +} + +static void swap_stop(struct seq_file *swap, void *v) +{ + up(&swapon_sem); +} + +static int swap_show(struct seq_file *swap, void *v) +{ + struct swap_info_struct *ptr = v; + struct file *file; + int len; + + if (v == swap_info) + seq_puts(swap, "Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + + file = ptr->swap_file; + len = seq_path(swap, file->f_vfsmnt, file->f_dentry, " \t\n\\"); + seq_printf(swap, "%*s%s\t%d\t%ld\t%d\n", + len < 40 ? 40 - len : 1, " ", + S_ISBLK(file->f_dentry->d_inode->i_mode) ? + "partition" : "file\t", + ptr->pages << (PAGE_SHIFT - 10), + ptr->inuse_pages << (PAGE_SHIFT - 10), + ptr->prio); + return 0; +} + +static struct seq_operations swaps_op = { + .start = swap_start, + .next = swap_next, + .stop = swap_stop, + .show = swap_show +}; + +static int swaps_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &swaps_op); +} + +static struct file_operations proc_swaps_operations = { + .open = swaps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init procswaps_init(void) +{ + struct proc_dir_entry *entry; + + entry = create_proc_entry("swaps", 0, NULL); + if (entry) + entry->proc_fops = &proc_swaps_operations; + return 0; +} +__initcall(procswaps_init); +#endif /* CONFIG_PROC_FS */ + +/* + * Written 01/25/92 by Simmule Turner, heavily changed by Linus. + * + * The swapon system call + */ +asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) +{ + struct swap_info_struct * p; + char *name = NULL; + struct block_device *bdev = NULL; + struct file *swap_file = NULL; + struct address_space *mapping; + unsigned int type; + int i, prev; + int error; + static int least_priority; + union swap_header *swap_header = NULL; + int swap_header_version; + int nr_good_pages = 0; + unsigned long maxpages = 1; + int swapfilesize; + unsigned short *swap_map; + struct page *page = NULL; + struct inode *inode = NULL; + int did_down = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + swap_list_lock(); + p = swap_info; + for (type = 0 ; type < nr_swapfiles ; type++,p++) + if (!(p->flags & SWP_USED)) + break; + error = -EPERM; + /* + * Test if adding another swap device is possible. There are + * two limiting factors: 1) the number of bits for the swap + * type swp_entry_t definition and 2) the number of bits for + * the swap type in the swap ptes as defined by the different + * architectures. To honor both limitations a swap entry + * with swap offset 0 and swap type ~0UL is created, encoded + * to a swap pte, decoded to a swp_entry_t again and finally + * the swap type part is extracted. This will mask all bits + * from the initial ~0UL that can't be encoded in either the + * swp_entry_t or the architecture definition of a swap pte. + */ + if (type > swp_type(pte_to_swp_entry(swp_entry_to_pte(swp_entry(~0UL,0))))) { + swap_list_unlock(); + goto out; + } + if (type >= nr_swapfiles) + nr_swapfiles = type+1; + INIT_LIST_HEAD(&p->extent_list); + p->flags = SWP_USED; + p->nr_extents = 0; + p->swap_file = NULL; + p->old_block_size = 0; + p->swap_map = NULL; + p->lowest_bit = 0; + p->highest_bit = 0; + p->cluster_nr = 0; + p->inuse_pages = 0; + spin_lock_init(&p->sdev_lock); + 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(); + name = getname(specialfile); + error = PTR_ERR(name); + if (IS_ERR(name)) { + name = NULL; + goto bad_swap_2; + } + swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0); + error = PTR_ERR(swap_file); + if (IS_ERR(swap_file)) { + swap_file = NULL; + goto bad_swap_2; + } + + p->swap_file = swap_file; + mapping = swap_file->f_mapping; + inode = mapping->host; + + 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 (mapping == q->swap_file->f_mapping) + goto bad_swap; + } + + error = -EINVAL; + if (S_ISBLK(inode->i_mode)) { + bdev = I_BDEV(inode); + error = bd_claim(bdev, sys_swapon); + if (error < 0) { + bdev = NULL; + goto bad_swap; + } + p->old_block_size = block_size(bdev); + error = set_blocksize(bdev, PAGE_SIZE); + if (error < 0) + goto bad_swap; + p->bdev = bdev; + } else if (S_ISREG(inode->i_mode)) { + p->bdev = inode->i_sb->s_bdev; + down(&inode->i_sem); + did_down = 1; + if (IS_SWAPFILE(inode)) { + error = -EBUSY; + goto bad_swap; + } + } else { + goto bad_swap; + } + + swapfilesize = i_size_read(inode) >> PAGE_SHIFT; + + /* + * Read the swap header. + */ + if (!mapping->a_ops->readpage) { + error = -EINVAL; + goto bad_swap; + } + page = read_cache_page(mapping, 0, + (filler_t *)mapping->a_ops->readpage, swap_file); + if (IS_ERR(page)) { + error = PTR_ERR(page); + goto bad_swap; + } + wait_on_page_locked(page); + if (!PageUptodate(page)) + goto bad_swap; + kmap(page); + swap_header = page_address(page); + + 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: + printk(KERN_ERR "version 0 swap is no longer supported. " + "Use mkswap -v1 %s\n", name); + error = -EINVAL; + goto bad_swap; + 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; + /* + * Find out how many pages are allowed for a single swap + * device. There are two limiting factors: 1) the number of + * bits for the swap offset in the swp_entry_t type and + * 2) the number of bits in the a swap pte as defined by + * the different architectures. In order to find the + * largest possible bit mask a swap entry with swap type 0 + * and swap offset ~0UL is created, encoded to a swap pte, + * decoded to a swp_entry_t again and finally the swap + * offset is extracted. This will mask all the bits from + * the initial ~0UL mask that can't be encoded in either + * the swp_entry_t or the architecture definition of a + * swap pte. + */ + maxpages = swp_offset(pte_to_swp_entry(swp_entry_to_pte(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; iinfo.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; + p->max = maxpages; + p->pages = nr_good_pages; + + error = setup_swap_extents(p); + if (error) + goto bad_swap; + + down(&swapon_sem); + swap_list_lock(); + swap_device_lock(p); + p->flags = SWP_ACTIVE; + nr_swap_pages += nr_good_pages; + total_swap_pages += nr_good_pages; + printk(KERN_INFO "Adding %dk swap on %s. Priority:%d extents:%d\n", + nr_good_pages<<(PAGE_SHIFT-10), name, + p->prio, p->nr_extents); + + /* 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(); + up(&swapon_sem); + error = 0; + goto out; +bad_swap: + if (bdev) { + set_blocksize(bdev, p->old_block_size); + bd_release(bdev); + } +bad_swap_2: + swap_list_lock(); + swap_map = p->swap_map; + p->swap_file = NULL; + p->swap_map = NULL; + p->flags = 0; + if (!(swap_flags & SWAP_FLAG_PREFER)) + ++least_priority; + swap_list_unlock(); + destroy_swap_extents(p); + if (swap_map) + vfree(swap_map); + if (swap_file) + filp_close(swap_file, NULL); +out: + if (page && !IS_ERR(page)) { + kunmap(page); + page_cache_release(page); + } + if (name) + putname(name); + if (did_down) { + if (!error) + inode->i_flags |= S_SWAPFILE; + up(&inode->i_sem); + } + 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++) { + if (!(swap_info[i].flags & SWP_USED) || + (swap_info[i].flags & SWP_WRITEOK)) + continue; + nr_to_be_unused += swap_info[i].inuse_pages; + } + 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; +} + +struct swap_info_struct * +get_swap_info_struct(unsigned type) +{ + return &swap_info[type]; +} + +/* + * 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; +} -- 2.30.2