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

Pull x86 kvm fixes from Paolo Bonzini:

 - Avoid freeing stack-allocated node in kvm_async_pf_queue_task

 - Clear XSTATE_BV[i] in guest XSAVE state whenever XFD[i]=1

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  selftests: kvm: Verify TILELOADD actually #NM faults when XFD[18]=1
  selftests: kvm: try getting XFD and XSAVE state out of sync
  selftests: kvm: replace numbered sync points with actions
  x86/fpu: Clear XSTATE_BV[i] in guest XSAVE state whenever XFD[i]=1
  x86/kvm: Avoid freeing stack-allocated node in kvm_async_pf_queue_task

3 files changed, 54 insertions, 6 deletions

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index da233f20ae6f..608983806fd7 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -319,10 +319,29 @@ EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features);
 #ifdef CONFIG_X86_64
 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd)
 {
+	struct fpstate *fpstate = guest_fpu->fpstate;
+
 	fpregs_lock();
-	guest_fpu->fpstate->xfd = xfd;
-	if (guest_fpu->fpstate->in_use)
-		xfd_update_state(guest_fpu->fpstate);
+
+	/*
+	 * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the
+	 * save state to its initial configuration.  Likewise, KVM_GET_XSAVE does
+	 * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1.
+	 *
+	 * If the guest's FPU state is in hardware, just update XFD: the XSAVE
+	 * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1.
+	 *
+	 * If however the guest's FPU state is NOT resident in hardware, clear
+	 * disabled components in XSTATE_BV now, or a subsequent XRSTOR will
+	 * attempt to load disabled components and generate #NM _in the host_.
+	 */
+	if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD))
+		fpstate->regs.xsave.header.xfeatures &= ~xfd;
+
+	fpstate->xfd = xfd;
+	if (fpstate->in_use)
+		xfd_update_state(fpstate);
+
 	fpregs_unlock();
 }
 EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd);
@@ -431,6 +450,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
 		return -EINVAL;
 
 	/*
+	 * Disabled features must be in their initial state, otherwise XRSTOR
+	 * causes an exception.
+	 */
+	if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd))
+		return -EINVAL;
+
+	/*
 	 * Nullify @vpkru to preserve its current value if PKRU's bit isn't set
 	 * in the header.  KVM's odd ABI is to leave PKRU untouched in this
 	 * case (all other components are eventually re-initialized).
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index df78ddee0abb..37dc8465e0f5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -89,6 +89,7 @@ struct kvm_task_sleep_node {
 	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
+	bool dummy;
 };
 
 static struct kvm_task_sleep_head {
@@ -120,15 +121,26 @@ static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
 	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
-		/* dummy entry exist -> wake up was delivered ahead of PF */
-		hlist_del(&e->link);
+		struct kvm_task_sleep_node *dummy = NULL;
+
+		/*
+		 * The entry can either be a 'dummy' entry (which is put on the
+		 * list when wake-up happens ahead of APF handling completion)
+		 * or a token from another task which should not be touched.
+		 */
+		if (e->dummy) {
+			hlist_del(&e->link);
+			dummy = e;
+		}
+
 		raw_spin_unlock(&b->lock);
-		kfree(e);
+		kfree(dummy);
 		return false;
 	}
 
 	n->token = token;
 	n->cpu = smp_processor_id();
+	n->dummy = false;
 	init_swait_queue_head(&n->wq);
 	hlist_add_head(&n->link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -231,6 +243,7 @@ again:
 		}
 		dummy->token = token;
 		dummy->cpu = smp_processor_id();
+		dummy->dummy = true;
 		init_swait_queue_head(&dummy->wq);
 		hlist_add_head(&dummy->link, &b->list);
 		dummy = NULL;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ff8812f3a129..63afdb6bb078 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5807,9 +5807,18 @@ static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
+	union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region;
+
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
 		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
+	/*
+	 * For backwards compatibility, do not expect disabled features to be in
+	 * their initial state.  XSTATE_BV[i] must still be cleared whenever
+	 * XFD[i]=1, or XRSTOR would cause a #NM.
+	 */
+	xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd;
+
 	return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
 					      guest_xsave->region,
 					      kvm_caps.supported_xcr0,