Skip to contentSkip to conversation

x86/kvm/pmu: Set AMD's virt PMU version to 1

PATCH In review Borislav Petkov 3 participants 4 messages May 8, 2019 – May 20, 2019

Subsystems (3)
x86 KVM KVM x86
lore
Share & tools
lore

Borislav Petkov

author maintainer
#0 lore raw

PATCH 1/1 x86/kvm/pmu: Set AMD's virt PMU version to 1

From: Borislav Petkov <[email protected]>

After commit:

672ff6cff80c ("KVM: x86: Raise #GP when guest vCPU do not support PMU")

my AMD guests started #GPing like this:

  general protection fault: 0000 [#1] PREEMPT SMP
  CPU: 1 PID: 4355 Comm: bash Not tainted 5.1.0-rc6+ #3
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
  RIP: 0010:x86_perf_event_update+0x3b/0xa0

with Code: pointing to RDPMC. It is RDPMC because the guest has the hardware watchdog CONFIG_HARDLOCKUP_DETECTOR_PERF enabled which uses perf. Instrumenting kvm_pmu_rdpmc() some, showed that it fails due to:

if (!pmu->version)
return 1;

which the above commit added. Since AMD's PMU leaves the version at 0, that causes the #GP injection into the guest.

Set pmu->version arbitrarily to 1 and move it above the non-applicable struct kvm_pmu members.

Signed-off-by Borislav Petkov <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Janakarajan Natarajan <[email protected]>
Cc [email protected]
Cc Liran Alon <[email protected]>
Cc Mihai Carabas <[email protected]>
Cc Paolo Bonzini <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc "Radim Krčmář" <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Tom Lendacky <[email protected]>
Cc [email protected]
---
 arch/x86/kvm/pmu_amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kvm/pmu_amd.c +1 -1
index 1495a735b38e..50fa9450fcf1 100644
@@ -269,10 +269,10 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
 	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
-	pmu->version = 0;
 	pmu->global_status = 0;
 }
Signature · 1 line
2.21.0
#1 lore raw
Quoted 5 lines · Borislav Petkov

From: Borislav Petkov <[email protected]>

After commit:

672ff6cff80c ("KVM: x86: Raise #GP when guest vCPU do not support PMU")

You should add this commit as a fixes tag. Since that commit went into 5.1 it would be worth this fix going into the 5.1 stable tree.

Thanks,
Tom

Quoted 57 lines

my AMD guests started #GPing like this:

  general protection fault: 0000 [#1] PREEMPT SMP
  CPU: 1 PID: 4355 Comm: bash Not tainted 5.1.0-rc6+ #3
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
  RIP: 0010:x86_perf_event_update+0x3b/0xa0

with Code: pointing to RDPMC. It is RDPMC because the guest has the hardware watchdog CONFIG_HARDLOCKUP_DETECTOR_PERF enabled which uses perf. Instrumenting kvm_pmu_rdpmc() some, showed that it fails due to:

if (!pmu->version)

        return 1;

which the above commit added. Since AMD's PMU leaves the version at 0, that causes the #GP injection into the guest.

Set pmu->version arbitrarily to 1 and move it above the non-applicable struct kvm_pmu members.

Signed-off-by Borislav Petkov <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Janakarajan Natarajan <[email protected]>
Cc [email protected]
Cc Liran Alon <[email protected]>
Cc Mihai Carabas <[email protected]>
Cc Paolo Bonzini <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc "Radim Krčmář" <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Tom Lendacky <[email protected]>
Cc [email protected]
---
 arch/x86/kvm/pmu_amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kvm/pmu_amd.c +1 -2
index 1495a735b38e..50fa9450fcf1 100644
@@ -269,10 +269,10 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 
        pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
        pmu->reserved_bits = 0xffffffff00200000ull;
+       pmu->version = 1;
        /* not applicable to AMD; but clean them to prevent any fall out */
        pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
        pmu->nr_arch_fixed_counters = 0;
-       pmu->version = 0;
        pmu->global_status = 0;
 }
 
--

2.21.0

author maintainer
#2 lore raw
Quoted 9 lines · Thomas
Quoted 5 lines · Borislav Petkov

From: Borislav Petkov <[email protected]>

After commit:

672ff6cff80c ("KVM: x86: Raise #GP when guest vCPU do not support PMU")

You should add this commit as a fixes tag. Since that commit went into 5.1 it would be worth this fix going into the 5.1 stable tree.

Paolo, Radim, can you do that pls, when applying?

Thx.

Signature · 4 lines
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.
maintainer
#3 lore raw
Quoted 4 lines · Borislav Petkov
Quoted 3 lines · Thomas
Quoted 2 lines · Borislav Petkov

From: Borislav Petkov <[email protected]>

Quoted 8 lines
Quoted 6 lines
Quoted 3 lines

After commit:

672ff6cff80c ("KVM: x86: Raise #GP when guest vCPU do not support PMU")

You should add this commit as a fixes tag. Since that commit went into 5.1 it would be worth this fix going into the 5.1 stable tree.

Paolo, Radim, can you do that pls, when applying?

Yes, done (and queued the patch).

Paolo