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 each 1024 iterations 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 | 34 +++++++++++++++++++++++-----------
arch/x86/kvm/x86.c | 19 ++++++++++++++++++-
3 files changed, 42 insertions(+), 12 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 541f3c9..c4da60e 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);
@@ -2422,6 +2425,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
u64 msr_data;
struct decode_cache *c = &ctxt->decode;
int rc = X86EMUL_CONTINUE;
+ int saved_dst_type = c->dst.type;
ctxt->interruptibility = 0;
@@ -2450,8 +2454,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
}
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;
}
@@ -2463,17 +2470,13 @@ 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;
}
@@ -2906,6 +2909,12 @@ writeback:
if (rc != X86EMUL_CONTINUE)
goto done;
+ /*
+ * restore dst type in case the decoding will be reused
+ * (happens for string instruction )
+ */
+ c->dst.type = saved_dst_type;
+
if ((c->d & SrcMask) == SrcSI)
string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI,
&c->src);
@@ -2913,8 +2922,11 @@ writeback:
if ((c->d & DstMask) == DstDI)
string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
- if (c->rep_prefix && (c->d & String))
+ if (c->rep_prefix && (c->d & String)) {
register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
+ if (!(c->regs[VCPU_REGS_RCX] & 0x3ff))
+ ctxt->restart = false;
+ }
/* Commit shadow register state. */
memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b8237ac..cd0043a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3718,6 +3718,7 @@ 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;
@@ -3740,7 +3741,7 @@ 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;
@@ -3755,6 +3756,13 @@ 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);
@@ -4523,6 +4531,15 @@ 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
