Currently when string instruction is only partially complete we go back
to a guest mode, guest tries to reexecute instruction and exits again
and at this point emulation continues. Avoid all of this by restarting
instruction without going back to a guest mode, but return to a guest
mode on each page boundary to allow interrupt injection. Pending
exception causes immediate guest entry too.
Signed-off-by: Gleb Natapov <gleb@xxxxxxxxxx>
---
arch/x86/include/asm/kvm_emulate.h | 1 +
arch/x86/kvm/emulate.c | 26 ++++++++++++++++----------
arch/x86/kvm/x86.c | 19 ++++++++++++++++++-
3 files changed, 35 insertions(+), 11 deletions(-)
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 679245c..7fda16f 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -193,6 +193,7 @@ struct x86_emulate_ctxt {
/* interruptibility state, as a result of execution of STI or MOV SS */
int interruptibility;
+ bool restart; /* restart string instruction after writeback */
/* decode cache */
struct decode_cache decode;
};
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9d8c7b6..5687b06 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -927,8 +927,11 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
int mode = ctxt->mode;
int def_op_bytes, def_ad_bytes, group;
- /* Shadow copy of register state. Committed on successful emulation. */
+ /* we cannot decode insn before we complete previous rep insn */
+ WARN_ON(ctxt->restart);
+
+ /* Shadow copy of register state. Committed on successful emulation. */
memset(c, 0, sizeof(struct decode_cache));
c->eip = ctxt->eip;
ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
@@ -2445,8 +2448,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
memop = c->modrm_ea;
if (c->rep_prefix && (c->d & String)) {
+ ctxt->restart = true;
/* All REP prefixes have the same first termination condition */
if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
+ string_done:
+ ctxt->restart = false;
kvm_rip_write(ctxt->vcpu, c->eip);
goto done;
}
@@ -2458,17 +2464,13 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
* - if REPNE/REPNZ and ZF = 1 then done
*/
if ((c->b == 0xa6) || (c->b == 0xa7) ||
- (c->b == 0xae) || (c->b == 0xaf)) {
+ (c->b == 0xae) || (c->b == 0xaf)) {
if ((c->rep_prefix == REPE_PREFIX) &&
- ((ctxt->eflags & EFLG_ZF) == 0)) {
- kvm_rip_write(ctxt->vcpu, c->eip);
- goto done;
- }
+ ((ctxt->eflags & EFLG_ZF) == 0))
+ goto string_done;
if ((c->rep_prefix == REPNE_PREFIX) &&
- ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) {
- kvm_rip_write(ctxt->vcpu, c->eip);
- goto done;
- }
+ ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))
+ goto string_done;
}
c->eip = ctxt->eip;
}
@@ -2904,6 +2906,8 @@ writeback:
c->src.ptr = (unsigned long *)
register_address(c, seg_override_base(ctxt, c),
c->regs[VCPU_REGS_RSI]);
+ if (!(c->regs[VCPU_REGS_RSI] & ~PAGE_MASK))
+ ctxt->restart = false;
}
if ((c->d & DstMask) == DstDI) {
@@ -2913,6 +2917,8 @@ writeback:
c->dst.ptr = (unsigned long *)
register_address(c, es_base(ctxt),
c->regs[VCPU_REGS_RDI]);
+ if (!(c->regs[VCPU_REGS_RDI] & ~PAGE_MASK))
+ ctxt->restart = false;
}
if (c->rep_prefix)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e38ba94..b158ef8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3702,6 +3702,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
return EMULATE_DONE;
}
+restart:
r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
@@ -3724,7 +3725,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
if (r) {
if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
- return EMULATE_DONE;
+ goto done;
if (!vcpu->mmio_needed) {
kvm_report_emulation_failure(vcpu, "mmio");
return EMULATE_FAIL;
@@ -3739,6 +3740,13 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
return EMULATE_DO_MMIO;
}
+done:
+ if (vcpu->arch.exception.pending)
+ vcpu->arch.emulate_ctxt.restart = false;
+
+ if (vcpu->arch.emulate_ctxt.restart)
+ goto restart;
+
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(emulate_instruction);
@@ -4507,6 +4515,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
goto out;
}
}
+ if (vcpu->arch.emulate_ctxt.restart) {
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+ if (r == EMULATE_DO_MMIO) {
+ r = 0;
+ goto out;
+ }
+ }
if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
kvm_register_write(vcpu, VCPU_REGS_RAX,
kvm_run->hypercall.ret);
--
1.6.5
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
