[v2,1/3] x86/vtx: Fix fault semantics for early task switch failures
diff mbox series

Message ID 20191126120357.13398-2-andrew.cooper3@citrix.com
State New
Headers show
Series
  • x86/hvm: Multiple corrections to task switch handling
Related show

Commit Message

Andrew Cooper Nov. 26, 2019, 12:03 p.m. UTC
The VT-x task switch handler adds inst_len to %rip before calling
hvm_task_switch(), which is problematic in two ways:

 1) Early faults (i.e. ones delivered in the context of the old task) get
    delivered with trap semantics, and break restartibility.

 2) The addition isn't truncated to 32 bits.  In the corner case of a task
    switch instruction crossing the 4G->0 boundary taking an early fault (with
    trap semantics), a VMEntry failure will occur due to %rip being out of
    range.

Instead, pass the instruction length into hvm_task_switch() and write it into
the outgoing TSS only, leaving %rip in its original location.

For now, pass 0 on the SVM side.  This highlights a separate preexisting bug
which will be addressed in the following patch.

While adjusting call sites, drop the unnecessary uint16_t cast.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
---
 xen/arch/x86/hvm/hvm.c        | 4 ++--
 xen/arch/x86/hvm/svm/svm.c    | 2 +-
 xen/arch/x86/hvm/vmx/vmx.c    | 4 ++--
 xen/include/asm-x86/hvm/hvm.h | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

Patch
diff mbox series

diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 818e705fd1..7f556171bd 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -2913,7 +2913,7 @@  void hvm_prepare_vm86_tss(struct vcpu *v, uint32_t base, uint32_t limit)
 
 void hvm_task_switch(
     uint16_t tss_sel, enum hvm_task_switch_reason taskswitch_reason,
-    int32_t errcode)
+    int32_t errcode, unsigned int insn_len)
 {
     struct vcpu *v = current;
     struct cpu_user_regs *regs = guest_cpu_user_regs();
@@ -2987,7 +2987,7 @@  void hvm_task_switch(
     if ( taskswitch_reason == TSW_iret )
         eflags &= ~X86_EFLAGS_NT;
 
-    tss.eip    = regs->eip;
+    tss.eip    = regs->eip + insn_len;
     tss.eflags = eflags;
     tss.eax    = regs->eax;
     tss.ecx    = regs->ecx;
diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index 4eb6b0e4c7..049b800e20 100644
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -2794,7 +2794,7 @@  void svm_vmexit_handler(struct cpu_user_regs *regs)
          */
         vmcb->eventinj.bytes = 0;
 
-        hvm_task_switch((uint16_t)vmcb->exitinfo1, reason, errcode);
+        hvm_task_switch(vmcb->exitinfo1, reason, errcode, 0);
         break;
     }
 
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index a71df71bc1..7450cbe40d 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -3962,8 +3962,8 @@  void vmx_vmexit_handler(struct cpu_user_regs *regs)
             __vmread(IDT_VECTORING_ERROR_CODE, &ecode);
         else
              ecode = -1;
-        regs->rip += inst_len;
-        hvm_task_switch((uint16_t)exit_qualification, reasons[source], ecode);
+
+        hvm_task_switch(exit_qualification, reasons[source], ecode, inst_len);
         break;
     }
     case EXIT_REASON_CPUID:
diff --git a/xen/include/asm-x86/hvm/hvm.h b/xen/include/asm-x86/hvm/hvm.h
index f86af09898..4cce59bb31 100644
--- a/xen/include/asm-x86/hvm/hvm.h
+++ b/xen/include/asm-x86/hvm/hvm.h
@@ -297,7 +297,7 @@  void hvm_set_rdtsc_exiting(struct domain *d, bool_t enable);
 enum hvm_task_switch_reason { TSW_jmp, TSW_iret, TSW_call_or_int };
 void hvm_task_switch(
     uint16_t tss_sel, enum hvm_task_switch_reason taskswitch_reason,
-    int32_t errcode);
+    int32_t errcode, unsigned int insn_len);
 
 enum hvm_access_type {
     hvm_access_insn_fetch,