21 files changed, 249 insertions, 100 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index a100483b47c4..46ec402e97ed 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/irq_work.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/smp.h>
@@ -269,6 +270,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 int apei_claim_sea(struct pt_regs *regs)
 {
 	int err = -ENOENT;
+	bool return_to_irqs_enabled;
 	unsigned long current_flags;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
@@ -276,6 +278,12 @@ int apei_claim_sea(struct pt_regs *regs)
 
 	current_flags = local_daif_save_flags();
 
+	/* current_flags isn't useful here as daif doesn't tell us about pNMI */
+	return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags());
+
+	if (regs)
+		return_to_irqs_enabled = interrupts_enabled(regs);
+
 	/*
 	 * SEA can interrupt SError, mask it and describe this as an NMI so
 	 * that APEI defers the handling.
@@ -284,6 +292,23 @@ int apei_claim_sea(struct pt_regs *regs)
 	nmi_enter();
 	err = ghes_notify_sea();
 	nmi_exit();
+
+	/*
+	 * APEI NMI-like notifications are deferred to irq_work. Unless
+	 * we interrupted irqs-masked code, we can do that now.
+	 */
+	if (!err) {
+		if (return_to_irqs_enabled) {
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+			__irq_enter();
+			irq_work_run();
+			__irq_exit();
+		} else {
+			pr_warn_ratelimited("APEI work queued but not completed");
+			err = -EINPROGRESS;
+		}
+	}
+
 	local_daif_restore(current_flags);
 
 	return err;
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef1b1e7..73039949b5ce 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature)
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0b2830379fe0..1e16c4e00e77 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -492,6 +492,12 @@ out_printmsg:
 	return required;
 }
 
+static void cpu_enable_ssbd_mitigation(const struct arm64_cpu_capabilities *cap)
+{
+	if (ssbd_state != ARM64_SSBD_FORCE_DISABLE)
+		cap->matches(cap, SCOPE_LOCAL_CPU);
+}
+
 /* known invulnerable cores */
 static const struct midr_range arm64_ssb_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
@@ -635,6 +641,12 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 	return (need_wa > 0);
 }
 
+static void
+cpu_enable_branch_predictor_hardening(const struct arm64_cpu_capabilities *cap)
+{
+	cap->matches(cap, SCOPE_LOCAL_CPU);
+}
+
 static const __maybe_unused struct midr_range tx2_family_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
 	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
@@ -894,9 +906,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	},
 #endif
 	{
+		.desc = "Branch predictor hardening",
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = check_branch_predictor,
+		.cpu_enable = cpu_enable_branch_predictor_hardening,
 	},
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 	{
@@ -910,6 +924,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_SSBD,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_ssbd_mitigation,
+		.cpu_enable = cpu_enable_ssbd_mitigation,
 		.midr_range_list = arm64_ssb_cpus,
 	},
 #ifdef CONFIG_ARM64_ERRATUM_1418040
@@ -917,6 +932,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.desc = "ARM erratum 1418040",
 		.capability = ARM64_WORKAROUND_1418040,
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
+		/*
+		 * We need to allow affected CPUs to come in late, but
+		 * also need the non-affected CPUs to be able to come
+		 * in at any point in time. Wonderful.
+		 */
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1165522
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 933f7a2eab59..5d790d45e737 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -160,11 +160,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
-	/* Linux doesn't care about the EL3 */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
 	ARM64_FTR_END,
 };
 
@@ -320,7 +319,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
+	/* [31:28] TraceFilt */
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),
@@ -737,9 +736,6 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu,
 				      info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2);
 
-	/*
-	 * EL3 is not our concern.
-	 */
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
 				      info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 48222a4760c2..d64a3c1e1b6b 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -393,17 +396,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 1765e5284994..04b982a2799e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -338,7 +338,7 @@ static unsigned int find_supported_vector_length(unsigned int vl)
 	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
-#ifdef CONFIG_SYSCTL
+#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
 
 static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 				  void __user *buffer, size_t *lenp,
@@ -384,9 +384,9 @@ static int __init sve_sysctl_init(void)
 	return 0;
 }
 
-#else /* ! CONFIG_SYSCTL */
+#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 static int __init sve_sysctl_init(void) { return 0; }
-#endif /* ! CONFIG_SYSCTL */
+#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 989b1944cb71..bdb5ec341900 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -393,13 +393,19 @@ __create_page_tables:
 
 	/*
 	 * Since the page tables have been populated with non-cacheable
-	 * accesses (MMU disabled), invalidate the idmap and swapper page
-	 * tables again to remove any speculatively loaded cache lines.
+	 * accesses (MMU disabled), invalidate those tables again to
+	 * remove any speculatively loaded cache lines.
 	 */
+	dmb	sy
+
 	adrp	x0, idmap_pg_dir
+	adrp	x1, idmap_pg_end
+	sub	x1, x1, x0
+	bl	__inval_dcache_area
+
+	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
 	sub	x1, x1, x0
-	dmb	sy
 	bl	__inval_dcache_area
 
 	ret	x28
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 38ee1514cd9c..b4a160795824 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 		return 0;
 }
 
+static int watchpoint_report(struct perf_event *wp, unsigned long addr,
+			     struct pt_regs *regs)
+{
+	int step = is_default_overflow_handler(wp);
+	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
+
+	info->trigger = addr;
+
+	/*
+	 * If we triggered a user watchpoint from a uaccess routine, then
+	 * handle the stepping ourselves since userspace really can't help
+	 * us with this.
+	 */
+	if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0)
+		step = 1;
+	else
+		perf_bp_event(wp, regs);
+
+	return step;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
-	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
@@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		if (dist != 0)
 			continue;
 
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
-
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
+		step = watchpoint_report(wp, addr, regs);
 	}
-	if (min_dist > 0 && min_dist != -1) {
-		/* No exact match found. */
-		wp = slots[closest_match];
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
 
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
-	}
+	/* No exact match found? */
+	if (min_dist > 0 && min_dist != -1)
+		step = watchpoint_report(slots[closest_match], addr, regs);
+
 	rcu_read_unlock();
 
 	if (!step)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index d801a7094076..53bcf5386907 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -21,6 +21,7 @@
 #include <asm/fixmap.h>
 #include <asm/insn.h>
 #include <asm/kprobes.h>
+#include <asm/sections.h>
 
 #define AARCH64_INSN_SF_BIT	BIT(31)
 #define AARCH64_INSN_N_BIT	BIT(22)
@@ -78,16 +79,29 @@ bool aarch64_insn_is_branch_imm(u32 insn)
 
 static DEFINE_RAW_SPINLOCK(patch_lock);
 
+static bool is_exit_text(unsigned long addr)
+{
+	/* discarded with init text/data */
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (unsigned long)__exittext_begin &&
+		addr < (unsigned long)__exittext_end;
+}
+
+static bool is_image_text(unsigned long addr)
+{
+	return core_kernel_text(addr) || is_exit_text(addr);
+}
+
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
 	unsigned long uintaddr = (uintptr_t) addr;
-	bool module = !core_kernel_text(uintaddr);
+	bool image = is_image_text(uintaddr);
 	struct page *page;
 
-	if (module && IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
-		page = vmalloc_to_page(addr);
-	else if (!module)
+	if (image)
 		page = phys_to_page(__pa_symbol(addr));
+	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		page = vmalloc_to_page(addr);
 	else
 		return addr;
 
@@ -1508,16 +1522,10 @@ static u32 aarch64_encode_immediate(u64 imm,
 				    u32 insn)
 {
 	unsigned int immr, imms, n, ones, ror, esz, tmp;
-	u64 mask = ~0UL;
-
-	/* Can't encode full zeroes or full ones */
-	if (!imm || !~imm)
-		return AARCH64_BREAK_FAULT;
+	u64 mask;
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		if (upper_32_bits(imm))
-			return AARCH64_BREAK_FAULT;
 		esz = 32;
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
@@ -1529,6 +1537,12 @@ static u32 aarch64_encode_immediate(u64 imm,
 		return AARCH64_BREAK_FAULT;
 	}
 
+	mask = GENMASK(esz - 1, 0);
+
+	/* Can't encode full zeroes, full ones, or value wider than the mask */
+	if (!imm || imm == mask || imm & ~mask)
+		return AARCH64_BREAK_FAULT;
+
 	/*
 	 * Inverse of Replicate(). Try to spot a repeating pattern
 	 * with a pow2 stride.
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index b182442b87a3..426018ebb700 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -270,8 +270,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			mod->arch.core.plt_shndx = i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
 			mod->arch.init.plt_shndx = i;
-		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
-			 !strcmp(secstrings + sechdrs[i].sh_name,
+		else if (!strcmp(secstrings + sechdrs[i].sh_name,
 				 ".text.ftrace_trampoline"))
 			tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index a0b4f1bca491..19128d994ee9 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -155,7 +155,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
 
-	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
 }
 
 #define ARMV8_EVENT_ATTR(name, config) \
@@ -303,10 +303,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
 		return attr->mode;
 
-	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
-	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
-	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
-		return attr->mode;
+	if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+		u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+		if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+		    test_bit(id, cpu_pmu->pmceid_ext_bitmap))
+			return attr->mode;
+	}
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 0bbac612146e..666b225aeb3a 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index fab013c5ee8c..10190c4b16dc 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -499,6 +499,39 @@ static void entry_task_switch(struct task_struct *next)
 }
 
 /*
+ * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT.
+ * Assuming the virtual counter is enabled at the beginning of times:
+ *
+ * - disable access when switching from a 64bit task to a 32bit task
+ * - enable access when switching from a 32bit task to a 64bit task
+ */
+static void erratum_1418040_thread_switch(struct task_struct *prev,
+					  struct task_struct *next)
+{
+	bool prev32, next32;
+	u64 val;
+
+	if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) &&
+	      cpus_have_const_cap(ARM64_WORKAROUND_1418040)))
+		return;
+
+	prev32 = is_compat_thread(task_thread_info(prev));
+	next32 = is_compat_thread(task_thread_info(next));
+
+	if (prev32 == next32)
+		return;
+
+	val = read_sysreg(cntkctl_el1);
+
+	if (!next32)
+		val |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+	else
+		val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN;
+
+	write_sysreg(val, cntkctl_el1);
+}
+
+/*
  * Thread switching.
  */
 __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
@@ -514,6 +547,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	uao_thread_switch(next);
 	ptrauth_thread_switch(next);
 	ssbs_thread_switch(next);
+	erratum_1418040_thread_switch(prev, next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 8d2d9d5b418f..30b877f8b85e 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1819,12 +1819,23 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1852,12 +1863,14 @@ int syscall_trace_enter(struct pt_regs *regs)
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1935,8 +1948,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 56f664561754..d98987b82874 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -85,7 +85,7 @@ u64 __cacheline_aligned boot_args[4];
 void __init smp_setup_processor_id(void)
 {
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
-	cpu_logical_map(0) = mpidr;
+	set_cpu_logical_map(0, mpidr);
 
 	/*
 	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
@@ -276,6 +276,12 @@ arch_initcall(reserve_memblock_reserved_regions);
 
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
+u64 cpu_logical_map(int cpu)
+{
+	return __cpu_logical_map[cpu];
+}
+EXPORT_SYMBOL_GPL(cpu_logical_map);
+
 void __init setup_arch(char **cmdline_p)
 {
 	init_mm.start_code = (unsigned long) _text;
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index dd2cdc0d5be2..ddb757b2c3e5 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -782,7 +782,6 @@ static void setup_restart_syscall(struct pt_regs *regs)
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -806,14 +805,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 993a4aedfd37..102dc3e7f2e1 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -549,7 +549,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 		return;
 
 	/* map the logical cpu id to cpu MPIDR */
-	cpu_logical_map(cpu_count) = hwid;
+	set_cpu_logical_map(cpu_count, hwid);
 
 	cpu_madt_gicc[cpu_count] = *processor;
 
@@ -663,7 +663,7 @@ static void __init of_parse_and_init_cpus(void)
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
-		cpu_logical_map(cpu_count) = hwid;
+		set_cpu_logical_map(cpu_count, hwid);
 
 		early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
 next:
@@ -704,7 +704,7 @@ void __init smp_init_cpus(void)
 	for (i = 1; i < nr_cpu_ids; i++) {
 		if (cpu_logical_map(i) != INVALID_HWID) {
 			if (smp_cpu_setup(i))
-				cpu_logical_map(i) = INVALID_HWID;
+				set_cpu_logical_map(i, INVALID_HWID);
 		}
 	}
 }
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 871c739f060a..1457a0ba83db 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 76b327f88fbb..40dffe60b845 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -190,7 +190,7 @@ quiet_cmd_vdsosym = VDSOSYM $@
       cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
 
 # Install commands for the unstripped file
-quiet_cmd_vdso_install = INSTALL $@
+quiet_cmd_vdso_install = INSTALL32 $@
       cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so
 
 vdso.so: $(obj)/vdso.so.dbg
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index aa76f7259668..0bab37b1acbe 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -24,6 +24,13 @@ ENTRY(_text)
 
 jiffies = jiffies_64;
 
+
+#define HYPERVISOR_EXTABLE					\
+	. = ALIGN(SZ_8);					\
+	__start___kvm_ex_table = .;				\
+	*(__kvm_ex_table)					\
+	__stop___kvm_ex_table = .;
+
 #define HYPERVISOR_TEXT					\
 	/*						\
 	 * Align to 4 KB so that			\
@@ -39,6 +46,7 @@ jiffies = jiffies_64;
 	__hyp_idmap_text_end = .;			\
 	__hyp_text_start = .;				\
 	*(.hyp.text)					\
+	HYPERVISOR_EXTABLE				\
 	__hyp_text_end = .;
 
 #define IDMAP_TEXT					\
@@ -142,6 +150,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	idmap_pg_dir = .;
 	. += IDMAP_DIR_SIZE;
+	idmap_pg_end = .;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	tramp_pg_dir = .;
@@ -161,9 +170,12 @@ SECTIONS
 	__inittext_begin = .;
 
 	INIT_TEXT_SECTION(8)
+
+	__exittext_begin = .;
 	.exit.text : {
 		ARM_EXIT_KEEP(EXIT_TEXT)
 	}
+	__exittext_end = .;
 
 	. = ALIGN(4);
 	.altinstructions : {
@@ -171,9 +183,6 @@ SECTIONS
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(PAGE_SIZE);
 	__inittext_end = .;