Skip to contentSkip to conversation

KVM: emulate: Don't inject #GP when emulating RDMPC if CR0.PE=0

PATCH Applied Wanpeng Li 3 participants 13 messages Oct 19, 2021 – Oct 20, 2021

Subsystems (3)

v3 of 5 Applied Latest is v5 →

lore
Share & tools
lore

Wanpeng Li

author
#0 lore raw

PATCH v3 1/3 KVM: emulate: Don't inject #GP when emulating RDMPC if CR0.PE=0

From: Wanpeng Li <[email protected]>

SDM mentioned that, RDPMC:

  IF (((CR4.PCE = 1) or (CPL = 0) or (CR0.PE = 0)) and (ECX indicates a supported counter))
      THEN
          EAX := counter[31:0];
          EDX := ZeroExtend(counter[MSCB:32]);
      ELSE (* ECX is not valid or CR4.PCE is 0 and CPL is 1, 2, or 3 and CR0.PE is 1 *)
          #GP(0);
  FI;

Let's add the CR0.PE is 1 checking to rdpmc emulate, though this isn't strictly necessary since it's impossible for CPL to be >0 if CR0.PE=0.

---
v2 -> v3:
* add the missing 'S'
v1 -> v2:
* update patch description

 arch/x86/kvm/emulate.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/kvm/emulate.c +2 -1
index 9a144ca8e146..ab7ec569e8c9 100644
@@ -4213,6 +4213,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt)
 static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
 {
 	u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
+	u64 cr0 = ctxt->ops->get_cr(ctxt, 0);
 	u64 rcx = reg_read(ctxt, VCPU_REGS_RCX);
 
 	/*
@@ -4222,7 +4223,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
 	if (enable_vmware_backdoor && is_vmware_backdoor_pmc(rcx))
 		return X86EMUL_CONTINUE;
 
-	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
+	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt) && (cr0 & X86_CR0_PE)) ||
 	    ctxt->ops->check_pmc(ctxt, rcx))
 		return emulate_gp(ctxt, 0);
 
Signature · 1 line
2.25.1
author
#1 lore raw

PATCH v3 2/3 KVM: vPMU: Fill get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0

From: Wanpeng Li <[email protected]>

SDM section 18.2.3 mentioned that:

"IA32_PERF_GLOBAL_OVF_CTL MSR allows software to clear overflow indicator(s) of
any general-purpose or fixed-function counters via a single WRMSR."

It is R/W mentioned by SDM, we read this msr on bare-metal during perf testing, the value is always 0 for ICX/SKX boxes on hands. Let's fill get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0 as hardware behavior and drop global_ovf_ctrl variable.

---
Btw, xen also fills get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0. v1 -> v2:
* drop 'u64 global_ovf_ctrl' directly

 arch/x86/include/asm/kvm_host.h | 1 -
 arch/x86/kvm/vmx/pmu_intel.c    | 6 ++----
 2 files changed, 2 insertions(+), 5 deletions(-)
arch/x86/include/asm/kvm_host.h +0 -1
index f8f48a7ec577..7aaac918e992 100644
@@ -499,7 +499,6 @@ struct kvm_pmu {
 	u64 fixed_ctr_ctrl;
 	u64 global_ctrl;
 	u64 global_status;
-	u64 global_ovf_ctrl;
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
 	u64 global_ovf_ctrl_mask;
arch/x86/kvm/vmx/pmu_intel.c +2 -4
index 10cc4f65c4ef..b8e0d21b7c8a 100644
@@ -365,7 +365,7 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = pmu->global_ctrl;
 		return 0;
 	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		msr_info->data = pmu->global_ovf_ctrl;
+		msr_info->data = 0;
 		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
@@ -423,7 +423,6 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & pmu->global_ovf_ctrl_mask)) {
 			if (!msr_info->host_initiated)
 				pmu->global_status &= ~data;
-			pmu->global_ovf_ctrl = data;
 			return 0;
 		}
 		break;
@@ -588,8 +587,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 		pmc->counter = 0;
 	}
 
-	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
-		pmu->global_ovf_ctrl = 0;
+	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
 
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
Signature · 1 line
2.25.1
maintainer Applied
#2 lore raw

Re: [PATCH v3 2/3] KVM: vPMU: Fill get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0

Quoted 58 lines · Wanpeng Li

From: Wanpeng Li <[email protected]>

SDM section 18.2.3 mentioned that:

"IA32_PERF_GLOBAL_OVF_CTL MSR allows software to clear overflow indicator(s) of
any general-purpose or fixed-function counters via a single WRMSR."

It is R/W mentioned by SDM, we read this msr on bare-metal during perf testing, the value is always 0 for ICX/SKX boxes on hands. Let's fill get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0 as hardware behavior and drop global_ovf_ctrl variable.

---
Btw, xen also fills get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0. v1 -> v2:
* drop 'u64 global_ovf_ctrl' directly

  arch/x86/include/asm/kvm_host.h | 1 -
  arch/x86/kvm/vmx/pmu_intel.c    | 6 ++----
  2 files changed, 2 insertions(+), 5 deletions(-)
arch/x86/include/asm/kvm_host.h +0 -1
index f8f48a7ec577..7aaac918e992 100644
@@ -499,7 +499,6 @@ struct kvm_pmu {
  	u64 fixed_ctr_ctrl;
  	u64 global_ctrl;
  	u64 global_status;
-	u64 global_ovf_ctrl;
  	u64 counter_bitmask[2];
  	u64 global_ctrl_mask;
  	u64 global_ovf_ctrl_mask;
arch/x86/kvm/vmx/pmu_intel.c +1 -2
index 10cc4f65c4ef..b8e0d21b7c8a 100644
@@ -365,7 +365,7 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
  		msr_info->data = pmu->global_ctrl;
  		return 0;
  	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		msr_info->data = pmu->global_ovf_ctrl;
+		msr_info->data = 0;
  		return 0;
  	default:
  		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
@@ -423,7 +423,6 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
  		if (!(data & pmu->global_ovf_ctrl_mask)) {
  			if (!msr_info->host_initiated)
  				pmu->global_status &= ~data;
-			pmu->global_ovf_ctrl = data;
  			return 0;
  		}
  		break;

arch/x86/kvm/vmx/pmu_intel.c static void intel_pmu_reset(struct kvm_vcpu *vcpu) · line 593

Quoted 9 lines
arch/x86/kvm/vmx/pmu_intel.c +1 -2
@@ -588,8 +587,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
  		pmc->counter = 0;
  	}
 
-	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
-		pmu->global_ovf_ctrl = 0;
+	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
 
  	intel_pmu_release_guest_lbr_event(vcpu);
  }

Queued, thanks.

Paolo

author
#3 lore raw

PATCH v3 3/3 KVM: vCPU kick tax cut for running vCPU

In reply to Wanpeng Li

From: Wanpeng Li <[email protected]>

Sometimes a vCPU kick is following a pending request, even if @vcpu is the running vCPU. It suffers from both rcuwait_wake_up() which has rcu/memory barrier operations and cmpxchg(). Let's check vcpu->wait before rcu_wait_wake_up() and whether @vcpu is the running vCPU before cmpxchg() to tax cut this overhead.

We evaluate the kvm-unit-test/vmexit.flat on an Intel ICX box, most of the scores can improve ~600 cpu cycles especially when APICv is disabled.

tscdeadline_immed
tscdeadline
self_ipi_sti_nop
..............
x2apic_self_ipi_tpr_sti_hlt

---
v2 -> v3:
* use kvm_arch_vcpu_get_wait()
v1 -> v2:
* move checking running vCPU logic to kvm_vcpu_kick
* check rcuwait_active(&vcpu->wait) etc

 virt/kvm/kvm_main.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)
virt/kvm/kvm_main.c +10 -3
index 7851f3a1b5f7..1bc52eab0a7d 100644
@@ -3314,8 +3314,15 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
 	int me, cpu;
 
-	if (kvm_vcpu_wake_up(vcpu))
-		return;
+	me = get_cpu();
+
+	if (rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)) && kvm_vcpu_wake_up(vcpu))
+		goto out;
+
+	if (vcpu == __this_cpu_read(kvm_running_vcpu)) {
+		WARN_ON_ONCE(vcpu->mode == IN_GUEST_MODE);
+		goto out;
+	}
 
 	/*
 	 * Note, the vCPU could get migrated to a different pCPU at any point
@@ -3324,12 +3331,12 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 	 * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the
 	 * vCPU also requires it to leave IN_GUEST_MODE.
 	 */
-	me = get_cpu();
 	if (kvm_arch_vcpu_should_kick(vcpu)) {
 		cpu = READ_ONCE(vcpu->cpu);
 		if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
 			smp_send_reschedule(cpu);
 	}
+out:
 	put_cpu();
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
Signature · 1 line
2.25.1
maintainer
#4 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

virt/kvm/kvm_main.c void kvm_vcpu_kick(struct kvm_vcpu *vcpu) · line 3320

Quoted 6 lines · Wanpeng Li
virt/kvm/kvm_main.c +4 -2
-	if (kvm_vcpu_wake_up(vcpu))
-		return;
+	me = get_cpu();
+
+	if (rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)) && kvm_vcpu_wake_up(vcpu))
+		goto out;

This is racy. You are basically doing the same check that rcuwait_wake_up does, but without the memory barrier before.

Also here:

virt/kvm/kvm_main.c void kvm_vcpu_kick(struct kvm_vcpu *vcpu) · line 3323

Quoted 2 lines
virt/kvm/kvm_main.c +2 -0
+	if (vcpu == __this_cpu_read(kvm_running_vcpu)) {
+		WARN_ON_ONCE(vcpu->mode == IN_GUEST_MODE);

it's better to do

	if (vcpu == ... && !WARN_ON_ONCE(vcpu->mode == IN_GUEST_MODE))
		goto out;

so that if the bug happens you do get a smp_send_reschedule() and fail safely.

Paolo

Quoted 2 lines
(quoted diff) +2 -0
+		goto out;
+	}
#5 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

Quoted 10 lines · Paolo Bonzini

Review

Quoted 6 lines · Wanpeng Li
(quoted diff) +4 -2
-	if (kvm_vcpu_wake_up(vcpu))
-		return;
+	me = get_cpu();
+
+	if (rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)) && kvm_vcpu_wake_up(vcpu))
+		goto out;

This is racy. You are basically doing the same check that rcuwait_wake_up does, but without the memory barrier before.

I was worried that was the case[*], but I didn't have the two hours it would have taken me to verify there was indeed a problem :-)

The intent of the extra check was to avoid the locked instruction that comes with disabling preemption via rcu_read_lock(). But thinking more, the extra op should be little more than a basic arithmetic operation in the grand scheme on modern x86 since the cache line is going to be locked and written no matter what, either immediately before or immediately after.

So with Paolo's other comment, maybe just this? And if this doesn't provide the desired performance boost, changes to the rcuwait behavior should go in separate patch.

virt/kvm/kvm_main.c +11 -0
index 9ec99f5b972c..ebc6d4f2fbfa 100644
@@ -3333,11 +3333,22 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
         * vCPU also requires it to leave IN_GUEST_MODE.
         */
        me = get_cpu();
+
+       /*
+        * Avoid the moderately expensive "should kick" operation if this pCPU
+        * is currently running the target vCPU, in which case it's a KVM bug
+        * if the vCPU is in the inner run loop.
+        */
+       if (vcpu == __this_cpu_read(kvm_running_vcpu) &&
+           !WARN_ON_ONCE(vcpu->mode == IN_GUEST_MODE))
+               goto out;
+
        if (kvm_arch_vcpu_should_kick(vcpu)) {
                cpu = READ_ONCE(vcpu->cpu);
                if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
                        smp_send_reschedule(cpu);
        }
+out:
        put_cpu();
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_kick);

[*] https://lkml.kernel.org/r/[email protected]

author
#6 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

Quoted 13 lines · Sean Christopherson
Quoted 10 lines · Paolo Bonzini

Review

Quoted 6 lines · Wanpeng Li
(quoted diff) +4 -2
-   if (kvm_vcpu_wake_up(vcpu))
-           return;
+   me = get_cpu();
+
+   if (rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)) && kvm_vcpu_wake_up(vcpu))
+           goto out;

This is racy. You are basically doing the same check that rcuwait_wake_up does, but without the memory barrier before.

Quoted 8 lines

I was worried that was the case[*], but I didn't have the two hours it would have taken me to verify there was indeed a problem :-)

The intent of the extra check was to avoid the locked instruction that comes with disabling preemption via rcu_read_lock(). But thinking more, the extra op should be little more than a basic arithmetic operation in the grand scheme on modern x86 since the cache line is going to be locked and written no matter what, either immediately before or immediately after.

I observe the main overhead of rcuwait_wake_up() is from rcu operations, especially rcu_read_lock/unlock().

Quoted 4 lines

So with Paolo's other comment, maybe just this? And if this doesn't provide the desired performance boost, changes to the rcuwait behavior should go in separate patch.

Ok.

Wanpeng

maintainer
#7 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

Quoted 8 lines · Wanpeng Li
Quoted 5 lines

The intent of the extra check was to avoid the locked instruction that comes with disabling preemption via rcu_read_lock(). But thinking more, the extra op should be little more than a basic arithmetic operation in the grand scheme on modern x86 since the cache line is going to be locked and written no matter what, either immediately before or immediately after.

I observe the main overhead of rcuwait_wake_up() is from rcu operations, especially rcu_read_lock/unlock().

Do you have CONFIG_PREEMPT_RCU set? If so, maybe something like this would help:

kernel/exit.c +8 -2
index fd1c04193e18..ca1e60a1234d 100644
@@ -235,8 +235,6 @@ int rcuwait_wake_up(struct rcuwait *w)
 	int ret = 0;
 	struct task_struct *task;
 
-	rcu_read_lock();
-
 	/*
 	 * Order condition vs @task, such that everything prior to the load
 	 * of @task is visible. This is the condition as to why the user called
@@ -250,6 +248,14 @@ int rcuwait_wake_up(struct rcuwait *w)
 	 */
 	smp_mb(); /* (B) */
 
+#ifdef CONFIG_PREEMPT_RCU
+	/* The cost of rcu_read_lock() is nontrivial for preemptable RCU.  */
+	if (!rcuwait_active(w))
+		return ret;
+#endif
+
+	rcu_read_lock();
+
 	task = rcu_dereference(w->task);
 	if (task)
 		ret = wake_up_process(task);

(If you don't, rcu_read_lock is essentially preempt_disable() and it should not have a large overhead). You still need the memory barrier though, in order to avoid missed wakeups; shameless plug for my article at https://lwn.net/Articles/847481/.

Paolo

Quoted 4 lines
Quoted 3 lines

So with Paolo's other comment, maybe just this? And if this doesn't provide the desired performance boost, changes to the rcuwait behavior should go in separate patch.

Ok.

author
#8 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

Quoted 8 lines · Paolo Bonzini
Quoted 6 lines · Wanpeng Li
Quoted 5 lines

The intent of the extra check was to avoid the locked instruction that comes with disabling preemption via rcu_read_lock(). But thinking more, the extra op should be little more than a basic arithmetic operation in the grand scheme on modern x86 since the cache line is going to be locked and written no matter what, either immediately before or immediately after.

Quoted 4 lines
Quoted 2 lines

I observe the main overhead of rcuwait_wake_up() is from rcu operations, especially rcu_read_lock/unlock().

Do you have CONFIG_PREEMPT_RCU set? If so, maybe something like this would help:

Yes.

Quoted 30 lines
kernel/exit.c +8 -2
index fd1c04193e18..ca1e60a1234d 100644
@@ -235,8 +235,6 @@ int rcuwait_wake_up(struct rcuwait *w)
        int ret = 0;
        struct task_struct *task;
 
-       rcu_read_lock();
-
        /*
         * Order condition vs @task, such that everything prior to the load
         * of @task is visible. This is the condition as to why the user called
@@ -250,6 +248,14 @@ int rcuwait_wake_up(struct rcuwait *w)
         */
        smp_mb(); /* (B) */
 
+#ifdef CONFIG_PREEMPT_RCU
+       /* The cost of rcu_read_lock() is nontrivial for preemptable RCU.  */
+       if (!rcuwait_active(w))
+               return ret;
+#endif
+
+       rcu_read_lock();
+
        task = rcu_dereference(w->task);
        if (task)
                ret = wake_up_process(task);
Quoted 4 lines

(If you don't, rcu_read_lock is essentially preempt_disable() and it should not have a large overhead). You still need the memory barrier though, in order to avoid missed wakeups; shameless plug for my article at https://lwn.net/Articles/847481/.

You are right, the cost of rcu_read_lock() for preemptable RCU introduces too much overhead, do you want to send a separate patch?

Wanpeng

maintainer
#9 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

Quoted 12 lines · Wanpeng Li
Quoted 12 lines
kernel/exit.c +8 -0
+#ifdef CONFIG_PREEMPT_RCU
+       /* The cost of rcu_read_lock() is nontrivial for preemptable RCU.  */
+       if (!rcuwait_active(w))
+               return ret;
+#endif
+
+       rcu_read_lock();
+
         task = rcu_dereference(w->task);
         if (task)
                 ret = wake_up_process(task);
Quoted 6 lines
Quoted 4 lines

(If you don't, rcu_read_lock is essentially preempt_disable() and it should not have a large overhead). You still need the memory barrier though, in order to avoid missed wakeups; shameless plug for my article athttps://lwn.net/Articles/847481/.

You are right, the cost of rcu_read_lock() for preemptable RCU introduces too much overhead, do you want to send a separate patch?

Yes, I'll take care of this. Thanks!

Paolo

maintainer
#10 lore raw

Re: [PATCH v3 3/3] KVM: vCPU kick tax cut for running vCPU

In reply to Sean Christopherson
Quoted 5 lines · Sean Christopherson

The intent of the extra check was to avoid the locked instruction that comes with disabling preemption via rcu_read_lock(). But thinking more, the extra op should be little more than a basic arithmetic operation in the grand scheme on modern x86 since the cache line is going to be locked and written no matter what, either immediately before or immediately after.

There should be no locked instructions unless you're using PREEMPT_RT/PREEMPT_RCU, no? The preempt_disable count is in a percpu variable.

virt/kvm/kvm_main.c void kvm_vcpu_kick(struct kvm_vcpu *vcpu) · line 3345

Quoted 10 lines
virt/kvm/kvm_main.c +9 -0
+       /*
+        * Avoid the moderately expensive "should kick" operation if this pCPU
+        * is currently running the target vCPU, in which case it's a KVM bug
+        * if the vCPU is in the inner run loop.
+        */
+       if (vcpu == __this_cpu_read(kvm_running_vcpu) &&
+           !WARN_ON_ONCE(vcpu->mode == IN_GUEST_MODE))
+               goto out;
+

It should not even be a problem if vcpu->mode == IN_GUEST_MODE, you just set it to EXITING_GUEST_MODE without even the need for atomic_cmpxchg. I'll send a few patches out, since I think I found some related issues.

Paolo

maintainer
#11 lore raw
In reply to Wanpeng Li
Quoted 12 lines · Wanpeng Li

From: Wanpeng Li <[email protected]>

SDM mentioned that, RDPMC:

   IF (((CR4.PCE = 1) or (CPL = 0) or (CR0.PE = 0)) and (ECX indicates a supported counter))
       THEN
           EAX := counter[31:0];
           EDX := ZeroExtend(counter[MSCB:32]);
       ELSE (* ECX is not valid or CR4.PCE is 0 and CPL is 1, 2, or 3 and CR0.PE is 1 *)
           #GP(0);
   FI;
Quoted 2 lines

Let's add the CR0.PE is 1 checking to rdpmc emulate, though this isn't strictly necessary since it's impossible for CPL to be >0 if CR0.PE=0.

Why not just add a comment then instead?

Paolo

Quoted 33 lines

---
v2 -> v3:
* add the missing 'S'
v1 -> v2:
* update patch description

  arch/x86/kvm/emulate.c | 3 ++-
  1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/kvm/emulate.c +2 -1
index 9a144ca8e146..ab7ec569e8c9 100644
@@ -4213,6 +4213,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt)
  static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
  {
  	u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
+	u64 cr0 = ctxt->ops->get_cr(ctxt, 0);
  	u64 rcx = reg_read(ctxt, VCPU_REGS_RCX);
 
  	/*
@@ -4222,7 +4223,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
  	if (enable_vmware_backdoor && is_vmware_backdoor_pmc(rcx))
  		return X86EMUL_CONTINUE;
 
-	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
+	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt) && (cr0 & X86_CR0_PE)) ||
  	    ctxt->ops->check_pmc(ctxt, rcx))
  		return emulate_gp(ctxt, 0);
 
author
#12 lore raw
Quoted 14 lines · Paolo Bonzini
Quoted 12 lines · Wanpeng Li

From: Wanpeng Li <[email protected]>

SDM mentioned that, RDPMC:

   IF (((CR4.PCE = 1) or (CPL = 0) or (CR0.PE = 0)) and (ECX indicates a supported counter))
       THEN
           EAX := counter[31:0];
           EDX := ZeroExtend(counter[MSCB:32]);
       ELSE (* ECX is not valid or CR4.PCE is 0 and CPL is 1, 2, or 3 and CR0.PE is 1 *)
           #GP(0);
   FI;
Quoted 4 lines
Quoted 2 lines

Let's add the CR0.PE is 1 checking to rdpmc emulate, though this isn't strictly necessary since it's impossible for CPL to be >0 if CR0.PE=0.

Why not just add a comment then instead?

Will do.

Wanpeng