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

Pull KVM fixes from Paolo Bonzini:

 - syzkaller NULL pointer dereference

 - TDP MMU performance issue with disabling dirty logging

 - 5.14 regression with SVM TSC scaling

 - indefinite stall on applying live patches

 - unstable selftest

 - memory leak from wrong copy-and-paste

 - missed PV TLB flush when racing with emulation

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: do not report a vCPU as preempted outside instruction boundaries
  KVM: x86: do not set st->preempted when going back to user space
  KVM: SVM: fix tsc scaling cache logic
  KVM: selftests: Make hyperv_clock selftest more stable
  KVM: x86/MMU: Zap non-leaf SPTEs when disabling dirty logging
  x86: drop bogus "cc" clobber from __try_cmpxchg_user_asm()
  KVM: x86/mmu: Check every prev_roots in __kvm_mmu_free_obsolete_roots()
  entry/kvm: Exit to user mode when TIF_NOTIFY_SIGNAL is set
  KVM: Don't null dereference ops->destroy

12 files changed, 113 insertions, 37 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 959d66b9be94..3a240a64ac68 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -653,6 +653,7 @@ struct kvm_vcpu_arch {
 	u64 ia32_misc_enable_msr;
 	u64 smbase;
 	u64 smi_count;
+	bool at_instruction_boundary;
 	bool tpr_access_reporting;
 	bool xsaves_enabled;
 	bool xfd_no_write_intercept;
@@ -1300,6 +1301,8 @@ struct kvm_vcpu_stat {
 	u64 nested_run;
 	u64 directed_yield_attempted;
 	u64 directed_yield_successful;
+	u64 preemption_reported;
+	u64 preemption_other;
 	u64 guest_mode;
 };
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 35f222aa66bf..913e593a3b45 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -439,7 +439,7 @@ do {									\
 		       [ptr] "+m" (*_ptr),				\
 		       [old] "+a" (__old)				\
 		     : [new] ltype (__new)				\
-		     : "memory", "cc");					\
+		     : "memory");					\
 	if (unlikely(__err))						\
 		goto label;						\
 	if (unlikely(!success))						\
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f4653688fa6d..e826ee9138fa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5179,7 +5179,7 @@ static void __kvm_mmu_free_obsolete_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 		roots_to_free |= KVM_MMU_ROOT_CURRENT;
 
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
-		if (is_obsolete_root(kvm, mmu->root.hpa))
+		if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa))
 			roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
 	}
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index 6d3b3e5a5533..ee4802d7b36c 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -146,6 +146,15 @@ static bool try_step_up(struct tdp_iter *iter)
 }
 
 /*
+ * Step the iterator back up a level in the paging structure. Should only be
+ * used when the iterator is below the root level.
+ */
+void tdp_iter_step_up(struct tdp_iter *iter)
+{
+	WARN_ON(!try_step_up(iter));
+}
+
+/*
  * Step to the next SPTE in a pre-order traversal of the paging structure.
  * To get to the next SPTE, the iterator either steps down towards the goal
  * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index f0af385c56e0..adfca0cf94d3 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -114,5 +114,6 @@ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
 		    int min_level, gfn_t next_last_level_gfn);
 void tdp_iter_next(struct tdp_iter *iter);
 void tdp_iter_restart(struct tdp_iter *iter);
+void tdp_iter_step_up(struct tdp_iter *iter);
 
 #endif /* __KVM_X86_MMU_TDP_ITER_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 841feaa48be5..7b9265d67131 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1742,12 +1742,12 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
 	struct tdp_iter iter;
+	int max_mapping_level;
 	kvm_pfn_t pfn;
 
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
-retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
 
@@ -1755,15 +1755,41 @@ retry:
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
+		/*
+		 * This is a leaf SPTE. Check if the PFN it maps can
+		 * be mapped at a higher level.
+		 */
 		pfn = spte_to_pfn(iter.old_spte);
-		if (kvm_is_reserved_pfn(pfn) ||
-		    iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn,
-							    pfn, PG_LEVEL_NUM))
+
+		if (kvm_is_reserved_pfn(pfn))
 			continue;
 
+		max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
+				iter.gfn, pfn, PG_LEVEL_NUM);
+
+		WARN_ON(max_mapping_level < iter.level);
+
+		/*
+		 * If this page is already mapped at the highest
+		 * viable level, there's nothing more to do.
+		 */
+		if (max_mapping_level == iter.level)
+			continue;
+
+		/*
+		 * The page can be remapped at a higher level, so step
+		 * up to zap the parent SPTE.
+		 */
+		while (max_mapping_level > iter.level)
+			tdp_iter_step_up(&iter);
+
 		/* Note, a successful atomic zap also does a remote TLB flush. */
-		if (tdp_mmu_zap_spte_atomic(kvm, &iter))
-			goto retry;
+		tdp_mmu_zap_spte_atomic(kvm, &iter);
+
+		/*
+		 * If the atomic zap fails, the iter will recurse back into
+		 * the same subtree to retry.
+		 */
 	}
 
 	rcu_read_unlock();
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index bed5e1692cef..3361258640a2 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -982,7 +982,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) {
 		WARN_ON(!svm->tsc_scaling_enabled);
 		vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
-		svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
+		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 	}
 
 	svm->nested.ctl.nested_cr3 = 0;
@@ -1387,7 +1387,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu)
 	vcpu->arch.tsc_scaling_ratio =
 		kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio,
 					       svm->tsc_ratio_msr);
-	svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
+	__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 }
 
 /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 200045f71df0..1dc02cdf6960 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -465,11 +465,24 @@ static int has_svm(void)
 	return 1;
 }
 
+void __svm_write_tsc_multiplier(u64 multiplier)
+{
+	preempt_disable();
+
+	if (multiplier == __this_cpu_read(current_tsc_ratio))
+		goto out;
+
+	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+	__this_cpu_write(current_tsc_ratio, multiplier);
+out:
+	preempt_enable();
+}
+
 static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
 	if (tsc_scaling)
-		wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
+		__svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
 
 	cpu_svm_disable();
 
@@ -515,8 +528,7 @@ static int svm_hardware_enable(void)
 		 * Set the default value, even if we don't use TSC scaling
 		 * to avoid having stale value in the msr
 		 */
-		wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
-		__this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT);
+		__svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
 	}
 
 
@@ -999,11 +1011,12 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
+static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
 {
-	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+	__svm_write_tsc_multiplier(multiplier);
 }
 
+
 /* Evaluate instruction intercepts that depend on guest CPUID features. */
 static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
 					      struct vcpu_svm *svm)
@@ -1363,13 +1376,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		sev_es_prepare_switch_to_guest(hostsa);
 	}
 
-	if (tsc_scaling) {
-		u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio;
-		if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
-			__this_cpu_write(current_tsc_ratio, tsc_ratio);
-			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
-		}
-	}
+	if (tsc_scaling)
+		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
 	if (likely(tsc_aux_uret_slot >= 0))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
@@ -4255,6 +4263,8 @@ out:
 
 static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {
+	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR)
+		vcpu->arch.at_instruction_boundary = true;
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 21c5460e947a..500348c1cb35 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -590,7 +590,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
 void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu);
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier);
+void __svm_write_tsc_multiplier(u64 multiplier);
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
 				       struct vmcb_control_area *control);
 void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a07e8cd753ec..9bd86ecccdab 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6547,6 +6547,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 		return;
 
 	handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
+	vcpu->arch.at_instruction_boundary = true;
 }
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e9473c7c7390..03fbfbbec460 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -296,6 +296,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, nested_run),
 	STATS_DESC_COUNTER(VCPU, directed_yield_attempted),
 	STATS_DESC_COUNTER(VCPU, directed_yield_successful),
+	STATS_DESC_COUNTER(VCPU, preemption_reported),
+	STATS_DESC_COUNTER(VCPU, preemption_other),
 	STATS_DESC_ICOUNTER(VCPU, guest_mode)
 };
 
@@ -4625,6 +4627,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	struct kvm_memslots *slots;
 	static const u8 preempted = KVM_VCPU_PREEMPTED;
 
+	/*
+	 * The vCPU can be marked preempted if and only if the VM-Exit was on
+	 * an instruction boundary and will not trigger guest emulation of any
+	 * kind (see vcpu_run).  Vendor specific code controls (conservatively)
+	 * when this is true, for example allowing the vCPU to be marked
+	 * preempted if and only if the VM-Exit was due to a host interrupt.
+	 */
+	if (!vcpu->arch.at_instruction_boundary) {
+		vcpu->stat.preemption_other++;
+		return;
+	}
+
+	vcpu->stat.preemption_reported++;
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -4654,19 +4669,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
-	if (vcpu->preempted && !vcpu->arch.guest_state_protected)
-		vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
+	if (vcpu->preempted) {
+		if (!vcpu->arch.guest_state_protected)
+			vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
 
-	/*
-	 * Take the srcu lock as memslots will be accessed to check the gfn
-	 * cache generation against the memslots generation.
-	 */
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvm_xen_msr_enabled(vcpu->kvm))
-		kvm_xen_runstate_set_preempted(vcpu);
-	else
-		kvm_steal_time_set_preempted(vcpu);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		/*
+		 * Take the srcu lock as memslots will be accessed to check the gfn
+		 * cache generation against the memslots generation.
+		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		if (kvm_xen_msr_enabled(vcpu->kvm))
+			kvm_xen_runstate_set_preempted(vcpu);
+		else
+			kvm_steal_time_set_preempted(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	}
 
 	static_call(kvm_x86_vcpu_put)(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
@@ -10422,6 +10439,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
+		/*
+		 * If another guest vCPU requests a PV TLB flush in the middle
+		 * of instruction emulation, the rest of the emulation could
+		 * use a stale page translation. Assume that any code after
+		 * this point can start executing an instruction.
+		 */
+		vcpu->arch.at_instruction_boundary = false;
 		if (kvm_vcpu_running(vcpu)) {
 			r = vcpu_enter_guest(vcpu);
 		} else {
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index ee5c4ae0755c..532a535a9e99 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -159,8 +159,10 @@ static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu)
 	 * behalf of the vCPU. Only if the VMM does actually block
 	 * does it need to enter RUNSTATE_blocked.
 	 */
-	if (vcpu->preempted)
-		kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
+	if (WARN_ON_ONCE(!vcpu->preempted))
+		return;
+
+	kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
 }
 
 /* 32-bit compatibility definitions, also used natively in 32-bit build */