Merge tag 'kvmarm-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.7

 - Generalized infrastructure for 'writable' ID registers, effectively
   allowing userspace to opt-out of certain vCPU features for its guest

 - Optimization for vSGI injection, opportunistically compressing MPIDR
   to vCPU mapping into a table

 - Improvements to KVM's PMU emulation, allowing userspace to select
   the number of PMCs available to a VM

 - Guest support for memory operation instructions (FEAT_MOPS)

 - Cleanups to handling feature flags in KVM_ARM_VCPU_INIT, squashing
   bugs and getting rid of useless code

 - Changes to the way the SMCCC filter is constructed, avoiding wasted
   memory allocations when not in use

 - Load the stage-2 MMU context at vcpu_load() for VHE systems, reducing
   the overhead of errata mitigations

 - Miscellaneous kernel and selftest fixes

8 files changed, 1191 insertions, 18 deletions

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index fb01c3f8d3da..a5963ab9215b 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -17,6 +17,15 @@ else
 	ARCH_DIR := $(ARCH)
 endif
 
+ifeq ($(ARCH),arm64)
+arm64_tools_dir := $(top_srcdir)/tools/arch/arm64/tools/
+GEN_HDRS := $(top_srcdir)/tools/arch/arm64/include/generated/
+CFLAGS += -I$(GEN_HDRS)
+
+$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
+	$(MAKE) -C $(arm64_tools_dir)
+endif
+
 LIBKVM += lib/assert.c
 LIBKVM += lib/elf.c
 LIBKVM += lib/guest_modes.c
@@ -146,10 +155,12 @@ TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/hypercalls
 TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test
 TEST_GEN_PROGS_aarch64 += aarch64/psci_test
+TEST_GEN_PROGS_aarch64 += aarch64/set_id_regs
 TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter
 TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
+TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access
 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
@@ -257,13 +268,18 @@ $(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c
 $(SPLIT_TESTS_TARGETS): %: %.o $(SPLIT_TESTS_OBJS)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@
 
-EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) $(SPLIT_TESTS_OBJS) cscope.*
+EXTRA_CLEAN += $(GEN_HDRS) \
+	       $(LIBKVM_OBJS) \
+	       $(SPLIT_TESTS_OBJS) \
+	       $(TEST_DEP_FILES) \
+	       $(TEST_GEN_OBJ) \
+	       cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
-$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
 # Compile the string overrides as freestanding to prevent the compiler from
@@ -273,8 +289,10 @@ $(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@
 
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
+$(SPLIT_TESTS_OBJS): $(GEN_HDRS)
 $(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)
+$(TEST_GEN_OBJ): $(GEN_HDRS)
 
 cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
 cscope:
diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
index b90580840b22..8e5bd07a3727 100644
--- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
@@ -146,8 +146,8 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 
 	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
 
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0), val);
-	return el0 == ID_AA64PFR0_ELx_64BIT_ONLY;
+	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	return el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY;
 }
 
 int main(void)
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index f5b6cb3a0019..866002917441 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -116,12 +116,12 @@ static void reset_debug_state(void)
 
 	/* Reset all bcr/bvr/wcr/wvr registers */
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_BRPS), dfr0);
+	brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), dfr0);
 	for (i = 0; i <= brps; i++) {
 		write_dbgbcr(i, 0);
 		write_dbgbvr(i, 0);
 	}
-	wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_WRPS), dfr0);
+	wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), dfr0);
 	for (i = 0; i <= wrps; i++) {
 		write_dbgwcr(i, 0);
 		write_dbgwvr(i, 0);
@@ -418,7 +418,7 @@ static void guest_code_ss(int test_cnt)
 
 static int debug_version(uint64_t id_aa64dfr0)
 {
-	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), id_aa64dfr0);
+	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), id_aa64dfr0);
 }
 
 static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn)
@@ -539,14 +539,14 @@ void test_guest_debug_exceptions_all(uint64_t aa64dfr0)
 	int b, w, c;
 
 	/* Number of breakpoints */
-	brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_BRPS), aa64dfr0) + 1;
+	brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), aa64dfr0) + 1;
 	__TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required");
 
 	/* Number of watchpoints */
-	wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_WRPS), aa64dfr0) + 1;
+	wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), aa64dfr0) + 1;
 
 	/* Number of context aware breakpoints */
-	ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_CTX_CMPS), aa64dfr0) + 1;
+	ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_CTX_CMPs), aa64dfr0) + 1;
 
 	pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__,
 		 brp_num, wrp_num, ctx_brp_num);
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 47bb914ab2fa..eb4217b7c768 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -96,14 +96,14 @@ static bool guest_check_lse(void)
 	uint64_t isar0 = read_sysreg(id_aa64isar0_el1);
 	uint64_t atomic;
 
-	atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_ATOMICS), isar0);
+	atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC), isar0);
 	return atomic >= 2;
 }
 
 static bool guest_check_dc_zva(void)
 {
 	uint64_t dczid = read_sysreg(dczid_el0);
-	uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_DZP), dczid);
+	uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_EL0_DZP), dczid);
 
 	return dzp == 0;
 }
@@ -135,8 +135,8 @@ static void guest_at(void)
 	uint64_t par;
 
 	asm volatile("at s1e1r, %0" :: "r" (guest_test_memory));
-	par = read_sysreg(par_el1);
 	isb();
+	par = read_sysreg(par_el1);
 
 	/* Bit 1 indicates whether the AT was successful */
 	GUEST_ASSERT_EQ(par & 1, 0);
@@ -196,7 +196,7 @@ static bool guest_set_ha(void)
 	uint64_t hadbs, tcr;
 
 	/* Skip if HA is not supported. */
-	hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_HADBS), mmfr1);
+	hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS), mmfr1);
 	if (hadbs == 0)
 		return false;
 
@@ -842,6 +842,7 @@ static void help(char *name)
 	.name			= SCAT2(ro_memslot_no_syndrome, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
 	.pt_memslot_flags	= KVM_MEM_READONLY,				\
+	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
 	.expected_events	= { .fail_vcpu_runs = 1 },			\
@@ -865,6 +866,7 @@ static void help(char *name)
 	.name			= SCAT2(ro_memslot_no_syn_and_dlog, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
 	.pt_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
+	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.guest_test_check	= { _test_check },				\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
@@ -894,6 +896,7 @@ static void help(char *name)
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
 	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
+	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.uffd_data_handler	= _uffd_data_handler,				\
 	.uffd_pt_handler	= uffd_pt_handler,			\
diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
new file mode 100644
index 000000000000..bac05210b539
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * set_id_regs - Test for setting ID register from usersapce.
+ *
+ * Copyright (c) 2023 Google LLC.
+ *
+ *
+ * Test that KVM supports setting ID registers from userspace and handles the
+ * feature set correctly.
+ */
+
+#include <stdint.h>
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+#include <linux/bitfield.h>
+
+enum ftr_type {
+	FTR_EXACT,			/* Use a predefined safe value */
+	FTR_LOWER_SAFE,			/* Smaller value is safe */
+	FTR_HIGHER_SAFE,		/* Bigger value is safe */
+	FTR_HIGHER_OR_ZERO_SAFE,	/* Bigger value is safe, but 0 is biggest */
+	FTR_END,			/* Mark the last ftr bits */
+};
+
+#define FTR_SIGNED	true	/* Value should be treated as signed */
+#define FTR_UNSIGNED	false	/* Value should be treated as unsigned */
+
+struct reg_ftr_bits {
+	char *name;
+	bool sign;
+	enum ftr_type type;
+	uint8_t shift;
+	uint64_t mask;
+	int64_t safe_val;
+};
+
+struct test_feature_reg {
+	uint32_t reg;
+	const struct reg_ftr_bits *ftr_bits;
+};
+
+#define __REG_FTR_BITS(NAME, SIGNED, TYPE, SHIFT, MASK, SAFE_VAL)	\
+	{								\
+		.name = #NAME,						\
+		.sign = SIGNED,						\
+		.type = TYPE,						\
+		.shift = SHIFT,						\
+		.mask = MASK,						\
+		.safe_val = SAFE_VAL,					\
+	}
+
+#define REG_FTR_BITS(type, reg, field, safe_val) \
+	__REG_FTR_BITS(reg##_##field, FTR_UNSIGNED, type, reg##_##field##_SHIFT, \
+		       reg##_##field##_MASK, safe_val)
+
+#define S_REG_FTR_BITS(type, reg, field, safe_val) \
+	__REG_FTR_BITS(reg##_##field, FTR_SIGNED, type, reg##_##field##_SHIFT, \
+		       reg##_##field##_MASK, safe_val)
+
+#define REG_FTR_END					\
+	{						\
+		.type = FTR_END,			\
+	}
+
+static const struct reg_ftr_bits ftr_id_aa64dfr0_el1[] = {
+	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, PMUVer, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_dfr0_el1[] = {
+	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64isar0_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, RNDR, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, TLB, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, TS, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, FHM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, DP, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, SM4, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, SM3, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, SHA3, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, RDM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, TME, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, ATOMIC, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, CRC32, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, SHA2, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, SHA1, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR0_EL1, AES, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64isar1_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, LS64, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, XS, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, I8MM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, DGH, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, BF16, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, SPECRES, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, SB, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, FRINTTS, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, LRCPC, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, FCMA, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, JSCVT, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR1_EL1, DPB, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64isar2_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR2_EL1, BC, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR2_EL1, RPRES, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR2_EL1, WFxT, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV3, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV2, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ECV, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, EXS, 0),
+	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, TGRAN4, 0),
+	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, TGRAN64, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, TGRAN16, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64mmfr1_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, TIDCP1, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, AFP, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, ETS, 0),
+	REG_FTR_BITS(FTR_HIGHER_SAFE, ID_AA64MMFR1_EL1, SpecSEI, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, PAN, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, LO, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, HPDS, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, HAFDBS, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64mmfr2_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, E0PD, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, BBM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, TTL, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, AT, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, ST, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, VARange, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, IESB, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, LSM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, UAO, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR2_EL1, CnP, 0),
+	REG_FTR_END,
+};
+
+static const struct reg_ftr_bits ftr_id_aa64zfr0_el1[] = {
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, F64MM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, F32MM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, I8MM, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, SM4, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, SHA3, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, BF16, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, BitPerm, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, AES, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, SVEver, 0),
+	REG_FTR_END,
+};
+
+#define TEST_REG(id, table)			\
+	{					\
+		.reg = id,			\
+		.ftr_bits = &((table)[0]),	\
+	}
+
+static struct test_feature_reg test_regs[] = {
+	TEST_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0_el1),
+	TEST_REG(SYS_ID_DFR0_EL1, ftr_id_dfr0_el1),
+	TEST_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0_el1),
+	TEST_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1_el1),
+	TEST_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2_el1),
+	TEST_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0_el1),
+	TEST_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0_el1),
+	TEST_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1_el1),
+	TEST_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2_el1),
+	TEST_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0_el1),
+};
+
+#define GUEST_REG_SYNC(id) GUEST_SYNC_ARGS(0, id, read_sysreg_s(id), 0, 0);
+
+static void guest_code(void)
+{
+	GUEST_REG_SYNC(SYS_ID_AA64DFR0_EL1);
+	GUEST_REG_SYNC(SYS_ID_DFR0_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64ISAR0_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64ISAR1_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64ISAR2_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64PFR0_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64MMFR2_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64ZFR0_EL1);
+
+	GUEST_DONE();
+}
+
+/* Return a safe value to a given ftr_bits an ftr value */
+uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
+{
+	uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+
+	if (ftr_bits->type == FTR_UNSIGNED) {
+		switch (ftr_bits->type) {
+		case FTR_EXACT:
+			ftr = ftr_bits->safe_val;
+			break;
+		case FTR_LOWER_SAFE:
+			if (ftr > 0)
+				ftr--;
+			break;
+		case FTR_HIGHER_SAFE:
+			if (ftr < ftr_max)
+				ftr++;
+			break;
+		case FTR_HIGHER_OR_ZERO_SAFE:
+			if (ftr == ftr_max)
+				ftr = 0;
+			else if (ftr != 0)
+				ftr++;
+			break;
+		default:
+			break;
+		}
+	} else if (ftr != ftr_max) {
+		switch (ftr_bits->type) {
+		case FTR_EXACT:
+			ftr = ftr_bits->safe_val;
+			break;
+		case FTR_LOWER_SAFE:
+			if (ftr > 0)
+				ftr--;
+			break;
+		case FTR_HIGHER_SAFE:
+			if (ftr < ftr_max - 1)
+				ftr++;
+			break;
+		case FTR_HIGHER_OR_ZERO_SAFE:
+			if (ftr != 0 && ftr != ftr_max - 1)
+				ftr++;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return ftr;
+}
+
+/* Return an invalid value to a given ftr_bits an ftr value */
+uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
+{
+	uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+
+	if (ftr_bits->type == FTR_UNSIGNED) {
+		switch (ftr_bits->type) {
+		case FTR_EXACT:
+			ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1);
+			break;
+		case FTR_LOWER_SAFE:
+			ftr++;
+			break;
+		case FTR_HIGHER_SAFE:
+			ftr--;
+			break;
+		case FTR_HIGHER_OR_ZERO_SAFE:
+			if (ftr == 0)
+				ftr = ftr_max;
+			else
+				ftr--;
+			break;
+		default:
+			break;
+		}
+	} else if (ftr != ftr_max) {
+		switch (ftr_bits->type) {
+		case FTR_EXACT:
+			ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1);
+			break;
+		case FTR_LOWER_SAFE:
+			ftr++;
+			break;
+		case FTR_HIGHER_SAFE:
+			ftr--;
+			break;
+		case FTR_HIGHER_OR_ZERO_SAFE:
+			if (ftr == 0)
+				ftr = ftr_max - 1;
+			else
+				ftr--;
+			break;
+		default:
+			break;
+		}
+	} else {
+		ftr = 0;
+	}
+
+	return ftr;
+}
+
+static void test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg,
+				 const struct reg_ftr_bits *ftr_bits)
+{
+	uint8_t shift = ftr_bits->shift;
+	uint64_t mask = ftr_bits->mask;
+	uint64_t val, new_val, ftr;
+
+	vcpu_get_reg(vcpu, reg, &val);
+	ftr = (val & mask) >> shift;
+
+	ftr = get_safe_value(ftr_bits, ftr);
+
+	ftr <<= shift;
+	val &= ~mask;
+	val |= ftr;
+
+	vcpu_set_reg(vcpu, reg, val);
+	vcpu_get_reg(vcpu, reg, &new_val);
+	TEST_ASSERT_EQ(new_val, val);
+}
+
+static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg,
+			      const struct reg_ftr_bits *ftr_bits)
+{
+	uint8_t shift = ftr_bits->shift;
+	uint64_t mask = ftr_bits->mask;
+	uint64_t val, old_val, ftr;
+	int r;
+
+	vcpu_get_reg(vcpu, reg, &val);
+	ftr = (val & mask) >> shift;
+
+	ftr = get_invalid_value(ftr_bits, ftr);
+
+	old_val = val;
+	ftr <<= shift;
+	val &= ~mask;
+	val |= ftr;
+
+	r = __vcpu_set_reg(vcpu, reg, val);
+	TEST_ASSERT(r < 0 && errno == EINVAL,
+		    "Unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno);
+
+	vcpu_get_reg(vcpu, reg, &val);
+	TEST_ASSERT_EQ(val, old_val);
+}
+
+static void test_user_set_reg(struct kvm_vcpu *vcpu, bool aarch64_only)
+{
+	uint64_t masks[KVM_ARM_FEATURE_ID_RANGE_SIZE];
+	struct reg_mask_range range = {
+		.addr = (__u64)masks,
+	};
+	int ret;
+
+	/* KVM should return error when reserved field is not zero */
+	range.reserved[0] = 1;
+	ret = __vm_ioctl(vcpu->vm, KVM_ARM_GET_REG_WRITABLE_MASKS, &range);
+	TEST_ASSERT(ret, "KVM doesn't check invalid parameters.");
+
+	/* Get writable masks for feature ID registers */
+	memset(range.reserved, 0, sizeof(range.reserved));
+	vm_ioctl(vcpu->vm, KVM_ARM_GET_REG_WRITABLE_MASKS, &range);
+
+	for (int i = 0; i < ARRAY_SIZE(test_regs); i++) {
+		const struct reg_ftr_bits *ftr_bits = test_regs[i].ftr_bits;
+		uint32_t reg_id = test_regs[i].reg;
+		uint64_t reg = KVM_ARM64_SYS_REG(reg_id);
+		int idx;
+
+		/* Get the index to masks array for the idreg */
+		idx = KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(reg_id), sys_reg_Op1(reg_id),
+						   sys_reg_CRn(reg_id), sys_reg_CRm(reg_id),
+						   sys_reg_Op2(reg_id));
+
+		for (int j = 0;  ftr_bits[j].type != FTR_END; j++) {
+			/* Skip aarch32 reg on aarch64 only system, since they are RAZ/WI. */
+			if (aarch64_only && sys_reg_CRm(reg_id) < 4) {
+				ksft_test_result_skip("%s on AARCH64 only system\n",
+						      ftr_bits[j].name);
+				continue;
+			}
+
+			/* Make sure the feature field is writable */
+			TEST_ASSERT_EQ(masks[idx] & ftr_bits[j].mask, ftr_bits[j].mask);
+
+			test_reg_set_fail(vcpu, reg, &ftr_bits[j]);
+			test_reg_set_success(vcpu, reg, &ftr_bits[j]);
+
+			ksft_test_result_pass("%s\n", ftr_bits[j].name);
+		}
+	}
+}
+
+static void test_guest_reg_read(struct kvm_vcpu *vcpu)
+{
+	bool done = false;
+	struct ucall uc;
+	uint64_t val;
+
+	while (!done) {
+		vcpu_run(vcpu);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		case UCALL_SYNC:
+			/* Make sure the written values are seen by guest */
+			vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(uc.args[2]), &val);
+			TEST_ASSERT_EQ(val, uc.args[3]);
+			break;
+		case UCALL_DONE:
+			done = true;
+			break;
+		default:
+			TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	bool aarch64_only;
+	uint64_t val, el0;
+	int ftr_cnt;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES));
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	/* Check for AARCH64 only system */
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
+	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	aarch64_only = (el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY);
+
+	ksft_print_header();
+
+	ftr_cnt = ARRAY_SIZE(ftr_id_aa64dfr0_el1) + ARRAY_SIZE(ftr_id_dfr0_el1) +
+		  ARRAY_SIZE(ftr_id_aa64isar0_el1) + ARRAY_SIZE(ftr_id_aa64isar1_el1) +
+		  ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) +
+		  ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + ARRAY_SIZE(ftr_id_aa64mmfr1_el1) +
+		  ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) -
+		  ARRAY_SIZE(test_regs);
+
+	ksft_set_plan(ftr_cnt);
+
+	test_user_set_reg(vcpu, aarch64_only);
+	test_guest_reg_read(vcpu);
+
+	kvm_vm_free(vm);
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
new file mode 100644
index 000000000000..5ea78986e665
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vpmu_counter_access - Test vPMU event counter access
+ *
+ * Copyright (c) 2023 Google LLC.
+ *
+ * This test checks if the guest can see the same number of the PMU event
+ * counters (PMCR_EL0.N) that userspace sets, if the guest can access
+ * those counters, and if the guest is prevented from accessing any
+ * other counters.
+ * It also checks if the userspace accesses to the PMU regsisters honor the
+ * PMCR.N value that's set for the guest.
+ * This test runs only when KVM_CAP_ARM_PMU_V3 is supported on the host.
+ */
+#include <kvm_util.h>
+#include <processor.h>
+#include <test_util.h>
+#include <vgic.h>
+#include <perf/arm_pmuv3.h>
+#include <linux/bitfield.h>
+
+/* The max number of the PMU event counters (excluding the cycle counter) */
+#define ARMV8_PMU_MAX_GENERAL_COUNTERS	(ARMV8_PMU_MAX_COUNTERS - 1)
+
+/* The cycle counter bit position that's common among the PMU registers */
+#define ARMV8_PMU_CYCLE_IDX		31
+
+struct vpmu_vm {
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	int gic_fd;
+};
+
+static struct vpmu_vm vpmu_vm;
+
+struct pmreg_sets {
+	uint64_t set_reg_id;
+	uint64_t clr_reg_id;
+};
+
+#define PMREG_SET(set, clr) {.set_reg_id = set, .clr_reg_id = clr}
+
+static uint64_t get_pmcr_n(uint64_t pmcr)
+{
+	return (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+}
+
+static void set_pmcr_n(uint64_t *pmcr, uint64_t pmcr_n)
+{
+	*pmcr = *pmcr & ~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+	*pmcr |= (pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+}
+
+static uint64_t get_counters_mask(uint64_t n)
+{
+	uint64_t mask = BIT(ARMV8_PMU_CYCLE_IDX);
+
+	if (n)
+		mask |= GENMASK(n - 1, 0);
+	return mask;
+}
+
+/* Read PMEVTCNTR<n>_EL0 through PMXEVCNTR_EL0 */
+static inline unsigned long read_sel_evcntr(int sel)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	return read_sysreg(pmxevcntr_el0);
+}
+
+/* Write PMEVTCNTR<n>_EL0 through PMXEVCNTR_EL0 */
+static inline void write_sel_evcntr(int sel, unsigned long val)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	write_sysreg(val, pmxevcntr_el0);
+	isb();
+}
+
+/* Read PMEVTYPER<n>_EL0 through PMXEVTYPER_EL0 */
+static inline unsigned long read_sel_evtyper(int sel)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	return read_sysreg(pmxevtyper_el0);
+}
+
+/* Write PMEVTYPER<n>_EL0 through PMXEVTYPER_EL0 */
+static inline void write_sel_evtyper(int sel, unsigned long val)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	write_sysreg(val, pmxevtyper_el0);
+	isb();
+}
+
+static inline void enable_counter(int idx)
+{
+	uint64_t v = read_sysreg(pmcntenset_el0);
+
+	write_sysreg(BIT(idx) | v, pmcntenset_el0);
+	isb();
+}
+
+static inline void disable_counter(int idx)
+{
+	uint64_t v = read_sysreg(pmcntenset_el0);
+
+	write_sysreg(BIT(idx) | v, pmcntenclr_el0);
+	isb();
+}
+
+static void pmu_disable_reset(void)
+{
+	uint64_t pmcr = read_sysreg(pmcr_el0);
+
+	/* Reset all counters, disabling them */
+	pmcr &= ~ARMV8_PMU_PMCR_E;
+	write_sysreg(pmcr | ARMV8_PMU_PMCR_P, pmcr_el0);
+	isb();
+}
+
+#define RETURN_READ_PMEVCNTRN(n) \
+	return read_sysreg(pmevcntr##n##_el0)
+static unsigned long read_pmevcntrn(int n)
+{
+	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
+	return 0;
+}
+
+#define WRITE_PMEVCNTRN(n) \
+	write_sysreg(val, pmevcntr##n##_el0)
+static void write_pmevcntrn(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
+	isb();
+}
+
+#define READ_PMEVTYPERN(n) \
+	return read_sysreg(pmevtyper##n##_el0)
+static unsigned long read_pmevtypern(int n)
+{
+	PMEVN_SWITCH(n, READ_PMEVTYPERN);
+	return 0;
+}
+
+#define WRITE_PMEVTYPERN(n) \
+	write_sysreg(val, pmevtyper##n##_el0)
+static void write_pmevtypern(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
+	isb();
+}
+
+/*
+ * The pmc_accessor structure has pointers to PMEV{CNTR,TYPER}<n>_EL0
+ * accessors that test cases will use. Each of the accessors will
+ * either directly reads/writes PMEV{CNTR,TYPER}<n>_EL0
+ * (i.e. {read,write}_pmev{cnt,type}rn()), or reads/writes them through
+ * PMXEV{CNTR,TYPER}_EL0 (i.e. {read,write}_sel_ev{cnt,type}r()).
+ *
+ * This is used to test that combinations of those accessors provide
+ * the consistent behavior.
+ */
+struct pmc_accessor {
+	/* A function to be used to read PMEVTCNTR<n>_EL0 */
+	unsigned long	(*read_cntr)(int idx);
+	/* A function to be used to write PMEVTCNTR<n>_EL0 */
+	void		(*write_cntr)(int idx, unsigned long val);
+	/* A function to be used to read PMEVTYPER<n>_EL0 */
+	unsigned long	(*read_typer)(int idx);
+	/* A function to be used to write PMEVTYPER<n>_EL0 */
+	void		(*write_typer)(int idx, unsigned long val);
+};
+
+struct pmc_accessor pmc_accessors[] = {
+	/* test with all direct accesses */
+	{ read_pmevcntrn, write_pmevcntrn, read_pmevtypern, write_pmevtypern },
+	/* test with all indirect accesses */
+	{ read_sel_evcntr, write_sel_evcntr, read_sel_evtyper, write_sel_evtyper },
+	/* read with direct accesses, and write with indirect accesses */
+	{ read_pmevcntrn, write_sel_evcntr, read_pmevtypern, write_sel_evtyper },
+	/* read with indirect accesses, and write with direct accesses */
+	{ read_sel_evcntr, write_pmevcntrn, read_sel_evtyper, write_pmevtypern },
+};
+
+/*
+ * Convert a pointer of pmc_accessor to an index in pmc_accessors[],
+ * assuming that the pointer is one of the entries in pmc_accessors[].
+ */
+#define PMC_ACC_TO_IDX(acc)	(acc - &pmc_accessors[0])
+
+#define GUEST_ASSERT_BITMAP_REG(regname, mask, set_expected)			 \
+{										 \
+	uint64_t _tval = read_sysreg(regname);					 \
+										 \
+	if (set_expected)							 \
+		__GUEST_ASSERT((_tval & mask),					 \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				_tval, mask, set_expected);			 \
+	else									 \
+		__GUEST_ASSERT(!(_tval & mask),					 \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				_tval, mask, set_expected);			 \
+}
+
+/*
+ * Check if @mask bits in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers
+ * are set or cleared as specified in @set_expected.
+ */
+static void check_bitmap_pmu_regs(uint64_t mask, bool set_expected)
+{
+	GUEST_ASSERT_BITMAP_REG(pmcntenset_el0, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmcntenclr_el0, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmintenset_el1, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmintenclr_el1, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmovsset_el0, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmovsclr_el0, mask, set_expected);
+}
+
+/*
+ * Check if the bit in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers corresponding
+ * to the specified counter (@pmc_idx) can be read/written as expected.
+ * When @set_op is true, it tries to set the bit for the counter in
+ * those registers by writing the SET registers (the bit won't be set
+ * if the counter is not implemented though).
+ * Otherwise, it tries to clear the bits in the registers by writing
+ * the CLR registers.
+ * Then, it checks if the values indicated in the registers are as expected.
+ */
+static void test_bitmap_pmu_regs(int pmc_idx, bool set_op)
+{
+	uint64_t pmcr_n, test_bit = BIT(pmc_idx);
+	bool set_expected = false;
+
+	if (set_op) {
+		write_sysreg(test_bit, pmcntenset_el0);
+		write_sysreg(test_bit, pmintenset_el1);
+		write_sysreg(test_bit, pmovsset_el0);
+
+		/* The bit will be set only if the counter is implemented */
+		pmcr_n = get_pmcr_n(read_sysreg(pmcr_el0));
+		set_expected = (pmc_idx < pmcr_n) ? true : false;
+	} else {
+		write_sysreg(test_bit, pmcntenclr_el0);
+		write_sysreg(test_bit, pmintenclr_el1);
+		write_sysreg(test_bit, pmovsclr_el0);
+	}
+	check_bitmap_pmu_regs(test_bit, set_expected);
+}
+
+/*
+ * Tests for reading/writing registers for the (implemented) event counter
+ * specified by @pmc_idx.
+ */
+static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
+{
+	uint64_t write_data, read_data;
+
+	/* Disable all PMCs and reset all PMCs to zero. */
+	pmu_disable_reset();
+
+	/*
+	 * Tests for reading/writing {PMCNTEN,PMINTEN,PMOVS}{SET,CLR}_EL1.
+	 */
+
+	/* Make sure that the bit in those registers are set to 0 */
+	test_bitmap_pmu_regs(pmc_idx, false);
+	/* Test if setting the bit in those registers works */
+	test_bitmap_pmu_regs(pmc_idx, true);
+	/* Test if clearing the bit in those registers works */
+	test_bitmap_pmu_regs(pmc_idx, false);
+
+	/*
+	 * Tests for reading/writing the event type register.
+	 */
+
+	/*
+	 * Set the event type register to an arbitrary value just for testing
+	 * of reading/writing the register.
+	 * Arm ARM says that for the event from 0x0000 to 0x003F,
+	 * the value indicated in the PMEVTYPER<n>_EL0.evtCount field is
+	 * the value written to the field even when the specified event
+	 * is not supported.
+	 */
+	write_data = (ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMUV3_PERFCTR_INST_RETIRED);
+	acc->write_typer(pmc_idx, write_data);
+	read_data = acc->read_typer(pmc_idx);
+	__GUEST_ASSERT(read_data == write_data,
+		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
+
+	/*
+	 * Tests for reading/writing the event count register.
+	 */
+
+	read_data = acc->read_cntr(pmc_idx);
+
+	/* The count value must be 0, as it is disabled and reset */
+	__GUEST_ASSERT(read_data == 0,
+		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx",
+		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data);
+
+	write_data = read_data + pmc_idx + 0x12345;
+	acc->write_cntr(pmc_idx, write_data);
+	read_data = acc->read_cntr(pmc_idx);
+	__GUEST_ASSERT(read_data == write_data,
+		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
+}
+
+#define INVALID_EC	(-1ul)
+uint64_t expected_ec = INVALID_EC;
+
+static void guest_sync_handler(struct ex_regs *regs)
+{
+	uint64_t esr, ec;
+
+	esr = read_sysreg(esr_el1);
+	ec = (esr >> ESR_EC_SHIFT) & ESR_EC_MASK;
+
+	__GUEST_ASSERT(expected_ec == ec,
+			"PC: 0x%lx; ESR: 0x%lx; EC: 0x%lx; EC expected: 0x%lx",
+			regs->pc, esr, ec, expected_ec);
+
+	/* skip the trapping instruction */
+	regs->pc += 4;
+
+	/* Use INVALID_EC to indicate an exception occurred */
+	expected_ec = INVALID_EC;
+}
+
+/*
+ * Run the given operation that should trigger an exception with the
+ * given exception class. The exception handler (guest_sync_handler)
+ * will reset op_end_addr to 0, expected_ec to INVALID_EC, and skip
+ * the instruction that trapped.
+ */
+#define TEST_EXCEPTION(ec, ops)				\
+({							\
+	GUEST_ASSERT(ec != INVALID_EC);			\
+	WRITE_ONCE(expected_ec, ec);			\
+	dsb(ish);					\
+	ops;						\
+	GUEST_ASSERT(expected_ec == INVALID_EC);	\
+})
+
+/*
+ * Tests for reading/writing registers for the unimplemented event counter
+ * specified by @pmc_idx (>= PMCR_EL0.N).
+ */
+static void test_access_invalid_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
+{
+	/*
+	 * Reading/writing the event count/type registers should cause
+	 * an UNDEFINED exception.
+	 */
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->read_cntr(pmc_idx));
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->write_cntr(pmc_idx, 0));
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->read_typer(pmc_idx));
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->write_typer(pmc_idx, 0));
+	/*
+	 * The bit corresponding to the (unimplemented) counter in
+	 * {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers should be RAZ.
+	 */
+	test_bitmap_pmu_regs(pmc_idx, 1);
+	test_bitmap_pmu_regs(pmc_idx, 0);
+}
+
+/*
+ * The guest is configured with PMUv3 with @expected_pmcr_n number of
+ * event counters.
+ * Check if @expected_pmcr_n is consistent with PMCR_EL0.N, and
+ * if reading/writing PMU registers for implemented or unimplemented
+ * counters works as expected.
+ */
+static void guest_code(uint64_t expected_pmcr_n)
+{
+	uint64_t pmcr, pmcr_n, unimp_mask;
+	int i, pmc;
+
+	__GUEST_ASSERT(expected_pmcr_n <= ARMV8_PMU_MAX_GENERAL_COUNTERS,
+			"Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%lx",
+			expected_pmcr_n, ARMV8_PMU_MAX_GENERAL_COUNTERS);
+
+	pmcr = read_sysreg(pmcr_el0);
+	pmcr_n = get_pmcr_n(pmcr);
+
+	/* Make sure that PMCR_EL0.N indicates the value userspace set */
+	__GUEST_ASSERT(pmcr_n == expected_pmcr_n,
+			"Expected PMCR.N: 0x%lx, PMCR.N: 0x%lx",
+			expected_pmcr_n, pmcr_n);
+
+	/*
+	 * Make sure that (RAZ) bits corresponding to unimplemented event
+	 * counters in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers are reset
+	 * to zero.
+	 * (NOTE: bits for implemented event counters are reset to UNKNOWN)
+	 */
+	unimp_mask = GENMASK_ULL(ARMV8_PMU_MAX_GENERAL_COUNTERS - 1, pmcr_n);
+	check_bitmap_pmu_regs(unimp_mask, false);
+
+	/*
+	 * Tests for reading/writing PMU registers for implemented counters.
+	 * Use each combination of PMEV{CNTR,TYPER}<n>_EL0 accessor functions.
+	 */
+	for (i = 0; i < ARRAY_SIZE(pmc_accessors); i++) {
+		for (pmc = 0; pmc < pmcr_n; pmc++)
+			test_access_pmc_regs(&pmc_accessors[i], pmc);
+	}
+
+	/*
+	 * Tests for reading/writing PMU registers for unimplemented counters.
+	 * Use each combination of PMEV{CNTR,TYPER}<n>_EL0 accessor functions.
+	 */
+	for (i = 0; i < ARRAY_SIZE(pmc_accessors); i++) {
+		for (pmc = pmcr_n; pmc < ARMV8_PMU_MAX_GENERAL_COUNTERS; pmc++)
+			test_access_invalid_pmc_regs(&pmc_accessors[i], pmc);
+	}
+
+	GUEST_DONE();
+}
+
+#define GICD_BASE_GPA	0x8000000ULL
+#define GICR_BASE_GPA	0x80A0000ULL
+
+/* Create a VM that has one vCPU with PMUv3 configured. */
+static void create_vpmu_vm(void *guest_code)
+{
+	struct kvm_vcpu_init init;
+	uint8_t pmuver, ec;
+	uint64_t dfr0, irq = 23;
+	struct kvm_device_attr irq_attr = {
+		.group = KVM_ARM_VCPU_PMU_V3_CTRL,
+		.attr = KVM_ARM_VCPU_PMU_V3_IRQ,
+		.addr = (uint64_t)&irq,
+	};
+	struct kvm_device_attr init_attr = {
+		.group = KVM_ARM_VCPU_PMU_V3_CTRL,
+		.attr = KVM_ARM_VCPU_PMU_V3_INIT,
+	};
+
+	/* The test creates the vpmu_vm multiple times. Ensure a clean state */
+	memset(&vpmu_vm, 0, sizeof(vpmu_vm));
+
+	vpmu_vm.vm = vm_create(1);
+	vm_init_descriptor_tables(vpmu_vm.vm);
+	for (ec = 0; ec < ESR_EC_NUM; ec++) {
+		vm_install_sync_handler(vpmu_vm.vm, VECTOR_SYNC_CURRENT, ec,
+					guest_sync_handler);
+	}
+
+	/* Create vCPU with PMUv3 */
+	vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init);
+	init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3);
+	vpmu_vm.vcpu = aarch64_vcpu_add(vpmu_vm.vm, 0, &init, guest_code);
+	vcpu_init_descriptor_tables(vpmu_vm.vcpu);
+	vpmu_vm.gic_fd = vgic_v3_setup(vpmu_vm.vm, 1, 64,
+					GICD_BASE_GPA, GICR_BASE_GPA);
+	__TEST_REQUIRE(vpmu_vm.gic_fd >= 0,
+		       "Failed to create vgic-v3, skipping");
+
+	/* Make sure that PMUv3 support is indicated in the ID register */
+	vcpu_get_reg(vpmu_vm.vcpu,
+		     KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &dfr0);
+	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0);
+	TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF &&
+		    pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP,
+		    "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver);
+
+	/* Initialize vPMU */
+	vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &irq_attr);
+	vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &init_attr);
+}
+
+static void destroy_vpmu_vm(void)
+{
+	close(vpmu_vm.gic_fd);
+	kvm_vm_free(vpmu_vm.vm);
+}
+
+static void run_vcpu(struct kvm_vcpu *vcpu, uint64_t pmcr_n)
+{
+	struct ucall uc;
+
+	vcpu_args_set(vcpu, 1, pmcr_n);
+	vcpu_run(vcpu);
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	case UCALL_DONE:
+		break;
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		break;
+	}
+}
+
+static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
+{
+	struct kvm_vcpu *vcpu;
+	uint64_t pmcr, pmcr_orig;
+
+	create_vpmu_vm(guest_code);
+	vcpu = vpmu_vm.vcpu;
+
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr_orig);
+	pmcr = pmcr_orig;
+
+	/*
+	 * Setting a larger value of PMCR.N should not modify the field, and
+	 * return a success.
+	 */
+	set_pmcr_n(&pmcr, pmcr_n);
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr);
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr);
+
+	if (expect_fail)
+		TEST_ASSERT(pmcr_orig == pmcr,
+			    "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx\n",
+			    pmcr, pmcr_n);
+	else
+		TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr),
+			    "Failed to update PMCR.N to %lu (received: %lu)\n",
+			    pmcr_n, get_pmcr_n(pmcr));
+}
+
+/*
+ * Create a guest with one vCPU, set the PMCR_EL0.N for the vCPU to @pmcr_n,
+ * and run the test.
+ */
+static void run_access_test(uint64_t pmcr_n)
+{
+	uint64_t sp;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_init init;
+
+	pr_debug("Test with pmcr_n %lu\n", pmcr_n);
+
+	test_create_vpmu_vm_with_pmcr_n(pmcr_n, false);
+	vcpu = vpmu_vm.vcpu;
+
+	/* Save the initial sp to restore them later to run the guest again */
+	vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1), &sp);
+
+	run_vcpu(vcpu, pmcr_n);
+
+	/*
+	 * Reset and re-initialize the vCPU, and run the guest code again to
+	 * check if PMCR_EL0.N is preserved.
+	 */
+	vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init);
+	init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3);
+	aarch64_vcpu_setup(vcpu, &init);
+	vcpu_init_descriptor_tables(vcpu);
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), sp);
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+
+	run_vcpu(vcpu, pmcr_n);
+
+	destroy_vpmu_vm();
+}
+
+static struct pmreg_sets validity_check_reg_sets[] = {
+	PMREG_SET(SYS_PMCNTENSET_EL0, SYS_PMCNTENCLR_EL0),
+	PMREG_SET(SYS_PMINTENSET_EL1, SYS_PMINTENCLR_EL1),
+	PMREG_SET(SYS_PMOVSSET_EL0, SYS_PMOVSCLR_EL0),
+};
+
+/*
+ * Create a VM, and check if KVM handles the userspace accesses of
+ * the PMU register sets in @validity_check_reg_sets[] correctly.
+ */
+static void run_pmregs_validity_test(uint64_t pmcr_n)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+	uint64_t set_reg_id, clr_reg_id, reg_val;
+	uint64_t valid_counters_mask, max_counters_mask;
+
+	test_create_vpmu_vm_with_pmcr_n(pmcr_n, false);
+	vcpu = vpmu_vm.vcpu;
+
+	valid_counters_mask = get_counters_mask(pmcr_n);
+	max_counters_mask = get_counters_mask(ARMV8_PMU_MAX_COUNTERS);
+
+	for (i = 0; i < ARRAY_SIZE(validity_check_reg_sets); i++) {
+		set_reg_id = validity_check_reg_sets[i].set_reg_id;
+		clr_reg_id = validity_check_reg_sets[i].clr_reg_id;
+
+		/*
+		 * Test if the 'set' and 'clr' variants of the registers
+		 * are initialized based on the number of valid counters.
+		 */
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
+
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
+
+		/*
+		 * Using the 'set' variant, force-set the register to the
+		 * max number of possible counters and test if KVM discards
+		 * the bits for unimplemented counters as it should.
+		 */
+		vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), max_counters_mask);
+
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
+
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
+	}
+
+	destroy_vpmu_vm();
+}
+
+/*
+ * Create a guest with one vCPU, and attempt to set the PMCR_EL0.N for
+ * the vCPU to @pmcr_n, which is larger than the host value.
+ * The attempt should fail as @pmcr_n is too big to set for the vCPU.
+ */
+static void run_error_test(uint64_t pmcr_n)
+{
+	pr_debug("Error test with pmcr_n %lu (larger than the host)\n", pmcr_n);
+
+	test_create_vpmu_vm_with_pmcr_n(pmcr_n, true);
+	destroy_vpmu_vm();
+}
+
+/*
+ * Return the default number of implemented PMU event counters excluding
+ * the cycle counter (i.e. PMCR_EL0.N value) for the guest.
+ */
+static uint64_t get_pmcr_n_limit(void)
+{
+	uint64_t pmcr;
+
+	create_vpmu_vm(guest_code);
+	vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr);
+	destroy_vpmu_vm();
+	return get_pmcr_n(pmcr);
+}
+
+int main(void)
+{
+	uint64_t i, pmcr_n;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_PMU_V3));
+
+	pmcr_n = get_pmcr_n_limit();
+	for (i = 0; i <= pmcr_n; i++) {
+		run_access_test(i);
+		run_pmregs_validity_test(i);
+	}
+
+	for (i = pmcr_n + 1; i < ARMV8_PMU_MAX_COUNTERS; i++)
+		run_error_test(i);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index cb537253a6b9..c42d683102c7 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -104,6 +104,7 @@ enum {
 #define ESR_EC_SHIFT		26
 #define ESR_EC_MASK		(ESR_EC_NUM - 1)
 
+#define ESR_EC_UNKNOWN		0x0
 #define ESR_EC_SVC64		0x15
 #define ESR_EC_IABT		0x21
 #define ESR_EC_DABT		0x25
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 3a0259e25335..6fe12e985ba5 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -518,9 +518,9 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN4), val) != 0xf;
-	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN64), val) == 0;
-	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN16), val) != 0;
+	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val) != 0xf;
+	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val) == 0;
+	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val) != 0;
 
 	close(vcpu_fd);
 	close(vm_fd);