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

Pull kvm fixes from Paolo Bonzini:
 "RISC-V:

   - Avoid redundant allocations when allocating IMSIC page tables

   - Apply SBI FWFT LOCK flag only on successful set

   - Bound SBI PMU counter mask scan to BITS_PER_LONG, since on RV32 the
     PMU SBI start/stop helper can only access 32 PMU counters.

   - Skip TLB flush when G-stage PTE becomes valid if the Svvptc
     extension is available.

   - Always show Zicbo[m|z|p] block sizes in ONE_REG

   - Inject instruction access fault on unmapped guest fetch

   - Use raw spinlock for irqs_pending and irqs_pending_mask

   - Fix Spectre-v1 in vector register access via ONE_REG

  x86:

   - Fixes to SEV selftests

   - Once free_nested() did a VMCLEAR of shadow VMCS, there's no need to
     VMCLEAR it again if the kernel is preempted and thread migration
     happens

   - Preserve nested TDP shadow page tables if they are used as roots,
     instead of clearing them unnecessarily

   - Fix use of stale data if out-of-memory happens after vendor module
     reload

   - Check for invalid/obsolete root *after* making MMU pages available,
     because the latter can make a page invalid

   - Only reset TSC Deadline Timer in apic_timer_expired on KVM_RUN"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Only reset TSC Deadline Timer in apic_timer_expired on KVM_RUN
  KVM: selftests: sev_init2_tests: Derive SEV availability from KVM
  KVM: selftests: sev_smoke_test: Only run VM types the host offers
  KVM: x86/mmu: Fix use-after-free on vendor module reload
  KVM: x86/mmu: Preserve nested TDP shadow page tables if they are used as roots
  KVM: x86: Check for invalid/obsolete root *after* making MMU pages available
  KVM: nVMX: Hide shadow VMCS right after VMCLEAR
  KVM: riscv: Fix Spectre-v1 in vector register access
  RISC-V: KVM: Serialize virtual interrupt pending state updates
  RISC-V: KVM: Inject instruction access fault on unmapped guest fetch
  RISC-V: KVM: Zicbo[m|z|p] block sizes should be always present in ONE_REG
  riscv: kvm: Skip TLB flush when G-stage PTE becomes valid with Svvptc
  KVM: riscv: PMU: Bound counter mask scan to BITS_PER_LONG
  KVM: riscv: SBI FWFT: Apply LOCK flag only on successful set
  RISC-V: KVM: Avoid redundant page-table allocations in ioremap topup

arch/riscv/include/asm/kvm_host.h

@@ -209,13 +209,13 @@ struct kvm_vcpu_arch {
 	/*
 	 * VCPU interrupts
 	 *
-	 * We have a lockless approach for tracking pending VCPU interrupts
-	 * implemented using atomic bitops. The irqs_pending bitmap represent
-	 * pending interrupts whereas irqs_pending_mask represent bits changed
-	 * in irqs_pending. Our approach is modeled around multiple producer
-	 * and single consumer problem where the consumer is the VCPU itself.
+	 * The irqs_pending bitmap represents pending interrupts whereas
+	 * irqs_pending_mask represents bits changed in irqs_pending. Updates
+	 * to these bitmaps are serialized so vcpu interrupt sync/flush cannot
+	 * drop a newly injected interrupt while syncing guest-visible HVIP.
 	 */
 #define KVM_RISCV_VCPU_NR_IRQS	64
+	raw_spinlock_t irqs_pending_lock;
 	DECLARE_BITMAP(irqs_pending, KVM_RISCV_VCPU_NR_IRQS);
 	DECLARE_BITMAP(irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS);
 

arch/riscv/kvm/aia.c

@@ -53,12 +53,15 @@ void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 	unsigned long mask, val;
 
+	lockdep_assert_held(&vcpu->arch.irqs_pending_lock);
+
 	if (!kvm_riscv_aia_available())
 		return;
 
-	if (READ_ONCE(vcpu->arch.irqs_pending_mask[1])) {
-		mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[1], 0);
-		val = READ_ONCE(vcpu->arch.irqs_pending[1]) & mask;
+	mask = vcpu->arch.irqs_pending_mask[1];
+	if (mask) {
+		vcpu->arch.irqs_pending_mask[1] = 0;
+		val = vcpu->arch.irqs_pending[1] & mask;
 
 		csr->hviph &= ~mask;
 		csr->hviph |= val;
@@ -69,6 +72,8 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 
+	lockdep_assert_held(&vcpu->arch.irqs_pending_lock);
+
 	if (kvm_riscv_aia_available())
 		csr->vsieh = ncsr_read(CSR_VSIEH);
 }
@@ -77,13 +82,22 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
 bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 {
 	unsigned long seip;
+#ifdef CONFIG_32BIT
+	unsigned long flags;
+	bool pending;
+#endif
 
 	if (!kvm_riscv_aia_available())
 		return false;
 
 #ifdef CONFIG_32BIT
-	if (READ_ONCE(vcpu->arch.irqs_pending[1]) &
-	    (vcpu->arch.aia_context.guest_csr.vsieh & upper_32_bits(mask)))
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
+	pending = vcpu->arch.irqs_pending[1] &
+		  (vcpu->arch.aia_context.guest_csr.vsieh &
+		   upper_32_bits(mask));
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
+
+	if (pending)
 		return true;
 #endif
 
@@ -207,6 +221,9 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
+#ifdef CONFIG_32BIT
+	unsigned long flags;
+#endif
 
 	if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA))
 		return -ENOENT;
@@ -219,8 +236,12 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 		((unsigned long *)csr)[reg_num] = val;
 
 #ifdef CONFIG_32BIT
-		if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph))
-			WRITE_ONCE(vcpu->arch.irqs_pending_mask[1], 0);
+		if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) {
+			raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
+			vcpu->arch.irqs_pending_mask[1] = 0;
+			raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock,
+						   flags);
+		}
 #endif
 	}
 

arch/riscv/kvm/gstage.c

@@ -5,11 +5,13 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/cpufeature.h>
 #include <linux/errno.h>
 #include <linux/kvm_host.h>
 #include <linux/module.h>
 #include <linux/pgtable.h>
 #include <asm/kvm_gstage.h>
+#include <asm/hwcap.h>
 
 #ifdef CONFIG_64BIT
 unsigned long kvm_riscv_gstage_max_pgd_levels __ro_after_init = 3;
@@ -171,8 +173,10 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
 	}
 
 	if (pte_val(*ptep) != pte_val(map->pte)) {
+		bool was_invalid = !pte_val(*ptep);
 		set_pte(ptep, map->pte);
-		if (gstage_pte_leaf(ptep))
+		if (gstage_pte_leaf(ptep) &&
+		    !(was_invalid && riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC)))
 			gstage_tlb_flush(gstage, current_level, map->addr);
 	}
 

arch/riscv/kvm/mmu.c

@@ -41,6 +41,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 	pgprot_t prot;
 	unsigned long pfn;
 	phys_addr_t addr, end;
+	unsigned long pgd_levels = kvm->arch.pgd_levels;
 	struct kvm_mmu_memory_cache pcache = {
 		.gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0,
 		.gfp_zero = __GFP_ZERO,
@@ -63,7 +64,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 		if (!writable)
 			map.pte = pte_wrprotect(map.pte);
 
-		ret = kvm_mmu_topup_memory_cache(&pcache, kvm->arch.pgd_levels);
+		ret = __kvm_mmu_topup_memory_cache(&pcache, pgd_levels, pgd_levels);
 		if (ret)
 			goto out;
 

arch/riscv/kvm/vcpu.c

@@ -80,6 +80,7 @@ static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu,
 
 static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset)
 {
+	unsigned long flags;
 	bool loaded;
 
 	/**
@@ -104,8 +105,10 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset)
 
 	kvm_riscv_vcpu_aia_reset(vcpu);
 
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
 	bitmap_zero(vcpu->arch.irqs_pending, KVM_RISCV_VCPU_NR_IRQS);
 	bitmap_zero(vcpu->arch.irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS);
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
 
 	kvm_riscv_vcpu_pmu_reset(vcpu);
 
@@ -151,6 +154,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	/* Setup VCPU hfence queue */
 	spin_lock_init(&vcpu->arch.hfence_lock);
+	raw_spin_lock_init(&vcpu->arch.irqs_pending_lock);
 
 	spin_lock_init(&vcpu->arch.reset_state.lock);
 
@@ -352,10 +356,14 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 	unsigned long mask, val;
+	unsigned long flags;
 
-	if (READ_ONCE(vcpu->arch.irqs_pending_mask[0])) {
-		mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[0], 0);
-		val = READ_ONCE(vcpu->arch.irqs_pending[0]) & mask;
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
+
+	mask = vcpu->arch.irqs_pending_mask[0];
+	if (mask) {
+		vcpu->arch.irqs_pending_mask[0] = 0;
+		val = vcpu->arch.irqs_pending[0] & mask;
 
 		csr->hvip &= ~mask;
 		csr->hvip |= val;
@@ -363,11 +371,14 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu)
 
 	/* Flush AIA high interrupts */
 	kvm_riscv_vcpu_aia_flush_interrupts(vcpu);
+
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
 }
 
 void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
 {
 	unsigned long hvip;
+	unsigned long flags;
 	struct kvm_vcpu_arch *v = &vcpu->arch;
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 
@@ -376,34 +387,41 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
 
 	/* Sync-up HVIP.VSSIP bit changes does by Guest */
 	hvip = ncsr_read(CSR_HVIP);
+
+	raw_spin_lock_irqsave(&v->irqs_pending_lock, flags);
+
 	if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) {
 		if (hvip & (1UL << IRQ_VS_SOFT)) {
-			if (!test_and_set_bit(IRQ_VS_SOFT,
-					      v->irqs_pending_mask))
-				set_bit(IRQ_VS_SOFT, v->irqs_pending);
+			if (!__test_and_set_bit(IRQ_VS_SOFT,
+						v->irqs_pending_mask))
+				__set_bit(IRQ_VS_SOFT, v->irqs_pending);
 		} else {
-			if (!test_and_set_bit(IRQ_VS_SOFT,
-					      v->irqs_pending_mask))
-				clear_bit(IRQ_VS_SOFT, v->irqs_pending);
+			if (!__test_and_set_bit(IRQ_VS_SOFT,
+						v->irqs_pending_mask))
+				__clear_bit(IRQ_VS_SOFT, v->irqs_pending);
 		}
 	}
 
 	/* Sync up the HVIP.LCOFIP bit changes (only clear) by the guest */
 	if ((csr->hvip ^ hvip) & (1UL << IRQ_PMU_OVF)) {
 		if (!(hvip & (1UL << IRQ_PMU_OVF)) &&
-		    !test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask))
-			clear_bit(IRQ_PMU_OVF, v->irqs_pending);
+		    !__test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask))
+			__clear_bit(IRQ_PMU_OVF, v->irqs_pending);
 	}
 
 	/* Sync-up AIA high interrupts */
 	kvm_riscv_vcpu_aia_sync_interrupts(vcpu);
 
+	raw_spin_unlock_irqrestore(&v->irqs_pending_lock, flags);
+
 	/* Sync-up timer CSRs */
 	kvm_riscv_vcpu_timer_sync(vcpu);
 }
 
 int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 {
+	unsigned long flags;
+
 	/*
 	 * We only allow VS-mode software, timer, and external
 	 * interrupts when irq is one of the local interrupts
@@ -416,9 +434,10 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 	    irq != IRQ_PMU_OVF)
 		return -EINVAL;
 
-	set_bit(irq, vcpu->arch.irqs_pending);
-	smp_mb__before_atomic();
-	set_bit(irq, vcpu->arch.irqs_pending_mask);
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
+	__set_bit(irq, vcpu->arch.irqs_pending);
+	__set_bit(irq, vcpu->arch.irqs_pending_mask);
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
 
 	kvm_vcpu_kick(vcpu);
 
@@ -427,6 +446,8 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 
 int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 {
+	unsigned long flags;
+
 	/*
 	 * We only allow VS-mode software, timer, counter overflow and external
 	 * interrupts when irq is one of the local interrupts
@@ -439,26 +460,33 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
 	    irq != IRQ_PMU_OVF)
 		return -EINVAL;
 
-	clear_bit(irq, vcpu->arch.irqs_pending);
-	smp_mb__before_atomic();
-	set_bit(irq, vcpu->arch.irqs_pending_mask);
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
+	__clear_bit(irq, vcpu->arch.irqs_pending);
+	__set_bit(irq, vcpu->arch.irqs_pending_mask);
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
 
 	return 0;
 }
 
 bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 {
+	unsigned long flags;
 	unsigned long ie;
+	bool ret;
 
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
 	ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK)
 		<< VSIP_TO_HVIP_SHIFT) & (unsigned long)mask;
 	ie |= vcpu->arch.guest_csr.vsie & ~IRQ_LOCAL_MASK &
 		(unsigned long)mask;
-	if (READ_ONCE(vcpu->arch.irqs_pending[0]) & ie)
-		return true;
+	ret = vcpu->arch.irqs_pending[0] & ie;
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
 
 	/* Check AIA high interrupts */
-	return kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask);
+	if (!ret)
+		ret = kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask);
+
+	return ret;
 }
 
 void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)

arch/riscv/kvm/vcpu_exit.c

@@ -38,6 +38,25 @@ static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			return kvm_riscv_vcpu_mmio_store(vcpu, run,
 							 fault_addr,
 							 trap->htinst);
+		case EXC_INST_GUEST_PAGE_FAULT: {
+			/*
+			 * No memslot backs this GPA and an instruction fetch
+			 * cannot be emulated as MMIO. On bare metal a fetch
+			 * from an unbacked physical address raises an
+			 * instruction access fault, so reflect that back to
+			 * the guest.
+			 */
+			struct kvm_cpu_trap inst_trap = {
+				.sepc	= trap->sepc,
+				.scause	= EXC_INST_ACCESS,
+				.stval	= trap->stval,
+				.htval	= 0,
+				.htinst	= 0,
+			};
+
+			kvm_riscv_vcpu_trap_redirect(vcpu, &inst_trap);
+			return 1;
+		}
 		default:
 			return -EOPNOTSUPP;
 		};

arch/riscv/kvm/vcpu_onereg.c

@@ -50,19 +50,13 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
 		reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
-		if (kvm_riscv_isa_check_host(ZICBOM))
-			return -ENOENT;
-		reg_val = riscv_cbom_block_size;
+		reg_val = (kvm_riscv_isa_check_host(ZICBOM)) ? 0 : riscv_cbom_block_size;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
-		if (kvm_riscv_isa_check_host(ZICBOZ))
-			return -ENOENT;
-		reg_val = riscv_cboz_block_size;
+		reg_val = (kvm_riscv_isa_check_host(ZICBOZ)) ? 0 : riscv_cboz_block_size;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size):
-		if (kvm_riscv_isa_check_host(ZICBOP))
-			return -ENOENT;
-		reg_val = riscv_cbop_block_size;
+		reg_val = (kvm_riscv_isa_check_host(ZICBOP)) ? 0 : riscv_cbop_block_size;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
 		reg_val = vcpu->arch.mvendorid;
@@ -144,21 +138,15 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 		}
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
-		if (kvm_riscv_isa_check_host(ZICBOM))
-			return -ENOENT;
-		if (reg_val != riscv_cbom_block_size)
+		if (reg_val && reg_val != riscv_cbom_block_size)
 			return -EINVAL;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size):
-		if (kvm_riscv_isa_check_host(ZICBOZ))
-			return -ENOENT;
-		if (reg_val != riscv_cboz_block_size)
+		if (reg_val && reg_val != riscv_cboz_block_size)
 			return -EINVAL;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size):
-		if (kvm_riscv_isa_check_host(ZICBOP))
-			return -ENOENT;
-		if (reg_val != riscv_cbop_block_size)
+		if (reg_val && reg_val != riscv_cbop_block_size)
 			return -EINVAL;
 		break;
 	case KVM_REG_RISCV_CONFIG_REG(mvendorid):
@@ -298,6 +286,7 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 	unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
+	unsigned long flags;
 
 	if (reg_num >= regs_max)
 		return -ENOENT;
@@ -311,8 +300,11 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
 
 	((unsigned long *)csr)[reg_num] = reg_val;
 
-	if (reg_num == KVM_REG_RISCV_CSR_REG(sip))
-		WRITE_ONCE(vcpu->arch.irqs_pending_mask[0], 0);
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
+		raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags);
+		vcpu->arch.irqs_pending_mask[0] = 0;
+		raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags);
+	}
 
 	return 0;
 }
@@ -614,20 +606,6 @@ static int copy_config_reg_indices(const struct kvm_vcpu *vcpu,
 		u64 size;
 		u64 reg;
 
-		/*
-		 * Avoid reporting config reg if the corresponding extension
-		 * was not available.
-		 */
-		if (i == KVM_REG_RISCV_CONFIG_REG(zicbom_block_size) &&
-		    kvm_riscv_isa_check_host(ZICBOM))
-			continue;
-		else if (i == KVM_REG_RISCV_CONFIG_REG(zicboz_block_size) &&
-			 kvm_riscv_isa_check_host(ZICBOZ))
-			continue;
-		else if (i == KVM_REG_RISCV_CONFIG_REG(zicbop_block_size) &&
-			 kvm_riscv_isa_check_host(ZICBOP))
-			continue;
-
 		size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
 		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CONFIG | i;
 

arch/riscv/kvm/vcpu_pmu.c

@@ -586,7 +586,7 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 		}
 	}
 	/* Start the counters that have been configured and requested by the guest */
-	for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) {
+	for_each_set_bit(i, &ctr_mask, BITS_PER_LONG) {
 		pmc_index = array_index_nospec(i + ctr_base,
 					       RISCV_KVM_MAX_COUNTERS);
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))
@@ -658,7 +658,7 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 	}
 
 	/* Stop the counters that have been configured and requested by the guest */
-	for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) {
+	for_each_set_bit(i, &ctr_mask, BITS_PER_LONG) {
 		pmc_index = array_index_nospec(i + ctr_base,
 					       RISCV_KVM_MAX_COUNTERS);
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))

arch/riscv/kvm/vcpu_sbi_fwft.c

@@ -327,9 +327,11 @@ static int kvm_sbi_fwft_set(struct kvm_vcpu *vcpu, u32 feature,
 	if (conf->flags & SBI_FWFT_SET_FLAG_LOCK)
 		return SBI_ERR_DENIED_LOCKED;
 
-	conf->flags = flags;
+	ret = conf->feature->set(vcpu, conf, false, value);
+	if (ret == SBI_SUCCESS)
+		conf->flags = flags;
 
-	return conf->feature->set(vcpu, conf, false, value);
+	return ret;
 }
 
 static int kvm_sbi_fwft_get(struct kvm_vcpu *vcpu, unsigned long feature,

arch/riscv/kvm/vcpu_vector.c

@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 #include <asm/cpufeature.h>
 #include <asm/kvm_isa.h>
@@ -129,11 +130,20 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 			return -ENOENT;
 		}
 	} else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) {
+		unsigned long reg_offset;
+
 		if (reg_size != vlenb)
 			return -EINVAL;
 		WARN_ON(!cntx->vector.datap);
-		*reg_addr = cntx->vector.datap +
-			    (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb;
+		/*
+		 * The reg_num is derived from the userspace-provided ONE_REG
+		 * id. Sanitize it with array_index_nospec() to prevent
+		 * speculative out-of-bounds access to the vector register
+		 * buffer (32 vector registers: v0..v31).
+		 */
+		reg_offset = array_index_nospec(
+				reg_num - KVM_REG_RISCV_VECTOR_REG(0), 32);
+		*reg_addr = cntx->vector.datap + reg_offset * vlenb;
 	} else {
 		return -ENOENT;
 	}

arch/x86/kvm/lapic.c

@@ -2052,7 +2052,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
 
-	if (!from_timer_fn && apic->apicv_active) {
+	if (!from_timer_fn && apic->apicv_active && vcpu->wants_to_run) {
 		WARN_ON(kvm_get_running_vcpu() != vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;

arch/x86/kvm/mmu/mmu.c

@@ -2642,6 +2642,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			 */
 			if (tdp_enabled && invalid_list &&
 			    child->role.guest_mode &&
+			    !child->root_count &&
 			    !atomic_long_read(&child->parent_ptes.val))
 				return kvm_mmu_prepare_zap_page(kvm, child,
 								invalid_list);
@@ -4852,16 +4853,17 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (r != RET_PF_CONTINUE)
 		return r;
 
-	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_page_fault_stale(vcpu, fault))
-		goto out_unlock;
-
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
 
+	if (is_page_fault_stale(vcpu, fault)) {
+		r = RET_PF_RETRY;
+		goto out_unlock;
+	}
+
 	r = direct_map(vcpu, fault);
 
 out_unlock:
@@ -7574,7 +7576,9 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 static void mmu_destroy_caches(void)
 {
 	kmem_cache_destroy(pte_list_desc_cache);
+	pte_list_desc_cache = NULL;
 	kmem_cache_destroy(mmu_page_header_cache);
+	mmu_page_header_cache = NULL;
 }
 
 static void kvm_wake_nx_recovery_thread(struct kvm *kvm)

arch/x86/kvm/mmu/paging_tmpl.h

@@ -864,15 +864,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	}
 #endif
 
-	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_page_fault_stale(vcpu, fault))
-		goto out_unlock;
-
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
+
+	if (is_page_fault_stale(vcpu, fault)) {
+		r = RET_PF_RETRY;
+		goto out_unlock;
+	}
+
 	r = FNAME(fetch)(vcpu, fault, &walker);
 
 out_unlock:

arch/x86/kvm/vmx/nested.c

@@ -336,6 +336,7 @@ static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu)
 static void free_nested(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs *shadow_vmcs;
 
 	if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01))
 		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
@@ -353,9 +354,15 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	vmx->nested.current_vmptr = INVALID_GPA;
 	if (enable_shadow_vmcs) {
 		vmx_disable_shadow_vmcs(vmx);
-		vmcs_clear(vmx->vmcs01.shadow_vmcs);
-		free_vmcs(vmx->vmcs01.shadow_vmcs);
+
+		/*
+		 * Keep the pointer visible until after VMCLEAR, so migration
+		 * can clear an active shadow VMCS on the old CPU.
+		 */
+		shadow_vmcs = vmx->vmcs01.shadow_vmcs;
+		vmcs_clear(shadow_vmcs);
 		vmx->vmcs01.shadow_vmcs = NULL;
+		free_vmcs(shadow_vmcs);
 	}
 	kfree(vmx->nested.cached_vmcs12);
 	vmx->nested.cached_vmcs12 = NULL;

tools/testing/selftests/kvm/x86/sev_init2_tests.c

@@ -130,12 +130,18 @@ int main(int argc, char *argv[])
 			    KVM_X86_SEV_VMSA_FEATURES,
 			    &supported_vmsa_features);
 
-	have_sev = kvm_cpu_has(X86_FEATURE_SEV);
-	TEST_ASSERT(have_sev == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)),
-		    "sev: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)",
-		    kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_VM);
+	/*
+	 * Whether a VM type is available depends on KVM, not just CPUID: e.g.
+	 * when all SEV ASIDs are assigned to SEV-SNP, KVM does not offer the
+	 * SEV VM type even though X86_FEATURE_SEV is set.  Derive availability
+	 * from KVM_CAP_VM_TYPES and only assert the one-way implication that a
+	 * type offered by KVM must also be reported in CPUID.
+	 */
+	have_sev = kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM);
+	TEST_ASSERT(!have_sev || kvm_cpu_has(X86_FEATURE_SEV),
+		    "sev: SEV_VM supported without SEV in CPUID");
 
-	TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM));
+	TEST_REQUIRE(have_sev);
 	have_sev_es = kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM);
 
 	TEST_ASSERT(!have_sev_es || kvm_cpu_has(X86_FEATURE_SEV_ES),

tools/testing/selftests/kvm/x86/sev_smoke_test.c

@@ -247,7 +247,14 @@ int main(int argc, char *argv[])
 {
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
 
-	test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0);
+	/*
+	 * Only exercise VM types the host actually offers.  CPUID reporting
+	 * SEV does not guarantee KVM offers the SEV VM type: when all SEV
+	 * ASIDs are assigned to SEV-SNP, KVM_X86_SEV_VM is unavailable even
+	 * though X86_FEATURE_SEV is set.  Gate every type on KVM_CAP_VM_TYPES.
+	 */
+	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM))
+		test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0);
 
 	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM))
 		test_sev_smoke(guest_sev_es_code, KVM_X86_SEV_ES_VM, SEV_POLICY_ES);