KVM: async_pf: avoid async pf injection when in guest mode

 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 patch fixes the hang by doing async pf when executing L1 guest.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5d3376f677949067f39c5e29fca2f3aceb7880bc..cb8225969255ec006fbff5eab76471f341d92b77 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3698,12 +3698,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
        return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
        if (unlikely(!lapic_in_kernel(vcpu) ||
                     kvm_event_needs_reinjection(vcpu)))
                return false;
 
+       if (is_guest_mode(vcpu))
+               return false;
+
        return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3719,7 +3722,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
        if (!async)
                return false; /* *pfn has correct page already */
 
-       if (!prefault && can_do_async_pf(vcpu)) {
+       if (!prefault && kvm_can_do_async_pf(vcpu)) {
                trace_kvm_try_async_get_page(gva, gfn);
                if (kvm_find_async_pf_gfn(vcpu, gfn)) {
                        trace_kvm_async_pf_doublefault(gva, gfn);

diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 27975807cc64fcae7bccbb53eecab35c3f0c64e2..330bf3a811fb07271de382b598be402c871f6496 100644 (file)
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -76,6 +76,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
                             bool accessed_dirty);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a2cd0997343c485051e849551b9fc9d904177fe0..87d3cb901935f2b251857f54ed53ca73567f10ef 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8607,8 +8607,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
        if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
                return true;
        else
-               return !kvm_event_needs_reinjection(vcpu) &&
-                       kvm_x86_ops->interrupt_allowed(vcpu);
+               return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)