Skip to contentSkip to conversation

x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume

PATCH In review Sasha Levin 2 participants 8 messages Apr 27, 2022

Subsystems (2)
lore
Share & tools
lore

Sasha Levin

author maintainer
#0 lore raw

PATCH 1/4 x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume

From: Wanpeng Li <[email protected]>

[ Upstream commit 0361bdfddca20c8855ea3bdbbbc9c999912b10ff ]

MSR_KVM_POLL_CONTROL is cleared on reset, thus reverting guests to host-side polling after suspend/resume. Non-bootstrap CPUs are restored correctly by the haltpoll driver because they are hot-unplugged during suspend and hot-plugged during resume; however, the BSP is not hotpluggable and remains in host-sde polling mode after the guest resume. The makes the guest pay for the cost of vmexits every time the guest enters idle.

Fix it by recording BSP's haltpoll state and resuming it during guest resume.

Cc Marcelo Tosatti <[email protected]>

Message-Id: <[email protected]>

---
 arch/x86/kernel/kvm.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
arch/x86/kernel/kvm.c +13 -0
index 18e952fed021..6c3d38b5a8ad 100644
@@ -66,6 +66,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align
 DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
+static int has_guest_poll = 0;
 /*
  * No need for any "IO delay" on KVM
  */
@@ -624,14 +625,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
 static int kvm_suspend(void)
 {
+	u64 val = 0;
+
 	kvm_guest_cpu_offline(false);
 
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+	has_guest_poll = !(val & 1);
+#endif
 	return 0;
 }
 
 static void kvm_resume(void)
 {
 	kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
 }
 
 static struct syscore_ops kvm_syscore_ops = {
Signature · 1 line
2.35.1
author maintainer
#1 lore raw

PATCH 2/4 KVM: x86: Do not change ICR on write to APIC_SELF_IPI

From: Paolo Bonzini <[email protected]>

[ Upstream commit d22a81b304a27fca6124174a8e842e826c193466 ]

Emulating writes to SELF_IPI with a write to ICR has an unwanted side effect:
the value of ICR in vAPIC page gets changed. The lists SELF_IPI as write-only, with no associated MMIO offset, so any write should have no visible side effect in the vAPIC page.

---
 arch/x86/kvm/lapic.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
arch/x86/kvm/lapic.c +3 -4
index de11149e28e0..e45ebf0870b6 100644
@@ -2106,10 +2106,9 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		break;
 
 	case APIC_SELF_IPI:
-		if (apic_x2apic_mode(apic)) {
-			kvm_lapic_reg_write(apic, APIC_ICR,
-					    APIC_DEST_SELF | (val & APIC_VECTOR_MASK));
-		} else
+		if (apic_x2apic_mode(apic))
+			kvm_apic_send_ipi(apic, APIC_DEST_SELF | (val & APIC_VECTOR_MASK), 0);
+		else
 			ret = 1;
 		break;
 	default:
Signature · 1 line
2.35.1
maintainer Acked-by on v1 2/4
#2 lore raw

Re: [PATCH MANUALSEL 5.10 2/4] KVM: x86: Do not change ICR on write to APIC_SELF_IPI

Quoted 25 lines · Sasha Levin

From: Paolo Bonzini <[email protected]>

[ Upstream commit d22a81b304a27fca6124174a8e842e826c193466 ]

Emulating writes to SELF_IPI with a write to ICR has an unwanted side effect:
the value of ICR in vAPIC page gets changed. The lists SELF_IPI as write-only, with no associated MMIO offset, so any write should have no visible side effect in the vAPIC page.

---
  arch/x86/kvm/lapic.c | 7 +++----
  1 file changed, 3 insertions(+), 4 deletions(-)
arch/x86/kvm/lapic.c +0 -0
index de11149e28e0..e45ebf0870b6 100644
@@ -2106,10 +2106,9 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
  		break;
 
  	case APIC_SELF_IPI:

arch/x86/kvm/lapic.c int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) · line 2114

Quoted 10 lines
arch/x86/kvm/lapic.c +3 -4
-		if (apic_x2apic_mode(apic)) {
-			kvm_lapic_reg_write(apic, APIC_ICR,
-					    APIC_DEST_SELF | (val & APIC_VECTOR_MASK));
-		} else
+		if (apic_x2apic_mode(apic))
+			kvm_apic_send_ipi(apic, APIC_DEST_SELF | (val & APIC_VECTOR_MASK), 0);
+		else
  			ret = 1;
  		break;
  	default:
author maintainer
#3 lore raw

PATCH 3/4 KVM: x86/mmu: avoid NULL-pointer dereference on page freeing bugs

In reply to Sasha Levin

From: Paolo Bonzini <[email protected]>

[ Upstream commit 9191b8f0745e63edf519e4a54a4aaae1d3d46fbd ]

WARN and bail if KVM attempts to free a root that isn't backed by a shadow page. KVM allocates a bare page for "special" roots, e.g. when using PAE paging or shadowing 2/3/4-level page tables with 4/5-level, and so root_hpa will be valid but won't be backed by a shadow page. It's all too easy to blindly call mmu_free_root_page() on root_hpa, be nice and WARN instead of crashing KVM and possibly the kernel.

---
 arch/x86/kvm/mmu/mmu.c | 2 ++
 1 file changed, 2 insertions(+)
arch/x86/kvm/mmu/mmu.c +2 -0
index 99ea1ec12ffe..70ef5b542681 100644
@@ -3140,6 +3140,8 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 		return;
 
 	sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK);
+	if (WARN_ON(!sp))
+		return;
 
 	if (kvm_mmu_put_root(kvm, sp)) {
 		if (sp->tdp_mmu_page)
Signature · 1 line
2.35.1
maintainer Acked-by on v1 3/4
#4 lore raw

Re: [PATCH MANUALSEL 5.10 3/4] KVM: x86/mmu: avoid NULL-pointer dereference on page freeing bugs

Quoted 23 lines · Sasha Levin

From: Paolo Bonzini <[email protected]>

[ Upstream commit 9191b8f0745e63edf519e4a54a4aaae1d3d46fbd ]

WARN and bail if KVM attempts to free a root that isn't backed by a shadow page. KVM allocates a bare page for "special" roots, e.g. when using PAE paging or shadowing 2/3/4-level page tables with 4/5-level, and so root_hpa will be valid but won't be backed by a shadow page. It's all too easy to blindly call mmu_free_root_page() on root_hpa, be nice and WARN instead of crashing KVM and possibly the kernel.

---
  arch/x86/kvm/mmu/mmu.c | 2 ++
  1 file changed, 2 insertions(+)
arch/x86/kvm/mmu/mmu.c +0 -0
index 99ea1ec12ffe..70ef5b542681 100644

arch/x86/kvm/mmu/mmu.c static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, · line 3147

Quoted 8 lines
arch/x86/kvm/mmu/mmu.c +2 -0
@@ -3140,6 +3140,8 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
  		return;
 
  	sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK);
+	if (WARN_ON(!sp))
+		return;
 
  	if (kvm_mmu_put_root(kvm, sp)) {
  		if (sp->tdp_mmu_page)
author maintainer
#5 lore raw

PATCH 4/4 KVM: LAPIC: Enable timer posted-interrupt only when mwait/hlt is advertised

In reply to Sasha Levin

From: Wanpeng Li <[email protected]>

[ Upstream commit 1714a4eb6fb0cb79f182873cd011a8ed60ac65e8 ]

As commit 0c5f81dad46 ("KVM: LAPIC: Inject timer interrupt via posted interrupt") mentioned that the host admin should well tune the guest setup, so that vCPUs are placed on isolated pCPUs, and with several pCPUs surplus for *busy* housekeeping. In this setup, it is preferrable to disable mwait/hlt/pause vmexits to keep the vCPUs in non-root mode.

However, if only some guests isolated and others not, they would not have any benefit from posted timer interrupts, and at the same time lose VMX preemption timer fast paths because kvm_can_post_timer_interrupt() returns true and therefore forces kvm_can_use_hv_timer() to false.

By guaranteeing that posted-interrupt timer is only used if MWAIT or HLT are done without vmexit, KVM can make a better choice and use the VMX preemption timer and the corresponding fast paths.

Message-Id: <[email protected]>

---
 arch/x86/kvm/lapic.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/kvm/lapic.c +2 -1
index e45ebf0870b6..a3ef793fce5f 100644
@@ -113,7 +113,8 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
 
 static bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu)
 {
-	return pi_inject_timer && kvm_vcpu_apicv_active(vcpu);
+	return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
+		(kvm_mwait_in_guest(vcpu->kvm) || kvm_hlt_in_guest(vcpu->kvm));
 }
 
 bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu)
Signature · 1 line
2.35.1
maintainer Acked-by on v1 4/4
#6 lore raw

Re: [PATCH MANUALSEL 5.10 4/4] KVM: LAPIC: Enable timer posted-interrupt only when mwait/hlt is advertised

Quoted 36 lines · Sasha Levin

From: Wanpeng Li <[email protected]>

[ Upstream commit 1714a4eb6fb0cb79f182873cd011a8ed60ac65e8 ]

As commit 0c5f81dad46 ("KVM: LAPIC: Inject timer interrupt via posted interrupt") mentioned that the host admin should well tune the guest setup, so that vCPUs are placed on isolated pCPUs, and with several pCPUs surplus for *busy* housekeeping. In this setup, it is preferrable to disable mwait/hlt/pause vmexits to keep the vCPUs in non-root mode.

However, if only some guests isolated and others not, they would not have any benefit from posted timer interrupts, and at the same time lose VMX preemption timer fast paths because kvm_can_post_timer_interrupt() returns true and therefore forces kvm_can_use_hv_timer() to false.

By guaranteeing that posted-interrupt timer is only used if MWAIT or HLT are done without vmexit, KVM can make a better choice and use the VMX preemption timer and the corresponding fast paths.

Message-Id: <[email protected]>

---
  arch/x86/kvm/lapic.c | 3 ++-
  1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/kvm/lapic.c +0 -0
index e45ebf0870b6..a3ef793fce5f 100644

arch/x86/kvm/lapic.c static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) · line 120

Quoted 9 lines
arch/x86/kvm/lapic.c +2 -1
@@ -113,7 +113,8 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
 
  static bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu)
  {
-	return pi_inject_timer && kvm_vcpu_apicv_active(vcpu);
+	return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
+		(kvm_mwait_in_guest(vcpu->kvm) || kvm_hlt_in_guest(vcpu->kvm));
  }
 
  bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu)
maintainer Acked-by on v1 1/4
#7 lore raw
In reply to Sasha Levin
Quoted 53 lines · Sasha Levin

From: Wanpeng Li <[email protected]>

[ Upstream commit 0361bdfddca20c8855ea3bdbbbc9c999912b10ff ]

MSR_KVM_POLL_CONTROL is cleared on reset, thus reverting guests to host-side polling after suspend/resume. Non-bootstrap CPUs are restored correctly by the haltpoll driver because they are hot-unplugged during suspend and hot-plugged during resume; however, the BSP is not hotpluggable and remains in host-sde polling mode after the guest resume. The makes the guest pay for the cost of vmexits every time the guest enters idle.

Fix it by recording BSP's haltpoll state and resuming it during guest resume.

Cc Marcelo Tosatti <[email protected]>

Message-Id: <[email protected]>

---
  arch/x86/kernel/kvm.c | 13 +++++++++++++
  1 file changed, 13 insertions(+)
arch/x86/kernel/kvm.c +8 -0
index 18e952fed021..6c3d38b5a8ad 100644
@@ -66,6 +66,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align
  DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
  static int has_steal_clock = 0;
 
+static int has_guest_poll = 0;
  /*
   * No need for any "IO delay" on KVM
   */
@@ -624,14 +625,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
  static int kvm_suspend(void)
  {
+	u64 val = 0;
+
  	kvm_guest_cpu_offline(false);
 
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+	has_guest_poll = !(val & 1);
+#endif
  	return 0;
  }
 
  static void kvm_resume(void)

arch/x86/kernel/kvm.c static int kvm_cpu_down_prepare(unsigned int cpu) · line 650

Quoted 10 lines
arch/x86/kernel/kvm.c +5 -0
  {
  	kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
  }
 
  static struct syscore_ops kvm_syscore_ops = {