Skip to contentSkip to conversation

KVM: arm/arm64: No need to zero CNTVOFF in kvm_timer_vcpu_put() for VHE

PATCH In review Shanker Donthineni 3 participants 3 messages Feb 19, 2018 – Feb 22, 2018 KVM arm64

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 KVM: arm/arm64: No need to zero CNTVOFF in kvm_timer_vcpu_put() for VHE

In AArch64/AArch32, the virtual counter uses a fixed virtual offset of zero in the following situations as per ARMv8 specifications:

1) HCR_EL2.E2H is 1, and CNTVCT_EL0/CNTVCT are read from EL2.
2) HCR_EL2.{E2H, TGE} is {1, 1}, and either:
— CNTVCT_EL0 is read from Non-secure EL0 or EL2. — CNTVCT is read from Non-secure EL0.

So, no need to zero CNTVOFF_EL2/CNTVOFF for VHE case.

---
 virt/kvm/arm/arch_timer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
virt/kvm/arm/arch_timer.c +4 -2
index 70268c0..86eca324 100644
@@ -541,9 +541,11 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	 * The kernel may decide to run userspace after calling vcpu_put, so
 	 * we reset cntvoff to 0 to ensure a consistent read between user
 	 * accesses to the virtual counter and kernel access to the physical
-	 * counter.
+	 * counter of non-VHE case. For VHE, the virtual counter uses a fixed
+	 * virtual offset of zero, so no need to zero CNTVOFF_EL2 register.
 	 */
-	set_cntvoff(0);
+	if (!has_vhe())
+		set_cntvoff(0);
 }
 
 /*
Signature · 8 lines
Qualcomm Datacenter Technologies, Inc. on behalf of the Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.


_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
#1 lore raw

Hi Shanker,

Quoted 23 lines · Shanker Donthineni

In AArch64/AArch32, the virtual counter uses a fixed virtual offset of zero in the following situations as per ARMv8 specifications:

1) HCR_EL2.E2H is 1, and CNTVCT_EL0/CNTVCT are read from EL2.
2) HCR_EL2.{E2H, TGE} is {1, 1}, and either:
— CNTVCT_EL0 is read from Non-secure EL0 or EL2. — CNTVCT is read from Non-secure EL0.

So, no need to zero CNTVOFF_EL2/CNTVOFF for VHE case.

---
 virt/kvm/arm/arch_timer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
virt/kvm/arm/arch_timer.c +0 -0
index 70268c0..86eca324 100644
@@ -541,9 +541,11 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	 * The kernel may decide to run userspace after calling vcpu_put, so
 	 * we reset cntvoff to 0 to ensure a consistent read between user
 	 * accesses to the virtual counter and kernel access to the physical

virt/kvm/arm/arch_timer.c void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) · line 551

Quoted 10 lines
virt/kvm/arm/arch_timer.c +4 -2
-	 * counter.
+	 * counter of non-VHE case. For VHE, the virtual counter uses a fixed
+	 * virtual offset of zero, so no need to zero CNTVOFF_EL2 register.
 	 */
-	set_cntvoff(0);
+	if (!has_vhe())
+		set_cntvoff(0);
 }
 
 /*

I'm okay with this change. I don't think there's a huge gain here though.

Marc, any thoughts or concerns?

Thanks,
-Christoffer

_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Acked-by
#2 lore raw
Quoted 36 lines · Christoffer Dall

Hi Shanker,

Quoted 32 lines · Shanker Donthineni

In AArch64/AArch32, the virtual counter uses a fixed virtual offset of zero in the following situations as per ARMv8 specifications:

1) HCR_EL2.E2H is 1, and CNTVCT_EL0/CNTVCT are read from EL2.
2) HCR_EL2.{E2H, TGE} is {1, 1}, and either:
― CNTVCT_EL0 is read from Non-secure EL0 or EL2. ― CNTVCT is read from Non-secure EL0.

So, no need to zero CNTVOFF_EL2/CNTVOFF for VHE case.

---
 virt/kvm/arm/arch_timer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
virt/kvm/arm/arch_timer.c +4 -2
index 70268c0..86eca324 100644
@@ -541,9 +541,11 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	 * The kernel may decide to run userspace after calling vcpu_put, so
 	 * we reset cntvoff to 0 to ensure a consistent read between user
 	 * accesses to the virtual counter and kernel access to the physical
-	 * counter.
+	 * counter of non-VHE case. For VHE, the virtual counter uses a fixed
+	 * virtual offset of zero, so no need to zero CNTVOFF_EL2 register.
 	 */
-	set_cntvoff(0);
+	if (!has_vhe())
+		set_cntvoff(0);
 }
 
Quoted 6 lines

virt/kvm/arm/arch_timer.c void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) · line 551

Quoted 1 line
virt/kvm/arm/arch_timer.c +0 -0
 /*

I'm okay with this change. I don't think there's a huge gain here though.

Marc, any thoughts or concerns?

None. I don't think this brings any visible performance gain, but hey, why not.

	M.
Signature · 1 line
Jazz is not dead, it just smell funny.