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

Pull kvm fixes from Paolo Bonzini:
 "This is a bit on the large side, mostly due to two changes:

   - Changes to disable some broken PMU virtualization (see below for
     details under "x86 PMU")

   - Clean up SVM's enter/exit assembly code so that it can be compiled
     without OBJECT_FILES_NON_STANDARD. This fixes a warning "Unpatched
     return thunk in use. This should not happen!" when running KVM
     selftests.

  Everything else is small bugfixes and selftest changes:

   - Fix a mostly benign bug in the gfn_to_pfn_cache infrastructure
     where KVM would allow userspace to refresh the cache with a bogus
     GPA. The bug has existed for quite some time, but was exposed by a
     new sanity check added in 6.9 (to ensure a cache is either
     GPA-based or HVA-based).

   - Drop an unused param from gfn_to_pfn_cache_invalidate_start() that
     got left behind during a 6.9 cleanup.

   - Fix a math goof in x86's hugepage logic for
     KVM_SET_MEMORY_ATTRIBUTES that results in an array overflow
     (detected by KASAN).

   - Fix a bug where KVM incorrectly clears root_role.direct when
     userspace sets guest CPUID.

   - Fix a dirty logging bug in the where KVM fails to write-protect
     SPTEs used by a nested guest, if KVM is using Page-Modification
     Logging and the nested hypervisor is NOT using EPT.

  x86 PMU:

   - Drop support for virtualizing adaptive PEBS, as KVM's
     implementation is architecturally broken without an obvious/easy
     path forward, and because exposing adaptive PEBS can leak host LBRs
     to the guest, i.e. can leak host kernel addresses to the guest.

   - Set the enable bits for general purpose counters in
     PERF_GLOBAL_CTRL at RESET time, as done by both Intel and AMD
     processors.

   - Disable LBR virtualization on CPUs that don't support LBR
     callstacks, as KVM unconditionally uses
     PERF_SAMPLE_BRANCH_CALL_STACK when creating the perf event, and
     would fail on such CPUs.

  Tests:

   - Fix a flaw in the max_guest_memory selftest that results in it
     exhausting the supply of ucall structures when run with more than
     256 vCPUs.

   - Mark KVM_MEM_READONLY as supported for RISC-V in
     set_memory_region_test"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (30 commits)
  KVM: Drop unused @may_block param from gfn_to_pfn_cache_invalidate_start()
  KVM: selftests: Add coverage of EPT-disabled to vmx_dirty_log_test
  KVM: x86/mmu: Fix and clarify comments about clearing D-bit vs. write-protecting
  KVM: x86/mmu: Remove function comments above clear_dirty_{gfn_range,pt_masked}()
  KVM: x86/mmu: Write-protect L2 SPTEs in TDP MMU when clearing dirty status
  KVM: x86/mmu: Precisely invalidate MMU root_role during CPUID update
  KVM: VMX: Disable LBR virtualization if the CPU doesn't support LBR callstacks
  perf/x86/intel: Expose existence of callback support to KVM
  KVM: VMX: Snapshot LBR capabilities during module initialization
  KVM: x86/pmu: Do not mask LVTPC when handling a PMI on AMD platforms
  KVM: x86: Snapshot if a vCPU's vendor model is AMD vs. Intel compatible
  KVM: x86: Stop compiling vmenter.S with OBJECT_FILES_NON_STANDARD
  KVM: SVM: Create a stack frame in __svm_sev_es_vcpu_run()
  KVM: SVM: Save/restore args across SEV-ES VMRUN via host save area
  KVM: SVM: Save/restore non-volatile GPRs in SEV-ES VMRUN via host save area
  KVM: SVM: Clobber RAX instead of RBX when discarding spec_ctrl_intercepted
  KVM: SVM: Drop 32-bit "support" from __svm_sev_es_vcpu_run()
  KVM: SVM: Wrap __svm_sev_es_vcpu_run() with #ifdef CONFIG_KVM_AMD_SEV
  KVM: SVM: Create a stack frame in __svm_vcpu_run() for unwinding
  KVM: SVM: Remove a useless zeroing of allocated memory
  ...

25 files changed, 267 insertions, 159 deletions

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 78cd5084104e..4367aa77cb8d 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1693,6 +1693,7 @@ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
 	lbr->from = x86_pmu.lbr_from;
 	lbr->to = x86_pmu.lbr_to;
 	lbr->info = x86_pmu.lbr_info;
+	lbr->has_callstack = x86_pmu_has_lbr_callstack();
 }
 EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 16e07a2eee19..6efd1497b026 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -855,6 +855,7 @@ struct kvm_vcpu_arch {
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	struct kvm_hypervisor_cpuid kvm_cpuid;
+	bool is_amd_compatible;
 
 	/*
 	 * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 3736b8a46c04..7f1e17250546 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -555,6 +555,7 @@ struct x86_pmu_lbr {
 	unsigned int	from;
 	unsigned int	to;
 	unsigned int	info;
+	bool		has_callstack;
 };
 
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a88bb14266b6..addc44fc7187 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -3,11 +3,6 @@
 ccflags-y += -I $(srctree)/arch/x86/kvm
 ccflags-$(CONFIG_KVM_WERROR) += -Werror
 
-ifeq ($(CONFIG_FRAME_POINTER),y)
-OBJECT_FILES_NON_STANDARD_vmx/vmenter.o := y
-OBJECT_FILES_NON_STANDARD_svm/vmenter.o := y
-endif
-
 include $(srctree)/virt/kvm/Makefile.kvm
 
 kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bfc0bfcb2bc6..77352a4abd87 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -376,6 +376,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	kvm_update_pv_runtime(vcpu);
 
+	vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu);
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 	vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu);
 
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 856e3037e74f..23dbb9eb277c 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -120,6 +120,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu)
 	return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx);
 }
 
+static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.is_amd_compatible;
+}
+
+static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu)
+{
+	return !guest_cpuid_is_amd_compatible(vcpu);
+}
+
 static inline int guest_cpuid_family(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cf37586f0466..ebf41023be38 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2776,7 +2776,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
 		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
 
 		r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
-		if (r && lvt_type == APIC_LVTPC)
+		if (r && lvt_type == APIC_LVTPC &&
+		    guest_cpuid_is_intel_compatible(apic->vcpu))
 			kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
 		return r;
 	}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 992e651540e8..db007a4dffa2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4935,7 +4935,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 				context->cpu_role.base.level, is_efer_nx(context),
 				guest_can_use(vcpu, X86_FEATURE_GBPAGES),
 				is_cr4_pse(context),
-				guest_cpuid_is_amd_or_hygon(vcpu));
+				guest_cpuid_is_amd_compatible(vcpu));
 }
 
 static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
@@ -5576,9 +5576,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * 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.root_role.word = 0;
-	vcpu->arch.guest_mmu.root_role.word = 0;
-	vcpu->arch.nested_mmu.root_role.word = 0;
+	vcpu->arch.root_mmu.root_role.invalid = 1;
+	vcpu->arch.guest_mmu.root_role.invalid = 1;
+	vcpu->arch.nested_mmu.root_role.invalid = 1;
 	vcpu->arch.root_mmu.cpu_role.ext.valid = 0;
 	vcpu->arch.guest_mmu.cpu_role.ext.valid = 0;
 	vcpu->arch.nested_mmu.cpu_role.ext.valid = 0;
@@ -7399,7 +7399,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 			 * by the memslot, KVM can't use a hugepage due to the
 			 * misaligned address regardless of memory attributes.
 			 */
-			if (gfn >= slot->base_gfn) {
+			if (gfn >= slot->base_gfn &&
+			    gfn + nr_pages <= slot->base_gfn + slot->npages) {
 				if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
 					hugepage_clear_mixed(slot, gfn, level);
 				else
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d078157e62aa..04c1f0957fea 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1548,17 +1548,21 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
 	}
 }
 
-/*
- * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
- * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
- * If AD bits are not enabled, this will require clearing the writable bit on
- * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
- * be flushed.
- */
+static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp)
+{
+	/*
+	 * All TDP MMU shadow pages share the same role as their root, aside
+	 * from level, so it is valid to key off any shadow page to determine if
+	 * write protection is needed for an entire tree.
+	 */
+	return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled();
+}
+
 static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			   gfn_t start, gfn_t end)
 {
-	u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK;
+	const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK :
+							    shadow_dirty_mask;
 	struct tdp_iter iter;
 	bool spte_set = false;
 
@@ -1573,7 +1577,7 @@ retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
 
-		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+		KVM_MMU_WARN_ON(dbit == shadow_dirty_mask &&
 				spte_ad_need_write_protect(iter.old_spte));
 
 		if (!(iter.old_spte & dbit))
@@ -1590,11 +1594,9 @@ retry:
 }
 
 /*
- * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
- * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
- * If AD bits are not enabled, this will require clearing the writable bit on
- * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
- * be flushed.
+ * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the
+ * memslot. Returns true if an SPTE has been changed and the TLBs need to be
+ * flushed.
  */
 bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
 				  const struct kvm_memory_slot *slot)
@@ -1610,18 +1612,11 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
 	return spte_set;
 }
 
-/*
- * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
- * set in mask, starting at gfn. The given memslot is expected to contain all
- * the GFNs represented by set bits in the mask. If AD bits are enabled,
- * clearing the dirty status will involve clearing the dirty bit on each SPTE
- * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
- */
 static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 				  gfn_t gfn, unsigned long mask, bool wrprot)
 {
-	u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK :
-						   shadow_dirty_mask;
+	const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK :
+									shadow_dirty_mask;
 	struct tdp_iter iter;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
@@ -1633,7 +1628,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 		if (!mask)
 			break;
 
-		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+		KVM_MMU_WARN_ON(dbit == shadow_dirty_mask &&
 				spte_ad_need_write_protect(iter.old_spte));
 
 		if (iter.level > PG_LEVEL_4K ||
@@ -1659,11 +1654,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 }
 
 /*
- * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
- * set in mask, starting at gfn. The given memslot is expected to contain all
- * the GFNs represented by set bits in the mask. If AD bits are enabled,
- * clearing the dirty status will involve clearing the dirty bit on each SPTE
- * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for
+ * which a bit is set in mask, starting at gfn. The given memslot is expected to
+ * contain all the GFNs represented by set bits in the mask.
  */
 void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				       struct kvm_memory_slot *slot,
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c397b28e3d1b..a593b03c9aed 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -775,8 +775,20 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->pebs_data_cfg_mask = ~0ull;
 	bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
 
-	if (vcpu->kvm->arch.enable_pmu)
-		static_call(kvm_x86_pmu_refresh)(vcpu);
+	if (!vcpu->kvm->arch.enable_pmu)
+		return;
+
+	static_call(kvm_x86_pmu_refresh)(vcpu);
+
+	/*
+	 * At RESET, both Intel and AMD CPUs set all enable bits for general
+	 * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that
+	 * was written for v1 PMUs don't unknowingly leave GP counters disabled
+	 * in the global controls).  Emulate that behavior when refreshing the
+	 * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL.
+	 */
+	if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters)
+		pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0);
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 61a7531d41b0..759581bb2128 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -434,7 +434,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 	/* Avoid using vmalloc for smaller buffers. */
 	size = npages * sizeof(struct page *);
 	if (size > PAGE_SIZE)
-		pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+		pages = __vmalloc(size, GFP_KERNEL_ACCOUNT);
 	else
 		pages = kmalloc(size, GFP_KERNEL_ACCOUNT);
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d1a9f9951635..9aaf83c8d57d 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1503,6 +1503,11 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
 }
 
+static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd)
+{
+	return page_address(sd->save_area) + 0x400;
+}
+
 static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1519,12 +1524,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	 * or subsequent vmload of host save area.
 	 */
 	vmsave(sd->save_area_pa);
-	if (sev_es_guest(vcpu->kvm)) {
-		struct sev_es_save_area *hostsa;
-		hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
-
-		sev_es_prepare_switch_to_guest(hostsa);
-	}
+	if (sev_es_guest(vcpu->kvm))
+		sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd));
 
 	if (tsc_scaling)
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
@@ -4101,6 +4102,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 
 static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted)
 {
+	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	guest_state_enter_irqoff();
@@ -4108,7 +4110,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	amd_clear_divider();
 
 	if (sev_es_guest(vcpu->kvm))
-		__svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted);
+		__svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted,
+				      sev_es_host_save_area(sd));
 	else
 		__svm_vcpu_run(svm, spec_ctrl_intercepted);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 7f1fbd874c45..33878efdebc8 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -698,7 +698,8 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
 
 /* vmenter.S */
 
-void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
+void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted,
+			   struct sev_es_save_area *hostsa);
 void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
 
 #define DEFINE_KVM_GHCB_ACCESSORS(field)						\
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 187018c424bf..a0c8eb37d3e1 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -3,6 +3,7 @@
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/bitsperlong.h>
+#include <asm/frame.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/nospec-branch.h>
 #include "kvm-asm-offsets.h"
@@ -67,7 +68,7 @@
 		"", X86_FEATURE_V_SPEC_CTRL
 901:
 .endm
-.macro RESTORE_HOST_SPEC_CTRL_BODY
+.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req
 900:
 	/* Same for after vmexit.  */
 	mov $MSR_IA32_SPEC_CTRL, %ecx
@@ -76,7 +77,7 @@
 	 * Load the value that the guest had written into MSR_IA32_SPEC_CTRL,
 	 * if it was not intercepted during guest execution.
 	 */
-	cmpb $0, (%_ASM_SP)
+	cmpb $0, \spec_ctrl_intercepted
 	jnz 998f
 	rdmsr
 	movl %eax, SVM_spec_ctrl(%_ASM_DI)
@@ -99,6 +100,7 @@
  */
 SYM_FUNC_START(__svm_vcpu_run)
 	push %_ASM_BP
+	mov  %_ASM_SP, %_ASM_BP
 #ifdef CONFIG_X86_64
 	push %r15
 	push %r14
@@ -268,7 +270,7 @@ SYM_FUNC_START(__svm_vcpu_run)
 	RET
 
 	RESTORE_GUEST_SPEC_CTRL_BODY
-	RESTORE_HOST_SPEC_CTRL_BODY
+	RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP)
 
 10:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
@@ -290,66 +292,68 @@ SYM_FUNC_START(__svm_vcpu_run)
 
 SYM_FUNC_END(__svm_vcpu_run)
 
+#ifdef CONFIG_KVM_AMD_SEV
+
+
+#ifdef CONFIG_X86_64
+#define SEV_ES_GPRS_BASE 0x300
+#define SEV_ES_RBX	(SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE)
+#define SEV_ES_RBP	(SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE)
+#define SEV_ES_RSI	(SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE)
+#define SEV_ES_RDI	(SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE)
+#define SEV_ES_R12	(SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE)
+#define SEV_ES_R13	(SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE)
+#define SEV_ES_R14	(SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE)
+#define SEV_ES_R15	(SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE)
+#endif
+
 /**
  * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode
  * @svm:	struct vcpu_svm *
  * @spec_ctrl_intercepted: bool
  */
 SYM_FUNC_START(__svm_sev_es_vcpu_run)
-	push %_ASM_BP
-#ifdef CONFIG_X86_64
-	push %r15
-	push %r14
-	push %r13
-	push %r12
-#else
-	push %edi
-	push %esi
-#endif
-	push %_ASM_BX
+	FRAME_BEGIN
 
 	/*
-	 * Save variables needed after vmexit on the stack, in inverse
-	 * order compared to when they are needed.
+	 * Save non-volatile (callee-saved) registers to the host save area.
+	 * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not
+	 * saved on VMRUN.
 	 */
+	mov %rbp, SEV_ES_RBP (%rdx)
+	mov %r15, SEV_ES_R15 (%rdx)
+	mov %r14, SEV_ES_R14 (%rdx)
+	mov %r13, SEV_ES_R13 (%rdx)
+	mov %r12, SEV_ES_R12 (%rdx)
+	mov %rbx, SEV_ES_RBX (%rdx)
 
-	/* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL.  */
-	push %_ASM_ARG2
-
-	/* Save @svm. */
-	push %_ASM_ARG1
-
-.ifnc _ASM_ARG1, _ASM_DI
 	/*
-	 * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX
-	 * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL.
+	 * Save volatile registers that hold arguments that are needed after
+	 * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted).
 	 */
-	mov %_ASM_ARG1, %_ASM_DI
-.endif
+	mov %rdi, SEV_ES_RDI (%rdx)
+	mov %rsi, SEV_ES_RSI (%rdx)
 
-	/* Clobbers RAX, RCX, RDX.  */
+	/* Clobbers RAX, RCX, RDX (@hostsa). */
 	RESTORE_GUEST_SPEC_CTRL
 
 	/* Get svm->current_vmcb->pa into RAX. */
-	mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
-	mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
+	mov SVM_current_vmcb(%rdi), %rax
+	mov KVM_VMCB_pa(%rax), %rax
 
 	/* Enter guest mode */
 	sti
 
-1:	vmrun %_ASM_AX
+1:	vmrun %rax
 
 2:	cli
 
-	/* Pop @svm to RDI, guest registers have been saved already. */
-	pop %_ASM_DI
-
 #ifdef CONFIG_MITIGATION_RETPOLINE
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
-	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 #endif
 
-	/* Clobbers RAX, RCX, RDX.  */
+	/* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */
 	RESTORE_HOST_SPEC_CTRL
 
 	/*
@@ -361,30 +365,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	 */
 	UNTRAIN_RET_VM
 
-	/* "Pop" @spec_ctrl_intercepted.  */
-	pop %_ASM_BX
-
-	pop %_ASM_BX
-
-#ifdef CONFIG_X86_64
-	pop %r12
-	pop %r13
-	pop %r14
-	pop %r15
-#else
-	pop %esi
-	pop %edi
-#endif
-	pop %_ASM_BP
+	FRAME_END
 	RET
 
 	RESTORE_GUEST_SPEC_CTRL_BODY
-	RESTORE_HOST_SPEC_CTRL_BODY
+	RESTORE_HOST_SPEC_CTRL_BODY %sil
 
-3:	cmpb $0, _ASM_RIP(kvm_rebooting)
+3:	cmpb $0, kvm_rebooting(%rip)
 	jne 2b
 	ud2
 
 	_ASM_EXTABLE(1b, 3b)
 
 SYM_FUNC_END(__svm_sev_es_vcpu_run)
+#endif /* CONFIG_KVM_AMD_SEV */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 12ade343a17e..be40474de6e4 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -535,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	perf_capabilities = vcpu_get_perf_capabilities(vcpu);
 	if (cpuid_model_is_consistent(vcpu) &&
 	    (perf_capabilities & PMU_CAP_LBR_FMT))
-		x86_perf_get_lbr(&lbr_desc->records);
+		memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps));
 	else
 		lbr_desc->records.nr = 0;
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c37a89eda90f..22411f4aff53 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -218,6 +218,8 @@ module_param(ple_window_max, uint, 0444);
 int __read_mostly pt_mode = PT_MODE_SYSTEM;
 module_param(pt_mode, int, S_IRUGO);
 
+struct x86_pmu_lbr __ro_after_init vmx_lbr_caps;
+
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
 static DEFINE_MUTEX(vmx_l1d_flush_mutex);
@@ -7862,10 +7864,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	vmx_update_exception_bitmap(vcpu);
 }
 
-static u64 vmx_get_perf_capabilities(void)
+static __init u64 vmx_get_perf_capabilities(void)
 {
 	u64 perf_cap = PMU_CAP_FW_WRITES;
-	struct x86_pmu_lbr lbr;
 	u64 host_perf_cap = 0;
 
 	if (!enable_pmu)
@@ -7875,15 +7876,43 @@ static u64 vmx_get_perf_capabilities(void)
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
 
 	if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) {
-		x86_perf_get_lbr(&lbr);
-		if (lbr.nr)
+		x86_perf_get_lbr(&vmx_lbr_caps);
+
+		/*
+		 * KVM requires LBR callstack support, as the overhead due to
+		 * context switching LBRs without said support is too high.
+		 * See intel_pmu_create_guest_lbr_event() for more info.
+		 */
+		if (!vmx_lbr_caps.has_callstack)
+			memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps));
+		else if (vmx_lbr_caps.nr)
 			perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
 	}
 
 	if (vmx_pebs_supported()) {
 		perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
-		if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
-			perf_cap &= ~PERF_CAP_PEBS_BASELINE;
+
+		/*
+		 * Disallow adaptive PEBS as it is functionally broken, can be
+		 * used by the guest to read *host* LBRs, and can be used to
+		 * bypass userspace event filters.  To correctly and safely
+		 * support adaptive PEBS, KVM needs to:
+		 *
+		 * 1. Account for the ADAPTIVE flag when (re)programming fixed
+		 *    counters.
+		 *
+		 * 2. Gain support from perf (or take direct control of counter
+		 *    programming) to support events without adaptive PEBS
+		 *    enabled for the hardware counter.
+		 *
+		 * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with
+		 *    adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1.
+		 *
+		 * 4. Document which PMU events are effectively exposed to the
+		 *    guest via adaptive PEBS, and make adaptive PEBS mutually
+		 *    exclusive with KVM_SET_PMU_EVENT_FILTER if necessary.
+		 */
+		perf_cap &= ~PERF_CAP_PEBS_BASELINE;
 	}
 
 	return perf_cap;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 65786dbe7d60..90f9e4434646 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -15,6 +15,7 @@
 #include "vmx_ops.h"
 #include "../cpuid.h"
 #include "run_flags.h"
+#include "../mmu.h"
 
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
@@ -109,6 +110,8 @@ struct lbr_desc {
 	bool msr_passthrough;
 };
 
+extern struct x86_pmu_lbr vmx_lbr_caps;
+
 /*
  * The nested_vmx structure is part of vcpu_vmx, and holds information we need
  * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -719,7 +722,8 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
 	if (!enable_ept)
 		return true;
 
-	return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
+	return allow_smaller_maxphyaddr &&
+	       cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits();
 }
 
 static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 984ea2089efc..91478b769af0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3470,7 +3470,7 @@ static bool is_mci_status_msr(u32 msr)
 static bool can_set_mci_status(struct kvm_vcpu *vcpu)
 {
 	/* McStatusWrEn enabled? */
-	if (guest_cpuid_is_amd_or_hygon(vcpu))
+	if (guest_cpuid_is_amd_compatible(vcpu))
 		return !!(vcpu->arch.msr_hwcr & BIT_ULL(18));
 
 	return false;
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 6628dc4dda89..1a6da7389bf1 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -22,10 +22,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
 	uint64_t gpa;
 
-	for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
-		*((volatile uint64_t *)gpa) = gpa;
-
-	GUEST_DONE();
+	for (;;) {
+		for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+			*((volatile uint64_t *)gpa) = gpa;
+		GUEST_SYNC(0);
+	}
 }
 
 struct vcpu_info {
@@ -55,7 +56,7 @@ static void rendezvous_with_boss(void)
 static void run_vcpu(struct kvm_vcpu *vcpu)
 {
 	vcpu_run(vcpu);
-	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
 }
 
 static void *vcpu_worker(void *data)
@@ -64,17 +65,13 @@ static void *vcpu_worker(void *data)
 	struct kvm_vcpu *vcpu = info->vcpu;
 	struct kvm_vm *vm = vcpu->vm;
 	struct kvm_sregs sregs;
-	struct kvm_regs regs;
 
 	vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
 
-	/* Snapshot regs before the first run. */
-	vcpu_regs_get(vcpu, &regs);
 	rendezvous_with_boss();
 
 	run_vcpu(vcpu);
 	rendezvous_with_boss();
-	vcpu_regs_set(vcpu, &regs);
 	vcpu_sregs_get(vcpu, &sregs);
 #ifdef __x86_64__
 	/* Toggle CR0.WP to trigger a MMU context reset. */
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 06b43ed23580..bd57d991e27d 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -333,7 +333,7 @@ static void test_invalid_memory_region_flags(void)
 	struct kvm_vm *vm;
 	int r, i;
 
-#if defined __aarch64__ || defined __x86_64__
+#if defined __aarch64__ || defined __riscv || defined __x86_64__
 	supported_flags |= KVM_MEM_READONLY;
 #endif
 
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
index 29609b52f8fa..26c85815f7e9 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -416,12 +416,30 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters
 
 static void guest_test_gp_counters(void)
 {
+	uint8_t pmu_version = guest_get_pmu_version();
 	uint8_t nr_gp_counters = 0;
 	uint32_t base_msr;
 
-	if (guest_get_pmu_version())
+	if (pmu_version)
 		nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
 
+	/*
+	 * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is
+	 * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number
+	 * of GP counters.  If there are no GP counters, require KVM to leave
+	 * PERF_GLOBAL_CTRL '0'.  This edge case isn't covered by the SDM, but
+	 * follow the spirit of the architecture and only globally enable GP
+	 * counters, of which there are none.
+	 */
+	if (pmu_version > 1) {
+		uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL);
+
+		if (nr_gp_counters)
+			GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0));
+		else
+			GUEST_ASSERT_EQ(global_ctrl, 0);
+	}
+
 	if (this_cpu_has(X86_FEATURE_PDCM) &&
 	    rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
 		base_msr = MSR_IA32_PMC0;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 7f6f5f23fb9b..977948fd52e6 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -28,16 +28,16 @@
 #define NESTED_TEST_MEM1		0xc0001000
 #define NESTED_TEST_MEM2		0xc0002000
 
-static void l2_guest_code(void)
+static void l2_guest_code(u64 *a, u64 *b)
 {
-	*(volatile uint64_t *)NESTED_TEST_MEM1;
-	*(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+	READ_ONCE(*a);
+	WRITE_ONCE(*a, 1);
 	GUEST_SYNC(true);
 	GUEST_SYNC(false);
 
-	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	WRITE_ONCE(*b, 1);
 	GUEST_SYNC(true);
-	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	WRITE_ONCE(*b, 1);
 	GUEST_SYNC(true);
 	GUEST_SYNC(false);
 
@@ -45,17 +45,33 @@ static void l2_guest_code(void)
 	vmcall();
 }
 
+static void l2_guest_code_ept_enabled(void)
+{
+	l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2);
+}
+
+static void l2_guest_code_ept_disabled(void)
+{
+	/* Access the same L1 GPAs as l2_guest_code_ept_enabled() */
+	l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM);
+}
+
 void l1_guest_code(struct vmx_pages *vmx)
 {
 #define L2_GUEST_STACK_SIZE 64
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	void *l2_rip;
 
 	GUEST_ASSERT(vmx->vmcs_gpa);
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
 	GUEST_ASSERT(load_vmcs(vmx));
 
-	prepare_vmcs(vmx, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	if (vmx->eptp_gpa)
+		l2_rip = l2_guest_code_ept_enabled;
+	else
+		l2_rip = l2_guest_code_ept_disabled;
+
+	prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
 
 	GUEST_SYNC(false);
 	GUEST_ASSERT(!vmlaunch());
@@ -64,7 +80,7 @@ void l1_guest_code(struct vmx_pages *vmx)
 	GUEST_DONE();
 }
 
-int main(int argc, char *argv[])
+static void test_vmx_dirty_log(bool enable_ept)
 {
 	vm_vaddr_t vmx_pages_gva = 0;
 	struct vmx_pages *vmx;
@@ -76,8 +92,7 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	bool done = false;
 
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
-	TEST_REQUIRE(kvm_cpu_has_ept());
+	pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled");
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
@@ -103,11 +118,16 @@ int main(int argc, char *argv[])
 	 *
 	 * Note that prepare_eptp should be called only L1's GPA map is done,
 	 * meaning after the last call to virt_map.
+	 *
+	 * When EPT is disabled, the L2 guest code will still access the same L1
+	 * GPAs as the EPT enabled case.
 	 */
-	prepare_eptp(vmx, vm, 0);
-	nested_map_memslot(vmx, vm, 0);
-	nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
-	nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+	if (enable_ept) {
+		prepare_eptp(vmx, vm, 0);
+		nested_map_memslot(vmx, vm, 0);
+		nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
+		nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+	}
 
 	bmap = bitmap_zalloc(TEST_MEM_PAGES);
 	host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
@@ -148,3 +168,15 @@ int main(int argc, char *argv[])
 		}
 	}
 }
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+
+	test_vmx_dirty_log(/*enable_ept=*/false);
+
+	if (kvm_cpu_has_ept())
+		test_vmx_dirty_log(/*enable_ept=*/true);
+
+	return 0;
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fb49c2a60200..ff0a20565f90 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -832,8 +832,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * mn_active_invalidate_count (see above) instead of
 	 * mmu_invalidate_in_progress.
 	 */
-	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
-					  hva_range.may_block);
+	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end);
 
 	/*
 	 * If one or more memslots were found and thus zapped, notify arch code
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index ecefc7ec51af..715f19669d01 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -26,13 +26,11 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
 #ifdef CONFIG_HAVE_KVM_PFNCACHE
 void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 				       unsigned long start,
-				       unsigned long end,
-				       bool may_block);
+				       unsigned long end);
 #else
 static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 						     unsigned long start,
-						     unsigned long end,
-						     bool may_block)
+						     unsigned long end)
 {
 }
 #endif /* HAVE_KVM_PFNCACHE */
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 4e07112a24c2..e3453e869e92 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -23,7 +23,7 @@
  * MMU notifier 'invalidate_range_start' hook.
  */
 void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
-				       unsigned long end, bool may_block)
+				       unsigned long end)
 {
 	struct gfn_to_pfn_cache *gpc;
 
@@ -57,6 +57,19 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
 	spin_unlock(&kvm->gpc_lock);
 }
 
+static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva,
+				 unsigned long len)
+{
+	unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) :
+						       offset_in_page(gpa);
+
+	/*
+	 * The cached access must fit within a single page. The 'len' argument
+	 * to activate() and refresh() exists only to enforce that.
+	 */
+	return offset + len <= PAGE_SIZE;
+}
+
 bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
 {
 	struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
@@ -74,7 +87,7 @@ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
 	if (kvm_is_error_hva(gpc->uhva))
 		return false;
 
-	if (offset_in_page(gpc->uhva) + len > PAGE_SIZE)
+	if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len))
 		return false;
 
 	if (!gpc->valid)
@@ -232,8 +245,7 @@ out_error:
 	return -EFAULT;
 }
 
-static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva,
-			     unsigned long len)
+static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva)
 {
 	unsigned long page_offset;
 	bool unmap_old = false;
@@ -247,15 +259,6 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l
 	if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva)))
 		return -EINVAL;
 
-	/*
-	 * The cached acces must fit within a single page. The 'len' argument
-	 * exists only to enforce that.
-	 */
-	page_offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) :
-					      offset_in_page(gpa);
-	if (page_offset + len > PAGE_SIZE)
-		return -EINVAL;
-
 	lockdep_assert_held(&gpc->refresh_lock);
 
 	write_lock_irq(&gpc->lock);
@@ -270,6 +273,8 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l
 	old_uhva = PAGE_ALIGN_DOWN(gpc->uhva);
 
 	if (kvm_is_error_gpa(gpa)) {
+		page_offset = offset_in_page(uhva);
+
 		gpc->gpa = INVALID_GPA;
 		gpc->memslot = NULL;
 		gpc->uhva = PAGE_ALIGN_DOWN(uhva);
@@ -279,6 +284,8 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l
 	} else {
 		struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
 
+		page_offset = offset_in_page(gpa);
+
 		if (gpc->gpa != gpa || gpc->generation != slots->generation ||
 		    kvm_is_error_hva(gpc->uhva)) {
 			gfn_t gfn = gpa_to_gfn(gpa);
@@ -354,6 +361,9 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len)
 
 	guard(mutex)(&gpc->refresh_lock);
 
+	if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len))
+		return -EINVAL;
+
 	/*
 	 * If the GPA is valid then ignore the HVA, as a cache can be GPA-based
 	 * or HVA-based, not both.  For GPA-based caches, the HVA will be
@@ -361,7 +371,7 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len)
 	 */
 	uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD;
 
-	return __kvm_gpc_refresh(gpc, gpc->gpa, uhva, len);
+	return __kvm_gpc_refresh(gpc, gpc->gpa, uhva);
 }
 
 void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm)
@@ -381,6 +391,9 @@ static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned
 {
 	struct kvm *kvm = gpc->kvm;
 
+	if (!kvm_gpc_is_valid_len(gpa, uhva, len))
+		return -EINVAL;
+
 	guard(mutex)(&gpc->refresh_lock);
 
 	if (!gpc->active) {
@@ -400,11 +413,18 @@ static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned
 		gpc->active = true;
 		write_unlock_irq(&gpc->lock);
 	}
-	return __kvm_gpc_refresh(gpc, gpa, uhva, len);
+	return __kvm_gpc_refresh(gpc, gpa, uhva);
 }
 
 int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
 {
+	/*
+	 * Explicitly disallow INVALID_GPA so that the magic value can be used
+	 * by KVM to differentiate between GPA-based and HVA-based caches.
+	 */
+	if (WARN_ON_ONCE(kvm_is_error_gpa(gpa)))
+		return -EINVAL;
+
 	return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len);
 }