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

Pull arm64 festive updates from Will Deacon: "In the end, we ended up with quite a lot more than I expected: - Support for ARMv8.3 Pointer Authentication in userspace (CRIU and kernel-side support to come later) - Support for per-thread stack canaries, pending an update to GCC that is currently undergoing review - Support for kexec_file_load(), which permits secure boot of a kexec payload but also happens to improve the performance of kexec dramatically because we can avoid the sucky purgatory code from userspace. Kdump will come later (requires updates to libfdt). - Optimisation of our dynamic CPU feature framework, so that all detected features are enabled via a single stop_machine() invocation - KPTI whitelisting of Cortex-A CPUs unaffected by Meltdown, so that they can benefit from global TLB entries when KASLR is not in use - 52-bit virtual addressing for userspace (kernel remains 48-bit) - Patch in LSE atomics for per-cpu atomic operations - Custom preempt.h implementation to avoid unconditional calls to preempt_schedule() from preempt_enable() - Support for the new 'SB' Speculation Barrier instruction - Vectorised implementation of XOR checksumming and CRC32 optimisations - Workaround for Cortex-A76 erratum #1165522 - Improved compatibility with Clang/LLD - Support for TX2 system PMUS for profiling the L3 cache and DMC - Reflect read-only permissions in the linear map by default - Ensure MMIO reads are ordered with subsequent calls to Xdelay() - Initial support for memory hotplug - Tweak the threshold when we invalidate the TLB by-ASID, so that mremap() performance is improved for ranges spanning multiple PMDs. - Minor refactoring and cleanups" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (125 commits) arm64: kaslr: print PHYS_OFFSET in dump_kernel_offset() arm64: sysreg: Use _BITUL() when defining register bits arm64: cpufeature: Rework ptr auth hwcaps using multi_entry_cap_matches arm64: cpufeature: Reduce number of pointer auth CPU caps from 6 to 4 arm64: docs: document pointer authentication arm64: ptr auth: Move per-thread keys from thread_info to thread_struct arm64: enable pointer authentication arm64: add prctl control for resetting ptrauth keys arm64: perf: strip PAC when unwinding userspace arm64: expose user PAC bit positions via ptrace arm64: add basic pointer authentication support arm64/cpufeature: detect pointer authentication arm64: Don't trap host pointer auth use to EL2 arm64/kvm: hide ptrauth from guests arm64/kvm: consistently handle host HCR_EL2 flags arm64: add pointer authentication register bits arm64: add comments about EC exception levels arm64: perf: Treat EXCLUDE_EL* bit definitions as unsigned arm64: kpti: Whitelist Cortex-A CPUs that don't implement the CSV3 field arm64: enable per-task stack canaries ...
2018-12-25 17:41:56 -08:00
parent 13e1ad2be3 12f799c8c7
commit 5694cecdb0
138 changed files with 4288 additions and 1198 deletions
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -30,7 +30,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
-arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
+arm64-obj-$(CONFIG_MODULES)		+= module.o
 arm64-obj-$(CONFIG_ARM64_MODULE_PLTS)	+= module-plts.o
 arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
@@ -49,14 +49,16 @@ arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
 arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
-arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
+arm64-obj-$(CONFIG_KEXEC_CORE)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
+arm64-obj-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o kexec_image.o
 arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 arm64-obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 arm64-obj-$(CONFIG_ARM_SDE_INTERFACE)	+= sdei.o
 arm64-obj-$(CONFIG_ARM64_SSBD)		+= ssbd.o
+arm64-obj-$(CONFIG_ARM64_PTR_AUTH)	+= pointer_auth.o

 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -1,88 +0,0 @@
-/*
- * Based on arch/arm/kernel/armksyms.c
- *
- * Copyright (C) 2000 Russell King
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/export.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/cryptohash.h>
-#include <linux/delay.h>
-#include <linux/in6.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <linux/io.h>
-#include <linux/arm-smccc.h>
-#include <linux/kprobes.h>
-
-#include <asm/checksum.h>
-
-EXPORT_SYMBOL(copy_page);
-EXPORT_SYMBOL(clear_page);
-
-	/* user mem (segment) */
-EXPORT_SYMBOL(__arch_copy_from_user);
-EXPORT_SYMBOL(__arch_copy_to_user);
-EXPORT_SYMBOL(__arch_clear_user);
-EXPORT_SYMBOL(__arch_copy_in_user);
-
-	/* physical memory */
-EXPORT_SYMBOL(memstart_addr);
-
-	/* string / mem functions */
-#ifndef CONFIG_KASAN
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strncmp);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strnlen);
-EXPORT_SYMBOL(memcmp);
-EXPORT_SYMBOL(memchr);
-#endif
-
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memcpy);
-EXPORT_SYMBOL(__memmove);
-
-	/* atomic bitops */
-EXPORT_SYMBOL(set_bit);
-EXPORT_SYMBOL(test_and_set_bit);
-EXPORT_SYMBOL(clear_bit);
-EXPORT_SYMBOL(test_and_clear_bit);
-EXPORT_SYMBOL(change_bit);
-EXPORT_SYMBOL(test_and_change_bit);
-
-#ifdef CONFIG_FUNCTION_TRACER
-EXPORT_SYMBOL(_mcount);
-NOKPROBE_SYMBOL(_mcount);
-#endif
-
-	/* arm-smccc */
-EXPORT_SYMBOL(__arm_smccc_smc);
-EXPORT_SYMBOL(__arm_smccc_hvc);
-
-	/* tishift.S */
-extern long long __ashlti3(long long a, int b);
-EXPORT_SYMBOL(__ashlti3);
-extern long long __ashrti3(long long a, int b);
-EXPORT_SYMBOL(__ashrti3);
-extern long long __lshrti3(long long a, int b);
-EXPORT_SYMBOL(__lshrti3);
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -46,6 +46,9 @@ int main(void)
  DEFINE(TSK_TI_TTBR0,		offsetof(struct task_struct, thread_info.ttbr0));
 #endif
  DEFINE(TSK_STACK,		offsetof(struct task_struct, stack));
+#ifdef CONFIG_STACKPROTECTOR
+  DEFINE(TSK_STACK_CANARY,	offsetof(struct task_struct, stack_canary));
+#endif
  BLANK();
  DEFINE(THREAD_CPU_CONTEXT,	offsetof(struct task_struct, thread.cpu_context));
  BLANK();
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -22,11 +22,11 @@
 * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
 * cpu_soft_restart.
 *
- * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @el2_switch: Flag to indicate a switch to EL2 is needed.
 * @entry: Location to jump to for soft reset.
- * arg0: First argument passed to @entry.
- * arg1: Second argument passed to @entry.
- * arg2: Third argument passed to @entry.
+ * arg0: First argument passed to @entry. (relocation list)
+ * arg1: Second argument passed to @entry.(physical kernel entry)
+ * arg2: Third argument passed to @entry. (physical dtb address)
 *
 * Put the CPU into the same state as it would be if it had been reset, and
 * branch to what would be the reset vector. It must be executed with the
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -135,7 +135,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
 {
-	static DEFINE_SPINLOCK(bp_lock);
+	static DEFINE_RAW_SPINLOCK(bp_lock);
 	int cpu, slot = -1;

 	/*
@@ -147,7 +147,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 		return;
 	}

-	spin_lock(&bp_lock);
+	raw_spin_lock(&bp_lock);
 	for_each_possible_cpu(cpu) {
 		if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
 			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
@@ -163,7 +163,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,

 	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
 	__this_cpu_write(bp_hardening_data.fn, fn);
-	spin_unlock(&bp_lock);
+	raw_spin_unlock(&bp_lock);
 }
 #else
 #define __smccc_workaround_1_smc_start		NULL
@@ -507,38 +507,6 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
 	.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,			\
 	CAP_MIDR_RANGE_LIST(midr_list)

-/*
- * Generic helper for handling capabilties with multiple (match,enable) pairs
- * of call backs, sharing the same capability bit.
- * Iterate over each entry to see if at least one matches.
- */
-static bool __maybe_unused
-multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, int scope)
-{
-	const struct arm64_cpu_capabilities *caps;
-
-	for (caps = entry->match_list; caps->matches; caps++)
-		if (caps->matches(caps, scope))
-			return true;
-
-	return false;
-}
-
-/*
- * Take appropriate action for all matching entries in the shared capability
- * entry.
- */
-static void __maybe_unused
-multi_entry_cap_cpu_enable(const struct arm64_cpu_capabilities *entry)
-{
-	const struct arm64_cpu_capabilities *caps;
-
-	for (caps = entry->match_list; caps->matches; caps++)
-		if (caps->matches(caps, SCOPE_LOCAL_CPU) &&
-		    caps->cpu_enable)
-			caps->cpu_enable(caps);
-}
-
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR

 /*
@@ -584,24 +552,63 @@ static const struct midr_range arm64_repeat_tlbi_cpus[] = {

 #endif

-const struct arm64_cpu_capabilities arm64_errata[] = {
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+static const struct midr_range cavium_erratum_27456_cpus[] = {
+	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+	MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+	/* Cavium ThunderX, T81 pass 1.0 */
+	MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+	{},
+};
+#endif
+
+#ifdef CONFIG_CAVIUM_ERRATUM_30115
+static const struct midr_range cavium_erratum_30115_cpus[] = {
+	/* Cavium ThunderX, T88 pass 1.x - 2.2 */
+	MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 2),
+	/* Cavium ThunderX, T81 pass 1.0 - 1.2 */
+	MIDR_REV_RANGE(MIDR_THUNDERX_81XX, 0, 0, 2),
+	/* Cavium ThunderX, T83 pass 1.0 */
+	MIDR_REV(MIDR_THUNDERX_83XX, 0, 0),
+	{},
+};
+#endif
+
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+static const struct arm64_cpu_capabilities qcom_erratum_1003_list[] = {
+	{
+		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0),
+	},
+	{
+		.midr_range.model = MIDR_QCOM_KRYO,
+		.matches = is_kryo_midr,
+	},
+	{},
+};
+#endif
+
+#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
+static const struct midr_range workaround_clean_cache[] = {
 #if	defined(CONFIG_ARM64_ERRATUM_826319) || \
 	defined(CONFIG_ARM64_ERRATUM_827319) || \
 	defined(CONFIG_ARM64_ERRATUM_824069)
-	{
-	/* Cortex-A53 r0p[012] */
-		.desc = "ARM errata 826319, 827319, 824069",
-		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 2),
-		.cpu_enable = cpu_enable_cache_maint_trap,
-	},
+	/* Cortex-A53 r0p[012]: ARM errata 826319, 827319, 824069 */
+	MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 2),
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_819472
+#ifdef	CONFIG_ARM64_ERRATUM_819472
+	/* Cortex-A53 r0p[01] : ARM errata 819472 */
+	MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 1),
+#endif
+	{},
+};
+#endif
+
+const struct arm64_cpu_capabilities arm64_errata[] = {
+#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
-	/* Cortex-A53 r0p[01] */
-		.desc = "ARM errata 819472",
+		.desc = "ARM errata 826319, 827319, 824069, 819472",
 		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 1),
+		ERRATA_MIDR_RANGE_LIST(workaround_clean_cache),
 		.cpu_enable = cpu_enable_cache_maint_trap,
 	},
 #endif
@@ -652,40 +659,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #endif
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
 	{
-	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
 		.desc = "Cavium erratum 27456",
 		.capability = ARM64_WORKAROUND_CAVIUM_27456,
-		ERRATA_MIDR_RANGE(MIDR_THUNDERX,
-				  0, 0,
-				  1, 1),
-	},
-	{
-	/* Cavium ThunderX, T81 pass 1.0 */
-		.desc = "Cavium erratum 27456",
-		.capability = ARM64_WORKAROUND_CAVIUM_27456,
-		ERRATA_MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+		ERRATA_MIDR_RANGE_LIST(cavium_erratum_27456_cpus),
 	},
 #endif
 #ifdef CONFIG_CAVIUM_ERRATUM_30115
 	{
-	/* Cavium ThunderX, T88 pass 1.x - 2.2 */
 		.desc = "Cavium erratum 30115",
 		.capability = ARM64_WORKAROUND_CAVIUM_30115,
-		ERRATA_MIDR_RANGE(MIDR_THUNDERX,
-				      0, 0,
-				      1, 2),
-	},
-	{
-	/* Cavium ThunderX, T81 pass 1.0 - 1.2 */
-		.desc = "Cavium erratum 30115",
-		.capability = ARM64_WORKAROUND_CAVIUM_30115,
-		ERRATA_MIDR_REV_RANGE(MIDR_THUNDERX_81XX, 0, 0, 2),
-	},
-	{
-	/* Cavium ThunderX, T83 pass 1.0 */
-		.desc = "Cavium erratum 30115",
-		.capability = ARM64_WORKAROUND_CAVIUM_30115,
-		ERRATA_MIDR_REV(MIDR_THUNDERX_83XX, 0, 0),
+		ERRATA_MIDR_RANGE_LIST(cavium_erratum_30115_cpus),
 	},
 #endif
 	{
@@ -697,16 +680,10 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	},
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
 	{
-		.desc = "Qualcomm Technologies Falkor erratum 1003",
+		.desc = "Qualcomm Technologies Falkor/Kryo erratum 1003",
 		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
-		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0),
-	},
-	{
-		.desc = "Qualcomm Technologies Kryo erratum 1003",
-		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
-		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
-		.midr_range.model = MIDR_QCOM_KRYO,
-		.matches = is_kryo_midr,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = qcom_erratum_1003_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
@@ -753,6 +730,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_1188873,
 		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
 	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1165522
+	{
+		/* Cortex-A76 r0p0 to r2p0 */
+		.desc = "ARM erratum 1165522",
+		.capability = ARM64_WORKAROUND_1165522,
+		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+	},
 #endif
 	{
 	}
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -52,6 +52,7 @@ unsigned int compat_elf_hwcap2 __read_mostly;

 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcaps);
+static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS];

 /*
 * Flag to indicate if we have computed the system wide
@@ -141,9 +142,18 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 };

 static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPI_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_API_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_APA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -518,6 +528,29 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
 }

 extern const struct arm64_cpu_capabilities arm64_errata[];
+static const struct arm64_cpu_capabilities arm64_features[];
+
+static void __init
+init_cpu_hwcaps_indirect_list_from_array(const struct arm64_cpu_capabilities *caps)
+{
+	for (; caps->matches; caps++) {
+		if (WARN(caps->capability >= ARM64_NCAPS,
+			"Invalid capability %d\n", caps->capability))
+			continue;
+		if (WARN(cpu_hwcaps_ptrs[caps->capability],
+			"Duplicate entry for capability %d\n",
+			caps->capability))
+			continue;
+		cpu_hwcaps_ptrs[caps->capability] = caps;
+	}
+}
+
+static void __init init_cpu_hwcaps_indirect_list(void)
+{
+	init_cpu_hwcaps_indirect_list_from_array(arm64_features);
+	init_cpu_hwcaps_indirect_list_from_array(arm64_errata);
+}
+
 static void __init setup_boot_cpu_capabilities(void);

 void __init init_cpu_features(struct cpuinfo_arm64 *info)
@@ -563,6 +596,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		sve_init_vq_map();
 	}

+	/*
+	 * Initialize the indirect array of CPU hwcaps capabilities pointers
+	 * before we handle the boot CPU below.
+	 */
+	init_cpu_hwcaps_indirect_list();
+
 	/*
 	 * Detect and enable early CPU capabilities based on the boot CPU,
 	 * after we have initialised the CPU feature infrastructure.
@@ -915,6 +954,12 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 	static const struct midr_range kpti_safe_list[] = {
 		MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
 		MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		{ /* sentinel */ }
 	};
 	char const *str = "command line option";
@@ -1145,6 +1190,14 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
 }
 #endif /* CONFIG_ARM64_RAS_EXTN */

+#ifdef CONFIG_ARM64_PTR_AUTH
+static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap)
+{
+	sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB |
+				       SCTLR_ELx_ENDA | SCTLR_ELx_ENDB);
+}
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -1368,22 +1421,115 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_enable_cnp,
 	},
 #endif
+	{
+		.desc = "Speculation barrier (SB)",
+		.capability = ARM64_HAS_SB,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.field_pos = ID_AA64ISAR1_SB_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = 1,
+	},
+#ifdef CONFIG_ARM64_PTR_AUTH
+	{
+		.desc = "Address authentication (architected algorithm)",
+		.capability = ARM64_HAS_ADDRESS_AUTH_ARCH,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_APA_SHIFT,
+		.min_field_value = ID_AA64ISAR1_APA_ARCHITECTED,
+		.matches = has_cpuid_feature,
+		.cpu_enable = cpu_enable_address_auth,
+	},
+	{
+		.desc = "Address authentication (IMP DEF algorithm)",
+		.capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_API_SHIFT,
+		.min_field_value = ID_AA64ISAR1_API_IMP_DEF,
+		.matches = has_cpuid_feature,
+		.cpu_enable = cpu_enable_address_auth,
+	},
+	{
+		.desc = "Generic authentication (architected algorithm)",
+		.capability = ARM64_HAS_GENERIC_AUTH_ARCH,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_GPA_SHIFT,
+		.min_field_value = ID_AA64ISAR1_GPA_ARCHITECTED,
+		.matches = has_cpuid_feature,
+	},
+	{
+		.desc = "Generic authentication (IMP DEF algorithm)",
+		.capability = ARM64_HAS_GENERIC_AUTH_IMP_DEF,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_GPI_SHIFT,
+		.min_field_value = ID_AA64ISAR1_GPI_IMP_DEF,
+		.matches = has_cpuid_feature,
+	},
+#endif /* CONFIG_ARM64_PTR_AUTH */
 	{},
 };

-#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap)	\
-	{							\
-		.desc = #cap,					\
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,		\
-		.matches = has_cpuid_feature,			\
-		.sys_reg = reg,					\
-		.field_pos = field,				\
-		.sign = s,					\
-		.min_field_value = min_value,			\
-		.hwcap_type = cap_type,				\
-		.hwcap = cap,					\
+#define HWCAP_CPUID_MATCH(reg, field, s, min_value)				\
+		.matches = has_cpuid_feature,					\
+		.sys_reg = reg,							\
+		.field_pos = field,						\
+		.sign = s,							\
+		.min_field_value = min_value,
+
+#define __HWCAP_CAP(name, cap_type, cap)					\
+		.desc = name,							\
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,				\
+		.hwcap_type = cap_type,						\
+		.hwcap = cap,							\
+
+#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap)			\
+	{									\
+		__HWCAP_CAP(#cap, cap_type, cap)				\
+		HWCAP_CPUID_MATCH(reg, field, s, min_value)			\
 	}

+#define HWCAP_MULTI_CAP(list, cap_type, cap)					\
+	{									\
+		__HWCAP_CAP(#cap, cap_type, cap)				\
+		.matches = cpucap_multi_entry_cap_matches,			\
+		.match_list = list,						\
+	}
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = {
+	{
+		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_APA_SHIFT,
+				  FTR_UNSIGNED, ID_AA64ISAR1_APA_ARCHITECTED)
+	},
+	{
+		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_API_SHIFT,
+				  FTR_UNSIGNED, ID_AA64ISAR1_API_IMP_DEF)
+	},
+	{},
+};
+
+static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
+	{
+		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_GPA_SHIFT,
+				  FTR_UNSIGNED, ID_AA64ISAR1_GPA_ARCHITECTED)
+	},
+	{
+		HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_GPI_SHIFT,
+				  FTR_UNSIGNED, ID_AA64ISAR1_GPI_IMP_DEF)
+	},
+	{},
+};
+#endif
+
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
@@ -1409,11 +1555,16 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SB),
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
 #endif
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
+#ifdef CONFIG_ARM64_PTR_AUTH
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, HWCAP_PACA),
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, HWCAP_PACG),
+#endif
 	{},
 };

@@ -1482,52 +1633,46 @@ static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 			cap_set_elf_hwcap(hwcaps);
 }

-/*
- * Check if the current CPU has a given feature capability.
- * Should be called from non-preemptible context.
- */
-static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
-			       unsigned int cap)
+static void update_cpu_capabilities(u16 scope_mask)
 {
+	int i;
 	const struct arm64_cpu_capabilities *caps;

-	if (WARN_ON(preemptible()))
-		return false;
-
-	for (caps = cap_array; caps->matches; caps++)
-		if (caps->capability == cap)
-			return caps->matches(caps, SCOPE_LOCAL_CPU);
-
-	return false;
-}
-
-static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
-				      u16 scope_mask, const char *info)
-{
 	scope_mask &= ARM64_CPUCAP_SCOPE_MASK;
-	for (; caps->matches; caps++) {
-		if (!(caps->type & scope_mask) ||
+	for (i = 0; i < ARM64_NCAPS; i++) {
+		caps = cpu_hwcaps_ptrs[i];
+		if (!caps || !(caps->type & scope_mask) ||
+		    cpus_have_cap(caps->capability) ||
 		    !caps->matches(caps, cpucap_default_scope(caps)))
 			continue;

-		if (!cpus_have_cap(caps->capability) && caps->desc)
-			pr_info("%s %s\n", info, caps->desc);
+		if (caps->desc)
+			pr_info("detected: %s\n", caps->desc);
 		cpus_set_cap(caps->capability);
 	}
 }

-static void update_cpu_capabilities(u16 scope_mask)
+/*
+ * Enable all the available capabilities on this CPU. The capabilities
+ * with BOOT_CPU scope are handled separately and hence skipped here.
+ */
+static int cpu_enable_non_boot_scope_capabilities(void *__unused)
 {
-	__update_cpu_capabilities(arm64_errata, scope_mask,
-				  "enabling workaround for");
-	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
-}
+	int i;
+	u16 non_boot_scope = SCOPE_ALL & ~SCOPE_BOOT_CPU;

-static int __enable_cpu_capability(void *arg)
-{
-	const struct arm64_cpu_capabilities *cap = arg;
+	for_each_available_cap(i) {
+		const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[i];

-	cap->cpu_enable(cap);
+		if (WARN_ON(!cap))
+			continue;
+
+		if (!(cap->type & non_boot_scope))
+			continue;
+
+		if (cap->cpu_enable)
+			cap->cpu_enable(cap);
+	}
 	return 0;
 }

@@ -1535,21 +1680,29 @@ static int __enable_cpu_capability(void *arg)
 * Run through the enabled capabilities and enable() it on all active
 * CPUs
 */
-static void __init
-__enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
-			  u16 scope_mask)
+static void __init enable_cpu_capabilities(u16 scope_mask)
 {
-	scope_mask &= ARM64_CPUCAP_SCOPE_MASK;
-	for (; caps->matches; caps++) {
-		unsigned int num = caps->capability;
+	int i;
+	const struct arm64_cpu_capabilities *caps;
+	bool boot_scope;

-		if (!(caps->type & scope_mask) || !cpus_have_cap(num))
+	scope_mask &= ARM64_CPUCAP_SCOPE_MASK;
+	boot_scope = !!(scope_mask & SCOPE_BOOT_CPU);
+
+	for (i = 0; i < ARM64_NCAPS; i++) {
+		unsigned int num;
+
+		caps = cpu_hwcaps_ptrs[i];
+		if (!caps || !(caps->type & scope_mask))
+			continue;
+		num = caps->capability;
+		if (!cpus_have_cap(num))
 			continue;

 		/* Ensure cpus_have_const_cap(num) works */
 		static_branch_enable(&cpu_hwcap_keys[num]);

-		if (caps->cpu_enable) {
+		if (boot_scope && caps->cpu_enable)
 			/*
 			 * Capabilities with SCOPE_BOOT_CPU scope are finalised
 			 * before any secondary CPU boots. Thus, each secondary
@@ -1558,25 +1711,19 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			 * the boot CPU, for which the capability must be
 			 * enabled here. This approach avoids costly
 			 * stop_machine() calls for this case.
-			 *
-			 * Otherwise, use stop_machine() as it schedules the
-			 * work allowing us to modify PSTATE, instead of
-			 * on_each_cpu() which uses an IPI, giving us a PSTATE
-			 * that disappears when we return.
 			 */
-			if (scope_mask & SCOPE_BOOT_CPU)
-				caps->cpu_enable(caps);
-			else
-				stop_machine(__enable_cpu_capability,
-					     (void *)caps, cpu_online_mask);
-		}
+			caps->cpu_enable(caps);
 	}
-}

-static void __init enable_cpu_capabilities(u16 scope_mask)
-{
-	__enable_cpu_capabilities(arm64_errata, scope_mask);
-	__enable_cpu_capabilities(arm64_features, scope_mask);
+	/*
+	 * For all non-boot scope capabilities, use stop_machine()
+	 * as it schedules the work allowing us to modify PSTATE,
+	 * instead of on_each_cpu() which uses an IPI, giving us a
+	 * PSTATE that disappears when we return.
+	 */
+	if (!boot_scope)
+		stop_machine(cpu_enable_non_boot_scope_capabilities,
+			     NULL, cpu_online_mask);
 }

 /*
@@ -1586,16 +1733,17 @@ static void __init enable_cpu_capabilities(u16 scope_mask)
 *
 * Returns "false" on conflicts.
 */
-static bool
-__verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps,
-			u16 scope_mask)
+static bool verify_local_cpu_caps(u16 scope_mask)
 {
+	int i;
 	bool cpu_has_cap, system_has_cap;
+	const struct arm64_cpu_capabilities *caps;

 	scope_mask &= ARM64_CPUCAP_SCOPE_MASK;

-	for (; caps->matches; caps++) {
-		if (!(caps->type & scope_mask))
+	for (i = 0; i < ARM64_NCAPS; i++) {
+		caps = cpu_hwcaps_ptrs[i];
+		if (!caps || !(caps->type & scope_mask))
 			continue;

 		cpu_has_cap = caps->matches(caps, SCOPE_LOCAL_CPU);
@@ -1626,7 +1774,7 @@ __verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps,
 		}
 	}

-	if (caps->matches) {
+	if (i < ARM64_NCAPS) {
 		pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n",
 			smp_processor_id(), caps->capability,
 			caps->desc, system_has_cap, cpu_has_cap);
@@ -1636,12 +1784,6 @@ __verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps,
 	return true;
 }

-static bool verify_local_cpu_caps(u16 scope_mask)
-{
-	return __verify_local_cpu_caps(arm64_errata, scope_mask) &&
-	       __verify_local_cpu_caps(arm64_features, scope_mask);
-}
-
 /*
 * Check for CPU features that are used in early boot
 * based on the Boot CPU value.
@@ -1750,12 +1892,16 @@ static void __init mark_const_caps_ready(void)
 	static_branch_enable(&arm64_const_caps_ready);
 }

-extern const struct arm64_cpu_capabilities arm64_errata[];
-
-bool this_cpu_has_cap(unsigned int cap)
+bool this_cpu_has_cap(unsigned int n)
 {
-	return (__this_cpu_has_cap(arm64_features, cap) ||
-		__this_cpu_has_cap(arm64_errata, cap));
+	if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) {
+		const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n];
+
+		if (cap)
+			return cap->matches(cap, SCOPE_LOCAL_CPU);
+	}
+
+	return false;
 }

 static void __init setup_system_capabilities(void)
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -82,6 +82,9 @@ static const char *const hwcap_str[] = {
 	"ilrcpc",
 	"flagm",
 	"ssbs",
+	"sb",
+	"paca",
+	"pacg",
 	NULL
 };

--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -79,7 +79,6 @@
 	.macro mcount_get_lr reg
 	ldr	\reg, [x29]
 	ldr	\reg, [\reg, #8]
-	mcount_adjust_addr	\reg, \reg
 	.endm

 	.macro mcount_get_lr_addr reg
@@ -121,6 +120,8 @@ skip_ftrace_call:			// }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 	mcount_exit
 ENDPROC(_mcount)
+EXPORT_SYMBOL(_mcount)
+NOKPROBE(_mcount)

 #else /* CONFIG_DYNAMIC_FTRACE */
 /*
@@ -132,6 +133,8 @@ ENDPROC(_mcount)
 ENTRY(_mcount)
 	ret
 ENDPROC(_mcount)
+EXPORT_SYMBOL(_mcount)
+NOKPROBE(_mcount)

 /*
 * void ftrace_caller(unsigned long return_address)
@@ -148,14 +151,12 @@ ENTRY(ftrace_caller)
 	mcount_get_pc0	x0		//     function's pc
 	mcount_get_lr	x1		//     function's lr

-	.global ftrace_call
-ftrace_call:				// tracer(pc, lr);
+GLOBAL(ftrace_call)			// tracer(pc, lr);
 	nop				// This will be replaced with "bl xxx"
 					// where xxx can be any kind of tracer.

 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	.global ftrace_graph_call
-ftrace_graph_call:			// ftrace_graph_caller();
+GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
 	nop				// If enabled, this will be replaced
 					// "b ftrace_graph_caller"
 #endif
@@ -169,24 +170,6 @@ ENTRY(ftrace_stub)
 ENDPROC(ftrace_stub)

 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* save return value regs*/
-	.macro save_return_regs
-	sub sp, sp, #64
-	stp x0, x1, [sp]
-	stp x2, x3, [sp, #16]
-	stp x4, x5, [sp, #32]
-	stp x6, x7, [sp, #48]
-	.endm
-
-	/* restore return value regs*/
-	.macro restore_return_regs
-	ldp x0, x1, [sp]
-	ldp x2, x3, [sp, #16]
-	ldp x4, x5, [sp, #32]
-	ldp x6, x7, [sp, #48]
-	add sp, sp, #64
-	.endm
-
 /*
 * void ftrace_graph_caller(void)
 *
@@ -197,10 +180,10 @@ ENDPROC(ftrace_stub)
 * and run return_to_handler() later on its exit.
 */
 ENTRY(ftrace_graph_caller)
-	mcount_get_lr_addr	  x0	//     pointer to function's saved lr
-	mcount_get_pc		  x1	//     function's pc
+	mcount_get_pc		  x0	//     function's pc
+	mcount_get_lr_addr	  x1	//     pointer to function's saved lr
 	mcount_get_parent_fp	  x2	//     parent's fp
-	bl	prepare_ftrace_return	// prepare_ftrace_return(&lr, pc, fp)
+	bl	prepare_ftrace_return	// prepare_ftrace_return(pc, &lr, fp)

 	mcount_exit
 ENDPROC(ftrace_graph_caller)
@@ -209,15 +192,27 @@ ENDPROC(ftrace_graph_caller)
 * void return_to_handler(void)
 *
 * Run ftrace_return_to_handler() before going back to parent.
- * @fp is checked against the value passed by ftrace_graph_caller()
- * only when HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
+ * @fp is checked against the value passed by ftrace_graph_caller().
 */
 ENTRY(return_to_handler)
-	save_return_regs
+	/* save return value regs */
+	sub sp, sp, #64
+	stp x0, x1, [sp]
+	stp x2, x3, [sp, #16]
+	stp x4, x5, [sp, #32]
+	stp x6, x7, [sp, #48]
+
 	mov	x0, x29			//     parent's fp
 	bl	ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
 	mov	x30, x0			// restore the original return address
-	restore_return_regs
+
+	/* restore return value regs */
+	ldp x0, x1, [sp]
+	ldp x2, x3, [sp, #16]
+	ldp x4, x5, [sp, #32]
+	ldp x6, x7, [sp, #48]
+	add sp, sp, #64
+
 	ret
 END(return_to_handler)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -344,10 +344,6 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #S_FRAME_SIZE		// restore sp
-	/*
-	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on eret context synchronization
-	 * when returning from IPI handler, and when returning to user-space.
-	 */

 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
@@ -363,6 +359,7 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 	.else
 	eret
 	.endif
+	sb
 	.endm

 	.macro	irq_stack_entry
@@ -622,10 +619,8 @@ el1_irq:
 	irq_handler

 #ifdef CONFIG_PREEMPT
-	ldr	w24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
-	cbnz	w24, 1f				// preempt count != 0
-	ldr	x0, [tsk, #TSK_TI_FLAGS]	// get flags
-	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
+	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
+	cbnz	x24, 1f				// preempt count != 0
 	bl	el1_preempt
 1:
 #endif
@@ -1006,6 +1001,7 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
 	mrs	x30, far_el1
 	.endif
 	eret
+	sb
 	.endm

 	.align	11
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -104,7 +104,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
 		 */
-		trampoline = get_plt_entry(addr);
+		trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
 		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
 				       &trampoline)) {
 			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
@@ -211,7 +211,7 @@ int __init ftrace_dyn_arch_init(void)
 *
 * Note that @frame_pointer is used only for sanity check later.
 */
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -31,6 +31,7 @@
 #include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
+#include <asm/image.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/kvm_arm.h>
 #include <asm/memory.h>
@@ -91,7 +92,7 @@ _head:
 	.quad	0				// reserved
 	.quad	0				// reserved
 	.quad	0				// reserved
-	.ascii	"ARM\x64"			// Magic number
+	.ascii	ARM64_IMAGE_MAGIC		// Magic number
 #ifdef CONFIG_EFI
 	.long	pe_header - _head		// Offset to the PE header.

@@ -318,6 +319,19 @@ __create_page_tables:
 	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)

+#ifdef CONFIG_ARM64_USER_VA_BITS_52
+	mrs_s	x6, SYS_ID_AA64MMFR2_EL1
+	and	x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT)
+	mov	x5, #52
+	cbnz	x6, 1f
+#endif
+	mov	x5, #VA_BITS
+1:
+	adr_l	x6, vabits_user
+	str	x5, [x6]
+	dmb	sy
+	dc	ivac, x6		// Invalidate potentially stale cache line
+
 	/*
 	 * VA_BITS may be too small to allow for an ID mapping to be created
 	 * that covers system RAM if that is located sufficiently high in the
@@ -496,10 +510,9 @@ ENTRY(el2_setup)
 #endif

 	/* Hyp configuration. */
-	mov	x0, #HCR_RW			// 64-bit EL1
+	mov_q	x0, HCR_HOST_NVHE_FLAGS
 	cbz	x2, set_hcr
-	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
-	orr	x0, x0, #HCR_E2H
+	mov_q	x0, HCR_HOST_VHE_FLAGS
 set_hcr:
 	msr	hcr_el2, x0
 	isb
@@ -707,6 +720,7 @@ secondary_startup:
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
+	bl	__cpu_secondary_check52bitva
 	bl	__cpu_setup			// initialise processor
 	adrp	x1, swapper_pg_dir
 	bl	__enable_mmu
@@ -769,6 +783,7 @@ ENTRY(__enable_mmu)
 	phys_to_ttbr x1, x1
 	phys_to_ttbr x2, x2
 	msr	ttbr0_el1, x2			// load TTBR0
+	offset_ttbr1 x1
 	msr	ttbr1_el1, x1			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
@@ -784,9 +799,30 @@ ENTRY(__enable_mmu)
 	ret
 ENDPROC(__enable_mmu)

+ENTRY(__cpu_secondary_check52bitva)
+#ifdef CONFIG_ARM64_USER_VA_BITS_52
+	ldr_l	x0, vabits_user
+	cmp	x0, #52
+	b.ne	2f
+
+	mrs_s	x0, SYS_ID_AA64MMFR2_EL1
+	and	x0, x0, #(0xf << ID_AA64MMFR2_LVA_SHIFT)
+	cbnz	x0, 2f
+
+	update_early_cpu_boot_status \
+		CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_52_BIT_VA, x0, x1
+1:	wfe
+	wfi
+	b	1b
+
+#endif
+2:	ret
+ENDPROC(__cpu_secondary_check52bitva)
+
 __no_granule_support:
 	/* Indicate that this CPU can't boot and is stuck in the kernel */
-	update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2
+	update_early_cpu_boot_status \
+		CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_NO_GRAN, x1, x2
 1:
 	wfe
 	wfi
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -40,6 +40,7 @@
 	tlbi	vmalle1
 	dsb	nsh
 	phys_to_ttbr \tmp, \page_table
+	offset_ttbr1 \tmp
 	msr	ttbr1_el1, \tmp
 	isb
 .endm
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -15,13 +15,15 @@
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
-#ifndef __ASM_IMAGE_H
-#define __ASM_IMAGE_H
+#ifndef __ARM64_KERNEL_IMAGE_H
+#define __ARM64_KERNEL_IMAGE_H

 #ifndef LINKER_SCRIPT
 #error This file should only be included in vmlinux.lds.S
 #endif

+#include <asm/image.h>
+
 /*
 * There aren't any ELF relocations we can use to endian-swap values known only
 * at link time (e.g. the subtraction of two symbol addresses), so we must get
@@ -47,19 +49,22 @@
 	sym##_lo32 = DATA_LE32((data) & 0xffffffff);		\
 	sym##_hi32 = DATA_LE32((data) >> 32)

+#define __HEAD_FLAG(field)	(__HEAD_FLAG_##field << \
+					ARM64_IMAGE_FLAG_##field##_SHIFT)
+
 #ifdef CONFIG_CPU_BIG_ENDIAN
-#define __HEAD_FLAG_BE		1
+#define __HEAD_FLAG_BE		ARM64_IMAGE_FLAG_BE
 #else
-#define __HEAD_FLAG_BE		0
+#define __HEAD_FLAG_BE		ARM64_IMAGE_FLAG_LE
 #endif

 #define __HEAD_FLAG_PAGE_SIZE	((PAGE_SHIFT - 10) / 2)

 #define __HEAD_FLAG_PHYS_BASE	1

-#define __HEAD_FLAGS		((__HEAD_FLAG_BE << 0) |	\
-				 (__HEAD_FLAG_PAGE_SIZE << 1) |	\
-				 (__HEAD_FLAG_PHYS_BASE << 3))
+#define __HEAD_FLAGS		(__HEAD_FLAG(BE)	| \
+				 __HEAD_FLAG(PAGE_SIZE) | \
+				 __HEAD_FLAG(PHYS_BASE))

 /*
 * These will output as part of the Image header, which should be little-endian
@@ -75,16 +80,6 @@

 __efistub_stext_offset = stext - _text;

-/*
- * Prevent the symbol aliases below from being emitted into the kallsyms
- * table, by forcing them to be absolute symbols (which are conveniently
- * ignored by scripts/kallsyms) rather than section relative symbols.
- * The distinction is only relevant for partial linking, and only for symbols
- * that are defined within a section declaration (which is not the case for
- * the definitions below) so the resulting values will be identical.
- */
-#define KALLSYMS_HIDE(sym)	ABSOLUTE(sym)
-
 /*
 * The EFI stub has its own symbol namespace prefixed by __efistub_, to
 * isolate it from the kernel proper. The following symbols are legally
@@ -94,29 +89,29 @@ __efistub_stext_offset = stext - _text;
 * linked at. The routines below are all implemented in assembler in a
 * position independent manner
 */
-__efistub_memcmp		= KALLSYMS_HIDE(__pi_memcmp);
-__efistub_memchr		= KALLSYMS_HIDE(__pi_memchr);
-__efistub_memcpy		= KALLSYMS_HIDE(__pi_memcpy);
-__efistub_memmove		= KALLSYMS_HIDE(__pi_memmove);
-__efistub_memset		= KALLSYMS_HIDE(__pi_memset);
-__efistub_strlen		= KALLSYMS_HIDE(__pi_strlen);
-__efistub_strnlen		= KALLSYMS_HIDE(__pi_strnlen);
-__efistub_strcmp		= KALLSYMS_HIDE(__pi_strcmp);
-__efistub_strncmp		= KALLSYMS_HIDE(__pi_strncmp);
-__efistub_strrchr		= KALLSYMS_HIDE(__pi_strrchr);
-__efistub___flush_dcache_area	= KALLSYMS_HIDE(__pi___flush_dcache_area);
+__efistub_memcmp		= __pi_memcmp;
+__efistub_memchr		= __pi_memchr;
+__efistub_memcpy		= __pi_memcpy;
+__efistub_memmove		= __pi_memmove;
+__efistub_memset		= __pi_memset;
+__efistub_strlen		= __pi_strlen;
+__efistub_strnlen		= __pi_strnlen;
+__efistub_strcmp		= __pi_strcmp;
+__efistub_strncmp		= __pi_strncmp;
+__efistub_strrchr		= __pi_strrchr;
+__efistub___flush_dcache_area	= __pi___flush_dcache_area;

 #ifdef CONFIG_KASAN
-__efistub___memcpy		= KALLSYMS_HIDE(__pi_memcpy);
-__efistub___memmove		= KALLSYMS_HIDE(__pi_memmove);
-__efistub___memset		= KALLSYMS_HIDE(__pi_memset);
+__efistub___memcpy		= __pi_memcpy;
+__efistub___memmove		= __pi_memmove;
+__efistub___memset		= __pi_memset;
 #endif

-__efistub__text			= KALLSYMS_HIDE(_text);
-__efistub__end			= KALLSYMS_HIDE(_end);
-__efistub__edata		= KALLSYMS_HIDE(_edata);
-__efistub_screen_info		= KALLSYMS_HIDE(screen_info);
+__efistub__text			= _text;
+__efistub__end			= _end;
+__efistub__edata		= _edata;
+__efistub_screen_info		= screen_info;

 #endif

-#endif /* __ASM_IMAGE_H */
+#endif /* __ARM64_KERNEL_IMAGE_H */
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1239,6 +1239,35 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }

+u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr,
+			 enum aarch64_insn_register reg,
+			 enum aarch64_insn_adr_type type)
+{
+	u32 insn;
+	s32 offset;
+
+	switch (type) {
+	case AARCH64_INSN_ADR_TYPE_ADR:
+		insn = aarch64_insn_get_adr_value();
+		offset = addr - pc;
+		break;
+	case AARCH64_INSN_ADR_TYPE_ADRP:
+		insn = aarch64_insn_get_adrp_value();
+		offset = (addr - ALIGN_DOWN(pc, SZ_4K)) >> 12;
+		break;
+	default:
+		pr_err("%s: unknown adr encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	if (offset < -SZ_1M || offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn, offset);
+}
+
 /*
 * Decode the imm field of a branch, and return the byte offset as a
 * signed value (so it can be used when computing a new branch
--- a/arch/arm64/kernel/kexec_image.c
+++ b/arch/arm64/kernel/kexec_image.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Kexec image loader
+
+ * Copyright (C) 2018 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ */
+
+#define pr_fmt(fmt)	"kexec_file(Image): " fmt
+
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/pe.h>
+#include <linux/string.h>
+#include <linux/verification.h>
+#include <asm/byteorder.h>
+#include <asm/cpufeature.h>
+#include <asm/image.h>
+#include <asm/memory.h>
+
+static int image_probe(const char *kernel_buf, unsigned long kernel_len)
+{
+	const struct arm64_image_header *h =
+		(const struct arm64_image_header *)(kernel_buf);
+
+	if (!h || (kernel_len < sizeof(*h)))
+		return -EINVAL;
+
+	if (memcmp(&h->magic, ARM64_IMAGE_MAGIC, sizeof(h->magic)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void *image_load(struct kimage *image,
+				char *kernel, unsigned long kernel_len,
+				char *initrd, unsigned long initrd_len,
+				char *cmdline, unsigned long cmdline_len)
+{
+	struct arm64_image_header *h;
+	u64 flags, value;
+	bool be_image, be_kernel;
+	struct kexec_buf kbuf;
+	unsigned long text_offset;
+	struct kexec_segment *kernel_segment;
+	int ret;
+
+	/* We don't support crash kernels yet. */
+	if (image->type == KEXEC_TYPE_CRASH)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/*
+	 * We require a kernel with an unambiguous Image header. Per
+	 * Documentation/booting.txt, this is the case when image_size
+	 * is non-zero (practically speaking, since v3.17).
+	 */
+	h = (struct arm64_image_header *)kernel;
+	if (!h->image_size)
+		return ERR_PTR(-EINVAL);
+
+	/* Check cpu features */
+	flags = le64_to_cpu(h->flags);
+	be_image = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_BE);
+	be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+	if ((be_image != be_kernel) && !system_supports_mixed_endian())
+		return ERR_PTR(-EINVAL);
+
+	value = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_PAGE_SIZE);
+	if (((value == ARM64_IMAGE_FLAG_PAGE_SIZE_4K) &&
+			!system_supports_4kb_granule()) ||
+	    ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_64K) &&
+			!system_supports_64kb_granule()) ||
+	    ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_16K) &&
+			!system_supports_16kb_granule()))
+		return ERR_PTR(-EINVAL);
+
+	/* Load the kernel */
+	kbuf.image = image;
+	kbuf.buf_min = 0;
+	kbuf.buf_max = ULONG_MAX;
+	kbuf.top_down = false;
+
+	kbuf.buffer = kernel;
+	kbuf.bufsz = kernel_len;
+	kbuf.mem = 0;
+	kbuf.memsz = le64_to_cpu(h->image_size);
+	text_offset = le64_to_cpu(h->text_offset);
+	kbuf.buf_align = MIN_KIMG_ALIGN;
+
+	/* Adjust kernel segment with TEXT_OFFSET */
+	kbuf.memsz += text_offset;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret)
+		return ERR_PTR(ret);
+
+	kernel_segment = &image->segment[image->nr_segments - 1];
+	kernel_segment->mem += text_offset;
+	kernel_segment->memsz -= text_offset;
+	image->start = kernel_segment->mem;
+
+	pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+				kernel_segment->mem, kbuf.bufsz,
+				kernel_segment->memsz);
+
+	/* Load additional data */
+	ret = load_other_segments(image,
+				kernel_segment->mem, kernel_segment->memsz,
+				initrd, initrd_len, cmdline);
+
+	return ERR_PTR(ret);
+}
+
+#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
+static int image_verify_sig(const char *kernel, unsigned long kernel_len)
+{
+	return verify_pefile_signature(kernel, kernel_len, NULL,
+				       VERIFYING_KEXEC_PE_SIGNATURE);
+}
+#endif
+
+const struct kexec_file_ops kexec_image_ops = {
+	.probe = image_probe,
+	.load = image_load,
+#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
+	.verify_sig = image_verify_sig,
+#endif
+};
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -212,9 +212,17 @@ void machine_kexec(struct kimage *kimage)
 	 * uses physical addressing to relocate the new image to its final
 	 * position and transfers control to the image entry point when the
 	 * relocation is complete.
+	 * In kexec case, kimage->start points to purgatory assuming that
+	 * kernel entry and dtb address are embedded in purgatory by
+	 * userspace (kexec-tools).
+	 * In kexec_file case, the kernel starts directly without purgatory.
 	 */
-
-	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0);
+	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start,
+#ifdef CONFIG_KEXEC_FILE
+						kimage->arch.dtb_mem);
+#else
+						0);
+#endif

 	BUG(); /* Should never get here. */
 }
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kexec_file for arm64
+ *
+ * Copyright (C) 2018 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * Most code is derived from arm64 port of kexec-tools
+ */
+
+#define pr_fmt(fmt) "kexec_file: " fmt
+
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <linux/of_fdt.h>
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <asm/byteorder.h>
+
+/* relevant device tree properties */
+#define FDT_PROP_INITRD_START	"linux,initrd-start"
+#define FDT_PROP_INITRD_END	"linux,initrd-end"
+#define FDT_PROP_BOOTARGS	"bootargs"
+#define FDT_PROP_KASLR_SEED	"kaslr-seed"
+
+const struct kexec_file_ops * const kexec_file_loaders[] = {
+	&kexec_image_ops,
+	NULL
+};
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	vfree(image->arch.dtb);
+	image->arch.dtb = NULL;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
+
+static int setup_dtb(struct kimage *image,
+		     unsigned long initrd_load_addr, unsigned long initrd_len,
+		     char *cmdline, void *dtb)
+{
+	int off, ret;
+
+	ret = fdt_path_offset(dtb, "/chosen");
+	if (ret < 0)
+		goto out;
+
+	off = ret;
+
+	/* add bootargs */
+	if (cmdline) {
+		ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline);
+		if (ret)
+			goto out;
+	} else {
+		ret = fdt_delprop(dtb, off, FDT_PROP_BOOTARGS);
+		if (ret && (ret != -FDT_ERR_NOTFOUND))
+			goto out;
+	}
+
+	/* add initrd-* */
+	if (initrd_load_addr) {
+		ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_START,
+				      initrd_load_addr);
+		if (ret)
+			goto out;
+
+		ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_END,
+				      initrd_load_addr + initrd_len);
+		if (ret)
+			goto out;
+	} else {
+		ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_START);
+		if (ret && (ret != -FDT_ERR_NOTFOUND))
+			goto out;
+
+		ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_END);
+		if (ret && (ret != -FDT_ERR_NOTFOUND))
+			goto out;
+	}
+
+	/* add kaslr-seed */
+	ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED);
+	if (ret && (ret != -FDT_ERR_NOTFOUND))
+		goto out;
+
+	if (rng_is_initialized()) {
+		u64 seed = get_random_u64();
+		ret = fdt_setprop_u64(dtb, off, FDT_PROP_KASLR_SEED, seed);
+		if (ret)
+			goto out;
+	} else {
+		pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+				FDT_PROP_KASLR_SEED);
+	}
+
+out:
+	if (ret)
+		return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
+
+	return 0;
+}
+
+/*
+ * More space needed so that we can add initrd, bootargs and kaslr-seed.
+ */
+#define DTB_EXTRA_SPACE 0x1000
+
+static int create_dtb(struct kimage *image,
+		      unsigned long initrd_load_addr, unsigned long initrd_len,
+		      char *cmdline, void **dtb)
+{
+	void *buf;
+	size_t buf_size;
+	int ret;
+
+	buf_size = fdt_totalsize(initial_boot_params)
+			+ strlen(cmdline) + DTB_EXTRA_SPACE;
+
+	for (;;) {
+		buf = vmalloc(buf_size);
+		if (!buf)
+			return -ENOMEM;
+
+		/* duplicate a device tree blob */
+		ret = fdt_open_into(initial_boot_params, buf, buf_size);
+		if (ret)
+			return -EINVAL;
+
+		ret = setup_dtb(image, initrd_load_addr, initrd_len,
+				cmdline, buf);
+		if (ret) {
+			vfree(buf);
+			if (ret == -ENOMEM) {
+				/* unlikely, but just in case */
+				buf_size += DTB_EXTRA_SPACE;
+				continue;
+			} else {
+				return ret;
+			}
+		}
+
+		/* trim it */
+		fdt_pack(buf);
+		*dtb = buf;
+
+		return 0;
+	}
+}
+
+int load_other_segments(struct kimage *image,
+			unsigned long kernel_load_addr,
+			unsigned long kernel_size,
+			char *initrd, unsigned long initrd_len,
+			char *cmdline)
+{
+	struct kexec_buf kbuf;
+	void *dtb = NULL;
+	unsigned long initrd_load_addr = 0, dtb_len;
+	int ret = 0;
+
+	kbuf.image = image;
+	/* not allocate anything below the kernel */
+	kbuf.buf_min = kernel_load_addr + kernel_size;
+
+	/* load initrd */
+	if (initrd) {
+		kbuf.buffer = initrd;
+		kbuf.bufsz = initrd_len;
+		kbuf.mem = 0;
+		kbuf.memsz = initrd_len;
+		kbuf.buf_align = 0;
+		/* within 1GB-aligned window of up to 32GB in size */
+		kbuf.buf_max = round_down(kernel_load_addr, SZ_1G)
+						+ (unsigned long)SZ_1G * 32;
+		kbuf.top_down = false;
+
+		ret = kexec_add_buffer(&kbuf);
+		if (ret)
+			goto out_err;
+		initrd_load_addr = kbuf.mem;
+
+		pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+				initrd_load_addr, initrd_len, initrd_len);
+	}
+
+	/* load dtb */
+	ret = create_dtb(image, initrd_load_addr, initrd_len, cmdline, &dtb);
+	if (ret) {
+		pr_err("Preparing for new dtb failed\n");
+		goto out_err;
+	}
+
+	dtb_len = fdt_totalsize(dtb);
+	kbuf.buffer = dtb;
+	kbuf.bufsz = dtb_len;
+	kbuf.mem = 0;
+	kbuf.memsz = dtb_len;
+	/* not across 2MB boundary */
+	kbuf.buf_align = SZ_2M;
+	kbuf.buf_max = ULONG_MAX;
+	kbuf.top_down = true;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret)
+		goto out_err;
+	image->arch.dtb = dtb;
+	image->arch.dtb_mem = kbuf.mem;
+
+	pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			kbuf.mem, dtb_len, dtb_len);
+
+	return 0;
+
+out_err:
+	vfree(dtb);
+	return ret;
+}
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -11,31 +11,91 @@
 #include <linux/module.h>
 #include <linux/sort.h>

+static struct plt_entry __get_adrp_add_pair(u64 dst, u64 pc,
+					    enum aarch64_insn_register reg)
+{
+	u32 adrp, add;
+
+	adrp = aarch64_insn_gen_adr(pc, dst, reg, AARCH64_INSN_ADR_TYPE_ADRP);
+	add = aarch64_insn_gen_add_sub_imm(reg, reg, dst % SZ_4K,
+					   AARCH64_INSN_VARIANT_64BIT,
+					   AARCH64_INSN_ADSB_ADD);
+
+	return (struct plt_entry){ cpu_to_le32(adrp), cpu_to_le32(add) };
+}
+
+struct plt_entry get_plt_entry(u64 dst, void *pc)
+{
+	struct plt_entry plt;
+	static u32 br;
+
+	if (!br)
+		br = aarch64_insn_gen_branch_reg(AARCH64_INSN_REG_16,
+						 AARCH64_INSN_BRANCH_NOLINK);
+
+	plt = __get_adrp_add_pair(dst, (u64)pc, AARCH64_INSN_REG_16);
+	plt.br = cpu_to_le32(br);
+
+	return plt;
+}
+
+bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b)
+{
+	u64 p, q;
+
+	/*
+	 * Check whether both entries refer to the same target:
+	 * do the cheapest checks first.
+	 * If the 'add' or 'br' opcodes are different, then the target
+	 * cannot be the same.
+	 */
+	if (a->add != b->add || a->br != b->br)
+		return false;
+
+	p = ALIGN_DOWN((u64)a, SZ_4K);
+	q = ALIGN_DOWN((u64)b, SZ_4K);
+
+	/*
+	 * If the 'adrp' opcodes are the same then we just need to check
+	 * that they refer to the same 4k region.
+	 */
+	if (a->adrp == b->adrp && p == q)
+		return true;
+
+	return (p + aarch64_insn_adrp_get_offset(le32_to_cpu(a->adrp))) ==
+	       (q + aarch64_insn_adrp_get_offset(le32_to_cpu(b->adrp)));
+}
+
 static bool in_init(const struct module *mod, void *loc)
 {
 	return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
 }

-u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
+u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
+			  void *loc, const Elf64_Rela *rela,
 			  Elf64_Sym *sym)
 {
 	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
 							  &mod->arch.init;
-	struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr;
+	struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr;
 	int i = pltsec->plt_num_entries;
+	int j = i - 1;
 	u64 val = sym->st_value + rela->r_addend;

-	plt[i] = get_plt_entry(val);
+	if (is_forbidden_offset_for_adrp(&plt[i].adrp))
+		i++;
+
+	plt[i] = get_plt_entry(val, &plt[i]);

 	/*
 	 * Check if the entry we just created is a duplicate. Given that the
 	 * relocations are sorted, this will be the last entry we allocated.
 	 * (if one exists).
 	 */
-	if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
-		return (u64)&plt[i - 1];
+	if (j >= 0 && plt_entries_equal(plt + i, plt + j))
+		return (u64)&plt[j];

-	pltsec->plt_num_entries++;
+	pltsec->plt_num_entries += i - j;
 	if (WARN_ON(pltsec->plt_num_entries > pltsec->plt_max_entries))
 		return 0;

@@ -43,41 +103,31 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 }

 #ifdef CONFIG_ARM64_ERRATUM_843419
-u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val)
+u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs,
+				void *loc, u64 val)
 {
 	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
 							  &mod->arch.init;
-	struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr;
+	struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr;
 	int i = pltsec->plt_num_entries++;
-	u32 mov0, mov1, mov2, br;
+	u32 br;
 	int rd;

 	if (WARN_ON(pltsec->plt_num_entries > pltsec->plt_max_entries))
 		return 0;

+	if (is_forbidden_offset_for_adrp(&plt[i].adrp))
+		i = pltsec->plt_num_entries++;
+
 	/* get the destination register of the ADRP instruction */
 	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD,
 					  le32_to_cpup((__le32 *)loc));

-	/* generate the veneer instructions */
-	mov0 = aarch64_insn_gen_movewide(rd, (u16)~val, 0,
-					 AARCH64_INSN_VARIANT_64BIT,
-					 AARCH64_INSN_MOVEWIDE_INVERSE);
-	mov1 = aarch64_insn_gen_movewide(rd, (u16)(val >> 16), 16,
-					 AARCH64_INSN_VARIANT_64BIT,
-					 AARCH64_INSN_MOVEWIDE_KEEP);
-	mov2 = aarch64_insn_gen_movewide(rd, (u16)(val >> 32), 32,
-					 AARCH64_INSN_VARIANT_64BIT,
-					 AARCH64_INSN_MOVEWIDE_KEEP);
 	br = aarch64_insn_gen_branch_imm((u64)&plt[i].br, (u64)loc + 4,
 					 AARCH64_INSN_BRANCH_NOLINK);

-	plt[i] = (struct plt_entry){
-			cpu_to_le32(mov0),
-			cpu_to_le32(mov1),
-			cpu_to_le32(mov2),
-			cpu_to_le32(br)
-		};
+	plt[i] = __get_adrp_add_pair(val, (u64)&plt[i], rd);
+	plt[i].br = cpu_to_le32(br);

 	return (u64)&plt[i];
 }
@@ -193,6 +243,15 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
 			break;
 		}
 	}
+
+	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
+	    cpus_have_const_cap(ARM64_WORKAROUND_843419))
+		/*
+		 * Add some slack so we can skip PLT slots that may trigger
+		 * the erratum due to the placement of the ADRP instruction.
+		 */
+		ret += DIV_ROUND_UP(ret, (SZ_4K / sizeof(struct plt_entry)));
+
 	return ret;
 }

@@ -202,7 +261,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned long core_plts = 0;
 	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
-	Elf_Shdr *tramp = NULL;
+	Elf_Shdr *pltsec, *tramp = NULL;
 	int i;

 	/*
@@ -211,9 +270,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	 */
 	for (i = 0; i < ehdr->e_shnum; i++) {
 		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
-			mod->arch.core.plt = sechdrs + i;
+			mod->arch.core.plt_shndx = i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
-			mod->arch.init.plt = sechdrs + i;
+			mod->arch.init.plt_shndx = i;
 		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
 			 !strcmp(secstrings + sechdrs[i].sh_name,
 				 ".text.ftrace_trampoline"))
@@ -222,7 +281,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}

-	if (!mod->arch.core.plt || !mod->arch.init.plt) {
+	if (!mod->arch.core.plt_shndx || !mod->arch.init.plt_shndx) {
 		pr_err("%s: module PLT section(s) missing\n", mod->name);
 		return -ENOEXEC;
 	}
@@ -254,17 +313,19 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 						sechdrs[i].sh_info, dstsec);
 	}

-	mod->arch.core.plt->sh_type = SHT_NOBITS;
-	mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
-	mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES;
-	mod->arch.core.plt->sh_size = (core_plts  + 1) * sizeof(struct plt_entry);
+	pltsec = sechdrs + mod->arch.core.plt_shndx;
+	pltsec->sh_type = SHT_NOBITS;
+	pltsec->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	pltsec->sh_addralign = L1_CACHE_BYTES;
+	pltsec->sh_size = (core_plts  + 1) * sizeof(struct plt_entry);
 	mod->arch.core.plt_num_entries = 0;
 	mod->arch.core.plt_max_entries = core_plts;

-	mod->arch.init.plt->sh_type = SHT_NOBITS;
-	mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
-	mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES;
-	mod->arch.init.plt->sh_size = (init_plts + 1) * sizeof(struct plt_entry);
+	pltsec = sechdrs + mod->arch.init.plt_shndx;
+	pltsec->sh_type = SHT_NOBITS;
+	pltsec->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	pltsec->sh_addralign = L1_CACHE_BYTES;
+	pltsec->sh_size = (init_plts + 1) * sizeof(struct plt_entry);
 	mod->arch.init.plt_num_entries = 0;
 	mod->arch.init.plt_max_entries = init_plts;

--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -198,13 +198,12 @@ static int reloc_insn_imm(enum aarch64_reloc_op op, __le32 *place, u64 val,
 	return 0;
 }

-static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val)
+static int reloc_insn_adrp(struct module *mod, Elf64_Shdr *sechdrs,
+			   __le32 *place, u64 val)
 {
 	u32 insn;

-	if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) ||
-	    !cpus_have_const_cap(ARM64_WORKAROUND_843419) ||
-	    ((u64)place & 0xfff) < 0xff8)
+	if (!is_forbidden_offset_for_adrp(place))
 		return reloc_insn_imm(RELOC_OP_PAGE, place, val, 12, 21,
 				      AARCH64_INSN_IMM_ADR);

@@ -215,7 +214,7 @@ static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val)
 		insn &= ~BIT(31);
 	} else {
 		/* out of range for ADR -> emit a veneer */
-		val = module_emit_veneer_for_adrp(mod, place, val & ~0xfff);
+		val = module_emit_veneer_for_adrp(mod, sechdrs, place, val & ~0xfff);
 		if (!val)
 			return -ENOEXEC;
 		insn = aarch64_insn_gen_branch_imm((u64)place, val,
@@ -368,7 +367,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
 		case R_AARCH64_ADR_PREL_PG_HI21:
-			ovf = reloc_insn_adrp(me, loc, val);
+			ovf = reloc_insn_adrp(me, sechdrs, loc, val);
 			if (ovf && ovf != -ERANGE)
 				return ovf;
 			break;
@@ -413,7 +412,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,

 			if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
 			    ovf == -ERANGE) {
-				val = module_emit_plt_entry(me, loc, &rel[i], sym);
+				val = module_emit_plt_entry(me, sechdrs, loc, &rel[i], sym);
 				if (!val)
 					return -ENOEXEC;
 				ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2,
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -18,6 +18,7 @@
 #include <linux/perf_event.h>
 #include <linux/uaccess.h>

+#include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>

 struct frame_tail {
@@ -35,6 +36,7 @@ user_backtrace(struct frame_tail __user *tail,
 {
 	struct frame_tail buftail;
 	unsigned long err;
+	unsigned long lr;

 	/* Also check accessibility of one struct frame_tail beyond */
 	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
@@ -47,7 +49,9 @@ user_backtrace(struct frame_tail __user *tail,
 	if (err)
 		return NULL;

-	perf_callchain_store(entry, buftail.lr);
+	lr = ptrauth_strip_insn_pac(buftail.lr);
+
+	perf_callchain_store(entry, lr);

 	/*
 	 * Frame pointers should strictly progress back up the stack
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1,5 +1,5 @@
 /*
- * PMU support
+ * ARMv8 PMUv3 Performance Events handling code.
 *
 * Copyright (C) 2012 ARM Limited
 * Author: Will Deacon <will.deacon@arm.com>
@@ -30,149 +30,6 @@
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>

-/*
- * ARMv8 PMUv3 Performance Events handling code.
- * Common event types (some are defined in asm/perf_event.h).
- */
-
-/* At least one of the following is required. */
-#define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
-#define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B
-
-/* Common architectural events. */
-#define ARMV8_PMUV3_PERFCTR_LD_RETIRED				0x06
-#define ARMV8_PMUV3_PERFCTR_ST_RETIRED				0x07
-#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x09
-#define ARMV8_PMUV3_PERFCTR_EXC_RETURN				0x0A
-#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED			0x0B
-#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED			0x0C
-#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED			0x0D
-#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED			0x0E
-#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED		0x0F
-#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED			0x1C
-#define ARMV8_PMUV3_PERFCTR_CHAIN				0x1E
-#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x21
-
-/* Common microarchitectural events. */
-#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL			0x01
-#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL			0x02
-#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL			0x05
-#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x13
-#define ARMV8_PMUV3_PERFCTR_L1I_CACHE				0x14
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB			0x15
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE				0x16
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL			0x17
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB			0x18
-#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x19
-#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR			0x1A
-#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x1D
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x1F
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x20
-#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x22
-#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x23
-#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x24
-#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x25
-#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x26
-#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x27
-#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x28
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x29
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x2A
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x2B
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x2C
-#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x2D
-#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL			0x2E
-#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
-#define ARMV8_PMUV3_PERFCTR_L2I_TLB				0x30
-
-/* ARMv8 recommended implementation defined event types */
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x40
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x41
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD		0x42
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR		0x43
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER		0x44
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER		0x45
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM		0x46
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN			0x47
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL			0x48
-
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD			0x4C
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR			0x4D
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD				0x4E
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR				0x4F
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD			0x50
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR			0x51
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD		0x52
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR		0x53
-
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM		0x56
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN			0x57
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL			0x58
-
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD			0x5C
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR			0x5D
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD				0x5E
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR				0x5F
-
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD			0x60
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR			0x61
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED			0x62
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED		0x63
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL			0x64
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH			0x65
-
-#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD			0x66
-#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR			0x67
-#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC			0x68
-#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC			0x69
-#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC		0x6A
-
-#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC				0x6C
-#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC			0x6D
-#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC			0x6E
-#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC				0x6F
-#define ARMV8_IMPDEF_PERFCTR_LD_SPEC				0x70
-#define ARMV8_IMPDEF_PERFCTR_ST_SPEC				0x71
-#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC				0x72
-#define ARMV8_IMPDEF_PERFCTR_DP_SPEC				0x73
-#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC				0x74
-#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC				0x75
-#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC			0x76
-#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC			0x77
-#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC			0x78
-#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC			0x79
-#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC			0x7A
-
-#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC				0x7C
-#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC				0x7D
-#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC				0x7E
-
-#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF				0x81
-#define ARMV8_IMPDEF_PERFCTR_EXC_SVC				0x82
-#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT				0x83
-#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT				0x84
-
-#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ				0x86
-#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ				0x87
-#define ARMV8_IMPDEF_PERFCTR_EXC_SMC				0x88
-
-#define ARMV8_IMPDEF_PERFCTR_EXC_HVC				0x8A
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT			0x8B
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT			0x8C
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER			0x8D
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ			0x8E
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ			0x8F
-#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC				0x90
-#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC				0x91
-
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD			0xA0
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR			0xA1
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD		0xA2
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR		0xA3
-
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM		0xA6
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN			0xA7
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL			0xA8
-
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2

@@ -183,12 +40,10 @@
 #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS		0xEC
 #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS		0xED

-/* PMUv3 HW events mapping. */
-
 /*
 * ARMv8 Architectural defined events, not all of these may
- * be supported on any given implementation. Undefined events will
- * be disabled at run-time.
+ * be supported on any given implementation. Unsupported events will
+ * be disabled at run-time based on the PMCEID registers.
 */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
@@ -210,8 +65,6 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

 	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
 	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,

 	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE,
 	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
@@ -224,8 +77,6 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

 	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
 	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
-	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
-	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
 };

 static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -370,6 +221,18 @@ 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);

 static struct attribute *armv8_pmuv3_event_attrs[] = {
 	&armv8_event_attr_sw_incr.attr.attr,
@@ -420,6 +283,18 @@ static struct attribute *armv8_pmuv3_event_attrs[] = {
 	&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,
 	NULL,
 };

@@ -434,7 +309,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,

 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);

-	if (test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
+	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
+		return attr->mode;
+
+	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
 		return attr->mode;

 	return 0;
@@ -1009,7 +890,7 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
 	if (armv8pmu_event_is_64bit(event))
 		event->hw.flags |= ARMPMU_EVT_64BIT;

-	/* Onl expose micro/arch events supported by this PMU */
+	/* Only expose micro/arch events supported by this PMU */
 	if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
 	    && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
 		return hw_event_id;
@@ -1061,6 +942,7 @@ static void __armv8pmu_probe_pmu(void *info)
 	struct armv8pmu_probe_info *probe = info;
 	struct arm_pmu *cpu_pmu = probe->pmu;
 	u64 dfr0;
+	u64 pmceid_raw[2];
 	u32 pmceid[2];
 	int pmuver;

@@ -1079,11 +961,17 @@ static void __armv8pmu_probe_pmu(void *info)
 	/* Add the CPU cycles counter */
 	cpu_pmu->num_events += 1;

-	pmceid[0] = read_sysreg(pmceid0_el0);
-	pmceid[1] = read_sysreg(pmceid1_el0);
+	pmceid[0] = pmceid_raw[0] = read_sysreg(pmceid0_el0);
+	pmceid[1] = pmceid_raw[1] = read_sysreg(pmceid1_el0);

 	bitmap_from_arr32(cpu_pmu->pmceid_bitmap,
 			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	pmceid[0] = pmceid_raw[0] >> 32;
+	pmceid[1] = pmceid_raw[1] >> 32;
+
+	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
+			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 }

 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
@@ -1109,16 +997,16 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	if (ret)
 		return ret;

-	cpu_pmu->handle_irq		= armv8pmu_handle_irq,
-	cpu_pmu->enable			= armv8pmu_enable_event,
-	cpu_pmu->disable		= armv8pmu_disable_event,
-	cpu_pmu->read_counter		= armv8pmu_read_counter,
-	cpu_pmu->write_counter		= armv8pmu_write_counter,
-	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx,
-	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx,
-	cpu_pmu->start			= armv8pmu_start,
-	cpu_pmu->stop			= armv8pmu_stop,
-	cpu_pmu->reset			= armv8pmu_reset,
+	cpu_pmu->handle_irq		= armv8pmu_handle_irq;
+	cpu_pmu->enable			= armv8pmu_enable_event;
+	cpu_pmu->disable		= armv8pmu_disable_event;
+	cpu_pmu->read_counter		= armv8pmu_read_counter;
+	cpu_pmu->write_counter		= armv8pmu_write_counter;
+	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx;
+	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx;
+	cpu_pmu->start			= armv8pmu_start;
+	cpu_pmu->stop			= armv8pmu_stop;
+	cpu_pmu->reset			= armv8pmu_reset;
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 	cpu_pmu->filter_match		= armv8pmu_filter_match;

@@ -1274,6 +1162,7 @@ static struct platform_driver armv8_pmu_driver = {
 	.driver		= {
 		.name	= ARMV8_PMU_PDEV_NAME,
 		.of_match_table = armv8_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= armv8_pmu_device_probe,
 };
--- a/arch/arm64/kernel/pointer_auth.c
+++ b/arch/arm64/kernel/pointer_auth.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/errno.h>
+#include <linux/prctl.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+#include <asm/cpufeature.h>
+#include <asm/pointer_auth.h>
+
+int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
+{
+	struct ptrauth_keys *keys = &tsk->thread.keys_user;
+	unsigned long addr_key_mask = PR_PAC_APIAKEY | PR_PAC_APIBKEY |
+				      PR_PAC_APDAKEY | PR_PAC_APDBKEY;
+	unsigned long key_mask = addr_key_mask | PR_PAC_APGAKEY;
+
+	if (!system_supports_address_auth() && !system_supports_generic_auth())
+		return -EINVAL;
+
+	if (!arg) {
+		ptrauth_keys_init(keys);
+		ptrauth_keys_switch(keys);
+		return 0;
+	}
+
+	if (arg & ~key_mask)
+		return -EINVAL;
+
+	if (((arg & addr_key_mask) && !system_supports_address_auth()) ||
+	    ((arg & PR_PAC_APGAKEY) && !system_supports_generic_auth()))
+		return -EINVAL;
+
+	if (arg & PR_PAC_APIAKEY)
+		get_random_bytes(&keys->apia, sizeof(keys->apia));
+	if (arg & PR_PAC_APIBKEY)
+		get_random_bytes(&keys->apib, sizeof(keys->apib));
+	if (arg & PR_PAC_APDAKEY)
+		get_random_bytes(&keys->apda, sizeof(keys->apda));
+	if (arg & PR_PAC_APDBKEY)
+		get_random_bytes(&keys->apdb, sizeof(keys->apdb));
+	if (arg & PR_PAC_APGAKEY)
+		get_random_bytes(&keys->apga, sizeof(keys->apga));
+
+	ptrauth_keys_switch(keys);
+
+	return 0;
+}
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -57,9 +57,10 @@
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
+#include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>

-#ifdef CONFIG_STACKPROTECTOR
+#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
 unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
@@ -429,6 +430,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	contextidr_thread_switch(next);
 	entry_task_switch(next);
 	uao_thread_switch(next);
+	ptrauth_thread_switch(next);

 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -496,4 +498,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 void arch_setup_new_exec(void)
 {
 	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+
+	ptrauth_thread_init_user(current);
 }
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -46,6 +46,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/fpsimd.h>
 #include <asm/pgtable.h>
+#include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
 #include <asm/syscall.h>
 #include <asm/traps.h>
@@ -956,6 +957,30 @@ out:

 #endif /* CONFIG_ARM64_SVE */

+#ifdef CONFIG_ARM64_PTR_AUTH
+static int pac_mask_get(struct task_struct *target,
+			const struct user_regset *regset,
+			unsigned int pos, unsigned int count,
+			void *kbuf, void __user *ubuf)
+{
+	/*
+	 * The PAC bits can differ across data and instruction pointers
+	 * depending on TCR_EL1.TBID*, which we may make use of in future, so
+	 * we expose separate masks.
+	 */
+	unsigned long mask = ptrauth_user_pac_mask();
+	struct user_pac_mask uregs = {
+		.data_mask = mask,
+		.insn_mask = mask,
+	};
+
+	if (!system_supports_address_auth())
+		return -EINVAL;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &uregs, 0, -1);
+}
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -968,6 +993,9 @@ enum aarch64_regset {
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SVE,
 #endif
+#ifdef CONFIG_ARM64_PTR_AUTH
+	REGSET_PAC_MASK,
+#endif
 };

 static const struct user_regset aarch64_regsets[] = {
@@ -1037,6 +1065,16 @@ static const struct user_regset aarch64_regsets[] = {
 		.get_size = sve_get_size,
 	},
 #endif
+#ifdef CONFIG_ARM64_PTR_AUTH
+	[REGSET_PAC_MASK] = {
+		.core_note_type = NT_ARM_PAC_MASK,
+		.n = sizeof(struct user_pac_mask) / sizeof(u64),
+		.size = sizeof(u64),
+		.align = sizeof(u64),
+		.get = pac_mask_get,
+		/* this cannot be set dynamically */
+	},
+#endif
 };

 static const struct user_regset_view user_aarch64_view = {
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -32,6 +32,7 @@
 ENTRY(arm64_relocate_new_kernel)

 	/* Setup the list loop variables. */
+	mov	x18, x2				/* x18 = dtb address */
 	mov	x17, x1				/* x17 = kimage_start */
 	mov	x16, x0				/* x16 = kimage_head */
 	raw_dcache_line_size x15, x0		/* x15 = dcache line size */
@@ -107,7 +108,7 @@ ENTRY(arm64_relocate_new_kernel)
 	isb

 	/* Start new image. */
-	mov	x0, xzr
+	mov	x0, x18
 	mov	x1, xzr
 	mov	x2, xzr
 	mov	x3, xzr
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -388,6 +388,7 @@ static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
 		pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
 			 offset, KIMAGE_VADDR);
+		pr_emerg("PHYS_OFFSET: 0x%llx\n", PHYS_OFFSET);
 	} else {
 		pr_emerg("Kernel Offset: disabled\n");
 	}
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -13,7 +13,9 @@
 */
 #include <linux/linkage.h>
 #include <linux/arm-smccc.h>
+
 #include <asm/asm-offsets.h>
+#include <asm/assembler.h>

 	.macro SMCCC instr
 	.cfi_startproc
@@ -40,6 +42,7 @@
 ENTRY(__arm_smccc_smc)
 	SMCCC	smc
 ENDPROC(__arm_smccc_smc)
+EXPORT_SYMBOL(__arm_smccc_smc)

 /*
 * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
@@ -50,3 +53,4 @@ ENDPROC(__arm_smccc_smc)
 ENTRY(__arm_smccc_hvc)
 	SMCCC	hvc
 ENDPROC(__arm_smccc_hvc)
+EXPORT_SYMBOL(__arm_smccc_hvc)
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -141,6 +141,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		}
 	} else {
 		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
+		return ret;
 	}

 	secondary_data.task = NULL;
@@ -151,7 +152,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		if (status == CPU_MMU_OFF)
 			status = READ_ONCE(__early_cpu_boot_status);

-		switch (status) {
+		switch (status & CPU_BOOT_STATUS_MASK) {
 		default:
 			pr_err("CPU%u: failed in unknown state : 0x%lx\n",
 					cpu, status);
@@ -165,6 +166,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 			pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
 		case CPU_STUCK_IN_KERNEL:
 			pr_crit("CPU%u: is stuck in kernel\n", cpu);
+			if (status & CPU_STUCK_REASON_52_BIT_VA)
+				pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
+			if (status & CPU_STUCK_REASON_NO_GRAN)
+				pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K);
 			cpus_stuck_in_kernel++;
 			break;
 		case CPU_PANIC_KERNEL:
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -99,7 +99,8 @@ SECTIONS
 		*(.discard)
 		*(.discard.*)
 		*(.interp .dynamic)
-		*(.dynsym .dynstr .hash)
+		*(.dynsym .dynstr .hash .gnu.hash)
+		*(.eh_frame)
 	}

 	. = KIMAGE_VADDR + TEXT_OFFSET;
@@ -192,12 +193,12 @@ SECTIONS

 	PERCPU_SECTION(L1_CACHE_BYTES)

-	.rela : ALIGN(8) {
+	.rela.dyn : ALIGN(8) {
 		*(.rela .rela*)
 	}

-	__rela_offset	= ABSOLUTE(ADDR(.rela) - KIMAGE_VADDR);
-	__rela_size	= SIZEOF(.rela);
+	__rela_offset	= ABSOLUTE(ADDR(.rela.dyn) - KIMAGE_VADDR);
+	__rela_size	= SIZEOF(.rela.dyn);

 	. = ALIGN(SEGMENT_ALIGN);
 	__initdata_end = .;