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

Pull kvm fixes from Paolo Bonzini:
 "ARM64:

   - Fix constant sign extension affecting TCR_EL2 and preventing
     running on ARMv8.7 models due to spurious bits being set

   - Fix use of helpers using PSTATE early on exit by always sampling it
     as soon as the exit takes place

   - Move pkvm's 32bit handling into a common helper

  RISC-V:

   - Fix incorrect KVM_MAX_VCPUS value

   - Unmap stage2 mapping when deleting/moving a memslot

  x86:

   - Fix and downgrade BUG_ON due to uninitialized cache

   - Many APICv and MOVE_ENC_CONTEXT_FROM fixes

   - Correctly emulate TLB flushes around nested vmentry/vmexit and when
     the nested hypervisor uses VPID

   - Prevent modifications to CPUID after the VM has run

   - Other smaller bugfixes

  Generic:

   - Memslot handling bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (44 commits)
  KVM: fix avic_set_running for preemptable kernels
  KVM: VMX: clear vmx_x86_ops.sync_pir_to_irr if APICv is disabled
  KVM: SEV: accept signals in sev_lock_two_vms
  KVM: SEV: do not take kvm->lock when destroying
  KVM: SEV: Prohibit migration of a VM that has mirrors
  KVM: SEV: Do COPY_ENC_CONTEXT_FROM with both VMs locked
  selftests: sev_migrate_tests: add tests for KVM_CAP_VM_COPY_ENC_CONTEXT_FROM
  KVM: SEV: move mirror status to destination of KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
  KVM: SEV: initialize regions_list of a mirror VM
  KVM: SEV: cleanup locking for KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
  KVM: SEV: do not use list_replace_init on an empty list
  KVM: x86: Use a stable condition around all VT-d PI paths
  KVM: x86: check PIR even for vCPUs with disabled APICv
  KVM: VMX: prepare sync_pir_to_irr for running with APICv disabled
  KVM: selftests: page_table_test: fix calculation of guest_test_phys_mem
  KVM: x86/mmu: Handle "default" period when selectively waking kthread
  KVM: MMU: shadow nested paging does not have PKU
  KVM: x86/mmu: Remove spurious TLB flushes in TDP MMU zap collapsible path
  KVM: x86/mmu: Use yield-safe TDP MMU root iter in MMU notifier unmapping
  KVM: X86: Use vcpu->arch.walk_mmu for kvm_mmu_invlpg()
  ...

22 files changed, 329 insertions, 253 deletions

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index a39fcf318c77..01d47c5886dc 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -91,7 +91,7 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
-#define TCR_EL2_RES1		((1 << 31) | (1 << 23))
+#define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
 #define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
@@ -276,7 +276,7 @@
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
-#define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 7a0af1d39303..96c5f3fb7838 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -403,6 +403,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code);
+
 /*
  * Allow the hypervisor to handle the exit with an exit handler if it has one.
  *
@@ -429,6 +431,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
  */
 static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	/*
+	 * Save PSTATE early so that we can evaluate the vcpu mode
+	 * early on.
+	 */
+	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+
+	/*
+	 * Check whether we want to repaint the state one way or
+	 * another.
+	 */
+	early_exit_filter(vcpu, exit_code);
+
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index de7e14c862e6..7ecca8b07851 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
-	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
+	/*
+	 * Guest PSTATE gets saved at guest fixup time in all
+	 * cases. We still need to handle the nVHE host side here.
+	 */
+	if (!has_vhe() && ctxt->__hyp_running_vcpu)
+		ctxt->regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index c0e3fed26d93..d13115a12434 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -233,7 +233,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
  * Returns false if the guest ran in AArch32 when it shouldn't have, and
  * thus should exit to the host, or true if a the guest run loop can continue.
  */
-static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
@@ -248,10 +248,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
 		vcpu->arch.target = -1;
 		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
 		*exit_code |= ARM_EXCEPTION_IL;
-		return false;
 	}
-
-	return true;
 }
 
 /* Switch to the guest for legacy non-VHE systems */
@@ -316,9 +313,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
-		if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
-			break;
-
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 5a2cb5d9bc4b..fbb26b93c347 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -112,6 +112,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 	return hyp_exit_handlers;
 }
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 25ba21f98504..2639b9ee48f9 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -12,14 +12,12 @@
 #include <linux/types.h>
 #include <linux/kvm.h>
 #include <linux/kvm_types.h>
+#include <asm/csr.h>
 #include <asm/kvm_vcpu_fp.h>
 #include <asm/kvm_vcpu_timer.h>
 
-#ifdef CONFIG_64BIT
-#define KVM_MAX_VCPUS			(1U << 16)
-#else
-#define KVM_MAX_VCPUS			(1U << 9)
-#endif
+#define KVM_MAX_VCPUS			\
+	((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1)
 
 #define KVM_HALT_POLL_NS_DEFAULT	500000
 
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index d81bae8eb55e..fc058ff5f4b6 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -453,6 +453,12 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_unmap_range(kvm, gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index e66e620c3bed..539333ac4b38 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -81,7 +81,6 @@ struct kvm_ioapic {
 	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 650642b18d15..c2d7cfe82d00 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -56,7 +56,6 @@ struct kvm_pic {
 	struct kvm_io_device dev_master;
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_elcr;
-	void (*ack_notifier)(void *opaque, int irq);
 	unsigned long irq_states[PIC_NUM_PINS];
 };
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 759952dd1222..f206fc35deff 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
 {
 	int highest_irr;
-	if (apic->vcpu->arch.apicv_active)
+	if (kvm_x86_ops.sync_pir_to_irr)
 		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
 	else
 		highest_irr = apic_find_highest_irr(apic);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3be9beea838d..6354297e92ae 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 		flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp);
 
 	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
+		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
 
 	return flush;
 }
@@ -2173,10 +2173,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
 	iterator->shadow_addr = root;
 	iterator->level = vcpu->arch.mmu->shadow_root_level;
 
-	if (iterator->level == PT64_ROOT_4LEVEL &&
+	if (iterator->level >= PT64_ROOT_4LEVEL &&
 	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
 	    !vcpu->arch.mmu->direct_map)
-		--iterator->level;
+		iterator->level = PT32E_ROOT_LEVEL;
 
 	if (iterator->level == PT32E_ROOT_LEVEL) {
 		/*
@@ -4855,7 +4855,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	struct kvm_mmu_role_regs regs = {
 		.cr0 = cr0,
-		.cr4 = cr4,
+		.cr4 = cr4 & ~X86_CR4_PKE,
 		.efer = efer,
 	};
 	union kvm_mmu_role new_role;
@@ -4919,7 +4919,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->direct_map = false;
 
 	update_permission_bitmask(context, true);
-	update_pkru_bitmask(context);
+	context->pkru_mask = 0;
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
@@ -5025,6 +5025,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/*
 	 * Invalidate all MMU roles to force them to reinitialize as CPUID
 	 * information is factored into reserved bit calculations.
+	 *
+	 * Correctly handling multiple vCPU models with respect to paging and
+	 * physical address properties) in a single VM would require tracking
+	 * all relevant CPUID information in kvm_mmu_page_role. That is very
+	 * undesirable as it would increase the memory requirements for
+	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
+	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.mmu_role.ext.valid = 0;
 	vcpu->arch.guest_mmu.mmu_role.ext.valid = 0;
@@ -5032,24 +5040,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 
 	/*
-	 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
-	 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
-	 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
-	 * faults due to reusing SPs/SPTEs.  Alert userspace, but otherwise
-	 * sweep the problem under the rug.
-	 *
-	 * KVM's horrific CPUID ABI makes the problem all but impossible to
-	 * solve, as correctly handling multiple vCPU models (with respect to
-	 * paging and physical address properties) in a single VM would require
-	 * tracking all relevant CPUID information in kvm_mmu_page_role.  That
-	 * is very undesirable as it would double the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments), and in practice
-	 * no sane VMM mucks with the core vCPU model on the fly.
+	 * Changing guest CPUID after KVM_RUN is forbidden, see the comment in
+	 * kvm_arch_vcpu_ioctl().
 	 */
-	if (vcpu->arch.last_vmentry_cpu != -1) {
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n");
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n");
-	}
+	KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm);
 }
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -5369,7 +5363,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE);
+	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -5854,8 +5848,6 @@ restart:
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
 		/*
@@ -5863,17 +5855,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 		 * logging at a 4k granularity and never creates collapsible
 		 * 2m SPTEs during dirty logging.
 		 */
-		flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
-		if (flush)
+		if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true))
 			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
-		if (flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
 		read_unlock(&kvm->mmu_lock);
 	}
 }
@@ -6182,23 +6171,46 @@ void kvm_mmu_module_exit(void)
 	mmu_audit_disable();
 }
 
+/*
+ * Calculate the effective recovery period, accounting for '0' meaning "let KVM
+ * select a halving time of 1 hour".  Returns true if recovery is enabled.
+ */
+static bool calc_nx_huge_pages_recovery_period(uint *period)
+{
+	/*
+	 * Use READ_ONCE to get the params, this may be called outside of the
+	 * param setters, e.g. by the kthread to compute its next timeout.
+	 */
+	bool enabled = READ_ONCE(nx_huge_pages);
+	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+
+	if (!enabled || !ratio)
+		return false;
+
+	*period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	if (!*period) {
+		/* Make sure the period is not less than one second.  */
+		ratio = min(ratio, 3600u);
+		*period = 60 * 60 * 1000 / ratio;
+	}
+	return true;
+}
+
 static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp)
 {
 	bool was_recovery_enabled, is_recovery_enabled;
 	uint old_period, new_period;
 	int err;
 
-	was_recovery_enabled = nx_huge_pages_recovery_ratio;
-	old_period = nx_huge_pages_recovery_period_ms;
+	was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period);
 
 	err = param_set_uint(val, kp);
 	if (err)
 		return err;
 
-	is_recovery_enabled = nx_huge_pages_recovery_ratio;
-	new_period = nx_huge_pages_recovery_period_ms;
+	is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period);
 
-	if (READ_ONCE(nx_huge_pages) && is_recovery_enabled &&
+	if (is_recovery_enabled &&
 	    (!was_recovery_enabled || old_period > new_period)) {
 		struct kvm *kvm;
 
@@ -6262,18 +6274,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 
 static long get_nx_lpage_recovery_timeout(u64 start_time)
 {
-	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
-	uint period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	bool enabled;
+	uint period;
 
-	if (!period && ratio) {
-		/* Make sure the period is not less than one second.  */
-		ratio = min(ratio, 3600u);
-		period = 60 * 60 * 1000 / ratio;
-	}
+	enabled = calc_nx_huge_pages_recovery_period(&period);
 
-	return READ_ONCE(nx_huge_pages) && ratio
-		? start_time + msecs_to_jiffies(period) - get_jiffies_64()
-		: MAX_SCHEDULE_TIMEOUT;
+	return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64()
+		       : MAX_SCHEDULE_TIMEOUT;
 }
 
 static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index a54c3491af42..1db8496259ad 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t 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;
-	u64 *sptep;
-	gfn_t gfn;
 	int i;
 
 	trace_kvm_mmu_prepare_zap_page(sp);
@@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = rcu_dereference(pt) + i;
-		gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 *sptep = rcu_dereference(pt) + i;
+		gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 old_child_spte;
 
 		if (shared) {
 			/*
@@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 				    shared);
 	}
 
-	kvm_flush_remote_tlbs_with_address(kvm, gfn,
+	kvm_flush_remote_tlbs_with_address(kvm, base_gfn,
 					   KVM_PAGES_PER_HPAGE(level + 1));
 
 	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
@@ -1033,9 +1031,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root(kvm, root, range->slot->as_id)
-		flush |= zap_gfn_range(kvm, root, range->start, range->end,
-				       range->may_block, flush, false);
+	for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
+		flush = zap_gfn_range(kvm, root, range->start, range->end,
+				      range->may_block, flush, false);
 
 	return flush;
 }
@@ -1364,10 +1362,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
  * Clear leaf entries which could be replaced by large mappings, for
  * GFNs within the slot.
  */
-static bool zap_collapsible_spte_range(struct kvm *kvm,
+static void zap_collapsible_spte_range(struct kvm *kvm,
 				       struct kvm_mmu_page *root,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+				       const struct kvm_memory_slot *slot)
 {
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
@@ -1378,10 +1375,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
-			flush = false;
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
-		}
 
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
@@ -1393,6 +1388,7 @@ retry:
 							    pfn, PG_LEVEL_NUM))
 			continue;
 
+		/* Note, a successful atomic zap also does a remote TLB flush. */
 		if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) {
 			/*
 			 * The iter must explicitly re-read the SPTE because
@@ -1401,30 +1397,24 @@ retry:
 			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
 			goto retry;
 		}
-		flush = true;
 	}
 
 	rcu_read_unlock();
-
-	return flush;
 }
 
 /*
  * Clear non-leaf entries (and free associated page tables) which could
  * be replaced by large mappings, for GFNs within the slot.
  */
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot)
 {
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
-		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
-
-	return flush;
+		zap_collapsible_spte_range(kvm, root, slot);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 476b133544dd..3899004a5d91 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				       struct kvm_memory_slot *slot,
 				       gfn_t gfn, unsigned long mask,
 				       bool wrprot);
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush);
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot);
 
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index affc0ea98d30..9d6066eb7c10 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -989,16 +989,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int cpu = get_cpu();
 
+	WARN_ON(cpu != vcpu->cpu);
 	svm->avic_is_running = is_run;
 
-	if (!kvm_vcpu_apicv_active(vcpu))
-		return;
-
-	if (is_run)
-		avic_vcpu_load(vcpu, vcpu->cpu);
-	else
-		avic_vcpu_put(vcpu);
+	if (kvm_vcpu_apicv_active(vcpu)) {
+		if (is_run)
+			avic_vcpu_load(vcpu, cpu);
+		else
+			avic_vcpu_put(vcpu);
+	}
+	put_cpu();
 }
 
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 21ac0a5de4e0..59727a966f90 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1543,28 +1543,50 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 	return false;
 }
 
-static int sev_lock_for_migration(struct kvm *kvm)
+static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+	int r = -EBUSY;
+
+	if (dst_kvm == src_kvm)
+		return -EINVAL;
 
 	/*
-	 * Bail if this VM is already involved in a migration to avoid deadlock
-	 * between two VMs trying to migrate to/from each other.
+	 * Bail if these VMs are already involved in a migration to avoid
+	 * deadlock between two VMs trying to migrate to/from each other.
 	 */
-	if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1))
+	if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1))
 		return -EBUSY;
 
-	mutex_lock(&kvm->lock);
+	if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1))
+		goto release_dst;
 
+	r = -EINTR;
+	if (mutex_lock_killable(&dst_kvm->lock))
+		goto release_src;
+	if (mutex_lock_killable(&src_kvm->lock))
+		goto unlock_dst;
 	return 0;
+
+unlock_dst:
+	mutex_unlock(&dst_kvm->lock);
+release_src:
+	atomic_set_release(&src_sev->migration_in_progress, 0);
+release_dst:
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	return r;
 }
 
-static void sev_unlock_after_migration(struct kvm *kvm)
+static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
 
-	mutex_unlock(&kvm->lock);
-	atomic_set_release(&sev->migration_in_progress, 0);
+	mutex_unlock(&dst_kvm->lock);
+	mutex_unlock(&src_kvm->lock);
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	atomic_set_release(&src_sev->migration_in_progress, 0);
 }
 
 
@@ -1607,14 +1629,15 @@ static void sev_migrate_from(struct kvm_sev_info *dst,
 	dst->asid = src->asid;
 	dst->handle = src->handle;
 	dst->pages_locked = src->pages_locked;
+	dst->enc_context_owner = src->enc_context_owner;
 
 	src->asid = 0;
 	src->active = false;
 	src->handle = 0;
 	src->pages_locked = 0;
+	src->enc_context_owner = NULL;
 
-	INIT_LIST_HEAD(&dst->regions_list);
-	list_replace_init(&src->regions_list, &dst->regions_list);
+	list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list);
 }
 
 static int sev_es_migrate_from(struct kvm *dst, struct kvm *src)
@@ -1666,15 +1689,6 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
 	bool charged = false;
 	int ret;
 
-	ret = sev_lock_for_migration(kvm);
-	if (ret)
-		return ret;
-
-	if (sev_guest(kvm)) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
@@ -1682,16 +1696,26 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	ret = sev_lock_for_migration(source_kvm);
+	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto out_fput;
 
-	if (!sev_guest(source_kvm)) {
+	if (sev_guest(kvm) || !sev_guest(source_kvm)) {
 		ret = -EINVAL;
-		goto out_source;
+		goto out_unlock;
 	}
 
 	src_sev = &to_kvm_svm(source_kvm)->sev_info;
+
+	/*
+	 * VMs mirroring src's encryption context rely on it to keep the
+	 * ASID allocated, but below we are clearing src_sev->asid.
+	 */
+	if (src_sev->num_mirrored_vms) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
 	dst_sev->misc_cg = get_current_misc_cg();
 	cg_cleanup_sev = dst_sev;
 	if (dst_sev->misc_cg != src_sev->misc_cg) {
@@ -1728,13 +1752,11 @@ out_dst_cgroup:
 		sev_misc_cg_uncharge(cg_cleanup_sev);
 	put_misc_cg(cg_cleanup_sev->misc_cg);
 	cg_cleanup_sev->misc_cg = NULL;
-out_source:
-	sev_unlock_after_migration(source_kvm);
+out_unlock:
+	sev_unlock_two_vms(kvm, source_kvm);
 out_fput:
 	if (source_kvm_file)
 		fput(source_kvm_file);
-out_unlock:
-	sev_unlock_after_migration(kvm);
 	return ret;
 }
 
@@ -1953,76 +1975,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info source_sev, *mirror_sev;
+	struct kvm_sev_info *source_sev, *mirror_sev;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
-		goto e_source_put;
+		goto e_source_fput;
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	mutex_lock(&source_kvm->lock);
-
-	if (!sev_guest(source_kvm)) {
-		ret = -EINVAL;
-		goto e_source_unlock;
-	}
+	ret = sev_lock_two_vms(kvm, source_kvm);
+	if (ret)
+		goto e_source_fput;
 
-	/* Mirrors of mirrors should work, but let's not get silly */
-	if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) {
+	/*
+	 * Mirrors of mirrors should work, but let's not get silly.  Also
+	 * disallow out-of-band SEV/SEV-ES init if the target is already an
+	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
+	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 */
+	if (sev_guest(kvm) || !sev_guest(source_kvm) ||
+	    is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
-		goto e_source_unlock;
+		goto e_unlock;
 	}
 
-	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
-	       sizeof(source_sev));
-
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
 	 * disappear until we're done with it
 	 */
+	source_sev = &to_kvm_svm(source_kvm)->sev_info;
 	kvm_get_kvm(source_kvm);
-
-	fput(source_kvm_file);
-	mutex_unlock(&source_kvm->lock);
-	mutex_lock(&kvm->lock);
-
-	/*
-	 * Disallow out-of-band SEV/SEV-ES init if the target is already an
-	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
-	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
-	 */
-	if (sev_guest(kvm) || kvm->created_vcpus) {
-		ret = -EINVAL;
-		goto e_mirror_unlock;
-	}
+	source_sev->num_mirrored_vms++;
 
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
 	mirror_sev->active = true;
-	mirror_sev->asid = source_sev.asid;
-	mirror_sev->fd = source_sev.fd;
-	mirror_sev->es_active = source_sev.es_active;
-	mirror_sev->handle = source_sev.handle;
+	mirror_sev->asid = source_sev->asid;
+	mirror_sev->fd = source_sev->fd;
+	mirror_sev->es_active = source_sev->es_active;
+	mirror_sev->handle = source_sev->handle;
+	INIT_LIST_HEAD(&mirror_sev->regions_list);
+	ret = 0;
+
 	/*
 	 * Do not copy ap_jump_table. Since the mirror does not share the same
 	 * KVM contexts as the original, and they may have different
 	 * memory-views.
 	 */
 
-	mutex_unlock(&kvm->lock);
-	return 0;
-
-e_mirror_unlock:
-	mutex_unlock(&kvm->lock);
-	kvm_put_kvm(source_kvm);
-	return ret;
-e_source_unlock:
-	mutex_unlock(&source_kvm->lock);
-e_source_put:
+e_unlock:
+	sev_unlock_two_vms(kvm, source_kvm);
+e_source_fput:
 	if (source_kvm_file)
 		fput(source_kvm_file);
 	return ret;
@@ -2034,17 +2040,24 @@ void sev_vm_destroy(struct kvm *kvm)
 	struct list_head *head = &sev->regions_list;
 	struct list_head *pos, *q;
 
+	WARN_ON(sev->num_mirrored_vms);
+
 	if (!sev_guest(kvm))
 		return;
 
 	/* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
 	if (is_mirroring_enc_context(kvm)) {
-		kvm_put_kvm(sev->enc_context_owner);
+		struct kvm *owner_kvm = sev->enc_context_owner;
+		struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info;
+
+		mutex_lock(&owner_kvm->lock);
+		if (!WARN_ON(!owner_sev->num_mirrored_vms))
+			owner_sev->num_mirrored_vms--;
+		mutex_unlock(&owner_kvm->lock);
+		kvm_put_kvm(owner_kvm);
 		return;
 	}
 
-	mutex_lock(&kvm->lock);
-
 	/*
 	 * Ensure that all guest tagged cache entries are flushed before
 	 * releasing the pages back to the system for use. CLFLUSH will
@@ -2064,8 +2077,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	mutex_unlock(&kvm->lock);
-
 	sev_unbind_asid(kvm, sev->handle);
 	sev_asid_free(sev);
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5630c241d5f6..d0f68d11ec70 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4651,7 +4651,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_irr_update = svm_hwapic_irr_update,
 	.hwapic_isr_update = svm_hwapic_isr_update,
-	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
 	.apicv_post_state_restore = avic_post_state_restore,
 
 	.set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5faad3dc10e2..1c7306c370fa 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -79,6 +79,7 @@ struct kvm_sev_info {
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 	struct kvm *enc_context_owner; /* Owner of copied encryption context */
+	unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
 	atomic_t migration_in_progress;
 };
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 1e2f66951566..64f2828035c2 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1162,29 +1162,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	WARN_ON(!enable_vpid);
 
 	/*
-	 * If VPID is enabled and used by vmc12, but L2 does not have a unique
-	 * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate
-	 * a VPID for L2, flush the current context as the effective ASID is
-	 * common to both L1 and L2.
-	 *
-	 * Defer the flush so that it runs after vmcs02.EPTP has been set by
-	 * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid
-	 * redundant flushes further down the nested pipeline.
-	 *
-	 * If a TLB flush isn't required due to any of the above, and vpid12 is
-	 * changing then the new "virtual" VPID (vpid12) will reuse the same
-	 * "real" VPID (vpid02), and so needs to be flushed.  There's no direct
-	 * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for
-	 * all nested vCPUs.  Remember, a flush on VM-Enter does not invalidate
-	 * guest-physical mappings, so there is no need to sync the nEPT MMU.
+	 * VPID is enabled and in use by vmcs12.  If vpid12 is changing, then
+	 * emulate a guest TLB flush as KVM does not track vpid12 history nor
+	 * is the VPID incorporated into the MMU context.  I.e. KVM must assume
+	 * that the new vpid12 has never been used and thus represents a new
+	 * guest ASID that cannot have entries in the TLB.
 	 */
-	if (!nested_has_guest_tlb_tag(vcpu)) {
-		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-	} else if (is_vmenter &&
-		   vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+	if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
 		vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+		return;
 	}
+
+	/*
+	 * If VPID is enabled, used by vmc12, and vpid12 is not changing but
+	 * does not have a unique TLB tag (ASID), i.e. EPT is disabled and
+	 * KVM was unable to allocate a VPID for L2, flush the current context
+	 * as the effective ASID is common to both L1 and L2.
+	 */
+	if (!nested_has_guest_tlb_tag(vcpu))
+		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 }
 
 static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
@@ -3344,8 +3341,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	};
 	u32 failed_index;
 
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
 		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
@@ -4502,9 +4498,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		(void)nested_get_evmcs_page(vcpu);
 	}
 
-	/* Service the TLB flush request for L2 before switching to L1. */
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	/* Service pending TLB flush requests for L2 before switching to L1. */
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	/*
 	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
@@ -4857,6 +4852,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.cached_vmcs12)
 		goto out_cached_vmcs12;
 
+	vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA;
 	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
 	if (!vmx->nested.cached_shadow_vmcs12)
 		goto out_cached_shadow_vmcs12;
@@ -5289,8 +5285,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
 		struct vmcs_hdr hdr;
 
-		if (ghc->gpa != vmptr &&
-		    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
 			/*
 			 * Reads from an unbacked page return all 1s,
 			 * which means that the 32 bits located at the
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 5f81ef092bd4..1c94783b5a54 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 
 #include "lapic.h"
+#include "irq.h"
 #include "posted_intr.h"
 #include "trace.h"
 #include "vmx.h"
@@ -77,13 +78,18 @@ after_clear_sn:
 		pi_set_on(pi_desc);
 }
 
+static bool vmx_can_use_vtd_pi(struct kvm *kvm)
+{
+	return irqchip_in_kernel(kvm) && enable_apicv &&
+		kvm_arch_has_assigned_device(kvm) &&
+		irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return 0;
 
 	WARN_ON(irqs_disabled());
@@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 	struct vcpu_data vcpu_info;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP) ||
-	    !kvm_vcpu_apicv_active(kvm->vcpus[0]))
+	if (!vmx_can_use_vtd_pi(kvm))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ba66c171d951..f90448809690 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2918,6 +2918,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return nested_get_vpid02(vcpu);
+	return to_vmx(vcpu)->vpid;
+}
+
 static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
@@ -2930,31 +2937,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 	if (enable_ept)
 		ept_sync_context(construct_eptp(vcpu, root_hpa,
 						mmu->shadow_root_level));
-	else if (!is_guest_mode(vcpu))
-		vpid_sync_context(to_vmx(vcpu)->vpid);
 	else
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
 {
 	/*
-	 * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in
+	 * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
 	 * vmx_flush_tlb_guest() for an explanation of why this is ok.
 	 */
-	vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr);
+	vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr);
 }
 
 static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 {
 	/*
-	 * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0
-	 * or a vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit
-	 * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is
+	 * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a
+	 * vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit are
+	 * required to flush GVA->{G,H}PA mappings from the TLB if vpid is
 	 * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed),
 	 * i.e. no explicit INVVPID is necessary.
 	 */
-	vpid_sync_context(to_vmx(vcpu)->vpid);
+	vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
@@ -6262,9 +6267,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
-	bool max_irr_updated;
+	bool got_posted_interrupt;
 
-	if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm))
+	if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
 		return -EIO;
 
 	if (pi_test_on(&vmx->pi_desc)) {
@@ -6274,22 +6279,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
-		max_irr_updated =
+		got_posted_interrupt =
 			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
-
-		/*
-		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, this may cause a vmexit or it may
-		 * be injected into L2.  Either way, this interrupt will be
-		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
-		 * virtual interrupt delivery to inject L1 interrupts into L2.
-		 */
-		if (is_guest_mode(vcpu) && max_irr_updated)
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
+		got_posted_interrupt = false;
 	}
-	vmx_hwapic_irr_update(vcpu, max_irr);
+
+	/*
+	 * Newly recognized interrupts are injected via either virtual interrupt
+	 * delivery (RVI) or KVM_REQ_EVENT.  Virtual interrupt delivery is
+	 * disabled in two cases:
+	 *
+	 * 1) If L2 is running and the vCPU has a new pending interrupt.  If L1
+	 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a
+	 * VM-Exit to L1.  If L1 doesn't want to exit, the interrupt is injected
+	 * into L2, but KVM doesn't use virtual interrupt delivery to inject
+	 * interrupts into L2, and so KVM_REQ_EVENT is again needed.
+	 *
+	 * 2) If APICv is disabled for this vCPU, assigned devices may still
+	 * attempt to post interrupts.  The posted interrupt vector will cause
+	 * a VM-Exit and the subsequent entry will call sync_pir_to_irr.
+	 */
+	if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu))
+		vmx_set_rvi(max_irr);
+	else if (got_posted_interrupt)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
 	return max_irr;
 }
 
@@ -7761,10 +7777,10 @@ static __init int hardware_setup(void)
 		ple_window_shrink = 0;
 	}
 
-	if (!cpu_has_vmx_apicv()) {
+	if (!cpu_has_vmx_apicv())
 		enable_apicv = 0;
+	if (!enable_apicv)
 		vmx_x86_ops.sync_pir_to_irr = NULL;
-	}
 
 	if (cpu_has_vmx_tsc_scaling()) {
 		kvm_has_tsc_control = true;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5a403d92833f..0ee1a039b490 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3258,6 +3258,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	static_call(kvm_x86_tlb_flush_guest)(vcpu);
 }
 
+
+static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	static_call(kvm_x86_tlb_flush_current)(vcpu);
+}
+
+/*
+ * Service "local" TLB flush requests, which are specific to the current MMU
+ * context.  In addition to the generic event handling in vcpu_enter_guest(),
+ * TLB flushes that are targeted at an MMU context also need to be serviced
+ * prior before nested VM-Enter/VM-Exit.
+ */
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
+		kvm_vcpu_flush_tlb_guest(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests);
+
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
@@ -4133,6 +4156,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SGX_ATTRIBUTE:
 #endif
 	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
+	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
 	case KVM_CAP_SREGS2:
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
 	case KVM_CAP_VCPU_ATTRIBUTES:
@@ -4448,8 +4472,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	if (vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
 }
@@ -5124,6 +5147,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
 
+		/*
+		 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+		 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+		 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
+		 * faults due to reusing SPs/SPTEs.  In practice no sane VMM mucks with
+		 * the core vCPU model on the fly, so fail.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5134,6 +5168,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
+		/*
+		 * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
+		 * KVM_SET_CPUID case above.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -9528,8 +9570,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 		if (ioapic_in_kernel(vcpu->kvm))
 			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
@@ -9648,10 +9689,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			/* Flushing all ASIDs flushes the current ASID... */
 			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-			kvm_vcpu_flush_tlb_current(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
-			kvm_vcpu_flush_tlb_guest(vcpu);
+		kvm_service_local_tlb_flush_requests(vcpu);
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -9802,10 +9840,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	/*
 	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.
+	 * notified with kvm_vcpu_kick.  Assigned devices can
+	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
+	 * so do it even if APICv is disabled on this vCPU.
 	 */
-	if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	if (kvm_lapic_enabled(vcpu))
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	if (kvm_vcpu_exit_request(vcpu)) {
 		vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -9849,8 +9889,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		if (kvm_lapic_enabled(vcpu))
+			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
 			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 997669ae9caa..4abcd8d9836d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
 
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
 int kvm_check_nested_events(struct kvm_vcpu *vcpu);
 
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
@@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
 }
 
-static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.tlb_flush;
-	static_call(kvm_x86_tlb_flush_current)(vcpu);
-}
-
 static inline int is_pae(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);