Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The highlights this time are support for dynamically enabling and
  disabling Clang's Shadow Call Stack at boot and a long-awaited
  optimisation to the way in which we handle the SVE register state on
  system call entry to avoid taking unnecessary traps from userspace.

  Summary:

  ACPI:
   - Enable FPDT support for boot-time profiling
   - Fix CPU PMU probing to work better with PREEMPT_RT
   - Update SMMUv3 MSI DeviceID parsing to latest IORT spec
   - APMT support for probing Arm CoreSight PMU devices

  CPU features:
   - Advertise new SVE instructions (v2.1)
   - Advertise range prefetch instruction
   - Advertise CSSC ("Common Short Sequence Compression") scalar
     instructions, adding things like min, max, abs, popcount
   - Enable DIT (Data Independent Timing) when running in the kernel
   - More conversion of system register fields over to the generated
     header

  CPU misfeatures:
   - Workaround for Cortex-A715 erratum #2645198

  Dynamic SCS:
   - Support for dynamic shadow call stacks to allow switching at
     runtime between Clang's SCS implementation and the CPU's pointer
     authentication feature when it is supported (complete with scary
     DWARF parser!)

  Tracing and debug:
   - Remove static ftrace in favour of, err, dynamic ftrace!
   - Seperate 'struct ftrace_regs' from 'struct pt_regs' in core ftrace
     and existing arch code
   - Introduce and implement FTRACE_WITH_ARGS on arm64 to replace the
     old FTRACE_WITH_REGS
   - Extend 'crashkernel=' parameter with default value and fallback to
     placement above 4G physical if initial (low) allocation fails

  SVE:
   - Optimisation to avoid disabling SVE unconditionally on syscall
     entry and just zeroing the non-shared state on return instead

  Exceptions:
   - Rework of undefined instruction handling to avoid serialisation on
     global lock (this includes emulation of user accesses to the ID
     registers)

  Perf and PMU:
   - Support for TLP filters in Hisilicon's PCIe PMU device
   - Support for the DDR PMU present in Amlogic Meson G12 SoCs
   - Support for the terribly-named "CoreSight PMU" architecture from
     Arm (and Nvidia's implementation of said architecture)

  Misc:
   - Tighten up our boot protocol for systems with memory above 52 bits
     physical
   - Const-ify static keys to satisty jump label asm constraints
   - Trivial FFA driver cleanups in preparation for v1.1 support
   - Export the kernel_neon_* APIs as GPL symbols
   - Harden our instruction generation routines against instrumentation
   - A bunch of robustness improvements to our arch-specific selftests
   - Minor cleanups and fixes all over (kbuild, kprobes, kfence, PMU, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (151 commits)
  arm64: kprobes: Return DBG_HOOK_ERROR if kprobes can not handle a BRK
  arm64: kprobes: Let arch do_page_fault() fix up page fault in user handler
  arm64: Prohibit instrumentation on arch_stack_walk()
  arm64:uprobe fix the uprobe SWBP_INSN in big-endian
  arm64: alternatives: add __init/__initconst to some functions/variables
  arm_pmu: Drop redundant armpmu->map_event() in armpmu_event_init()
  kselftest/arm64: Allow epoll_wait() to return more than one result
  kselftest/arm64: Don't drain output while spawning children
  kselftest/arm64: Hold fp-stress children until they're all spawned
  arm64/sysreg: Remove duplicate definitions from asm/sysreg.h
  arm64/sysreg: Convert ID_DFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_DFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_AFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_MMFR5_EL1 to automatic generation
  arm64/sysreg: Convert MVFR2_EL1 to automatic generation
  arm64/sysreg: Convert MVFR1_EL1 to automatic generation
  arm64/sysreg: Convert MVFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR2_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR0_EL1 to automatic generation
  ...

32 files changed, 1059 insertions, 792 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2f361a883d8c..8dd925f4a4c6 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -80,6 +80,8 @@ obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
+obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
+CFLAGS_patch-scs.o			+= -mbranch-protection=none
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 91263d09ea65..d32d4ed5519b 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -196,7 +196,7 @@ static void __apply_alternatives(const struct alt_region *region,
 	}
 }
 
-void apply_alternatives_vdso(void)
+static void __init apply_alternatives_vdso(void)
 {
 	struct alt_region region;
 	const struct elf64_hdr *hdr;
@@ -220,7 +220,7 @@ void apply_alternatives_vdso(void)
 	__apply_alternatives(&region, false, &all_capabilities[0]);
 }
 
-static const struct alt_region kernel_alternatives = {
+static const struct alt_region kernel_alternatives __initconst = {
 	.begin	= (struct alt_instr *)__alt_instructions,
 	.end	= (struct alt_instr *)__alt_instructions_end,
 };
@@ -229,7 +229,7 @@ static const struct alt_region kernel_alternatives = {
  * We might be patching the stop_machine state machine, so implement a
  * really simple polling protocol here.
  */
-static int __apply_alternatives_multi_stop(void *unused)
+static int __init __apply_alternatives_multi_stop(void *unused)
 {
 	/* We always have a CPU 0 at this point (__init) */
 	if (smp_processor_id()) {
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index fb0e7c7b2e20..8a9052cf3013 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -17,7 +17,6 @@
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/traps.h>
-#include <asm/kprobes.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace-events-emulation.h"
@@ -39,226 +38,46 @@ enum insn_emulation_mode {
 enum legacy_insn_status {
 	INSN_DEPRECATED,
 	INSN_OBSOLETE,
-};
-
-struct insn_emulation_ops {
-	const char		*name;
-	enum legacy_insn_status	status;
-	struct undef_hook	*hooks;
-	int			(*set_hw_mode)(bool enable);
+	INSN_UNAVAILABLE,
 };
 
 struct insn_emulation {
-	struct list_head node;
-	struct insn_emulation_ops *ops;
+	const char			*name;
+	enum legacy_insn_status		status;
+	bool				(*try_emulate)(struct pt_regs *regs,
+						       u32 insn);
+	int				(*set_hw_mode)(bool enable);
+
 	int current_mode;
 	int min;
 	int max;
-};
-
-static LIST_HEAD(insn_emulation);
-static int nr_insn_emulated __initdata;
-static DEFINE_RAW_SPINLOCK(insn_emulation_lock);
-static DEFINE_MUTEX(insn_emulation_mutex);
-
-static void register_emulation_hooks(struct insn_emulation_ops *ops)
-{
-	struct undef_hook *hook;
-
-	BUG_ON(!ops->hooks);
-
-	for (hook = ops->hooks; hook->instr_mask; hook++)
-		register_undef_hook(hook);
-
-	pr_notice("Registered %s emulation handler\n", ops->name);
-}
-
-static void remove_emulation_hooks(struct insn_emulation_ops *ops)
-{
-	struct undef_hook *hook;
-
-	BUG_ON(!ops->hooks);
-
-	for (hook = ops->hooks; hook->instr_mask; hook++)
-		unregister_undef_hook(hook);
-
-	pr_notice("Removed %s emulation handler\n", ops->name);
-}
-
-static void enable_insn_hw_mode(void *data)
-{
-	struct insn_emulation *insn = (struct insn_emulation *)data;
-	if (insn->ops->set_hw_mode)
-		insn->ops->set_hw_mode(true);
-}
-
-static void disable_insn_hw_mode(void *data)
-{
-	struct insn_emulation *insn = (struct insn_emulation *)data;
-	if (insn->ops->set_hw_mode)
-		insn->ops->set_hw_mode(false);
-}
-
-/* Run set_hw_mode(mode) on all active CPUs */
-static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
-{
-	if (!insn->ops->set_hw_mode)
-		return -EINVAL;
-	if (enable)
-		on_each_cpu(enable_insn_hw_mode, (void *)insn, true);
-	else
-		on_each_cpu(disable_insn_hw_mode, (void *)insn, true);
-	return 0;
-}
-
-/*
- * Run set_hw_mode for all insns on a starting CPU.
- * Returns:
- *  0 		- If all the hooks ran successfully.
- * -EINVAL	- At least one hook is not supported by the CPU.
- */
-static int run_all_insn_set_hw_mode(unsigned int cpu)
-{
-	int rc = 0;
-	unsigned long flags;
-	struct insn_emulation *insn;
-
-	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
-	list_for_each_entry(insn, &insn_emulation, node) {
-		bool enable = (insn->current_mode == INSN_HW);
-		if (insn->ops->set_hw_mode && insn->ops->set_hw_mode(enable)) {
-			pr_warn("CPU[%u] cannot support the emulation of %s",
-				cpu, insn->ops->name);
-			rc = -EINVAL;
-		}
-	}
-	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
-	return rc;
-}
-
-static int update_insn_emulation_mode(struct insn_emulation *insn,
-				       enum insn_emulation_mode prev)
-{
-	int ret = 0;
-
-	switch (prev) {
-	case INSN_UNDEF: /* Nothing to be done */
-		break;
-	case INSN_EMULATE:
-		remove_emulation_hooks(insn->ops);
-		break;
-	case INSN_HW:
-		if (!run_all_cpu_set_hw_mode(insn, false))
-			pr_notice("Disabled %s support\n", insn->ops->name);
-		break;
-	}
-
-	switch (insn->current_mode) {
-	case INSN_UNDEF:
-		break;
-	case INSN_EMULATE:
-		register_emulation_hooks(insn->ops);
-		break;
-	case INSN_HW:
-		ret = run_all_cpu_set_hw_mode(insn, true);
-		if (!ret)
-			pr_notice("Enabled %s support\n", insn->ops->name);
-		break;
-	}
 
-	return ret;
-}
-
-static void __init register_insn_emulation(struct insn_emulation_ops *ops)
-{
-	unsigned long flags;
-	struct insn_emulation *insn;
-
-	insn = kzalloc(sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return;
-
-	insn->ops = ops;
-	insn->min = INSN_UNDEF;
-
-	switch (ops->status) {
-	case INSN_DEPRECATED:
-		insn->current_mode = INSN_EMULATE;
-		/* Disable the HW mode if it was turned on at early boot time */
-		run_all_cpu_set_hw_mode(insn, false);
-		insn->max = INSN_HW;
-		break;
-	case INSN_OBSOLETE:
-		insn->current_mode = INSN_UNDEF;
-		insn->max = INSN_EMULATE;
-		break;
-	}
-
-	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
-	list_add(&insn->node, &insn_emulation);
-	nr_insn_emulated++;
-	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
-
-	/* Register any handlers if required */
-	update_insn_emulation_mode(insn, INSN_UNDEF);
-}
-
-static int emulation_proc_handler(struct ctl_table *table, int write,
-				  void *buffer, size_t *lenp,
-				  loff_t *ppos)
-{
-	int ret = 0;
-	struct insn_emulation *insn = container_of(table->data, struct insn_emulation, current_mode);
-	enum insn_emulation_mode prev_mode = insn->current_mode;
-
-	mutex_lock(&insn_emulation_mutex);
-	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	/*
+	 * sysctl for this emulation + a sentinal entry.
+	 */
+	struct ctl_table sysctl[2];
+};
 
-	if (ret || !write || prev_mode == insn->current_mode)
-		goto ret;
+#define ARM_OPCODE_CONDTEST_FAIL   0
+#define ARM_OPCODE_CONDTEST_PASS   1
+#define ARM_OPCODE_CONDTEST_UNCOND 2
 
-	ret = update_insn_emulation_mode(insn, prev_mode);
-	if (ret) {
-		/* Mode change failed, revert to previous mode. */
-		insn->current_mode = prev_mode;
-		update_insn_emulation_mode(insn, INSN_UNDEF);
-	}
-ret:
-	mutex_unlock(&insn_emulation_mutex);
-	return ret;
-}
+#define	ARM_OPCODE_CONDITION_UNCOND	0xf
 
-static void __init register_insn_emulation_sysctl(void)
+static unsigned int __maybe_unused aarch32_check_condition(u32 opcode, u32 psr)
 {
-	unsigned long flags;
-	int i = 0;
-	struct insn_emulation *insn;
-	struct ctl_table *insns_sysctl, *sysctl;
-
-	insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl),
-			       GFP_KERNEL);
-	if (!insns_sysctl)
-		return;
-
-	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
-	list_for_each_entry(insn, &insn_emulation, node) {
-		sysctl = &insns_sysctl[i];
-
-		sysctl->mode = 0644;
-		sysctl->maxlen = sizeof(int);
+	u32 cc_bits  = opcode >> 28;
 
-		sysctl->procname = insn->ops->name;
-		sysctl->data = &insn->current_mode;
-		sysctl->extra1 = &insn->min;
-		sysctl->extra2 = &insn->max;
-		sysctl->proc_handler = emulation_proc_handler;
-		i++;
+	if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
+		if ((*aarch32_opcode_cond_checks[cc_bits])(psr))
+			return ARM_OPCODE_CONDTEST_PASS;
+		else
+			return ARM_OPCODE_CONDTEST_FAIL;
 	}
-	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
-
-	register_sysctl("abi", insns_sysctl);
+	return ARM_OPCODE_CONDTEST_UNCOND;
 }
 
+#ifdef CONFIG_SWP_EMULATION
 /*
  *  Implement emulation of the SWP/SWPB instructions using load-exclusive and
  *  store-exclusive.
@@ -339,25 +158,6 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 	return res;
 }
 
-#define ARM_OPCODE_CONDTEST_FAIL   0
-#define ARM_OPCODE_CONDTEST_PASS   1
-#define ARM_OPCODE_CONDTEST_UNCOND 2
-
-#define	ARM_OPCODE_CONDITION_UNCOND	0xf
-
-static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr)
-{
-	u32 cc_bits  = opcode >> 28;
-
-	if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
-		if ((*aarch32_opcode_cond_checks[cc_bits])(psr))
-			return ARM_OPCODE_CONDTEST_PASS;
-		else
-			return ARM_OPCODE_CONDTEST_FAIL;
-	}
-	return ARM_OPCODE_CONDTEST_UNCOND;
-}
-
 /*
  * swp_handler logs the id of calling process, dissects the instruction, sanity
  * checks the memory location, calls emulate_swpX for the actual operation and
@@ -430,28 +230,27 @@ fault:
 	return 0;
 }
 
-/*
- * Only emulate SWP/SWPB executed in ARM state/User mode.
- * The kernel must be SWP free and SWP{B} does not exist in Thumb.
- */
-static struct undef_hook swp_hooks[] = {
-	{
-		.instr_mask	= 0x0fb00ff0,
-		.instr_val	= 0x01000090,
-		.pstate_mask	= PSR_AA32_MODE_MASK,
-		.pstate_val	= PSR_AA32_MODE_USR,
-		.fn		= swp_handler
-	},
-	{ }
-};
+static bool try_emulate_swp(struct pt_regs *regs, u32 insn)
+{
+	/* SWP{B} only exists in ARM state and does not exist in Thumb */
+	if (!compat_user_mode(regs) || compat_thumb_mode(regs))
+		return false;
 
-static struct insn_emulation_ops swp_ops = {
+	if ((insn & 0x0fb00ff0) != 0x01000090)
+		return false;
+
+	return swp_handler(regs, insn) == 0;
+}
+
+static struct insn_emulation insn_swp = {
 	.name = "swp",
 	.status = INSN_OBSOLETE,
-	.hooks = swp_hooks,
+	.try_emulate = try_emulate_swp,
 	.set_hw_mode = NULL,
 };
+#endif /* CONFIG_SWP_EMULATION */
 
+#ifdef CONFIG_CP15_BARRIER_EMULATION
 static int cp15barrier_handler(struct pt_regs *regs, u32 instr)
 {
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
@@ -514,31 +313,29 @@ static int cp15_barrier_set_hw_mode(bool enable)
 	return 0;
 }
 
-static struct undef_hook cp15_barrier_hooks[] = {
-	{
-		.instr_mask	= 0x0fff0fdf,
-		.instr_val	= 0x0e070f9a,
-		.pstate_mask	= PSR_AA32_MODE_MASK,
-		.pstate_val	= PSR_AA32_MODE_USR,
-		.fn		= cp15barrier_handler,
-	},
-	{
-		.instr_mask	= 0x0fff0fff,
-		.instr_val	= 0x0e070f95,
-		.pstate_mask	= PSR_AA32_MODE_MASK,
-		.pstate_val	= PSR_AA32_MODE_USR,
-		.fn		= cp15barrier_handler,
-	},
-	{ }
-};
+static bool try_emulate_cp15_barrier(struct pt_regs *regs, u32 insn)
+{
+	if (!compat_user_mode(regs) || compat_thumb_mode(regs))
+		return false;
+
+	if ((insn & 0x0fff0fdf) == 0x0e070f9a)
+		return cp15barrier_handler(regs, insn) == 0;
+
+	if ((insn & 0x0fff0fff) == 0x0e070f95)
+		return cp15barrier_handler(regs, insn) == 0;
 
-static struct insn_emulation_ops cp15_barrier_ops = {
+	return false;
+}
+
+static struct insn_emulation insn_cp15_barrier = {
 	.name = "cp15_barrier",
 	.status = INSN_DEPRECATED,
-	.hooks = cp15_barrier_hooks,
+	.try_emulate = try_emulate_cp15_barrier,
 	.set_hw_mode = cp15_barrier_set_hw_mode,
 };
+#endif /* CONFIG_CP15_BARRIER_EMULATION */
 
+#ifdef CONFIG_SETEND_EMULATION
 static int setend_set_hw_mode(bool enable)
 {
 	if (!cpu_supports_mixed_endian_el0())
@@ -586,31 +383,218 @@ static int t16_setend_handler(struct pt_regs *regs, u32 instr)
 	return rc;
 }
 
-static struct undef_hook setend_hooks[] = {
-	{
-		.instr_mask	= 0xfffffdff,
-		.instr_val	= 0xf1010000,
-		.pstate_mask	= PSR_AA32_MODE_MASK,
-		.pstate_val	= PSR_AA32_MODE_USR,
-		.fn		= a32_setend_handler,
-	},
-	{
-		/* Thumb mode */
-		.instr_mask	= 0xfffffff7,
-		.instr_val	= 0x0000b650,
-		.pstate_mask	= (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
-		.pstate_val	= (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),
-		.fn		= t16_setend_handler,
-	},
-	{}
-};
+static bool try_emulate_setend(struct pt_regs *regs, u32 insn)
+{
+	if (compat_thumb_mode(regs) &&
+	    (insn & 0xfffffff7) == 0x0000b650)
+		return t16_setend_handler(regs, insn) == 0;
+
+	if (compat_user_mode(regs) &&
+	    (insn & 0xfffffdff) == 0xf1010000)
+		return a32_setend_handler(regs, insn) == 0;
 
-static struct insn_emulation_ops setend_ops = {
+	return false;
+}
+
+static struct insn_emulation insn_setend = {
 	.name = "setend",
 	.status = INSN_DEPRECATED,
-	.hooks = setend_hooks,
+	.try_emulate = try_emulate_setend,
 	.set_hw_mode = setend_set_hw_mode,
 };
+#endif /* CONFIG_SETEND_EMULATION */
+
+static struct insn_emulation *insn_emulations[] = {
+#ifdef CONFIG_SWP_EMULATION
+	&insn_swp,
+#endif
+#ifdef CONFIG_CP15_BARRIER_EMULATION
+	&insn_cp15_barrier,
+#endif
+#ifdef CONFIG_SETEND_EMULATION
+	&insn_setend,
+#endif
+};
+
+static DEFINE_MUTEX(insn_emulation_mutex);
+
+static void enable_insn_hw_mode(void *data)
+{
+	struct insn_emulation *insn = (struct insn_emulation *)data;
+	if (insn->set_hw_mode)
+		insn->set_hw_mode(true);
+}
+
+static void disable_insn_hw_mode(void *data)
+{
+	struct insn_emulation *insn = (struct insn_emulation *)data;
+	if (insn->set_hw_mode)
+		insn->set_hw_mode(false);
+}
+
+/* Run set_hw_mode(mode) on all active CPUs */
+static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
+{
+	if (!insn->set_hw_mode)
+		return -EINVAL;
+	if (enable)
+		on_each_cpu(enable_insn_hw_mode, (void *)insn, true);
+	else
+		on_each_cpu(disable_insn_hw_mode, (void *)insn, true);
+	return 0;
+}
+
+/*
+ * Run set_hw_mode for all insns on a starting CPU.
+ * Returns:
+ *  0 		- If all the hooks ran successfully.
+ * -EINVAL	- At least one hook is not supported by the CPU.
+ */
+static int run_all_insn_set_hw_mode(unsigned int cpu)
+{
+	int rc = 0;
+	unsigned long flags;
+
+	/*
+	 * Disable IRQs to serialize against an IPI from
+	 * run_all_cpu_set_hw_mode(), ensuring the HW is programmed to the most
+	 * recent enablement state if the two race with one another.
+	 */
+	local_irq_save(flags);
+	for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
+		struct insn_emulation *insn = insn_emulations[i];
+		bool enable = READ_ONCE(insn->current_mode) == INSN_HW;
+		if (insn->set_hw_mode && insn->set_hw_mode(enable)) {
+			pr_warn("CPU[%u] cannot support the emulation of %s",
+				cpu, insn->name);
+			rc = -EINVAL;
+		}
+	}
+	local_irq_restore(flags);
+
+	return rc;
+}
+
+static int update_insn_emulation_mode(struct insn_emulation *insn,
+				       enum insn_emulation_mode prev)
+{
+	int ret = 0;
+
+	switch (prev) {
+	case INSN_UNDEF: /* Nothing to be done */
+		break;
+	case INSN_EMULATE:
+		break;
+	case INSN_HW:
+		if (!run_all_cpu_set_hw_mode(insn, false))
+			pr_notice("Disabled %s support\n", insn->name);
+		break;
+	}
+
+	switch (insn->current_mode) {
+	case INSN_UNDEF:
+		break;
+	case INSN_EMULATE:
+		break;
+	case INSN_HW:
+		ret = run_all_cpu_set_hw_mode(insn, true);
+		if (!ret)
+			pr_notice("Enabled %s support\n", insn->name);
+		break;
+	}
+
+	return ret;
+}
+
+static int emulation_proc_handler(struct ctl_table *table, int write,
+				  void *buffer, size_t *lenp,
+				  loff_t *ppos)
+{
+	int ret = 0;
+	struct insn_emulation *insn = container_of(table->data, struct insn_emulation, current_mode);
+	enum insn_emulation_mode prev_mode = insn->current_mode;
+
+	mutex_lock(&insn_emulation_mutex);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (ret || !write || prev_mode == insn->current_mode)
+		goto ret;
+
+	ret = update_insn_emulation_mode(insn, prev_mode);
+	if (ret) {
+		/* Mode change failed, revert to previous mode. */
+		WRITE_ONCE(insn->current_mode, prev_mode);
+		update_insn_emulation_mode(insn, INSN_UNDEF);
+	}
+ret:
+	mutex_unlock(&insn_emulation_mutex);
+	return ret;
+}
+
+static void __init register_insn_emulation(struct insn_emulation *insn)
+{
+	struct ctl_table *sysctl;
+
+	insn->min = INSN_UNDEF;
+
+	switch (insn->status) {
+	case INSN_DEPRECATED:
+		insn->current_mode = INSN_EMULATE;
+		/* Disable the HW mode if it was turned on at early boot time */
+		run_all_cpu_set_hw_mode(insn, false);
+		insn->max = INSN_HW;
+		break;
+	case INSN_OBSOLETE:
+		insn->current_mode = INSN_UNDEF;
+		insn->max = INSN_EMULATE;
+		break;
+	case INSN_UNAVAILABLE:
+		insn->current_mode = INSN_UNDEF;
+		insn->max = INSN_UNDEF;
+		break;
+	}
+
+	/* Program the HW if required */
+	update_insn_emulation_mode(insn, INSN_UNDEF);
+
+	if (insn->status != INSN_UNAVAILABLE) {
+		sysctl = &insn->sysctl[0];
+
+		sysctl->mode = 0644;
+		sysctl->maxlen = sizeof(int);
+
+		sysctl->procname = insn->name;
+		sysctl->data = &insn->current_mode;
+		sysctl->extra1 = &insn->min;
+		sysctl->extra2 = &insn->max;
+		sysctl->proc_handler = emulation_proc_handler;
+
+		register_sysctl("abi", sysctl);
+	}
+}
+
+bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn)
+{
+	for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
+		struct insn_emulation *ie = insn_emulations[i];
+
+		if (ie->status == INSN_UNAVAILABLE)
+			continue;
+
+		/*
+		 * A trap may race with the mode being changed
+		 * INSN_EMULATE<->INSN_HW. Try to emulate the instruction to
+		 * avoid a spurious UNDEF.
+		 */
+		if (READ_ONCE(ie->current_mode) == INSN_UNDEF)
+			continue;
+
+		if (ie->try_emulate(regs, insn))
+			return true;
+	}
+
+	return false;
+}
 
 /*
  * Invoked as core_initcall, which guarantees that the instruction
@@ -618,24 +602,25 @@ static struct insn_emulation_ops setend_ops = {
  */
 static int __init armv8_deprecated_init(void)
 {
-	if (IS_ENABLED(CONFIG_SWP_EMULATION))
-		register_insn_emulation(&swp_ops);
+#ifdef CONFIG_SETEND_EMULATION
+	if (!system_supports_mixed_endian_el0()) {
+		insn_setend.status = INSN_UNAVAILABLE;
+		pr_info("setend instruction emulation is not supported on this system\n");
+	}
 
-	if (IS_ENABLED(CONFIG_CP15_BARRIER_EMULATION))
-		register_insn_emulation(&cp15_barrier_ops);
+#endif
+	for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
+		struct insn_emulation *ie = insn_emulations[i];
 
-	if (IS_ENABLED(CONFIG_SETEND_EMULATION)) {
-		if (system_supports_mixed_endian_el0())
-			register_insn_emulation(&setend_ops);
-		else
-			pr_info("setend instruction emulation is not supported on this system\n");
+		if (ie->status == INSN_UNAVAILABLE)
+			continue;
+
+		register_insn_emulation(ie);
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
 				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
-	register_insn_emulation_sysctl();
-
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 1197e7679882..2234624536d9 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -82,6 +82,19 @@ int main(void)
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
   DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
   BLANK();
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+  DEFINE(FREGS_X0,		offsetof(struct ftrace_regs, regs[0]));
+  DEFINE(FREGS_X2,		offsetof(struct ftrace_regs, regs[2]));
+  DEFINE(FREGS_X4,		offsetof(struct ftrace_regs, regs[4]));
+  DEFINE(FREGS_X6,		offsetof(struct ftrace_regs, regs[6]));
+  DEFINE(FREGS_X8,		offsetof(struct ftrace_regs, regs[8]));
+  DEFINE(FREGS_FP,		offsetof(struct ftrace_regs, fp));
+  DEFINE(FREGS_LR,		offsetof(struct ftrace_regs, lr));
+  DEFINE(FREGS_SP,		offsetof(struct ftrace_regs, sp));
+  DEFINE(FREGS_PC,		offsetof(struct ftrace_regs, pc));
+  DEFINE(FREGS_SIZE,		sizeof(struct ftrace_regs));
+  BLANK();
+#endif
 #ifdef CONFIG_COMPAT
   DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
   DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET,	offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 89ac00084f38..307faa2b4395 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+	{
+		.desc = "ARM erratum 2645198",
+		.capability = ARM64_WORKAROUND_2645198,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2077057
 	{
 		.desc = "ARM erratum 2077057",
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b3f37e2209ad..7e76e1fda2a1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -212,6 +212,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
 		       FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0),
@@ -402,14 +404,14 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_INNERSHR_SHIFT, 4, 0xf),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_FCSE_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_AUXREG_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_TCM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_SHARELVL_SHIFT, 4, 0),
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_OUTERSHR_SHIFT, 4, 0xf),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_PMSA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_VMSA_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_InnerShr_SHIFT, 4, 0xf),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_FCSE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_AuxReg_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_TCM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_ShareLvl_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_OuterShr_SHIFT, 4, 0xf),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_PMSA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_VMSA_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -429,32 +431,32 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_mvfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPRound_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPShVec_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPSqrt_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPDivide_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPTrap_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPDP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPSP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_SIMDReg_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_mvfr1[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDFMAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDSP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDInt_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDLS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPDNaN_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPFtZ_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_mvfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_EL1_FPMisc_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_EL1_SIMDMisc_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -470,34 +472,34 @@ static const struct arm64_ftr_bits ftr_gmid[] = {
 };
 
 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),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_COPROC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_CMPBRANCH_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_BITFIELD_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_BITCOUNT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_SWAP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Divide_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Debug_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Coproc_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_CmpBranch_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_BitField_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_BitCount_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Swap_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_isar5[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_RDM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_CRC32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SHA2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SHA1_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SEVL_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EVT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CCIDX_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_LSM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_HPDS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CNP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_XNX_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_AC2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_EVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_CCIDX_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_LSM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_HPDS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_CnP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_XNX_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_AC2_SHIFT, 4, 0),
 
 	/*
 	 * SpecSEI = 1 indicates that the PE might generate an SError on an
@@ -505,80 +507,80 @@ static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
 	 * SError might be generated than it will not be. Hence it has been
 	 * classified as FTR_HIGHER_SAFE.
 	 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_MMFR4_SPECSEI_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_MMFR4_EL1_SpecSEI_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_isar4[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SWP_FRAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_PSR_M_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_BARRIER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SMC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_WRITEBACK_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_WITHSHIFTS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_UNPRIV_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SWP_frac_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_PSR_M_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SynchPrim_frac_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Barrier_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SMC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Writeback_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_WithShifts_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Unpriv_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr5[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR5_ETS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR5_EL1_ETS_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_isar6[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_I8MM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_BF16_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SPECRES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SB_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_FHM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_DP_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_JSCVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SPECRES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_JSCVT_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_DIT_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_CSV2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE1_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE0_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_DIT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_CSV2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State1_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State0_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr1[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_GIC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_VIRT_FRAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_SEC_FRAC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_GENTIMER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_VIRTUALIZATION_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_MPROGMOD_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_SECURITY_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_PROGMOD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_GIC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Virt_frac_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Sec_frac_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_GenTimer_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Virtualization_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_MProgMod_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Security_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_ProgMod_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_SSBS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_CSV3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	/* [31:28] TraceFilt */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_PERFMON_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MPROFDBG_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPTRC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPTRC_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPDBG_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPSDBG_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPDBG_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_EL1_PerfMon_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MProfDbg_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapTrc_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopTrc_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapDbg_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopSDbg_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopDbg_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_dfr1[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR1_MTPMU_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR1_EL1_MTPMU_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1119,12 +1121,12 @@ static int update_32bit_cpu_features(int cpu, struct cpuinfo_32bit *info,
 	 * EL1-dependent register fields to avoid spurious sanity check fails.
 	 */
 	if (!id_aa64pfr0_32bit_el1(pfr0)) {
-		relax_cpu_ftr_reg(SYS_ID_ISAR4_EL1, ID_ISAR4_SMC_SHIFT);
-		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_VIRT_FRAC_SHIFT);
-		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_SEC_FRAC_SHIFT);
-		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_VIRTUALIZATION_SHIFT);
-		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_SECURITY_SHIFT);
-		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_PROGMOD_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_ISAR4_EL1, ID_ISAR4_EL1_SMC_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Virt_frac_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Sec_frac_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Virtualization_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Security_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_ProgMod_SHIFT);
 	}
 
 	taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
@@ -2101,6 +2103,11 @@ static void cpu_trap_el0_impdef(const struct arm64_cpu_capabilities *__unused)
 	sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_TIDCP);
 }
 
+static void cpu_enable_dit(const struct arm64_cpu_capabilities *__unused)
+{
+	set_pstate_dit(1);
+}
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2664,6 +2671,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = cpu_trap_el0_impdef,
 	},
+	{
+		.desc = "Data independent timing control (DIT)",
+		.capability = ARM64_HAS_DIT,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_EL1_DIT_SHIFT,
+		.field_width = 4,
+		.min_field_value = ID_AA64PFR0_EL1_DIT_IMP,
+		.matches = has_cpuid_feature,
+		.cpu_enable = cpu_enable_dit,
+	},
 	{},
 };
 
@@ -2772,6 +2791,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
@@ -2798,6 +2818,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 #endif /* CONFIG_ARM64_MTE */
 	HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
 	HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
+	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_CSSC_IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
+	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_RPRFM_IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
 	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
 	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
 #ifdef CONFIG_ARM64_SME
@@ -2829,24 +2851,24 @@ static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope)
 	else
 		mvfr1 = read_sysreg_s(SYS_MVFR1_EL1);
 
-	return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) &&
-		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) &&
-		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT);
+	return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDSP_SHIFT) &&
+		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDInt_SHIFT) &&
+		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDLS_SHIFT);
 }
 #endif
 
 static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
 #ifdef CONFIG_COMPAT
 	HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON),
-	HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
+	HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_EL1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
 	/* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */
-	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
-	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
-	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
+	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
+	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
+	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
+	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
+	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
+	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
+	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
 #endif
 	{},
 };
@@ -3435,35 +3457,22 @@ int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt)
 	return rc;
 }
 
-static int emulate_mrs(struct pt_regs *regs, u32 insn)
+bool try_emulate_mrs(struct pt_regs *regs, u32 insn)
 {
 	u32 sys_reg, rt;
 
+	if (compat_user_mode(regs) || !aarch64_insn_is_mrs(insn))
+		return false;
+
 	/*
 	 * sys_reg values are defined as used in mrs/msr instruction.
 	 * shift the imm value to get the encoding.
 	 */
 	sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
 	rt = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
-	return do_emulate_mrs(regs, sys_reg, rt);
+	return do_emulate_mrs(regs, sys_reg, rt) == 0;
 }
 
-static struct undef_hook mrs_hook = {
-	.instr_mask = 0xffff0000,
-	.instr_val  = 0xd5380000,
-	.pstate_mask = PSR_AA32_MODE_MASK,
-	.pstate_val = PSR_MODE_EL0t,
-	.fn = emulate_mrs,
-};
-
-static int __init enable_mrs_emulation(void)
-{
-	register_undef_hook(&mrs_hook);
-	return 0;
-}
-
-core_initcall(enable_mrs_emulation);
-
 enum mitigation_state arm64_get_meltdown_state(void)
 {
 	if (__meltdown_safe)
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 28d4f442b0bc..379695262b77 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -116,6 +116,9 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_WFXT]		= "wfxt",
 	[KERNEL_HWCAP_EBF16]		= "ebf16",
 	[KERNEL_HWCAP_SVE_EBF16]	= "sveebf16",
+	[KERNEL_HWCAP_CSSC]		= "cssc",
+	[KERNEL_HWCAP_RPRFM]		= "rprfm",
+	[KERNEL_HWCAP_SVE2P1]		= "sve2p1",
 };
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 27369fa1c032..cce1167199e3 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -30,7 +30,7 @@
 /*
  * Handle IRQ/context state management when entering from kernel mode.
  * Before this function is called it is not safe to call regular kernel code,
- * intrumentable code, or any code which may trigger an exception.
+ * instrumentable code, or any code which may trigger an exception.
  *
  * This is intended to match the logic in irqentry_enter(), handling the kernel
  * mode transitions only.
@@ -63,7 +63,7 @@ static void noinstr enter_from_kernel_mode(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when exiting to kernel mode.
  * After this function returns it is not safe to call regular kernel code,
- * intrumentable code, or any code which may trigger an exception.
+ * instrumentable code, or any code which may trigger an exception.
  *
  * This is intended to match the logic in irqentry_exit(), handling the kernel
  * mode transitions only, and with preemption handled elsewhere.
@@ -97,7 +97,7 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when entering from user mode.
  * Before this function is called it is not safe to call regular kernel code,
- * intrumentable code, or any code which may trigger an exception.
+ * instrumentable code, or any code which may trigger an exception.
  */
 static __always_inline void __enter_from_user_mode(void)
 {
@@ -116,7 +116,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when exiting to user mode.
  * After this function returns it is not safe to call regular kernel code,
- * intrumentable code, or any code which may trigger an exception.
+ * instrumentable code, or any code which may trigger an exception.
  */
 static __always_inline void __exit_to_user_mode(void)
 {
@@ -152,7 +152,7 @@ asmlinkage void noinstr asm_exit_to_user_mode(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when entering an NMI from user/kernel
  * mode. Before this function is called it is not safe to call regular kernel
- * code, intrumentable code, or any code which may trigger an exception.
+ * code, instrumentable code, or any code which may trigger an exception.
  */
 static void noinstr arm64_enter_nmi(struct pt_regs *regs)
 {
@@ -170,7 +170,7 @@ static void noinstr arm64_enter_nmi(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when exiting an NMI from user/kernel
  * mode. After this function returns it is not safe to call regular kernel
- * code, intrumentable code, or any code which may trigger an exception.
+ * code, instrumentable code, or any code which may trigger an exception.
  */
 static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 {
@@ -192,7 +192,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when entering a debug exception from
  * kernel mode. Before this function is called it is not safe to call regular
- * kernel code, intrumentable code, or any code which may trigger an exception.
+ * kernel code, instrumentable code, or any code which may trigger an exception.
  */
 static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
 {
@@ -207,7 +207,7 @@ static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
 /*
  * Handle IRQ/context state management when exiting a debug exception from
  * kernel mode. After this function returns it is not safe to call regular
- * kernel code, intrumentable code, or any code which may trigger an exception.
+ * kernel code, instrumentable code, or any code which may trigger an exception.
  */
 static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
 {
@@ -384,7 +384,7 @@ static void noinstr el1_undef(struct pt_regs *regs, unsigned long esr)
 {
 	enter_from_kernel_mode(regs);
 	local_daif_inherit(regs);
-	do_undefinstr(regs, esr);
+	do_el1_undef(regs, esr);
 	local_daif_mask();
 	exit_to_kernel_mode(regs);
 }
@@ -570,7 +570,7 @@ static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr)
 {
 	enter_from_user_mode(regs);
 	local_daif_restore(DAIF_PROCCTX);
-	do_sysinstr(esr, regs);
+	do_el0_sys(esr, regs);
 	exit_to_user_mode(regs);
 }
 
@@ -599,7 +599,7 @@ static void noinstr el0_undef(struct pt_regs *regs, unsigned long esr)
 {
 	enter_from_user_mode(regs);
 	local_daif_restore(DAIF_PROCCTX);
-	do_undefinstr(regs, esr);
+	do_el0_undef(regs, esr);
 	exit_to_user_mode(regs);
 }
 
@@ -762,7 +762,7 @@ static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
 {
 	enter_from_user_mode(regs);
 	local_daif_restore(DAIF_PROCCTX);
-	do_cp15instr(esr, regs);
+	do_el0_cp15(esr, regs);
 	exit_to_user_mode(regs);
 }
 
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 322a831f8ede..3b625f76ffba 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -13,83 +13,58 @@
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 /*
  * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before
  * the regular function prologue. For an enabled callsite, ftrace_init_nop() and
  * ftrace_make_call() have patched those NOPs to:
  *
  * 	MOV	X9, LR
- * 	BL	<entry>
- *
- * ... where <entry> is either ftrace_caller or ftrace_regs_caller.
+ * 	BL	ftrace_caller
  *
  * Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are
  * live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to
  * clobber.
  *
- * We save the callsite's context into a pt_regs before invoking any ftrace
- * callbacks. So that we can get a sensible backtrace, we create a stack record
- * for the callsite and the ftrace entry assembly. This is not sufficient for
- * reliable stacktrace: until we create the callsite stack record, its caller
- * is missing from the LR and existing chain of frame records.
+ * We save the callsite's context into a struct ftrace_regs before invoking any
+ * ftrace callbacks. So that we can get a sensible backtrace, we create frame
+ * records for the callsite and the ftrace entry assembly. This is not
+ * sufficient for reliable stacktrace: until we create the callsite stack
+ * record, its caller is missing from the LR and existing chain of frame
+ * records.
  */
-	.macro  ftrace_regs_entry, allregs=0
-	/* Make room for pt_regs, plus a callee frame */
-	sub	sp, sp, #(PT_REGS_SIZE + 16)
-
-	/* Save function arguments (and x9 for simplicity) */
-	stp	x0, x1, [sp, #S_X0]
-	stp	x2, x3, [sp, #S_X2]
-	stp	x4, x5, [sp, #S_X4]
-	stp	x6, x7, [sp, #S_X6]
-	stp	x8, x9, [sp, #S_X8]
-
-	/* Optionally save the callee-saved registers, always save the FP */
-	.if \allregs == 1
-	stp	x10, x11, [sp, #S_X10]
-	stp	x12, x13, [sp, #S_X12]
-	stp	x14, x15, [sp, #S_X14]
-	stp	x16, x17, [sp, #S_X16]
-	stp	x18, x19, [sp, #S_X18]
-	stp	x20, x21, [sp, #S_X20]
-	stp	x22, x23, [sp, #S_X22]
-	stp	x24, x25, [sp, #S_X24]
-	stp	x26, x27, [sp, #S_X26]
-	stp	x28, x29, [sp, #S_X28]
-	.else
-	str	x29, [sp, #S_FP]
-	.endif
-
-	/* Save the callsite's SP and LR */
-	add	x10, sp, #(PT_REGS_SIZE + 16)
-	stp	x9, x10, [sp, #S_LR]
+SYM_CODE_START(ftrace_caller)
+	bti	c
 
-	/* Save the PC after the ftrace callsite */
-	str	x30, [sp, #S_PC]
+	/* Save original SP */
+	mov	x10, sp
 
-	/* Create a frame record for the callsite above pt_regs */
-	stp	x29, x9, [sp, #PT_REGS_SIZE]
-	add	x29, sp, #PT_REGS_SIZE
+	/* Make room for ftrace regs, plus two frame records */
+	sub	sp, sp, #(FREGS_SIZE + 32)
 
-	/* Create our frame record within pt_regs. */
-	stp	x29, x30, [sp, #S_STACKFRAME]
-	add	x29, sp, #S_STACKFRAME
-	.endm
+	/* Save function arguments */
+	stp	x0, x1, [sp, #FREGS_X0]
+	stp	x2, x3, [sp, #FREGS_X2]
+	stp	x4, x5, [sp, #FREGS_X4]
+	stp	x6, x7, [sp, #FREGS_X6]
+	str	x8,     [sp, #FREGS_X8]
 
-SYM_CODE_START(ftrace_regs_caller)
-	bti	c
-	ftrace_regs_entry	1
-	b	ftrace_common
-SYM_CODE_END(ftrace_regs_caller)
+	/* Save the callsite's FP, LR, SP */
+	str	x29, [sp, #FREGS_FP]
+	str	x9,  [sp, #FREGS_LR]
+	str	x10, [sp, #FREGS_SP]
 
-SYM_CODE_START(ftrace_caller)
-	bti	c
-	ftrace_regs_entry	0
-	b	ftrace_common
-SYM_CODE_END(ftrace_caller)
+	/* Save the PC after the ftrace callsite */
+	str	x30, [sp, #FREGS_PC]
+
+	/* Create a frame record for the callsite above the ftrace regs */
+	stp	x29, x9, [sp, #FREGS_SIZE + 16]
+	add	x29, sp, #FREGS_SIZE + 16
+
+	/* Create our frame record above the ftrace regs */
+	stp	x29, x30, [sp, #FREGS_SIZE]
+	add	x29, sp, #FREGS_SIZE
 
-SYM_CODE_START(ftrace_common)
 	sub	x0, x30, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	mov	x1, x9				// parent_ip (callsite's LR)
 	ldr_l	x2, function_trace_op		// op
@@ -104,24 +79,24 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
  * to restore x0-x8, x29, and x30.
  */
 	/* Restore function arguments */
-	ldp	x0, x1, [sp]
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	ldr	x8, [sp, #S_X8]
+	ldp	x0, x1, [sp, #FREGS_X0]
+	ldp	x2, x3, [sp, #FREGS_X2]
+	ldp	x4, x5, [sp, #FREGS_X4]
+	ldp	x6, x7, [sp, #FREGS_X6]
+	ldr	x8,     [sp, #FREGS_X8]
 
 	/* Restore the callsite's FP, LR, PC */
-	ldr	x29, [sp, #S_FP]
-	ldr	x30, [sp, #S_LR]
-	ldr	x9, [sp, #S_PC]
+	ldr	x29, [sp, #FREGS_FP]
+	ldr	x30, [sp, #FREGS_LR]
+	ldr	x9,  [sp, #FREGS_PC]
 
 	/* Restore the callsite's SP */
-	add	sp, sp, #PT_REGS_SIZE + 16
+	add	sp, sp, #FREGS_SIZE + 32
 
 	ret	x9
-SYM_CODE_END(ftrace_common)
+SYM_CODE_END(ftrace_caller)
 
-#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 /*
  * Gcc with -pg will put the following code in the beginning of each function:
@@ -195,44 +170,6 @@ SYM_CODE_END(ftrace_common)
 	add	\reg, \reg, #8
 	.endm
 
-#ifndef CONFIG_DYNAMIC_FTRACE
-/*
- * void _mcount(unsigned long return_address)
- * @return_address: return address to instrumented function
- *
- * This function makes calls, if enabled, to:
- *     - tracer function to probe instrumented function's entry,
- *     - ftrace_graph_caller to set up an exit hook
- */
-SYM_FUNC_START(_mcount)
-	mcount_enter
-
-	ldr_l	x2, ftrace_trace_function
-	adr	x0, ftrace_stub
-	cmp	x0, x2			// if (ftrace_trace_function
-	b.eq	skip_ftrace_call	//     != ftrace_stub) {
-
-	mcount_get_pc	x0		//       function's pc
-	mcount_get_lr	x1		//       function's lr (= parent's pc)
-	blr	x2			//   (*ftrace_trace_function)(pc, lr);
-
-skip_ftrace_call:			// }
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	ldr_l	x2, ftrace_graph_return
-	cmp	x0, x2			//   if ((ftrace_graph_return
-	b.ne	ftrace_graph_caller	//        != ftrace_stub)
-
-	ldr_l	x2, ftrace_graph_entry	//     || (ftrace_graph_entry
-	adr_l	x0, ftrace_graph_entry_stub //     != ftrace_graph_entry_stub))
-	cmp	x0, x2
-	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-	mcount_exit
-SYM_FUNC_END(_mcount)
-EXPORT_SYMBOL(_mcount)
-NOKPROBE(_mcount)
-
-#else /* CONFIG_DYNAMIC_FTRACE */
 /*
  * _mcount() is used to build the kernel with -pg option, but all the branch
  * instructions to _mcount() are replaced to NOP initially at kernel start up,
@@ -272,7 +209,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
 
 	mcount_exit
 SYM_FUNC_END(ftrace_caller)
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -293,7 +229,7 @@ SYM_FUNC_START(ftrace_graph_caller)
 	mcount_exit
 SYM_FUNC_END(ftrace_graph_caller)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 SYM_TYPED_FUNC_START(ftrace_stub)
 	ret
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e28137d64b76..11cb99c4d298 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -197,6 +197,9 @@ alternative_cb_end
 	.endm
 
 	.macro	kernel_entry, el, regsize = 64
+	.if	\el == 0
+	alternative_insn nop, SET_PSTATE_DIT(1), ARM64_HAS_DIT
+	.endif
 	.if	\regsize == 32
 	mov	w0, w0				// zero upper 32 bits of x0
 	.endif
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 23834d96d1e7..dcc81e7200d4 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -118,16 +118,8 @@
  *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
  *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
  */
-struct fpsimd_last_state_struct {
-	struct user_fpsimd_state *st;
-	void *sve_state;
-	void *za_state;
-	u64 *svcr;
-	unsigned int sve_vl;
-	unsigned int sme_vl;
-};
 
-static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
+static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
 
 __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
 #ifdef CONFIG_ARM64_SVE
@@ -330,15 +322,6 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
  *
- *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
- *    corresponding Zn), P0-P15 and FFR are encoded in
- *    task->thread.sve_state, formatted appropriately for vector
- *    length task->thread.sve_vl or, if SVCR.SM is set,
- *    task->thread.sme_vl.
- *
- *    task->thread.sve_state must point to a valid buffer at least
- *    sve_state_size(task) bytes in size.
- *
  *    During any syscall, the kernel may optionally clear TIF_SVE and
  *    discard the vector state except for the FPSIMD subset.
  *
@@ -348,7 +331,15 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    do_sve_acc() to be called, which does some preparation and then
  *    sets TIF_SVE.
  *
- *    When stored, FPSIMD registers V0-V31 are encoded in
+ * During any syscall, the kernel may optionally clear TIF_SVE and
+ * discard the vector state except for the FPSIMD subset.
+ *
+ * The data will be stored in one of two formats:
+ *
+ *  * FPSIMD only - FP_STATE_FPSIMD:
+ *
+ *    When the FPSIMD only state stored task->thread.fp_type is set to
+ *    FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in
  *    task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are
  *    logically zero but not stored anywhere; P0-P15 and FFR are not
  *    stored and have unspecified values from userspace's point of
@@ -356,7 +347,23 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    but userspace is discouraged from relying on this.
  *
  *    task->thread.sve_state does not need to be non-NULL, valid or any
- *    particular size: it must not be dereferenced.
+ *    particular size: it must not be dereferenced and any data stored
+ *    there should be considered stale and not referenced.
+ *
+ *  * SVE state - FP_STATE_SVE:
+ *
+ *    When the full SVE state is stored task->thread.fp_type is set to
+ *    FP_STATE_SVE and Z0-Z31 (incorporating Vn in bits[127:0] or the
+ *    corresponding Zn), P0-P15 and FFR are encoded in in
+ *    task->thread.sve_state, formatted appropriately for vector
+ *    length task->thread.sve_vl or, if SVCR.SM is set,
+ *    task->thread.sme_vl. The storage for the vector registers in
+ *    task->thread.uw.fpsimd_state should be ignored.
+ *
+ *    task->thread.sve_state must point to a valid buffer at least
+ *    sve_state_size(task) bytes in size. The data stored in
+ *    task->thread.uw.fpsimd_state.vregs should be considered stale
+ *    and not referenced.
  *
  *  * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state
  *    irrespective of whether TIF_SVE is clear or set, since these are
@@ -378,11 +385,37 @@ static void task_fpsimd_load(void)
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
-	/* Check if we should restore SVE first */
-	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
-		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
-		restore_sve_regs = true;
-		restore_ffr = true;
+	if (system_supports_sve()) {
+		switch (current->thread.fp_type) {
+		case FP_STATE_FPSIMD:
+			/* Stop tracking SVE for this task until next use. */
+			if (test_and_clear_thread_flag(TIF_SVE))
+				sve_user_disable();
+			break;
+		case FP_STATE_SVE:
+			if (!thread_sm_enabled(&current->thread) &&
+			    !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE)))
+				sve_user_enable();
+
+			if (test_thread_flag(TIF_SVE))
+				sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+
+			restore_sve_regs = true;
+			restore_ffr = true;
+			break;
+		default:
+			/*
+			 * This indicates either a bug in
+			 * fpsimd_save() or memory corruption, we
+			 * should always record an explicit format
+			 * when we save. We always at least have the
+			 * memory allocated for FPSMID registers so
+			 * try that and hope for the best.
+			 */
+			WARN_ON_ONCE(1);
+			clear_thread_flag(TIF_SVE);
+			break;
+		}
 	}
 
 	/* Restore SME, override SVE register configuration if needed */
@@ -398,18 +431,19 @@ static void task_fpsimd_load(void)
 		if (thread_za_enabled(&current->thread))
 			za_load_state(current->thread.za_state);
 
-		if (thread_sm_enabled(&current->thread)) {
-			restore_sve_regs = true;
+		if (thread_sm_enabled(&current->thread))
 			restore_ffr = system_supports_fa64();
-		}
 	}
 
-	if (restore_sve_regs)
+	if (restore_sve_regs) {
+		WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
 		sve_load_state(sve_pffr(&current->thread),
 			       &current->thread.uw.fpsimd_state.fpsr,
 			       restore_ffr);
-	else
+	} else {
+		WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD);
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
+	}
 }
 
 /*
@@ -419,12 +453,12 @@ static void task_fpsimd_load(void)
  * last, if KVM is involved this may be the guest VM context rather
  * than the host thread for the VM pointed to by current. This means
  * that we must always reference the state storage via last rather
- * than via current, other than the TIF_ flags which KVM will
- * carefully maintain for us.
+ * than via current, if we are saving KVM state then it will have
+ * ensured that the type of registers to save is set in last->to_save.
  */
 static void fpsimd_save(void)
 {
-	struct fpsimd_last_state_struct const *last =
+	struct cpu_fp_state const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
 	bool save_sve_regs = false;
@@ -437,7 +471,14 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
-	if (test_thread_flag(TIF_SVE)) {
+	/*
+	 * If a task is in a syscall the ABI allows us to only
+	 * preserve the state shared with FPSIMD so don't bother
+	 * saving the full SVE state in that case.
+	 */
+	if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) &&
+	     !in_syscall(current_pt_regs())) ||
+	    last->to_save == FP_STATE_SVE) {
 		save_sve_regs = true;
 		save_ffr = true;
 		vl = last->sve_vl;
@@ -474,8 +515,10 @@ static void fpsimd_save(void)
 		sve_save_state((char *)last->sve_state +
 					sve_ffr_offset(vl),
 			       &last->st->fpsr, save_ffr);
+		*last->fp_type = FP_STATE_SVE;
 	} else {
 		fpsimd_save_state(last->st);
+		*last->fp_type = FP_STATE_FPSIMD;
 	}
 }
 
@@ -768,8 +811,7 @@ void fpsimd_sync_to_sve(struct task_struct *task)
  */
 void sve_sync_to_fpsimd(struct task_struct *task)
 {
-	if (test_tsk_thread_flag(task, TIF_SVE) ||
-	    thread_sm_enabled(&task->thread))
+	if (task->thread.fp_type == FP_STATE_SVE)
 		sve_to_fpsimd(task);
 }
 
@@ -848,8 +890,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 
 	fpsimd_flush_task_state(task);
 	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
-	    thread_sm_enabled(&task->thread))
+	    thread_sm_enabled(&task->thread)) {
 		sve_to_fpsimd(task);
+		task->thread.fp_type = FP_STATE_FPSIMD;
+	}
 
 	if (system_supports_sme() && type == ARM64_VEC_SME) {
 		task->thread.svcr &= ~(SVCR_SM_MASK |
@@ -1368,6 +1412,7 @@ static void sve_init_regs(void)
 		fpsimd_bind_task_to_cpu();
 	} else {
 		fpsimd_to_sve(current);
+		current->thread.fp_type = FP_STATE_SVE;
 	}
 }
 
@@ -1596,6 +1641,8 @@ void fpsimd_flush_thread(void)
 		current->thread.svcr = 0;
 	}
 
+	current->thread.fp_type = FP_STATE_FPSIMD;
+
 	put_cpu_fpsimd_context();
 	kfree(sve_state);
 	kfree(za_state);
@@ -1628,14 +1675,38 @@ void fpsimd_signal_preserve_current_state(void)
 }
 
 /*
+ * Called by KVM when entering the guest.
+ */
+void fpsimd_kvm_prepare(void)
+{
+	if (!system_supports_sve())
+		return;
+
+	/*
+	 * KVM does not save host SVE state since we can only enter
+	 * the guest from a syscall so the ABI means that only the
+	 * non-saved SVE state needs to be saved.  If we have left
+	 * SVE enabled for performance reasons then update the task
+	 * state to be FPSIMD only.
+	 */
+	get_cpu_fpsimd_context();
+
+	if (test_and_clear_thread_flag(TIF_SVE)) {
+		sve_to_fpsimd(current);
+		current->thread.fp_type = FP_STATE_FPSIMD;
+	}
+
+	put_cpu_fpsimd_context();
+}
+
+/*
  * Associate current's FPSIMD context with this cpu
  * The caller must have ownership of the cpu FPSIMD context before calling
  * this function.
  */
 static void fpsimd_bind_task_to_cpu(void)
 {
-	struct fpsimd_last_state_struct *last =
-		this_cpu_ptr(&fpsimd_last_state);
+	struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
 
 	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
@@ -1644,6 +1715,8 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
+	last->fp_type = &current->thread.fp_type;
+	last->to_save = FP_STATE_CURRENT;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
 	/*
@@ -1665,22 +1738,14 @@ static void fpsimd_bind_task_to_cpu(void)
 	}
 }
 
-void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
-			      unsigned int sve_vl, void *za_state,
-			      unsigned int sme_vl, u64 *svcr)
+void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state)
 {
-	struct fpsimd_last_state_struct *last =
-		this_cpu_ptr(&fpsimd_last_state);
+	struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
 
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
-	last->st = st;
-	last->svcr = svcr;
-	last->sve_state = sve_state;
-	last->za_state = za_state;
-	last->sve_vl = sve_vl;
-	last->sme_vl = sme_vl;
+	*last = *state;
 }
 
 /*
@@ -1838,7 +1903,7 @@ void kernel_neon_begin(void)
 	/* Invalidate any task state remaining in the fpsimd regs: */
 	fpsimd_flush_cpu_state();
 }
-EXPORT_SYMBOL(kernel_neon_begin);
+EXPORT_SYMBOL_GPL(kernel_neon_begin);
 
 /*
  * kernel_neon_end(): give the CPU FPSIMD registers back to the current task
@@ -1856,7 +1921,7 @@ void kernel_neon_end(void)
 
 	put_cpu_fpsimd_context();
 }
-EXPORT_SYMBOL(kernel_neon_end);
+EXPORT_SYMBOL_GPL(kernel_neon_end);
 
 #ifdef CONFIG_EFI
 
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 8745175f4a75..b30b955a8921 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -17,7 +17,49 @@
 #include <asm/insn.h>
 #include <asm/patching.h>
 
-#ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+struct fregs_offset {
+	const char *name;
+	int offset;
+};
+
+#define FREGS_OFFSET(n, field)				\
+{							\
+	.name = n,					\
+	.offset = offsetof(struct ftrace_regs, field),	\
+}
+
+static const struct fregs_offset fregs_offsets[] = {
+	FREGS_OFFSET("x0", regs[0]),
+	FREGS_OFFSET("x1", regs[1]),
+	FREGS_OFFSET("x2", regs[2]),
+	FREGS_OFFSET("x3", regs[3]),
+	FREGS_OFFSET("x4", regs[4]),
+	FREGS_OFFSET("x5", regs[5]),
+	FREGS_OFFSET("x6", regs[6]),
+	FREGS_OFFSET("x7", regs[7]),
+	FREGS_OFFSET("x8", regs[8]),
+
+	FREGS_OFFSET("x29", fp),
+	FREGS_OFFSET("x30", lr),
+	FREGS_OFFSET("lr", lr),
+
+	FREGS_OFFSET("sp", sp),
+	FREGS_OFFSET("pc", pc),
+};
+
+int ftrace_regs_query_register_offset(const char *name)
+{
+	for (int i = 0; i < ARRAY_SIZE(fregs_offsets); i++) {
+		const struct fregs_offset *roff = &fregs_offsets[i];
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	}
+
+	return -EINVAL;
+}
+#endif
+
 /*
  * Replace a single instruction, which may be a branch or NOP.
  * If @validate == true, a replaced instruction is checked against 'old'.
@@ -70,9 +112,6 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
 
 	if (addr == FTRACE_ADDR)
 		return &plt[FTRACE_PLT_IDX];
-	if (addr == FTRACE_REGS_ADDR &&
-	    IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
-		return &plt[FTRACE_REGS_PLT_IDX];
 #endif
 	return NULL;
 }
@@ -154,25 +193,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(pc, old, new, true);
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
-			unsigned long addr)
-{
-	unsigned long pc = rec->ip;
-	u32 old, new;
-
-	if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
-		return -EINVAL;
-	if (!ftrace_find_callable_addr(rec, NULL, &addr))
-		return -EINVAL;
-
-	old = aarch64_insn_gen_branch_imm(pc, old_addr,
-					  AARCH64_INSN_BRANCH_LINK);
-	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
-
-	return ftrace_modify_code(pc, old, new, true);
-}
-
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 /*
  * The compiler has inserted two NOPs before the regular function prologue.
  * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live,
@@ -228,7 +249,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	 *
 	 * Note: 'mod' is only set at module load time.
 	 */
-	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) &&
 	    IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) {
 		return aarch64_insn_patch_text_nosync((void *)pc, new);
 	}
@@ -246,7 +267,6 @@ void arch_ftrace_update_code(int command)
 	command |= FTRACE_MAY_SLEEP;
 	ftrace_modify_all_code(command);
 }
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -277,21 +297,11 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	}
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	/*
-	 * When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL
-	 * and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs
-	 * in which we can safely modify the LR.
-	 */
-	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
-	unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs);
-
-	prepare_ftrace_return(ip, parent, frame_pointer(regs));
+	prepare_ftrace_return(ip, &fregs->lr, fregs->fp);
 }
 #else
 /*
@@ -323,6 +333,5 @@ int ftrace_disable_ftrace_graph_caller(void)
 {
 	return ftrace_modify_graph_caller(false);
 }
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
-#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2196aad7b55b..952e17bd1c0b 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -462,6 +462,9 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	bl	early_fdt_map			// Try mapping the FDT early
 	mov	x0, x20				// pass the full boot status
 	bl	init_feature_override		// Parse cpu feature overrides
+#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
+	bl	scs_patch_vmlinux
+#endif
 	mov	x0, x20
 	bl	finalise_el2			// Prefer VHE if possible
 	ldp	x29, x30, [sp], #16
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 38dbd3828f13..6ad5c6ef5329 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -10,20 +10,21 @@
  * Copyright (C) 2012 ARM Ltd.
  */
 
-#include <linux/irq.h>
-#include <linux/memory.h>
-#include <linux/smp.h>
 #include <linux/hardirq.h>
 #include <linux/init.h>
+#include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/kprobes.h>
+#include <linux/memory.h>
 #include <linux/scs.h>
 #include <linux/seq_file.h>
+#include <linux/smp.h>
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
 #include <asm/exception.h>
-#include <asm/vmap_stack.h>
 #include <asm/softirq_stack.h>
+#include <asm/stacktrace.h>
+#include <asm/vmap_stack.h>
 
 /* Only access this in an NMI enter/exit */
 DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
@@ -41,7 +42,7 @@ static void init_irq_scs(void)
 {
 	int cpu;
 
-	if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
+	if (!scs_is_enabled())
 		return;
 
 	for_each_possible_cpu(cpu)
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 76b41e4ca9fa..5af4975caeb5 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -15,9 +15,11 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/moduleloader.h>
+#include <linux/scs.h>
 #include <linux/vmalloc.h>
 #include <asm/alternative.h>
 #include <asm/insn.h>
+#include <asm/scs.h>
 #include <asm/sections.h>
 
 void *module_alloc(unsigned long size)
@@ -497,9 +499,6 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
 
 	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
 
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
-		__init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR);
-
 	mod->arch.ftrace_trampolines = plts;
 #endif
 	return 0;
@@ -514,5 +513,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 	if (s)
 		apply_alternatives_module((void *)s->sh_addr, s->sh_size);
 
+	if (scs_is_dynamic()) {
+		s = find_section(hdr, sechdrs, ".init.eh_frame");
+		if (s)
+			scs_patch((void *)s->sh_addr, s->sh_size);
+	}
+
 	return module_init_ftrace_plt(hdr, sechdrs, me);
 }
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 57c7c211f8c7..aa718d6a9274 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -141,10 +141,6 @@ static bool __init has_pv_steal_clock(void)
 {
 	struct arm_smccc_res res;
 
-	/* To detect the presence of PV time support we require SMCCC 1.1+ */
-	if (arm_smccc_1_1_get_conduit() == SMCCC_CONDUIT_NONE)
-		return false;
-
 	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 			     ARM_SMCCC_HV_PV_TIME_FEATURES, &res);
 
diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/patch-scs.c
new file mode 100644
index 000000000000..1b3da02d5b74
--- /dev/null
+++ b/arch/arm64/kernel/patch-scs.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 - Google LLC
+ * Author: Ard Biesheuvel <ardb@google.com>
+ */
+
+#include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/printk.h>
+#include <linux/types.h>
+
+#include <asm/cacheflush.h>
+#include <asm/scs.h>
+
+//
+// This minimal DWARF CFI parser is partially based on the code in
+// arch/arc/kernel/unwind.c, and on the document below:
+// https://refspecs.linuxbase.org/LSB_4.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html
+//
+
+#define DW_CFA_nop                          0x00
+#define DW_CFA_set_loc                      0x01
+#define DW_CFA_advance_loc1                 0x02
+#define DW_CFA_advance_loc2                 0x03
+#define DW_CFA_advance_loc4                 0x04
+#define DW_CFA_offset_extended              0x05
+#define DW_CFA_restore_extended             0x06
+#define DW_CFA_undefined                    0x07
+#define DW_CFA_same_value                   0x08
+#define DW_CFA_register                     0x09
+#define DW_CFA_remember_state               0x0a
+#define DW_CFA_restore_state                0x0b
+#define DW_CFA_def_cfa                      0x0c
+#define DW_CFA_def_cfa_register             0x0d
+#define DW_CFA_def_cfa_offset               0x0e
+#define DW_CFA_def_cfa_expression           0x0f
+#define DW_CFA_expression                   0x10
+#define DW_CFA_offset_extended_sf           0x11
+#define DW_CFA_def_cfa_sf                   0x12
+#define DW_CFA_def_cfa_offset_sf            0x13
+#define DW_CFA_val_offset                   0x14
+#define DW_CFA_val_offset_sf                0x15
+#define DW_CFA_val_expression               0x16
+#define DW_CFA_lo_user                      0x1c
+#define DW_CFA_negate_ra_state              0x2d
+#define DW_CFA_GNU_args_size                0x2e
+#define DW_CFA_GNU_negative_offset_extended 0x2f
+#define DW_CFA_hi_user                      0x3f
+
+extern const u8 __eh_frame_start[], __eh_frame_end[];
+
+enum {
+	PACIASP		= 0xd503233f,
+	AUTIASP		= 0xd50323bf,
+	SCS_PUSH	= 0xf800865e,
+	SCS_POP		= 0xf85f8e5e,
+};
+
+static void __always_inline scs_patch_loc(u64 loc)
+{
+	u32 insn = le32_to_cpup((void *)loc);
+
+	switch (insn) {
+	case PACIASP:
+		*(u32 *)loc = cpu_to_le32(SCS_PUSH);
+		break;
+	case AUTIASP:
+		*(u32 *)loc = cpu_to_le32(SCS_POP);
+		break;
+	default:
+		/*
+		 * While the DW_CFA_negate_ra_state directive is guaranteed to
+		 * appear right after a PACIASP/AUTIASP instruction, it may
+		 * also appear after a DW_CFA_restore_state directive that
+		 * restores a state that is only partially accurate, and is
+		 * followed by DW_CFA_negate_ra_state directive to toggle the
+		 * PAC bit again. So we permit other instructions here, and ignore
+		 * them.
+		 */
+		return;
+	}
+	dcache_clean_pou(loc, loc + sizeof(u32));
+}
+
+/*
+ * Skip one uleb128/sleb128 encoded quantity from the opcode stream. All bytes
+ * except the last one have bit #7 set.
+ */
+static int __always_inline skip_xleb128(const u8 **opcode, int size)
+{
+	u8 c;
+
+	do {
+		c = *(*opcode)++;
+		size--;
+	} while (c & BIT(7));
+
+	return size;
+}
+
+struct eh_frame {
+	/*
+	 * The size of this frame if 0 < size < U32_MAX, 0 terminates the list.
+	 */
+	u32	size;
+
+	/*
+	 * The first frame is a Common Information Entry (CIE) frame, followed
+	 * by one or more Frame Description Entry (FDE) frames. In the former
+	 * case, this field is 0, otherwise it is the negated offset relative
+	 * to the associated CIE frame.
+	 */
+	u32	cie_id_or_pointer;
+
+	union {
+		struct { // CIE
+			u8	version;
+			u8	augmentation_string[];
+		};
+
+		struct { // FDE
+			s32	initial_loc;
+			s32	range;
+			u8	opcodes[];
+		};
+	};
+};
+
+static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
+					bool fde_has_augmentation_data,
+					int code_alignment_factor)
+{
+	int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
+	u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
+	const u8 *opcode = frame->opcodes;
+
+	if (fde_has_augmentation_data) {
+		int l;
+
+		// assume single byte uleb128_t
+		if (WARN_ON(*opcode & BIT(7)))
+			return -ENOEXEC;
+
+		l = *opcode++;
+		opcode += l;
+		size -= l + 1;
+	}
+
+	/*
+	 * Starting from 'loc', apply the CFA opcodes that advance the location
+	 * pointer, and identify the locations of the PAC instructions.
+	 */
+	while (size-- > 0) {
+		switch (*opcode++) {
+		case DW_CFA_nop:
+		case DW_CFA_remember_state:
+		case DW_CFA_restore_state:
+			break;
+
+		case DW_CFA_advance_loc1:
+			loc += *opcode++ * code_alignment_factor;
+			size--;
+			break;
+
+		case DW_CFA_advance_loc2:
+			loc += *opcode++ * code_alignment_factor;
+			loc += (*opcode++ << 8) * code_alignment_factor;
+			size -= 2;
+			break;
+
+		case DW_CFA_def_cfa:
+		case DW_CFA_offset_extended:
+			size = skip_xleb128(&opcode, size);
+			fallthrough;
+		case DW_CFA_def_cfa_offset:
+		case DW_CFA_def_cfa_offset_sf:
+		case DW_CFA_def_cfa_register:
+		case DW_CFA_same_value:
+		case DW_CFA_restore_extended:
+		case 0x80 ... 0xbf:
+			size = skip_xleb128(&opcode, size);
+			break;
+
+		case DW_CFA_negate_ra_state:
+			scs_patch_loc(loc - 4);
+			break;
+
+		case 0x40 ... 0x7f:
+			// advance loc
+			loc += (opcode[-1] & 0x3f) * code_alignment_factor;
+			break;
+
+		case 0xc0 ... 0xff:
+			break;
+
+		default:
+			pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame);
+			return -ENOEXEC;
+		}
+	}
+	return 0;
+}
+
+int noinstr scs_patch(const u8 eh_frame[], int size)
+{
+	const u8 *p = eh_frame;
+
+	while (size > 4) {
+		const struct eh_frame *frame = (const void *)p;
+		bool fde_has_augmentation_data = true;
+		int code_alignment_factor = 1;
+		int ret;
+
+		if (frame->size == 0 ||
+		    frame->size == U32_MAX ||
+		    frame->size > size)
+			break;
+
+		if (frame->cie_id_or_pointer == 0) {
+			const u8 *p = frame->augmentation_string;
+
+			/* a 'z' in the augmentation string must come first */
+			fde_has_augmentation_data = *p == 'z';
+
+			/*
+			 * The code alignment factor is a uleb128 encoded field
+			 * but given that the only sensible values are 1 or 4,
+			 * there is no point in decoding the whole thing.
+			 */
+			p += strlen(p) + 1;
+			if (!WARN_ON(*p & BIT(7)))
+				code_alignment_factor = *p;
+		} else {
+			ret = scs_handle_fde_frame(frame,
+						   fde_has_augmentation_data,
+						   code_alignment_factor);
+			if (ret)
+				return ret;
+		}
+
+		p += sizeof(frame->size) + frame->size;
+		size -= sizeof(frame->size) + frame->size;
+	}
+	return 0;
+}
+
+asmlinkage void __init scs_patch_vmlinux(void)
+{
+	if (!should_patch_pac_into_scs())
+		return;
+
+	WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start));
+	icache_inval_all_pou();
+	isb();
+}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 7b0643fe2f13..a15b3c1d15d9 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1146,7 +1146,8 @@ static void __armv8pmu_probe_pmu(void *info)
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
 	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
 			ID_AA64DFR0_EL1_PMUVer_SHIFT);
-	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || pmuver == 0)
+	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF ||
+	    pmuver == ID_AA64DFR0_EL1_PMUVer_NI)
 		return;
 
 	cpu_pmu->pmuver = pmuver;
diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index 839291430cb3..4c0ea3cd4ea4 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -7,6 +7,7 @@ KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
 		   -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
 		   -include $(srctree)/include/linux/hidden.h \
 		   -D__DISABLE_EXPORTS -ffreestanding -D__NO_FORTIFY \
+		   -fno-asynchronous-unwind-tables -fno-unwind-tables \
 		   $(call cc-option,-fno-addrsig)
 
 # remove SCS flags from all objects in this directory
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 104101f633b1..968d5fffe233 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -24,7 +24,7 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
 	 * currently safe. Lastly, MSR instructions can do any number of nasty
 	 * things we can't handle during single-stepping.
 	 */
-	if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) {
+	if (aarch64_insn_is_class_branch_sys(insn)) {
 		if (aarch64_insn_is_branch(insn) ||
 		    aarch64_insn_is_msr_imm(insn) ||
 		    aarch64_insn_is_msr_reg(insn) ||
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c9e4d0720285..f35d059a9a36 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -294,19 +294,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 		}
 
 		break;
-	case KPROBE_HIT_ACTIVE:
-	case KPROBE_HIT_SSDONE:
-		/*
-		 * In case the user-specified fault handler returned
-		 * zero, try to fix up.
-		 */
-		if (fixup_exception(regs))
-			return 1;
 	}
 	return 0;
 }
 
-static void __kprobes kprobe_handler(struct pt_regs *regs)
+static int __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr)
 {
 	struct kprobe *p, *cur_kprobe;
 	struct kprobe_ctlblk *kcb;
@@ -316,39 +309,44 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 	cur_kprobe = kprobe_running();
 
 	p = get_kprobe((kprobe_opcode_t *) addr);
+	if (WARN_ON_ONCE(!p)) {
+		/*
+		 * Something went wrong. This BRK used an immediate reserved
+		 * for kprobes, but we couldn't find any corresponding probe.
+		 */
+		return DBG_HOOK_ERROR;
+	}
 
-	if (p) {
-		if (cur_kprobe) {
-			if (reenter_kprobe(p, regs, kcb))
-				return;
-		} else {
-			/* Probe hit */
-			set_current_kprobe(p);
-			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-
-			/*
-			 * If we have no pre-handler or it returned 0, we
-			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it will
-			 * modify the execution path and no need to single
-			 * stepping. Let's just reset current kprobe and exit.
-			 */
-			if (!p->pre_handler || !p->pre_handler(p, regs)) {
-				setup_singlestep(p, regs, kcb, 0);
-			} else
-				reset_current_kprobe();
-		}
+	if (cur_kprobe) {
+		/* Hit a kprobe inside another kprobe */
+		if (!reenter_kprobe(p, regs, kcb))
+			return DBG_HOOK_ERROR;
+	} else {
+		/* Probe hit */
+		set_current_kprobe(p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+		/*
+		 * If we have no pre-handler or it returned 0, we
+		 * continue with normal processing.  If we have a
+		 * pre-handler and it returned non-zero, it will
+		 * modify the execution path and not need to single-step
+		 * Let's just reset current kprobe and exit.
+		 */
+		if (!p->pre_handler || !p->pre_handler(p, regs))
+			setup_singlestep(p, regs, kcb, 0);
+		else
+			reset_current_kprobe();
 	}
-	/*
-	 * The breakpoint instruction was removed right
-	 * after we hit it.  Another cpu has removed
-	 * either a probepoint or a debugger breakpoint
-	 * at this address.  In either case, no further
-	 * handling of this interrupt is appropriate.
-	 * Return back to original instruction, and continue.
-	 */
+
+	return DBG_HOOK_HANDLED;
 }
 
+static struct break_hook kprobes_break_hook = {
+	.imm = KPROBES_BRK_IMM,
+	.fn = kprobe_breakpoint_handler,
+};
+
 static int __kprobes
 kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned long esr)
 {
@@ -373,18 +371,6 @@ static struct break_hook kprobes_break_ss_hook = {
 	.fn = kprobe_breakpoint_ss_handler,
 };
 
-static int __kprobes
-kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr)
-{
-	kprobe_handler(regs);
-	return DBG_HOOK_HANDLED;
-}
-
-static struct break_hook kprobes_break_hook = {
-	.imm = KPROBES_BRK_IMM,
-	.fn = kprobe_breakpoint_handler,
-};
-
 /*
  * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
  * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 044a7d7f1f6a..19cd05eea3f0 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -331,6 +331,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 		clear_tsk_thread_flag(dst, TIF_SME);
 	}
 
+	dst->thread.fp_type = FP_STATE_FPSIMD;
+
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
 
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index bfce41c2a53b..fca9cc6f5581 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -521,10 +521,13 @@ bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope)
 	return state != SPECTRE_UNAFFECTED;
 }
 
-static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
+bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr)
 {
-	if (user_mode(regs))
-		return 1;
+	const u32 instr_mask = ~(1U << PSTATE_Imm_shift);
+	const u32 instr_val = 0xd500401f | PSTATE_SSBS;
+
+	if ((instr & instr_mask) != instr_val)
+		return false;
 
 	if (instr & BIT(PSTATE_Imm_shift))
 		regs->pstate |= PSR_SSBS_BIT;
@@ -532,19 +535,11 @@ static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
 		regs->pstate &= ~PSR_SSBS_BIT;
 
 	arm64_skip_faulting_instruction(regs, 4);
-	return 0;
+	return true;
 }
 
-static struct undef_hook ssbs_emulation_hook = {
-	.instr_mask	= ~(1U << PSTATE_Imm_shift),
-	.instr_val	= 0xd500401f | PSTATE_SSBS,
-	.fn		= ssbs_emulation_handler,
-};
-
 static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
 {
-	static bool undef_hook_registered = false;
-	static DEFINE_RAW_SPINLOCK(hook_lock);
 	enum mitigation_state state;
 
 	/*
@@ -555,13 +550,6 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
 	if (state != SPECTRE_MITIGATED || !this_cpu_has_cap(ARM64_SSBS))
 		return state;
 
-	raw_spin_lock(&hook_lock);
-	if (!undef_hook_registered) {
-		register_undef_hook(&ssbs_emulation_hook);
-		undef_hook_registered = true;
-	}
-	raw_spin_unlock(&hook_lock);
-
 	if (spectre_v4_mitigations_off()) {
 		sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
 		set_pstate_ssbs(1);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index c2fb5755bbec..979dbdc36d52 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -907,8 +907,7 @@ static int sve_set_common(struct task_struct *target,
 		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
 				SVE_PT_FPSIMD_OFFSET);
 		clear_tsk_thread_flag(target, TIF_SVE);
-		if (type == ARM64_VEC_SME)
-			fpsimd_force_sync_to_sve(target);
+		target->thread.fp_type = FP_STATE_FPSIMD;
 		goto out;
 	}
 
@@ -931,6 +930,7 @@ static int sve_set_common(struct task_struct *target,
 	if (!target->thread.sve_state) {
 		ret = -ENOMEM;
 		clear_tsk_thread_flag(target, TIF_SVE);
+		target->thread.fp_type = FP_STATE_FPSIMD;
 		goto out;
 	}
 
@@ -942,6 +942,7 @@ static int sve_set_common(struct task_struct *target,
 	 */
 	fpsimd_sync_to_sve(target);
 	set_tsk_thread_flag(target, TIF_SVE);
+	target->thread.fp_type = FP_STATE_SVE;
 
 	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
 	start = SVE_PT_SVE_OFFSET;
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index d56e170e1ca7..830be01af32d 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -144,7 +144,7 @@ static int init_sdei_scs(void)
 	int cpu;
 	int err = 0;
 
-	if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
+	if (!scs_is_enabled())
 		return 0;
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index fea3223704b6..12cfe9d0d3fa 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -30,6 +30,7 @@
 #include <linux/efi.h>
 #include <linux/psci.h>
 #include <linux/sched/task.h>
+#include <linux/scs.h>
 #include <linux/mm.h>
 
 #include <asm/acpi.h>
@@ -42,6 +43,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/kasan.h>
 #include <asm/numa.h>
+#include <asm/scs.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -312,6 +314,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
 	jump_label_init();
 	parse_early_param();
 
+	dynamic_scs_init();
+
 	/*
 	 * Unmask asynchronous aborts and fiq after bringing up possible
 	 * earlycon. (Report possible System Errors once we can report this
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 9ad911f1647c..e0d09bf5b01b 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -207,6 +207,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
 	clear_thread_flag(TIF_SVE);
+	current->thread.fp_type = FP_STATE_FPSIMD;
 
 	/* load the hardware registers from the fpsimd_state structure */
 	if (!err)
@@ -292,6 +293,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	if (sve.head.size <= sizeof(*user->sve)) {
 		clear_thread_flag(TIF_SVE);
 		current->thread.svcr &= ~SVCR_SM_MASK;
+		current->thread.fp_type = FP_STATE_FPSIMD;
 		goto fpsimd_only;
 	}
 
@@ -327,6 +329,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 		current->thread.svcr |= SVCR_SM_MASK;
 	else
 		set_thread_flag(TIF_SVE);
+	current->thread.fp_type = FP_STATE_SVE;
 
 fpsimd_only:
 	/* copy the FP and status/control registers */
@@ -932,9 +935,11 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		 * FPSIMD register state - flush the saved FPSIMD
 		 * register state in case it gets loaded.
 		 */
-		if (current->thread.svcr & SVCR_SM_MASK)
+		if (current->thread.svcr & SVCR_SM_MASK) {
 			memset(&current->thread.uw.fpsimd_state, 0,
 			       sizeof(current->thread.uw.fpsimd_state));
+			current->thread.fp_type = FP_STATE_FPSIMD;
+		}
 
 		current->thread.svcr &= ~(SVCR_ZA_MASK |
 					  SVCR_SM_MASK);
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 634279b3b03d..117e2c180f3c 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -23,8 +23,8 @@
  *
  * The regs must be on a stack currently owned by the calling task.
  */
-static inline void unwind_init_from_regs(struct unwind_state *state,
-					 struct pt_regs *regs)
+static __always_inline void unwind_init_from_regs(struct unwind_state *state,
+						  struct pt_regs *regs)
 {
 	unwind_init_common(state, current);
 
@@ -58,8 +58,8 @@ static __always_inline void unwind_init_from_caller(struct unwind_state *state)
  * duration of the unwind, or the unwind will be bogus. It is never valid to
  * call this for the current task.
  */
-static inline void unwind_init_from_task(struct unwind_state *state,
-					 struct task_struct *task)
+static __always_inline void unwind_init_from_task(struct unwind_state *state,
+						  struct task_struct *task)
 {
 	unwind_init_common(state, task);
 
@@ -186,7 +186,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 			: stackinfo_get_unknown();		\
 	})
 
-noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry,
+noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
 			      void *cookie, struct task_struct *task,
 			      struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 8b02d310838f..e7163f31f716 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -60,6 +60,8 @@ void notrace __cpu_suspend_exit(void)
 	 * PSTATE was not saved over suspend/resume, re-enable any detected
 	 * features that might not have been set correctly.
 	 */
+	if (cpus_have_const_cap(ARM64_HAS_DIT))
+		set_pstate_dit(1);
 	__uaccess_enable_hw_pan();
 
 	/*
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index d72e8f23422d..a5de47e3df2b 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -183,21 +183,12 @@ static inline void fp_user_discard(void)
 	if (!system_supports_sve())
 		return;
 
-	/*
-	 * If SME is not active then disable SVE, the registers will
-	 * be cleared when userspace next attempts to access them and
-	 * we do not need to track the SVE register state until then.
-	 */
-	clear_thread_flag(TIF_SVE);
+	if (test_thread_flag(TIF_SVE)) {
+		unsigned int sve_vq_minus_one;
 
-	/*
-	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
-	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
-	 * happens if a context switch or kernel_neon_begin() or context
-	 * modification (sigreturn, ptrace) intervenes.
-	 * So, ensure that CPACR_EL1 is already correct for the fast-path case.
-	 */
-	sve_user_disable();
+		sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
+		sve_flush_live(true, sve_vq_minus_one);
+	}
 }
 
 void do_el0_svc(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 23d281ed7621..4c0caa589e12 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -373,51 +373,22 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 		regs->pstate &= ~PSR_BTYPE_MASK;
 }
 
-static LIST_HEAD(undef_hook);
-static DEFINE_RAW_SPINLOCK(undef_lock);
-
-void register_undef_hook(struct undef_hook *hook)
+static int user_insn_read(struct pt_regs *regs, u32 *insnp)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&undef_lock, flags);
-	list_add(&hook->node, &undef_hook);
-	raw_spin_unlock_irqrestore(&undef_lock, flags);
-}
-
-void unregister_undef_hook(struct undef_hook *hook)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&undef_lock, flags);
-	list_del(&hook->node);
-	raw_spin_unlock_irqrestore(&undef_lock, flags);
-}
-
-static int call_undef_hook(struct pt_regs *regs)
-{
-	struct undef_hook *hook;
-	unsigned long flags;
 	u32 instr;
-	int (*fn)(struct pt_regs *regs, u32 instr) = NULL;
 	unsigned long pc = instruction_pointer(regs);
 
-	if (!user_mode(regs)) {
-		__le32 instr_le;
-		if (get_kernel_nofault(instr_le, (__le32 *)pc))
-			goto exit;
-		instr = le32_to_cpu(instr_le);
-	} else if (compat_thumb_mode(regs)) {
+	if (compat_thumb_mode(regs)) {
 		/* 16-bit Thumb instruction */
 		__le16 instr_le;
 		if (get_user(instr_le, (__le16 __user *)pc))
-			goto exit;
+			return -EFAULT;
 		instr = le16_to_cpu(instr_le);
 		if (aarch32_insn_is_wide(instr)) {
 			u32 instr2;
 
 			if (get_user(instr_le, (__le16 __user *)(pc + 2)))
-				goto exit;
+				return -EFAULT;
 			instr2 = le16_to_cpu(instr_le);
 			instr = (instr << 16) | instr2;
 		}
@@ -425,19 +396,12 @@ static int call_undef_hook(struct pt_regs *regs)
 		/* 32-bit ARM instruction */
 		__le32 instr_le;
 		if (get_user(instr_le, (__le32 __user *)pc))
-			goto exit;
+			return -EFAULT;
 		instr = le32_to_cpu(instr_le);
 	}
 
-	raw_spin_lock_irqsave(&undef_lock, flags);
-	list_for_each_entry(hook, &undef_hook, node)
-		if ((instr & hook->instr_mask) == hook->instr_val &&
-			(regs->pstate & hook->pstate_mask) == hook->pstate_val)
-			fn = hook->fn;
-
-	raw_spin_unlock_irqrestore(&undef_lock, flags);
-exit:
-	return fn ? fn(regs, instr) : 1;
+	*insnp = instr;
+	return 0;
 }
 
 void force_signal_inject(int signal, int code, unsigned long address, unsigned long err)
@@ -486,21 +450,40 @@ void arm64_notify_segfault(unsigned long addr)
 	force_signal_inject(SIGSEGV, code, addr, 0);
 }
 
-void do_undefinstr(struct pt_regs *regs, unsigned long esr)
+void do_el0_undef(struct pt_regs *regs, unsigned long esr)
 {
+	u32 insn;
+
 	/* check for AArch32 breakpoint instructions */
 	if (!aarch32_break_handler(regs))
 		return;
 
-	if (call_undef_hook(regs) == 0)
+	if (user_insn_read(regs, &insn))
+		goto out_err;
+
+	if (try_emulate_mrs(regs, insn))
 		return;
 
-	if (!user_mode(regs))
-		die("Oops - Undefined instruction", regs, esr);
+	if (try_emulate_armv8_deprecated(regs, insn))
+		return;
 
+out_err:
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 }
-NOKPROBE_SYMBOL(do_undefinstr);
+
+void do_el1_undef(struct pt_regs *regs, unsigned long esr)
+{
+	u32 insn;
+
+	if (aarch64_insn_read((void *)regs->pc, &insn))
+		goto out_err;
+
+	if (try_emulate_el1_ssbs(regs, insn))
+		return;
+
+out_err:
+	die("Oops - Undefined instruction", regs, esr);
+}
 
 void do_el0_bti(struct pt_regs *regs)
 {
@@ -511,7 +494,6 @@ void do_el1_bti(struct pt_regs *regs, unsigned long esr)
 {
 	die("Oops - BTI", regs, esr);
 }
-NOKPROBE_SYMBOL(do_el1_bti);
 
 void do_el0_fpac(struct pt_regs *regs, unsigned long esr)
 {
@@ -526,7 +508,6 @@ void do_el1_fpac(struct pt_regs *regs, unsigned long esr)
 	 */
 	die("Oops - FPAC", regs, esr);
 }
-NOKPROBE_SYMBOL(do_el1_fpac)
 
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= TASK_SIZE_MAX) {				\
@@ -748,7 +729,7 @@ static const struct sys64_hook cp15_64_hooks[] = {
 	{},
 };
 
-void do_cp15instr(unsigned long esr, struct pt_regs *regs)
+void do_el0_cp15(unsigned long esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook, *hook_base;
 
@@ -769,7 +750,7 @@ void do_cp15instr(unsigned long esr, struct pt_regs *regs)
 		hook_base = cp15_64_hooks;
 		break;
 	default:
-		do_undefinstr(regs, esr);
+		do_el0_undef(regs, esr);
 		return;
 	}
 
@@ -784,12 +765,11 @@ void do_cp15instr(unsigned long esr, struct pt_regs *regs)
 	 * EL0. Fall back to our usual undefined instruction handler
 	 * so that we handle these consistently.
 	 */
-	do_undefinstr(regs, esr);
+	do_el0_undef(regs, esr);
 }
-NOKPROBE_SYMBOL(do_cp15instr);
 #endif
 
-void do_sysinstr(unsigned long esr, struct pt_regs *regs)
+void do_el0_sys(unsigned long esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook;
 
@@ -804,9 +784,8 @@ void do_sysinstr(unsigned long esr, struct pt_regs *regs)
 	 * back to our usual undefined instruction handler so that we handle
 	 * these consistently.
 	 */
-	do_undefinstr(regs, esr);
+	do_el0_undef(regs, esr);
 }
-NOKPROBE_SYMBOL(do_sysinstr);
 
 static const char *esr_class_str[] = {
 	[0 ... ESR_ELx_EC_MAX]		= "UNRECOGNIZED EC",
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 45131e354e27..4c13dafc98b8 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -121,6 +121,17 @@ jiffies = jiffies_64;
 #define TRAMP_TEXT
 #endif
 
+#ifdef CONFIG_UNWIND_TABLES
+#define UNWIND_DATA_SECTIONS				\
+	.eh_frame : {					\
+		__eh_frame_start = .;			\
+		*(.eh_frame)				\
+		__eh_frame_end = .;			\
+	}
+#else
+#define UNWIND_DATA_SECTIONS
+#endif
+
 /*
  * The size of the PE/COFF section that covers the kernel image, which
  * runs from _stext to _edata, must be a round multiple of the PE/COFF
@@ -231,6 +242,8 @@ SECTIONS
 		__alt_instructions_end = .;
 	}
 
+	UNWIND_DATA_SECTIONS
+
 	. = ALIGN(SEGMENT_ALIGN);
 	__inittext_end = .;
 	__initdata_begin = .;