18 files changed, 505 insertions, 256 deletions
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index e6f66491fbe9..b9a66fc146c9 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -379,7 +379,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 				prot = __acpi_get_writethrough_mem_attribute();
 		}
 	}
-	return ioremap_prot(phys, size, pgprot_val(prot));
+	return ioremap_prot(phys, size, prot);
 }
 
 /*
diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c
index deff21bfa680..b68e1d328d4c 100644
--- a/arch/arm64/kernel/compat_alignment.c
+++ b/arch/arm64/kernel/compat_alignment.c
@@ -368,6 +368,8 @@ int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs)
 		return 1;
 	}
 
+	if (!handler)
+		return 1;
 	type = handler(addr, instr, regs);
 
 	if (type == TYPE_ERROR || type == TYPE_FAULT)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 7ce555862895..6b0ad5070d3e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -14,31 +14,85 @@
 #include <asm/kvm_asm.h>
 #include <asm/smp_plat.h>
 
+static u64 target_impl_cpu_num;
+static struct target_impl_cpu *target_impl_cpus;
+
+bool cpu_errata_set_target_impl(u64 num, void *impl_cpus)
+{
+	if (target_impl_cpu_num || !num || !impl_cpus)
+		return false;
+
+	target_impl_cpu_num = num;
+	target_impl_cpus = impl_cpus;
+	return true;
+}
+
+static inline bool is_midr_in_range(struct midr_range const *range)
+{
+	int i;
+
+	if (!target_impl_cpu_num)
+		return midr_is_cpu_model_range(read_cpuid_id(), range->model,
+					       range->rv_min, range->rv_max);
+
+	for (i = 0; i < target_impl_cpu_num; i++) {
+		if (midr_is_cpu_model_range(target_impl_cpus[i].midr,
+					    range->model,
+					    range->rv_min, range->rv_max))
+			return true;
+	}
+	return false;
+}
+
+bool is_midr_in_range_list(struct midr_range const *ranges)
+{
+	while (ranges->model)
+		if (is_midr_in_range(ranges++))
+			return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(is_midr_in_range_list);
+
 static bool __maybe_unused
-is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
+__is_affected_midr_range(const struct arm64_cpu_capabilities *entry,
+			 u32 midr, u32 revidr)
 {
 	const struct arm64_midr_revidr *fix;
-	u32 midr = read_cpuid_id(), revidr;
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	if (!is_midr_in_range(midr, &entry->midr_range))
+	if (!is_midr_in_range(&entry->midr_range))
 		return false;
 
 	midr &= MIDR_REVISION_MASK | MIDR_VARIANT_MASK;
-	revidr = read_cpuid(REVIDR_EL1);
 	for (fix = entry->fixed_revs; fix && fix->revidr_mask; fix++)
 		if (midr == fix->midr_rv && (revidr & fix->revidr_mask))
 			return false;
-
 	return true;
 }
 
 static bool __maybe_unused
+is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	int i;
+
+	if (!target_impl_cpu_num) {
+		WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+		return __is_affected_midr_range(entry, read_cpuid_id(),
+						read_cpuid(REVIDR_EL1));
+	}
+
+	for (i = 0; i < target_impl_cpu_num; i++) {
+		if (__is_affected_midr_range(entry, target_impl_cpus[i].midr,
+					     target_impl_cpus[i].midr))
+			return true;
+	}
+	return false;
+}
+
+static bool __maybe_unused
 is_affected_midr_range_list(const struct arm64_cpu_capabilities *entry,
 			    int scope)
 {
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list);
+	return is_midr_in_range_list(entry->midr_range_list);
 }
 
 static bool __maybe_unused
@@ -186,12 +240,48 @@ static bool __maybe_unused
 has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 				int scope)
 {
-	u32 midr = read_cpuid_id();
 	bool has_dic = read_cpuid_cachetype() & BIT(CTR_EL0_DIC_SHIFT);
 	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range(midr, &range) && has_dic;
+	return is_midr_in_range(&range) && has_dic;
+}
+
+static const struct midr_range impdef_pmuv3_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX),
+	{},
+};
+
+static bool has_impdef_pmuv3(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	unsigned int pmuver;
+
+	if (!is_kernel_in_hyp_mode())
+		return false;
+
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
+						      ID_AA64DFR0_EL1_PMUVer_SHIFT);
+	if (pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		return false;
+
+	return is_midr_in_range_list(impdef_pmuv3_cpus);
+}
+
+static void cpu_enable_impdef_pmuv3_traps(const struct arm64_cpu_capabilities *__unused)
+{
+	sysreg_clear_set_s(SYS_HACR_EL2, 0, BIT(56));
 }
 
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
@@ -245,7 +335,7 @@ static const struct midr_range cavium_erratum_23154_cpus[] = {
 #endif
 
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
 	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
 	MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
 	/* Cavium ThunderX, T81 pass 1.0 */
@@ -795,5 +885,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 				})),
 	},
 	{
+		.desc = "Apple IMPDEF PMUv3 Traps",
+		.capability = ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_impdef_pmuv3,
+		.cpu_enable = cpu_enable_impdef_pmuv3_traps,
+	},
+	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d561cf3b8ac7..9c4d6d552b25 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -86,6 +86,7 @@
 #include <asm/kvm_host.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
+#include <asm/hypervisor.h>
 #include <asm/processor.h>
 #include <asm/smp.h>
 #include <asm/sysreg.h>
@@ -497,6 +498,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr4[] = {
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_E2H0_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_NV_frac_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1792,7 +1794,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 	char const *str = "kpti command line option";
 	bool meltdown_safe;
 
-	meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+	meltdown_safe = is_midr_in_range_list(kpti_safe_list);
 
 	/* Defer to CPU feature registers */
 	if (has_cpuid_feature(entry, scope))
@@ -1862,7 +1864,7 @@ static bool has_nv1(const struct arm64_cpu_capabilities *entry, int scope)
 
 	return (__system_matches_cap(ARM64_HAS_NESTED_VIRT) &&
 		!(has_cpuid_feature(entry, scope) ||
-		  is_midr_in_range_list(read_cpuid_id(), nv1_ni_list)));
+		  is_midr_in_range_list(nv1_ni_list)));
 }
 
 #if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2)
@@ -1898,6 +1900,28 @@ static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope)
 }
 #endif
 
+#ifdef CONFIG_HW_PERF_EVENTS
+static bool has_pmuv3(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	unsigned int pmuver;
+
+	/*
+	 * PMUVer follows the standard ID scheme for an unsigned field with the
+	 * exception of 0xF (IMP_DEF) which is treated specially and implies
+	 * FEAT_PMUv3 is not implemented.
+	 *
+	 * See DDI0487L.a D24.1.3.2 for more details.
+	 */
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
+						      ID_AA64DFR0_EL1_PMUVer_SHIFT);
+	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		return false;
+
+	return pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP;
+}
+#endif
+
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 #define KPTI_NG_TEMP_VA		(-(1UL << PMD_SHIFT))
 
@@ -2045,7 +2069,7 @@ static bool cpu_has_broken_dbm(void)
 		{},
 	};
 
-	return is_midr_in_range_list(read_cpuid_id(), cpus);
+	return is_midr_in_range_list(cpus);
 }
 
 static bool cpu_can_use_dbm(const struct arm64_cpu_capabilities *cap)
@@ -2162,7 +2186,7 @@ static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap,
 	if (kvm_get_mode() != KVM_MODE_NV)
 		return false;
 
-	if (!has_cpuid_feature(cap, scope)) {
+	if (!cpucap_multi_entry_cap_matches(cap, scope)) {
 		pr_warn("unavailable: %s\n", cap->desc);
 		return false;
 	}
@@ -2519,7 +2543,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_NESTED_VIRT,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_nested_virt_support,
-		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2)
+		.match_list = (const struct arm64_cpu_capabilities []){
+			{
+				.matches = has_cpuid_feature,
+				ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2)
+			},
+			{
+				.matches = has_cpuid_feature,
+				ARM64_CPUID_FIELDS(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)
+			},
+			{ /* Sentinel */ }
+		},
 	},
 	{
 		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
@@ -2999,6 +3033,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, GCS, IMP)
 	},
 #endif
+#ifdef CONFIG_HW_PERF_EVENTS
+	{
+		.desc = "PMUv3",
+		.capability = ARM64_HAS_PMUV3,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_pmuv3,
+	},
+#endif
 	{},
 };
 
@@ -3680,6 +3722,7 @@ unsigned long cpu_get_elf_hwcap3(void)
 
 static void __init setup_boot_cpu_capabilities(void)
 {
+	kvm_arm_target_impl_cpu_init();
 	/*
 	 * The boot CPU's feature register values have been recorded. Detect
 	 * boot cpucaps and local cpucaps for the boot CPU, then enable and
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 2e94d20c4ac7..b735f4c2fe5e 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -27,9 +27,10 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 	int ret = 1;
 	unsigned long addr;
 	void *tags = NULL;
+	int locked = 0;
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
-		struct page *page = get_dump_page(addr);
+		struct page *page = get_dump_page(addr, &locked);
 
 		/*
 		 * get_dump_page() returns NULL when encountering an empty
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index d7c0d023dfe5..5a890714ee2e 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -320,14 +320,13 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	 * dealing with an out-of-range condition, we can assume it
 	 * is due to a module being loaded far away from the kernel.
 	 *
-	 * NOTE: __module_text_address() must be called with preemption
-	 * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+	 * NOTE: __module_text_address() must be called within a RCU read
+	 * section, but we can rely on ftrace_lock to ensure that 'mod'
 	 * retains its validity throughout the remainder of this code.
 	 */
 	if (!mod) {
-		preempt_disable();
+		guard(rcu)();
 		mod = __module_text_address(pc);
-		preempt_enable();
 	}
 
 	if (WARN_ON(!mod))
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index ef3a69cc398e..2004b4f41ade 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -47,9 +47,6 @@ PROVIDE(__pi_id_aa64smfr0_override	= id_aa64smfr0_override);
 PROVIDE(__pi_id_aa64zfr0_override	= id_aa64zfr0_override);
 PROVIDE(__pi_arm64_sw_feature_override	= arm64_sw_feature_override);
 PROVIDE(__pi_arm64_use_ng_mappings	= arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus	= cavium_erratum_27456_cpus);
-#endif
 PROVIDE(__pi__ctype			= _ctype);
 PROVIDE(__pi_memstart_offset_seed	= memstart_offset_seed);
 
@@ -112,11 +109,6 @@ KVM_NVHE_ALIAS(broken_cntvoff_key);
 KVM_NVHE_ALIAS(__start___kvm_ex_table);
 KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 
-/* PMU available static key */
-#ifdef CONFIG_HW_PERF_EVENTS
-KVM_NVHE_ALIAS(kvm_arm_pmu_available);
-#endif
-
 /* Position-independent library routines */
 KVM_NVHE_ALIAS_HYP(clear_page, __pi_clear_page);
 KVM_NVHE_ALIAS_HYP(copy_page, __pi_copy_page);
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index e57b043f324b..c6650cfe706c 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -207,6 +207,29 @@ static void __init map_fdt(u64 fdt)
 	dsb(ishst);
 }
 
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+	static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+		/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+		/* Cavium ThunderX, T81 pass 1.0 */
+		MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+		{},
+	};
+
+	for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+		if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+					    r->rv_min, r->rv_max))
+			return false;
+	}
+
+	return true;
+}
+
 asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 {
 	static char const chosen_str[] __initconst = "/chosen";
@@ -246,7 +269,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 		u64 kaslr_seed = kaslr_early_init(fdt, chosen);
 
 		if (kaslr_seed && kaslr_requires_kpti())
-			arm64_use_ng_mappings = true;
+			arm64_use_ng_mappings = ng_mappings_allowed();
 
 		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
 	}
diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c
index 2b69e3beeef8..81345f68f9fc 100644
--- a/arch/arm64/kernel/pi/map_range.c
+++ b/arch/arm64/kernel/pi/map_range.c
@@ -31,7 +31,7 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 {
 	u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX;
 	pteval_t protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
-	int lshift = (3 - level) * (PAGE_SHIFT - 3);
+	int lshift = (3 - level) * PTDESC_TABLE_SHIFT;
 	u64 lmask = (PAGE_SIZE << lshift) - 1;
 
 	start	&= PAGE_MASK;
@@ -45,12 +45,12 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 	 * clearing the mapping
 	 */
 	if (protval)
-		protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
+		protval |= (level == 2) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
 
 	while (start < end) {
 		u64 next = min((start | lmask) + 1, PAGE_ALIGN(end));
 
-		if (level < 3 && (start | next | pa) & lmask) {
+		if (level < 2 || (level == 2 && (start | next | pa) & lmask)) {
 			/*
 			 * This chunk needs a finer grained mapping. Create a
 			 * table mapping if necessary and recurse.
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index da53722f95d4..b198dde79e59 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -172,7 +172,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void)
 		return SPECTRE_UNAFFECTED;
 
 	/* Alternatively, we have a list of unaffected CPUs */
-	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+	if (is_midr_in_range_list(spectre_v2_safe_list))
 		return SPECTRE_UNAFFECTED;
 
 	return SPECTRE_VULNERABLE;
@@ -331,7 +331,7 @@ bool has_spectre_v3a(const struct arm64_cpu_capabilities *entry, int scope)
 	};
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range_list(read_cpuid_id(), spectre_v3a_unsafe_list);
+	return is_midr_in_range_list(spectre_v3a_unsafe_list);
 }
 
 void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
@@ -475,7 +475,7 @@ static enum mitigation_state spectre_v4_get_cpu_hw_mitigation_state(void)
 		{ /* sentinel */ },
 	};
 
-	if (is_midr_in_range_list(read_cpuid_id(), spectre_v4_safe_list))
+	if (is_midr_in_range_list(spectre_v4_safe_list))
 		return SPECTRE_UNAFFECTED;
 
 	/* CPU features are detected first */
@@ -845,52 +845,87 @@ static unsigned long system_bhb_mitigations;
  * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any
  * SCOPE_SYSTEM call will give the right answer.
  */
-u8 spectre_bhb_loop_affected(int scope)
+static bool is_spectre_bhb_safe(int scope)
+{
+	static const struct midr_range spectre_bhb_safe_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A520),
+		MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
+		{},
+	};
+	static bool all_safe = true;
+
+	if (scope != SCOPE_LOCAL_CPU)
+		return all_safe;
+
+	if (is_midr_in_range_list(spectre_bhb_safe_list))
+		return true;
+
+	all_safe = false;
+
+	return false;
+}
+
+static u8 spectre_bhb_loop_affected(void)
 {
 	u8 k = 0;
-	static u8 max_bhb_k;
-
-	if (scope == SCOPE_LOCAL_CPU) {
-		static const struct midr_range spectre_bhb_k32_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k24_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k11_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_AMPERE1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k8_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-			{},
-		};
-
-		if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list))
-			k = 32;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list))
-			k = 24;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list))
-			k = 11;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list))
-			k =  8;
-
-		max_bhb_k = max(max_bhb_k, k);
-	} else {
-		k = max_bhb_k;
-	}
+
+	static const struct midr_range spectre_bhb_k132_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+	};
+	static const struct midr_range spectre_bhb_k38_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+	};
+	static const struct midr_range spectre_bhb_k32_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k24_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A76AE),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD),
+		MIDR_ALL_VERSIONS(MIDR_HISI_HIP09),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k11_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_AMPERE1),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k8_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		{},
+	};
+
+	if (is_midr_in_range_list(spectre_bhb_k132_list))
+		k = 132;
+	else if (is_midr_in_range_list(spectre_bhb_k38_list))
+		k = 38;
+	else if (is_midr_in_range_list(spectre_bhb_k32_list))
+		k = 32;
+	else if (is_midr_in_range_list(spectre_bhb_k24_list))
+		k = 24;
+	else if (is_midr_in_range_list(spectre_bhb_k11_list))
+		k = 11;
+	else if (is_midr_in_range_list(spectre_bhb_k8_list))
+		k =  8;
 
 	return k;
 }
@@ -916,29 +951,13 @@ static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void)
 	}
 }
 
-static bool is_spectre_bhb_fw_affected(int scope)
+static bool has_spectre_bhb_fw_mitigation(void)
 {
-	static bool system_affected;
 	enum mitigation_state fw_state;
 	bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE;
-	static const struct midr_range spectre_bhb_firmware_mitigated_list[] = {
-		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-		{},
-	};
-	bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(),
-					 spectre_bhb_firmware_mitigated_list);
-
-	if (scope != SCOPE_LOCAL_CPU)
-		return system_affected;
 
 	fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
-	if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) {
-		system_affected = true;
-		return true;
-	}
-
-	return false;
+	return has_smccc && fw_state == SPECTRE_MITIGATED;
 }
 
 static bool supports_ecbhb(int scope)
@@ -954,6 +973,8 @@ static bool supports_ecbhb(int scope)
 						    ID_AA64MMFR1_EL1_ECBHB_SHIFT);
 }
 
+static u8 max_bhb_k;
+
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 			     int scope)
 {
@@ -962,16 +983,18 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 	if (supports_csv2p3(scope))
 		return false;
 
-	if (supports_clearbhb(scope))
-		return true;
-
-	if (spectre_bhb_loop_affected(scope))
-		return true;
+	if (is_spectre_bhb_safe(scope))
+		return false;
 
-	if (is_spectre_bhb_fw_affected(scope))
-		return true;
+	/*
+	 * At this point the core isn't known to be "safe" so we're going to
+	 * assume it's vulnerable. We still need to update `max_bhb_k` though,
+	 * but only if we aren't mitigating with clearbhb though.
+	 */
+	if (scope == SCOPE_LOCAL_CPU && !supports_clearbhb(SCOPE_LOCAL_CPU))
+		max_bhb_k = max(max_bhb_k, spectre_bhb_loop_affected());
 
-	return false;
+	return true;
 }
 
 static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
@@ -1002,7 +1025,7 @@ early_param("nospectre_bhb", parse_spectre_bhb_param);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 {
 	bp_hardening_cb_t cpu_cb;
-	enum mitigation_state fw_state, state = SPECTRE_VULNERABLE;
+	enum mitigation_state state = SPECTRE_VULNERABLE;
 	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
 
 	if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU))
@@ -1028,7 +1051,7 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN);
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_INSN, &system_bhb_mitigations);
-	} else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) {
+	} else if (spectre_bhb_loop_affected()) {
 		/*
 		 * Ensure KVM uses the indirect vector which will have the
 		 * branchy-loop added. A57/A72-r0 will already have selected
@@ -1041,32 +1064,29 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP);
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_LOOP, &system_bhb_mitigations);
-	} else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) {
-		fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
-		if (fw_state == SPECTRE_MITIGATED) {
-			/*
-			 * Ensure KVM uses one of the spectre bp_hardening
-			 * vectors. The indirect vector doesn't include the EL3
-			 * call, so needs upgrading to
-			 * HYP_VECTOR_SPECTRE_INDIRECT.
-			 */
-			if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
-				data->slot += 1;
-
-			this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
-
-			/*
-			 * The WA3 call in the vectors supersedes the WA1 call
-			 * made during context-switch. Uninstall any firmware
-			 * bp_hardening callback.
-			 */
-			cpu_cb = spectre_v2_get_sw_mitigation_cb();
-			if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
-				__this_cpu_write(bp_hardening_data.fn, NULL);
-
-			state = SPECTRE_MITIGATED;
-			set_bit(BHB_FW, &system_bhb_mitigations);
-		}
+	} else if (has_spectre_bhb_fw_mitigation()) {
+		/*
+		 * Ensure KVM uses one of the spectre bp_hardening
+		 * vectors. The indirect vector doesn't include the EL3
+		 * call, so needs upgrading to
+		 * HYP_VECTOR_SPECTRE_INDIRECT.
+		 */
+		if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
+			data->slot += 1;
+
+		this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
+
+		/*
+		 * The WA3 call in the vectors supersedes the WA1 call
+		 * made during context-switch. Uninstall any firmware
+		 * bp_hardening callback.
+		 */
+		cpu_cb = spectre_v2_get_sw_mitigation_cb();
+		if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
+			__this_cpu_write(bp_hardening_data.fn, NULL);
+
+		state = SPECTRE_MITIGATED;
+		set_bit(BHB_FW, &system_bhb_mitigations);
 	}
 
 	update_mitigation_state(&spectre_bhb_state, state);
@@ -1100,7 +1120,6 @@ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
 {
 	u8 rd;
 	u32 insn;
-	u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM);
 
 	BUG_ON(nr_inst != 1); /* MOV -> MOV */
 
@@ -1109,7 +1128,7 @@ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
 
 	insn = le32_to_cpu(*origptr);
 	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
-	insn = aarch64_insn_gen_movewide(rd, loop_count, 0,
+	insn = aarch64_insn_gen_movewide(rd, max_bhb_k, 0,
 					 AARCH64_INSN_VARIANT_64BIT,
 					 AARCH64_INSN_MOVEWIDE_ZERO);
 	*updptr++ = cpu_to_le32(insn);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 99ea26d400ff..a7c37afb4ebe 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -91,7 +91,7 @@ static void save_reset_user_access_state(struct user_access_state *ua_state)
 		u64 por_enable_all = 0;
 
 		for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
-			por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
+			por_enable_all |= POR_ELx_PERM_PREP(pkey, POE_RWX);
 
 		ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
 		write_sysreg_s(por_enable_all, SYS_POR_EL0);
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index cb180684d10d..5d07ee85bdae 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -15,8 +15,11 @@
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
+#include <linux/sched/isolation.h>
+#include <linux/xarray.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
@@ -37,17 +40,28 @@ static bool __init acpi_cpu_is_threaded(int cpu)
 	return !!is_threaded;
 }
 
+struct cpu_smt_info {
+	unsigned int thread_num;
+	int core_id;
+};
+
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
 int __init parse_acpi_topology(void)
 {
+	unsigned int max_smt_thread_num = 1;
+	struct cpu_smt_info *entry;
+	struct xarray hetero_cpu;
+	unsigned long hetero_id;
 	int cpu, topology_id;
 
 	if (acpi_disabled)
 		return 0;
 
+	xa_init(&hetero_cpu);
+
 	for_each_possible_cpu(cpu) {
 		topology_id = find_acpi_cpu_topology(cpu, 0);
 		if (topology_id < 0)
@@ -57,6 +71,34 @@ int __init parse_acpi_topology(void)
 			cpu_topology[cpu].thread_id = topology_id;
 			topology_id = find_acpi_cpu_topology(cpu, 1);
 			cpu_topology[cpu].core_id   = topology_id;
+
+			/*
+			 * In the PPTT, CPUs below a node with the 'identical
+			 * implementation' flag have the same number of threads.
+			 * Count the number of threads for only one CPU (i.e.
+			 * one core_id) among those with the same hetero_id.
+			 * See the comment of find_acpi_cpu_topology_hetero_id()
+			 * for more details.
+			 *
+			 * One entry is created for each node having:
+			 * - the 'identical implementation' flag
+			 * - its parent not having the flag
+			 */
+			hetero_id = find_acpi_cpu_topology_hetero_id(cpu);
+			entry = xa_load(&hetero_cpu, hetero_id);
+			if (!entry) {
+				entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+				WARN_ON_ONCE(!entry);
+
+				if (entry) {
+					entry->core_id = topology_id;
+					entry->thread_num = 1;
+					xa_store(&hetero_cpu, hetero_id,
+						 entry, GFP_KERNEL);
+				}
+			} else if (entry->core_id == topology_id) {
+				entry->thread_num++;
+			}
 		} else {
 			cpu_topology[cpu].thread_id  = -1;
 			cpu_topology[cpu].core_id    = topology_id;
@@ -67,6 +109,19 @@ int __init parse_acpi_topology(void)
 		cpu_topology[cpu].package_id = topology_id;
 	}
 
+	/*
+	 * This is a short loop since the number of XArray elements is the
+	 * number of heterogeneous CPU clusters. On a homogeneous system
+	 * there's only one entry in the XArray.
+	 */
+	xa_for_each(&hetero_cpu, hetero_id, entry) {
+		max_smt_thread_num = max(max_smt_thread_num, entry->thread_num);
+		xa_erase(&hetero_cpu, hetero_id);
+		kfree(entry);
+	}
+
+	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+	xa_destroy(&hetero_cpu);
 	return 0;
 }
 #endif
@@ -88,18 +143,28 @@ int __init parse_acpi_topology(void)
  * initialized.
  */
 static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
-static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
-static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
 static cpumask_var_t amu_fie_cpus;
 
+struct amu_cntr_sample {
+	u64		arch_const_cycles_prev;
+	u64		arch_core_cycles_prev;
+	unsigned long	last_scale_update;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct amu_cntr_sample, cpu_amu_samples);
+
 void update_freq_counters_refs(void)
 {
-	this_cpu_write(arch_core_cycles_prev, read_corecnt());
-	this_cpu_write(arch_const_cycles_prev, read_constcnt());
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
+
+	amu_sample->arch_core_cycles_prev = read_corecnt();
+	amu_sample->arch_const_cycles_prev = read_constcnt();
 }
 
 static inline bool freq_counters_valid(int cpu)
 {
+	struct amu_cntr_sample *amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
 	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
 		return false;
 
@@ -108,8 +173,8 @@ static inline bool freq_counters_valid(int cpu)
 		return false;
 	}
 
-	if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
-		     !per_cpu(arch_core_cycles_prev, cpu))) {
+	if (unlikely(!amu_sample->arch_const_cycles_prev ||
+		     !amu_sample->arch_core_cycles_prev)) {
 		pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
 		return false;
 	}
@@ -152,17 +217,22 @@ void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 
 static void amu_scale_freq_tick(void)
 {
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
 	u64 prev_core_cnt, prev_const_cnt;
 	u64 core_cnt, const_cnt, scale;
 
-	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
-	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+	prev_const_cnt = amu_sample->arch_const_cycles_prev;
+	prev_core_cnt = amu_sample->arch_core_cycles_prev;
 
 	update_freq_counters_refs();
 
-	const_cnt = this_cpu_read(arch_const_cycles_prev);
-	core_cnt = this_cpu_read(arch_core_cycles_prev);
+	const_cnt = amu_sample->arch_const_cycles_prev;
+	core_cnt = amu_sample->arch_core_cycles_prev;
 
+	/*
+	 * This should not happen unless the AMUs have been reset and the
+	 * counter values have not been restored - unlikely
+	 */
 	if (unlikely(core_cnt <= prev_core_cnt ||
 		     const_cnt <= prev_const_cnt))
 		return;
@@ -182,6 +252,8 @@ static void amu_scale_freq_tick(void)
 
 	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
 	this_cpu_write(arch_freq_scale, (unsigned long)scale);
+
+	amu_sample->last_scale_update = jiffies;
 }
 
 static struct scale_freq_data amu_sfd = {
@@ -189,6 +261,96 @@ static struct scale_freq_data amu_sfd = {
 	.set_freq_scale = amu_scale_freq_tick,
 };
 
+static __always_inline bool amu_fie_cpu_supported(unsigned int cpu)
+{
+	return cpumask_available(amu_fie_cpus) &&
+		cpumask_test_cpu(cpu, amu_fie_cpus);
+}
+
+void arch_cpu_idle_enter(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (!amu_fie_cpu_supported(cpu))
+		return;
+
+	/* Kick in AMU update but only if one has not happened already */
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK) &&
+	    time_is_before_jiffies(per_cpu(cpu_amu_samples.last_scale_update, cpu)))
+		amu_scale_freq_tick();
+}
+
+#define AMU_SAMPLE_EXP_MS	20
+
+int arch_freq_get_on_cpu(int cpu)
+{
+	struct amu_cntr_sample *amu_sample;
+	unsigned int start_cpu = cpu;
+	unsigned long last_update;
+	unsigned int freq = 0;
+	u64 scale;
+
+	if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
+		return -EOPNOTSUPP;
+
+	while (1) {
+
+		amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
+		last_update = amu_sample->last_scale_update;
+
+		/*
+		 * For those CPUs that are in full dynticks mode, or those that have
+		 * not seen tick for a while, try an alternative source for the counters
+		 * (and thus freq scale), if available, for given policy: this boils
+		 * down to identifying an active cpu within the same freq domain, if any.
+		 */
+		if (!housekeeping_cpu(cpu, HK_TYPE_TICK) ||
+		    time_is_before_jiffies(last_update + msecs_to_jiffies(AMU_SAMPLE_EXP_MS))) {
+			struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+			int ref_cpu;
+
+			if (!policy)
+				return -EINVAL;
+
+			if (!cpumask_intersects(policy->related_cpus,
+						housekeeping_cpumask(HK_TYPE_TICK))) {
+				cpufreq_cpu_put(policy);
+				return -EOPNOTSUPP;
+			}
+
+			for_each_cpu_wrap(ref_cpu, policy->cpus, cpu + 1) {
+				if (ref_cpu == start_cpu) {
+					/* Prevent verifying same CPU twice */
+					ref_cpu = nr_cpu_ids;
+					break;
+				}
+				if (!idle_cpu(ref_cpu))
+					break;
+			}
+
+			cpufreq_cpu_put(policy);
+
+			if (ref_cpu >= nr_cpu_ids)
+				/* No alternative to pull info from */
+				return -EAGAIN;
+
+			cpu = ref_cpu;
+		} else {
+			break;
+		}
+	}
+	/*
+	 * Reversed computation to the one used to determine
+	 * the arch_freq_scale value
+	 * (see amu_scale_freq_tick for details)
+	 */
+	scale = arch_scale_freq_capacity(cpu);
+	freq = scale * arch_scale_freq_ref(cpu);
+	freq >>= SCHED_CAPACITY_SHIFT;
+	return freq;
+}
+
 static void amu_fie_setup(const struct cpumask *cpus)
 {
 	int cpu;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 4e26bd356a48..529cff825531 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -172,14 +172,6 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 	printk("%sCode: %s\n", lvl, str);
 }
 
-#ifdef CONFIG_PREEMPT
-#define S_PREEMPT " PREEMPT"
-#elif defined(CONFIG_PREEMPT_RT)
-#define S_PREEMPT " PREEMPT_RT"
-#else
-#define S_PREEMPT ""
-#endif
-
 #define S_SMP " SMP"
 
 static int __die(const char *str, long err, struct pt_regs *regs)
@@ -187,7 +179,7 @@ static int __die(const char *str, long err, struct pt_regs *regs)
 	static int die_counter;
 	int ret;
 
-	pr_emerg("Internal error: %s: %016lx [#%d]" S_PREEMPT S_SMP "\n",
+	pr_emerg("Internal error: %s: %016lx [#%d] " S_SMP "\n",
 		 str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index e8ed8e5b713b..78ddf6bdecad 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,7 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
@@ -57,12 +57,6 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
-/*
- * The vDSO data page.
- */
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
@@ -104,78 +98,6 @@ static int __init __vdso_init(enum vdso_abi abi)
 	return 0;
 }
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-static const struct vm_special_mapping vvar_map;
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_map))
-			zap_vma_pages(vma);
-	}
-
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
-static const struct vm_special_mapping vvar_map = {
-	.name   = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static int __setup_additional_pages(enum vdso_abi abi,
 				    struct mm_struct *mm,
 				    struct linux_binprm *bprm,
@@ -185,11 +107,11 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VDSO_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
@@ -197,20 +119,19 @@ static int __setup_additional_pages(enum vdso_abi abi,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_PFNMAP,
-				       &vvar_map);
+	ret = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(ret))
 		goto up_fail;
 
 	if (system_supports_bti_kernel())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_base += VDSO_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
 				       vdso_info[abi].cm);
 	if (IS_ERR(ret))
 		goto up_fail;
@@ -336,7 +257,8 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	 */
 	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
 				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC,
+				       VM_MAYREAD | VM_MAYEXEC |
+				       VM_SEALED_SYSMAP,
 				       &aarch32_vdso_maps[AA32_MAP_VECTORS]);
 
 	return PTR_ERR_OR_ZERO(ret);
@@ -359,7 +281,8 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	 */
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
-				       VM_MAYWRITE | VM_MAYEXEC,
+				       VM_MAYWRITE | VM_MAYEXEC |
+				       VM_SEALED_SYSMAP,
 				       &aarch32_vdso_maps[AA32_MAP_SIGPAGE]);
 	if (IS_ERR(ret))
 		goto out;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 35685c036044..5e27e46aa496 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -7,7 +7,7 @@
 #
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso := vgettimeofday.o note.o sigreturn.o vgetrandom.o vgetrandom-chacha.o
 
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 47ad6944f9f0..52314be29191 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -20,11 +20,8 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-	PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 25a2cb6317f3..f2dfdc7dc818 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -3,7 +3,7 @@
 # Makefile for vdso32
 #
 
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Same as cc-*option, but using CC_COMPAT instead of CC
 ifeq ($(CONFIG_CC_IS_CLANG), y)
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index 732702a187e9..e02b27487ce8 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -12,16 +12,15 @@
 #include <asm/page.h>
 #include <asm/vdso.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
 OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text