From 86009969c9f59b34de3ce78c173562e4a589cfaa Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 8 Jun 2017 20:13:40 -0700 Subject: [PATCH] KVM: async_pf: avoid async pf injection when in guest mode MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit commit 9bc1f09f6fa76fdf31eb7d6a4a4df43574725f93 upstream. 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 Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini [bwh: Backported to 3.2: adjust context] Signed-off-by: Ben Hutchings --- arch/x86/kvm/mmu.c | 7 +++++-- arch/x86/kvm/mmu.h | 1 + arch/x86/kvm/x86.c | 3 +-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 4a949c7f6423..5b2bf2b4acae 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3011,12 +3011,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) return kvm_setup_async_pf(vcpu, gva, gfn, &arch); } -static bool can_do_async_pf(struct kvm_vcpu *vcpu) +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!irqchip_in_kernel(vcpu->kvm) || kvm_event_needs_reinjection(vcpu))) return false; + if (is_guest_mode(vcpu)) + return false; + return kvm_x86_ops->interrupt_allowed(vcpu); } @@ -3032,7 +3035,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, put_page(pfn_to_page(*pfn)); - 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 e374db9af021..943198e63bdd 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -52,6 +52,7 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); +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 ca35c527d10d..c8c3c39f5bf7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6935,8 +6935,7 @@ 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); } EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); -- 2.39.2