x86/svm: Write the correct %eip into the outgoing task

The TASK_SWITCH vmexit has fault semantics, and doesn't provide any NRIPs
assistance with instruction length.  As a result, any instruction-induced task
switch has the outgoing task's %eip pointing at the instruction switch caused
the switch, rather than after it.

This causes callers of task gates to livelock (repeatedly execute the call/jmp
to enter the task), and any restartable task to become a nop after its first
use (the (re)entry state points at the iret used to exit the task).

32bit Windows in particular is known to use task gates for NMI handling, and
to use NMI IPIs.

In the task switch handler, distinguish instruction-induced from
interrupt/exception-induced task switches, and decode the instruction under
%rip to calculate its length.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: 1d758bc6d1a8c0f658a874470c349ee4e27aee46
master date: 2019-11-28 17:14:38 +0000

diff --git a/xen/arch/x86/hvm/svm/emulate.c b/xen/arch/x86/hvm/svm/emulate.c
index 0897944760816f7873483a9545cea7145d84e41b..3f9ddaedd9a799042c22e21e28bfe763df32e5f7 100644 (file)
--- a/xen/arch/x86/hvm/svm/emulate.c
+++ b/xen/arch/x86/hvm/svm/emulate.c
@@ -159,6 +159,60 @@ int __get_instruction_length_from_list(struct vcpu *v,
     return 0;
 }
 
+/*
+ * TASK_SWITCH vmexits never provide an instruction length.  We must always
+ * decode under %rip to find the answer.
+ */
+unsigned int svm_get_task_switch_insn_len(void)
+{
+    struct hvm_emulate_ctxt ctxt;
+    struct x86_emulate_state *state;
+    unsigned int emul_len, modrm_reg;
+
+    hvm_emulate_init_once(&ctxt, NULL, guest_cpu_user_regs());
+    hvm_emulate_init_per_insn(&ctxt, NULL, 0);
+    state = x86_decode_insn(&ctxt.ctxt, hvmemul_insn_fetch);
+    if ( IS_ERR_OR_NULL(state) )
+        return 0;
+
+    emul_len = x86_insn_length(state, &ctxt.ctxt);
+
+    /*
+     * Check for an instruction which can cause a task switch.  Any far
+     * jmp/call/ret, any software interrupt/exception with trap semantics
+     * (except icebp - handled specially), and iret.
+     */
+    switch ( ctxt.ctxt.opcode )
+    {
+    case 0xff: /* Grp 5 */
+        /* call / jmp (far, absolute indirect) */
+        if ( (unsigned int)x86_insn_modrm(state, NULL, &modrm_reg) >= 3 ||
+             (modrm_reg != 3 && modrm_reg != 5) )
+        {
+    default:
+            printk(XENLOG_G_WARNING "Bad instruction for task switch\n");
+            hvm_dump_emulation_state(XENLOG_G_WARNING, "SVM Insn len",
+                                     &ctxt, X86EMUL_UNHANDLEABLE);
+            emul_len = 0;
+            break;
+        }
+        /* Fallthrough */
+    case 0x9a: /* call (far, absolute) */
+    case 0xca: /* ret imm16 (far) */
+    case 0xcb: /* ret (far) */
+    case 0xcc: /* int3 */
+    case 0xcd: /* int imm8 */
+    case 0xce: /* into */
+    case 0xcf: /* iret */
+    case 0xea: /* jmp (far, absolute) */
+        break;
+    }
+
+    x86_emulate_free_state(state);
+
+    return emul_len;
+}
+
 /*
  * Local variables:
  * mode: C

diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index fad2a7bba23915cc1b5d0707db3883c6e939abc7..2f8aed8cb97962166caa3de2ff4796c5f54c2369 100644 (file)
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -2902,7 +2902,52 @@ void svm_vmexit_handler(struct cpu_user_regs *regs)
 
     case VMEXIT_TASK_SWITCH: {
         enum hvm_task_switch_reason reason;
-        int32_t errcode = -1;
+        int32_t errcode = -1, insn_len = -1;
+
+        /*
+         * All TASK_SWITCH intercepts have fault-like semantics.  NRIP is
+         * never provided, even for instruction-induced task switches, but we
+         * need to know the instruction length in order to set %eip suitably
+         * in the outgoing TSS.
+         *
+         * For a task switch which vectored through the IDT, look at the type
+         * to distinguish interrupts/exceptions from instruction based
+         * switches.
+         */
+        if ( vmcb->exitintinfo.fields.v )
+        {
+            switch ( vmcb->exitintinfo.fields.type )
+            {
+                /*
+                 * #BP and #OF are from INT3/INTO respectively.  #DB from
+                 * ICEBP is handled specially, and already has fault
+                 * semantics.
+                 */
+            case X86_EVENTTYPE_HW_EXCEPTION:
+                if ( vmcb->exitintinfo.fields.vector == TRAP_int3 ||
+                     vmcb->exitintinfo.fields.vector == TRAP_overflow )
+                    break;
+                /* Fallthrough */
+            case X86_EVENTTYPE_EXT_INTR:
+            case X86_EVENTTYPE_NMI:
+                insn_len = 0;
+                break;
+            }
+
+            /*
+             * The common logic above will have forwarded the vectoring
+             * information.  Undo this as we are going to emulate.
+             */
+            vmcb->eventinj.bytes = 0;
+        }
+
+        /*
+         * insn_len being -1 indicates that we have an instruction-induced
+         * task switch.  Decode under %rip to find its length.
+         */
+        if ( insn_len < 0 && (insn_len = svm_get_task_switch_insn_len()) == 0 )
+            goto crash_or_fault;
+
         if ( (vmcb->exitinfo2 >> 36) & 1 )
             reason = TSW_iret;
         else if ( (vmcb->exitinfo2 >> 38) & 1 )
@@ -2912,15 +2957,7 @@ void svm_vmexit_handler(struct cpu_user_regs *regs)
         if ( (vmcb->exitinfo2 >> 44) & 1 )
             errcode = (uint32_t)vmcb->exitinfo2;
 
-        /*
-         * Some processors set the EXITINTINFO field when the task switch
-         * is caused by a task gate in the IDT. In this case we will be
-         * emulating the event injection, so we do not want the processor
-         * to re-inject the original event!
-         */
-        vmcb->eventinj.bytes = 0;
-
-        hvm_task_switch(vmcb->exitinfo1, reason, errcode, 0);
+        hvm_task_switch(vmcb->exitinfo1, reason, errcode, insn_len);
         break;
     }
 
@@ -3117,6 +3154,7 @@ void svm_vmexit_handler(struct cpu_user_regs *regs)
         gprintk(XENLOG_ERR, "Unexpected vmexit: reason %#"PRIx64", "
                 "exitinfo1 %#"PRIx64", exitinfo2 %#"PRIx64"\n",
                 exit_reason, vmcb->exitinfo1, vmcb->exitinfo2);
+    crash_or_fault:
         svm_crash_or_fault(v);
         break;
     }

diff --git a/xen/include/asm-x86/hvm/svm/emulate.h b/xen/include/asm-x86/hvm/svm/emulate.h
index ca92abbe28c5c69bb9edd3cf2b60c0b54ba1b83d..df94e5fc5641882e2ff8ea39e3130a565fee3e57 100644 (file)
--- a/xen/include/asm-x86/hvm/svm/emulate.h
+++ b/xen/include/asm-x86/hvm/svm/emulate.h
@@ -54,6 +54,8 @@ static inline int __get_instruction_length(
     return __get_instruction_length_from_list(v, &instr, 1);
 }
 
+unsigned int svm_get_task_switch_insn_len(void);
+
 #endif /* __ASM_X86_HVM_SVM_EMULATE_H__ */
 
 /*