Merge tag 'tags/mute-led-rework' into for-next

ALSA: control - add generic LED API

This patchset tries to resolve the diversity in the audio LED
control among the ALSA drivers. A new control layer registration
is introduced which allows to run additional operations on
top of the elementary ALSA sound controls.

A new control access group (three bits in the access flags)
was introduced to carry the LED group information for
the sound controls. The low-level sound drivers can just
mark those controls using this access group. This information
is not exported to the user space, but user space can
manage the LED sound control associations through sysfs
(last patch) per Mark's request. It makes things fully
configurable in the kernel and user space (UCM).

The actual state ('route') evaluation is really easy
(the minimal value check for all channels / controls / cards).
If there's more complicated logic for a given hardware,
the card driver may eventually export a new read-only
sound control for the LED group and do the logic itself.

The new LED trigger control code is completely separated
and possibly optional (there's no symbol dependency).
The full code separation allows eventually to move this
LED trigger control to the user space in future.
Actually it replaces the already present functionality
in the kernel space (HDA drivers) and allows a quick adoption
for the recent hardware (ASoC codecs including SoundWire).

snd_ctl_led            24576  0

The sound driver implementation is really easy:

1) call snd_ctl_led_request() when control LED layer should be
   automatically activated
   / it calls module_request("snd-ctl-led") on demand /
2) mark all related kcontrols with
        SNDRV_CTL_ELEM_ACCESS_SPK_LED or
        SNDRV_CTL_ELEM_ACCESS_MIC_LED

Link: https://lore.kernel.org/r/20210317172945.842280-1-perex@perex.cz
Signed-off-by: Takashi Iwai <tiwai@suse.de>

10 files changed, 228 insertions, 108 deletions

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 58fa8c029867..f98370a39936 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -520,10 +520,10 @@ static u64 get_time_ref_counter(struct kvm *kvm)
 	u64 tsc;
 
 	/*
-	 * The guest has not set up the TSC page or the clock isn't
-	 * stable, fall back to get_kvmclock_ns.
+	 * Fall back to get_kvmclock_ns() when TSC page hasn't been set up,
+	 * is broken, disabled or being updated.
 	 */
-	if (!hv->tsc_ref.tsc_sequence)
+	if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET)
 		return div_u64(get_kvmclock_ns(kvm), 100);
 
 	vcpu = kvm_get_vcpu(kvm, 0);
@@ -1077,6 +1077,21 @@ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock,
 	return true;
 }
 
+/*
+ * Don't touch TSC page values if the guest has opted for TSC emulation after
+ * migration. KVM doesn't fully support reenlightenment notifications and TSC
+ * access emulation and Hyper-V is known to expect the values in TSC page to
+ * stay constant before TSC access emulation is disabled from guest side
+ * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC
+ * frequency and guest visible TSC value across migration (and prevent it when
+ * TSC scaling is unsupported).
+ */
+static inline bool tsc_page_update_unsafe(struct kvm_hv *hv)
+{
+	return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) &&
+		hv->hv_tsc_emulation_control;
+}
+
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock)
 {
@@ -1087,7 +1102,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
 	BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
 
-	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
 		return;
 
 	mutex_lock(&hv->hv_lock);
@@ -1101,7 +1117,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	 */
 	if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn),
 				    &tsc_seq, sizeof(tsc_seq))))
+		goto out_err;
+
+	if (tsc_seq && tsc_page_update_unsafe(hv)) {
+		if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
+			goto out_err;
+
+		hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
 		goto out_unlock;
+	}
 
 	/*
 	 * While we're computing and writing the parameters, force the
@@ -1110,15 +1134,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	hv->tsc_ref.tsc_sequence = 0;
 	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
 			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
-		goto out_unlock;
+		goto out_err;
 
 	if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref))
-		goto out_unlock;
+		goto out_err;
 
 	/* Ensure sequence is zero before writing the rest of the struct.  */
 	smp_wmb();
 	if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
-		goto out_unlock;
+		goto out_err;
 
 	/*
 	 * Now switch to the TSC page mechanism by writing the sequence.
@@ -1131,8 +1155,45 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	smp_wmb();
 
 	hv->tsc_ref.tsc_sequence = tsc_seq;
-	kvm_write_guest(kvm, gfn_to_gpa(gfn),
-			&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+		goto out_err;
+
+	hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+	goto out_unlock;
+
+out_err:
+	hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+out_unlock:
+	mutex_unlock(&hv->hv_lock);
+}
+
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
+{
+	struct kvm_hv *hv = to_kvm_hv(kvm);
+	u64 gfn;
+
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
+	    tsc_page_update_unsafe(hv))
+		return;
+
+	mutex_lock(&hv->hv_lock);
+
+	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+		goto out_unlock;
+
+	/* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET)
+		hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING;
+
+	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+
+	hv->tsc_ref.tsc_sequence = 0;
+	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+		hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+
 out_unlock:
 	mutex_unlock(&hv->hv_lock);
 }
@@ -1193,8 +1254,15 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 	}
 	case HV_X64_MSR_REFERENCE_TSC:
 		hv->hv_tsc_page = data;
-		if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)
+		if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) {
+			if (!host)
+				hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED;
+			else
+				hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+		} else {
+			hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET;
+		}
 		break;
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 		return kvm_hv_msr_set_crash_data(kvm,
@@ -1229,6 +1297,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 		hv->hv_tsc_emulation_control = data;
 		break;
 	case HV_X64_MSR_TSC_EMULATION_STATUS:
+		if (data && !host)
+			return 1;
+
 		hv->hv_tsc_emulation_status = data;
 		break;
 	case HV_X64_MSR_TIME_REF_COUNT:
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index e951af1fcb2c..60547d5cb6d7 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -133,6 +133,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
 
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm);
 
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 45d40bfacb7c..cc369b9ad8f1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1642,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
-		kvm_wait_lapic_expire(vcpu);
+		/*
+		 * Ensure the guest's timer has truly expired before posting an
+		 * interrupt.  Open code the relevant checks to avoid querying
+		 * lapic_timer_int_injected(), which will be false since the
+		 * interrupt isn't yet injected.  Waiting until after injecting
+		 * is not an option since that won't help a posted interrupt.
+		 */
+		if (vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+		    vcpu->arch.apic->lapic_timer.timer_advance_ns)
+			__kvm_wait_lapic_expire(vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;
 	}
@@ -2595,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic->lapic_timer.expired_tscdeadline = 0;
 	apic_update_lvtt(apic);
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index ec4fc28b325a..1f6f98c76bdf 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -78,6 +78,11 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
 	return to_shadow_page(__pa(sptep));
 }
 
+static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
+{
+	return sp->role.smm ? 1 : 0;
+}
+
 static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
 {
 	/*
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index e5f148106e20..b3ed302c1a35 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -21,6 +21,21 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
 }
 
 /*
+ * Return the TDP iterator to the root PT and allow it to continue its
+ * traversal over the paging structure from there.
+ */
+void tdp_iter_restart(struct tdp_iter *iter)
+{
+	iter->yielded_gfn = iter->next_last_level_gfn;
+	iter->level = iter->root_level;
+
+	iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+	tdp_iter_refresh_sptep(iter);
+
+	iter->valid = true;
+}
+
+/*
  * Sets a TDP iterator to walk a pre-order traversal of the paging structure
  * rooted at root_pt, starting with the walk to translate next_last_level_gfn.
  */
@@ -31,16 +46,12 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
 	WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
 
 	iter->next_last_level_gfn = next_last_level_gfn;
-	iter->yielded_gfn = iter->next_last_level_gfn;
 	iter->root_level = root_level;
 	iter->min_level = min_level;
-	iter->level = root_level;
-	iter->pt_path[iter->level - 1] = (tdp_ptep_t)root_pt;
-
-	iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
-	tdp_iter_refresh_sptep(iter);
+	iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt;
+	iter->as_id = kvm_mmu_page_as_id(sptep_to_sp(root_pt));
 
-	iter->valid = true;
+	tdp_iter_restart(iter);
 }
 
 /*
@@ -159,8 +170,3 @@ void tdp_iter_next(struct tdp_iter *iter)
 	iter->valid = false;
 }
 
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter)
-{
-	return iter->pt_path[iter->root_level - 1];
-}
-
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 4cc177d75c4a..b1748b988d3a 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -36,6 +36,8 @@ struct tdp_iter {
 	int min_level;
 	/* The iterator's current level within the paging structure */
 	int level;
+	/* The address space ID, i.e. SMM vs. regular. */
+	int as_id;
 	/* A snapshot of the value at sptep */
 	u64 old_spte;
 	/*
@@ -62,6 +64,6 @@ tdp_ptep_t spte_to_child_pt(u64 pte, int level);
 void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
 		    int min_level, gfn_t next_last_level_gfn);
 void tdp_iter_next(struct tdp_iter *iter);
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter);
+void tdp_iter_restart(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 c926c6b899a1..462b1f71c77f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -203,11 +203,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 				u64 old_spte, u64 new_spte, int level,
 				bool shared);
 
-static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
-{
-	return sp->role.smm ? 1 : 0;
-}
-
 static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
 {
 	bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
@@ -301,11 +296,16 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
  *
  * Given a page table that has been removed from the TDP paging structure,
  * iterates through the page table to clear SPTEs and free child page tables.
+ *
+ * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU
+ * protection. Since this thread removed it from the paging structure,
+ * this thread will be responsible for ensuring the page is freed. Hence the
+ * early rcu_dereferences in the function.
  */
-static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
+static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 					bool shared)
 {
-	struct kvm_mmu_page *sp = sptep_to_sp(pt);
+	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
 	int level = sp->role.level;
 	gfn_t base_gfn = sp->gfn;
 	u64 old_child_spte;
@@ -318,7 +318,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = pt + i;
+		sptep = rcu_dereference(pt) + i;
 		gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1));
 
 		if (shared) {
@@ -337,7 +337,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
 				cpu_relax();
 			}
 		} else {
+			/*
+			 * If the SPTE is not MMU-present, there is no backing
+			 * page associated with the SPTE and so no side effects
+			 * that need to be recorded, and exclusive ownership of
+			 * mmu_lock ensures the SPTE can't be made present.
+			 * Note, zapping MMIO SPTEs is also unnecessary as they
+			 * are guarded by the memslots generation, not by being
+			 * unreachable.
+			 */
 			old_child_spte = READ_ONCE(*sptep);
+			if (!is_shadow_present_pte(old_child_spte))
+				continue;
 
 			/*
 			 * Marking the SPTE as a removed SPTE is not
@@ -481,10 +492,6 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
 					   struct tdp_iter *iter,
 					   u64 new_spte)
 {
-	u64 *root_pt = tdp_iter_root_pt(iter);
-	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
-	int as_id = kvm_mmu_page_as_id(root);
-
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	/*
@@ -498,8 +505,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
 		      new_spte) != iter->old_spte)
 		return false;
 
-	handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
-			    iter->level, true);
+	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+			    new_spte, iter->level, true);
 
 	return true;
 }
@@ -527,7 +534,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	 * here since the SPTE is going from non-present
 	 * to non-present.
 	 */
-	WRITE_ONCE(*iter->sptep, 0);
+	WRITE_ONCE(*rcu_dereference(iter->sptep), 0);
 
 	return true;
 }
@@ -553,10 +560,6 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				      u64 new_spte, bool record_acc_track,
 				      bool record_dirty_log)
 {
-	tdp_ptep_t root_pt = tdp_iter_root_pt(iter);
-	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
-	int as_id = kvm_mmu_page_as_id(root);
-
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	/*
@@ -570,13 +573,13 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 
 	WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
 
-	__handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
-			      iter->level, false);
+	__handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+			      new_spte, iter->level, false);
 	if (record_acc_track)
 		handle_changed_spte_acc_track(iter->old_spte, new_spte,
 					      iter->level);
 	if (record_dirty_log)
-		handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+		handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn,
 					      iter->old_spte, new_spte,
 					      iter->level);
 }
@@ -648,9 +651,7 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
 
 		WARN_ON(iter->gfn > iter->next_last_level_gfn);
 
-		tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
-			       iter->root_level, iter->min_level,
-			       iter->next_last_level_gfn);
+		tdp_iter_restart(iter);
 
 		return true;
 	}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index baee91c1e936..58a45bb139f8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -115,13 +115,6 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_INVALID,				.always = false },
 };
 
-/* enable NPT for AMD64 and X86 with PAE */
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-bool npt_enabled = true;
-#else
-bool npt_enabled;
-#endif
-
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * pause_filter_count: On processors that support Pause filtering(indicated
@@ -170,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444);
 static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
 module_param(pause_filter_count_max, ushort, 0444);
 
-/* allow nested paging (virtualized MMU) for all guests */
-static int npt = true;
-module_param(npt, int, S_IRUGO);
+/*
+ * Use nested page tables by default.  Note, NPT may get forced off by
+ * svm_hardware_setup() if it's unsupported by hardware or the host kernel.
+ */
+bool npt_enabled = true;
+module_param_named(npt, npt_enabled, bool, 0444);
 
 /* allow nested virtualization in KVM/SVM */
 static int nested = true;
@@ -988,10 +984,15 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	if (!boot_cpu_has(X86_FEATURE_NPT))
+	/*
+	 * KVM's MMU doesn't support using 2-level paging for itself, and thus
+	 * NPT isn't supported if the host is using 2-level paging since host
+	 * CR4 is unchanged on VMRUN.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
 		npt_enabled = false;
 
-	if (npt_enabled && !npt)
+	if (!boot_cpu_has(X86_FEATURE_NPT))
 		npt_enabled = false;
 
 	kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50810d471462..32cf8287d4a7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6580,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 	int i, nr_msrs;
 	struct perf_guest_switch_msr *msrs;
 
+	/* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */
 	msrs = perf_guest_get_msrs(&nr_msrs);
-
 	if (!msrs)
 		return;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2a20ce60152e..fe806e894212 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1526,35 +1526,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
 bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
 {
+	struct kvm_x86_msr_filter *msr_filter;
+	struct msr_bitmap_range *ranges;
 	struct kvm *kvm = vcpu->kvm;
-	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
-	u32 count = kvm->arch.msr_filter.count;
-	u32 i;
-	bool r = kvm->arch.msr_filter.default_allow;
+	bool allowed;
 	int idx;
+	u32 i;
 
-	/* MSR filtering not set up or x2APIC enabled, allow everything */
-	if (!count || (index >= 0x800 && index <= 0x8ff))
+	/* x2APIC MSRs do not support filtering. */
+	if (index >= 0x800 && index <= 0x8ff)
 		return true;
 
-	/* Prevent collision with set_msr_filter */
 	idx = srcu_read_lock(&kvm->srcu);
 
-	for (i = 0; i < count; i++) {
+	msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu);
+	if (!msr_filter) {
+		allowed = true;
+		goto out;
+	}
+
+	allowed = msr_filter->default_allow;
+	ranges = msr_filter->ranges;
+
+	for (i = 0; i < msr_filter->count; i++) {
 		u32 start = ranges[i].base;
 		u32 end = start + ranges[i].nmsrs;
 		u32 flags = ranges[i].flags;
 		unsigned long *bitmap = ranges[i].bitmap;
 
 		if ((index >= start) && (index < end) && (flags & type)) {
-			r = !!test_bit(index - start, bitmap);
+			allowed = !!test_bit(index - start, bitmap);
 			break;
 		}
 	}
 
+out:
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	return r;
+	return allowed;
 }
 EXPORT_SYMBOL_GPL(kvm_msr_allowed);
 
@@ -2551,6 +2560,8 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	struct kvm_arch *ka = &kvm->arch;
 
+	kvm_hv_invalidate_tsc_page(kvm);
+
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	kvm_make_mclock_inprogress_request(kvm);
 	/* no guest entries from this point */
@@ -5352,25 +5363,34 @@ split_irqchip_unlock:
 	return r;
 }
 
-static void kvm_clear_msr_filter(struct kvm *kvm)
+static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow)
+{
+	struct kvm_x86_msr_filter *msr_filter;
+
+	msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT);
+	if (!msr_filter)
+		return NULL;
+
+	msr_filter->default_allow = default_allow;
+	return msr_filter;
+}
+
+static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter)
 {
 	u32 i;
-	u32 count = kvm->arch.msr_filter.count;
-	struct msr_bitmap_range ranges[16];
 
-	mutex_lock(&kvm->lock);
-	kvm->arch.msr_filter.count = 0;
-	memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
-	mutex_unlock(&kvm->lock);
-	synchronize_srcu(&kvm->srcu);
+	if (!msr_filter)
+		return;
+
+	for (i = 0; i < msr_filter->count; i++)
+		kfree(msr_filter->ranges[i].bitmap);
 
-	for (i = 0; i < count; i++)
-		kfree(ranges[i].bitmap);
+	kfree(msr_filter);
 }
 
-static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
+			      struct kvm_msr_filter_range *user_range)
 {
-	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
 	struct msr_bitmap_range range;
 	unsigned long *bitmap = NULL;
 	size_t bitmap_size;
@@ -5404,11 +5424,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user
 		goto err;
 	}
 
-	/* Everything ok, add this range identifier to our global pool */
-	ranges[kvm->arch.msr_filter.count] = range;
-	/* Make sure we filled the array before we tell anyone to walk it */
-	smp_wmb();
-	kvm->arch.msr_filter.count++;
+	/* Everything ok, add this range identifier. */
+	msr_filter->ranges[msr_filter->count] = range;
+	msr_filter->count++;
 
 	return 0;
 err:
@@ -5419,10 +5437,11 @@ err:
 static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_msr_filter __user *user_msr_filter = argp;
+	struct kvm_x86_msr_filter *new_filter, *old_filter;
 	struct kvm_msr_filter filter;
 	bool default_allow;
-	int r = 0;
 	bool empty = true;
+	int r = 0;
 	u32 i;
 
 	if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
@@ -5435,25 +5454,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
 	if (empty && !default_allow)
 		return -EINVAL;
 
-	kvm_clear_msr_filter(kvm);
-
-	kvm->arch.msr_filter.default_allow = default_allow;
+	new_filter = kvm_alloc_msr_filter(default_allow);
+	if (!new_filter)
+		return -ENOMEM;
 
-	/*
-	 * Protect from concurrent calls to this function that could trigger
-	 * a TOCTOU violation on kvm->arch.msr_filter.count.
-	 */
-	mutex_lock(&kvm->lock);
 	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
-		r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
-		if (r)
-			break;
+		r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
+		if (r) {
+			kvm_free_msr_filter(new_filter);
+			return r;
+		}
 	}
 
+	mutex_lock(&kvm->lock);
+
+	/* The per-VM filter is protected by kvm->lock... */
+	old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1);
+
+	rcu_assign_pointer(kvm->arch.msr_filter, new_filter);
+	synchronize_srcu(&kvm->srcu);
+
+	kvm_free_msr_filter(old_filter);
+
 	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
 	mutex_unlock(&kvm->lock);
 
-	return r;
+	return 0;
 }
 
 long kvm_arch_vm_ioctl(struct file *filp,
@@ -6603,7 +6629,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 		int cpu = get_cpu();
 
 		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
-		smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
+		on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
 				wbinvd_ipi, NULL, 1);
 		put_cpu();
 		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
@@ -10601,7 +10627,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
-			return 0;
+			return NULL;
 
 		old_npages = slot->npages;
 		hva = slot->userspace_addr;
@@ -10634,8 +10660,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
-	u32 i;
-
 	if (current->mm == kvm->mm) {
 		/*
 		 * Free memory regions allocated on behalf of userspace,
@@ -10651,8 +10675,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	static_call_cond(kvm_x86_vm_destroy)(kvm);
-	for (i = 0; i < kvm->arch.msr_filter.count; i++)
-		kfree(kvm->arch.msr_filter.ranges[i].bitmap);
+	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);