Merge tag 'kvm-x86-misc-7.2' of https://github.com/kvm-x86/linux into HEAD

KVM misc x86 changes for 7.2

 - Handle EXIT_FASTPATH_EXIT_USERSPACE in vendor code to ensure vendor code
   gets a chance to handle things like reaping the PML buffer.

 - Ensure KVM's copy of CR0 and CR3 are up-to-date on SVM prior to invoking
   fastpath handlers.

 - Update KVM's view of PV async enabling if and only if the MSR write fully
   succeeds.

 - Fix a variety of issues where the emulator doesn't honor guest-debug state,
   and clean up related code along the way.

 - Synthesize EPT Violation and #NPF "error code" bits when injecting faults
   into L1 that didn't originate in hardware (in which case the VMCS/VMCB
   doesn't hold relevant information).

 - Add support for virtualizing (well, emulating) AMD's flavor of CPL>0 CPUID
   faulting.

 - Clean up the GPR APIs so that KVM's use of "raw" is consistent, and fix a
   variety of minor bugs along the way.

 - Fix an OOB memory access due to not checking the VP ID when handling a
   Hyper-V PV TLB flush for L2.

 - Fix a bug in the mediated PMU's handling of fixed counters that allowed the
   guest to bypass the PMU event filter.

 - Allow userspace to return EAGAIN when handling SNP and TDX hypercalls, so
   the KVM can forward a "retry" status code to the guest, and reserve all
   unused error codes for future usage.

 - Misc fixes and cleanups.

8 files changed, 442 insertions, 8 deletions

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 9118a5a51b89..0a0a02a1dffe 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -97,6 +97,7 @@ TEST_GEN_PROGS_x86 += x86/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
 TEST_GEN_PROGS_x86 += x86/nested_invalid_cr3_test
 TEST_GEN_PROGS_x86 += x86/nested_set_state_test
+TEST_GEN_PROGS_x86 += x86/nested_tdp_fault_test
 TEST_GEN_PROGS_x86 += x86/nested_tsc_adjust_test
 TEST_GEN_PROGS_x86 += x86/nested_tsc_scaling_test
 TEST_GEN_PROGS_x86 += x86/nested_vmsave_vmload_test
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 77f576ee7789..513e4a1075fa 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -38,7 +38,24 @@ extern u64 guest_tsc_khz;
 
 const char *ex_str(int vector);
 
-#define X86_EFLAGS_FIXED	 (1u << 1)
+#define X86_EFLAGS_CF		BIT(0)  /* Carry Flag */
+#define X86_EFLAGS_FIXED	BIT(1)  /* Bit 1 - always on */
+#define X86_EFLAGS_PF		BIT(2)  /* Parity Flag */
+#define X86_EFLAGS_AF		BIT(4)  /* Auxiliary carry Flag */
+#define X86_EFLAGS_ZF		BIT(6)  /* Zero Flag */
+#define X86_EFLAGS_SF		BIT(7)  /* Sign Flag */
+#define X86_EFLAGS_TF		BIT(8)  /* Trap Flag */
+#define X86_EFLAGS_IF		BIT(9)  /* Interrupt Flag */
+#define X86_EFLAGS_DF		BIT(10) /* Direction Flag */
+#define X86_EFLAGS_OF		BIT(11) /* Overflow Flag */
+#define X86_EFLAGS_IOPL		BIT(12) /* I/O Privilege Level (2 bits) */
+#define X86_EFLAGS_NT		BIT(14) /* Nested Task */
+#define X86_EFLAGS_RF		BIT(16) /* Resume Flag */
+#define X86_EFLAGS_VM		BIT(17) /* Virtual Mode */
+#define X86_EFLAGS_AC		BIT(18) /* Alignment Check/Access Control */
+#define X86_EFLAGS_VIF		BIT(19) /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP		BIT(20) /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID		BIT(21) /* CPUID detection */
 
 #define X86_CR4_VME		(1ul << 0)
 #define X86_CR4_PVI		(1ul << 1)
@@ -209,6 +226,7 @@ struct kvm_x86_cpu_feature {
 #define X86_FEATURE_SEV			KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1)
 #define X86_FEATURE_SEV_ES		KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3)
 #define X86_FEATURE_SEV_SNP		KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 4)
+#define	X86_FEATURE_GP_ON_USER_CPUID	KVM_X86_CPU_FEATURE(0x80000021, 0, EAX, 17)
 #define	X86_FEATURE_PERFMON_V2		KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 0)
 #define	X86_FEATURE_LBR_PMC_FREEZE	KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 2)
 
@@ -1556,6 +1574,15 @@ u64 *tdp_get_pte(struct kvm_vm *vm, u64 l2_gpa);
 #define PFERR_GUEST_PAGE_MASK	BIT_ULL(PFERR_GUEST_PAGE_BIT)
 #define PFERR_IMPLICIT_ACCESS	BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
 
+#define EPT_VIOLATION_ACC_READ		BIT(0)
+#define EPT_VIOLATION_ACC_WRITE		BIT(1)
+#define EPT_VIOLATION_ACC_INSTR		BIT(2)
+#define EPT_VIOLATION_PROT_READ		BIT(3)
+#define EPT_VIOLATION_PROT_WRITE	BIT(4)
+#define EPT_VIOLATION_PROT_EXEC		BIT(5)
+#define EPT_VIOLATION_GVA_IS_VALID	BIT(7)
+#define EPT_VIOLATION_GVA_TRANSLATED	BIT(8)
+
 bool sys_clocksource_is_based_on_tsc(void);
 
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index b51467d70f6e..4ca48de7a926 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -848,7 +848,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
 
 	/* Setup guest general purpose registers */
 	vcpu_regs_get(vcpu, &regs);
-	regs.rflags = regs.rflags | 0x2;
+	regs.rflags = regs.rflags | X86_EFLAGS_FIXED;
 	regs.rsp = stack_gva;
 	vcpu_regs_set(vcpu, &regs);
 
diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
index 67642759e4a0..7c10ba6e6fb4 100644
--- a/tools/testing/selftests/kvm/lib/x86/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
@@ -360,7 +360,7 @@ static inline void init_vmcs_guest_state(void *rip, void *rsp)
 	vmwrite(GUEST_DR7, 0x400);
 	vmwrite(GUEST_RSP, (u64)rsp);
 	vmwrite(GUEST_RIP, (u64)rip);
-	vmwrite(GUEST_RFLAGS, 2);
+	vmwrite(GUEST_RFLAGS, X86_EFLAGS_FIXED);
 	vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
 	vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
 	vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
diff --git a/tools/testing/selftests/kvm/x86/debug_regs.c b/tools/testing/selftests/kvm/x86/debug_regs.c
index 0dfaf03cd0a0..2a2ef3e179ff 100644
--- a/tools/testing/selftests/kvm/x86/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86/debug_regs.c
@@ -15,10 +15,51 @@
 
 #define IRQ_VECTOR 0xAA
 
+#define  CAST_TO_RIP(v)  ((unsigned long long)&(v))
+
 /* For testing data access debug BP */
 u32 guest_value;
 
 extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start;
+extern unsigned char fep_bd_start, fep_sti_start, fep_sti_end;
+
+static int irqs_received;
+
+static void guest_db_handler(struct ex_regs *regs)
+{
+	static int count;
+	unsigned long target_rips[2] = {
+		CAST_TO_RIP(fep_sti_start),
+		CAST_TO_RIP(fep_sti_end),
+	};
+
+	__GUEST_ASSERT(regs->rip == target_rips[count],
+	               "STI[%u]: unexpected rip 0x%lx (should be 0x%lx)",
+		       count, regs->rip, target_rips[count]);
+	regs->rflags &= ~X86_EFLAGS_TF;
+	count++;
+}
+
+static void guest_irq_handler(struct ex_regs *regs)
+{
+	/*
+	 * The pending IRQ should finally be take when KVM_GUESTDBG_BLOCKIRQ is
+	 * cleared and IRQs are enabled.  Note, the IRQ is expected to arrive
+	 * on the instruction immediately after STI, even though its in an STI
+	 * shadow.  Because the next instruction has a coincident #DB, and #DBs
+	 * are not subject to STI-blocking, the #DB will push RFLAGS.IF=1 on
+	 * the stack, and the eventual IRET will unmask IRQs and obliterate the
+	 * STI shadow in the process.
+	 */
+	unsigned long target_rip = CAST_TO_RIP(fep_sti_start);
+
+	__GUEST_ASSERT(regs->rip == target_rip,
+		       "IRQ: unexpected rip 0x%lx (should be 0x%lx)",
+		       regs->rip, target_rip);
+
+	irqs_received++;
+	x2apic_write_reg(APIC_EOI, 0);
+}
 
 static void guest_code(void)
 {
@@ -64,11 +105,33 @@ static void guest_code(void)
 
 	/* DR6.BD test */
 	asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax");
+
+	/*
+	 * Note, the IRET from the #DB that occurs in the below STI-shadow will
+	 * unmask IRQs, i.e. the pending interrupt will be delivered after #DB
+	 * handling, on the CLI!
+	 */
+	if (is_forced_emulation_enabled) {
+		asm volatile(KVM_FEP "fep_bd_start: mov %%dr0, %%rax" : : : "rax");
+
+		/* pending debug exceptions for emulation */
+		asm volatile("pushf\n\t"
+			     "orq $" __stringify(X86_EFLAGS_TF) ", (%rsp)\n\t"
+			     "popf\n\t"
+			     "sti\n\t"
+			     "fep_sti_start:"
+			     "cli\n\t"
+			     "pushf\n\t"
+			     "orq $" __stringify(X86_EFLAGS_TF) ", (%rsp)\n\t"
+			     "popf\n\t"
+			     KVM_FEP "sti\n\t"
+			     "fep_sti_end:"
+			     "cli\n\t");
+		GUEST_ASSERT(irqs_received == 1);
+	}
 	GUEST_DONE();
 }
 
-#define  CAST_TO_RIP(v)  ((unsigned long long)&(v))
-
 static void vcpu_skip_insn(struct kvm_vcpu *vcpu, int insn_len)
 {
 	struct kvm_regs regs;
@@ -185,7 +248,7 @@ int main(void)
 			    target_dr6);
 	}
 
-	/* Finally test global disable */
+	/* test global disable */
 	memset(&debug, 0, sizeof(debug));
 	debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
 	debug.arch.debugreg[7] = 0x400 | DR7_GD;
@@ -202,10 +265,29 @@ int main(void)
 			    run->debug.arch.pc, target_rip, run->debug.arch.dr6,
 			    target_dr6);
 
+	/* test global disable in emulation */
+	if (is_forced_emulation_enabled) {
+		/* Skip the 3-bytes "mov dr0" */
+		vcpu_skip_insn(vcpu, 3);
+		vcpu_run(vcpu);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+			    run->debug.arch.exception == DB_VECTOR &&
+			    run->debug.arch.pc == CAST_TO_RIP(fep_bd_start) &&
+			    run->debug.arch.dr6 == target_dr6,
+			    "DR7.GD: exit %d exception %d rip 0x%llx "
+			    "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+			    run->exit_reason, run->debug.arch.exception,
+			    run->debug.arch.pc, CAST_TO_RIP(fep_bd_start),
+			    run->debug.arch.dr6, target_dr6);
+	}
+
 	/* Disable all debug controls, run to the end */
 	memset(&debug, 0, sizeof(debug));
 	vcpu_guest_debug_set(vcpu, &debug);
 
+	vm_install_exception_handler(vm, DB_VECTOR, guest_db_handler);
+	vm_install_exception_handler(vm, IRQ_VECTOR, guest_irq_handler);
+
 	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	cmd = get_ucall(vcpu, &uc);
diff --git a/tools/testing/selftests/kvm/x86/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c
index 8e20a03b3329..53b7971aa072 100644
--- a/tools/testing/selftests/kvm/x86/hwcr_msr_test.c
+++ b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c
@@ -11,12 +11,17 @@
 void test_hwcr_bit(struct kvm_vcpu *vcpu, unsigned int bit)
 {
 	const u64 ignored = BIT_ULL(3) | BIT_ULL(6) | BIT_ULL(8);
-	const u64 valid = BIT_ULL(18) | BIT_ULL(24);
-	const u64 legal = ignored | valid;
+	u64 valid = BIT_ULL(18) | BIT_ULL(24);
 	u64 val = BIT_ULL(bit);
 	u64 actual;
+	u64 legal;
 	int r;
 
+	if (kvm_cpu_has(X86_FEATURE_GP_ON_USER_CPUID))
+		valid |= BIT_ULL(35);
+
+	legal = ignored | valid;
+
 	r = _vcpu_set_msr(vcpu, MSR_K7_HWCR, val);
 	TEST_ASSERT(val & ~legal ? !r : r == 1,
 		    "Expected KVM_SET_MSRS(MSR_K7_HWCR) = 0x%lx to %s",
diff --git a/tools/testing/selftests/kvm/x86/nested_tdp_fault_test.c b/tools/testing/selftests/kvm/x86/nested_tdp_fault_test.c
new file mode 100644
index 000000000000..fa95568f55ff
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/nested_tdp_fault_test.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025, Google, Inc.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "vmx.h"
+
+#define L2_GUEST_STACK_SIZE 64
+
+enum test_type {
+	TEST_FINAL_PAGE_UNMAPPED,	    /* Final data page not present */
+	TEST_PT_PAGE_UNMAPPED,		    /* Page table page not present */
+	TEST_FINAL_PAGE_WRITE_PROTECTED,    /* Final data page read-only */
+	TEST_PT_PAGE_WRITE_PROTECTED,	    /* Page table page read-only */
+};
+
+static gva_t l2_test_page;
+static void (*l2_entry)(void);
+
+#define TEST_IO_PORT 0x80
+#define TEST1_VADDR 0x8000000ULL
+#define TEST2_VADDR 0x10000000ULL
+#define TEST3_VADDR 0x18000000ULL
+#define TEST4_VADDR 0x20000000ULL
+
+/*
+ * L2 executes OUTS reading from l2_test_page, triggering a nested page
+ * fault on the read access.
+ */
+static void l2_guest_code_outs(void)
+{
+	asm volatile("outsb" ::"S"(l2_test_page), "d"(TEST_IO_PORT) : "memory");
+	GUEST_FAIL("L2 should not reach here");
+}
+
+/*
+ * L2 executes INS writing to l2_test_page, triggering a nested page
+ * fault on the write access.
+ */
+static void l2_guest_code_ins(void)
+{
+	asm volatile("insb" ::"D"(l2_test_page), "d"(TEST_IO_PORT) : "memory");
+	GUEST_FAIL("L2 should not reach here");
+}
+
+#define GUEST_ASSERT_EXIT_QUAL(ac_eq, ex_eq)		\
+	__GUEST_ASSERT((ac_eq) == (ex_eq),		\
+		       "Wanted EXIT_QUAL '0x%lx', got '0x%lx'", ex_eq, ac_eq)
+
+static void l1_vmx_code(struct vmx_pages *vmx, u64 expected_fault_gpa,
+			u64 test_type)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	u64 exit_qual;
+
+	GUEST_ASSERT(vmx->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
+	GUEST_ASSERT(load_vmcs(vmx));
+
+	prepare_vmcs(vmx, l2_entry, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_ASSERT(!vmlaunch());
+
+	/* Verify we got an EPT violation exit */
+	__GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_EPT_VIOLATION,
+		       "Expected EPT violation (0x%x), got 0x%lx",
+		       EXIT_REASON_EPT_VIOLATION,
+		       vmreadz(VM_EXIT_REASON));
+
+	__GUEST_ASSERT(vmreadz(GUEST_PHYSICAL_ADDRESS) == expected_fault_gpa,
+		       "Expected guest_physical_address = 0x%lx, got 0x%lx",
+		       expected_fault_gpa,
+		       vmreadz(GUEST_PHYSICAL_ADDRESS));
+
+	exit_qual = vmreadz(EXIT_QUALIFICATION);
+
+	/*
+	 * Note, EPT page table accesses are always read+write, e.g. so that
+	 * the CPU can do A/D updates at-will.
+	 */
+	switch (test_type) {
+	case TEST_FINAL_PAGE_UNMAPPED:
+		GUEST_ASSERT_EXIT_QUAL(exit_qual, EPT_VIOLATION_ACC_READ |
+						  EPT_VIOLATION_GVA_IS_VALID |
+						  EPT_VIOLATION_GVA_TRANSLATED);
+		break;
+	case TEST_PT_PAGE_UNMAPPED:
+		GUEST_ASSERT_EXIT_QUAL(exit_qual, EPT_VIOLATION_ACC_READ |
+						  EPT_VIOLATION_ACC_WRITE |
+						  EPT_VIOLATION_GVA_IS_VALID);
+		break;
+	case TEST_FINAL_PAGE_WRITE_PROTECTED:
+		GUEST_ASSERT_EXIT_QUAL(exit_qual, EPT_VIOLATION_ACC_WRITE |
+						  EPT_VIOLATION_PROT_READ |
+						  EPT_VIOLATION_PROT_EXEC |
+						  EPT_VIOLATION_GVA_IS_VALID |
+						  EPT_VIOLATION_GVA_TRANSLATED);
+		break;
+	case TEST_PT_PAGE_WRITE_PROTECTED:
+		GUEST_ASSERT_EXIT_QUAL(exit_qual, EPT_VIOLATION_ACC_READ |
+						  EPT_VIOLATION_ACC_WRITE |
+						  EPT_VIOLATION_PROT_READ |
+						  EPT_VIOLATION_PROT_EXEC |
+						  EPT_VIOLATION_GVA_IS_VALID);
+		break;
+	}
+
+	GUEST_DONE();
+}
+
+#define GUEST_ASSERT_NPF_EC(ac_ec, ex_ec)		\
+	__GUEST_ASSERT((ac_ec) == (ex_ec),		\
+		       "Wanted NPF error code '0x%lx', got '0x%lx'", (u64)(ex_ec), ac_ec)
+
+
+static void l1_svm_code(struct svm_test_data *svm, u64 expected_fault_gpa,
+			 u64 test_type)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+	u64 exit_info_1;
+
+	generic_svm_setup(svm, l2_entry,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	run_guest(vmcb, svm->vmcb_gpa);
+
+	/* Verify we got an NPF exit */
+	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_NPF,
+		       "Expected NPF exit (0x%x), got 0x%lx", SVM_EXIT_NPF,
+		       vmcb->control.exit_code);
+
+	__GUEST_ASSERT(vmcb->control.exit_info_2 == expected_fault_gpa,
+		       "Expected exit_info_2 = 0x%lx, got 0x%lx",
+		       expected_fault_gpa,
+		       vmcb->control.exit_info_2);
+
+	exit_info_1 = vmcb->control.exit_info_1;
+
+	/*
+	 * Note, without GMET enabled, NPT walks are always user accesses.  And
+	 * like EPT, page table accesses are always read+write.
+	 */
+	switch (test_type) {
+	case TEST_FINAL_PAGE_UNMAPPED:
+		GUEST_ASSERT_NPF_EC(exit_info_1, PFERR_USER_MASK |
+						 PFERR_GUEST_FINAL_MASK);
+		break;
+	case TEST_PT_PAGE_UNMAPPED:
+		GUEST_ASSERT_NPF_EC(exit_info_1, PFERR_WRITE_MASK |
+						 PFERR_USER_MASK |
+						 PFERR_GUEST_PAGE_MASK);
+		break;
+	case TEST_FINAL_PAGE_WRITE_PROTECTED:
+		GUEST_ASSERT_NPF_EC(exit_info_1, PFERR_PRESENT_MASK |
+						 PFERR_WRITE_MASK |
+						 PFERR_USER_MASK |
+						 PFERR_GUEST_FINAL_MASK);
+		break;
+	case TEST_PT_PAGE_WRITE_PROTECTED:
+		GUEST_ASSERT_NPF_EC(exit_info_1, PFERR_PRESENT_MASK |
+						 PFERR_WRITE_MASK |
+						 PFERR_USER_MASK |
+						 PFERR_GUEST_PAGE_MASK);
+		break;
+	}
+
+	GUEST_DONE();
+}
+
+static void l1_guest_code(void *data, u64 expected_fault_gpa,
+			  u64 test_type)
+{
+	if (this_cpu_has(X86_FEATURE_VMX))
+		l1_vmx_code(data, expected_fault_gpa, test_type);
+	else
+		l1_svm_code(data, expected_fault_gpa, test_type);
+}
+
+/* Returns the GPA of the PT page that maps @vaddr. */
+static u64 get_pt_gpa_for_vaddr(struct kvm_vm *vm, u64 vaddr)
+{
+	u64 *pte;
+
+	pte = vm_get_pte(vm, vaddr);
+	TEST_ASSERT(pte && (*pte & 0x1), "PTE not present for vaddr 0x%lx",
+		    (unsigned long)vaddr);
+
+	return addr_hva2gpa(vm, (void *)((u64)pte & ~0xFFFULL));
+}
+
+static void run_test(enum test_type type)
+{
+	gpa_t expected_fault_gpa;
+	gva_t nested_gva;
+
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+	vm_enable_tdp(vm);
+
+	if (kvm_cpu_has(X86_FEATURE_VMX))
+		vcpu_alloc_vmx(vm, &nested_gva);
+	else
+		vcpu_alloc_svm(vm, &nested_gva);
+
+	switch (type) {
+	case TEST_FINAL_PAGE_UNMAPPED:
+		/*
+		 * Unmap the final data page from NPT/EPT. The guest page
+		 * table walk succeeds, but the final GPA->HPA translation
+		 * fails. L2 reads from the page via OUTS.
+		 */
+		l2_entry = l2_guest_code_outs;
+		l2_test_page = vm_alloc(vm, vm->page_size, TEST1_VADDR);
+		expected_fault_gpa = addr_gva2gpa(vm, l2_test_page);
+		break;
+	case TEST_PT_PAGE_UNMAPPED:
+		/*
+		 * Unmap a page table page from NPT/EPT. The hardware page
+		 * table walk fails when translating the PT page's GPA
+		 * through NPT/EPT. L2 reads from the page via OUTS.
+		 */
+		l2_entry = l2_guest_code_outs;
+		l2_test_page = vm_alloc(vm, vm->page_size, TEST2_VADDR);
+		expected_fault_gpa = get_pt_gpa_for_vaddr(vm, l2_test_page);
+		break;
+	case TEST_FINAL_PAGE_WRITE_PROTECTED:
+		/*
+		 * Write-protect the final data page in NPT/EPT.  The page
+		 * is present and readable, but not writable.  L2 writes to
+		 * the page via INS, triggering a protection violation.
+		 */
+		l2_entry = l2_guest_code_ins;
+		l2_test_page = vm_alloc(vm, vm->page_size, TEST3_VADDR);
+		expected_fault_gpa = addr_gva2gpa(vm, l2_test_page);
+		break;
+	case TEST_PT_PAGE_WRITE_PROTECTED:
+		/*
+		 * Write-protect a page table page in NPT/EPT.  The page is
+		 * present and readable, but not writable.  The guest page
+		 * table walk needs write access to set A/D bits, so it
+		 * triggers a protection violation on the PT page.
+		 * L2 reads from the page via OUTS.
+		 */
+		l2_entry = l2_guest_code_outs;
+		l2_test_page = vm_alloc(vm, vm->page_size, TEST4_VADDR);
+		expected_fault_gpa = get_pt_gpa_for_vaddr(vm, l2_test_page);
+		break;
+	}
+
+	tdp_identity_map_default_memslots(vm);
+
+	if (type == TEST_FINAL_PAGE_WRITE_PROTECTED ||
+	    type == TEST_PT_PAGE_WRITE_PROTECTED)
+		*tdp_get_pte(vm, expected_fault_gpa) &= ~PTE_WRITABLE_MASK(&vm->stage2_mmu);
+	else
+		*tdp_get_pte(vm, expected_fault_gpa) &= ~(PTE_PRESENT_MASK(&vm->stage2_mmu) |
+							   PTE_READABLE_MASK(&vm->stage2_mmu) |
+							   PTE_WRITABLE_MASK(&vm->stage2_mmu) |
+							   PTE_EXECUTABLE_MASK(&vm->stage2_mmu));
+
+	sync_global_to_guest(vm, l2_entry);
+	sync_global_to_guest(vm, l2_test_page);
+	vcpu_args_set(vcpu, 3, nested_gva, expected_fault_gpa, (u64)type);
+
+	/*
+	 * For the INS-based write test, KVM emulates the instruction and
+	 * first reads from the I/O port, which exits to userspace.
+	 * Re-enter the guest so emulation can proceed to the memory
+	 * write, where the nested page fault is triggered.
+	 */
+	for (;;) {
+		vcpu_run(vcpu);
+
+		if (vcpu->run->exit_reason == KVM_EXIT_IO &&
+		    vcpu->run->io.port == TEST_IO_PORT &&
+		    vcpu->run->io.direction == KVM_EXIT_IO_IN) {
+			continue;
+		}
+		break;
+	}
+
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+	default:
+		TEST_FAIL("Unexpected exit reason: %d", vcpu->run->exit_reason);
+	}
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) || kvm_cpu_has(X86_FEATURE_SVM));
+	TEST_REQUIRE(kvm_cpu_has_tdp());
+
+	run_test(TEST_FINAL_PAGE_UNMAPPED);
+	run_test(TEST_PT_PAGE_UNMAPPED);
+	run_test(TEST_FINAL_PAGE_WRITE_PROTECTED);
+	run_test(TEST_PT_PAGE_WRITE_PROTECTED);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
index c1232344fda8..84e4c6ca67a3 100644
--- a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
@@ -731,6 +731,8 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu)
 
 static void intel_run_fixed_counter_guest_code(u8 idx)
 {
+	u8 nr_fixed_counters = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+
 	for (;;) {
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 		wrmsr(MSR_CORE_PERF_FIXED_CTR0 + idx, 0);
@@ -738,6 +740,10 @@ static void intel_run_fixed_counter_guest_code(u8 idx)
 		/* Only OS_EN bit is enabled for fixed counter[idx]. */
 		wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(idx, FIXED_PMC_KERNEL));
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(idx));
+		if (nr_fixed_counters > 1)
+			wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL,
+			      FIXED_PMC_CTRL(idx, FIXED_PMC_KERNEL) |
+			      FIXED_PMC_CTRL((idx + 1) % nr_fixed_counters, FIXED_PMC_KERNEL));
 		__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);