Merge branch 'for-next/cpufeature' into for-next/core

Additional CPU sanity checks for MTE and preparatory changes for systems
where not all of the CPUs support 32-bit EL0.

* for-next/cpufeature:
  arm64: Restrict undef hook for cpufeature registers
  arm64: Kill 32-bit applications scheduled on 64-bit-only CPUs
  KVM: arm64: Kill 32-bit vCPUs on systems with mismatched EL0 support
  arm64: Allow mismatched 32-bit EL0 support
  arm64: cpuinfo: Split AArch32 registers out into a separate struct
  arm64: Check if GMID_EL1.BS is the same on all CPUs
  arm64: Change the cpuinfo_arm64 member type for some sysregs to u64

8 files changed, 288 insertions, 98 deletions

diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 7faae6ff3ab4..0f6d16faa540 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -12,26 +12,7 @@
 /*
  * Records attributes of an individual CPU.
  */
-struct cpuinfo_arm64 {
-	struct cpu	cpu;
-	struct kobject	kobj;
-	u32		reg_ctr;
-	u32		reg_cntfrq;
-	u32		reg_dczid;
-	u32		reg_midr;
-	u32		reg_revidr;
-
-	u64		reg_id_aa64dfr0;
-	u64		reg_id_aa64dfr1;
-	u64		reg_id_aa64isar0;
-	u64		reg_id_aa64isar1;
-	u64		reg_id_aa64mmfr0;
-	u64		reg_id_aa64mmfr1;
-	u64		reg_id_aa64mmfr2;
-	u64		reg_id_aa64pfr0;
-	u64		reg_id_aa64pfr1;
-	u64		reg_id_aa64zfr0;
-
+struct cpuinfo_32bit {
 	u32		reg_id_dfr0;
 	u32		reg_id_dfr1;
 	u32		reg_id_isar0;
@@ -54,6 +35,30 @@ struct cpuinfo_arm64 {
 	u32		reg_mvfr0;
 	u32		reg_mvfr1;
 	u32		reg_mvfr2;
+};
+
+struct cpuinfo_arm64 {
+	struct cpu	cpu;
+	struct kobject	kobj;
+	u64		reg_ctr;
+	u64		reg_cntfrq;
+	u64		reg_dczid;
+	u64		reg_midr;
+	u64		reg_revidr;
+	u64		reg_gmid;
+
+	u64		reg_id_aa64dfr0;
+	u64		reg_id_aa64dfr1;
+	u64		reg_id_aa64isar0;
+	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64mmfr0;
+	u64		reg_id_aa64mmfr1;
+	u64		reg_id_aa64mmfr2;
+	u64		reg_id_aa64pfr0;
+	u64		reg_id_aa64pfr1;
+	u64		reg_id_aa64zfr0;
+
+	struct cpuinfo_32bit	aarch32;
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 338840c00e8e..9bb9d11750d7 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -619,6 +619,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0)
 	return val > 0;
 }
 
+static inline bool id_aa64pfr1_mte(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT);
+
+	return val >= ID_AA64PFR1_MTE;
+}
+
 void __init setup_cpu_features(void);
 void check_local_cpu_capabilities(void);
 
@@ -630,9 +637,15 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
 }
 
+const struct cpumask *system_32bit_el0_cpumask(void);
+DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
+
 static inline bool system_supports_32bit_el0(void)
 {
-	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	return static_branch_unlikely(&arm64_mismatched_32bit_el0) ||
+	       id_aa64pfr0_32bit_el0(pfr0);
 }
 
 static inline bool system_supports_4kb_granule(void)
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index efed2830d141..dbae006f625f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -108,6 +108,24 @@ bool arm64_use_ng_mappings = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
 /*
+ * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs
+ * support it?
+ */
+static bool __read_mostly allow_mismatched_32bit_el0;
+
+/*
+ * Static branch enabled only if allow_mismatched_32bit_el0 is set and we have
+ * seen at least one CPU capable of 32-bit EL0.
+ */
+DEFINE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
+
+/*
+ * Mask of CPUs supporting 32-bit EL0.
+ * Only valid if arm64_mismatched_32bit_el0 is enabled.
+ */
+static cpumask_var_t cpu_32bit_el0_mask __cpumask_var_read_mostly;
+
+/*
  * Flag to indicate if we have computed the system wide
  * capabilities based on the boot time active CPUs. This
  * will be used to determine if a new booting CPU should
@@ -400,6 +418,11 @@ static const struct arm64_ftr_bits ftr_dczid[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_gmid[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, SYS_GMID_EL1_BS_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_isar0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DIVIDE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DEBUG_SHIFT, 4, 0),
@@ -617,6 +640,9 @@ static const struct __ftr_reg_entry {
 	/* Op1 = 0, CRn = 1, CRm = 2 */
 	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
 
+	/* Op1 = 1, CRn = 0, CRm = 0 */
+	ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
+
 	/* Op1 = 3, CRn = 0, CRm = 0 */
 	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
@@ -767,7 +793,7 @@ static void __init sort_ftr_regs(void)
  * Any bits that are not covered by an arm64_ftr_bits entry are considered
  * RES0 for the system-wide value, and must strictly match.
  */
-static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
+static void init_cpu_ftr_reg(u32 sys_reg, u64 new)
 {
 	u64 val = 0;
 	u64 strict_mask = ~0x0ULL;
@@ -863,6 +889,31 @@ static void __init init_cpu_hwcaps_indirect_list(void)
 
 static void __init setup_boot_cpu_capabilities(void);
 
+static void init_32bit_cpu_features(struct cpuinfo_32bit *info)
+{
+	init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
+	init_cpu_ftr_reg(SYS_ID_DFR1_EL1, info->reg_id_dfr1);
+	init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
+	init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
+	init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
+	init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
+	init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
+	init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
+	init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6);
+	init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
+	init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
+	init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
+	init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
+	init_cpu_ftr_reg(SYS_ID_MMFR4_EL1, info->reg_id_mmfr4);
+	init_cpu_ftr_reg(SYS_ID_MMFR5_EL1, info->reg_id_mmfr5);
+	init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
+	init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
+	init_cpu_ftr_reg(SYS_ID_PFR2_EL1, info->reg_id_pfr2);
+	init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
+	init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
+	init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
+}
+
 void __init init_cpu_features(struct cpuinfo_arm64 *info)
 {
 	/* Before we start using the tables, make sure it is sorted */
@@ -882,35 +933,17 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
 
-	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
-		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
-		init_cpu_ftr_reg(SYS_ID_DFR1_EL1, info->reg_id_dfr1);
-		init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
-		init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
-		init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
-		init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
-		init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
-		init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
-		init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6);
-		init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
-		init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
-		init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
-		init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
-		init_cpu_ftr_reg(SYS_ID_MMFR4_EL1, info->reg_id_mmfr4);
-		init_cpu_ftr_reg(SYS_ID_MMFR5_EL1, info->reg_id_mmfr5);
-		init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
-		init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
-		init_cpu_ftr_reg(SYS_ID_PFR2_EL1, info->reg_id_pfr2);
-		init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
-		init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
-		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
-	}
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
+		init_32bit_cpu_features(&info->aarch32);
 
 	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
 		init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr);
 		sve_init_vq_map();
 	}
 
+	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
+		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
+
 	/*
 	 * Initialize the indirect array of CPU hwcaps capabilities pointers
 	 * before we handle the boot CPU below.
@@ -975,21 +1008,29 @@ static void relax_cpu_ftr_reg(u32 sys_id, int field)
 	WARN_ON(!ftrp->width);
 }
 
-static int update_32bit_cpu_features(int cpu, struct cpuinfo_arm64 *info,
-				     struct cpuinfo_arm64 *boot)
+static void lazy_init_32bit_cpu_features(struct cpuinfo_arm64 *info,
+					 struct cpuinfo_arm64 *boot)
+{
+	static bool boot_cpu_32bit_regs_overridden = false;
+
+	if (!allow_mismatched_32bit_el0 || boot_cpu_32bit_regs_overridden)
+		return;
+
+	if (id_aa64pfr0_32bit_el0(boot->reg_id_aa64pfr0))
+		return;
+
+	boot->aarch32 = info->aarch32;
+	init_32bit_cpu_features(&boot->aarch32);
+	boot_cpu_32bit_regs_overridden = true;
+}
+
+static int update_32bit_cpu_features(int cpu, struct cpuinfo_32bit *info,
+				     struct cpuinfo_32bit *boot)
 {
 	int taint = 0;
 	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
 	/*
-	 * If we don't have AArch32 at all then skip the checks entirely
-	 * as the register values may be UNKNOWN and we're not going to be
-	 * using them for anything.
-	 */
-	if (!id_aa64pfr0_32bit_el0(pfr0))
-		return taint;
-
-	/*
 	 * If we don't have AArch32 at EL1, then relax the strictness of
 	 * EL1-dependent register fields to avoid spurious sanity check fails.
 	 */
@@ -1135,10 +1176,29 @@ void update_cpu_features(int cpu,
 	}
 
 	/*
+	 * The kernel uses the LDGM/STGM instructions and the number of tags
+	 * they read/write depends on the GMID_EL1.BS field. Check that the
+	 * value is the same on all CPUs.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_MTE) &&
+	    id_aa64pfr1_mte(info->reg_id_aa64pfr1)) {
+		taint |= check_update_ftr_reg(SYS_GMID_EL1, cpu,
+					      info->reg_gmid, boot->reg_gmid);
+	}
+
+	/*
+	 * If we don't have AArch32 at all then skip the checks entirely
+	 * as the register values may be UNKNOWN and we're not going to be
+	 * using them for anything.
+	 *
 	 * This relies on a sanitised view of the AArch64 ID registers
 	 * (e.g. SYS_ID_AA64PFR0_EL1), so we call it last.
 	 */
-	taint |= update_32bit_cpu_features(cpu, info, boot);
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
+		lazy_init_32bit_cpu_features(info, boot);
+		taint |= update_32bit_cpu_features(cpu, &info->aarch32,
+						   &boot->aarch32);
+	}
 
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
@@ -1248,6 +1308,28 @@ has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
 	return feature_matches(val, entry);
 }
 
+const struct cpumask *system_32bit_el0_cpumask(void)
+{
+	if (!system_supports_32bit_el0())
+		return cpu_none_mask;
+
+	if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		return cpu_32bit_el0_mask;
+
+	return cpu_possible_mask;
+}
+
+static bool has_32bit_el0(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	if (!has_cpuid_feature(entry, scope))
+		return allow_mismatched_32bit_el0;
+
+	if (scope == SCOPE_SYSTEM)
+		pr_info("detected: 32-bit EL0 Support\n");
+
+	return true;
+}
+
 static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry, int scope)
 {
 	bool has_sre;
@@ -1866,10 +1948,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_copy_el2regs,
 	},
 	{
-		.desc = "32-bit EL0 Support",
-		.capability = ARM64_HAS_32BIT_EL0,
+		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
-		.matches = has_cpuid_feature,
+		.matches = has_32bit_el0,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.sign = FTR_UNSIGNED,
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
@@ -2378,7 +2459,7 @@ static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
 	{},
 };
 
-static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
+static void cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
@@ -2423,7 +2504,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 	return rc;
 }
 
-static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
+static void setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 {
 	/* We support emulation of accesses to CPU ID feature registers */
 	cpu_set_named_feature(CPUID);
@@ -2598,7 +2679,7 @@ static void check_early_cpu_features(void)
 }
 
 static void
-verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
+__verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
 {
 
 	for (; caps->matches; caps++)
@@ -2609,6 +2690,14 @@ verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
 		}
 }
 
+static void verify_local_elf_hwcaps(void)
+{
+	__verify_local_elf_hwcaps(arm64_elf_hwcaps);
+
+	if (id_aa64pfr0_32bit_el0(read_cpuid(ID_AA64PFR0_EL1)))
+		__verify_local_elf_hwcaps(compat_elf_hwcaps);
+}
+
 static void verify_sve_features(void)
 {
 	u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
@@ -2673,11 +2762,7 @@ static void verify_local_cpu_capabilities(void)
 	 * on all secondary CPUs.
 	 */
 	verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU);
-
-	verify_local_elf_hwcaps(arm64_elf_hwcaps);
-
-	if (system_supports_32bit_el0())
-		verify_local_elf_hwcaps(compat_elf_hwcaps);
+	verify_local_elf_hwcaps();
 
 	if (system_supports_sve())
 		verify_sve_features();
@@ -2812,6 +2897,34 @@ void __init setup_cpu_features(void)
 			ARCH_DMA_MINALIGN);
 }
 
+static int enable_mismatched_32bit_el0(unsigned int cpu)
+{
+	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
+	bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
+
+	if (cpu_32bit) {
+		cpumask_set_cpu(cpu, cpu_32bit_el0_mask);
+		static_branch_enable_cpuslocked(&arm64_mismatched_32bit_el0);
+		setup_elf_hwcaps(compat_elf_hwcaps);
+	}
+
+	return 0;
+}
+
+static int __init init_32bit_el0_mask(void)
+{
+	if (!allow_mismatched_32bit_el0)
+		return 0;
+
+	if (!zalloc_cpumask_var(&cpu_32bit_el0_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				 "arm64/mismatched_32bit_el0:online",
+				 enable_mismatched_32bit_el0, NULL);
+}
+subsys_initcall_sync(init_32bit_el0_mask);
+
 static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap)
 {
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
@@ -2905,8 +3018,8 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn)
 }
 
 static struct undef_hook mrs_hook = {
-	.instr_mask = 0xfff00000,
-	.instr_val  = 0xd5300000,
+	.instr_mask = 0xffff0000,
+	.instr_val  = 0xd5380000,
 	.pstate_mask = PSR_AA32_MODE_MASK,
 	.pstate_val = PSR_MODE_EL0t,
 	.fn = emulate_mrs,
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 51fcf99d5351..87731fea5e41 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -246,7 +246,7 @@ static struct kobj_type cpuregs_kobj_type = {
 		struct cpuinfo_arm64 *info = kobj_to_cpuinfo(kobj);		\
 										\
 		if (info->reg_midr)						\
-			return sprintf(buf, "0x%016x\n", info->reg_##_field);	\
+			return sprintf(buf, "0x%016llx\n", info->reg_##_field);	\
 		else								\
 			return 0;						\
 	}									\
@@ -344,6 +344,32 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
 	pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
 }
 
+static void __cpuinfo_store_cpu_32bit(struct cpuinfo_32bit *info)
+{
+	info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
+	info->reg_id_dfr1 = read_cpuid(ID_DFR1_EL1);
+	info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
+	info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
+	info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
+	info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
+	info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
+	info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
+	info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1);
+	info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
+	info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
+	info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
+	info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
+	info->reg_id_mmfr4 = read_cpuid(ID_MMFR4_EL1);
+	info->reg_id_mmfr5 = read_cpuid(ID_MMFR5_EL1);
+	info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
+	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
+	info->reg_id_pfr2 = read_cpuid(ID_PFR2_EL1);
+
+	info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
+	info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
+	info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
+}
+
 static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 {
 	info->reg_cntfrq = arch_timer_get_cntfrq();
@@ -371,31 +397,11 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 	info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
 
-	/* Update the 32bit ID registers only if AArch32 is implemented */
-	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
-		info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
-		info->reg_id_dfr1 = read_cpuid(ID_DFR1_EL1);
-		info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
-		info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
-		info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
-		info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
-		info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
-		info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
-		info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1);
-		info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
-		info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
-		info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
-		info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
-		info->reg_id_mmfr4 = read_cpuid(ID_MMFR4_EL1);
-		info->reg_id_mmfr5 = read_cpuid(ID_MMFR5_EL1);
-		info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
-		info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
-		info->reg_id_pfr2 = read_cpuid(ID_PFR2_EL1);
-
-		info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
-		info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
-		info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
-	}
+	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
+		info->reg_gmid = read_cpuid(GMID_EL1);
+
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
+		__cpuinfo_store_cpu_32bit(&info->aarch32);
 
 	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
 	    id_aa64pfr0_sve(info->reg_id_aa64pfr0))
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 8928fba54e4b..80bed2659922 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -532,6 +532,15 @@ static void erratum_1418040_thread_switch(struct task_struct *prev,
 	write_sysreg(val, cntkctl_el1);
 }
 
+static void compat_thread_switch(struct task_struct *next)
+{
+	if (!is_compat_thread(task_thread_info(next)))
+		return;
+
+	if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		set_tsk_thread_flag(next, TIF_NOTIFY_RESUME);
+}
+
 static void update_sctlr_el1(u64 sctlr)
 {
 	/*
@@ -573,6 +582,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	ssbs_thread_switch(next);
 	erratum_1418040_thread_switch(prev, next);
 	ptrauth_thread_switch_user(next);
+	compat_thread_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -638,8 +648,15 @@ unsigned long arch_align_stack(unsigned long sp)
  */
 void arch_setup_new_exec(void)
 {
-	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+	unsigned long mmflags = 0;
+
+	if (is_compat_task()) {
+		mmflags = MMCF_AARCH32;
+		if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+			set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+	}
 
+	current->mm->context.flags = mmflags;
 	ptrauth_thread_init_user();
 	mte_thread_init_user();
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 6237486ff6bb..f8192f4ae0b8 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -911,6 +911,19 @@ static void do_signal(struct pt_regs *regs)
 	restore_saved_sigmask();
 }
 
+static bool cpu_affinity_invalid(struct pt_regs *regs)
+{
+	if (!compat_user_mode(regs))
+		return false;
+
+	/*
+	 * We're preemptible, but a reschedule will cause us to check the
+	 * affinity again.
+	 */
+	return !cpumask_test_cpu(raw_smp_processor_id(),
+				 system_32bit_el0_cpumask());
+}
+
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
@@ -938,6 +951,19 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
+
+				/*
+				 * If we reschedule after checking the affinity
+				 * then we must ensure that TIF_NOTIFY_RESUME
+				 * is set so that we check the affinity again.
+				 * Since tracehook_notify_resume() clears the
+				 * flag, ensure that the compiler doesn't move
+				 * it after the affinity check.
+				 */
+				barrier();
+
+				if (cpu_affinity_invalid(regs))
+					force_sig(SIGKILL);
 			}
 
 			if (thread_flags & _TIF_FOREIGN_FPSTATE)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c1953f65ca0e..dc2bc5589493 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -692,6 +692,15 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
+{
+	if (likely(!vcpu_mode_is_32bit(vcpu)))
+		return false;
+
+	return !system_supports_32bit_el0() ||
+		static_branch_unlikely(&arm64_mismatched_32bit_el0);
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -875,7 +884,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * with the asymmetric AArch32 case), return to userspace with
 		 * a fatal error.
 		 */
-		if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) {
+		if (vcpu_mode_is_bad_32bit(vcpu)) {
 			/*
 			 * As we have caught the guest red-handed, decide that
 			 * it isn't fit for purpose anymore by making the vcpu
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 21fbdda7086e..49305c2e6dfd 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -3,7 +3,8 @@
 # Internal CPU capabilities constants, keep this list sorted
 
 BTI
-HAS_32BIT_EL0
+# Unreliable: use system_supports_32bit_el0() instead.
+HAS_32BIT_EL0_DO_NOT_USE
 HAS_32BIT_EL1
 HAS_ADDRESS_AUTH
 HAS_ADDRESS_AUTH_ARCH