Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1671309 > unrolled thread

[PATCH v3 0/4] KVM: async_pf: Fix async_pf exception injection

Back to article view | Back to linux.kernel

Contents

  [PATCH v3 0/4] KVM: async_pf: Fix async_pf exception injection Wanpeng Li <kernellwp@gmail.com> - 2017-06-21 05:10 +0200
    [PATCH v3 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf Wanpeng Li <kernellwp@gmail.com> - 2017-06-21 05:10 +0200
    [PATCH v3 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit Wanpeng Li <kernellwp@gmail.com> - 2017-06-21 05:10 +0200

#1671309 — [PATCH v3 0/4] KVM: async_pf: Fix async_pf exception injection

 INFO: task gnome-terminal-:1734 blocked for more than 120 seconds.
       Not tainted 4.12.0-rc4+ #8
 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 gnome-terminal- D    0  1734   1015 0x00000000
 Call Trace:
  __schedule+0x3cd/0xb30
  schedule+0x40/0x90
  kvm_async_pf_task_wait+0x1cc/0x270
  ? __vfs_read+0x37/0x150
  ? prepare_to_swait+0x22/0x70
  do_async_page_fault+0x77/0xb0
  ? do_async_page_fault+0x77/0xb0
  async_page_fault+0x28/0x30

This is triggered by running both win7 and win2016 on L1 KVM simultaneously, 
and then gives stress to memory on L1, I can observed this hang on L1 when 
at least ~70% swap area is occupied on L0.

This is due to async pf was injected to L2 which should be injected to L1, 
L2 guest starts receiving pagefault w/ bogus %cr2(apf token from the host 
actually), and L1 guest starts accumulating tasks stuck in D state in 
kvm_async_pf_task_wait() since missing PAGE_READY async_pfs.

This patchset fixes it according to Radim's proposal "force a nested VM exit 
from nested_vmx_check_exception if the injected #PF is async_pf and handle 
the #PF VM exit in L1". https://www.spinics.net/lists/kvm/msg142498.html

Note: The patchset almost not touch SVM since I don't have AMD CPU to verify
the modification.

v2 -> v3:
 * add the flag to the userspace interface(KVM_GET/PUT_VCPU_EVENTS)

v1 -> v2:
 * remove nested_vmx_check_exception nr parameter
 * construct a simple special vm-exit information field for async pf
 * introduce nested_apf_token to vcpu->arch.apf to avoid change the CR2 
   visible in L2 guest 
 * avoid pass the apf directed towards it (L1) into L2 if there is L3 
   at the moment

Wanpeng Li (4):
  KVM: x86: Simple kvm_x86_ops->queue_exception parameter
  KVM: async_pf: Add L1 guest async_pf #PF vmexit handler
  KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf
  KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit

 Documentation/virtual/kvm/msr.txt     |  5 +--
 arch/x86/include/asm/kvm_emulate.h    |  1 +
 arch/x86/include/asm/kvm_host.h       |  7 ++--
 arch/x86/include/uapi/asm/kvm.h       |  2 ++
 arch/x86/include/uapi/asm/kvm_para.h  |  1 +
 arch/x86/kernel/kvm.c                 |  1 +
 arch/x86/kvm/mmu.c                    |  2 +-
 arch/x86/kvm/svm.c                    |  8 +++--
 arch/x86/kvm/vmx.c                    | 61 +++++++++++++++++++++++++++--------
 arch/x86/kvm/x86.c                    | 26 +++++++++------
 tools/arch/x86/include/uapi/asm/kvm.h |  2 ++
 11 files changed, 85 insertions(+), 31 deletions(-)

-- 
2.7.4

[toc] | [next] | [standalone]

#1671310 — [PATCH v3 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf

From: Wanpeng Li <wanpeng.li@hotmail.com>

Add an async_page_fault field to vcpu->arch.exception to identify an async 
page fault, and constructs the expected vm-exit information fields. Force 
a nested VM exit from nested_vmx_check_exception() if the injected #PF 
is async page fault. Extending the userspace interface KVM_GET_VCPU_EVENTS
and KVM_SET_VCPU_EVENTS for live migration.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
 arch/x86/include/asm/kvm_emulate.h    |  1 +
 arch/x86/include/asm/kvm_host.h       |  2 ++
 arch/x86/include/uapi/asm/kvm.h       |  2 ++
 arch/x86/kvm/vmx.c                    | 17 ++++++++++++++---
 arch/x86/kvm/x86.c                    | 16 +++++++++++++---
 tools/arch/x86/include/uapi/asm/kvm.h |  2 ++
 6 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 0559626..b5bcad9 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -23,6 +23,7 @@ struct x86_exception {
 	u16 error_code;
 	bool nested_page_fault;
 	u64 address; /* cr2 or nested page fault gpa */
+	bool async_page_fault;
 };
 
 /*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1f01bfb..100ad9a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -545,6 +545,7 @@ struct kvm_vcpu_arch {
 		bool reinject;
 		u8 nr;
 		u32 error_code;
+		bool async_page_fault;
 	} exception;
 
 	struct kvm_queued_interrupt {
@@ -645,6 +646,7 @@ struct kvm_vcpu_arch {
 		u64 msr_val;
 		u32 id;
 		bool send_user_only;
+		unsigned long nested_apf_token;
 	} apf;
 
 	/* OSVW MSRs (AMD only) */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index c2824d0..435f03f 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -287,6 +287,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
+#define KVM_VCPUEVENT_VALID_ASYNC_PF 0x00000010
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -300,6 +301,7 @@ struct kvm_vcpu_events {
 		__u8 has_error_code;
 		__u8 pad;
 		__u32 error_code;
+		bool async_page_fault;
 	} exception;
 	struct {
 		__u8 injected;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f533cc1..e7b9844 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2419,13 +2419,24 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
  */
-static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
 
-	if (!(vmcs12->exception_bitmap & (1u << nr)))
+	if (!((vmcs12->exception_bitmap & (1u << nr)) ||
+		(nr == PF_VECTOR && vcpu->arch.exception.async_page_fault)))
 		return 0;
 
+	if (vcpu->arch.exception.async_page_fault) {
+		vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+			PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+			INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+			vcpu->arch.apf.nested_apf_token);
+		return 1;
+	}
+
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
@@ -2442,7 +2453,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
 	if (!reinject && is_guest_mode(vcpu) &&
-	    nested_vmx_check_exception(vcpu, nr))
+	    nested_vmx_check_exception(vcpu))
 		return;
 
 	if (has_error_code) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1b28a31..0c201eb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -452,7 +452,11 @@ EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 {
 	++vcpu->stat.pf_guest;
-	vcpu->arch.cr2 = fault->address;
+	vcpu->arch.exception.async_page_fault = fault->async_page_fault;
+	if (is_guest_mode(vcpu) && vcpu->arch.exception.async_page_fault)
+		vcpu->arch.apf.nested_apf_token = fault->address;
+	else
+		vcpu->arch.cr2 = fault->address;
 	kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
@@ -3096,7 +3100,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
 			 | KVM_VCPUEVENT_VALID_SHADOW
-			 | KVM_VCPUEVENT_VALID_SMM);
+			 | KVM_VCPUEVENT_VALID_SMM
+			 | KVM_VCPUEVENT_VALID_ASYNC_PF);
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
@@ -3108,7 +3113,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
 			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
 			      | KVM_VCPUEVENT_VALID_SHADOW
-			      | KVM_VCPUEVENT_VALID_SMM))
+			      | KVM_VCPUEVENT_VALID_SMM
+			      | KVM_VCPUEVENT_VALID_ASYNC_PF))
 		return -EINVAL;
 
 	if (events->exception.injected &&
@@ -3127,6 +3133,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	vcpu->arch.exception.nr = events->exception.nr;
 	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
 	vcpu->arch.exception.error_code = events->exception.error_code;
+	if (events->flags & KVM_VCPUEVENT_VALID_ASYNC_PF)
+		vcpu->arch.exception.async_page_fault = events->exception.async_page_fault;
 
 	vcpu->arch.interrupt.pending = events->interrupt.injected;
 	vcpu->arch.interrupt.nr = events->interrupt.nr;
@@ -8571,6 +8579,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 		fault.error_code = 0;
 		fault.nested_page_fault = false;
 		fault.address = work->arch.token;
+		fault.async_page_fault = true;
 		kvm_inject_page_fault(vcpu, &fault);
 	}
 }
@@ -8593,6 +8602,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		fault.error_code = 0;
 		fault.nested_page_fault = false;
 		fault.address = work->arch.token;
+		fault.async_page_fault = true;
 		kvm_inject_page_fault(vcpu, &fault);
 	}
 	vcpu->arch.apf.halted = false;
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index c2824d0..435f03f 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -287,6 +287,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
+#define KVM_VCPUEVENT_VALID_ASYNC_PF 0x00000010
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -300,6 +301,7 @@ struct kvm_vcpu_events {
 		__u8 has_error_code;
 		__u8 pad;
 		__u32 error_code;
+		bool async_page_fault;
 	} exception;
 	struct {
 		__u8 injected;
-- 
2.7.4

[toc] | [prev] | [next] | [standalone]

#1671311 — [PATCH v3 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit

From: Wanpeng Li <wanpeng.li@hotmail.com>

Adds another flag bit (bit 2) to MSR_KVM_ASYNC_PF_EN. If bit 2 is 1, async
page faults are delivered to L1 as #PF vmexits; if bit 2 is 0, kvm_can_do_async_pf
returns 0 if in guest mode.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
 Documentation/virtual/kvm/msr.txt    | 5 +++--
 arch/x86/include/asm/kvm_host.h      | 1 +
 arch/x86/include/uapi/asm/kvm_para.h | 1 +
 arch/x86/kernel/kvm.c                | 1 +
 arch/x86/kvm/mmu.c                   | 2 +-
 arch/x86/kvm/vmx.c                   | 2 +-
 arch/x86/kvm/x86.c                   | 5 +++--
 7 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index 0a9ea51..1ebecc1 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -166,10 +166,11 @@ MSR_KVM_SYSTEM_TIME: 0x12
 MSR_KVM_ASYNC_PF_EN: 0x4b564d02
 	data: Bits 63-6 hold 64-byte aligned physical address of a
 	64 byte memory area which must be in guest RAM and must be
-	zeroed. Bits 5-2 are reserved and should be zero. Bit 0 is 1
+	zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
 	when asynchronous page faults are enabled on the vcpu 0 when
 	disabled. Bit 1 is 1 if asynchronous page faults can be injected
-	when vcpu is in cpl == 0.
+	when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
+	are delivered to L1 as #PF vmexits.
 
 	First 4 byte of 64 byte memory location will be written to by
 	the hypervisor at the time of asynchronous page fault (APF)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 100ad9a..9e18de4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -647,6 +647,7 @@ struct kvm_vcpu_arch {
 		u32 id;
 		bool send_user_only;
 		unsigned long nested_apf_token;
+		bool delivery_as_pf_vmexit;
 	} apf;
 
 	/* OSVW MSRs (AMD only) */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index cff0bb6..a965e5b 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -67,6 +67,7 @@ struct kvm_clock_pairing {
 
 #define KVM_ASYNC_PF_ENABLED			(1 << 0)
 #define KVM_ASYNC_PF_SEND_ALWAYS		(1 << 1)
+#define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT	(1 << 2)
 
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 43e10d6..1e29a77 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -330,6 +330,7 @@ static void kvm_guest_cpu_init(void)
 #ifdef CONFIG_PREEMPT
 		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
 #endif
+		pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
 		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index cb82259..c49aecd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3704,7 +3704,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
-	if (is_guest_mode(vcpu))
+	if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
 		return false;
 
 	return kvm_x86_ops->interrupt_allowed(vcpu);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e7b9844..2e906cf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8025,7 +8025,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		if (is_nmi(intr_info))
 			return false;
 		else if (is_page_fault(intr_info))
-			return enable_ept;
+			return !vmx->apf_reason && enable_ept;
 		else if (is_no_device(intr_info) &&
 			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return false;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c201eb..8278be1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2064,8 +2064,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
 	gpa_t gpa = data & ~0x3f;
 
-	/* Bits 2:5 are reserved, Should be zero */
-	if (data & 0x3c)
+	/* Bits 3:5 are reserved, Should be zero */
+	if (data & 0x38)
 		return 1;
 
 	vcpu->arch.apf.msr_val = data;
@@ -2081,6 +2081,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 1;
 
 	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+	vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 	kvm_async_pf_wakeup_all(vcpu);
 	return 0;
 }
-- 
2.7.4

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web