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

Pull arm64 updates from Catalin Marinas:
 "Apart from the arm64-specific bits (core arch and perf, new arm64
  selftests), it touches the generic cow_user_page() (reviewed by
  Kirill) together with a macro for x86 to preserve the existing
  behaviour on this architecture.

  Summary:

   - On ARMv8 CPUs without hardware updates of the access flag, avoid
     failing cow_user_page() on PFN mappings if the pte is old. The
     patches introduce an arch_faults_on_old_pte() macro, defined as
     false on x86. When true, cow_user_page() makes the pte young before
     attempting __copy_from_user_inatomic().

   - Covert the synchronous exception handling paths in
     arch/arm64/kernel/entry.S to C.

   - FTRACE_WITH_REGS support for arm64.

   - ZONE_DMA re-introduced on arm64 to support Raspberry Pi 4

   - Several kselftest cases specific to arm64, together with a
     MAINTAINERS update for these files (moved to the ARM64 PORT entry).

   - Workaround for a Neoverse-N1 erratum where the CPU may fetch stale
     instructions under certain conditions.

   - Workaround for Cortex-A57 and A72 errata where the CPU may
     speculatively execute an AT instruction and associate a VMID with
     the wrong guest page tables (corrupting the TLB).

   - Perf updates for arm64: additional PMU topologies on HiSilicon
     platforms, support for CCN-512 interconnect, AXI ID filtering in
     the IMX8 DDR PMU, support for the CCPI2 uncore PMU in ThunderX2.

   - GICv3 optimisation to avoid a heavy barrier when accessing the
     ICC_PMR_EL1 register.

   - ELF HWCAP documentation updates and clean-up.

   - SMC calling convention conduit code clean-up.

   - KASLR diagnostics printed during boot

   - NVIDIA Carmel CPU added to the KPTI whitelist

   - Some arm64 mm clean-ups: use generic free_initrd_mem(), remove
     stale macro, simplify calculation in __create_pgd_mapping(), typos.

   - Kconfig clean-ups: CMDLINE_FORCE to depend on CMDLINE, choice for
     endinanness to help with allmodconfig"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (93 commits)
  arm64: Kconfig: add a choice for endianness
  kselftest: arm64: fix spelling mistake "contiguos" -> "contiguous"
  arm64: Kconfig: make CMDLINE_FORCE depend on CMDLINE
  MAINTAINERS: Add arm64 selftests to the ARM64 PORT entry
  arm64: kaslr: Check command line before looking for a seed
  arm64: kaslr: Announce KASLR status on boot
  kselftest: arm64: fake_sigreturn_misaligned_sp
  kselftest: arm64: fake_sigreturn_bad_size
  kselftest: arm64: fake_sigreturn_duplicated_fpsimd
  kselftest: arm64: fake_sigreturn_missing_fpsimd
  kselftest: arm64: fake_sigreturn_bad_size_for_magic0
  kselftest: arm64: fake_sigreturn_bad_magic
  kselftest: arm64: add helper get_current_context
  kselftest: arm64: extend test_init functionalities
  kselftest: arm64: mangle_pstate_invalid_mode_el[123][ht]
  kselftest: arm64: mangle_pstate_invalid_daif_bits
  kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils
  kselftest: arm64: extend toplevel skeleton Makefile
  drivers/perf: hisi: update the sccl_id/ccl_id for certain HiSilicon platform
  arm64: mm: reserve CMA and crashkernel in ZONE_DMA32
  ...

22 files changed, 823 insertions, 520 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 478491f07b4f..fc6488660f64 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
-			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
-			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o	\
+			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
+			   setup.o signal.o sys.o stacktrace.o time.o traps.o	\
+			   io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 214685760e1c..a5bdce8af65b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -56,6 +56,7 @@ int main(void)
   DEFINE(S_X24,			offsetof(struct pt_regs, regs[24]));
   DEFINE(S_X26,			offsetof(struct pt_regs, regs[26]));
   DEFINE(S_X28,			offsetof(struct pt_regs, regs[28]));
+  DEFINE(S_FP,			offsetof(struct pt_regs, regs[29]));
   DEFINE(S_LR,			offsetof(struct pt_regs, regs[30]));
   DEFINE(S_SP,			offsetof(struct pt_regs, sp));
   DEFINE(S_PSTATE,		offsetof(struct pt_regs, pstate));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 93f34b4eca25..bbdc95ee4642 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <asm/cpu.h>
@@ -88,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -167,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-#include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 
 static void call_smc_arch_workaround_1(void)
 {
@@ -213,11 +218,8 @@ static int detect_harden_bp_fw(void)
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return -1;
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		switch ((int)res.a0) {
@@ -235,7 +237,7 @@ static int detect_harden_bp_fw(void)
 		}
 		break;
 
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		switch ((int)res.a0) {
@@ -309,11 +311,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 1);
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		insn = aarch64_insn_get_hvc_value();
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		insn = aarch64_insn_get_smc_value();
 		break;
 	default:
@@ -352,12 +354,12 @@ void arm64_set_ssbd_mitigation(bool state)
 		return;
 	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
 		break;
 
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
 		break;
 
@@ -391,20 +393,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		goto out_printmsg;
 	}
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
 		break;
 
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
 		break;
@@ -650,9 +645,21 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
 	return false;
 }
 
-#ifdef CONFIG_HARDEN_EL2_VECTORS
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
 
-static const struct midr_range arm64_harden_el2_vectors[] = {
+#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367)
+
+static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
 	{},
@@ -881,7 +888,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
-		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
+		ERRATA_MIDR_RANGE_LIST(ca57_a72),
 	},
 #endif
 	{
@@ -927,6 +934,23 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1319367
+	{
+		.desc = "ARM erratum 1319367",
+		.capability = ARM64_WORKAROUND_1319367,
+		ERRATA_MIDR_RANGE_LIST(ca57_a72),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 80f459ad0190..04cf64e9f0c9 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -982,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
 		{ /* sentinel */ }
 	};
 	char const *str = "kpti command line option";
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 05933c065732..56bba746da1c 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_cntfrq = arch_timer_get_cntfrq();
 	/*
 	 * Use the effective value of the CTR_EL0 than the raw value
-	 * exposed by the CPU. CTR_E0.IDC field value must be interpreted
+	 * exposed by the CPU. CTR_EL0.IDC field value must be interpreted
 	 * with the CLIDR_EL1 fields to avoid triggering false warnings
 	 * when there is a mismatch across the CPUs. Keep track of the
 	 * effective value of the CTR_EL0 in our internal records for
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
new file mode 100644
index 000000000000..5dce5e56995a
--- /dev/null
+++ b/arch/arm64/kernel/entry-common.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Exception handling code
+ *
+ * Copyright (C) 2019 ARM Ltd.
+ */
+
+#include <linux/context_tracking.h>
+#include <linux/ptrace.h>
+#include <linux/thread_info.h>
+
+#include <asm/cpufeature.h>
+#include <asm/daifflags.h>
+#include <asm/esr.h>
+#include <asm/exception.h>
+#include <asm/kprobes.h>
+#include <asm/mmu.h>
+#include <asm/sysreg.h>
+
+static void notrace el1_abort(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	local_daif_inherit(regs);
+	far = untagged_addr(far);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_abort);
+
+static void notrace el1_pc(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	local_daif_inherit(regs);
+	do_sp_pc_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_pc);
+
+static void el1_undef(struct pt_regs *regs)
+{
+	local_daif_inherit(regs);
+	do_undefinstr(regs);
+}
+NOKPROBE_SYMBOL(el1_undef);
+
+static void el1_inv(struct pt_regs *regs, unsigned long esr)
+{
+	local_daif_inherit(regs);
+	bad_mode(regs, 0, esr);
+}
+NOKPROBE_SYMBOL(el1_inv);
+
+static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	/*
+	 * The CPU masked interrupts, and we are leaving them masked during
+	 * do_debug_exception(). Update PMR as if we had called
+	 * local_mask_daif().
+	 */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	do_debug_exception(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_dbg);
+
+asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_DABT_CUR:
+	case ESR_ELx_EC_IABT_CUR:
+		el1_abort(regs, esr);
+		break;
+	/*
+	 * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a
+	 * recursive exception when trying to push the initial pt_regs.
+	 */
+	case ESR_ELx_EC_PC_ALIGN:
+		el1_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_SYS64:
+	case ESR_ELx_EC_UNKNOWN:
+		el1_undef(regs);
+		break;
+	case ESR_ELx_EC_BREAKPT_CUR:
+	case ESR_ELx_EC_SOFTSTP_CUR:
+	case ESR_ELx_EC_WATCHPT_CUR:
+	case ESR_ELx_EC_BRK64:
+		el1_dbg(regs, esr);
+		break;
+	default:
+		el1_inv(regs, esr);
+	};
+}
+NOKPROBE_SYMBOL(el1_sync_handler);
+
+static void notrace el0_da(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	far = untagged_addr(far);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_da);
+
+static void notrace el0_ia(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	/*
+	 * We've taken an instruction abort from userspace and not yet
+	 * re-enabled IRQs. If the address is a kernel address, apply
+	 * BP hardening prior to enabling IRQs and pre-emption.
+	 */
+	if (!is_ttbr0_addr(far))
+		arm64_apply_bp_hardening();
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_ia);
+
+static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_fpsimd_acc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_fpsimd_acc);
+
+static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sve_acc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sve_acc);
+
+static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_fpsimd_exc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_fpsimd_exc);
+
+static void notrace el0_sys(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sysinstr(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sys);
+
+static void notrace el0_pc(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	if (!is_ttbr0_addr(instruction_pointer(regs)))
+		arm64_apply_bp_hardening();
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sp_pc_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_pc);
+
+static void notrace el0_sp(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	do_sp_pc_abort(regs->sp, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sp);
+
+static void notrace el0_undef(struct pt_regs *regs)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_undefinstr(regs);
+}
+NOKPROBE_SYMBOL(el0_undef);
+
+static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	bad_el0_sync(regs, 0, esr);
+}
+NOKPROBE_SYMBOL(el0_inv);
+
+static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr)
+{
+	/* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */
+	unsigned long far = read_sysreg(far_el1);
+
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	user_exit_irqoff();
+	do_debug_exception(far, esr, regs);
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+}
+NOKPROBE_SYMBOL(el0_dbg);
+
+static void notrace el0_svc(struct pt_regs *regs)
+{
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	el0_svc_handler(regs);
+}
+NOKPROBE_SYMBOL(el0_svc);
+
+asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_SVC64:
+		el0_svc(regs);
+		break;
+	case ESR_ELx_EC_DABT_LOW:
+		el0_da(regs, esr);
+		break;
+	case ESR_ELx_EC_IABT_LOW:
+		el0_ia(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_ASIMD:
+		el0_fpsimd_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_SVE:
+		el0_sve_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_EXC64:
+		el0_fpsimd_exc(regs, esr);
+		break;
+	case ESR_ELx_EC_SYS64:
+	case ESR_ELx_EC_WFx:
+		el0_sys(regs, esr);
+		break;
+	case ESR_ELx_EC_SP_ALIGN:
+		el0_sp(regs, esr);
+		break;
+	case ESR_ELx_EC_PC_ALIGN:
+		el0_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_UNKNOWN:
+		el0_undef(regs);
+		break;
+	case ESR_ELx_EC_BREAKPT_LOW:
+	case ESR_ELx_EC_SOFTSTP_LOW:
+	case ESR_ELx_EC_WATCHPT_LOW:
+	case ESR_ELx_EC_BRK64:
+		el0_dbg(regs, esr);
+		break;
+	default:
+		el0_inv(regs, esr);
+	}
+}
+NOKPROBE_SYMBOL(el0_sync_handler);
+
+#ifdef CONFIG_COMPAT
+static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_cp15instr(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_cp15);
+
+static void notrace el0_svc_compat(struct pt_regs *regs)
+{
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	el0_svc_compat_handler(regs);
+}
+NOKPROBE_SYMBOL(el0_svc_compat);
+
+asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_SVC32:
+		el0_svc_compat(regs);
+		break;
+	case ESR_ELx_EC_DABT_LOW:
+		el0_da(regs, esr);
+		break;
+	case ESR_ELx_EC_IABT_LOW:
+		el0_ia(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_ASIMD:
+		el0_fpsimd_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_EXC32:
+		el0_fpsimd_exc(regs, esr);
+		break;
+	case ESR_ELx_EC_PC_ALIGN:
+		el0_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_UNKNOWN:
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_LS:
+	case ESR_ELx_EC_CP14_64:
+		el0_undef(regs);
+		break;
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+		el0_cp15(regs, esr);
+		break;
+	case ESR_ELx_EC_BREAKPT_LOW:
+	case ESR_ELx_EC_SOFTSTP_LOW:
+	case ESR_ELx_EC_WATCHPT_LOW:
+	case ESR_ELx_EC_BKPT32:
+		el0_dbg(regs, esr);
+		break;
+	default:
+		el0_inv(regs, esr);
+	}
+}
+NOKPROBE_SYMBOL(el0_sync_compat_handler);
+#endif /* CONFIG_COMPAT */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 33d003d80121..4fe1514fcbfd 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -7,10 +7,137 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+/*
+ * 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.
+ *
+ * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are
+ * live, and x9-x18 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.
+ */
+	.macro  ftrace_regs_entry, allregs=0
+	/* Make room for pt_regs, plus a callee frame */
+	sub	sp, sp, #(S_FRAME_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, #(S_FRAME_SIZE + 16)
+	stp	x9, x10, [sp, #S_LR]
+
+	/* Save the PC after the ftrace callsite */
+	str	x30, [sp, #S_PC]
+
+	/* Create a frame record for the callsite above pt_regs */
+	stp	x29, x9, [sp, #S_FRAME_SIZE]
+	add	x29, sp, #S_FRAME_SIZE
+
+	/* Create our frame record within pt_regs. */
+	stp	x29, x30, [sp, #S_STACKFRAME]
+	add	x29, sp, #S_STACKFRAME
+	.endm
+
+ENTRY(ftrace_regs_caller)
+	ftrace_regs_entry	1
+	b	ftrace_common
+ENDPROC(ftrace_regs_caller)
+
+ENTRY(ftrace_caller)
+	ftrace_regs_entry	0
+	b	ftrace_common
+ENDPROC(ftrace_caller)
+
+ENTRY(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
+	mov	x3, sp				// regs
+
+GLOBAL(ftrace_call)
+	bl	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
+	nop				// If enabled, this will be replaced
+					// "b ftrace_graph_caller"
+#endif
+
+/*
+ * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
+ * x19-x29 per the AAPCS, and we created frame records upon entry, so we need
+ * to restore x0-x8, x29, and x30.
+ */
+ftrace_common_return:
+	/* 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]
+
+	/* Restore the callsite's FP, LR, PC */
+	ldr	x29, [sp, #S_FP]
+	ldr	x30, [sp, #S_LR]
+	ldr	x9, [sp, #S_PC]
+
+	/* Restore the callsite's SP */
+	add	sp, sp, #S_FRAME_SIZE + 16
+
+	ret	x9
+ENDPROC(ftrace_common)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	ldr	x0, [sp, #S_PC]
+	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
+	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
+	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	bl	prepare_ftrace_return
+	b	ftrace_common_return
+ENDPROC(ftrace_graph_caller)
+#else
+#endif
+
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
 /*
  * Gcc with -pg will put the following code in the beginning of each function:
  *      mov x0, x30
@@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
 
 	mcount_exit
 ENDPROC(ftrace_caller)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(ftrace_stub)
-	ret
-ENDPROC(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller)
 
 	mcount_exit
 ENDPROC(ftrace_graph_caller)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * void return_to_handler(void)
  *
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index cf3bd2976e57..583f71abbe98 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -269,8 +269,10 @@ alternative_else_nop_endif
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	ldr	x20, [sp, #S_PMR_SAVE]
 	msr_s	SYS_ICC_PMR_EL1, x20
-	/* Ensure priority change is seen by redistributor */
-	dsb	sy
+	mrs_s	x21, SYS_ICC_CTLR_EL1
+	tbz	x21, #6, .L__skip_pmr_sync\@	// Check for ICC_CTLR_EL1.PMHE
+	dsb	sy				// Ensure priority change is seen by redistributor
+.L__skip_pmr_sync\@:
 alternative_else_nop_endif
 
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
@@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid)
 	.align	6
 el1_sync:
 	kernel_entry 1
-	mrs	x1, esr_el1			// read the syndrome register
-	lsr	x24, x1, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_DABT_CUR	// data abort in EL1
-	b.eq	el1_da
-	cmp	x24, #ESR_ELx_EC_IABT_CUR	// instruction abort in EL1
-	b.eq	el1_ia
-	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
-	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el1_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL1
-	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_CUR	// debug exception in EL1
-	b.ge	el1_dbg
-	b	el1_inv
-
-el1_ia:
-	/*
-	 * Fall through to the Data abort case
-	 */
-el1_da:
-	/*
-	 * Data abort handling
-	 */
-	mrs	x3, far_el1
-	inherit_daif	pstate=x23, tmp=x2
-	untagged_addr	x0, x3
-	mov	x2, sp				// struct pt_regs
-	bl	do_mem_abort
-
-	kernel_exit 1
-el1_pc:
-	/*
-	 * PC alignment exception handling. We don't handle SP alignment faults,
-	 * since we will have hit a recursive exception when trying to push the
-	 * initial pt_regs.
-	 */
-	mrs	x0, far_el1
-	inherit_daif	pstate=x23, tmp=x2
-	mov	x2, sp
-	bl	do_sp_pc_abort
-	ASM_BUG()
-el1_undef:
-	/*
-	 * Undefined instruction
-	 */
-	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
-	bl	do_undefinstr
+	bl	el1_sync_handler
 	kernel_exit 1
-el1_dbg:
-	/*
-	 * Debug exception handling
-	 */
-	cmp	x24, #ESR_ELx_EC_BRK64		// if BRK64
-	cinc	x24, x24, eq			// set bit '0'
-	tbz	x24, #0, el1_inv		// EL1 only
-	gic_prio_kentry_setup tmp=x3
-	mrs	x0, far_el1
-	mov	x2, sp				// struct pt_regs
-	bl	do_debug_exception
-	kernel_exit 1
-el1_inv:
-	// TODO: add support for undefined instructions in kernel mode
-	inherit_daif	pstate=x23, tmp=x2
-	mov	x0, sp
-	mov	x2, x1
-	mov	x1, #BAD_SYNC
-	bl	bad_mode
-	ASM_BUG()
 ENDPROC(el1_sync)
 
 	.align	6
@@ -714,71 +649,18 @@ ENDPROC(el1_irq)
 	.align	6
 el0_sync:
 	kernel_entry 0
-	mrs	x25, esr_el1			// read the syndrome register
-	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_SVC64		// SVC in 64-bit state
-	b.eq	el0_svc
-	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
-	b.eq	el0_da
-	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
-	b.eq	el0_ia
-	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
-	b.eq	el0_fpsimd_acc
-	cmp	x24, #ESR_ELx_EC_SVE		// SVE access
-	b.eq	el0_sve_acc
-	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
-	b.eq	el0_fpsimd_exc
-	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
-	ccmp	x24, #ESR_ELx_EC_WFx, #4, ne
-	b.eq	el0_sys
-	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
-	b.eq	el0_sp
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
-	b.ge	el0_dbg
-	b	el0_inv
+	mov	x0, sp
+	bl	el0_sync_handler
+	b	ret_to_user
 
 #ifdef CONFIG_COMPAT
 	.align	6
 el0_sync_compat:
 	kernel_entry 0, 32
-	mrs	x25, esr_el1			// read the syndrome register
-	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_SVC32		// SVC in 32-bit state
-	b.eq	el0_svc_compat
-	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
-	b.eq	el0_da
-	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
-	b.eq	el0_ia
-	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
-	b.eq	el0_fpsimd_acc
-	cmp	x24, #ESR_ELx_EC_FP_EXC32	// FP/ASIMD exception
-	b.eq	el0_fpsimd_exc
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP15_32	// CP15 MRC/MCR trap
-	b.eq	el0_cp15
-	cmp	x24, #ESR_ELx_EC_CP15_64	// CP15 MRRC/MCRR trap
-	b.eq	el0_cp15
-	cmp	x24, #ESR_ELx_EC_CP14_MR	// CP14 MRC/MCR trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP14_LS	// CP14 LDC/STC trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP14_64	// CP14 MRRC/MCRR trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
-	b.ge	el0_dbg
-	b	el0_inv
-el0_svc_compat:
-	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
-	bl	el0_svc_compat_handler
+	bl	el0_sync_compat_handler
 	b	ret_to_user
+ENDPROC(el0_sync)
 
 	.align	6
 el0_irq_compat:
@@ -788,139 +670,7 @@ el0_irq_compat:
 el0_error_compat:
 	kernel_entry 0, 32
 	b	el0_error_naked
-
-el0_cp15:
-	/*
-	 * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_cp15instr
-	b	ret_to_user
-#endif
-
-el0_da:
-	/*
-	 * Data abort handling
-	 */
-	mrs	x26, far_el1
-	ct_user_exit_irqoff
-	enable_daif
-	untagged_addr	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_mem_abort
-	b	ret_to_user
-el0_ia:
-	/*
-	 * Instruction abort handling
-	 */
-	mrs	x26, far_el1
-	gic_prio_kentry_setup tmp=x0
-	ct_user_exit_irqoff
-	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
-	mov	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_el0_ia_bp_hardening
-	b	ret_to_user
-el0_fpsimd_acc:
-	/*
-	 * Floating Point or Advanced SIMD access
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_fpsimd_acc
-	b	ret_to_user
-el0_sve_acc:
-	/*
-	 * Scalable Vector Extension access
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_sve_acc
-	b	ret_to_user
-el0_fpsimd_exc:
-	/*
-	 * Floating Point, Advanced SIMD or SVE exception
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_fpsimd_exc
-	b	ret_to_user
-el0_sp:
-	ldr	x26, [sp, #S_SP]
-	b	el0_sp_pc
-el0_pc:
-	mrs	x26, far_el1
-el0_sp_pc:
-	/*
-	 * Stack or PC alignment exception handling
-	 */
-	gic_prio_kentry_setup tmp=x0
-	ct_user_exit_irqoff
-	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
 #endif
-	mov	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_sp_pc_abort
-	b	ret_to_user
-el0_undef:
-	/*
-	 * Undefined instruction
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, sp
-	bl	do_undefinstr
-	b	ret_to_user
-el0_sys:
-	/*
-	 * System instructions, for trapped cache maintenance instructions
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_sysinstr
-	b	ret_to_user
-el0_dbg:
-	/*
-	 * Debug exception handling
-	 */
-	tbnz	x24, #0, el0_inv		// EL0 only
-	mrs	x24, far_el1
-	gic_prio_kentry_setup tmp=x3
-	ct_user_exit_irqoff
-	mov	x0, x24
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_debug_exception
-	enable_da_f
-	b	ret_to_user
-el0_inv:
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, sp
-	mov	x1, #BAD_SYNC
-	mov	x2, x25
-	bl	bad_el0_sync
-	b	ret_to_user
-ENDPROC(el0_sync)
 
 	.align	6
 el0_irq:
@@ -999,17 +749,6 @@ finish_ret_to_user:
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
-/*
- * SVC handler.
- */
-	.align	6
-el0_svc:
-	gic_prio_kentry_setup tmp=x1
-	mov	x0, sp
-	bl	el0_svc_handler
-	b	ret_to_user
-ENDPROC(el0_svc)
-
 	.popsection				// .entry.text
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 37d3912cfe06..3eb338f14386 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task)
  * would have disabled the SVE access trap for userspace during
  * ret_to_user, making an SVE access trap impossible in that case.
  */
-asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* Even if we chose not to use SVE, the hardware could still trap: */
 	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
@@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Trapped FP/ASIMD access.
  */
-asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* TODO: implement lazy context saving/restoring */
 	WARN_ON(1);
@@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Raise a SIGFPE for the current process.
  */
-asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
 	unsigned int si_code = FPE_FLTUNK;
 
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 06e56b470315..8618faa82e6d 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(pc, 0, new, false);
 }
 
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
+{
+#ifdef CONFIG_ARM64_MODULE_PLTS
+	struct plt_entry *plt = mod->arch.ftrace_trampolines;
+
+	if (addr == FTRACE_ADDR)
+		return &plt[FTRACE_PLT_IDX];
+	if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS))
+		return &plt[FTRACE_REGS_PLT_IDX];
+#endif
+	return NULL;
+}
+
 /*
  * Turn on the call to ftrace_caller() in instrumented function
  */
@@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	long offset = (long)pc - (long)addr;
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
-#ifdef CONFIG_ARM64_MODULE_PLTS
-		struct plt_entry trampoline, *dst;
 		struct module *mod;
+		struct plt_entry *plt;
+
+		if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+			return -EINVAL;
 
 		/*
 		 * On kernels that support module PLTs, the offset between the
@@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		if (WARN_ON(!mod))
 			return -EINVAL;
 
-		/*
-		 * There is only one ftrace trampoline per module. For now,
-		 * this is not a problem since on arm64, all dynamic ftrace
-		 * invocations are routed via ftrace_caller(). This will need
-		 * to be revisited if support for multiple ftrace entry points
-		 * is added in the future, but for now, the pr_err() below
-		 * deals with a theoretical issue only.
-		 *
-		 * Note that PLTs are place relative, and plt_entries_equal()
-		 * checks whether they point to the same target. Here, we need
-		 * to check if the actual opcodes are in fact identical,
-		 * regardless of the offset in memory so use memcmp() instead.
-		 */
-		dst = mod->arch.ftrace_trampoline;
-		trampoline = get_plt_entry(addr, dst);
-		if (memcmp(dst, &trampoline, sizeof(trampoline))) {
-			if (plt_entry_is_initialized(dst)) {
-				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
-				return -EINVAL;
-			}
-
-			/* point the trampoline to our ftrace entry point */
-			module_disable_ro(mod);
-			*dst = trampoline;
-			module_enable_ro(mod, true);
-
-			/*
-			 * Ensure updated trampoline is visible to instruction
-			 * fetch before we patch in the branch. Although the
-			 * architecture doesn't require an IPI in this case,
-			 * Neoverse-N1 erratum #1542419 does require one
-			 * if the TLB maintenance in module_enable_ro() is
-			 * skipped due to rodata_enabled. It doesn't seem worth
-			 * it to make it conditional given that this is
-			 * certainly not a fast-path.
-			 */
-			flush_icache_range((unsigned long)&dst[0],
-					   (unsigned long)&dst[1]);
+		plt = get_ftrace_plt(mod, addr);
+		if (!plt) {
+			pr_err("ftrace: no module PLT for %ps\n", (void *)addr);
+			return -EINVAL;
 		}
-		addr = (unsigned long)dst;
-#else /* CONFIG_ARM64_MODULE_PLTS */
-		return -EINVAL;
-#endif /* CONFIG_ARM64_MODULE_PLTS */
+
+		addr = (unsigned long)plt;
 	}
 
 	old = aarch64_insn_gen_nop();
@@ -144,6 +123,55 @@ 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;
+
+	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);
+}
+
+/*
+ * 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,
+ * and x9-x18 are free for our use.
+ *
+ * At runtime we want to be able to swing a single NOP <-> BL to enable or
+ * disable the ftrace call. The BL requires us to save the original LR value,
+ * so here we insert a <MOV X9, LR> over the first NOP so the instructions
+ * before the regular prologue are:
+ *
+ * | Compiled | Disabled   | Enabled    |
+ * +----------+------------+------------+
+ * | NOP      | MOV X9, LR | MOV X9, LR |
+ * | NOP      | NOP        | BL <entry> |
+ *
+ * The LR value will be recovered by ftrace_regs_entry, and restored into LR
+ * before returning to the regular function prologue. When a function is not
+ * being traced, the MOV is not harmful given x9 is not live per the AAPCS.
+ *
+ * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of
+ * the BL.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
+					AARCH64_INSN_REG_LR,
+					AARCH64_INSN_VARIANT_64BIT);
+	return ftrace_modify_code(pc, old, new, true);
+}
+#endif
+
 /*
  * Turn off the call to ftrace_caller() in instrumented function
  */
@@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	long offset = (long)pc - (long)addr;
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
-#ifdef CONFIG_ARM64_MODULE_PLTS
 		u32 replaced;
 
+		if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+			return -EINVAL;
+
 		/*
 		 * 'mod' is only set at module load time, but if we end up
 		 * dealing with an out-of-range condition, we can assume it
@@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 			return -EINVAL;
 
 		validate = false;
-#else /* CONFIG_ARM64_MODULE_PLTS */
-		return -EINVAL;
-#endif /* CONFIG_ARM64_MODULE_PLTS */
 	} else {
 		old = aarch64_insn_gen_branch_imm(pc, addr,
 						  AARCH64_INSN_BRANCH_LINK);
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index d801a7094076..513b29c3e735 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }
 
+/*
+ * MOV (register) is architecturally an alias of ORR (shifted register) where
+ * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m>
+ */
+u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant)
+{
+	return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR,
+						    src, 0, variant,
+						    AARCH64_INSN_LOGIC_ORR);
+}
+
 u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr,
 			 enum aarch64_insn_register reg,
 			 enum aarch64_insn_adr_type type)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 416f537bf614..2a11a962e571 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -19,6 +19,14 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 
+enum kaslr_status {
+	KASLR_ENABLED,
+	KASLR_DISABLED_CMDLINE,
+	KASLR_DISABLED_NO_SEED,
+	KASLR_DISABLED_FDT_REMAP,
+};
+
+static enum kaslr_status __initdata kaslr_status;
 u64 __ro_after_init module_alloc_base;
 u16 __initdata memstart_offset_seed;
 
@@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 */
 	early_fixmap_init();
 	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
-	if (!fdt)
+	if (!fdt) {
+		kaslr_status = KASLR_DISABLED_FDT_REMAP;
 		return 0;
+	}
 
 	/*
 	 * Retrieve (and wipe) the seed from the FDT
 	 */
 	seed = get_kaslr_seed(fdt);
-	if (!seed)
-		return 0;
 
 	/*
 	 * Check if 'nokaslr' appears on the command line, and
@@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 */
 	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
-	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
+	if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) {
+		kaslr_status = KASLR_DISABLED_CMDLINE;
+		return 0;
+	}
+
+	if (!seed) {
+		kaslr_status = KASLR_DISABLED_NO_SEED;
 		return 0;
+	}
 
 	/*
 	 * OK, so we are proceeding with KASLR enabled. Calculate a suitable
@@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys)
 
 	return offset;
 }
+
+static int __init kaslr_init(void)
+{
+	switch (kaslr_status) {
+	case KASLR_ENABLED:
+		pr_info("KASLR enabled\n");
+		break;
+	case KASLR_DISABLED_CMDLINE:
+		pr_info("KASLR disabled on command line\n");
+		break;
+	case KASLR_DISABLED_NO_SEED:
+		pr_warn("KASLR disabled due to lack of seed\n");
+		break;
+	case KASLR_DISABLED_FDT_REMAP:
+		pr_warn("KASLR disabled due to FDT remapping failure\n");
+		break;
+	}
+
+	return 0;
+}
+core_initcall(kaslr_init)
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index b182442b87a3..65b08a74aec6 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sort.h>
@@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		tramp->sh_type = SHT_NOBITS;
 		tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
 		tramp->sh_addralign = __alignof__(struct plt_entry);
-		tramp->sh_size = sizeof(struct plt_entry);
+		tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 03ff15bffbb6..1cd1a4d0ed30 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -9,6 +9,7 @@
 
 #include <linux/bitops.h>
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/gfp.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
@@ -470,22 +471,58 @@ overflow:
 	return -ENOEXEC;
 }
 
-int module_finalize(const Elf_Ehdr *hdr,
-		    const Elf_Shdr *sechdrs,
-		    struct module *me)
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+				    const Elf_Shdr *sechdrs,
+				    const char *name)
 {
 	const Elf_Shdr *s, *se;
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
-		if (strcmp(".altinstructions", secstrs + s->sh_name) == 0)
-			apply_alternatives_module((void *)s->sh_addr, s->sh_size);
-#ifdef CONFIG_ARM64_MODULE_PLTS
-		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
-		    !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
-			me->arch.ftrace_trampoline = (void *)s->sh_addr;
-#endif
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
 	}
 
+	return NULL;
+}
+
+static inline void __init_plt(struct plt_entry *plt, unsigned long addr)
+{
+	*plt = get_plt_entry(addr, plt);
+}
+
+static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
+				  const Elf_Shdr *sechdrs,
+				  struct module *mod)
+{
+#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)
+	const Elf_Shdr *s;
+	struct plt_entry *plts;
+
+	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");
+	if (!s)
+		return -ENOEXEC;
+
+	plts = (void *)s->sh_addr;
+
+	__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;
 }
+
+int module_finalize(const Elf_Ehdr *hdr,
+		    const Elf_Shdr *sechdrs,
+		    struct module *me)
+{
+	const Elf_Shdr *s;
+	s = find_section(hdr, sechdrs, ".altinstructions");
+	if (s)
+		apply_alternatives_module((void *)s->sh_addr, s->sh_size);
+
+	return module_init_ftrace_plt(hdr, sechdrs, me);
+}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index a0b4f1bca491..e40b65645c86 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
 }
 
-#define ARMV8_EVENT_ATTR(name, config) \
-	PMU_EVENT_ATTR(name, armv8_event_attr_##name, \
-		       config, armv8pmu_events_sysfs_show)
-
-ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR);
-ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL);
-ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE);
-ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL);
-ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED);
-ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED);
-ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED);
-ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN);
-ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN);
-ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED);
-ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED);
-ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED);
-ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED);
-ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES);
-ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED);
-ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS);
-ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE);
-ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB);
-ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE);
-ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB);
-ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS);
-ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR);
-ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC);
-ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES);
-/* Don't expose the chain event in /sys, since it's useless in isolation */
-ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED);
-ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED);
-ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND);
-ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND);
-ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB);
-ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB);
-ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE);
-ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE);
-ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB);
-ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL);
-ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL);
-ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB);
-ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB);
-ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS);
-ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE);
-ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS);
-ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK);
-ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK);
-ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD);
-ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD);
-ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD);
-ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP);
-ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED);
-ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE);
-ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION);
+#define ARMV8_EVENT_ATTR(name, config)						\
+	(&((struct perf_pmu_events_attr) {					\
+		.attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL),	\
+		.id = config,							\
+	}).attr.attr)
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
-	&armv8_event_attr_sw_incr.attr.attr,
-	&armv8_event_attr_l1i_cache_refill.attr.attr,
-	&armv8_event_attr_l1i_tlb_refill.attr.attr,
-	&armv8_event_attr_l1d_cache_refill.attr.attr,
-	&armv8_event_attr_l1d_cache.attr.attr,
-	&armv8_event_attr_l1d_tlb_refill.attr.attr,
-	&armv8_event_attr_ld_retired.attr.attr,
-	&armv8_event_attr_st_retired.attr.attr,
-	&armv8_event_attr_inst_retired.attr.attr,
-	&armv8_event_attr_exc_taken.attr.attr,
-	&armv8_event_attr_exc_return.attr.attr,
-	&armv8_event_attr_cid_write_retired.attr.attr,
-	&armv8_event_attr_pc_write_retired.attr.attr,
-	&armv8_event_attr_br_immed_retired.attr.attr,
-	&armv8_event_attr_br_return_retired.attr.attr,
-	&armv8_event_attr_unaligned_ldst_retired.attr.attr,
-	&armv8_event_attr_br_mis_pred.attr.attr,
-	&armv8_event_attr_cpu_cycles.attr.attr,
-	&armv8_event_attr_br_pred.attr.attr,
-	&armv8_event_attr_mem_access.attr.attr,
-	&armv8_event_attr_l1i_cache.attr.attr,
-	&armv8_event_attr_l1d_cache_wb.attr.attr,
-	&armv8_event_attr_l2d_cache.attr.attr,
-	&armv8_event_attr_l2d_cache_refill.attr.attr,
-	&armv8_event_attr_l2d_cache_wb.attr.attr,
-	&armv8_event_attr_bus_access.attr.attr,
-	&armv8_event_attr_memory_error.attr.attr,
-	&armv8_event_attr_inst_spec.attr.attr,
-	&armv8_event_attr_ttbr_write_retired.attr.attr,
-	&armv8_event_attr_bus_cycles.attr.attr,
-	&armv8_event_attr_l1d_cache_allocate.attr.attr,
-	&armv8_event_attr_l2d_cache_allocate.attr.attr,
-	&armv8_event_attr_br_retired.attr.attr,
-	&armv8_event_attr_br_mis_pred_retired.attr.attr,
-	&armv8_event_attr_stall_frontend.attr.attr,
-	&armv8_event_attr_stall_backend.attr.attr,
-	&armv8_event_attr_l1d_tlb.attr.attr,
-	&armv8_event_attr_l1i_tlb.attr.attr,
-	&armv8_event_attr_l2i_cache.attr.attr,
-	&armv8_event_attr_l2i_cache_refill.attr.attr,
-	&armv8_event_attr_l3d_cache_allocate.attr.attr,
-	&armv8_event_attr_l3d_cache_refill.attr.attr,
-	&armv8_event_attr_l3d_cache.attr.attr,
-	&armv8_event_attr_l3d_cache_wb.attr.attr,
-	&armv8_event_attr_l2d_tlb_refill.attr.attr,
-	&armv8_event_attr_l2i_tlb_refill.attr.attr,
-	&armv8_event_attr_l2d_tlb.attr.attr,
-	&armv8_event_attr_l2i_tlb.attr.attr,
-	&armv8_event_attr_remote_access.attr.attr,
-	&armv8_event_attr_ll_cache.attr.attr,
-	&armv8_event_attr_ll_cache_miss.attr.attr,
-	&armv8_event_attr_dtlb_walk.attr.attr,
-	&armv8_event_attr_itlb_walk.attr.attr,
-	&armv8_event_attr_ll_cache_rd.attr.attr,
-	&armv8_event_attr_ll_cache_miss_rd.attr.attr,
-	&armv8_event_attr_remote_access_rd.attr.attr,
-	&armv8_event_attr_sample_pop.attr.attr,
-	&armv8_event_attr_sample_feed.attr.attr,
-	&armv8_event_attr_sample_filtrate.attr.attr,
-	&armv8_event_attr_sample_collision.attr.attr,
+	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
+	ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE),
+	ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED),
+	ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED),
+	ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED),
+	ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN),
+	ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN),
+	ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED),
+	ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED),
+	ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED),
+	ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES),
+	ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED),
+	ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS),
+	ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE),
+	ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE),
+	ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB),
+	ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS),
+	ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR),
+	ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC),
+	ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES),
+	/* Don't expose the chain event in /sys, since it's useless in isolation */
+	ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED),
+	ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND),
+	ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB),
+	ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB),
+	ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE),
+	ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE),
+	ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB),
+	ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB),
+	ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS),
+	ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE),
+	ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS),
+	ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK),
+	ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK),
+	ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
+	ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
+	ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+	ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
+	ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
+	ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
+	ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
 	NULL,
 };
 
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c4452827419b..d1c95dcf1d78 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void)
 					(unsigned long)__irqentry_text_end);
 	if (ret)
 		return ret;
-	ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start,
-					(unsigned long)__exception_text_end);
-	if (ret)
-		return ret;
 	ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start,
 					(unsigned long)__idmap_text_end);
 	if (ret)
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index c9f72b2665f1..43ae4e0c968f 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 
 static int cpu_psci_cpu_kill(unsigned int cpu)
 {
-	int err, i;
+	int err;
+	unsigned long start, end;
 
 	if (!psci_ops.affinity_info)
 		return 0;
@@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	 * while it is dying. So, try again a few times.
 	 */
 
-	for (i = 0; i < 10; i++) {
+	start = jiffies;
+	end = start + msecs_to_jiffies(100);
+	do {
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
-			pr_info("CPU%d killed.\n", cpu);
+			pr_info("CPU%d killed (polled %d ms)\n", cpu,
+				jiffies_to_msecs(jiffies - start));
 			return 0;
 		}
 
-		msleep(10);
-		pr_info("Retrying again to check for CPU kill\n");
-	}
+		usleep_range(100, 1000);
+	} while (time_before(jiffies, end));
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index ea94cf8f9dc6..d6259dac62b6 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2017 Arm Ltd.
 #define pr_fmt(fmt) "sdei: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/arm_sdei.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
@@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 			return 0;
 	}
 
-	sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+	sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	if (arm64_kernel_unmapped_at_el0()) {
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f1cb64959427..3c18c2454089 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 871c739f060a..9a9d98a443fc 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -154,14 +154,14 @@ static inline void sve_user_discard(void)
 	sve_user_disable();
 }
 
-asmlinkage void el0_svc_handler(struct pt_regs *regs)
+void el0_svc_handler(struct pt_regs *regs)
 {
 	sve_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
 #ifdef CONFIG_COMPAT
-asmlinkage void el0_svc_compat_handler(struct pt_regs *regs)
+void el0_svc_compat_handler(struct pt_regs *regs)
 {
 	el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
 		       compat_sys_call_table);
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 34739e80211b..73caf35c2262 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -35,6 +35,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/insn.h>
+#include <asm/kprobes.h>
 #include <asm/traps.h>
 #include <asm/smp.h>
 #include <asm/stack_pointer.h>
@@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr)
 	force_signal_inject(SIGSEGV, code, addr);
 }
 
-asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
+void do_undefinstr(struct pt_regs *regs)
 {
 	/* check for AArch32 breakpoint instructions */
 	if (!aarch32_break_handler(regs))
@@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	BUG_ON(!user_mode(regs));
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
 }
+NOKPROBE_SYMBOL(do_undefinstr);
 
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
@@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
@@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = {
 	{},
 };
 
-asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
+void do_cp15instr(unsigned int esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook, *hook_base;
 
@@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
 	 */
 	do_undefinstr(regs);
 }
+NOKPROBE_SYMBOL(do_cp15instr);
 #endif
 
-asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+void do_sysinstr(unsigned int esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook;
 
@@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 	 */
 	do_undefinstr(regs);
 }
+NOKPROBE_SYMBOL(do_sysinstr);
 
 static const char *esr_class_str[] = {
 	[0 ... ESR_ELx_EC_MAX]		= "UNRECOGNIZED EC",
@@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
  * bad_el0_sync handles unexpected, but potentially recoverable synchronous
  * exceptions taken from EL0. Unlike bad_mode, this returns.
  */
-asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
 	void __user *pc = (void __user *)instruction_pointer(regs);
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index aa76f7259668..009057517bdd 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -111,9 +111,6 @@ SECTIONS
 	}
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
-			__exception_text_start = .;
-			*(.exception.text)
-			__exception_text_end = .;
 			IRQENTRY_TEXT
 			SOFTIRQENTRY_TEXT
 			ENTRY_TEXT