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

Pull kvm fixes from Paolo Bonzini: "Arm: - Fix trapping regression when no in-kernel irqchip is present - Check host-provided, untrusted ranges and offsets in pKVM - Fix regression restoring the ID_PFR1_EL1 register - Fix vgic ITS locking issues when LPIs are not directly injected Arm selftests: - Correct target CPU programming in vgic_lpi_stress selftest - Fix exposure of SCTLR2_EL2 and ZCR_EL2 in get-reg-list selftest RISC-V: - Fix check for local interrupts on riscv32 - Read HGEIP CSR on the correct cpu when checking for IMSIC interrupts - Remove automatic I/O mapping from kvm_arch_prepare_memory_region() x86: - Inject #UD if the guest attempts to execute SEAMCALL or TDCALL as KVM doesn't support virtualization the instructions, but the instructions are gated only by VMXON. That is, they will VM-Exit instead of taking a #UD and until now this resulted in KVM exiting to userspace with an emulation error. - Unload the "FPU" when emulating INIT of XSTATE features if and only if the FPU is actually loaded, instead of trying to predict when KVM will emulate an INIT (CET support missed the MP_STATE path). Add sanity checks to detect and harden against similar bugs in the future. - Unregister KVM's GALog notifier (for AVIC) when kvm-amd.ko is unloaded. - Use a raw spinlock for svm->ir_list_lock as the lock is taken during schedule(), and "normal" spinlocks are sleepable locks when PREEMPT_RT=y. - Remove guest_memfd bindings on memslot deletion when a gmem file is dying to fix a use-after-free race found by syzkaller. - Fix a goof in the EPT Violation handler where KVM checks the wrong variable when determining if the reported GVA is valid. - Fix and simplify the handling of LBR virtualization on AMD, which was made buggy and unnecessarily complicated by nested VM support Misc: - Update Oliver's email address" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits) KVM: nSVM: Fix and simplify LBR virtualization handling with nested KVM: nSVM: Always recalculate LBR MSR intercepts in svm_update_lbrv() KVM: SVM: Mark VMCB_LBR dirty when MSR_IA32_DEBUGCTLMSR is updated MAINTAINERS: Switch myself to using kernel.org address KVM: arm64: vgic-v3: Release reserved slot outside of lpi_xa's lock KVM: arm64: vgic-v3: Reinstate IRQ lock ordering for LPI xarray KVM: arm64: Limit clearing of ID_{AA64PFR0,PFR1}_EL1.GIC to userspace irqchip KVM: arm64: Set ID_{AA64PFR0,PFR1}_EL1.GIC when GICv3 is configured KVM: arm64: Make all 32bit ID registers fully writable KVM: VMX: Fix check for valid GVA on an EPT violation KVM: guest_memfd: Remove bindings on memslot deletion when gmem is dying KVM: SVM: switch to raw spinlock for svm->ir_list_lock KVM: SVM: Make avic_ga_log_notifier() local to avic.c KVM: SVM: Unregister KVM's GALog notifier on kvm-amd.ko exit KVM: SVM: Initialize per-CPU svm_data at the end of hardware setup KVM: x86: Call out MSR_IA32_S_CET is not handled by XSAVES KVM: x86: Harden KVM against imbalanced load/put of guest FPU state KVM: x86: Unload "FPU" state on INIT if and only if its currently in-use KVM: arm64: Check the untrusted offset in FF-A memory share KVM: arm64: Check range args for pKVM mem transitions ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2025-11-10 08:54:36 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2025-11-10 08:54:36 -0800
commit: 4ea7c1717f3f2344f7a1cdab4f5875cfa89c87a9 (patch)
tree: 981d445641d11f9a623f7250fe233293742d4ec7 /arch
parent: e9a6fb0bcdd7609be6969112f3fbfcce3b1d4a7c (diff)
parent: 8a4821412cf2c1429fffa07c012dd150f2edf78c (diff)
download: linux-4ea7c1717f3f2344f7a1cdab4f5875cfa89c87a9.tar.gz
20 files changed, 250 insertions, 180 deletions
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index 4e16f9b96f6375..58b7d0c477d7fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -479,7 +479,7 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 	struct ffa_mem_region_attributes *ep_mem_access;
 	struct ffa_composite_mem_region *reg;
 	struct ffa_mem_region *buf;
-	u32 offset, nr_ranges;
+	u32 offset, nr_ranges, checked_offset;
 	int ret = 0;
 
 	if (addr_mbz || npages_mbz || fraglen > len ||
@@ -516,7 +516,12 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 		goto out_unlock;
 	}
 
-	if (fraglen < offset + sizeof(struct ffa_composite_mem_region)) {
+	if (check_add_overflow(offset, sizeof(struct ffa_composite_mem_region), &checked_offset)) {
+		ret = FFA_RET_INVALID_PARAMETERS;
+		goto out_unlock;
+	}
+
+	if (fraglen < checked_offset) {
 		ret = FFA_RET_INVALID_PARAMETERS;
 		goto out_unlock;
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index ddc8beb55eee6d..49db32f3ddf715 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -367,6 +367,19 @@ static int host_stage2_unmap_dev_all(void)
 	return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr);
 }
 
+/*
+ * Ensure the PFN range is contained within PA-range.
+ *
+ * This check is also robust to overflows and is therefore a requirement before
+ * using a pfn/nr_pages pair from an untrusted source.
+ */
+static bool pfn_range_is_valid(u64 pfn, u64 nr_pages)
+{
+	u64 limit = BIT(kvm_phys_shift(&host_mmu.arch.mmu) - PAGE_SHIFT);
+
+	return pfn < limit && ((limit - pfn) >= nr_pages);
+}
+
 struct kvm_mem_range {
 	u64 start;
 	u64 end;
@@ -776,6 +789,9 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
 	void *virt = __hyp_va(phys);
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	hyp_lock_component();
 
@@ -804,6 +820,9 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
 	u64 virt = (u64)__hyp_va(phys);
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	hyp_lock_component();
 
@@ -887,6 +906,9 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages)
 	u64 size = PAGE_SIZE * nr_pages;
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
 	if (!ret)
@@ -902,6 +924,9 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
 	u64 size = PAGE_SIZE * nr_pages;
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
 	if (!ret)
@@ -945,6 +970,9 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu
 	if (prot & ~KVM_PGTABLE_PROT_RWX)
 		return -EINVAL;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	ret = __guest_check_transition_size(phys, ipa, nr_pages, &size);
 	if (ret)
 		return ret;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e67eb39ddc1184..8ae2bca8161486 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2595,19 +2595,23 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
 	.val = 0,				\
 }
 
-/* sys_reg_desc initialiser for known cpufeature ID registers */
-#define AA32_ID_SANITISED(name) {		\
-	ID_DESC(name),				\
-	.visibility = aa32_id_visibility,	\
-	.val = 0,				\
-}
-
 /* sys_reg_desc initialiser for writable ID registers */
 #define ID_WRITABLE(name, mask) {		\
 	ID_DESC(name),				\
 	.val = mask,				\
 }
 
+/*
+ * 32bit ID regs are fully writable when the guest is 32bit
+ * capable. Nothing in the KVM code should rely on 32bit features
+ * anyway, only 64bit, so let the VMM do its worse.
+ */
+#define AA32_ID_WRITABLE(name) {		\
+	ID_DESC(name),				\
+	.visibility = aa32_id_visibility,	\
+	.val = GENMASK(31, 0),			\
+}
+
 /* sys_reg_desc initialiser for cpufeature ID registers that need filtering */
 #define ID_FILTERED(sysreg, name, mask) {	\
 	ID_DESC(sysreg),				\
@@ -3128,40 +3132,39 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
-	AA32_ID_SANITISED(ID_PFR0_EL1),
-	AA32_ID_SANITISED(ID_PFR1_EL1),
+	AA32_ID_WRITABLE(ID_PFR0_EL1),
+	AA32_ID_WRITABLE(ID_PFR1_EL1),
 	{ SYS_DESC(SYS_ID_DFR0_EL1),
 	  .access = access_id_reg,
 	  .get_user = get_id_reg,
 	  .set_user = set_id_dfr0_el1,
 	  .visibility = aa32_id_visibility,
 	  .reset = read_sanitised_id_dfr0_el1,
-	  .val = ID_DFR0_EL1_PerfMon_MASK |
-		 ID_DFR0_EL1_CopDbg_MASK, },
+	  .val = GENMASK(31, 0) },
 	ID_HIDDEN(ID_AFR0_EL1),
-	AA32_ID_SANITISED(ID_MMFR0_EL1),
-	AA32_ID_SANITISED(ID_MMFR1_EL1),
-	AA32_ID_SANITISED(ID_MMFR2_EL1),
-	AA32_ID_SANITISED(ID_MMFR3_EL1),
+	AA32_ID_WRITABLE(ID_MMFR0_EL1),
+	AA32_ID_WRITABLE(ID_MMFR1_EL1),
+	AA32_ID_WRITABLE(ID_MMFR2_EL1),
+	AA32_ID_WRITABLE(ID_MMFR3_EL1),
 
 	/* CRm=2 */
-	AA32_ID_SANITISED(ID_ISAR0_EL1),
-	AA32_ID_SANITISED(ID_ISAR1_EL1),
-	AA32_ID_SANITISED(ID_ISAR2_EL1),
-	AA32_ID_SANITISED(ID_ISAR3_EL1),
-	AA32_ID_SANITISED(ID_ISAR4_EL1),
-	AA32_ID_SANITISED(ID_ISAR5_EL1),
-	AA32_ID_SANITISED(ID_MMFR4_EL1),
-	AA32_ID_SANITISED(ID_ISAR6_EL1),
+	AA32_ID_WRITABLE(ID_ISAR0_EL1),
+	AA32_ID_WRITABLE(ID_ISAR1_EL1),
+	AA32_ID_WRITABLE(ID_ISAR2_EL1),
+	AA32_ID_WRITABLE(ID_ISAR3_EL1),
+	AA32_ID_WRITABLE(ID_ISAR4_EL1),
+	AA32_ID_WRITABLE(ID_ISAR5_EL1),
+	AA32_ID_WRITABLE(ID_MMFR4_EL1),
+	AA32_ID_WRITABLE(ID_ISAR6_EL1),
 
 	/* CRm=3 */
-	AA32_ID_SANITISED(MVFR0_EL1),
-	AA32_ID_SANITISED(MVFR1_EL1),
-	AA32_ID_SANITISED(MVFR2_EL1),
+	AA32_ID_WRITABLE(MVFR0_EL1),
+	AA32_ID_WRITABLE(MVFR1_EL1),
+	AA32_ID_WRITABLE(MVFR2_EL1),
 	ID_UNALLOCATED(3,3),
-	AA32_ID_SANITISED(ID_PFR2_EL1),
+	AA32_ID_WRITABLE(ID_PFR2_EL1),
 	ID_HIDDEN(ID_DFR1_EL1),
-	AA32_ID_SANITISED(ID_MMFR5_EL1),
+	AA32_ID_WRITABLE(ID_MMFR5_EL1),
 	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */
@@ -5606,11 +5609,13 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu)
 
 	guard(mutex)(&kvm->arch.config_lock);
 
-	if (!(static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) &&
-	      irqchip_in_kernel(kvm) &&
-	      kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)) {
-		kvm->arch.id_regs[IDREG_IDX(SYS_ID_AA64PFR0_EL1)] &= ~ID_AA64PFR0_EL1_GIC_MASK;
-		kvm->arch.id_regs[IDREG_IDX(SYS_ID_PFR1_EL1)] &= ~ID_PFR1_EL1_GIC_MASK;
+	if (!irqchip_in_kernel(kvm)) {
+		u64 val;
+
+		val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
+		kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val);
+		val = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;
+		kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, val);
 	}
 
 	if (vcpu_has_nv(vcpu)) {
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index 4c1209261b65d4..bb92853d1fd3a5 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -64,29 +64,37 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter)
 static int iter_mark_lpis(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long intid, flags;
 	struct vgic_irq *irq;
-	unsigned long intid;
 	int nr_lpis = 0;
 
+	xa_lock_irqsave(&dist->lpi_xa, flags);
+
 	xa_for_each(&dist->lpi_xa, intid, irq) {
 		if (!vgic_try_get_irq_ref(irq))
 			continue;
 
-		xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+		__xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
 		nr_lpis++;
 	}
 
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
 	return nr_lpis;
 }
 
 static void iter_unmark_lpis(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long intid, flags;
 	struct vgic_irq *irq;
-	unsigned long intid;
 
 	xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
-		xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+		xa_lock_irqsave(&dist->lpi_xa, flags);
+		__xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+		xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
+		/* vgic_put_irq() expects to be called outside of the xa_lock */
 		vgic_put_irq(kvm, irq);
 	}
 }
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 1796b1a22a72a1..da62edbc1205ad 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -53,7 +53,7 @@ void kvm_vgic_early_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	xa_init(&dist->lpi_xa);
+	xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ);
 }
 
 /* CREATION */
@@ -71,6 +71,7 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type);
 int kvm_vgic_create(struct kvm *kvm, u32 type)
 {
 	struct kvm_vcpu *vcpu;
+	u64 aa64pfr0, pfr1;
 	unsigned long i;
 	int ret;
 
@@ -161,10 +162,19 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 
-	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
+	aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
+	pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;
+
+	if (type == KVM_DEV_TYPE_ARM_VGIC_V2) {
 		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
-	else
+	} else {
 		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
+		aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
+		pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3);
+	}
+
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0);
+	kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1);
 
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V3)
 		kvm->arch.vgic.nassgicap = system_supports_direct_sgis();
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index ce3e3ed3f29f04..3f1c4b10fed900 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -78,6 +78,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq;
+	unsigned long flags;
 	int ret;
 
 	/* In this case there is no put, since we keep the reference. */
@@ -88,7 +89,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	if (!irq)
 		return ERR_PTR(-ENOMEM);
 
-	ret = xa_reserve(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT);
+	ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT);
 	if (ret) {
 		kfree(irq);
 		return ERR_PTR(ret);
@@ -103,7 +104,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	irq->target_vcpu = vcpu;
 	irq->group = 1;
 
-	xa_lock(&dist->lpi_xa);
+	xa_lock_irqsave(&dist->lpi_xa, flags);
 
 	/*
 	 * There could be a race with another vgic_add_lpi(), so we need to
@@ -114,21 +115,18 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 		/* Someone was faster with adding this LPI, lets use that. */
 		kfree(irq);
 		irq = oldirq;
-
-		goto out_unlock;
+	} else {
+		ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0));
 	}
 
-	ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0));
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
 	if (ret) {
 		xa_release(&dist->lpi_xa, intid);
 		kfree(irq);
-	}
-
-out_unlock:
-	xa_unlock(&dist->lpi_xa);
 
-	if (ret)
 		return ERR_PTR(ret);
+	}
 
 	/*
 	 * We "cache" the configuration table entries in our struct vgic_irq's.
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 6fbb4b09985521..2f75ef14d33999 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -301,7 +301,8 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
 		return;
 
 	/* Hide GICv3 sysreg if necessary */
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2 ||
+	    !irqchip_in_kernel(vcpu->kvm)) {
 		vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
 				      ICH_HCR_EL2_TC);
 		return;
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 6dd5a10081e27e..8d20c53faef02c 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -28,7 +28,7 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
  *     kvm->arch.config_lock (mutex)
  *       its->cmd_lock (mutex)
  *         its->its_lock (mutex)
- *           vgic_dist->lpi_xa.xa_lock
+ *           vgic_dist->lpi_xa.xa_lock		must be taken with IRQs disabled
  *             vgic_cpu->ap_list_lock		must be taken with IRQs disabled
  *               vgic_irq->irq_lock		must be taken with IRQs disabled
  *
@@ -141,32 +141,39 @@ static __must_check bool vgic_put_irq_norelease(struct kvm *kvm, struct vgic_irq
 void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long flags;
 
-	if (irq->intid >= VGIC_MIN_LPI)
-		might_lock(&dist->lpi_xa.xa_lock);
+	/*
+	 * Normally the lock is only taken when the refcount drops to 0.
+	 * Acquire/release it early on lockdep kernels to make locking issues
+	 * in rare release paths a bit more obvious.
+	 */
+	if (IS_ENABLED(CONFIG_LOCKDEP) && irq->intid >= VGIC_MIN_LPI) {
+		guard(spinlock_irqsave)(&dist->lpi_xa.xa_lock);
+	}
 
 	if (!__vgic_put_irq(kvm, irq))
 		return;
 
-	xa_lock(&dist->lpi_xa);
+	xa_lock_irqsave(&dist->lpi_xa, flags);
 	vgic_release_lpi_locked(dist, irq);
-	xa_unlock(&dist->lpi_xa);
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
 }
 
 static void vgic_release_deleted_lpis(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
-	unsigned long intid;
+	unsigned long flags, intid;
 	struct vgic_irq *irq;
 
-	xa_lock(&dist->lpi_xa);
+	xa_lock_irqsave(&dist->lpi_xa, flags);
 
 	xa_for_each(&dist->lpi_xa, intid, irq) {
 		if (irq->pending_release)
 			vgic_release_lpi_locked(dist, irq);
 	}
 
-	xa_unlock(&dist->lpi_xa);
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
 }
 
 void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index fda0346f0ea1fb..11422cb95a6440 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -689,8 +689,20 @@ bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu)
 	 */
 
 	read_lock_irqsave(&imsic->vsfile_lock, flags);
-	if (imsic->vsfile_cpu > -1)
-		ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	if (imsic->vsfile_cpu > -1) {
+		/*
+		 * This function is typically called from kvm_vcpu_block() via
+		 * kvm_arch_vcpu_runnable() upon WFI trap. The kvm_vcpu_block()
+		 * can be preempted and the blocking VCPU might resume on a
+		 * different CPU. This means it is possible that current CPU
+		 * does not match the imsic->vsfile_cpu hence this function
+		 * must check imsic->vsfile_cpu before accessing HGEIP CSR.
+		 */
+		if (imsic->vsfile_cpu != vcpu->cpu)
+			ret = true;
+		else
+			ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	}
 	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
 
 	return ret;
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 525fb5a330c0d2..58f5f3536ffdff 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -171,7 +171,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				enum kvm_mr_change change)
 {
 	hva_t hva, reg_end, size;
-	gpa_t base_gpa;
 	bool writable;
 	int ret = 0;
 
@@ -190,15 +189,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	hva = new->userspace_addr;
 	size = new->npages << PAGE_SHIFT;
 	reg_end = hva + size;
-	base_gpa = new->base_gfn << PAGE_SHIFT;
 	writable = !(new->flags & KVM_MEM_READONLY);
 
 	mmap_read_lock(current->mm);
 
 	/*
 	 * A memory region could potentially cover multiple VMAs, and
-	 * any holes between them, so iterate over all of them to find
-	 * out if we can map any of them right now.
+	 * any holes between them, so iterate over all of them.
 	 *
 	 *     +--------------------------------------------+
 	 * +---------------+----------------+   +----------------+
@@ -209,7 +206,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 */
 	do {
 		struct vm_area_struct *vma;
-		hva_t vm_start, vm_end;
+		hva_t vm_end;
 
 		vma = find_vma_intersection(current->mm, hva, reg_end);
 		if (!vma)
@@ -225,36 +222,18 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		}
 
 		/* Take the intersection of this VMA with the memory region */
-		vm_start = max(hva, vma->vm_start);
 		vm_end = min(reg_end, vma->vm_end);
 
 		if (vma->vm_flags & VM_PFNMAP) {
-			gpa_t gpa = base_gpa + (vm_start - hva);
-			phys_addr_t pa;
-
-			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
-			pa += vm_start - vma->vm_start;
-
 			/* IO region dirty page logging not allowed */
 			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
 				ret = -EINVAL;
 				goto out;
 			}
-
-			ret = kvm_riscv_mmu_ioremap(kvm, gpa, pa, vm_end - vm_start,
-						    writable, false);
-			if (ret)
-				break;
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
 
-	if (change == KVM_MR_FLAGS_ONLY)
-		goto out;
-
-	if (ret)
-		kvm_riscv_mmu_iounmap(kvm, base_gpa, size);
-
 out:
 	mmap_read_unlock(current->mm);
 	return ret;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index bccb919ca6153f..5ce35aba60696c 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -212,7 +212,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
+	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1ULL) &&
 		!kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause);
 }
 
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 9792e329343e87..1baa86dfe02932 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -93,6 +93,7 @@
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
 #define EXIT_REASON_NOTIFY              75
+#define EXIT_REASON_SEAMCALL            76
 #define EXIT_REASON_TDCALL              77
 #define EXIT_REASON_MSR_READ_IMM        84
 #define EXIT_REASON_MSR_WRITE_IMM       85
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index f286b5706d7c14..fef00546c88566 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -216,7 +216,7 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm)
  * This function is called from IOMMU driver to notify
  * SVM to schedule in a particular vCPU of a particular VM.
  */
-int avic_ga_log_notifier(u32 ga_tag)
+static int avic_ga_log_notifier(u32 ga_tag)
 {
 	unsigned long flags;
 	struct kvm_svm *kvm_svm;
@@ -788,7 +788,7 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	INIT_LIST_HEAD(&svm->ir_list);
-	spin_lock_init(&svm->ir_list_lock);
+	raw_spin_lock_init(&svm->ir_list_lock);
 
 	if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm))
 		return 0;
@@ -816,9 +816,9 @@ static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd)
 	if (!vcpu)
 		return;
 
-	spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
+	raw_spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
 	list_del(&irqfd->vcpu_list);
-	spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
+	raw_spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
 }
 
 int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
@@ -855,7 +855,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		 * list of IRQs being posted to the vCPU, to ensure the IRTE
 		 * isn't programmed with stale pCPU/IsRunning information.
 		 */
-		guard(spinlock_irqsave)(&svm->ir_list_lock);
+		guard(raw_spinlock_irqsave)(&svm->ir_list_lock);
 
 		/*
 		 * Update the target pCPU for IOMMU doorbells if the vCPU is
@@ -972,7 +972,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
 	 * up-to-date entry information, or that this task will wait until
 	 * svm_ir_list_add() completes to set the new target pCPU.
 	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
+	raw_spin_lock_irqsave(&svm->ir_list_lock, flags);
 
 	entry = svm->avic_physical_id_entry;
 	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
@@ -997,7 +997,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
 
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action);
 
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -1035,7 +1035,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
 	 * or that this task will wait until svm_ir_list_add() completes to
 	 * mark the vCPU as not running.
 	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
+	raw_spin_lock_irqsave(&svm->ir_list_lock, flags);
 
 	avic_update_iommu_vcpu_affinity(vcpu, -1, action);
 
@@ -1059,7 +1059,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
 
 	svm->avic_physical_id_entry = entry;
 
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
 void avic_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1243,3 +1243,9 @@ bool __init avic_hardware_setup(void)
 
 	return true;
 }
+
+void avic_hardware_unsetup(void)
+{
+	if (avic)
+		amd_iommu_register_ga_log_notifier(NULL);
+}
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index a6443feab2520d..da6e80b3ac353c 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -677,11 +677,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 		 */
 		svm_copy_lbrs(vmcb02, vmcb12);
 		vmcb02->save.dbgctl &= ~DEBUGCTL_RESERVED_BITS;
-		svm_update_lbrv(&svm->vcpu);
-
-	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
+	} else {
 		svm_copy_lbrs(vmcb02, vmcb01);
 	}
+	svm_update_lbrv(&svm->vcpu);
 }
 
 static inline bool is_evtinj_soft(u32 evtinj)
@@ -833,11 +832,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 			svm->soft_int_next_rip = vmcb12_rip;
 	}
 
-	vmcb02->control.virt_ext            = vmcb01->control.virt_ext &
-					      LBR_CTL_ENABLE_MASK;
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV))
-		vmcb02->control.virt_ext  |=
-			(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK);
+	/* LBR_CTL_ENABLE_MASK is controlled by svm_update_lbrv() */
 
 	if (!nested_vmcb_needs_vls_intercept(svm))
 		vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
@@ -1189,13 +1184,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
 	if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
-		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
+		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)))
 		svm_copy_lbrs(vmcb12, vmcb02);
-		svm_update_lbrv(vcpu);
-	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
+	else
 		svm_copy_lbrs(vmcb01, vmcb02);
-		svm_update_lbrv(vcpu);
-	}
+
+	svm_update_lbrv(vcpu);
 
 	if (vnmi) {
 		if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 153c12dbf3eb15..10c21e4c5406f9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -806,60 +806,43 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
 }
 
-void svm_enable_lbrv(struct kvm_vcpu *vcpu)
+static void __svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
-	svm_recalc_lbr_msr_intercepts(vcpu);
-
-	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
-	if (is_guest_mode(vcpu))
-		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
+	to_svm(vcpu)->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
 }
 
-static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
+void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
-	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
+	__svm_enable_lbrv(vcpu);
 	svm_recalc_lbr_msr_intercepts(vcpu);
-
-	/*
-	 * Move the LBR msrs back to the vmcb01 to avoid copying them
-	 * on nested guest entries.
-	 */
-	if (is_guest_mode(vcpu))
-		svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb);
 }
 
-static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm)
+static void __svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * If LBR virtualization is disabled, the LBR MSRs are always kept in
-	 * vmcb01.  If LBR virtualization is enabled and L1 is running VMs of
-	 * its own, the MSRs are moved between vmcb01 and vmcb02 as needed.
-	 */
-	return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb :
-								   svm->vmcb01.ptr;
+	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
+	to_svm(vcpu)->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
 }
 
 void svm_update_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK;
-	bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) ||
+	bool enable_lbrv = (svm->vmcb->save.dbgctl & DEBUGCTLMSR_LBR) ||
 			    (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
 			    (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK));
 
-	if (enable_lbrv == current_enable_lbrv)
-		return;
+	if (enable_lbrv && !current_enable_lbrv)
+		__svm_enable_lbrv(vcpu);
+	else if (!enable_lbrv && current_enable_lbrv)
+		__svm_disable_lbrv(vcpu);
 
-	if (enable_lbrv)
-		svm_enable_lbrv(vcpu);
-	else
-		svm_disable_lbrv(vcpu);
+	/*
+	 * During nested transitions, it is possible that the current VMCB has
+	 * LBR_CTL set, but the previous LBR_CTL had it cleared (or vice versa).
+	 * In this case, even though LBR_CTL does not need an update, intercepts
+	 * do, so always recalculate the intercepts here.
+	 */
+	svm_recalc_lbr_msr_intercepts(vcpu);
 }
 
 void disable_nmi_singlestep(struct vcpu_svm *svm)
@@ -921,6 +904,8 @@ static void svm_hardware_unsetup(void)
 {
 	int cpu;
 
+	avic_hardware_unsetup();
+
 	sev_hardware_unsetup();
 
 	for_each_possible_cpu(cpu)
@@ -2722,19 +2707,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = svm->tsc_aux;
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl;
+		msr_info->data = svm->vmcb->save.dbgctl;
 		break;
 	case MSR_IA32_LASTBRANCHFROMIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from;
+		msr_info->data = svm->vmcb->save.br_from;
 		break;
 	case MSR_IA32_LASTBRANCHTOIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to;
+		msr_info->data = svm->vmcb->save.br_to;
 		break;
 	case MSR_IA32_LASTINTFROMIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from;
+		msr_info->data = svm->vmcb->save.last_excp_from;
 		break;
 	case MSR_IA32_LASTINTTOIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to;
+		msr_info->data = svm->vmcb->save.last_excp_to;
 		break;
 	case MSR_VM_HSAVE_PA:
 		msr_info->data = svm->nested.hsave_msr;
@@ -3002,7 +2987,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
-		svm_get_lbr_vmcb(svm)->save.dbgctl = data;
+		if (svm->vmcb->save.dbgctl == data)
+			break;
+
+		svm->vmcb->save.dbgctl = data;
+		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
 		svm_update_lbrv(vcpu);
 		break;
 	case MSR_VM_HSAVE_PA:
@@ -5386,12 +5375,6 @@ static __init int svm_hardware_setup(void)
 
 	svm_hv_hardware_setup();
 
-	for_each_possible_cpu(cpu) {
-		r = svm_cpu_init(cpu);
-		if (r)
-			goto err;
-	}
-
 	enable_apicv = avic_hardware_setup();
 	if (!enable_apicv) {
 		enable_ipiv = false;
@@ -5435,6 +5418,13 @@ static __init int svm_hardware_setup(void)
 	svm_set_cpu_caps();
 
 	kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED;
+
+	for_each_possible_cpu(cpu) {
+		r = svm_cpu_init(cpu);
+		if (r)
+			goto err;
+	}
+
 	return 0;
 
 err:
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e4b04f435b3d03..c856d8e0f95e7c 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -329,7 +329,7 @@ struct vcpu_svm {
 	 * back into remapped mode).
 	 */
 	struct list_head ir_list;
-	spinlock_t ir_list_lock;
+	raw_spinlock_t ir_list_lock;
 
 	struct vcpu_sev_es_state sev_es;
 
@@ -805,7 +805,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 )
 
 bool __init avic_hardware_setup(void);
-int avic_ga_log_notifier(u32 ga_tag);
+void avic_hardware_unsetup(void);
 void avic_vm_destroy(struct kvm *kvm);
 int avic_vm_init(struct kvm *kvm);
 void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb);
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index bc5ece76533ae2..412d0829d7a217 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -98,7 +98,7 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa,
 	error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK)
 		      ? PFERR_PRESENT_MASK : 0;
 
-	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
+	if (exit_qualification & EPT_VIOLATION_GVA_IS_VALID)
 		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
 			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 76271962cb7083..bcea087b642fd0 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6728,6 +6728,14 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_NOTIFY:
 		/* Notify VM exit is not exposed to L1 */
 		return false;
+	case EXIT_REASON_SEAMCALL:
+	case EXIT_REASON_TDCALL:
+		/*
+		 * SEAMCALL and TDCALL unconditionally VM-Exit, but aren't
+		 * virtualized by KVM for L1 hypervisors, i.e. L1 should
+		 * never want or expect such an exit.
+		 */
+		return false;
 	default:
 		return true;
 	}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f87c216d976d7d..91b6f2f3edc2ab 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6032,6 +6032,12 @@ static int handle_vmx_instruction(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_tdx_instruction(struct kvm_vcpu *vcpu)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
 #ifndef CONFIG_X86_SGX_KVM
 static int handle_encls(struct kvm_vcpu *vcpu)
 {
@@ -6157,6 +6163,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_ENCLS]		      = handle_encls,
 	[EXIT_REASON_BUS_LOCK]                = handle_bus_lock_vmexit,
 	[EXIT_REASON_NOTIFY]		      = handle_notify,
+	[EXIT_REASON_SEAMCALL]		      = handle_tdx_instruction,
+	[EXIT_REASON_TDCALL]		      = handle_tdx_instruction,
 	[EXIT_REASON_MSR_READ_IMM]            = handle_rdmsr_imm,
 	[EXIT_REASON_MSR_WRITE_IMM]           = handle_wrmsr_imm,
 };
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b4b5d2d0963467..c9c2aa6f4705e1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3874,15 +3874,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 
 /*
  * Returns true if the MSR in question is managed via XSTATE, i.e. is context
- * switched with the rest of guest FPU state.  Note!  S_CET is _not_ context
- * switched via XSTATE even though it _is_ saved/restored via XSAVES/XRSTORS.
- * Because S_CET is loaded on VM-Enter and VM-Exit via dedicated VMCS fields,
- * the value saved/restored via XSTATE is always the host's value.  That detail
- * is _extremely_ important, as the guest's S_CET must _never_ be resident in
- * hardware while executing in the host.  Loading guest values for U_CET and
- * PL[0-3]_SSP while executing in the kernel is safe, as U_CET is specific to
- * userspace, and PL[0-3]_SSP are only consumed when transitioning to lower
- * privilege levels, i.e. are effectively only consumed by userspace as well.
+ * switched with the rest of guest FPU state.
+ *
+ * Note, S_CET is _not_ saved/restored via XSAVES/XRSTORS.
  */
 static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
@@ -3905,6 +3899,11 @@ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr)
  * MSR that is managed via XSTATE.  Note, the caller is responsible for doing
  * the initial FPU load, this helper only ensures that guest state is resident
  * in hardware (the kernel can load its FPU state in IRQ context).
+ *
+ * Note, loading guest values for U_CET and PL[0-3]_SSP while executing in the
+ * kernel is safe, as U_CET is specific to userspace, and PL[0-3]_SSP are only
+ * consumed when transitioning to lower privilege levels, i.e. are effectively
+ * only consumed by userspace as well.
  */
 static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu,
 						  struct msr_data *msr_info,
@@ -11807,6 +11806,9 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
+	if (KVM_BUG_ON(vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm))
+		return;
+
 	/* Exclude PKRU, it's restored separately immediately after VM-Exit. */
 	fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true);
 	trace_kvm_fpu(1);
@@ -11815,6 +11817,9 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 /* When vcpu_run ends, restore user space FPU context. */
 static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
+	if (KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm))
+		return;
+
 	fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false);
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
@@ -12137,9 +12142,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 	int r;
 
 	vcpu_load(vcpu);
-	if (kvm_mpx_supported())
-		kvm_load_guest_fpu(vcpu);
-
 	kvm_vcpu_srcu_read_lock(vcpu);
 
 	r = kvm_apic_accept_events(vcpu);
@@ -12156,9 +12158,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 
 out:
 	kvm_vcpu_srcu_read_unlock(vcpu);
-
-	if (kvm_mpx_supported())
-		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
 	return r;
 }
@@ -12788,6 +12787,7 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
 	u64 xfeatures_mask;
+	bool fpu_in_use;
 	int i;
 
 	/*
@@ -12811,13 +12811,23 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event)
 	BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX);
 
 	/*
-	 * All paths that lead to INIT are required to load the guest's FPU
-	 * state (because most paths are buried in KVM_RUN).
-	 */
-	kvm_put_guest_fpu(vcpu);
+	 * Unload guest FPU state (if necessary) before zeroing XSTATE fields
+	 * as the kernel can only modify the state when its resident in memory,
+	 * i.e. when it's not loaded into hardware.
+	 *
+	 * WARN if the vCPU's desire to run, i.e. whether or not its in KVM_RUN,
+	 * doesn't match the loaded/in-use state of the FPU, as KVM_RUN is the
+	 * only path that can trigger INIT emulation _and_ loads FPU state, and
+	 * KVM_RUN should _always_ load FPU state.
+	 */
+	WARN_ON_ONCE(vcpu->wants_to_run != fpstate->in_use);
+	fpu_in_use = fpstate->in_use;
+	if (fpu_in_use)
+		kvm_put_guest_fpu(vcpu);
 	for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX)
 		fpstate_clear_xstate_component(fpstate, i);
-	kvm_load_guest_fpu(vcpu);
+	if (fpu_in_use)
+		kvm_load_guest_fpu(vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
author	Linus Torvalds <torvalds@linux-foundation.org>	2025-11-10 08:54:36 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2025-11-10 08:54:36 -0800
commit	4ea7c1717f3f2344f7a1cdab4f5875cfa89c87a9 (patch)
tree	981d445641d11f9a623f7250fe233293742d4ec7 /arch
parent	e9a6fb0bcdd7609be6969112f3fbfcce3b1d4a7c (diff)
parent	8a4821412cf2c1429fffa07c012dd150f2edf78c (diff)
download	linux-4ea7c1717f3f2344f7a1cdab4f5875cfa89c87a9.tar.gz