Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "Bugfixes, a pvspinlock optimization, and documentation moving"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: X86: Boost queue head vCPU to mitigate lock waiter preemption
  Documentation: move Documentation/virtual to Documentation/virt
  KVM: nVMX: Set cached_vmcs12 and cached_shadow_vmcs12 NULL after free
  KVM: X86: Dynamically allocate user_fpu
  KVM: X86: Fix fpu state crash in kvm guest
  Revert "kvm: x86: Use task structs fpu field for user"
  KVM: nVMX: Clear pending KVM_REQ_GET_VMCS12_PAGES when leaving nested

6 files changed, 43 insertions, 12 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8282b8d41209..7b0a4ee77313 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -607,15 +607,16 @@ struct kvm_vcpu_arch {
 
 	/*
 	 * QEMU userspace and the guest each have their own FPU state.
-	 * In vcpu_run, we switch between the user, maintained in the
-	 * task_struct struct, and guest FPU contexts. While running a VCPU,
-	 * the VCPU thread will have the guest FPU context.
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
+	 * While running a VCPU, the VCPU thread will have the guest FPU
+	 * context.
 	 *
 	 * Note that while the PKRU state lives inside the fpu registers,
 	 * it is switched out separately at VMENTER and VMEXIT time. The
 	 * "guest_fpu" state here contains the guest FPU context, with the
 	 * host PRKU bits.
 	 */
+	struct fpu *user_fpu;
 	struct fpu *guest_fpu;
 
 	u64 xcr0;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8f72526e2f68..24843cf49579 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3466,7 +3466,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 		/*
 		 * Currently, fast page fault only works for direct mapping
 		 * since the gfn is not stable for indirect shadow page. See
-		 * Documentation/virtual/kvm/locking.txt to get more detail.
+		 * Documentation/virt/kvm/locking.txt to get more detail.
 		 */
 		fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
 							iterator.sptep, spte,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 19f69df96758..7eafc6907861 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2143,12 +2143,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto out;
 	}
 
+	svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						     GFP_KERNEL_ACCOUNT);
+	if (!svm->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_svm;
+	}
+
 	svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
 						     GFP_KERNEL_ACCOUNT);
 	if (!svm->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
-		goto free_partial_svm;
+		goto free_user_fpu;
 	}
 
 	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
@@ -2211,6 +2219,8 @@ uninit:
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
 	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
 free_partial_svm:
 	kmem_cache_free(kvm_vcpu_cache, svm);
 out:
@@ -2241,6 +2251,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
 	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
 }
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0f1378789bd0..ced9fba32598 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -220,6 +220,8 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
 		return;
 
+	kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+
 	vmx->nested.vmxon = false;
 	vmx->nested.smm.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
@@ -232,7 +234,9 @@ static void free_nested(struct kvm_vcpu *vcpu)
 		vmx->vmcs01.shadow_vmcs = NULL;
 	}
 	kfree(vmx->nested.cached_vmcs12);
+	vmx->nested.cached_vmcs12 = NULL;
 	kfree(vmx->nested.cached_shadow_vmcs12);
+	vmx->nested.cached_shadow_vmcs12 = NULL;
 	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		kvm_release_page_dirty(vmx->nested.apic_access_page);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a279447eb75b..074385c86c09 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6598,6 +6598,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
 	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 }
@@ -6613,12 +6614,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
+	vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+			GFP_KERNEL_ACCOUNT);
+	if (!vmx->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_vcpu;
+	}
+
 	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
 			GFP_KERNEL_ACCOUNT);
 	if (!vmx->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
-		goto free_partial_vcpu;
+		goto free_user_fpu;
 	}
 
 	vmx->vpid = allocate_vpid();
@@ -6721,6 +6730,8 @@ uninit_vcpu:
 free_vcpu:
 	free_vpid(vmx->vpid);
 	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
 free_partial_vcpu:
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 	return ERR_PTR(err);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 58305cf81182..c6d951cbd76c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3306,6 +3306,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -7202,7 +7206,7 @@ static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
 
 	rcu_read_unlock();
 
-	if (target)
+	if (target && READ_ONCE(target->ready))
 		kvm_vcpu_yield_to(target);
 }
 
@@ -7242,6 +7246,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	case KVM_HC_KICK_CPU:
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+		kvm_sched_yield(vcpu->kvm, a1);
 		ret = 0;
 		break;
 #ifdef CONFIG_X86_64
@@ -7990,9 +7995,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	trace_kvm_entry(vcpu->vcpu_id);
 	guest_enter_irqoff();
 
-	fpregs_assert_state_consistent();
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_return();
+	/* The preempt notifier should have taken care of the FPU already.  */
+	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -8270,7 +8274,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(&current->thread.fpu);
+	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8287,7 +8291,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	fpregs_lock();
 
 	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
-	copy_kernel_to_fpregs(&current->thread.fpu.state);
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();
 	fpregs_unlock();