Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 4c8b13b..478491f 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,12 +7,12 @@
 AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_armv8_deprecated.o := -I$(src)
 
-CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_insn.o = -pg
-CFLAGS_REMOVE_return_address.o = -pg
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
 # Object file lists.
-arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
+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	\
@@ -27,39 +27,45 @@
 $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
-arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
+obj-$(CONFIG_COMPAT)			+= sys32.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-$(CONFIG_ARM64_MODULE_PLTS)	+= module-plts.o
-arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
-arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
-arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
-arm64-obj-$(CONFIG_CPU_PM)		+= sleep.o suspend.o
-arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
-arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
-arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
-arm64-obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o		\
+ifneq ($(CONFIG_COMPAT_VDSO), y)
+obj-$(CONFIG_COMPAT)			+= sigreturn32.o
+endif
+obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
+obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
+obj-$(CONFIG_MODULES)			+= module.o
+obj-$(CONFIG_ARM64_MODULE_PLTS)		+= module-plts.o
+obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
+obj-$(CONFIG_HW_PERF_EVENTS)		+= perf_event.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
+obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
+obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
+obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+obj-$(CONFIG_KGDB)			+= kgdb.o
+obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o		\
 					   efi-rt-wrapper.o
-arm64-obj-$(CONFIG_PCI)			+= pci.o
-arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
-arm64-obj-$(CONFIG_ACPI)		+= acpi.o
-arm64-obj-$(CONFIG_ACPI_NUMA)		+= acpi_numa.o
-arm64-obj-$(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	\
+obj-$(CONFIG_PCI)			+= pci.o
+obj-$(CONFIG_ARMV8_DEPRECATED)		+= armv8_deprecated.o
+obj-$(CONFIG_ACPI)			+= acpi.o
+obj-$(CONFIG_ACPI_NUMA)			+= acpi_numa.o
+obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
+obj-$(CONFIG_PARAVIRT)			+= paravirt.o
+obj-$(CONFIG_RANDOMIZE_BASE)		+= kaslr.o
+obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
+obj-$(CONFIG_KEXEC_CORE)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
-arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
+obj-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o kexec_image.o
+obj-$(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
+obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
+obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
+obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
+obj-$(CONFIG_ARM64_SSBD)		+= ssbd.o
+obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 
-obj-y					+= $(arm64-obj-y) vdso/ probes/
-obj-m					+= $(arm64-obj-m)
+obj-y					+= vdso/ probes/
+obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/
 head-y					:= head.o
 extra-y					+= $(head-y) vmlinux.lds
 
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index ed46dc1..3a58e9d 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  ARM64 Specific Low-Level ACPI Boot Support
  *
@@ -7,16 +8,11 @@
  *	Author: Hanjun Guo <hanjun.guo@linaro.org>
  *	Author: Tomasz Nowicki <tomasz.nowicki@linaro.org>
  *	Author: Naresh Bhat <naresh.bhat@linaro.org>
- *
- *  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.
  */
 
 #define pr_fmt(fmt) "ACPI: " fmt
 
 #include <linux/acpi.h>
-#include <linux/bootmem.h>
 #include <linux/cpumask.h>
 #include <linux/efi.h>
 #include <linux/efi-bgrt.h>
@@ -28,8 +24,10 @@
 #include <linux/smp.h>
 #include <linux/serial_core.h>
 
+#include <acpi/ghes.h>
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
+#include <asm/daifflags.h>
 #include <asm/pgtable.h>
 #include <asm/smp_plat.h>
 
@@ -154,10 +152,14 @@
 	 */
 	if (table->revision < 5 ||
 	   (table->revision == 5 && fadt->minor_revision < 1)) {
-		pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n",
+		pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n",
 		       table->revision, fadt->minor_revision);
-		ret = -EINVAL;
-		goto out;
+
+		if (!fadt->arm_boot_flags) {
+			ret = -EINVAL;
+			goto out;
+		}
+		pr_err("FADT has ARM boot flags set, assuming 5.1\n");
 	}
 
 	if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) {
@@ -257,3 +259,32 @@
 		return __pgprot(PROT_NORMAL_NC);
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
+
+/*
+ * Claim Synchronous External Aborts as a firmware first notification.
+ *
+ * Used by KVM and the arch do_sea handler.
+ * @regs may be NULL when called from process context.
+ */
+int apei_claim_sea(struct pt_regs *regs)
+{
+	int err = -ENOENT;
+	unsigned long current_flags;
+
+	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
+		return err;
+
+	current_flags = arch_local_save_flags();
+
+	/*
+	 * SEA can interrupt SError, mask it and describe this as an NMI so
+	 * that APEI defers the handling.
+	 */
+	local_daif_restore(DAIF_ERRCTX);
+	nmi_enter();
+	err = ghes_notify_sea();
+	nmi_exit();
+	local_daif_restore(current_flags);
+
+	return err;
+}
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
index 4f4f181..7ff8000 100644
--- a/arch/arm64/kernel/acpi_numa.c
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -18,7 +18,6 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
-#include <linux/bootmem.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/memblock.h>
@@ -46,7 +45,7 @@
 	return -EINVAL;
 }
 
-static int __init acpi_parse_gicc_pxm(struct acpi_subtable_header *header,
+static int __init acpi_parse_gicc_pxm(union acpi_subtable_headers *header,
 				      const unsigned long end)
 {
 	struct acpi_srat_gicc_affinity *pa;
diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c
index 98a20e5..e7c941d 100644
--- a/arch/arm64/kernel/acpi_parking_protocol.c
+++ b/arch/arm64/kernel/acpi_parking_protocol.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * ARM64 ACPI Parking Protocol implementation
  *
  * Authors: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
  *	    Mark Salter <msalter@redhat.com>
- *
- * 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/acpi.h>
 #include <linux/mm.h>
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index b5d6039..d1757ef 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * alternative runtime patching
  * inspired by the x86 version
  *
  * Copyright (C) 2014 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/>.
  */
 
 #define pr_fmt(fmt) "alternatives: " fmt
@@ -32,13 +21,23 @@
 #define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
 #define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
 
-int alternatives_applied;
+static int all_alternatives_applied;
+
+static DECLARE_BITMAP(applied_alternatives, ARM64_NCAPS);
 
 struct alt_region {
 	struct alt_instr *begin;
 	struct alt_instr *end;
 };
 
+bool alternative_is_applied(u16 cpufeature)
+{
+	if (WARN_ON(cpufeature >= ARM64_NCAPS))
+		return false;
+
+	return test_bit(cpufeature, applied_alternatives);
+}
+
 /*
  * Check if the target PC is within an alternative block.
  */
@@ -145,7 +144,8 @@
 	} while (cur += d_size, cur < end);
 }
 
-static void __apply_alternatives(void *alt_region, bool is_module)
+static void __apply_alternatives(void *alt_region,  bool is_module,
+				 unsigned long *feature_mask)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
@@ -155,6 +155,9 @@
 	for (alt = region->begin; alt < region->end; alt++) {
 		int nr_inst;
 
+		if (!test_bit(alt->cpufeature, feature_mask))
+			continue;
+
 		/* Use ARM64_CB_PATCH as an unconditional patch */
 		if (alt->cpufeature < ARM64_CB_PATCH &&
 		    !cpus_have_cap(alt->cpufeature))
@@ -192,6 +195,12 @@
 		dsb(ish);
 		__flush_icache_all();
 		isb();
+
+		/* Ignore ARM64_CB bit from feature mask */
+		bitmap_or(applied_alternatives, applied_alternatives,
+			  feature_mask, ARM64_NCAPS);
+		bitmap_and(applied_alternatives, applied_alternatives,
+			   cpu_hwcaps, ARM64_NCAPS);
 	}
 }
 
@@ -208,14 +217,19 @@
 
 	/* We always have a CPU 0 at this point (__init) */
 	if (smp_processor_id()) {
-		while (!READ_ONCE(alternatives_applied))
+		while (!READ_ONCE(all_alternatives_applied))
 			cpu_relax();
 		isb();
 	} else {
-		BUG_ON(alternatives_applied);
-		__apply_alternatives(&region, false);
+		DECLARE_BITMAP(remaining_capabilities, ARM64_NPATCHABLE);
+
+		bitmap_complement(remaining_capabilities, boot_capabilities,
+				  ARM64_NPATCHABLE);
+
+		BUG_ON(all_alternatives_applied);
+		__apply_alternatives(&region, false, remaining_capabilities);
 		/* Barriers provided by the cache flushing */
-		WRITE_ONCE(alternatives_applied, 1);
+		WRITE_ONCE(all_alternatives_applied, 1);
 	}
 
 	return 0;
@@ -227,6 +241,24 @@
 	stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
 }
 
+/*
+ * This is called very early in the boot process (directly after we run
+ * a feature detect on the boot CPU). No need to worry about other CPUs
+ * here.
+ */
+void __init apply_boot_alternatives(void)
+{
+	struct alt_region region = {
+		.begin	= (struct alt_instr *)__alt_instructions,
+		.end	= (struct alt_instr *)__alt_instructions_end,
+	};
+
+	/* If called on non-boot cpu things could go wrong */
+	WARN_ON(smp_processor_id() != 0);
+
+	__apply_alternatives(&region, false, &boot_capabilities[0]);
+}
+
 #ifdef CONFIG_MODULES
 void apply_alternatives_module(void *start, size_t length)
 {
@@ -234,7 +266,10 @@
 		.begin	= start,
 		.end	= start + length,
 	};
+	DECLARE_BITMAP(all_capabilities, ARM64_NPATCHABLE);
 
-	__apply_alternatives(&region, true);
+	bitmap_fill(all_capabilities, ARM64_NPATCHABLE);
+
+	__apply_alternatives(&region, true, &all_capabilities[0]);
 }
 #endif
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
deleted file mode 100644
index d894a20..0000000
--- a/arch/arm64/kernel/arm64ksyms.c
+++ /dev/null
@@ -1,85 +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 */
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strncmp);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strnlen);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memcpy);
-EXPORT_SYMBOL(__memmove);
-EXPORT_SYMBOL(memchr);
-EXPORT_SYMBOL(memcmp);
-
-	/* 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);
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 92be1d1..ca158be 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2014 ARM Limited
- *
- * 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.
  */
 
 #include <linux/cpu.h>
@@ -177,6 +174,9 @@
 	struct insn_emulation *insn;
 
 	insn = kzalloc(sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return;
+
 	insn->ops = ops;
 	insn->min = INSN_UNDEF;
 
@@ -236,6 +236,8 @@
 
 	insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl),
 			       GFP_KERNEL);
+	if (!insns_sysctl)
+		return;
 
 	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
 	list_for_each_entry(insn, &insn_emulation, node) {
@@ -402,7 +404,7 @@
 
 	/* Check access in reasonable access range for both SWP and SWPB */
 	user_ptr = (const void __user *)(unsigned long)(address & ~3);
-	if (!access_ok(VERIFY_WRITE, user_ptr, 4)) {
+	if (!access_ok(user_ptr, 4)) {
 		pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n",
 			address);
 		goto fault;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 323aeb5..2146857 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/asm-offsets.c
  *
  * Copyright (C) 1995-2003 Russell King
  *               2001-2002 Keith Owens
  * 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/arm_sdei.h>
@@ -29,9 +18,9 @@
 #include <asm/fixmap.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
+#include <asm/signal32.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
-#include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
 #include <linux/arm-smccc.h>
 
@@ -46,17 +35,16 @@
   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();
   DEFINE(S_X0,			offsetof(struct pt_regs, regs[0]));
-  DEFINE(S_X1,			offsetof(struct pt_regs, regs[1]));
   DEFINE(S_X2,			offsetof(struct pt_regs, regs[2]));
-  DEFINE(S_X3,			offsetof(struct pt_regs, regs[3]));
   DEFINE(S_X4,			offsetof(struct pt_regs, regs[4]));
-  DEFINE(S_X5,			offsetof(struct pt_regs, regs[5]));
   DEFINE(S_X6,			offsetof(struct pt_regs, regs[6]));
-  DEFINE(S_X7,			offsetof(struct pt_regs, regs[7]));
   DEFINE(S_X8,			offsetof(struct pt_regs, regs[8]));
   DEFINE(S_X10,			offsetof(struct pt_regs, regs[10]));
   DEFINE(S_X12,			offsetof(struct pt_regs, regs[12]));
@@ -70,17 +58,19 @@
   DEFINE(S_X28,			offsetof(struct pt_regs, regs[28]));
   DEFINE(S_LR,			offsetof(struct pt_regs, regs[30]));
   DEFINE(S_SP,			offsetof(struct pt_regs, sp));
-#ifdef CONFIG_COMPAT
-  DEFINE(S_COMPAT_SP,		offsetof(struct pt_regs, compat_sp));
-#endif
   DEFINE(S_PSTATE,		offsetof(struct pt_regs, pstate));
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
-  DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
   DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
+  DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
+#ifdef CONFIG_COMPAT
+  DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
+  DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET,	offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0));
+  BLANK();
+#endif
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
   BLANK();
   DEFINE(VMA_VM_MM,		offsetof(struct vm_area_struct, vm_mm));
@@ -90,46 +80,11 @@
   BLANK();
   DEFINE(PAGE_SZ,	       	PAGE_SIZE);
   BLANK();
-  DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
   BLANK();
   DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
   BLANK();
-  DEFINE(CLOCK_REALTIME,	CLOCK_REALTIME);
-  DEFINE(CLOCK_MONOTONIC,	CLOCK_MONOTONIC);
-  DEFINE(CLOCK_MONOTONIC_RAW,	CLOCK_MONOTONIC_RAW);
-  DEFINE(CLOCK_REALTIME_RES,	MONOTONIC_RES_NSEC);
-  DEFINE(CLOCK_REALTIME_COARSE,	CLOCK_REALTIME_COARSE);
-  DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE);
-  DEFINE(CLOCK_COARSE_RES,	LOW_RES_NSEC);
-  DEFINE(NSEC_PER_SEC,		NSEC_PER_SEC);
-  BLANK();
-  DEFINE(VDSO_CS_CYCLE_LAST,	offsetof(struct vdso_data, cs_cycle_last));
-  DEFINE(VDSO_RAW_TIME_SEC,	offsetof(struct vdso_data, raw_time_sec));
-  DEFINE(VDSO_RAW_TIME_NSEC,	offsetof(struct vdso_data, raw_time_nsec));
-  DEFINE(VDSO_XTIME_CLK_SEC,	offsetof(struct vdso_data, xtime_clock_sec));
-  DEFINE(VDSO_XTIME_CLK_NSEC,	offsetof(struct vdso_data, xtime_clock_nsec));
-  DEFINE(VDSO_XTIME_CRS_SEC,	offsetof(struct vdso_data, xtime_coarse_sec));
-  DEFINE(VDSO_XTIME_CRS_NSEC,	offsetof(struct vdso_data, xtime_coarse_nsec));
-  DEFINE(VDSO_WTM_CLK_SEC,	offsetof(struct vdso_data, wtm_clock_sec));
-  DEFINE(VDSO_WTM_CLK_NSEC,	offsetof(struct vdso_data, wtm_clock_nsec));
-  DEFINE(VDSO_TB_SEQ_COUNT,	offsetof(struct vdso_data, tb_seq_count));
-  DEFINE(VDSO_CS_MONO_MULT,	offsetof(struct vdso_data, cs_mono_mult));
-  DEFINE(VDSO_CS_RAW_MULT,	offsetof(struct vdso_data, cs_raw_mult));
-  DEFINE(VDSO_CS_SHIFT,		offsetof(struct vdso_data, cs_shift));
-  DEFINE(VDSO_TZ_MINWEST,	offsetof(struct vdso_data, tz_minuteswest));
-  DEFINE(VDSO_TZ_DSTTIME,	offsetof(struct vdso_data, tz_dsttime));
-  DEFINE(VDSO_USE_SYSCALL,	offsetof(struct vdso_data, use_syscall));
-  BLANK();
-  DEFINE(TVAL_TV_SEC,		offsetof(struct timeval, tv_sec));
-  DEFINE(TVAL_TV_USEC,		offsetof(struct timeval, tv_usec));
-  DEFINE(TSPEC_TV_SEC,		offsetof(struct timespec, tv_sec));
-  DEFINE(TSPEC_TV_NSEC,		offsetof(struct timespec, tv_nsec));
-  BLANK();
-  DEFINE(TZ_MINWEST,		offsetof(struct timezone, tz_minuteswest));
-  DEFINE(TZ_DSTTIME,		offsetof(struct timezone, tz_dsttime));
-  BLANK();
   DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
   BLANK();
@@ -137,15 +92,18 @@
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
+  DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
   DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
+  DEFINE(CPU_APIBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
+  DEFINE(CPU_APDAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));
+  DEFINE(CPU_APDBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDBKEYLO_EL1]));
+  DEFINE(CPU_APGAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1]));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
-  DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
-  DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
-  DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
   DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
+  DEFINE(HOST_DATA_CONTEXT,	offsetof(struct kvm_host_data, host_ctxt));
 #endif
 #ifdef CONFIG_CPU_PM
-  DEFINE(CPU_SUSPEND_SZ,	sizeof(struct cpu_suspend_ctx));
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
   DEFINE(MPIDR_HASH_MASK,	offsetof(struct mpidr_hash, mask));
   DEFINE(MPIDR_HASH_SHIFTS,	offsetof(struct mpidr_hash, shift_aff));
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 0bf0a83..7fa6828 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  ARM64 cacheinfo support
  *
  *  Copyright (C) 2015 ARM Ltd.
  *  All Rights Reserved
- *
- * 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 "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; 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/acpi.h>
@@ -28,6 +17,15 @@
 #define CLIDR_CTYPE(clidr, level)	\
 	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
 
+int cache_line_size(void)
+{
+	if (coherency_max_size != 0)
+		return coherency_max_size;
+
+	return cache_line_size_of_cpu();
+}
+EXPORT_SYMBOL_GPL(cache_line_size);
+
 static inline enum cache_type get_cache_type(int level)
 {
 	u64 clidr;
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 8021b46..6ea337d 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * CPU reset routines
  *
  * Copyright (C) 2001 Deep Blue Solutions Ltd.
  * Copyright (C) 2012 ARM Ltd.
  * Copyright (C) 2015 Huawei Futurewei Technologies.
- *
- * 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.
  */
 
 #include <linux/linkage.h>
@@ -22,11 +19,11 @@
  * __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
diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
index fad90e4..ed50e95 100644
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * CPU reset routines
  *
  * Copyright (C) 2015 Huawei Futurewei Technologies.
- *
- * 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.
  */
 
 #ifndef _ARM64_CPU_RESET_H
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index dec1089..93f34b4 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -1,27 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Contains CPU specific errata definitions
  *
  * Copyright (C) 2014 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/arm-smccc.h>
 #include <linux/psci.h>
 #include <linux/types.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/smp_plat.h>
 
 static bool __maybe_unused
 is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
@@ -68,26 +59,47 @@
 has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 			  int scope)
 {
-	u64 mask = CTR_CACHE_MINLINE_MASK;
-
-	/* Skip matching the min line sizes for cache type check */
-	if (entry->capability == ARM64_MISMATCHED_CACHE_TYPE)
-		mask ^= arm64_ftr_reg_ctrel0.strict_mask;
+	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	u64 sys = arm64_ftr_reg_ctrel0.sys_val & mask;
+	u64 ctr_raw, ctr_real;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return (read_cpuid_cachetype() & mask) !=
-	       (arm64_ftr_reg_ctrel0.sys_val & mask);
+
+	/*
+	 * We want to make sure that all the CPUs in the system expose
+	 * a consistent CTR_EL0 to make sure that applications behaves
+	 * correctly with migration.
+	 *
+	 * If a CPU has CTR_EL0.IDC but does not advertise it via CTR_EL0 :
+	 *
+	 * 1) It is safe if the system doesn't support IDC, as CPU anyway
+	 *    reports IDC = 0, consistent with the rest.
+	 *
+	 * 2) If the system has IDC, it is still safe as we trap CTR_EL0
+	 *    access on this CPU via the ARM64_HAS_CACHE_IDC capability.
+	 *
+	 * So, we need to make sure either the raw CTR_EL0 or the effective
+	 * CTR_EL0 matches the system's copy to allow a secondary CPU to boot.
+	 */
+	ctr_raw = read_cpuid_cachetype() & mask;
+	ctr_real = read_cpuid_effective_cachetype() & mask;
+
+	return (ctr_real != sys) && (ctr_raw != sys);
 }
 
 static void
 cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 {
-	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
+	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+
+	/* 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))
+		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
 atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
@@ -109,14 +121,23 @@
 	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
-				      const char *hyp_vecs_start,
-				      const char *hyp_vecs_end)
+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;
 
-	spin_lock(&bp_lock);
+	/*
+	 * detect_harden_bp_fw() passes NULL for the hyp_vecs start/end if
+	 * we're a guest. Skip the hyp-vectors work.
+	 */
+	if (!hyp_vecs_start) {
+		__this_cpu_write(bp_hardening_data.fn, fn);
+		return;
+	}
+
+	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);
@@ -132,13 +153,13 @@
 
 	__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
 #define __smccc_workaround_1_smc_end		NULL
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
 {
@@ -146,23 +167,6 @@
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
-				     bp_hardening_cb_t fn,
-				     const char *hyp_vecs_start,
-				     const char *hyp_vecs_end)
-{
-	u64 pfr0;
-
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
-	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
-	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
-		return;
-
-	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
-}
-
 #include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
@@ -189,60 +193,83 @@
 		     : "=&r" (tmp));
 }
 
-static void
-enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+static bool __nospectre_v2;
+static int __init parse_nospectre_v2(char *str)
+{
+	__nospectre_v2 = true;
+	return 0;
+}
+early_param("nospectre_v2", parse_nospectre_v2);
+
+/*
+ * -1: No workaround
+ *  0: No workaround required
+ *  1: Workaround installed
+ */
+static int detect_harden_bp_fw(void)
 {
 	bp_hardening_cb_t cb;
 	void *smccc_start, *smccc_end;
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return;
+		return -1;
 
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_hvc_arch_workaround_1;
-		/* This is a guest, no need to patch KVM vectors */
-		smccc_start = NULL;
-		smccc_end = NULL;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_hvc_arch_workaround_1;
+			/* This is a guest, no need to patch KVM vectors */
+			smccc_start = NULL;
+			smccc_end = NULL;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	case PSCI_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc_start;
-		smccc_end = __smccc_workaround_1_smc_end;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_smc_arch_workaround_1;
+			smccc_start = __smccc_workaround_1_smc_start;
+			smccc_end = __smccc_workaround_1_smc_end;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	default:
-		return;
+		return -1;
 	}
 
 	if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
 	    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1))
 		cb = qcom_link_stack_sanitization;
 
-	install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
+	if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR))
+		install_bp_hardening_cb(cb, smccc_start, smccc_end);
 
-	return;
+	return 1;
 }
-#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
-#ifdef CONFIG_ARM64_SSBD
 DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
 
 int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
+static bool __ssb_safe = true;
 
 static const struct ssbd_options {
 	const char	*str;
@@ -312,6 +339,19 @@
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
+		pr_info_once("SSBD disabled by kernel configuration\n");
+		return;
+	}
+
+	if (this_cpu_has_cap(ARM64_SSBS)) {
+		if (state)
+			asm volatile(SET_PSTATE_SSBS(0));
+		else
+			asm volatile(SET_PSTATE_SSBS(1));
+		return;
+	}
+
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
@@ -333,11 +373,28 @@
 	struct arm_smccc_res res;
 	bool required = true;
 	s32 val;
+	bool this_cpu_safe = false;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
+	if (cpu_mitigations_off())
+		ssbd_state = ARM64_SSBD_FORCE_DISABLE;
+
+	/* delay setting __ssb_safe until we get a firmware response */
+	if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list))
+		this_cpu_safe = true;
+
+	if (this_cpu_has_cap(ARM64_SSBS)) {
+		if (!this_cpu_safe)
+			__ssb_safe = false;
+		required = false;
+		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;
 	}
 
@@ -354,6 +411,8 @@
 
 	default:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -362,14 +421,18 @@
 	switch (val) {
 	case SMCCC_RET_NOT_SUPPORTED:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 
+	/* machines with mixed mitigation requirements must not return this */
 	case SMCCC_RET_NOT_REQUIRED:
 		pr_info_once("%s mitigation not required\n", entry->desc);
 		ssbd_state = ARM64_SSBD_MITIGATED;
 		return false;
 
 	case SMCCC_RET_SUCCESS:
+		__ssb_safe = false;
 		required = true;
 		break;
 
@@ -379,12 +442,13 @@
 
 	default:
 		WARN_ON(1);
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
 	switch (ssbd_state) {
 	case ARM64_SSBD_FORCE_DISABLE:
-		pr_info_once("%s disabled from command-line\n", entry->desc);
 		arm64_set_ssbd_mitigation(false);
 		required = false;
 		break;
@@ -397,7 +461,6 @@
 		break;
 
 	case ARM64_SSBD_FORCE_ENABLE:
-		pr_info_once("%s forced from command-line\n", entry->desc);
 		arm64_set_ssbd_mitigation(true);
 		required = true;
 		break;
@@ -407,9 +470,50 @@
 		break;
 	}
 
+out_printmsg:
+	switch (ssbd_state) {
+	case ARM64_SSBD_FORCE_DISABLE:
+		pr_info_once("%s disabled from command-line\n", entry->desc);
+		break;
+
+	case ARM64_SSBD_FORCE_ENABLE:
+		pr_info_once("%s forced from command-line\n", entry->desc);
+		break;
+	}
+
 	return required;
 }
-#endif	/* CONFIG_ARM64_SSBD */
+
+/* known invulnerable cores */
+static const struct midr_range arm64_ssb_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	{},
+};
+
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
+
+static bool
+has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry,
+			       int scope)
+{
+	u32 midr = read_cpuid_id();
+	/* Cortex-A76 r0p0 - r3p1 */
+	struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode();
+}
+#endif
+
+static void __maybe_unused
+cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
+{
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
+}
 
 #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max)	\
 	.matches = is_affected_midr_range,			\
@@ -448,58 +552,103 @@
 	.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,			\
 	CAP_MIDR_RANGE_LIST(midr_list)
 
+/* Track overall mitigation state. We are only mitigated if all cores are ok */
+static bool __hardenbp_enab = true;
+static bool __spectrev2_safe = true;
+
+int get_spectre_v2_workaround_state(void)
+{
+	if (__spectrev2_safe)
+		return ARM64_BP_HARDEN_NOT_REQUIRED;
+
+	if (!__hardenbp_enab)
+		return ARM64_BP_HARDEN_UNKNOWN;
+
+	return ARM64_BP_HARDEN_WA_NEEDED;
+}
+
 /*
- * 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.
+ * List of CPUs that do not need any Spectre-v2 mitigation at all.
+ */
+static const struct midr_range spectre_v2_safe_list[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	{ /* sentinel */ }
+};
+
+/*
+ * Track overall bp hardening for all heterogeneous cores in the machine.
+ * We are only considered "safe" if all booted cores are known safe.
  */
 static bool __maybe_unused
-multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, int scope)
+check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 {
-	const struct arm64_cpu_capabilities *caps;
+	int need_wa;
 
-	for (caps = entry->match_list; caps->matches; caps++)
-		if (caps->matches(caps, scope))
-			return true;
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
-	return false;
+	/* If the CPU has CSV2 set, we're safe */
+	if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1),
+						 ID_AA64PFR0_CSV2_SHIFT))
+		return false;
+
+	/* Alternatively, we have a list of unaffected CPUs */
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+		return false;
+
+	/* Fallback to firmware detection */
+	need_wa = detect_harden_bp_fw();
+	if (!need_wa)
+		return false;
+
+	__spectrev2_safe = false;
+
+	if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) {
+		pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	/* forced off */
+	if (__nospectre_v2 || cpu_mitigations_off()) {
+		pr_info_once("spectrev2 mitigation disabled by command line option\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	if (need_wa < 0) {
+		pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n");
+		__hardenbp_enab = false;
+	}
+
+	return (need_wa > 0);
 }
 
-/*
- * 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
-
-/*
- * List of CPUs where we need to issue a psci call to
- * harden the branch predictor.
- */
-static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
+static const __maybe_unused struct midr_range tx2_family_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
 	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
-	MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
 	{},
 };
 
-#endif
+static bool __maybe_unused
+needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
+			 int scope)
+{
+	int i;
+
+	if (!is_affected_midr_range_list(entry, scope) ||
+	    !is_hyp_mode_available())
+		return false;
+
+	for_each_possible_cpu(i) {
+		if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0)
+			return true;
+	}
+
+	return false;
+}
 
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
@@ -511,24 +660,124 @@
 
 #endif
 
-const struct arm64_cpu_capabilities arm64_errata[] = {
+#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
+static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
+	{
+		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0)
+	},
+	{
+		.midr_range.model = MIDR_QCOM_KRYO,
+		.matches = is_kryo_midr,
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1286807
+	{
+		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
+#endif
+	{},
+};
+#endif
+
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+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
+
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+/*
+ * - 1188873 affects r0p0 to r2p0
+ * - 1418040 affects r0p0 to r3p1
+ */
+static const struct midr_range erratum_1418040_list[] = {
+	/* Cortex-A76 r0p0 to r3p1 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
+	/* Neoverse-N1 r0p0 to r3p1 */
+	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1),
+	{},
+};
+#endif
+
+#ifdef CONFIG_ARM64_ERRATUM_845719
+static const struct midr_range erratum_845719_list[] = {
+	/* Cortex-A53 r0p[01234] */
+	MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+	/* Brahma-B53 r0p[0] */
+	MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	{},
+};
+#endif
+
+#ifdef CONFIG_ARM64_ERRATUM_843419
+static const struct arm64_cpu_capabilities erratum_843419_list[] = {
 	{
-	/* Cortex-A53 r0p[01] */
-		.desc = "ARM errata 819472",
+		/* Cortex-A53 r0p[01234] */
+		.matches = is_affected_midr_range,
+		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+		MIDR_FIXED(0x4, BIT(8)),
+	},
+	{
+		/* Brahma-B53 r0p[0] */
+		.matches = is_affected_midr_range,
+		ERRATA_MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	},
+	{},
+};
+#endif
+
+const struct arm64_cpu_capabilities arm64_errata[] = {
+#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
+	{
+		.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
@@ -554,19 +803,18 @@
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_843419
 	{
-	/* Cortex-A53 r0p[01234] */
 		.desc = "ARM erratum 843419",
 		.capability = ARM64_WORKAROUND_843419,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
-		MIDR_FIXED(0x4, BIT(8)),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = erratum_843419_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
-	/* Cortex-A53 r0p[01234] */
 		.desc = "ARM erratum 845719",
 		.capability = ARM64_WORKAROUND_845719,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+		ERRATA_MIDR_RANGE_LIST(erratum_845719_list),
 	},
 #endif
 #ifdef CONFIG_CAVIUM_ERRATUM_23154
@@ -579,51 +827,20 @@
 #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
 	{
-		.desc = "Mismatched cache line size",
-		.capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
-		.matches = has_mismatched_cache_type,
-		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
-		.cpu_enable = cpu_enable_trap_ctr_access,
-	},
-	{
-		.desc = "Mismatched cache type",
+		.desc = "Mismatched cache type (CTR_EL0)",
 		.capability = ARM64_MISMATCHED_CACHE_TYPE,
 		.matches = has_mismatched_cache_type,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
@@ -631,23 +848,20 @@
 	},
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
 	{
-		.desc = "Qualcomm Technologies Falkor erratum 1003",
-		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
-		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0),
-	},
-	{
-		.desc = "Qualcomm Technologies Kryo erratum 1003",
+		.desc = "Qualcomm Technologies Falkor/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_QCOM_FALKOR_ERRATUM_1009
+#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
 	{
-		.desc = "Qualcomm Technologies Falkor erratum 1009",
+		.desc = "Qualcomm erratum 1009, ARM erratum 1286807",
 		.capability = ARM64_WORKAROUND_REPEAT_TLBI,
-		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = arm64_repeat_tlbi_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_858921
@@ -658,13 +872,11 @@
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 	},
 #endif
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
-		.cpu_enable = enable_smccc_arch_workaround_1,
-		ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = check_branch_predictor,
 	},
-#endif
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 	{
 		.desc = "EL2 vector hardening",
@@ -672,14 +884,86 @@
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
 #endif
-#ifdef CONFIG_ARM64_SSBD
 	{
 		.desc = "Speculative Store Bypass Disable",
 		.capability = ARM64_SSBD,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_ssbd_mitigation,
+		.midr_range_list = arm64_ssb_cpus,
+	},
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+	{
+		.desc = "ARM erratum 1418040",
+		.capability = ARM64_WORKAROUND_1418040,
+		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
+	},
+#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
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+	{
+		.desc = "ARM erratum 1463225",
+		.capability = ARM64_WORKAROUND_1463225,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_cortex_a76_erratum_1463225,
+	},
+#endif
+#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+		.matches = needs_tx2_tvm_workaround,
+	},
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (PRFM removal)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 	},
 #endif
 	{
 	}
 };
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	switch (get_spectre_v2_workaround_state()) {
+	case ARM64_BP_HARDEN_NOT_REQUIRED:
+		return sprintf(buf, "Not affected\n");
+        case ARM64_BP_HARDEN_WA_NEEDED:
+		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+        case ARM64_BP_HARDEN_UNKNOWN:
+	default:
+		return sprintf(buf, "Vulnerable\n");
+	}
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (__ssb_safe)
+		return sprintf(buf, "Not affected\n");
+
+	switch (ssbd_state) {
+	case ARM64_SSBD_KERNEL:
+	case ARM64_SSBD_FORCE_ENABLE:
+		if (IS_ENABLED(CONFIG_ARM64_SSBD))
+			return sprintf(buf,
+			    "Mitigation: Speculative Store Bypass disabled via prctl\n");
+	}
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index ea00124..7e07072 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * CPU kernel entry/exit control
  *
  * Copyright (C) 2013 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/acpi.h>
@@ -85,6 +74,7 @@
 				pr_err("%pOF: missing enable-method property\n",
 					dn);
 		}
+		of_node_put(dn);
 	} else {
 		enable_method = acpi_get_enable_method(cpu);
 		if (!enable_method) {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 93f69d8..80f459a 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1,29 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Contains CPU feature definitions
  *
  * Copyright (C) 2015 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/>.
  */
 
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
 #include <linux/cpumask.h>
+#include <linux/crash_dump.h>
 #include <linux/sort.h>
 #include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -34,8 +25,8 @@
 #include <asm/traps.h>
 #include <asm/virt.h>
 
-unsigned long elf_hwcap __read_mostly;
-EXPORT_SYMBOL_GPL(elf_hwcap);
+/* Kernel representation of AT_HWCAP and AT_HWCAP2 */
+static unsigned long elf_hwcap __read_mostly;
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP_DEFAULT	\
@@ -51,6 +42,10 @@
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcaps);
+static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS];
+
+/* Need also bit for ARM64_CB_PATCH */
+DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
 
 /*
  * Flag to indicate if we have computed the system wide
@@ -117,6 +112,7 @@
 static bool __maybe_unused
 cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
 
+static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap);
 
 /*
  * NOTE: Any changes to the visibility of features should be kept in
@@ -139,9 +135,19 @@
 };
 
 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, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_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,
 };
@@ -164,10 +170,37 @@
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+	ARM64_FTR_END,
+};
+
+static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+	/*
+	 * We already refuse to boot CPUs that don't support our configured
+	 * page size, so we can only detect mismatches for a page size other
+	 * than the one we're currently using. Unfortunately, SoCs like this
+	 * exist in the wild so, even though we don't like it, we'll have to go
+	 * along with it and treat them as non-strict.
+	 */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
 	/* Linux shouldn't care about secure memory */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
@@ -206,8 +239,8 @@
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1),
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
@@ -371,8 +404,8 @@
 
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
-	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz),
-	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
+	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
+	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -449,6 +482,10 @@
 	case FTR_LOWER_SAFE:
 		ret = new < cur ? new : cur;
 		break;
+	case FTR_HIGHER_OR_ZERO_SAFE:
+		if (!cur || !new)
+			break;
+		/* Fallthrough */
 	case FTR_HIGHER_SAFE:
 		ret = new > cur ? new : cur;
 		break;
@@ -511,6 +548,29 @@
 }
 
 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)
@@ -557,6 +617,12 @@
 	}
 
 	/*
+	 * 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.
 	 */
@@ -657,7 +723,6 @@
 
 	/*
 	 * EL3 is not our concern.
-	 * ID_AA64PFR1 is currently RES0.
 	 */
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
 				      info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
@@ -772,6 +837,7 @@
 
 	read_sysreg_case(SYS_ID_AA64PFR0_EL1);
 	read_sysreg_case(SYS_ID_AA64PFR1_EL1);
+	read_sysreg_case(SYS_ID_AA64ZFR0_EL1);
 	read_sysreg_case(SYS_ID_AA64DFR0_EL1);
 	read_sysreg_case(SYS_ID_AA64DFR1_EL1);
 	read_sysreg_case(SYS_ID_AA64MMFR0_EL1);
@@ -834,7 +900,7 @@
 	u32 midr = read_cpuid_id();
 
 	/* Cavium ThunderX pass 1.x and 2.x */
-	return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX,
+	return midr_is_cpu_model_range(midr, MIDR_THUNDERX,
 		MIDR_CPU_VAR_REV(0, 0),
 		MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK));
 }
@@ -855,11 +921,23 @@
 	if (scope == SCOPE_SYSTEM)
 		ctr = arm64_ftr_reg_ctrel0.sys_val;
 	else
-		ctr = read_cpuid_cachetype();
+		ctr = read_cpuid_effective_cachetype();
 
 	return ctr & BIT(CTR_IDC_SHIFT);
 }
 
+static void cpu_emulate_effective_ctr(const struct arm64_cpu_capabilities *__unused)
+{
+	/*
+	 * If the CPU exposes raw CTR_EL0.IDC = 0, while effectively
+	 * CTR_EL0.IDC = 1 (from CLIDR values), we need to trap accesses
+	 * to the CTR_EL0 on this CPU and emulate it with the real/safe
+	 * value.
+	 */
+	if (!(read_cpuid_cachetype() & BIT(CTR_IDC_SHIFT)))
+		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
+}
+
 static bool has_cache_dic(const struct arm64_cpu_capabilities *entry,
 			  int scope)
 {
@@ -873,7 +951,21 @@
 	return ctr & BIT(CTR_DIC_SHIFT);
 }
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static bool __maybe_unused
+has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	/*
+	 * Kdump isn't guaranteed to power-off all secondary CPUs, CNP
+	 * may share TLB entries with a CPU stuck in the crashed
+	 * kernel.
+	 */
+	 if (is_kdump_kernel())
+		return false;
+
+	return has_cpuid_feature(entry, scope);
+}
+
+static bool __meltdown_safe = true;
 static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
 
 static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
@@ -883,9 +975,26 @@
 	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),
+		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		{ /* sentinel */ }
 	};
-	char const *str = "command line option";
+	char const *str = "kpti command line option";
+	bool meltdown_safe;
+
+	meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+
+	/* Defer to CPU feature registers */
+	if (has_cpuid_feature(entry, scope))
+		meltdown_safe = true;
+
+	if (!meltdown_safe)
+		__meltdown_safe = false;
 
 	/*
 	 * For reasons that aren't entirely clear, enabling KPTI on Cavium
@@ -897,6 +1006,24 @@
 		__kpti_forced = -1;
 	}
 
+	/* Useful for KASLR robustness */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) {
+		if (!__kpti_forced) {
+			str = "KASLR";
+			__kpti_forced = 1;
+		}
+	}
+
+	if (cpu_mitigations_off() && !__kpti_forced) {
+		str = "mitigations=off";
+		__kpti_forced = -1;
+	}
+
+	if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) {
+		pr_info_once("kernel page table isolation disabled by kernel configuration\n");
+		return false;
+	}
+
 	/* Forced? */
 	if (__kpti_forced) {
 		pr_info_once("kernel page table isolation forced %s by %s\n",
@@ -904,18 +1031,10 @@
 		return __kpti_forced > 0;
 	}
 
-	/* Useful for KASLR robustness */
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return true;
-
-	/* Don't force KPTI for CPUs that are not vulnerable */
-	if (is_midr_in_range_list(read_cpuid_id(), kpti_safe_list))
-		return false;
-
-	/* Defer to CPU feature registers */
-	return !has_cpuid_feature(entry, scope);
+	return !meltdown_safe;
 }
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static void
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
@@ -926,7 +1045,12 @@
 	static bool kpti_applied = false;
 	int cpu = smp_processor_id();
 
-	if (kpti_applied)
+	/*
+	 * We don't need to rewrite the page-tables if either we've done
+	 * it already or we have KASLR enabled and therefore have not
+	 * created any global mappings at all.
+	 */
+	if (kpti_applied || kaslr_offset() > 0)
 		return;
 
 	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
@@ -940,6 +1064,12 @@
 
 	return;
 }
+#else
+static void
+kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
+{
+}
+#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 static int __init parse_kpti(char *str)
 {
@@ -953,7 +1083,6 @@
 	return 0;
 }
 early_param("kpti", parse_kpti);
-#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 static inline void __cpu_enable_hw_dbm(void)
@@ -1036,7 +1165,7 @@
 	 * that, freshly-onlined CPUs will set tpidr_el2, so we don't need to
 	 * do anything here.
 	 */
-	if (!alternatives_applied)
+	if (!alternative_is_applied(ARM64_HAS_VIRT_HOST_EXTN))
 		write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
 }
 #endif
@@ -1049,11 +1178,99 @@
 	WARN_ON(val & (7 << 27 | 7 << 21));
 }
 
+#ifdef CONFIG_ARM64_SSBD
+static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
+{
+	if (user_mode(regs))
+		return 1;
+
+	if (instr & BIT(PSTATE_Imm_shift))
+		regs->pstate |= PSR_SSBS_BIT;
+	else
+		regs->pstate &= ~PSR_SSBS_BIT;
+
+	arm64_skip_faulting_instruction(regs, 4);
+	return 0;
+}
+
+static struct undef_hook ssbs_emulation_hook = {
+	.instr_mask	= ~(1U << PSTATE_Imm_shift),
+	.instr_val	= 0xd500401f | PSTATE_SSBS,
+	.fn		= ssbs_emulation_handler,
+};
+
+static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused)
+{
+	static bool undef_hook_registered = false;
+	static DEFINE_RAW_SPINLOCK(hook_lock);
+
+	raw_spin_lock(&hook_lock);
+	if (!undef_hook_registered) {
+		register_undef_hook(&ssbs_emulation_hook);
+		undef_hook_registered = true;
+	}
+	raw_spin_unlock(&hook_lock);
+
+	if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
+		arm64_set_ssbd_mitigation(false);
+	} else {
+		arm64_set_ssbd_mitigation(true);
+	}
+}
+#endif /* CONFIG_ARM64_SSBD */
+
+#ifdef CONFIG_ARM64_PAN
+static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
+{
+	/*
+	 * We modify PSTATE. This won't work from irq context as the PSTATE
+	 * is discarded once we return from the exception.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
+	asm(SET_PSTATE_PAN(1));
+}
+#endif /* CONFIG_ARM64_PAN */
+
+#ifdef CONFIG_ARM64_RAS_EXTN
+static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
+{
+	/* Firmware may have left a deferred SError in this register. */
+	write_sysreg_s(0, SYS_DISR_EL1);
+}
+#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 */
+
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+static bool enable_pseudo_nmi;
+
+static int __init early_enable_pseudo_nmi(char *p)
+{
+	return strtobool(p, &enable_pseudo_nmi);
+}
+early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi);
+
+static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
+				   int scope)
+{
+	return enable_pseudo_nmi && has_useable_gicv3_cpuif(entry, scope);
+}
+#endif
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
 		.matches = has_useable_gicv3_cpuif,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.field_pos = ID_AA64PFR0_GIC_SHIFT,
@@ -1132,7 +1349,6 @@
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	{
 		.desc = "Kernel page table isolation (KPTI)",
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
@@ -1148,7 +1364,6 @@
 		.matches = unmap_kernel_at_el0,
 		.cpu_enable = kpti_install_ng_mappings,
 	},
-#endif
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
@@ -1166,6 +1381,16 @@
 		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
 		.min_field_value = 1,
 	},
+	{
+		.desc = "Data cache clean to Point of Deep Persistence",
+		.capability = ARM64_HAS_DCPODP,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
+		.min_field_value = 2,
+	},
 #endif
 #ifdef CONFIG_ARM64_SVE
 	{
@@ -1198,6 +1423,7 @@
 		.capability = ARM64_HAS_CACHE_IDC,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_cache_idc,
+		.cpu_enable = cpu_emulate_effective_ctr,
 	},
 	{
 		.desc = "Instruction cache invalidation not required for I/D coherence",
@@ -1236,50 +1462,208 @@
 		.cpu_enable = cpu_enable_hw_dbm,
 	},
 #endif
+	{
+		.desc = "CRC32 instructions",
+		.capability = ARM64_HAS_CRC32,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR0_EL1,
+		.field_pos = ID_AA64ISAR0_CRC32_SHIFT,
+		.min_field_value = 1,
+	},
+#ifdef CONFIG_ARM64_SSBD
+	{
+		.desc = "Speculative Store Bypassing Safe (SSBS)",
+		.capability = ARM64_SSBS,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.field_pos = ID_AA64PFR1_SSBS_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY,
+		.cpu_enable = cpu_enable_ssbs,
+	},
+#endif
+#ifdef CONFIG_ARM64_CNP
+	{
+		.desc = "Common not Private translations",
+		.capability = ARM64_HAS_CNP,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_useable_cnp,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_CNP_SHIFT,
+		.min_field_value = 1,
+		.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 */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	{
+		/*
+		 * Depends on having GICv3
+		 */
+		.desc = "IRQ priority masking",
+		.capability = ARM64_HAS_IRQ_PRIO_MASKING,
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+		.matches = can_use_gic_priorities,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.field_pos = ID_AA64PFR0_GIC_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = 1,
+	},
+#endif
 	{},
 };
 
-#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),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FLAGM),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_DIT),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
-	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_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
+	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_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),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
+#endif
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
+#ifdef CONFIG_ARM64_PTR_AUTH
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
 #endif
 	{},
 };
@@ -1299,7 +1683,7 @@
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
-		elf_hwcap |= cap->hwcap;
+		cpu_set_feature(cap->hwcap);
 		break;
 #ifdef CONFIG_COMPAT
 	case CAP_COMPAT_HWCAP:
@@ -1322,7 +1706,7 @@
 
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
-		rc = (elf_hwcap & cap->hwcap) != 0;
+		rc = cpu_have_feature(cap->hwcap);
 		break;
 #ifdef CONFIG_COMPAT
 	case CAP_COMPAT_HWCAP:
@@ -1343,58 +1727,55 @@
 static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 {
 	/* We support emulation of accesses to CPU ID feature registers */
-	elf_hwcap |= HWCAP_CPUID;
+	cpu_set_named_feature(CPUID);
 	for (; hwcaps->matches; hwcaps++)
 		if (hwcaps->matches(hwcaps, cpucap_default_scope(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);
+
+		if ((scope_mask & SCOPE_BOOT_CPU) && (caps->type & SCOPE_BOOT_CPU))
+			set_bit(caps->capability, boot_capabilities);
 	}
 }
 
-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;
 }
 
@@ -1402,21 +1783,29 @@
  * 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
@@ -1425,25 +1814,19 @@
 			 * 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);
 }
 
 /*
@@ -1453,16 +1836,17 @@
  *
  * 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);
@@ -1493,7 +1877,7 @@
 		}
 	}
 
-	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);
@@ -1503,12 +1887,6 @@
 	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.
@@ -1545,7 +1923,7 @@
 	unsigned int len = zcr & ZCR_ELx_LEN_MASK;
 
 	if (len < safe_len || sve_verify_vq_map()) {
-		pr_crit("CPU%d: SVE: required vector length(s) missing\n",
+		pr_crit("CPU%d: SVE: vector length support mismatch\n",
 			smp_processor_id());
 		cpu_die_early();
 	}
@@ -1617,12 +1995,45 @@
 	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;
+}
+
+void cpu_set_feature(unsigned int num)
+{
+	WARN_ON(num >= MAX_CPU_FEATURES);
+	elf_hwcap |= BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_set_feature);
+
+bool cpu_have_feature(unsigned int num)
+{
+	WARN_ON(num >= MAX_CPU_FEATURES);
+	return elf_hwcap & BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_have_feature);
+
+unsigned long cpu_get_elf_hwcap(void)
+{
+	/*
+	 * We currently only populate the first 32 bits of AT_HWCAP. Please
+	 * note that for userspace compatibility we guarantee that bits 62
+	 * and 63 will always be returned as 0.
+	 */
+	return lower_32_bits(elf_hwcap);
+}
+
+unsigned long cpu_get_elf_hwcap2(void)
+{
+	return upper_32_bits(elf_hwcap);
 }
 
 static void __init setup_system_capabilities(void)
@@ -1672,6 +2083,11 @@
 	return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO));
 }
 
+static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap)
+{
+	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+}
+
 /*
  * We emulate only the following system register space.
  * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7]
@@ -1733,25 +2149,30 @@
 	return 0;
 }
 
-static int emulate_mrs(struct pt_regs *regs, u32 insn)
+int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt)
 {
 	int rc;
-	u32 sys_reg, dst;
 	u64 val;
 
+	rc = emulate_sys_reg(sys_reg, &val);
+	if (!rc) {
+		pt_regs_write_reg(regs, rt, val);
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+	}
+	return rc;
+}
+
+static int emulate_mrs(struct pt_regs *regs, u32 insn)
+{
+	u32 sys_reg, rt;
+
 	/*
 	 * sys_reg values are defined as used in mrs/msr instruction.
 	 * shift the imm value to get the encoding.
 	 */
 	sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
-	rc = emulate_sys_reg(sys_reg, &val);
-	if (!rc) {
-		dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
-		pt_regs_write_reg(regs, dst, val);
-		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
-	}
-
-	return rc;
+	rt = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
+	return do_emulate_mrs(regs, sys_reg, rt);
 }
 
 static struct undef_hook mrs_hook = {
@@ -1770,8 +2191,14 @@
 
 core_initcall(enable_mrs_emulation);
 
-void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
-	/* Firmware may have left a deferred SError in this register. */
-	write_sysreg_s(0, SYS_DISR_EL1);
+	if (__meltdown_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (arm64_kernel_unmapped_at_el0())
+		return sprintf(buf, "Mitigation: PTI\n");
+
+	return sprintf(buf, "Vulnerable\n");
 }
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index f2d1381..e4d6af2 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * ARM64 CPU idle arch support
  *
  * Copyright (C) 2014 ARM Ltd.
  * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
- *
- * 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.
  */
 
 #include <linux/acpi.h>
@@ -14,6 +11,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/psci.h>
 
 #include <asm/cpuidle.h>
 #include <asm/cpu_ops.h>
@@ -49,17 +47,58 @@
 
 #define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags))
 
+static int psci_acpi_cpu_init_idle(unsigned int cpu)
+{
+	int i, count;
+	struct acpi_lpi_state *lpi;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	if (unlikely(!pr || !pr->flags.has_lpi))
+		return -EINVAL;
+
+	count = pr->power.count - 1;
+	if (count <= 0)
+		return -ENODEV;
+
+	for (i = 0; i < count; i++) {
+		u32 state;
+
+		lpi = &pr->power.lpi_states[i + 1];
+		/*
+		 * Only bits[31:0] represent a PSCI power_state while
+		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification
+		 */
+		state = lpi->address;
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 {
-	return arm_cpuidle_init(cpu);
+	return psci_acpi_cpu_init_idle(cpu);
 }
 
 int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
+	u32 state = lpi->address;
+
 	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
-		return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend,
-						lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter,
+						lpi->index, state);
 	else
-		return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter,
+					     lpi->index, state);
 }
 #endif
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index e9ab7b3..05933c0 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -1,18 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Record and handle CPU attributes.
  *
  * Copyright (C) 2014 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 <asm/arch_timer.h>
 #include <asm/cache.h>
@@ -43,7 +33,7 @@
 DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
 static struct cpuinfo_arm64 boot_cpu_data;
 
-static char *icache_policy_str[] = {
+static const char *icache_policy_str[] = {
 	[0 ... ICACHE_POLICY_PIPT]	= "RESERVED/UNKNOWN",
 	[ICACHE_POLICY_VIPT]		= "VIPT",
 	[ICACHE_POLICY_PIPT]		= "PIPT",
@@ -81,6 +71,19 @@
 	"uscat",
 	"ilrcpc",
 	"flagm",
+	"ssbs",
+	"sb",
+	"paca",
+	"pacg",
+	"dcpodp",
+	"sve2",
+	"sveaes",
+	"svepmull",
+	"svebitperm",
+	"svesha3",
+	"svesm4",
+	"flagm2",
+	"frint",
 	NULL
 };
 
@@ -163,7 +166,7 @@
 #endif /* CONFIG_COMPAT */
 		} else {
 			for (j = 0; hwcap_str[j]; j++)
-				if (elf_hwcap & (1 << j))
+				if (cpu_have_feature(j))
 					seq_printf(m, " %s", hwcap_str[j]);
 		}
 		seq_puts(m, "\n");
@@ -324,7 +327,15 @@
 static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 {
 	info->reg_cntfrq = arch_timer_get_cntfrq();
-	info->reg_ctr = read_cpuid_cachetype();
+	/*
+	 * Use the effective value of the CTR_EL0 than the raw value
+	 * exposed by the CPU. CTR_E0.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
+	 * acurate sanity check and feature enablement.
+	 */
+	info->reg_ctr = read_cpuid_effective_cachetype();
 	info->reg_dczid = read_cpuid(DCZID_EL0);
 	info->reg_midr = read_cpuid_id();
 	info->reg_revidr = read_cpuid(REVIDR_EL1);
diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
index f46d57c..e6e2842 100644
--- a/arch/arm64/kernel/crash_dump.c
+++ b/arch/arm64/kernel/crash_dump.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Routines for doing kexec-based kdump
  *
  * Copyright (C) 2017 Linaro Limited
  * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
- *
- * 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.
  */
 
 #include <linux/crash_dump.h>
@@ -58,7 +55,7 @@
 /**
  * elfcorehdr_read - read from ELF core header
  * @buf: buffer where the data is placed
- * @csize: number of bytes to read
+ * @count: number of bytes to read
  * @ppos: address in the memory
  *
  * This function reads @count bytes from elf core header which exists
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 06ca574..48222a4 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * ARMv8 single-step debug support and mdscr context switching.
  *
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  */
 
@@ -135,6 +124,7 @@
  */
 static int clear_os_lock(unsigned int cpu)
 {
+	write_sysreg(0, osdlr_el1);
 	write_sysreg(0, oslar_el1);
 	isb();
 	return 0;
@@ -163,25 +153,46 @@
 }
 NOKPROBE_SYMBOL(clear_regs_spsr_ss);
 
-/* EL1 Single Step Handler hooks */
-static LIST_HEAD(step_hook);
-static DEFINE_SPINLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(debug_hook_lock);
+static LIST_HEAD(user_step_hook);
+static LIST_HEAD(kernel_step_hook);
 
-void register_step_hook(struct step_hook *hook)
+static void register_debug_hook(struct list_head *node, struct list_head *list)
 {
-	spin_lock(&step_hook_lock);
-	list_add_rcu(&hook->node, &step_hook);
-	spin_unlock(&step_hook_lock);
+	spin_lock(&debug_hook_lock);
+	list_add_rcu(node, list);
+	spin_unlock(&debug_hook_lock);
+
 }
 
-void unregister_step_hook(struct step_hook *hook)
+static void unregister_debug_hook(struct list_head *node)
 {
-	spin_lock(&step_hook_lock);
-	list_del_rcu(&hook->node);
-	spin_unlock(&step_hook_lock);
+	spin_lock(&debug_hook_lock);
+	list_del_rcu(node);
+	spin_unlock(&debug_hook_lock);
 	synchronize_rcu();
 }
 
+void register_user_step_hook(struct step_hook *hook)
+{
+	register_debug_hook(&hook->node, &user_step_hook);
+}
+
+void unregister_user_step_hook(struct step_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_step_hook(struct step_hook *hook)
+{
+	register_debug_hook(&hook->node, &kernel_step_hook);
+}
+
+void unregister_kernel_step_hook(struct step_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
+}
+
 /*
  * Call registered single step handlers
  * There is no Syndrome info to check for determining the handler.
@@ -191,18 +202,21 @@
 static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 {
 	struct step_hook *hook;
+	struct list_head *list;
 	int retval = DBG_HOOK_ERROR;
 
-	rcu_read_lock();
+	list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
 
-	list_for_each_entry_rcu(hook, &step_hook, node)	{
+	/*
+	 * Since single-step exception disables interrupt, this function is
+	 * entirely not preemptible, and we can use rcu list safely here.
+	 */
+	list_for_each_entry_rcu(hook, list, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
 	}
 
-	rcu_read_unlock();
-
 	return retval;
 }
 NOKPROBE_SYMBOL(call_step_hook);
@@ -210,13 +224,6 @@
 static void send_user_sigtrap(int si_code)
 {
 	struct pt_regs *regs = current_pt_regs();
-	siginfo_t info;
-
-	clear_siginfo(&info);
-	info.si_signo	= SIGTRAP;
-	info.si_errno	= 0;
-	info.si_code	= si_code;
-	info.si_addr	= (void __user *)instruction_pointer(regs);
 
 	if (WARN_ON(!user_mode(regs)))
 		return;
@@ -224,10 +231,12 @@
 	if (interrupts_enabled(regs))
 		local_irq_enable();
 
-	arm64_force_sig_info(&info, "User debug trap", current);
+	arm64_force_sig_fault(SIGTRAP, si_code,
+			     (void __user *)instruction_pointer(regs),
+			     "User debug trap");
 }
 
-static int single_step_handler(unsigned long addr, unsigned int esr,
+static int single_step_handler(unsigned long unused, unsigned int esr,
 			       struct pt_regs *regs)
 {
 	bool handler_found = false;
@@ -239,10 +248,6 @@
 	if (!reinstall_suspended_bps(regs))
 		return 0;
 
-#ifdef	CONFIG_KPROBES
-	if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
-		handler_found = true;
-#endif
 	if (!handler_found && call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
 		handler_found = true;
 
@@ -269,61 +274,61 @@
 }
 NOKPROBE_SYMBOL(single_step_handler);
 
-/*
- * Breakpoint handler is re-entrant as another breakpoint can
- * hit within breakpoint handler, especically in kprobes.
- * Use reader/writer locks instead of plain spinlock.
- */
-static LIST_HEAD(break_hook);
-static DEFINE_SPINLOCK(break_hook_lock);
+static LIST_HEAD(user_break_hook);
+static LIST_HEAD(kernel_break_hook);
 
-void register_break_hook(struct break_hook *hook)
+void register_user_break_hook(struct break_hook *hook)
 {
-	spin_lock(&break_hook_lock);
-	list_add_rcu(&hook->node, &break_hook);
-	spin_unlock(&break_hook_lock);
+	register_debug_hook(&hook->node, &user_break_hook);
 }
 
-void unregister_break_hook(struct break_hook *hook)
+void unregister_user_break_hook(struct break_hook *hook)
 {
-	spin_lock(&break_hook_lock);
-	list_del_rcu(&hook->node);
-	spin_unlock(&break_hook_lock);
-	synchronize_rcu();
+	unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_break_hook(struct break_hook *hook)
+{
+	register_debug_hook(&hook->node, &kernel_break_hook);
+}
+
+void unregister_kernel_break_hook(struct break_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 {
 	struct break_hook *hook;
+	struct list_head *list;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(hook, &break_hook, node)
-		if ((esr & hook->esr_mask) == hook->esr_val)
+	list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
+
+	/*
+	 * Since brk exception disables interrupt, this function is
+	 * entirely not preemptible, and we can use rcu list safely here.
+	 */
+	list_for_each_entry_rcu(hook, list, node) {
+		unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+		if ((comment & ~hook->mask) == hook->imm)
 			fn = hook->fn;
-	rcu_read_unlock();
+	}
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
 NOKPROBE_SYMBOL(call_break_hook);
 
-static int brk_handler(unsigned long addr, unsigned int esr,
+static int brk_handler(unsigned long unused, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	bool handler_found = false;
+	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
+		return 0;
 
-#ifdef	CONFIG_KPROBES
-	if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
-		if (kprobe_breakpoint_handler(regs, esr) == DBG_HOOK_HANDLED)
-			handler_found = true;
-	}
-#endif
-	if (!handler_found && call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
-		handler_found = true;
-
-	if (!handler_found && user_mode(regs)) {
+	if (user_mode(regs)) {
 		send_user_sigtrap(TRAP_BRKPT);
-	} else if (!handler_found) {
+	} else {
 		pr_warn("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
 	}
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 6b9736c..304d5b0 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * EFI entry point.
  *
  * Copyright (C) 2013, 2014 Red Hat, Inc.
  * Author: Mark Salter <msalter@redhat.com>
- *
- * 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.
- *
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S
index 613fc30..a7cfacc 100644
--- a/arch/arm64/kernel/efi-header.S
+++ b/arch/arm64/kernel/efi-header.S
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2013 - 2017 Linaro, Ltd.
  * Copyright (C) 2013, 2014 Red Hat, Inc.
- *
- * 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.
  */
 
 #include <linux/pe.h>
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index 05235eb..3fc7110 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * 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.
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 4f9acb5..d0cf596 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Extensible Firmware Interface
  *
  * Based on Extensible Firmware Interface Specification version 2.4
  *
  * Copyright (C) 2013, 2014 Linaro 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.
- *
  */
 
 #include <linux/efi.h>
@@ -86,8 +82,7 @@
 	return 0;
 }
 
-static int __init set_permissions(pte_t *ptep, pgtable_t token,
-				  unsigned long addr, void *data)
+static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
 	pte_t pte = READ_ONCE(*ptep);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 12d4958..0f24eae 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * FP/SIMD state saving and restoring
  *
  * Copyright (C) 2012 ARM Ltd.
  * Author: Catalin Marinas <catalin.marinas@arm.com>
- *
- * 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/linkage.h>
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 1175f58..33d003d 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * arch/arm64/kernel/entry-ftrace.S
  *
  * Copyright (C) 2013 Linaro Limited
  * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
- *
- * 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.
  */
 
 #include <linux/linkage.h>
@@ -79,7 +76,6 @@
 	.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 +117,8 @@
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 	mcount_exit
 ENDPROC(_mcount)
+EXPORT_SYMBOL(_mcount)
+NOKPROBE(_mcount)
 
 #else /* CONFIG_DYNAMIC_FTRACE */
 /*
@@ -132,6 +130,8 @@
 ENTRY(_mcount)
 	ret
 ENDPROC(_mcount)
+EXPORT_SYMBOL(_mcount)
+NOKPROBE(_mcount)
 
 /*
  * void ftrace_caller(unsigned long return_address)
@@ -148,14 +148,12 @@
 	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 +167,6 @@
 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 +177,10 @@
  * 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 +189,27 @@
  * 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 */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 8556876..cf3bd29 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -1,21 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Low-level exception handling code
  *
  * Copyright (C) 2012 ARM Ltd.
  * Authors:	Catalin Marinas <catalin.marinas@arm.com>
  *		Will Deacon <will.deacon@arm.com>
- *
- * 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/arm-smccc.h>
@@ -41,9 +30,9 @@
  * Context tracking subsystem.  Used to instrument transitions
  * between user and kernel mode.
  */
-	.macro ct_user_exit
+	.macro ct_user_exit_irqoff
 #ifdef CONFIG_CONTEXT_TRACKING
-	bl	context_tracking_user_exit
+	bl	enter_from_user_mode
 #endif
 	.endm
 
@@ -185,7 +174,7 @@
 
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	get_thread_info tsk
+	get_current_task tsk
 	/* Save the task's original addr_limit and set USER_DS */
 	ldr	x20, [tsk, #TSK_TI_ADDR_LIMIT]
 	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
@@ -249,9 +238,16 @@
 	msr	sp_el0, tsk
 	.endif
 
+	/* Save pmr */
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	mrs_s	x20, SYS_ICC_PMR_EL1
+	str	x20, [sp, #S_PMR_SAVE]
+alternative_else_nop_endif
+
 	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
+	 * x20 - ICC_PMR_EL1
 	 * x21 - aborted SP
 	 * x22 - aborted PC
 	 * x23 - aborted PSTATE
@@ -269,6 +265,14 @@
 	/* No need to restore UAO, it will be restored from SPSR_EL1 */
 	.endif
 
+	/* Restore pmr */
+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
+alternative_else_nop_endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -322,6 +326,21 @@
 alternative_else_nop_endif
 #endif
 3:
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if_not ARM64_WORKAROUND_1418040
+	b	4f
+alternative_else_nop_endif
+	/*
+	 * if (x22.mode32 == cntkctl_el1.el0vcten)
+	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
+	 */
+	mrs	x1, cntkctl_el1
+	eon	x0, x1, x22, lsr #3
+	tbz	x0, #1, 4f
+	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x1
+4:
+#endif
 	apply_ssbd 0, x0, x1
 	.endif
 
@@ -344,25 +363,22 @@
 	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
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	4f
+	bne	5f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-4:
+5:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
 	.else
 	eret
 	.endif
+	sb
 	.endm
 
 	.macro	irq_stack_entry
@@ -395,17 +411,7 @@
 	mov	sp, x19
 	.endm
 
-/*
- * These are the registers used in the syscall handler, and allow us to
- * have in theory up to 7 arguments to a function - x0 to x6.
- *
- * x7 is reserved for the system call number in 32-bit mode.
- */
-wsc_nr	.req	w25		// number of system calls
-xsc_nr	.req	x25		// number of system calls (zero-extended)
-wscno	.req	w26		// syscall number
-xscno	.req	x26		// syscall number (zero-extended)
-stbl	.req	x27		// syscall table pointer
+/* GPRs used by entry code */
 tsk	.req	x28		// current thread_info
 
 /*
@@ -419,6 +425,38 @@
 	irq_stack_exit
 	.endm
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	/*
+	 * Set res to 0 if irqs were unmasked in interrupted context.
+	 * Otherwise set res to non-0 value.
+	 */
+	.macro	test_irqs_unmasked res:req, pmr:req
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	sub	\res, \pmr, #GIC_PRIO_IRQON
+alternative_else
+	mov	\res, xzr
+alternative_endif
+	.endm
+#endif
+
+	.macro	gic_prio_kentry_setup, tmp:req
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	mov	\tmp, #(GIC_PRIO_PSR_I_SET | GIC_PRIO_IRQON)
+	msr_s	SYS_ICC_PMR_EL1, \tmp
+	alternative_else_nop_endif
+#endif
+	.endm
+
+	.macro	gic_prio_irq_setup, pmr:req, tmp:req
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	orr	\tmp, \pmr, #GIC_PRIO_PSR_I_SET
+	msr_s	SYS_ICC_PMR_EL1, \tmp
+	alternative_else_nop_endif
+#endif
+	.endm
+
 	.text
 
 /*
@@ -548,10 +586,8 @@
 	b.eq	el1_ia
 	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
 	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
-	b.eq	el1_sp_pc
 	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el1_sp_pc
+	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
@@ -568,14 +604,16 @@
 	 */
 	mrs	x3, far_el1
 	inherit_daif	pstate=x23, tmp=x2
-	clear_address_tag x0, x3
+	untagged_addr	x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
 	kernel_exit 1
-el1_sp_pc:
+el1_pc:
 	/*
-	 * Stack or PC alignment exception handling
+	 * 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
@@ -597,6 +635,7 @@
 	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
@@ -614,7 +653,16 @@
 	.align	6
 el1_irq:
 	kernel_entry 1
+	gic_prio_irq_setup pmr=x20, tmp=x1
 	enable_da_f
+
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	test_irqs_unmasked	res=x0, pmr=x20
+	cbz	x0, 1f
+	bl	asm_nmi_enter
+1:
+#endif
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -622,28 +670,44 @@
 	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?
-	bl	el1_preempt
+	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+	/*
+	 * DA_F were cleared at start of handling. If anything is set in DAIF,
+	 * we come back from an NMI, so skip preemption
+	 */
+	mrs	x0, daif
+	orr	x24, x24, x0
+alternative_else_nop_endif
+	cbnz	x24, 1f				// preempt count != 0 || NMI return path
+	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
 1:
 #endif
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_on
+
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	/*
+	 * When using IRQ priority masking, we can get spurious interrupts while
+	 * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a
+	 * section with interrupts disabled. Skip tracing in those cases.
+	 */
+	test_irqs_unmasked	res=x0, pmr=x20
+	cbz	x0, 1f
+	bl	asm_nmi_exit
+1:
 #endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+	test_irqs_unmasked	res=x0, pmr=x20
+	cbnz	x0, 1f
+#endif
+	bl	trace_hardirqs_on
+1:
+#endif
+
 	kernel_exit 1
 ENDPROC(el1_irq)
 
-#ifdef CONFIG_PREEMPT
-el1_preempt:
-	mov	x24, lr
-1:	bl	preempt_schedule_irq		// irq en/disable is done inside
-	ldr	x0, [tsk, #TSK_TI_FLAGS]	// get new tasks TI_FLAGS
-	tbnz	x0, #TIF_NEED_RESCHED, 1b	// needs rescheduling?
-	ret	x24
-#endif
-
 /*
  * EL0 mode handlers.
  */
@@ -665,11 +729,12 @@
 	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_pc
+	b.eq	el0_sp
 	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_sp_pc
+	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
@@ -693,13 +758,13 @@
 	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_sp_pc
+	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_undef
+	b.eq	el0_cp15
 	cmp	x24, #ESR_ELx_EC_CP15_64	// CP15 MRRC/MCRR trap
-	b.eq	el0_undef
+	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
@@ -710,6 +775,7 @@
 	b.ge	el0_dbg
 	b	el0_inv
 el0_svc_compat:
+	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
 	bl	el0_svc_compat_handler
 	b	ret_to_user
@@ -722,6 +788,17 @@
 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:
@@ -729,9 +806,9 @@
 	 * Data abort handling
 	 */
 	mrs	x26, far_el1
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
-	clear_address_tag x0, x26
+	untagged_addr	x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort
@@ -741,11 +818,12 @@
 	 * 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
-	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -755,8 +833,8 @@
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_acc
@@ -765,8 +843,8 @@
 	/*
 	 * Scalable Vector Extension access
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_sve_acc
@@ -775,22 +853,27 @@
 	/*
 	 * Floating Point, Advanced SIMD or SVE exception
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	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
 	 */
-	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
-	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -800,8 +883,8 @@
 	/*
 	 * Undefined instruction
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, sp
 	bl	do_undefinstr
 	b	ret_to_user
@@ -809,8 +892,8 @@
 	/*
 	 * System instructions, for trapped cache maintenance instructions
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_sysinstr
@@ -820,16 +903,18 @@
 	 * Debug exception handling
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
-	mrs	x0, far_el1
+	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_daif
-	ct_user_exit
+	enable_da_f
 	b	ret_to_user
 el0_inv:
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
@@ -841,12 +926,14 @@
 el0_irq:
 	kernel_entry 0
 el0_irq_naked:
+	gic_prio_irq_setup pmr=x20, tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 
-	ct_user_exit
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	tbz	x22, #55, 1f
 	bl	do_el0_irq_bp_hardening
@@ -863,6 +950,7 @@
 el1_error:
 	kernel_entry 1
 	mrs	x1, esr_el1
+	gic_prio_kentry_setup tmp=x2
 	enable_dbg
 	mov	x0, sp
 	bl	do_serror
@@ -872,12 +960,14 @@
 el0_error:
 	kernel_entry 0
 el0_error_naked:
-	mrs	x1, esr_el1
+	mrs	x25, esr_el1
+	gic_prio_kentry_setup tmp=x2
+	ct_user_exit_irqoff
 	enable_dbg
 	mov	x0, sp
+	mov	x1, x25
 	bl	do_serror
-	enable_daif
-	ct_user_exit
+	enable_da_f
 	b	ret_to_user
 ENDPROC(el0_error)
 
@@ -897,6 +987,7 @@
  */
 ret_to_user:
 	disable_daif
+	gic_prio_kentry_setup tmp=x3
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
@@ -913,6 +1004,7 @@
  */
 	.align	6
 el0_svc:
+	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
 	bl	el0_svc_handler
 	b	ret_to_user
@@ -979,7 +1071,9 @@
 #else
 	ldr	x30, =vectors
 #endif
+alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
 	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+alternative_else_nop_endif
 	msr	vbar_el1, x30
 	add	x30, x30, #(1b - tramp_vectors)
 	isb
@@ -994,6 +1088,7 @@
 	mrs	x30, far_el1
 	.endif
 	eret
+	sb
 	.endm
 
 	.align	11
@@ -1072,7 +1167,7 @@
 	cbz	x19, 1f				// not a kernel thread
 	mov	x0, x20
 	blr	x19
-1:	get_thread_info tsk
+1:	get_current_task tsk
 	b	ret_to_user
 ENDPROC(ret_from_fork)
 NOKPROBE(ret_from_fork)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 58c53bc..37d3912 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1,23 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * FP/SIMD context switching and fault handling
  *
  * Copyright (C) 2012 ARM Ltd.
  * Author: Catalin Marinas <catalin.marinas@arm.com>
- *
- * 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/bitmap.h>
+#include <linux/bitops.h>
 #include <linux/bottom_half.h>
 #include <linux/bug.h>
 #include <linux/cache.h>
@@ -38,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
+#include <linux/swab.h>
 
 #include <asm/esr.h>
 #include <asm/fpsimd.h>
@@ -48,6 +39,7 @@
 #include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 #include <asm/traps.h>
+#include <asm/virt.h>
 
 #define FPEXC_IOF	(1 << 0)
 #define FPEXC_DZF	(1 << 1)
@@ -90,7 +82,8 @@
  * To prevent this from racing with the manipulation of the task's FPSIMD state
  * from task context and thereby corrupting the state, it is necessary to
  * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
- * flag with local_bh_disable() unless softirqs are already masked.
+ * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
+ * run but prevent them to use FPSIMD.
  *
  * For a certain task, the sequence may look something like this:
  * - the task gets scheduled in; if both the task's fpsimd_cpu field
@@ -119,6 +112,8 @@
  */
 struct fpsimd_last_state_struct {
 	struct user_fpsimd_state *st;
+	void *sve_state;
+	unsigned int sve_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -130,18 +125,77 @@
 
 /* Maximum supported vector length across all CPUs (initially poisoned) */
 int __ro_after_init sve_max_vl = SVE_VL_MIN;
-/* Set of available vector lengths, as vq_to_bit(vq): */
-static __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN;
+
+/*
+ * Set of available vector lengths,
+ * where length vq encoded as bit __vq_to_bit(vq):
+ */
+__ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+/* Set of vector lengths present on at least one cpu: */
+static __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
+
 static void __percpu *efi_sve_state;
 
 #else /* ! CONFIG_ARM64_SVE */
 
 /* Dummy declaration for code that will be optimised out: */
 extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+extern __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
 extern void __percpu *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+DEFINE_PER_CPU(bool, fpsimd_context_busy);
+EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
+
+static void __get_cpu_fpsimd_context(void)
+{
+	bool busy = __this_cpu_xchg(fpsimd_context_busy, true);
+
+	WARN_ON(busy);
+}
+
+/*
+ * Claim ownership of the CPU FPSIMD context for use by the calling context.
+ *
+ * The caller may freely manipulate the FPSIMD context metadata until
+ * put_cpu_fpsimd_context() is called.
+ *
+ * The double-underscore version must only be called if you know the task
+ * can't be preempted.
+ */
+static void get_cpu_fpsimd_context(void)
+{
+	preempt_disable();
+	__get_cpu_fpsimd_context();
+}
+
+static void __put_cpu_fpsimd_context(void)
+{
+	bool busy = __this_cpu_xchg(fpsimd_context_busy, false);
+
+	WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */
+}
+
+/*
+ * Release the CPU FPSIMD context.
+ *
+ * Must be called from a context in which get_cpu_fpsimd_context() was
+ * previously called, with no call to put_cpu_fpsimd_context() in the
+ * meantime.
+ */
+static void put_cpu_fpsimd_context(void)
+{
+	__put_cpu_fpsimd_context();
+	preempt_enable();
+}
+
+static bool have_cpu_fpsimd_context(void)
+{
+	return !preemptible() && __this_cpu_read(fpsimd_context_busy);
+}
+
 /*
  * Call __sve_free() directly only if you know task can't be scheduled
  * or preempted.
@@ -212,12 +266,10 @@
  * This function should be called only when the FPSIMD/SVE state in
  * thread_struct is known to be up to date, when preparing to enter
  * userspace.
- *
- * Softirqs (and preemption) must be disabled.
  */
 static void task_fpsimd_load(void)
 {
-	WARN_ON(!in_softirq() && !irqs_disabled());
+	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		sve_load_state(sve_pffr(&current->thread),
@@ -230,19 +282,18 @@
 /*
  * Ensure FPSIMD/SVE storage in memory for the loaded context is up to
  * date with respect to the CPU registers.
- *
- * Softirqs (and preemption) must be disabled.
  */
-void fpsimd_save(void)
+static void fpsimd_save(void)
 {
-	struct user_fpsimd_state *st = __this_cpu_read(fpsimd_last_state.st);
+	struct fpsimd_last_state_struct const *last =
+		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
 
-	WARN_ON(!in_softirq() && !irqs_disabled());
+	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
-			if (WARN_ON(sve_get_vl() != current->thread.sve_vl)) {
+			if (WARN_ON(sve_get_vl() != last->sve_vl)) {
 				/*
 				 * Can't save the user regs, so current would
 				 * re-enter user with corrupt state.
@@ -252,32 +303,15 @@
 				return;
 			}
 
-			sve_save_state(sve_pffr(&current->thread), &st->fpsr);
+			sve_save_state((char *)last->sve_state +
+						sve_ffr_offset(last->sve_vl),
+				       &last->st->fpsr);
 		} else
-			fpsimd_save_state(st);
+			fpsimd_save_state(last->st);
 	}
 }
 
 /*
- * Helpers to translate bit indices in sve_vq_map to VQ values (and
- * vice versa).  This allows find_next_bit() to be used to find the
- * _maximum_ VQ not exceeding a certain value.
- */
-
-static unsigned int vq_to_bit(unsigned int vq)
-{
-	return SVE_VQ_MAX - vq;
-}
-
-static unsigned int bit_to_vq(unsigned int bit)
-{
-	if (WARN_ON(bit >= SVE_VQ_MAX))
-		bit = SVE_VQ_MAX - 1;
-
-	return SVE_VQ_MAX - bit;
-}
-
-/*
  * All vector length selection from userspace comes through here.
  * We're on a slow path, so some sanity-checks are included.
  * If things go wrong there's a bug somewhere, but try to fall back to a
@@ -298,8 +332,8 @@
 		vl = max_vl;
 
 	bit = find_next_bit(sve_vq_map, SVE_VQ_MAX,
-			    vq_to_bit(sve_vq_from_vl(vl)));
-	return sve_vl_from_vq(bit_to_vq(bit));
+			    __vq_to_bit(sve_vq_from_vl(vl)));
+	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -355,12 +389,42 @@
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
 
+#ifdef CONFIG_CPU_BIG_ENDIAN
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+	u64 a = swab64(x);
+	u64 b = swab64(x >> 64);
+
+	return ((__uint128_t)a << 64) | b;
+}
+#else
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+	return x;
+}
+#endif
+
+#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
+
+static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
+			    unsigned int vq)
+{
+	unsigned int i;
+	__uint128_t *p;
+
+	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
+		p = (__uint128_t *)ZREG(sst, vq, i);
+		*p = arm64_cpu_to_le128(fst->vregs[i]);
+	}
+}
+
 /*
  * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
  * task->thread.sve_state.
  *
  * Task can be a non-runnable task, or current.  In the latter case,
- * softirqs (and preemption) must be disabled.
+ * the caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  * task->thread.sve_state must point to at least sve_state_size(task)
  * bytes of allocated kernel memory.
  * task->thread.uw.fpsimd_state must be up to date before calling this
@@ -371,15 +435,12 @@
 	unsigned int vq;
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
-	unsigned int i;
 
 	if (!system_supports_sve())
 		return;
 
 	vq = sve_vq_from_vl(task->thread.sve_vl);
-	for (i = 0; i < 32; ++i)
-		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
-		       sizeof(fst->vregs[i]));
+	__fpsimd_to_sve(sst, fst, vq);
 }
 
 /*
@@ -387,7 +448,8 @@
  * task->thread.uw.fpsimd_state.
  *
  * Task can be a non-runnable task, or current.  In the latter case,
- * softirqs (and preemption) must be disabled.
+ * the caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  * task->thread.sve_state must point to at least sve_state_size(task)
  * bytes of allocated kernel memory.
  * task->thread.sve_state must be up to date before calling this function.
@@ -398,14 +460,16 @@
 	void const *sst = task->thread.sve_state;
 	struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
+	__uint128_t const *p;
 
 	if (!system_supports_sve())
 		return;
 
 	vq = sve_vq_from_vl(task->thread.sve_vl);
-	for (i = 0; i < 32; ++i)
-		memcpy(&fst->vregs[i], ZREG(sst, vq, i),
-		       sizeof(fst->vregs[i]));
+	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
+		p = (__uint128_t const *)ZREG(sst, vq, i);
+		fst->vregs[i] = arm64_le128_to_cpu(*p);
+	}
 }
 
 #ifdef CONFIG_ARM64_SVE
@@ -493,7 +557,6 @@
 	unsigned int vq;
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
-	unsigned int i;
 
 	if (!test_tsk_thread_flag(task, TIF_SVE))
 		return;
@@ -501,10 +564,7 @@
 	vq = sve_vq_from_vl(task->thread.sve_vl);
 
 	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
-
-	for (i = 0; i < 32; ++i)
-		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
-		       sizeof(fst->vregs[i]));
+	__fpsimd_to_sve(sst, fst, vq);
 }
 
 int sve_set_vector_length(struct task_struct *task,
@@ -547,10 +607,9 @@
 	 * non-SVE thread.
 	 */
 	if (task == current) {
-		local_bh_disable();
+		get_cpu_fpsimd_context();
 
 		fpsimd_save();
-		set_thread_flag(TIF_FOREIGN_FPSTATE);
 	}
 
 	fpsimd_flush_task_state(task);
@@ -558,7 +617,7 @@
 		sve_to_fpsimd(task);
 
 	if (task == current)
-		local_bh_enable();
+		put_cpu_fpsimd_context();
 
 	/*
 	 * Force reallocation of task SVE state to the correct size
@@ -624,12 +683,6 @@
 	return sve_prctl_status(0);
 }
 
-/*
- * Bitmap for temporary storage of the per-CPU set of supported vector lengths
- * during secondary boot.
- */
-static DECLARE_BITMAP(sve_secondary_vq_map, SVE_VQ_MAX);
-
 static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
 {
 	unsigned int vq, vl;
@@ -644,40 +697,82 @@
 		write_sysreg_s(zcr | (vq - 1), SYS_ZCR_EL1); /* self-syncing */
 		vl = sve_get_vl();
 		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
-		set_bit(vq_to_bit(vq), map);
+		set_bit(__vq_to_bit(vq), map);
 	}
 }
 
+/*
+ * Initialise the set of known supported VQs for the boot CPU.
+ * This is called during kernel boot, before secondary CPUs are brought up.
+ */
 void __init sve_init_vq_map(void)
 {
 	sve_probe_vqs(sve_vq_map);
+	bitmap_copy(sve_vq_partial_map, sve_vq_map, SVE_VQ_MAX);
 }
 
 /*
  * If we haven't committed to the set of supported VQs yet, filter out
  * those not supported by the current CPU.
+ * This function is called during the bring-up of early secondary CPUs only.
  */
 void sve_update_vq_map(void)
 {
-	sve_probe_vqs(sve_secondary_vq_map);
-	bitmap_and(sve_vq_map, sve_vq_map, sve_secondary_vq_map, SVE_VQ_MAX);
+	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+
+	sve_probe_vqs(tmp_map);
+	bitmap_and(sve_vq_map, sve_vq_map, tmp_map, SVE_VQ_MAX);
+	bitmap_or(sve_vq_partial_map, sve_vq_partial_map, tmp_map, SVE_VQ_MAX);
 }
 
-/* Check whether the current CPU supports all VQs in the committed set */
+/*
+ * Check whether the current CPU supports all VQs in the committed set.
+ * This function is called during the bring-up of late secondary CPUs only.
+ */
 int sve_verify_vq_map(void)
 {
-	int ret = 0;
+	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+	unsigned long b;
 
-	sve_probe_vqs(sve_secondary_vq_map);
-	bitmap_andnot(sve_secondary_vq_map, sve_vq_map, sve_secondary_vq_map,
-		      SVE_VQ_MAX);
-	if (!bitmap_empty(sve_secondary_vq_map, SVE_VQ_MAX)) {
+	sve_probe_vqs(tmp_map);
+
+	bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
+	if (bitmap_intersects(tmp_map, sve_vq_map, SVE_VQ_MAX)) {
 		pr_warn("SVE: cpu%d: Required vector length(s) missing\n",
 			smp_processor_id());
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
-	return ret;
+	if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
+		return 0;
+
+	/*
+	 * For KVM, it is necessary to ensure that this CPU doesn't
+	 * support any vector length that guests may have probed as
+	 * unsupported.
+	 */
+
+	/* Recover the set of supported VQs: */
+	bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
+	/* Find VQs supported that are not globally supported: */
+	bitmap_andnot(tmp_map, tmp_map, sve_vq_map, SVE_VQ_MAX);
+
+	/* Find the lowest such VQ, if any: */
+	b = find_last_bit(tmp_map, SVE_VQ_MAX);
+	if (b >= SVE_VQ_MAX)
+		return 0; /* no mismatches */
+
+	/*
+	 * Mismatches above sve_max_virtualisable_vl are fine, since
+	 * no guest is allowed to configure ZCR_EL2.LEN to exceed this:
+	 */
+	if (sve_vl_from_vq(__bit_to_vq(b)) <= sve_max_virtualisable_vl) {
+		pr_warn("SVE: cpu%d: Unsupported vector length(s) present\n",
+			smp_processor_id());
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static void __init sve_efi_setup(void)
@@ -744,6 +839,8 @@
 void __init sve_setup(void)
 {
 	u64 zcr;
+	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+	unsigned long b;
 
 	if (!system_supports_sve())
 		return;
@@ -753,8 +850,8 @@
 	 * so sve_vq_map must have at least SVE_VQ_MIN set.
 	 * If something went wrong, at least try to patch it up:
 	 */
-	if (WARN_ON(!test_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
-		set_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map);
+	if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
+		set_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map);
 
 	zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
 	sve_max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
@@ -772,11 +869,31 @@
 	 */
 	sve_default_vl = find_supported_vector_length(64);
 
+	bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map,
+		      SVE_VQ_MAX);
+
+	b = find_last_bit(tmp_map, SVE_VQ_MAX);
+	if (b >= SVE_VQ_MAX)
+		/* No non-virtualisable VLs found */
+		sve_max_virtualisable_vl = SVE_VQ_MAX;
+	else if (WARN_ON(b == SVE_VQ_MAX - 1))
+		/* No virtualisable VLs?  This is architecturally forbidden. */
+		sve_max_virtualisable_vl = SVE_VQ_MIN;
+	else /* b + 1 < SVE_VQ_MAX */
+		sve_max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1));
+
+	if (sve_max_virtualisable_vl > sve_max_vl)
+		sve_max_virtualisable_vl = sve_max_vl;
+
 	pr_info("SVE: maximum available vector length %u bytes per vector\n",
 		sve_max_vl);
 	pr_info("SVE: default vector length %u bytes per vector\n",
 		sve_default_vl);
 
+	/* KVM decides whether to support mismatched systems. Just warn here: */
+	if (sve_max_virtualisable_vl < sve_max_vl)
+		pr_warn("SVE: unvirtualisable vector lengths present\n");
+
 	sve_efi_setup();
 }
 
@@ -813,19 +930,18 @@
 
 	sve_alloc(current);
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	fpsimd_save();
-	fpsimd_to_sve(current);
 
 	/* Force ret_to_user to reload the registers: */
 	fpsimd_flush_task_state(current);
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
 
+	fpsimd_to_sve(current);
 	if (test_and_set_thread_flag(TIF_SVE))
 		WARN_ON(1); /* SVE access shouldn't have trapped */
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -842,7 +958,6 @@
  */
 asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
-	siginfo_t info;
 	unsigned int si_code = FPE_FLTUNK;
 
 	if (esr & ESR_ELx_FP_EXC_TFV) {
@@ -858,12 +973,9 @@
 			si_code = FPE_FLTRES;
 	}
 
-	clear_siginfo(&info);
-	info.si_signo = SIGFPE;
-	info.si_code = si_code;
-	info.si_addr = (void __user *)instruction_pointer(regs);
-
-	send_sig_info(SIGFPE, &info, current);
+	send_sig_fault(SIGFPE, si_code,
+		       (void __user *)instruction_pointer(regs),
+		       current);
 }
 
 void fpsimd_thread_switch(struct task_struct *next)
@@ -873,6 +985,8 @@
 	if (!system_supports_fpsimd())
 		return;
 
+	__get_cpu_fpsimd_context();
+
 	/* Save unsaved fpsimd state, if any: */
 	fpsimd_save();
 
@@ -887,6 +1001,8 @@
 
 	update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
 			       wrong_task || wrong_cpu);
+
+	__put_cpu_fpsimd_context();
 }
 
 void fpsimd_flush_thread(void)
@@ -896,11 +1012,11 @@
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
+	fpsimd_flush_task_state(current);
 	memset(&current->thread.uw.fpsimd_state, 0,
 	       sizeof(current->thread.uw.fpsimd_state));
-	fpsimd_flush_task_state(current);
 
 	if (system_supports_sve()) {
 		clear_thread_flag(TIF_SVE);
@@ -937,9 +1053,7 @@
 			current->thread.sve_vl_onexec = 0;
 	}
 
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
-
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -951,9 +1065,9 @@
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 	fpsimd_save();
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -970,7 +1084,8 @@
 
 /*
  * Associate current's FPSIMD context with this cpu
- * Preemption must be disabled when calling this function.
+ * The caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  */
 void fpsimd_bind_task_to_cpu(void)
 {
@@ -978,6 +1093,8 @@
 		this_cpu_ptr(&fpsimd_last_state);
 
 	last->st = &current->thread.uw.fpsimd_state;
+	last->sve_state = current->thread.sve_state;
+	last->sve_vl = current->thread.sve_vl;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
 	if (system_supports_sve()) {
@@ -991,7 +1108,8 @@
 	}
 }
 
-void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st)
+void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
+			      unsigned int sve_vl)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -999,6 +1117,8 @@
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
+	last->sve_state = sve_state;
+	last->sve_vl = sve_vl;
 }
 
 /*
@@ -1011,14 +1131,14 @@
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		task_fpsimd_load();
 		fpsimd_bind_task_to_cpu();
 	}
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1031,7 +1151,7 @@
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	current->thread.uw.fpsimd_state = *state;
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
@@ -1042,27 +1162,55 @@
 
 	clear_thread_flag(TIF_FOREIGN_FPSTATE);
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
  * Invalidate live CPU copies of task t's FPSIMD state
+ *
+ * This function may be called with preemption enabled.  The barrier()
+ * ensures that the assignment to fpsimd_cpu is visible to any
+ * preemption/softirq that could race with set_tsk_thread_flag(), so
+ * that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared.
+ *
+ * The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any
+ * subsequent code.
  */
 void fpsimd_flush_task_state(struct task_struct *t)
 {
 	t->thread.fpsimd_cpu = NR_CPUS;
+
+	barrier();
+	set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
+
+	barrier();
 }
 
-void fpsimd_flush_cpu_state(void)
+/*
+ * Invalidate any task's FPSIMD state that is present on this cpu.
+ * The FPSIMD context should be acquired with get_cpu_fpsimd_context()
+ * before calling this function.
+ */
+static void fpsimd_flush_cpu_state(void)
 {
 	__this_cpu_write(fpsimd_last_state.st, NULL);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 
-#ifdef CONFIG_KERNEL_MODE_NEON
+/*
+ * Save the FPSIMD state to memory and invalidate cpu view.
+ * This function must be called with preemption disabled.
+ */
+void fpsimd_save_and_flush_cpu_state(void)
+{
+	WARN_ON(preemptible());
+	__get_cpu_fpsimd_context();
+	fpsimd_save();
+	fpsimd_flush_cpu_state();
+	__put_cpu_fpsimd_context();
+}
 
-DEFINE_PER_CPU(bool, kernel_neon_busy);
-EXPORT_PER_CPU_SYMBOL(kernel_neon_busy);
+#ifdef CONFIG_KERNEL_MODE_NEON
 
 /*
  * Kernel-side NEON support functions
@@ -1088,19 +1236,13 @@
 
 	BUG_ON(!may_use_simd());
 
-	local_bh_disable();
-
-	__this_cpu_write(kernel_neon_busy, true);
+	get_cpu_fpsimd_context();
 
 	/* Save unsaved fpsimd state, if any: */
 	fpsimd_save();
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
 	fpsimd_flush_cpu_state();
-
-	preempt_disable();
-
-	local_bh_enable();
 }
 EXPORT_SYMBOL(kernel_neon_begin);
 
@@ -1115,15 +1257,10 @@
  */
 void kernel_neon_end(void)
 {
-	bool busy;
-
 	if (!system_supports_fpsimd())
 		return;
 
-	busy = __this_cpu_xchg(kernel_neon_busy, false);
-	WARN_ON(!busy);	/* No matching kernel_neon_begin()? */
-
-	preempt_enable();
+	put_cpu_fpsimd_context();
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
@@ -1215,8 +1352,7 @@
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		fpsimd_save();
-		fpsimd_flush_cpu_state();
+		fpsimd_save_and_flush_cpu_state();
 		break;
 	case CPU_PM_EXIT:
 		break;
@@ -1262,14 +1398,14 @@
  */
 static int __init fpsimd_init(void)
 {
-	if (elf_hwcap & HWCAP_FP) {
+	if (cpu_have_named_feature(FP)) {
 		fpsimd_pm_init();
 		fpsimd_hotplug_init();
 	} else {
 		pr_notice("Floating-point is not implemented\n");
 	}
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
 	return sve_sysctl_init();
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 57e9622..06e56b4 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm64/kernel/ftrace.c
  *
  * Copyright (C) 2013 Linaro Limited
  * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
- *
- * 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.
  */
 
 #include <linux/ftrace.h>
@@ -76,7 +73,7 @@
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-		struct plt_entry trampoline;
+		struct plt_entry trampoline, *dst;
 		struct module *mod;
 
 		/*
@@ -103,25 +100,39 @@
 		 * 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.
 		 */
-		trampoline = get_plt_entry(addr);
-		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
-				       &trampoline)) {
-			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
-					       &(struct plt_entry){})) {
+		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);
-			*mod->arch.ftrace_trampoline = trampoline;
+			*dst = trampoline;
 			module_enable_ro(mod, true);
 
-			/* update trampoline before patching in the branch */
-			smp_wmb();
+			/*
+			 * 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]);
 		}
-		addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
+		addr = (unsigned long)dst;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */
@@ -193,6 +204,7 @@
 
 void arch_ftrace_update_code(int command)
 {
+	command |= FTRACE_MAY_SLEEP;
 	ftrace_modify_all_code(command);
 }
 
@@ -211,7 +223,7 @@
  *
  * 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;
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b085306..989b194 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Low-level CPU initialisation
  * Based on arch/arm/kernel/head.S
@@ -6,18 +7,6 @@
  * Copyright (C) 2003-2012 ARM Ltd.
  * Authors:	Catalin Marinas <catalin.marinas@arm.com>
  *		Will Deacon <will.deacon@arm.com>
- *
- * 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/linkage.h>
@@ -31,6 +20,7 @@
 #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 +81,7 @@
 	.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.
 
@@ -112,6 +102,8 @@
 	 *  x23        stext() .. start_kernel()  physical misalignment/KASLR offset
 	 *  x28        __create_page_tables()     callee preserved temp register
 	 *  x19/x20    __primary_switch()         callee preserved temp registers
+	 *  x24        __primary_switch() .. relocate_kernel()
+	 *                                        current RELR displacement
 	 */
 ENTRY(stext)
 	bl	preserve_boot_args
@@ -287,19 +279,21 @@
 	mov	x28, lr
 
 	/*
-	 * Invalidate the idmap and swapper page tables to avoid potential
-	 * dirty cache lines being evicted.
+	 * Invalidate the init page tables to avoid potential dirty cache lines
+	 * being evicted. Other page tables are allocated in rodata as part of
+	 * the kernel image, and thus are clean to the PoC per the boot
+	 * protocol.
 	 */
-	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_end
+	adrp	x0, init_pg_dir
+	adrp	x1, init_pg_end
 	sub	x1, x1, x0
 	bl	__inval_dcache_area
 
 	/*
-	 * Clear the idmap and swapper page tables.
+	 * Clear the init page tables.
 	 */
-	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_end
+	adrp	x0, init_pg_dir
+	adrp	x1, init_pg_end
 	sub	x1, x1, x0
 1:	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
@@ -316,6 +310,19 @@
 	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
+#ifdef CONFIG_ARM64_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_MIN
+1:
+	adr_l	x6, vabits_actual
+	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
@@ -373,7 +380,7 @@
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
-	adrp	x0, swapper_pg_dir
+	adrp	x0, init_pg_dir
 	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
 	mov	x4, PTRS_PER_PGD
@@ -390,7 +397,7 @@
 	 * tables again to remove any speculatively loaded cache lines.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_end
+	adrp	x1, init_pg_end
 	sub	x1, x1, x0
 	dmb	sy
 	bl	__inval_dcache_area
@@ -459,6 +466,7 @@
 
 ENTRY(kimage_vaddr)
 	.quad		_text - TEXT_OFFSET
+EXPORT_SYMBOL(kimage_vaddr)
 
 /*
  * If we're fortunate enough to boot at EL2, ensure that the world is
@@ -488,16 +496,15 @@
 	 * kernel is intended to run at EL2.
 	 */
 	mrs	x2, id_aa64mmfr1_el1
-	ubfx	x2, x2, #8, #4
+	ubfx	x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
 #else
 	mov	x2, xzr
 #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
@@ -522,9 +529,8 @@
 #ifdef CONFIG_ARM_GIC_V3
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
-	ubfx	x0, x0, #24, #4
-	cmp	x0, #1
-	b.ne	3f
+	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
+	cbz	x0, 3f
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
@@ -549,8 +555,8 @@
 #endif
 
 	/* EL2 debug */
-	mrs	x1, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	x0, x1, #8, #4
+	mrs	x1, id_aa64dfr0_el1
+	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	x0, #1
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
@@ -559,7 +565,7 @@
 	csel	x3, xzr, x0, lt			// all PMU counters from EL1
 
 	/* Statistical profiling */
-	ubfx	x0, x1, #32, #4			// Check ID_AA64DFR0_EL1 PMSVer
+	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cbz	x0, 7f				// Skip if SPE not present
 	cbnz	x2, 6f				// VHE?
 	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
@@ -669,7 +675,7 @@
  * with MMU turned off.
  */
 ENTRY(__early_cpu_boot_status)
-	.long 	0
+	.quad 	0
 
 	.popsection
 
@@ -705,7 +711,9 @@
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
+	bl	__cpu_secondary_check52bitva
 	bl	__cpu_setup			// initialise processor
+	adrp	x1, swapper_pg_dir
 	bl	__enable_mmu
 	ldr	x8, =__secondary_switched
 	br	x8
@@ -718,14 +726,22 @@
 
 	adr_l	x0, secondary_data
 	ldr	x1, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
+	cbz	x1, __secondary_too_slow
 	mov	sp, x1
 	ldr	x2, [x0, #CPU_BOOT_TASK]
+	cbz	x2, __secondary_too_slow
 	msr	sp_el0, x2
 	mov	x29, #0
 	mov	x30, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
 
+__secondary_too_slow:
+	wfe
+	wfi
+	b	__secondary_too_slow
+ENDPROC(__secondary_too_slow)
+
 /*
  * The booting CPU updates the failed status @__early_cpu_boot_status,
  * with MMU turned off.
@@ -748,6 +764,7 @@
  * Enable the MMU.
  *
  *  x0  = SCTLR_EL1 value for turning on the MMU.
+ *  x1  = TTBR1_EL1 value
  *
  * Returns to the caller via x30/lr. This requires the caller to be covered
  * by the .idmap.text section.
@@ -756,17 +773,17 @@
  * If it isn't, park the CPU
  */
 ENTRY(__enable_mmu)
-	mrs	x1, ID_AA64MMFR0_EL1
-	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
+	mrs	x2, ID_AA64MMFR0_EL1
+	ubfx	x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
 	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
 	b.ne	__no_granule_support
-	update_early_cpu_boot_status 0, x1, x2
-	adrp	x1, idmap_pg_dir
-	adrp	x2, swapper_pg_dir
-	phys_to_ttbr x3, x1
-	phys_to_ttbr x4, x2
-	msr	ttbr0_el1, x3			// load TTBR0
-	msr	ttbr1_el1, x4			// load TTBR1
+	update_early_cpu_boot_status 0, x2, x3
+	adrp	x2, idmap_pg_dir
+	phys_to_ttbr x1, x1
+	phys_to_ttbr x2, x2
+	msr	ttbr0_el1, x2			// load TTBR0
+	offset_ttbr1 x1, x3
+	msr	ttbr1_el1, x1			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
 	isb
@@ -781,9 +798,30 @@
 	ret
 ENDPROC(__enable_mmu)
 
+ENTRY(__cpu_secondary_check52bitva)
+#ifdef CONFIG_ARM64_VA_BITS_52
+	ldr_l	x0, vabits_actual
+	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
@@ -806,14 +844,93 @@
 
 0:	cmp	x9, x10
 	b.hs	1f
-	ldp	x11, x12, [x9], #24
-	ldr	x13, [x9, #-8]
-	cmp	w12, #R_AARCH64_RELATIVE
+	ldp	x12, x13, [x9], #24
+	ldr	x14, [x9, #-8]
+	cmp	w13, #R_AARCH64_RELATIVE
 	b.ne	0b
-	add	x13, x13, x23			// relocate
-	str	x13, [x11, x23]
+	add	x14, x14, x23			// relocate
+	str	x14, [x12, x23]
 	b	0b
-1:	ret
+
+1:
+#ifdef CONFIG_RELR
+	/*
+	 * Apply RELR relocations.
+	 *
+	 * RELR is a compressed format for storing relative relocations. The
+	 * encoded sequence of entries looks like:
+	 * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ]
+	 *
+	 * i.e. start with an address, followed by any number of bitmaps. The
+	 * address entry encodes 1 relocation. The subsequent bitmap entries
+	 * encode up to 63 relocations each, at subsequent offsets following
+	 * the last address entry.
+	 *
+	 * The bitmap entries must have 1 in the least significant bit. The
+	 * assumption here is that an address cannot have 1 in lsb. Odd
+	 * addresses are not supported. Any odd addresses are stored in the RELA
+	 * section, which is handled above.
+	 *
+	 * Excluding the least significant bit in the bitmap, each non-zero
+	 * bit in the bitmap represents a relocation to be applied to
+	 * a corresponding machine word that follows the base address
+	 * word. The second least significant bit represents the machine
+	 * word immediately following the initial address, and each bit
+	 * that follows represents the next word, in linear order. As such,
+	 * a single bitmap can encode up to 63 relocations in a 64-bit object.
+	 *
+	 * In this implementation we store the address of the next RELR table
+	 * entry in x9, the address being relocated by the current address or
+	 * bitmap entry in x13 and the address being relocated by the current
+	 * bit in x14.
+	 *
+	 * Because addends are stored in place in the binary, RELR relocations
+	 * cannot be applied idempotently. We use x24 to keep track of the
+	 * currently applied displacement so that we can correctly relocate if
+	 * __relocate_kernel is called twice with non-zero displacements (i.e.
+	 * if there is both a physical misalignment and a KASLR displacement).
+	 */
+	ldr	w9, =__relr_offset		// offset to reloc table
+	ldr	w10, =__relr_size		// size of reloc table
+	add	x9, x9, x11			// __va(.relr)
+	add	x10, x9, x10			// __va(.relr) + sizeof(.relr)
+
+	sub	x15, x23, x24			// delta from previous offset
+	cbz	x15, 7f				// nothing to do if unchanged
+	mov	x24, x23			// save new offset
+
+2:	cmp	x9, x10
+	b.hs	7f
+	ldr	x11, [x9], #8
+	tbnz	x11, #0, 3f			// branch to handle bitmaps
+	add	x13, x11, x23
+	ldr	x12, [x13]			// relocate address entry
+	add	x12, x12, x15
+	str	x12, [x13], #8			// adjust to start of bitmap
+	b	2b
+
+3:	mov	x14, x13
+4:	lsr	x11, x11, #1
+	cbz	x11, 6f
+	tbz	x11, #0, 5f			// skip bit if not set
+	ldr	x12, [x14]			// relocate bit
+	add	x12, x12, x15
+	str	x12, [x14]
+
+5:	add	x14, x14, #8			// move to next bit's address
+	b	4b
+
+6:	/*
+	 * Move to the next bitmap's address. 8 is the word size, and 63 is the
+	 * number of significant bits in a bitmap entry.
+	 */
+	add	x13, x13, #(8 * 63)
+	b	2b
+
+7:
+#endif
+	ret
+
 ENDPROC(__relocate_kernel)
 #endif
 
@@ -823,8 +940,12 @@
 	mrs	x20, sctlr_el1			// preserve old SCTLR_EL1 value
 #endif
 
+	adrp	x1, init_pg_dir
 	bl	__enable_mmu
 #ifdef CONFIG_RELOCATABLE
+#ifdef CONFIG_RELR
+	mov	x24, #0				// no RELR displacement yet
+#endif
 	bl	__relocate_kernel
 #ifdef CONFIG_RANDOMIZE_BASE
 	ldr	x8, =__primary_switched
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index dd14ab8..38bcd4d 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Hibernate low-level support
  *
  * Copyright (C) 2016 ARM Ltd.
  * Author:	James Morse <james.morse@arm.com>
- *
- * 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/linkage.h>
 #include <linux/errno.h>
@@ -33,13 +22,14 @@
  * Even switching to our copied tables will cause a changed output address at
  * each stage of the walk.
  */
-.macro break_before_make_ttbr_switch zero_page, page_table, tmp
+.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2
 	phys_to_ttbr \tmp, \zero_page
 	msr	ttbr1_el1, \tmp
 	isb
 	tlbi	vmalle1
 	dsb	nsh
 	phys_to_ttbr \tmp, \page_table
+	offset_ttbr1 \tmp, \tmp2
 	msr	ttbr1_el1, \tmp
 	isb
 .endm
@@ -80,7 +70,7 @@
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
 	 */
-	break_before_make_ttbr_switch	x5, x0, x6
+	break_before_make_ttbr_switch	x5, x0, x6, x8
 
 	mov	x21, x1
 	mov	x30, x2
@@ -111,7 +101,7 @@
 	dsb	ish		/* wait for PoU cleaning to finish */
 
 	/* switch to the restored kernels page tables */
-	break_before_make_ttbr_switch	x25, x21, x6
+	break_before_make_ttbr_switch	x25, x21, x6, x8
 
 	ic	ialluis
 	dsb	ish
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 29cdc99..a96b292 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*:
  * Hibernate support specific for ARM64
  *
@@ -11,8 +12,6 @@
  *  https://patchwork.kernel.org/patch/96442/
  *
  * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- *
- * License terms: GNU General Public License (GPL) version 2
  */
 #define pr_fmt(x) "hibernate: " x
 #include <linux/cpu.h>
@@ -202,6 +201,7 @@
 				 gfp_t mask)
 {
 	int rc = 0;
+	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -216,7 +216,13 @@
 	memcpy((void *)dst, src_start, length);
 	__flush_icache_range(dst, dst + length);
 
-	pgdp = pgd_offset_raw(allocator(mask), dst_addr);
+	trans_pgd = allocator(mask);
+	if (!trans_pgd) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
 		pudp = allocator(mask);
 		if (!pudp) {
@@ -299,8 +305,10 @@
 		dcache_clean_range(__idmap_text_start, __idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
-		if (el2_reset_needed())
+		if (el2_reset_needed()) {
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+		}
 
 		/* make the crash dump kernel image protected again */
 		crash_post_resume();
@@ -495,7 +503,7 @@
 		rc = -ENOMEM;
 		goto out;
 	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END);
 	if (rc)
 		goto out;
 
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 8c96443..38ee151 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
  * using the CPU's debug registers.
  *
  * Copyright (C) 2012 ARM Limited
  * Author: Will Deacon <will.deacon@arm.com>
- *
- * 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/>.
  */
 
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
@@ -547,13 +536,18 @@
 			/* Aligned */
 			break;
 		case 1:
-			/* Allow single byte watchpoint. */
-			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
-				break;
 		case 2:
 			/* Allow halfword watchpoints and breakpoints. */
 			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
+
+			/* Fallthrough */
+		case 3:
+			/* Allow single byte watchpoint. */
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
+				break;
+
+			/* Fallthrough */
 		default:
 			return -EINVAL;
 		}
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index e1261fb..73d4607 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Hypervisor stub
  *
  * Copyright (C) 2012 ARM Ltd.
  * Author:	Marc Zyngier <marc.zyngier@arm.com>
- *
- * 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/init.h>
@@ -28,6 +17,8 @@
 #include <asm/virt.h>
 
 	.text
+	.pushsection	.hyp.text, "ax"
+
 	.align 11
 
 ENTRY(__hyp_stub_vectors)
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
new file mode 100644
index 0000000..25a2a9b
--- /dev/null
+++ b/arch/arm64/kernel/image-vars.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linker script variables to be set after section resolution, as
+ * ld.lld does not like variables assigned before SECTIONS is processed.
+ */
+#ifndef __ARM64_KERNEL_IMAGE_VARS_H
+#define __ARM64_KERNEL_IMAGE_VARS_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+#ifdef CONFIG_EFI
+
+__efistub_stext_offset = stext - _text;
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__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		= __pi_memcpy;
+__efistub___memmove		= __pi_memmove;
+__efistub___memset		= __pi_memset;
+#endif
+
+__efistub__text			= _text;
+__efistub__end			= _end;
+__efistub__edata		= _edata;
+__efistub_screen_info		= screen_info;
+
+#endif
+
+#endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index a820ed0..c7d38c6 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -1,27 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linker script macros to generate Image header fields.
  *
  * Copyright (C) 2014 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/>.
  */
-#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 +38,22 @@
 	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
@@ -71,52 +65,4 @@
 	DEFINE_IMAGE_LE64(_kernel_offset_le, TEXT_OFFSET);	\
 	DEFINE_IMAGE_LE64(_kernel_flags_le, __HEAD_FLAGS);
 
-#ifdef CONFIG_EFI
-
-__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
- * accessed by the stub, so provide some aliases to make them accessible.
- * Only include data symbols here, or text symbols of functions that are
- * guaranteed to be safe when executed at another offset than they were
- * 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);
-
-#ifdef CONFIG_KASAN
-__efistub___memcpy		= KALLSYMS_HIDE(__pi_memcpy);
-__efistub___memmove		= KALLSYMS_HIDE(__pi_memmove);
-__efistub___memset		= KALLSYMS_HIDE(__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);
-
-#endif
-
-#endif /* __ASM_IMAGE_H */
+#endif /* __ARM64_KERNEL_IMAGE_H */
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 2b34135..d801a70 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2013 Huawei Ltd.
  * Author: Jiang Liu <liuj97@gmail.com>
  *
  * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
- *
- * 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/bitops.h>
 #include <linux/bug.h>
@@ -37,7 +26,7 @@
 #define AARCH64_INSN_N_BIT	BIT(22)
 #define AARCH64_INSN_LSL_12	BIT(22)
 
-static int aarch64_insn_encoding_class[] = {
+static const int aarch64_insn_encoding_class[] = {
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_UNKNOWN,
@@ -734,6 +723,46 @@
 					    state);
 }
 
+u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result,
+			   enum aarch64_insn_register address,
+			   enum aarch64_insn_register value,
+			   enum aarch64_insn_size_type size)
+{
+	u32 insn = aarch64_insn_get_ldadd_value();
+
+	switch (size) {
+	case AARCH64_INSN_SIZE_32:
+	case AARCH64_INSN_SIZE_64:
+		break;
+	default:
+		pr_err("%s: unimplemented size encoding %d\n", __func__, size);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    result);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    address);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+					    value);
+}
+
+u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address,
+			   enum aarch64_insn_register value,
+			   enum aarch64_insn_size_type size)
+{
+	/*
+	 * STADD is simply encoded as an alias for LDADD with XZR as
+	 * the destination register.
+	 */
+	return aarch64_insn_gen_ldadd(AARCH64_INSN_REG_ZR, address,
+				      value, size);
+}
+
 static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type,
 					enum aarch64_insn_prfm_target target,
 					enum aarch64_insn_prfm_policy policy,
@@ -1239,6 +1268,35 @@
 	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
diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c
index 79b1738..aa7a4ec 100644
--- a/arch/arm64/kernel/io.c
+++ b/arch/arm64/kernel/io.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/io.c
  *
  * 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>
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 780a12f..04a327c 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/irq.c
  *
@@ -7,18 +8,6 @@
  * Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and
  * Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>.
  * 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/kernel_stat.h>
@@ -27,12 +16,17 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/irqchip.h>
+#include <linux/kprobes.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <asm/daifflags.h>
 #include <asm/vmap_stack.h>
 
 unsigned long irq_err_count;
 
+/* Only access this in an NMI enter/exit */
+DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
 DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
 int arch_show_interrupts(struct seq_file *p, int prec)
@@ -72,4 +66,28 @@
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
+
+	if (system_uses_irq_prio_masking()) {
+		/*
+		 * Now that we have a stack for our IRQ handler, set
+		 * the PMR/PSR pair to a consistent state.
+		 */
+		WARN_ON(read_sysreg(daif) & PSR_A_BIT);
+		local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	}
 }
+
+/*
+ * Stubs to make nmi_enter/exit() code callable from ASM
+ */
+asmlinkage void notrace asm_nmi_enter(void)
+{
+	nmi_enter();
+}
+NOKPROBE_SYMBOL(asm_nmi_enter);
+
+asmlinkage void notrace asm_nmi_exit(void)
+{
+	nmi_exit();
+}
+NOKPROBE_SYMBOL(asm_nmi_exit);
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
index e075641..9a8a0ae 100644
--- a/arch/arm64/kernel/jump_label.c
+++ b/arch/arm64/kernel/jump_label.c
@@ -1,36 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2013 Huawei Ltd.
  * Author: Jiang Liu <liuj97@gmail.com>
  *
  * Based on arch/arm/kernel/jump_label.c
- *
- * 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/kernel.h>
 #include <linux/jump_label.h>
 #include <asm/insn.h>
 
-#ifdef HAVE_JUMP_LABEL
-
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	void *addr = (void *)entry->code;
+	void *addr = (void *)jump_entry_code(entry);
 	u32 insn;
 
 	if (type == JUMP_LABEL_JMP) {
-		insn = aarch64_insn_gen_branch_imm(entry->code,
-						   entry->target,
+		insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry),
+						   jump_entry_target(entry),
 						   AARCH64_INSN_BRANCH_NOLINK);
 	} else {
 		insn = aarch64_insn_gen_nop();
@@ -49,5 +36,3 @@
 	 * NOP needs to be replaced by a branch.
 	 */
 }
-
-#endif	/* HAVE_JUMP_LABEL */
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index f0e6ab8..416f537 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * 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.
  */
 
 #include <linux/cache.h>
@@ -14,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
+#include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
@@ -43,7 +41,7 @@
 	return ret;
 }
 
-static __init const u8 *get_cmdline(void *fdt)
+static __init const u8 *kaslr_get_cmdline(void *fdt)
 {
 	static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE;
 
@@ -64,9 +62,6 @@
 	return default_cmdline;
 }
 
-extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size,
-				       pgprot_t prot);
-
 /*
  * This routine will be executed with the kernel mapped at its default virtual
  * address, and if it returns successfully, the kernel will be remapped, and
@@ -87,6 +82,7 @@
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,
@@ -94,7 +90,7 @@
 	 * attempt at mapping the FDT in setup_machine()
 	 */
 	early_fixmap_init();
-	fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
+	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	if (!fdt)
 		return 0;
 
@@ -109,7 +105,7 @@
 	 * Check if 'nokaslr' appears on the command line, and
 	 * return 0 if that is the case.
 	 */
-	cmdline = get_cmdline(fdt);
+	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
 	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
 		return 0;
@@ -117,15 +113,15 @@
 	/*
 	 * OK, so we are proceeding with KASLR enabled. Calculate a suitable
 	 * kernel image offset from the seed. Let's place the kernel in the
-	 * middle half of the VMALLOC area (VA_BITS - 2), and stay clear of
+	 * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of
 	 * the lower and upper quarters to avoid colliding with other
 	 * allocations.
 	 * Even if we could randomize at page granularity for 16k and 64k pages,
 	 * let's always round to 2 MB so we don't interfere with the ability to
 	 * map using contiguous PTEs
 	 */
-	mask = ((1UL << (VA_BITS - 2)) - 1) & ~(SZ_2M - 1);
-	offset = BIT(VA_BITS - 3) + (seed & mask);
+	mask = ((1UL << (VA_BITS_MIN - 2)) - 1) & ~(SZ_2M - 1);
+	offset = BIT(VA_BITS_MIN - 3) + (seed & mask);
 
 	/* use the top 16 bits to randomize the linear region */
 	memstart_offset_seed = seed >> 48;
@@ -143,15 +139,15 @@
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) {
 		/*
-		 * Randomize the module region over a 4 GB window covering the
+		 * Randomize the module region over a 2 GB window covering the
 		 * kernel. This reduces the risk of modules leaking information
 		 * about the address of the kernel itself, but results in
 		 * branches between modules and the core kernel that are
 		 * resolved via PLTs. (Branches between modules will be
 		 * resolved normally.)
 		 */
-		module_range = SZ_4G - (u64)(_end - _stext);
-		module_alloc_base = max((u64)_end + offset - SZ_4G,
+		module_range = SZ_2G - (u64)(_end - _stext);
+		module_alloc_base = max((u64)_end + offset - SZ_2G,
 					(u64)MODULES_VADDR);
 	} else {
 		/*
@@ -169,5 +165,8 @@
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+
 	return offset;
 }
diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c
new file mode 100644
index 0000000..29a9428
--- /dev/null
+++ 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/arm64/booting.rst, 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 = KEXEC_BUF_MEM_UNKNOWN;
+	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
+};
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index a20de58..4311992 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * AArch64 KGDB support
  *
@@ -5,18 +6,6 @@
  *
  * Copyright (C) 2013 Cavium Inc.
  * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
- *
- * 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/bug.h>
@@ -245,7 +234,7 @@
 static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
-	return 0;
+	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_brk_fn)
 
@@ -254,7 +243,7 @@
 	compiled_break = 1;
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 
-	return 0;
+	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
 
@@ -264,38 +253,24 @@
 		return DBG_HOOK_ERROR;
 
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
-	return 0;
+	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
 
 static struct break_hook kgdb_brkpt_hook = {
-	.esr_mask	= 0xffffffff,
-	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM),
-	.fn		= kgdb_brk_fn
+	.fn		= kgdb_brk_fn,
+	.imm		= KGDB_DYN_DBG_BRK_IMM,
 };
 
 static struct break_hook kgdb_compiled_brkpt_hook = {
-	.esr_mask	= 0xffffffff,
-	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM),
-	.fn		= kgdb_compiled_brk_fn
+	.fn		= kgdb_compiled_brk_fn,
+	.imm		= KGDB_COMPILED_DBG_BRK_IMM,
 };
 
 static struct step_hook kgdb_step_hook = {
 	.fn		= kgdb_step_brk_fn
 };
 
-static void kgdb_call_nmi_hook(void *ignored)
-{
-	kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
-}
-
-void kgdb_roundup_cpus(unsigned long flags)
-{
-	local_irq_enable();
-	smp_call_function(kgdb_call_nmi_hook, NULL, 0);
-	local_irq_disable();
-}
-
 static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 {
 	struct pt_regs *regs = args->regs;
@@ -338,9 +313,9 @@
 	if (ret != 0)
 		return ret;
 
-	register_break_hook(&kgdb_brkpt_hook);
-	register_break_hook(&kgdb_compiled_brkpt_hook);
-	register_step_hook(&kgdb_step_hook);
+	register_kernel_break_hook(&kgdb_brkpt_hook);
+	register_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+	register_kernel_step_hook(&kgdb_step_hook);
 	return 0;
 }
 
@@ -351,13 +326,13 @@
  */
 void kgdb_arch_exit(void)
 {
-	unregister_break_hook(&kgdb_brkpt_hook);
-	unregister_break_hook(&kgdb_compiled_brkpt_hook);
-	unregister_step_hook(&kgdb_step_hook);
+	unregister_kernel_break_hook(&kgdb_brkpt_hook);
+	unregister_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+	unregister_kernel_step_hook(&kgdb_step_hook);
 	unregister_die_notifier(&kgdb_notifier);
 }
 
-struct kgdb_arch arch_kgdb_ops;
+const struct kgdb_arch arch_kgdb_ops;
 
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 997e6b2..42bd8c0 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -1,31 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Low-level user helpers placed in the vectors page for AArch32.
+ * AArch32 user helpers.
  * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
  *
  * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2012-2018 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.
+ * The kuser helpers below are mapped at a fixed address by
+ * aarch32_setup_additional_pages() and are provided for compatibility
+ * reasons with 32 bit (aarch32) applications that need them.
  *
- * 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/>.
- *
- *
- * AArch32 user helpers.
- *
- * Each segment is 32-byte aligned and will be moved to the top of the high
- * vector page.  New segments (if ever needed) must be added in front of
- * existing ones.  This mechanism should be used only for things that are
- * really small and justified, and not be abused freely.
- *
- * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
+ * See Documentation/arm/kernel_user_helpers.rst for formal definitions.
  */
 
 #include <asm/unistd.h>
@@ -77,42 +62,3 @@
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 	.globl	__kuser_helper_end
 __kuser_helper_end:
-
-/*
- * AArch32 sigreturn code
- *
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- *
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-	.globl __aarch32_sigret_code_start
-__aarch32_sigret_code_start:
-
-	/*
-	 * ARM Code
-	 */
-	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
-
-	/*
-	 * ARM code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
-
-        .globl __aarch32_sigret_code_end
-__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 922add8..0df8493 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * kexec for arm64
  *
  * Copyright (C) Linaro.
  * Copyright (C) Huawei Futurewei Technologies.
- *
- * 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.
  */
 
 #include <linux/interrupt.h>
@@ -212,9 +209,17 @@
 	 * 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. */
 }
@@ -313,7 +318,7 @@
  * but does not hold any data of loaded kernel image.
  *
  * Note that all the pages in crash dump kernel memory have been initially
- * marked as Reserved in kexec_reserve_crashkres_pages().
+ * marked as Reserved as memory was allocated via memblock_reserve().
  *
  * In hibernation, the pages which are Reserved and yet "nosave" are excluded
  * from the hibernation iamge. crash_is_nosave() does thich check for crash
@@ -353,7 +358,6 @@
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		page = phys_to_page(addr);
-		ClearPageReserved(page);
 		free_reserved_page(page);
 	}
 }
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
new file mode 100644
index 0000000..7b08bf9
--- /dev/null
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -0,0 +1,244 @@
+// 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"
+#define FDT_PROP_RNG_SEED	"rng-seed"
+#define RNG_SEED_SIZE		128
+
+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 == -FDT_ERR_NOTFOUND)
+		ret = 0;
+	else if (ret)
+		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);
+	}
+
+	/* add rng-seed */
+	if (rng_is_initialized()) {
+		u8 rng_seed[RNG_SEED_SIZE];
+		get_random_bytes(rng_seed, RNG_SEED_SIZE);
+		ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed,
+				RNG_SEED_SIZE);
+		if (ret)
+			goto out;
+	} else {
+		pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+				FDT_PROP_RNG_SEED);
+	}
+
+out:
+	if (ret)
+		return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
+
+	return 0;
+}
+
+/*
+ * More space needed so that we can add initrd, bootargs, kaslr-seed, and
+ * rng-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;
+	size_t cmdline_len;
+	int ret;
+
+	cmdline_len = cmdline ? strlen(cmdline) : 0;
+	buf_size = fdt_totalsize(initial_boot_params)
+			+ cmdline_len + 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 = KEXEC_BUF_MEM_UNKNOWN;
+		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 = KEXEC_BUF_MEM_UNKNOWN;
+	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;
+}
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index f0690c2..b182442 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
- *
- * 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.
  */
 
 #include <linux/elf.h>
@@ -11,31 +8,91 @@
 #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 +100,31 @@
 }
 
 #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 +240,15 @@
 			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 +258,7 @@
 	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 +267,9 @@
 	 */
 	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 +278,7 @@
 			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;
 	}
@@ -246,7 +302,7 @@
 		/* sort by type, symbol index and addend */
 		sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL);
 
-		if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0)
+		if (!str_has_prefix(secstrings + dstsec->sh_name, ".init"))
 			core_plts += count_plts(syms, rels, numrels,
 						sechdrs[i].sh_info, dstsec);
 		else
@@ -254,17 +310,19 @@
 						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;
 
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index f0f27ae..03ff15b 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * AArch64 loadable module support.
  *
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  */
 
@@ -32,6 +21,7 @@
 
 void *module_alloc(unsigned long size)
 {
+	u64 module_alloc_end = module_alloc_base + MODULES_VSIZE;
 	gfp_t gfp_mask = GFP_KERNEL;
 	void *p;
 
@@ -39,9 +29,12 @@
 	if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
 		gfp_mask |= __GFP_NOWARN;
 
+	if (IS_ENABLED(CONFIG_KASAN))
+		/* don't exceed the static module region - see below */
+		module_alloc_end = MODULES_END;
+
 	p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
-				module_alloc_base + MODULES_VSIZE,
-				gfp_mask, PAGE_KERNEL_EXEC, 0,
+				module_alloc_end, gfp_mask, PAGE_KERNEL, 0,
 				NUMA_NO_NODE, __builtin_return_address(0));
 
 	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
@@ -56,8 +49,8 @@
 		 * can simply omit this fallback in that case.
 		 */
 		p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
-				module_alloc_base + SZ_4G, GFP_KERNEL,
-				PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				module_alloc_base + SZ_2G, GFP_KERNEL,
+				PAGE_KERNEL, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 
 	if (p && (kasan_module_alloc(p, size) < 0)) {
@@ -96,16 +89,50 @@
 {
 	s64 sval = do_reloc(op, place, val);
 
+	/*
+	 * The ELF psABI for AArch64 documents the 16-bit and 32-bit place
+	 * relative and absolute relocations as having a range of [-2^15, 2^16)
+	 * or [-2^31, 2^32), respectively. However, in order to be able to
+	 * detect overflows reliably, we have to choose whether we interpret
+	 * such quantities as signed or as unsigned, and stick with it.
+	 * The way we organize our address space requires a signed
+	 * interpretation of 32-bit relative references, so let's use that
+	 * for all R_AARCH64_PRELxx relocations. This means our upper
+	 * bound for overflow detection should be Sxx_MAX rather than Uxx_MAX.
+	 */
+
 	switch (len) {
 	case 16:
 		*(s16 *)place = sval;
-		if (sval < S16_MIN || sval > U16_MAX)
-			return -ERANGE;
+		switch (op) {
+		case RELOC_OP_ABS:
+			if (sval < 0 || sval > U16_MAX)
+				return -ERANGE;
+			break;
+		case RELOC_OP_PREL:
+			if (sval < S16_MIN || sval > S16_MAX)
+				return -ERANGE;
+			break;
+		default:
+			pr_err("Invalid 16-bit data relocation (%d)\n", op);
+			return 0;
+		}
 		break;
 	case 32:
 		*(s32 *)place = sval;
-		if (sval < S32_MIN || sval > U32_MAX)
-			return -ERANGE;
+		switch (op) {
+		case RELOC_OP_ABS:
+			if (sval < 0 || sval > U32_MAX)
+				return -ERANGE;
+			break;
+		case RELOC_OP_PREL:
+			if (sval < S32_MIN || sval > S32_MAX)
+				return -ERANGE;
+			break;
+		default:
+			pr_err("Invalid 32-bit data relocation (%d)\n", op);
+			return 0;
+		}
 		break;
 	case 64:
 		*(s64 *)place = sval;
@@ -198,13 +225,12 @@
 	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 +241,7 @@
 		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,
@@ -288,18 +314,21 @@
 		/* MOVW instruction relocations. */
 		case R_AARCH64_MOVW_UABS_G0_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
 					      AARCH64_INSN_IMM_MOVKZ);
@@ -367,8 +396,9 @@
 			break;
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
+			/* Fall through */
 		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 +443,7 @@
 
 			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,
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 53f371e..4cfed91 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -1,12 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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.
  *
  * Copyright (C) 2013 Citrix Systems
  *
@@ -21,5 +14,5 @@
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops pv_time_ops;
-EXPORT_SYMBOL_GPL(pv_time_ops);
+struct paravirt_patch_template pv_ops;
+EXPORT_SYMBOL_GPL(pv_ops);
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 0e2ea1c..570988c 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Code borrowed from powerpc/kernel/pci-common.c
  *
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
  * Copyright (C) 2014 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.
- *
  */
 
 #include <linux/acpi.h>
@@ -165,16 +161,16 @@
 /* Interface called from ACPI code to setup PCI host controller */
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 {
-	int node = acpi_get_node(root->device->handle);
 	struct acpi_pci_generic_root_info *ri;
 	struct pci_bus *bus, *child;
 	struct acpi_pci_root_ops *root_ops;
+	struct pci_host_bridge *host;
 
-	ri = kzalloc_node(sizeof(*ri), GFP_KERNEL, node);
+	ri = kzalloc(sizeof(*ri), GFP_KERNEL);
 	if (!ri)
 		return NULL;
 
-	root_ops = kzalloc_node(sizeof(*root_ops), GFP_KERNEL, node);
+	root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL);
 	if (!root_ops) {
 		kfree(ri);
 		return NULL;
@@ -194,8 +190,16 @@
 	if (!bus)
 		return NULL;
 
-	pci_bus_size_bridges(bus);
-	pci_bus_assign_resources(bus);
+	/* If we must preserve the resource configuration, claim now */
+	host = pci_find_host_bridge(bus);
+	if (host->preserve_config)
+		pci_bus_claim_resources(bus);
+
+	/*
+	 * Assign whatever was left unassigned. If we didn't claim above,
+	 * this will reassign everything.
+	 */
+	pci_assign_unassigned_root_bus_resources(bus);
 
 	list_for_each_entry(child, &bus->children, node)
 		pcie_bus_configure_settings(child);
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index bcafd7d..b0e03e0 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -1,23 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arm64 callchain support
  *
  * Copyright (C) 2015 ARM Limited
- *
- * 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/perf_event.h>
 #include <linux/uaccess.h>
 
+#include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
 
 struct frame_tail {
@@ -35,9 +25,10 @@
 {
 	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)))
+	if (!access_ok(tail, sizeof(buftail)))
 		return NULL;
 
 	pagefault_disable();
@@ -47,7 +38,9 @@
 	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
@@ -82,7 +75,7 @@
 	unsigned long err;
 
 	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+	if (!access_ok(tail, sizeof(buftail)))
 		return NULL;
 
 	pagefault_disable();
@@ -161,12 +154,7 @@
 		return;
 	}
 
-	frame.fp = regs->regs[29];
-	frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
-#endif
-
+	start_backtrace(&frame, regs->regs[29], regs->pc);
 	walk_stackframe(current, &frame, callchain_trace, entry);
 }
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index e213f8e..a0b4f1b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1,22 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * PMU support
+ * ARMv8 PMUv3 Performance Events handling code.
  *
  * Copyright (C) 2012 ARM Limited
  * Author: Will Deacon <will.deacon@arm.com>
  *
  * This code is based heavily on the ARMv7 perf event code.
- *
- * 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 <asm/irq_regs.h>
@@ -26,152 +15,11 @@
 
 #include <linux/acpi.h>
 #include <linux/clocksource.h>
+#include <linux/kvm_host.h>
 #include <linux/of.h>
 #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
+#include <linux/smp.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -183,12 +31,10 @@
 #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 +56,6 @@
 
 	[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 +68,6 @@
 
 	[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]
@@ -316,7 +158,6 @@
 	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
 }
 
-#define ARMV8_EVENT_ATTR_RESOLVE(m) #m
 #define ARMV8_EVENT_ATTR(name, config) \
 	PMU_EVENT_ATTR(name, armv8_event_attr_##name, \
 		       config, armv8pmu_events_sysfs_show)
@@ -370,6 +211,18 @@
 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 +273,18 @@
 	&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 +299,13 @@
 
 	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;
@@ -550,7 +421,7 @@
 	return val;
 }
 
-static inline u64 armv8pmu_read_counter(struct perf_event *event)
+static u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -587,7 +458,7 @@
 	}
 }
 
-static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
+static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -647,12 +518,21 @@
 
 static inline void armv8pmu_enable_event_counter(struct perf_event *event)
 {
+	struct perf_event_attr *attr = &event->attr;
 	int idx = event->hw.idx;
+	u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
 
-	armv8pmu_enable_counter(idx);
 	if (armv8pmu_event_is_chained(event))
-		armv8pmu_enable_counter(idx - 1);
-	isb();
+		counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+	kvm_set_pmu_events(counter_bits, attr);
+
+	/* We rely on the hypervisor switch code to enable guest counters */
+	if (!kvm_pmu_counter_deferred(attr)) {
+		armv8pmu_enable_counter(idx);
+		if (armv8pmu_event_is_chained(event))
+			armv8pmu_enable_counter(idx - 1);
+	}
 }
 
 static inline int armv8pmu_disable_counter(int idx)
@@ -665,11 +545,21 @@
 static inline void armv8pmu_disable_event_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct perf_event_attr *attr = &event->attr;
 	int idx = hwc->idx;
+	u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
 
 	if (armv8pmu_event_is_chained(event))
-		armv8pmu_disable_counter(idx - 1);
-	armv8pmu_disable_counter(idx);
+		counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+	kvm_clr_pmu_events(counter_bits);
+
+	/* We rely on the hypervisor switch code to disable guest counters */
+	if (!kvm_pmu_counter_deferred(attr)) {
+		if (armv8pmu_event_is_chained(event))
+			armv8pmu_disable_counter(idx - 1);
+		armv8pmu_disable_counter(idx);
+	}
 }
 
 static inline int armv8pmu_enable_intens(int idx)
@@ -929,7 +819,7 @@
 }
 
 /*
- * Add an event filter to a given event. This will only work for PMUv2 PMUs.
+ * Add an event filter to a given event.
  */
 static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 				     struct perf_event_attr *attr)
@@ -946,14 +836,23 @@
 	 * with other architectures (x86 and Power).
 	 */
 	if (is_kernel_in_hyp_mode()) {
-		if (!attr->exclude_kernel)
+		if (!attr->exclude_kernel && !attr->exclude_host)
 			config_base |= ARMV8_PMU_INCLUDE_EL2;
-	} else {
-		if (attr->exclude_kernel)
+		if (attr->exclude_guest)
 			config_base |= ARMV8_PMU_EXCLUDE_EL1;
-		if (!attr->exclude_hv)
+		if (attr->exclude_host)
+			config_base |= ARMV8_PMU_EXCLUDE_EL0;
+	} else {
+		if (!attr->exclude_hv && !attr->exclude_host)
 			config_base |= ARMV8_PMU_INCLUDE_EL2;
 	}
+
+	/*
+	 * Filter out !VHE kernels and guest kernels
+	 */
+	if (attr->exclude_kernel)
+		config_base |= ARMV8_PMU_EXCLUDE_EL1;
+
 	if (attr->exclude_user)
 		config_base |= ARMV8_PMU_EXCLUDE_EL0;
 
@@ -983,6 +882,9 @@
 		armv8pmu_disable_intens(idx);
 	}
 
+	/* Clear the counters we flip at guest entry/exit */
+	kvm_clr_pmu_events(U32_MAX);
+
 	/*
 	 * Initialize & Reset PMNC. Request overflow interrupt for
 	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
@@ -1009,7 +911,7 @@
 	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 +963,7 @@
 	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 +982,17 @@
 	/* 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 +1018,16 @@
 	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 +1183,7 @@
 	.driver		= {
 		.name	= ARMV8_PMU_PDEV_NAME,
 		.of_match_table = armv8_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= armv8_pmu_device_probe,
 };
diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c
new file mode 100644
index 0000000..c507b58
--- /dev/null
+++ 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;
+}
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 6bf6657..b78fac9 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm64/kernel/probes/decode-insn.c
  *
  * Copyright (C) 2013 Linaro Limited.
- *
- * 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.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/arm64/kernel/probes/decode-insn.h b/arch/arm64/kernel/probes/decode-insn.h
index 192ab00..8b758c5 100644
--- a/arch/arm64/kernel/probes/decode-insn.h
+++ b/arch/arm64/kernel/probes/decode-insn.h
@@ -1,16 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * arch/arm64/kernel/probes/decode-insn.h
  *
  * Copyright (C) 2013 Linaro Limited.
- *
- * 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.
  */
 
 #ifndef _ARM_KERNEL_KPROBES_ARM64_H
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index b5a367d..c445282 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm64/kernel/probes/kprobes.c
  *
@@ -5,16 +6,6 @@
  *
  * Copyright (C) 2013 Linaro Limited.
  * Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org>
- *
- * 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.
- *
  */
 #include <linux/kasan.h>
 #include <linux/kernel.h>
@@ -30,6 +21,7 @@
 #include <asm/ptrace.h>
 #include <asm/cacheflush.h>
 #include <asm/debug-monitors.h>
+#include <asm/daifflags.h>
 #include <asm/system_misc.h>
 #include <asm/insn.h>
 #include <linux/uaccess.h>
@@ -91,8 +83,6 @@
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
 	unsigned long probe_addr = (unsigned long)p->addr;
-	extern char __start_rodata[];
-	extern char __end_rodata[];
 
 	if (probe_addr & 0x3)
 		return -EINVAL;
@@ -100,10 +90,7 @@
 	/* copy instruction */
 	p->opcode = le32_to_cpu(*p->addr);
 
-	if (in_exception_text(probe_addr))
-		return -EINVAL;
-	if (probe_addr >= (unsigned long) __start_rodata &&
-	    probe_addr <= (unsigned long) __end_rodata)
+	if (search_exception_tables(probe_addr))
 		return -EINVAL;
 
 	/* decode instruction */
@@ -120,7 +107,7 @@
 		if (!p->ainsn.api.insn)
 			return -ENOMEM;
 		break;
-	};
+	}
 
 	/* prepare the instruction */
 	if (p->ainsn.api.insn)
@@ -136,8 +123,10 @@
 	void *page;
 
 	page = vmalloc_exec(PAGE_SIZE);
-	if (page)
+	if (page) {
 		set_memory_ro((unsigned long)page, 1);
+		set_vm_flush_reset_perms(page);
+	}
 
 	return page;
 }
@@ -180,33 +169,6 @@
 }
 
 /*
- * When PSTATE.D is set (masked), then software step exceptions can not be
- * generated.
- * SPSR's D bit shows the value of PSTATE.D immediately before the
- * exception was taken. PSTATE.D is set while entering into any exception
- * mode, however software clears it for any normal (none-debug-exception)
- * mode in the exception entry. Therefore, when we are entering into kprobe
- * breakpoint handler from any normal mode then SPSR.D bit is already
- * cleared, however it is set when we are entering from any debug exception
- * mode.
- * Since we always need to generate single step exception after a kprobe
- * breakpoint exception therefore we need to clear it unconditionally, when
- * we become sure that the current breakpoint exception is for kprobe.
- */
-static void __kprobes
-spsr_set_debug_flag(struct pt_regs *regs, int mask)
-{
-	unsigned long spsr = regs->pstate;
-
-	if (mask)
-		spsr |= PSR_D_BIT;
-	else
-		spsr &= ~PSR_D_BIT;
-
-	regs->pstate = spsr;
-}
-
-/*
  * Interrupts need to be disabled before single-step mode is set, and not
  * reenabled until after single-step mode ends.
  * Without disabling interrupt on local CPU, there is a chance of
@@ -217,17 +179,17 @@
 static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
 						struct pt_regs *regs)
 {
-	kcb->saved_irqflag = regs->pstate;
+	kcb->saved_irqflag = regs->pstate & DAIF_MASK;
 	regs->pstate |= PSR_I_BIT;
+	/* Unmask PSTATE.D for enabling software step exceptions. */
+	regs->pstate &= ~PSR_D_BIT;
 }
 
 static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
 						struct pt_regs *regs)
 {
-	if (kcb->saved_irqflag & PSR_I_BIT)
-		regs->pstate |= PSR_I_BIT;
-	else
-		regs->pstate &= ~PSR_I_BIT;
+	regs->pstate &= ~DAIF_MASK;
+	regs->pstate |= kcb->saved_irqflag;
 }
 
 static void __kprobes
@@ -264,8 +226,6 @@
 
 		set_ss_context(kcb, slot);	/* mark pending ss */
 
-		spsr_set_debug_flag(regs, 0);
-
 		/* IRQs and single stepping do not mix well. */
 		kprobes_save_local_irqflag(kcb, regs);
 		kernel_enable_single_step(regs);
@@ -444,7 +404,7 @@
 	return DBG_HOOK_ERROR;
 }
 
-int __kprobes
+static int __kprobes
 kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -463,33 +423,53 @@
 	return retval;
 }
 
-int __kprobes
+static struct step_hook kprobes_step_hook = {
+	.fn = kprobe_single_step_handler,
+};
+
+static int __kprobes
 kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 {
 	kprobe_handler(regs);
 	return DBG_HOOK_HANDLED;
 }
 
-bool arch_within_kprobe_blacklist(unsigned long addr)
+static struct break_hook kprobes_break_hook = {
+	.imm = KPROBES_BRK_IMM,
+	.fn = kprobe_breakpoint_handler,
+};
+
+/*
+ * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
+ * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
+ */
+int __init arch_populate_kprobe_blacklist(void)
 {
-	if ((addr >= (unsigned long)__kprobes_text_start &&
-	    addr < (unsigned long)__kprobes_text_end) ||
-	    (addr >= (unsigned long)__entry_text_start &&
-	    addr < (unsigned long)__entry_text_end) ||
-	    (addr >= (unsigned long)__idmap_text_start &&
-	    addr < (unsigned long)__idmap_text_end) ||
-	    !!search_exception_tables(addr))
-		return true;
+	int ret;
 
-	if (!is_kernel_in_hyp_mode()) {
-		if ((addr >= (unsigned long)__hyp_text_start &&
-		    addr < (unsigned long)__hyp_text_end) ||
-		    (addr >= (unsigned long)__hyp_idmap_text_start &&
-		    addr < (unsigned long)__hyp_idmap_text_end))
-			return true;
-	}
-
-	return false;
+	ret = kprobe_add_area_blacklist((unsigned long)__entry_text_start,
+					(unsigned long)__entry_text_end);
+	if (ret)
+		return ret;
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					(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)
+		return ret;
+	ret = kprobe_add_area_blacklist((unsigned long)__hyp_text_start,
+					(unsigned long)__hyp_text_end);
+	if (ret || is_kernel_in_hyp_mode())
+		return ret;
+	ret = kprobe_add_area_blacklist((unsigned long)__hyp_idmap_text_start,
+					(unsigned long)__hyp_idmap_text_end);
+	return ret;
 }
 
 void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
@@ -587,5 +567,8 @@
 
 int __init arch_init_kprobes(void)
 {
+	register_kernel_break_hook(&kprobes_break_hook);
+	register_kernel_step_hook(&kprobes_step_hook);
+
 	return 0;
 }
diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c
index be05868..25f67ec 100644
--- a/arch/arm64/kernel/probes/simulate-insn.c
+++ b/arch/arm64/kernel/probes/simulate-insn.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm64/kernel/probes/simulate-insn.c
  *
  * Copyright (C) 2013 Linaro Limited.
- *
- * 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.
  */
 
 #include <linux/bitops.h>
diff --git a/arch/arm64/kernel/probes/simulate-insn.h b/arch/arm64/kernel/probes/simulate-insn.h
index 050bde6..e065dc9 100644
--- a/arch/arm64/kernel/probes/simulate-insn.h
+++ b/arch/arm64/kernel/probes/simulate-insn.h
@@ -1,16 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * arch/arm64/kernel/probes/simulate-insn.h
  *
  * Copyright (C) 2013 Linaro Limited
- *
- * 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.
  */
 
 #ifndef _ARM_KERNEL_KPROBES_SIMULATE_INSN_H
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 636ca01..a412d8e 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
- *
- * 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.
  */
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
@@ -171,7 +168,7 @@
 static int uprobe_breakpoint_handler(struct pt_regs *regs,
 		unsigned int esr)
 {
-	if (user_mode(regs) && uprobe_pre_sstep_notifier(regs))
+	if (uprobe_pre_sstep_notifier(regs))
 		return DBG_HOOK_HANDLED;
 
 	return DBG_HOOK_ERROR;
@@ -182,21 +179,16 @@
 {
 	struct uprobe_task *utask = current->utask;
 
-	if (user_mode(regs)) {
-		WARN_ON(utask &&
-			(instruction_pointer(regs) != utask->xol_vaddr + 4));
-
-		if (uprobe_post_sstep_notifier(regs))
-			return DBG_HOOK_HANDLED;
-	}
+	WARN_ON(utask && (instruction_pointer(regs) != utask->xol_vaddr + 4));
+	if (uprobe_post_sstep_notifier(regs))
+		return DBG_HOOK_HANDLED;
 
 	return DBG_HOOK_ERROR;
 }
 
 /* uprobe breakpoint handler hook */
 static struct break_hook uprobes_break_hook = {
-	.esr_mask = BRK64_ESR_MASK,
-	.esr_val = BRK64_ESR_UPROBES,
+	.imm = UPROBES_BRK_IMM,
 	.fn = uprobe_breakpoint_handler,
 };
 
@@ -207,8 +199,8 @@
 
 static int __init arch_init_uprobes(void)
 {
-	register_break_hook(&uprobes_break_hook);
-	register_step_hook(&uprobes_step_hook);
+	register_user_break_hook(&uprobes_break_hook);
+	register_user_step_hook(&uprobes_step_hook);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7f1628e..71f788c 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/process.c
  *
  * Original Copyright (C) 1995  Linus Torvalds
  * Copyright (C) 1996-2000 Russell King - Converted to ARM.
  * 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 <stdarg.h>
@@ -28,8 +17,10 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
+#include <linux/lockdep.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>
@@ -49,17 +40,21 @@
 #include <trace/events/power.h>
 #include <linux/percpu.h>
 #include <linux/thread_info.h>
+#include <linux/prctl.h>
 
 #include <asm/alternative.h>
+#include <asm/arch_gicv3.h>
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/cacheflush.h>
 #include <asm/exec.h>
 #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);
@@ -73,6 +68,50 @@
 
 void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 
+static void __cpu_do_idle(void)
+{
+	dsb(sy);
+	wfi();
+}
+
+static void __cpu_do_idle_irqprio(void)
+{
+	unsigned long pmr;
+	unsigned long daif_bits;
+
+	daif_bits = read_sysreg(daif);
+	write_sysreg(daif_bits | PSR_I_BIT, daif);
+
+	/*
+	 * Unmask PMR before going idle to make sure interrupts can
+	 * be raised.
+	 */
+	pmr = gic_read_pmr();
+	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	__cpu_do_idle();
+
+	gic_write_pmr(pmr);
+	write_sysreg(daif_bits, daif);
+}
+
+/*
+ *	cpu_do_idle()
+ *
+ *	Idle the processor (wait for interrupt).
+ *
+ *	If the CPU supports priority masking we must do additional work to
+ *	ensure that interrupts are not masked at the PMR (because the core will
+ *	not wake up if we block the wake up signal in the interrupt controller).
+ */
+void cpu_do_idle(void)
+{
+	if (system_uses_irq_prio_masking())
+		__cpu_do_idle_irqprio();
+	else
+		__cpu_do_idle();
+}
+
 /*
  * This is our default idle handler.
  */
@@ -231,6 +270,9 @@
 
 	printk("sp : %016llx\n", sp);
 
+	if (system_uses_irq_prio_masking())
+		printk("pmr_save: %08llx\n", regs->pmr_save);
+
 	i = top_reg;
 
 	while (i >= 0) {
@@ -269,11 +311,18 @@
 	}
 }
 
+static void flush_tagged_addr_state(void)
+{
+	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI))
+		clear_thread_flag(TIF_TAGGED_ADDR);
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	flush_tagged_addr_state();
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -285,22 +334,27 @@
 	fpsimd_release_task(tsk);
 }
 
-/*
- * src and dst may temporarily have aliased sve_state after task_struct
- * is copied.  We cannot fix this properly here, because src may have
- * live SVE state and dst's thread_info may not exist yet, so tweaking
- * either src's or dst's TIF_SVE is not safe.
- *
- * The unaliasing is done in copy_thread() instead.  This works because
- * dst is not schedulable or traceable until both of these functions
- * have been called.
- */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	if (current->mm)
 		fpsimd_preserve_current_state();
 	*dst = *src;
 
+	/* We rely on the above assignment to initialize dst's thread_flags: */
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK));
+
+	/*
+	 * Detach src's sve_state (if any) from dst so that it does not
+	 * get erroneously used or freed prematurely.  dst's sve_state
+	 * will be allocated on demand later on if dst uses SVE.
+	 * For consistency, also clear TIF_SVE here: this could be done
+	 * later in copy_process(), but to avoid tripping up future
+	 * maintainers it is best not to leave TIF_SVE and sve_state in
+	 * an inconsistent state, even temporarily.
+	 */
+	dst->thread.sve_state = NULL;
+	clear_tsk_thread_flag(dst, TIF_SVE);
+
 	return 0;
 }
 
@@ -314,13 +368,6 @@
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
 	/*
-	 * Unalias p->thread.sve_state (if any) from the parent task
-	 * and disable discard SVE state for p:
-	 */
-	clear_tsk_thread_flag(p, TIF_SVE);
-	p->thread.sve_state = NULL;
-
-	/*
 	 * In case p was allocated the same task_struct pointer as some
 	 * other recently-exited task, make sure p is disassociated from
 	 * any cpu that may have run that now-exited task recently.
@@ -358,6 +405,13 @@
 		if (IS_ENABLED(CONFIG_ARM64_UAO) &&
 		    cpus_have_const_cap(ARM64_HAS_UAO))
 			childregs->pstate |= PSR_UAO_BIT;
+
+		if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
+			set_ssbs_bit(childregs);
+
+		if (system_uses_irq_prio_masking())
+			childregs->pmr_save = GIC_PRIO_IRQON;
+
 		p->thread.cpu_context.x19 = stack_start;
 		p->thread.cpu_context.x20 = stk_sz;
 	}
@@ -398,6 +452,32 @@
 }
 
 /*
+ * Force SSBS state on context-switch, since it may be lost after migrating
+ * from a CPU which treats the bit as RES0 in a heterogeneous system.
+ */
+static void ssbs_thread_switch(struct task_struct *next)
+{
+	struct pt_regs *regs = task_pt_regs(next);
+
+	/*
+	 * Nothing to do for kernel threads, but 'regs' may be junk
+	 * (e.g. idle task) so check the flags and bail early.
+	 */
+	if (unlikely(next->flags & PF_KTHREAD))
+		return;
+
+	/* If the mitigation is enabled, then we leave SSBS clear. */
+	if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
+	    test_tsk_thread_flag(next, TIF_SSBD))
+		return;
+
+	if (compat_user_mode(regs))
+		set_compat_ssbs_bit(regs);
+	else if (user_mode(regs))
+		set_ssbs_bit(regs);
+}
+
+/*
  * We store our current task in sp_el0, which is clobbered by userspace. Keep a
  * shadow copy so that we can restore this upon entry from userspace.
  *
@@ -425,6 +505,8 @@
 	contextidr_thread_switch(next);
 	entry_task_switch(next);
 	uao_thread_switch(next);
+	ptrauth_thread_switch(next);
+	ssbs_thread_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -452,11 +534,8 @@
 	if (!stack_page)
 		return 0;
 
-	frame.fp = thread_saved_fp(p);
-	frame.pc = thread_saved_pc(p);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = p->curr_ret_stack;
-#endif
+	start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p));
+
 	do {
 		if (unwind_frame(p, &frame))
 			goto out;
@@ -478,40 +557,95 @@
 	return sp & ~0xf;
 }
 
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	if (is_compat_task())
-		return randomize_page(mm->brk, SZ_32M);
-	else
-		return randomize_page(mm->brk, SZ_1G);
-}
-
 /*
  * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY.
  */
 void arch_setup_new_exec(void)
 {
 	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+
+	ptrauth_thread_init_user(current);
 }
 
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
-void __used stackleak_check_alloca(unsigned long size)
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_disabled;
+
+long set_tagged_addr_ctrl(unsigned long arg)
 {
-	unsigned long stack_left;
-	unsigned long current_sp = current_stack_pointer;
-	struct stack_info info;
-
-	BUG_ON(!on_accessible_stack(current, current_sp, &info));
-
-	stack_left = current_sp - info.low;
+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;
 
 	/*
-	 * There's a good chance we're almost out of stack space if this
-	 * is true. Using panic() over BUG() is more likely to give
-	 * reliable debugging output.
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled.
 	 */
-	if (size >= stack_left)
-		panic("alloca() over the kernel stack boundary\n");
+	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
+		return -EINVAL;
+
+	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+
+	return 0;
 }
-EXPORT_SYMBOL(stackleak_check_alloca);
-#endif
+
+long get_tagged_addr_ctrl(void)
+{
+	if (is_compat_task())
+		return -EINVAL;
+
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		return PR_TAGGED_ADDR_ENABLE;
+
+	return 0;
+}
+
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+static int zero;
+static int one = 1;
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr_disabled",
+		.mode		= 0644,
+		.data		= &tagged_addr_disabled,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{ }
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+	return 0;
+}
+
+core_initcall(tagged_addr_init);
+#endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
+
+asmlinkage void __sched arm64_preempt_schedule_irq(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Preempting a task from an IRQ means we leave copies of PSTATE
+	 * on the stack. cpufeature's enable calls may modify PSTATE, but
+	 * resuming one of these preempted tasks would undo those changes.
+	 *
+	 * Only allow a task to be preempted once cpufeatures have been
+	 * enabled.
+	 */
+	if (static_branch_likely(&arm64_const_caps_ready))
+		preempt_schedule_irq();
+}
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index e8edbf1..c9f72b2 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -1,12 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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.
  *
  * Copyright (C) 2013 ARM Limited
  *
@@ -24,7 +17,6 @@
 
 #include <uapi/linux/psci.h>
 
-#include <asm/compiler.h>
 #include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/smp_plat.h>
@@ -54,6 +46,11 @@
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static bool cpu_psci_cpu_can_disable(unsigned int cpu)
+{
+	return !psci_tos_resident_on(cpu);
+}
+
 static int cpu_psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
@@ -113,14 +110,11 @@
 
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
-#ifdef CONFIG_CPU_IDLE
-	.cpu_init_idle	= psci_cpu_init_idle,
-	.cpu_suspend	= psci_cpu_suspend_enter,
-#endif
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
 #ifdef CONFIG_HOTPLUG_CPU
+	.cpu_can_disable = cpu_psci_cpu_can_disable,
 	.cpu_disable	= cpu_psci_cpu_disable,
 	.cpu_die	= cpu_psci_cpu_die,
 	.cpu_kill	= cpu_psci_cpu_kill,
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6219486..21176d0 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/ptrace.c
  *
@@ -5,18 +6,6 @@
  * edited by Linus Torvalds
  * ARM modifications 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/audit.h>
@@ -46,6 +35,7 @@
 #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>
@@ -182,13 +172,7 @@
 				struct pt_regs *regs)
 {
 	struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
-	siginfo_t info;
-
-	clear_siginfo(&info);
-	info.si_signo	= SIGTRAP;
-	info.si_errno	= 0;
-	info.si_code	= TRAP_HWBKPT;
-	info.si_addr	= (void __user *)(bkpt->trigger);
+	const char *desc = "Hardware breakpoint trap (ptrace)";
 
 #ifdef CONFIG_COMPAT
 	if (is_compat_task()) {
@@ -208,10 +192,14 @@
 				break;
 			}
 		}
-		force_sig_ptrace_errno_trap(si_errno, (void __user *)bkpt->trigger);
+		arm64_force_sig_ptrace_errno_trap(si_errno,
+						  (void __user *)bkpt->trigger,
+						  desc);
 	}
 #endif
-	arm64_force_sig_info(&info, "Hardware breakpoint trap (ptrace)", current);
+	arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT,
+			      (void __user *)(bkpt->trigger),
+			      desc);
 }
 
 /*
@@ -882,7 +870,7 @@
 		goto out;
 
 	/*
-	 * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by
+	 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
 	 * sve_set_vector_length(), which will also validate them for us:
 	 */
 	ret = sve_set_vector_length(target, header.vl,
@@ -958,6 +946,155 @@
 
 #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);
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static __uint128_t pac_key_to_user(const struct ptrauth_key *key)
+{
+	return (__uint128_t)key->hi << 64 | key->lo;
+}
+
+static struct ptrauth_key pac_key_from_user(__uint128_t ukey)
+{
+	struct ptrauth_key key = {
+		.lo = (unsigned long)ukey,
+		.hi = (unsigned long)(ukey >> 64),
+	};
+
+	return key;
+}
+
+static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys,
+				     const struct ptrauth_keys *keys)
+{
+	ukeys->apiakey = pac_key_to_user(&keys->apia);
+	ukeys->apibkey = pac_key_to_user(&keys->apib);
+	ukeys->apdakey = pac_key_to_user(&keys->apda);
+	ukeys->apdbkey = pac_key_to_user(&keys->apdb);
+}
+
+static void pac_address_keys_from_user(struct ptrauth_keys *keys,
+				       const struct user_pac_address_keys *ukeys)
+{
+	keys->apia = pac_key_from_user(ukeys->apiakey);
+	keys->apib = pac_key_from_user(ukeys->apibkey);
+	keys->apda = pac_key_from_user(ukeys->apdakey);
+	keys->apdb = pac_key_from_user(ukeys->apdbkey);
+}
+
+static int pac_address_keys_get(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				void *kbuf, void __user *ubuf)
+{
+	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct user_pac_address_keys user_keys;
+
+	if (!system_supports_address_auth())
+		return -EINVAL;
+
+	pac_address_keys_to_user(&user_keys, keys);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &user_keys, 0, -1);
+}
+
+static int pac_address_keys_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct user_pac_address_keys user_keys;
+	int ret;
+
+	if (!system_supports_address_auth())
+		return -EINVAL;
+
+	pac_address_keys_to_user(&user_keys, keys);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &user_keys, 0, -1);
+	if (ret)
+		return ret;
+	pac_address_keys_from_user(keys, &user_keys);
+
+	return 0;
+}
+
+static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys,
+				     const struct ptrauth_keys *keys)
+{
+	ukeys->apgakey = pac_key_to_user(&keys->apga);
+}
+
+static void pac_generic_keys_from_user(struct ptrauth_keys *keys,
+				       const struct user_pac_generic_keys *ukeys)
+{
+	keys->apga = pac_key_from_user(ukeys->apgakey);
+}
+
+static int pac_generic_keys_get(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				void *kbuf, void __user *ubuf)
+{
+	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct user_pac_generic_keys user_keys;
+
+	if (!system_supports_generic_auth())
+		return -EINVAL;
+
+	pac_generic_keys_to_user(&user_keys, keys);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &user_keys, 0, -1);
+}
+
+static int pac_generic_keys_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct user_pac_generic_keys user_keys;
+	int ret;
+
+	if (!system_supports_generic_auth())
+		return -EINVAL;
+
+	pac_generic_keys_to_user(&user_keys, keys);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &user_keys, 0, -1);
+	if (ret)
+		return ret;
+	pac_generic_keys_from_user(keys, &user_keys);
+
+	return 0;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -970,6 +1107,13 @@
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SVE,
 #endif
+#ifdef CONFIG_ARM64_PTR_AUTH
+	REGSET_PAC_MASK,
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REGSET_PACA_KEYS,
+	REGSET_PACG_KEYS,
+#endif
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -1039,6 +1183,34 @@
 		.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 */
+	},
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	[REGSET_PACA_KEYS] = {
+		.core_note_type = NT_ARM_PACA_KEYS,
+		.n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t),
+		.size = sizeof(__uint128_t),
+		.align = sizeof(__uint128_t),
+		.get = pac_address_keys_get,
+		.set = pac_address_keys_set,
+	},
+	[REGSET_PACG_KEYS] = {
+		.core_note_type = NT_ARM_PACG_KEYS,
+		.n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t),
+		.size = sizeof(__uint128_t),
+		.align = sizeof(__uint128_t),
+		.get = pac_generic_keys_get,
+		.set = pac_generic_keys_set,
+	},
+#endif
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {
@@ -1636,8 +1808,12 @@
 
 int syscall_trace_enter(struct pt_regs *regs)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (test_thread_flag(TIF_SYSCALL_TRACE) ||
+		test_thread_flag(TIF_SYSCALL_EMU)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+		if (!in_syscall(regs) || test_thread_flag(TIF_SYSCALL_EMU))
+			return -1;
+	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
 	if (secure_computing(NULL) == -1)
@@ -1666,19 +1842,20 @@
 }
 
 /*
- * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a
- * We also take into account DIT (bit 24), which is not yet documented, and
- * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be
- * allocated an EL0 meaning in future.
+ * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a.
+ * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is
+ * not described in ARM DDI 0487D.a.
+ * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may
+ * be allocated an EL0 meaning in future.
  * Userspace cannot use these until they have an architectural meaning.
  * Note that this follows the SPSR_ELx format, not the AArch32 PSR format.
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
-	 GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5))
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	 GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20))
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
 
 static int valid_compat_regs(struct user_pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/reloc_test_core.c b/arch/arm64/kernel/reloc_test_core.c
index 5915ce5..e87a2b7 100644
--- a/arch/arm64/kernel/reloc_test_core.c
+++ b/arch/arm64/kernel/reloc_test_core.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- *
- * 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.
- *
  */
 
 #include <linux/module.h>
diff --git a/arch/arm64/kernel/reloc_test_syms.S b/arch/arm64/kernel/reloc_test_syms.S
index 2b8d9cb..16a34f1 100644
--- a/arch/arm64/kernel/reloc_test_syms.S
+++ b/arch/arm64/kernel/reloc_test_syms.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- *
- * 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.
- *
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index f407e42..c1d7db7 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * kexec for arm64
  *
  * Copyright (C) Linaro.
  * Copyright (C) Huawei Futurewei Technologies.
- *
- * 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.
  */
 
 #include <linux/kexec.h>
@@ -32,6 +29,7 @@
 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 +105,7 @@
 	isb
 
 	/* Start new image. */
-	mov	x0, xzr
+	mov	x0, x18
 	mov	x1, xzr
 	mov	x2, xzr
 	mov	x3, xzr
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index 933adbc..a5e8b3b 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -1,16 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm64/kernel/return_address.c
  *
  * Copyright (C) 2013 Linaro Limited
  * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
- *
- * 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.
  */
 
 #include <linux/export.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 
 #include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
@@ -32,6 +30,7 @@
 		return 0;
 	}
 }
+NOKPROBE_SYMBOL(save_return_addr);
 
 void *return_address(unsigned int level)
 {
@@ -41,12 +40,9 @@
 	data.level = level + 2;
 	data.addr = NULL;
 
-	frame.fp = (unsigned long)__builtin_frame_address(0);
-	frame.pc = (unsigned long)return_address; /* dummy */
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
-#endif
-
+	start_backtrace(&frame,
+			(unsigned long)__builtin_frame_address(0),
+			(unsigned long)return_address);
 	walk_stackframe(current, &frame, save_return_addr, &data);
 
 	if (!data.level)
@@ -55,3 +51,4 @@
 		return NULL;
 }
 EXPORT_SYMBOL_GPL(return_address);
+NOKPROBE_SYMBOL(return_address);
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 5ba4465..ea94cf8 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -94,6 +94,9 @@
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
+	if (!low)
+		return false;
+
 	if (sp < low || sp >= high)
 		return false;
 
@@ -111,6 +114,9 @@
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
+	if (!low)
+		return false;
+
 	if (sp < low || sp >= high)
 		return false;
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index b3354ff..56f6645 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/setup.c
  *
  * Copyright (C) 1995-2001 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/acpi.h>
@@ -26,7 +15,6 @@
 #include <linux/initrd.h>
 #include <linux/console.h>
 #include <linux/cache.h>
-#include <linux/bootmem.h>
 #include <linux/screen_info.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
@@ -59,7 +47,6 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
-#include <asm/memblock.h>
 #include <asm/efi.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/mmu_context.h>
@@ -183,9 +170,13 @@
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	void *dt_virt = fixmap_remap_fdt(dt_phys);
+	int size;
+	void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	const char *name;
 
+	if (dt_virt)
+		memblock_reserve(dt_phys, size);
+
 	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
 		pr_crit("\n"
 			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
@@ -197,6 +188,9 @@
 			cpu_relax();
 	}
 
+	/* Early fixups are done, map the FDT as read-only now */
+	fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
+
 	name = of_flat_dt_get_machine_name();
 	if (!name)
 		return;
@@ -210,6 +204,7 @@
 	struct memblock_region *region;
 	struct resource *res;
 	unsigned long i = 0;
+	size_t res_size;
 
 	kernel_code.start   = __pa_symbol(_text);
 	kernel_code.end     = __pa_symbol(__init_begin - 1);
@@ -217,8 +212,10 @@
 	kernel_data.end     = __pa_symbol(_end - 1);
 
 	num_standard_resources = memblock.memory.cnt;
-	standard_resources = alloc_bootmem_low(num_standard_resources *
-					       sizeof(*standard_resources));
+	res_size = num_standard_resources * sizeof(*standard_resources);
+	standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
+	if (!standard_resources)
+		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
 
 	for_each_memblock(memory, region) {
 		res = &standard_resources[i++];
@@ -293,6 +290,11 @@
 
 	setup_machine_fdt(__fdt_pointer);
 
+	/*
+	 * Initialise the static keys early as they may be enabled by the
+	 * cpufeature code and early parameters.
+	 */
+	jump_label_init();
 	parse_early_param();
 
 	/*
@@ -339,6 +341,9 @@
 	smp_init_cpus();
 	smp_build_mpidr_hash();
 
+	/* Init percpu seeds for random tags after cpus are set up. */
+	kasan_init_tags();
+
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Make sure init_thread_info.ttbr0 always generates translation
@@ -349,12 +354,8 @@
 #endif
 
 #ifdef CONFIG_VT
-#if defined(CONFIG_VGA_CONSOLE)
-	conswitchp = &vga_con;
-#elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
 #endif
-#endif
 	if (boot_args[1] || boot_args[2] || boot_args[3]) {
 		pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
 			"\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n"
@@ -363,6 +364,15 @@
 	}
 }
 
+static inline bool cpu_can_disable(unsigned int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable)
+		return cpu_ops[cpu]->cpu_can_disable(cpu);
+#endif
+	return false;
+}
+
 static int __init topology_init(void)
 {
 	int i;
@@ -372,7 +382,7 @@
 
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
-		cpu->hotpluggable = 1;
+		cpu->hotpluggable = cpu_can_disable(i);
 		register_cpu(cpu, i);
 	}
 
@@ -391,6 +401,7 @@
 	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");
 	}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 5dcc942..dd2cdc0 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/signal.c
  *
  * Copyright (C) 1995-2009 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/cache.h>
@@ -296,11 +285,6 @@
 	 */
 
 	fpsimd_flush_task_state(current);
-	barrier();
-	/* From now, fpsimd_thread_switch() won't clear TIF_FOREIGN_FPSTATE */
-
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
-	barrier();
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
 	sve_alloc(current);
@@ -470,7 +454,7 @@
 			offset = 0;
 			limit = extra_size;
 
-			if (!access_ok(VERIFY_READ, base, limit))
+			if (!access_ok(base, limit))
 				goto invalid;
 
 			continue;
@@ -556,7 +540,7 @@
 
 	frame = (struct rt_sigframe __user *)regs->sp;
 
-	if (!access_ok(VERIFY_READ, frame, sizeof (*frame)))
+	if (!access_ok(frame, sizeof (*frame)))
 		goto badframe;
 
 	if (restore_sigframe(regs, frame))
@@ -730,7 +714,7 @@
 	/*
 	 * Check that we can actually write to the signal frame.
 	 */
-	if (!access_ok(VERIFY_WRITE, user->sigframe, sp_top - sp))
+	if (!access_ok(user->sigframe, sp_top - sp))
 		return -EFAULT;
 
 	return 0;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 24b0900..12a5853 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/signal.c
  *
  * Copyright (C) 1995-2009 Russell King
  * Copyright (C) 2012 ARM Ltd.
  * Modified by Will Deacon <will.deacon@arm.com>
- *
- * 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/compat.h>
@@ -29,42 +18,7 @@
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
-
-struct compat_sigcontext {
-	/* We always set these two fields to 0 */
-	compat_ulong_t			trap_no;
-	compat_ulong_t			error_code;
-
-	compat_ulong_t			oldmask;
-	compat_ulong_t			arm_r0;
-	compat_ulong_t			arm_r1;
-	compat_ulong_t			arm_r2;
-	compat_ulong_t			arm_r3;
-	compat_ulong_t			arm_r4;
-	compat_ulong_t			arm_r5;
-	compat_ulong_t			arm_r6;
-	compat_ulong_t			arm_r7;
-	compat_ulong_t			arm_r8;
-	compat_ulong_t			arm_r9;
-	compat_ulong_t			arm_r10;
-	compat_ulong_t			arm_fp;
-	compat_ulong_t			arm_ip;
-	compat_ulong_t			arm_sp;
-	compat_ulong_t			arm_lr;
-	compat_ulong_t			arm_pc;
-	compat_ulong_t			arm_cpsr;
-	compat_ulong_t			fault_address;
-};
-
-struct compat_ucontext {
-	compat_ulong_t			uc_flags;
-	compat_uptr_t			uc_link;
-	compat_stack_t			uc_stack;
-	struct compat_sigcontext	uc_mcontext;
-	compat_sigset_t			uc_sigmask;
-	int		__unused[32 - (sizeof (compat_sigset_t) / sizeof (int))];
-	compat_ulong_t	uc_regspace[128] __attribute__((__aligned__(8)));
-};
+#include <asm/vdso.h>
 
 struct compat_vfp_sigframe {
 	compat_ulong_t	magic;
@@ -92,16 +46,6 @@
 	unsigned long			end_magic;
 } __attribute__((__aligned__(8)));
 
-struct compat_sigframe {
-	struct compat_ucontext	uc;
-	compat_ulong_t		retcode[2];
-};
-
-struct compat_rt_sigframe {
-	struct compat_siginfo info;
-	struct compat_sigframe sig;
-};
-
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
@@ -303,7 +247,7 @@
 
 	frame = (struct compat_sigframe __user *)regs->compat_sp;
 
-	if (!access_ok(VERIFY_READ, frame, sizeof (*frame)))
+	if (!access_ok(frame, sizeof (*frame)))
 		goto badframe;
 
 	if (compat_restore_sigframe(regs, frame))
@@ -334,7 +278,7 @@
 
 	frame = (struct compat_rt_sigframe __user *)regs->compat_sp;
 
-	if (!access_ok(VERIFY_READ, frame, sizeof (*frame)))
+	if (!access_ok(frame, sizeof (*frame)))
 		goto badframe;
 
 	if (compat_restore_sigframe(regs, &frame->sig))
@@ -365,7 +309,7 @@
 	/*
 	 * Check that we can actually write to the signal frame.
 	 */
-	if (!access_ok(VERIFY_WRITE, frame, framesize))
+	if (!access_ok(frame, framesize))
 		frame = NULL;
 
 	return frame;
@@ -398,14 +342,38 @@
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
 	} else {
 		/* Set up sigreturn pointer */
+#ifdef CONFIG_COMPAT_VDSO
+		void *vdso_base = current->mm->context.vdso;
+		void *vdso_trampoline;
+
+		if (ka->sa.sa_flags & SA_SIGINFO) {
+			if (thumb) {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_rt_sigreturn_thumb);
+			} else {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_rt_sigreturn_arm);
+			}
+		} else {
+			if (thumb) {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_sigreturn_thumb);
+			} else {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_sigreturn_arm);
+			}
+		}
+
+		retcode = ptr_to_compat(vdso_trampoline) + thumb;
+#else
 		unsigned int idx = thumb << 1;
 
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = AARCH32_VECTORS_BASE +
-			  AARCH32_KERN_SIGRET_CODE_OFFSET +
+		retcode = (unsigned long)current->mm->context.vdso +
 			  (idx << 2) + thumb;
+#endif
 	}
 
 	regs->regs[0]	= usig;
diff --git a/arch/arm64/kernel/sigreturn32.S b/arch/arm64/kernel/sigreturn32.S
new file mode 100644
index 0000000..475d30d
--- /dev/null
+++ b/arch/arm64/kernel/sigreturn32.S
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch32 sigreturn code.
+ * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
+ *
+ * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
+ * Copyright (C) 2012-2018 ARM Ltd.
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+
+#include <asm/unistd.h>
+
+	.globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+	/*
+	 * ARM Code
+	 */
+	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3		// mov	r7, #__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef		// svc	#__NR_compat_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
+
+	/*
+	 * ARM code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
+
+        .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index bebec8e..f5b04dd 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -27,7 +27,7 @@
  *	aff0 = mpidr_masked & 0xff;
  *	aff1 = mpidr_masked & 0xff00;
  *	aff2 = mpidr_masked & 0xff0000;
- *	aff2 = mpidr_masked & 0xff00000000;
+ *	aff3 = mpidr_masked & 0xff00000000;
  *	dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3);
  *}
  * Input registers: rs0, rs1, rs2, rs3, mpidr, mask
@@ -101,6 +101,7 @@
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
+	adrp	x1, swapper_pg_dir
 	bl	__enable_mmu
 	ldr	x8, =_cpu_resume
 	br	x8
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index 6252234..5465527 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -1,19 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (c) 2015, Linaro Limited
- *
- * 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.
- *
  */
 #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 +33,7 @@
 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 +44,4 @@
 ENTRY(__arm_smccc_hvc)
 	SMCCC	hvc
 ENDPROC(__arm_smccc_hvc)
+EXPORT_SYMBOL(__arm_smccc_hvc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 25fcd22..dc9fe87 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * SMP initialisation and IPI support
  * Based on arch/arm/kernel/smp.c
  *
  * 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/acpi.h>
@@ -35,6 +24,7 @@
 #include <linux/smp.h>
 #include <linux/seq_file.h>
 #include <linux/irq.h>
+#include <linux/irqchip/arm-gic-v3.h>
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
 #include <linux/completion.h>
@@ -133,7 +123,7 @@
 		 * time out.
 		 */
 		wait_for_completion_timeout(&cpu_running,
-					    msecs_to_jiffies(1000));
+					    msecs_to_jiffies(5000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
@@ -141,30 +131,37 @@
 		}
 	} else {
 		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
+		return ret;
 	}
 
 	secondary_data.task = NULL;
 	secondary_data.stack = NULL;
+	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
 	if (ret && status) {
 
 		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);
+			cpus_stuck_in_kernel++;
 			break;
 		case CPU_KILL_ME:
 			if (!op_cpu_kill(cpu)) {
 				pr_crit("CPU%u: died during early boot\n", cpu);
 				break;
 			}
-			/* Fall through */
 			pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+			/* Fall through */
 		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:
@@ -175,6 +172,20 @@
 	return ret;
 }
 
+static void init_gic_priority_masking(void)
+{
+	u32 cpuflags;
+
+	if (WARN_ON(!gic_enable_sre()))
+		return;
+
+	cpuflags = read_sysreg(daif);
+
+	WARN_ON(!(cpuflags & PSR_I_BIT));
+
+	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -201,6 +212,9 @@
 	 */
 	cpu_uninstall_idmap();
 
+	if (system_uses_irq_prio_masking())
+		init_gic_priority_masking();
+
 	preempt_disable();
 	trace_hardirqs_off();
 
@@ -408,12 +422,18 @@
 void __init smp_prepare_boot_cpu(void)
 {
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
-	/*
-	 * Initialise the static keys early as they may be enabled by the
-	 * cpufeature code.
-	 */
-	jump_label_init();
 	cpuinfo_store_boot_cpu();
+
+	/*
+	 * We now know enough about the boot CPU to apply the
+	 * alternatives that cannot wait until interrupt handling
+	 * and/or scheduling is enabled.
+	 */
+	apply_boot_alternatives();
+
+	/* Conditionally switch to GIC PMR for interrupt masking */
+	if (system_uses_irq_prio_masking())
+		init_gic_priority_masking();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -548,7 +568,7 @@
 }
 
 static int __init
-acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
+acpi_parse_gic_cpu_interface(union acpi_subtable_headers *header,
 			     const unsigned long end)
 {
 	struct acpi_madt_generic_interrupt *processor;
@@ -557,7 +577,7 @@
 	if (BAD_MADT_GICC_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	acpi_map_gic_cpu_interface(processor);
 
@@ -602,7 +622,7 @@
 {
 	struct device_node *dn;
 
-	for_each_node_by_type(dn, "cpu") {
+	for_each_of_cpu_node(dn) {
 		u64 hwid = of_get_cpu_mpidr(dn);
 
 		if (hwid == INVALID_HWID)
@@ -807,18 +827,23 @@
 }
 #endif
 
-/*
- * ipi_cpu_stop - handle IPI from smp_send_stop()
- */
-static void ipi_cpu_stop(unsigned int cpu)
+static void local_cpu_stop(void)
 {
-	set_cpu_online(cpu, false);
+	set_cpu_online(smp_processor_id(), false);
 
 	local_daif_mask();
 	sdei_mask_local_cpu();
+	cpu_park_loop();
+}
 
-	while (1)
-		cpu_relax();
+/*
+ * We need to implement panic_smp_self_stop() for parallel panic() calls, so
+ * that cpu_online_mask gets correctly updated and smp_send_stop() can skip
+ * CPUs that have already stopped themselves.
+ */
+void panic_smp_self_stop(void)
+{
+	local_cpu_stop();
 }
 
 #ifdef CONFIG_KEXEC_CORE
@@ -871,7 +896,7 @@
 
 	case IPI_CPU_STOP:
 		irq_enter();
-		ipi_cpu_stop(cpu);
+		local_cpu_stop();
 		irq_exit();
 		break;
 
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 9303465..c8a3fee 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Spin Table SMP initialisation
  *
  * Copyright (C) 2013 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/delay.h>
@@ -30,7 +19,7 @@
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
-volatile unsigned long __section(".mmuoff.data.read")
+volatile unsigned long __section(.mmuoff.data.read)
 secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c
index 3432e5e..52cfc61 100644
--- a/arch/arm64/kernel/ssbd.c
+++ b/arch/arm64/kernel/ssbd.c
@@ -3,17 +3,34 @@
  * Copyright (C) 2018 ARM Ltd, All Rights Reserved.
  */
 
+#include <linux/compat.h>
 #include <linux/errno.h>
+#include <linux/prctl.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/thread_info.h>
 
 #include <asm/cpufeature.h>
 
+static void ssbd_ssbs_enable(struct task_struct *task)
+{
+	u64 val = is_compat_thread(task_thread_info(task)) ?
+		  PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+	task_pt_regs(task)->pstate |= val;
+}
+
+static void ssbd_ssbs_disable(struct task_struct *task)
+{
+	u64 val = is_compat_thread(task_thread_info(task)) ?
+		  PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+	task_pt_regs(task)->pstate &= ~val;
+}
+
 /*
  * prctl interface for SSBD
- * FIXME: Drop the below ifdefery once merged in 4.18.
  */
-#ifdef PR_SPEC_STORE_BYPASS
 static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	int state = arm64_get_ssbd_state();
@@ -46,12 +63,14 @@
 			return -EPERM;
 		task_clear_spec_ssb_disable(task);
 		clear_tsk_thread_flag(task, TIF_SSBD);
+		ssbd_ssbs_enable(task);
 		break;
 	case PR_SPEC_DISABLE:
 		if (state == ARM64_SSBD_FORCE_DISABLE)
 			return -EPERM;
 		task_set_spec_ssb_disable(task);
 		set_tsk_thread_flag(task, TIF_SSBD);
+		ssbd_ssbs_disable(task);
 		break;
 	case PR_SPEC_FORCE_DISABLE:
 		if (state == ARM64_SSBD_FORCE_DISABLE)
@@ -59,6 +78,7 @@
 		task_set_spec_ssb_disable(task);
 		task_set_spec_ssb_force_disable(task);
 		set_tsk_thread_flag(task, TIF_SSBD);
+		ssbd_ssbs_disable(task);
 		break;
 	default:
 		return -ERANGE;
@@ -107,4 +127,3 @@
 		return -ENODEV;
 	}
 }
-#endif	/* PR_SPEC_STORE_BYPASS */
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 4989f7e..a336cb1 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -1,23 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Stack tracing support
  *
  * 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/kernel.h>
 #include <linux/export.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
@@ -40,9 +30,18 @@
  *	ldp	x29, x30, [sp]
  *	add	sp, sp, #0x10
  */
+
+/*
+ * Unwind from one frame record (A) to the next frame record (B).
+ *
+ * We terminate early if the location of B indicates a malformed chain of frame
+ * records (e.g. a cycle), determined based on the location and fp value of A
+ * and the location (but not the fp value) of B.
+ */
 int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 {
 	unsigned long fp = frame->fp;
+	struct stack_info info;
 
 	if (fp & 0xf)
 		return -EINVAL;
@@ -50,27 +49,55 @@
 	if (!tsk)
 		tsk = current;
 
-	if (!on_accessible_stack(tsk, fp, NULL))
+	if (!on_accessible_stack(tsk, fp, &info))
 		return -EINVAL;
 
+	if (test_bit(info.type, frame->stacks_done))
+		return -EINVAL;
+
+	/*
+	 * As stacks grow downward, any valid record on the same stack must be
+	 * at a strictly higher address than the prior record.
+	 *
+	 * Stacks can nest in several valid orders, e.g.
+	 *
+	 * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
+	 * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
+	 *
+	 * ... but the nesting itself is strict. Once we transition from one
+	 * stack to another, it's never valid to unwind back to that first
+	 * stack.
+	 */
+	if (info.type == frame->prev_type) {
+		if (fp <= frame->prev_fp)
+			return -EINVAL;
+	} else {
+		set_bit(frame->prev_type, frame->stacks_done);
+	}
+
+	/*
+	 * Record this frame record's values and location. The prev_fp and
+	 * prev_type are only meaningful to the next unwind_frame() invocation.
+	 */
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
 	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
+	frame->prev_fp = fp;
+	frame->prev_type = info.type;
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
-		if (WARN_ON_ONCE(frame->graph == -1))
-			return -EINVAL;
-		if (frame->graph < -1)
-			frame->graph += FTRACE_NOTRACE_DEPTH;
-
+		struct ftrace_ret_stack *ret_stack;
 		/*
 		 * This is a case where function graph tracer has
 		 * modified a return address (LR) in a stack frame
 		 * to hook a function return.
 		 * So replace it to an original value.
 		 */
-		frame->pc = tsk->ret_stack[frame->graph--].ret;
+		ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++);
+		if (WARN_ON_ONCE(!ret_stack))
+			return -EINVAL;
+		frame->pc = ret_stack->ret;
 	}
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -85,6 +112,7 @@
 
 	return 0;
 }
+NOKPROBE_SYMBOL(unwind_frame);
 
 void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 		     int (*fn)(struct stackframe *, void *), void *data)
@@ -99,6 +127,7 @@
 			break;
 	}
 }
+NOKPROBE_SYMBOL(walk_stackframe);
 
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {
@@ -134,16 +163,10 @@
 	data.skip = trace->skip;
 	data.no_sched_functions = 0;
 
-	frame.fp = regs->regs[29];
-	frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
-#endif
-
+	start_backtrace(&frame, regs->regs[29], regs->pc);
 	walk_stackframe(current, &frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);
 
 static noinline void __save_stack_trace(struct task_struct *tsk,
 	struct stack_trace *trace, unsigned int nosched)
@@ -159,21 +182,17 @@
 	data.no_sched_functions = nosched;
 
 	if (tsk != current) {
-		frame.fp = thread_saved_fp(tsk);
-		frame.pc = thread_saved_pc(tsk);
+		start_backtrace(&frame, thread_saved_fp(tsk),
+				thread_saved_pc(tsk));
 	} else {
 		/* We don't want this function nor the caller */
 		data.skip += 2;
-		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.pc = (unsigned long)__save_stack_trace;
+		start_backtrace(&frame,
+				(unsigned long)__builtin_frame_address(0),
+				(unsigned long)__save_stack_trace);
 	}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = tsk->curr_ret_stack;
-#endif
 
 	walk_stackframe(tsk, &frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
 	put_task_stack(tsk);
 }
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 70c2833..9405d1b 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -48,6 +48,10 @@
 	 */
 	cpu_uninstall_idmap();
 
+	/* Restore CnP bit in TTBR1_EL1 */
+	if (system_supports_cnp())
+		cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+
 	/*
 	 * PSTATE was not saved over suspend/resume, re-enable any detected
 	 * features that might not have been set correctly.
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index b44065f..d5ffaaa 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * AArch64-specific system calls implementation
  *
  * Copyright (C) 2012 ARM Ltd.
  * Author: Catalin Marinas <catalin.marinas@arm.com>
- *
- * 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/compiler.h>
@@ -31,7 +20,7 @@
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, off_t, off)
+		unsigned long, fd, unsigned long, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
@@ -47,22 +36,26 @@
 	return ksys_personality(personality);
 }
 
+asmlinkage long sys_ni_syscall(void);
+
+asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused)
+{
+	return sys_ni_syscall();
+}
+
 /*
  * Wrappers to pass the pt_regs argument.
  */
-#define sys_personality		sys_arm64_personality
-
-asmlinkage long sys_ni_syscall(const struct pt_regs *);
-#define __arm64_sys_ni_syscall	sys_ni_syscall
+#define __arm64_sys_personality		__arm64_sys_arm64_personality
 
 #undef __SYSCALL
 #define __SYSCALL(nr, sym)	asmlinkage long __arm64_##sym(const struct pt_regs *);
 #include <asm/unistd.h>
 
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)__arm64_##sym,
+#define __SYSCALL(nr, sym)	[nr] = __arm64_##sym,
 
 const syscall_fn_t sys_call_table[__NR_syscalls] = {
-	[0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
+	[0 ... __NR_syscalls - 1] = __arm64_sys_ni_syscall,
 #include <asm/unistd.h>
 };
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index 0f8bcb7..fc40386 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm64/kernel/sys32.c
  *
  * Copyright (C) 2015 ARM Ltd.
- *
- * This program is free software(void); 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(void);//www.gnu.org/licenses/>.
  */
 
 /*
@@ -133,17 +122,14 @@
 	return ksys_fallocate(fd, mode, arg_u64(offset), arg_u64(len));
 }
 
-asmlinkage long sys_ni_syscall(const struct pt_regs *);
-#define __arm64_sys_ni_syscall	sys_ni_syscall
-
 #undef __SYSCALL
 #define __SYSCALL(nr, sym)	asmlinkage long __arm64_##sym(const struct pt_regs *);
 #include <asm/unistd32.h>
 
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)__arm64_##sym,
+#define __SYSCALL(nr, sym)	[nr] = __arm64_##sym,
 
 const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] = {
-	[0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
+	[0 ... __NR_compat_syscalls - 1] = __arm64_sys_ni_syscall,
 #include <asm/unistd32.h>
 };
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index a610982..f1cb649 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/sys_arm.c
  *
  * Copyright (C) People who wrote linux/arch/i386/kernel/sys_i386.c
  * Copyright (C) 1995, 1996 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/compat.h>
@@ -58,7 +47,7 @@
 	if (end < start || flags)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_READ, (const void __user *)start, end - start))
+	if (!access_ok((const void __user *)start, end - start))
 		return -EFAULT;
 
 	return __do_compat_cache_op(start, end);
@@ -66,12 +55,11 @@
 /*
  * Handle all unrecognised system calls.
  */
-long compat_arm_syscall(struct pt_regs *regs)
+long compat_arm_syscall(struct pt_regs *regs, int scno)
 {
-	siginfo_t info;
-	unsigned int no = regs->regs[7];
+	void __user *addr;
 
-	switch (no) {
+	switch (scno) {
 	/*
 	 * Flush a region from virtual address 'r0' to virtual address 'r1'
 	 * _exclusive_.  There is no alignment requirement on either address;
@@ -102,23 +90,20 @@
 
 	default:
 		/*
-		 * Calls 9f00xx..9f07ff are defined to return -ENOSYS
+		 * Calls 0xf0xxx..0xf07ff are defined to return -ENOSYS
 		 * if not implemented, rather than raising SIGILL. This
 		 * way the calling program can gracefully determine whether
 		 * a feature is supported.
 		 */
-		if ((no & 0xffff) <= 0x7ff)
+		if (scno < __ARM_NR_COMPAT_END)
 			return -ENOSYS;
 		break;
 	}
 
-	clear_siginfo(&info);
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code  = ILL_ILLTRP;
-	info.si_addr  = (void __user *)instruction_pointer(regs) -
-			 (compat_thumb_mode(regs) ? 2 : 4);
+	addr  = (void __user *)instruction_pointer(regs) -
+		(compat_thumb_mode(regs) ? 2 : 4);
 
-	arm64_notify_die("Oops - bad compat syscall(2)", regs, &info, no);
+	arm64_notify_die("Oops - bad compat syscall(2)", regs,
+			 SIGILL, ILL_ILLTRP, addr, scno);
 	return 0;
 }
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 032d223..871c739 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -8,21 +8,21 @@
 #include <linux/syscalls.h>
 
 #include <asm/daifflags.h>
+#include <asm/debug-monitors.h>
 #include <asm/fpsimd.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
-long compat_arm_syscall(struct pt_regs *regs);
-
+long compat_arm_syscall(struct pt_regs *regs, int scno);
 long sys_ni_syscall(void);
 
-asmlinkage long do_ni_syscall(struct pt_regs *regs)
+static long do_ni_syscall(struct pt_regs *regs, int scno)
 {
 #ifdef CONFIG_COMPAT
 	long ret;
 	if (is_compat_task()) {
-		ret = compat_arm_syscall(regs);
+		ret = compat_arm_syscall(regs, scno);
 		if (ret != -ENOSYS)
 			return ret;
 	}
@@ -47,7 +47,7 @@
 		syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
 		ret = __invoke_syscall(regs, syscall_fn);
 	} else {
-		ret = do_ni_syscall(regs);
+		ret = do_ni_syscall(regs, scno);
 	}
 
 	regs->regs[0] = ret;
@@ -61,6 +61,35 @@
 int syscall_trace_enter(struct pt_regs *regs);
 void syscall_trace_exit(struct pt_regs *regs);
 
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
+
+static void cortex_a76_erratum_1463225_svc_handler(void)
+{
+	u32 reg, val;
+
+	if (!unlikely(test_thread_flag(TIF_SINGLESTEP)))
+		return;
+
+	if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225)))
+		return;
+
+	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1);
+	reg = read_sysreg(mdscr_el1);
+	val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE;
+	write_sysreg(val, mdscr_el1);
+	asm volatile("msr daifclr, #8");
+	isb();
+
+	/* We will have taken a single-step exception by this point */
+
+	write_sysreg(reg, mdscr_el1);
+	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0);
+}
+#else
+static void cortex_a76_erratum_1463225_svc_handler(void) { }
+#endif /* CONFIG_ARM64_ERRATUM_1463225 */
+
 static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 			   const syscall_fn_t syscall_table[])
 {
@@ -69,6 +98,7 @@
 	regs->orig_x0 = regs->regs[0];
 	regs->syscallno = scno;
 
+	cortex_a76_erratum_1463225_svc_handler();
 	local_daif_restore(DAIF_PROCCTX);
 	user_exit();
 
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index f258636..0b29464 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/time.c
  *
  * Copyright (C) 1991, 1992, 1995  Linus Torvalds
  * Modifications for ARM (C) 1994-2001 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/clockchips.h>
@@ -49,11 +38,8 @@
 	if (!in_lock_functions(regs->pc))
 		return regs->pc;
 
-	frame.fp = regs->regs[29];
-	frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
-#endif
+	start_backtrace(&frame, regs->regs[29], regs->pc);
+
 	do {
 		int ret = unwind_frame(NULL, &frame);
 		if (ret < 0)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0825c4a..fa9528d 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -14,250 +14,13 @@
 #include <linux/acpi.h>
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
-#include <linux/cpu.h>
-#include <linux/cpumask.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
-#include <linux/node.h>
-#include <linux/nodemask.h>
-#include <linux/of.h>
-#include <linux/sched.h>
-#include <linux/sched/topology.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/string.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
-static int __init get_cpu_for_node(struct device_node *node)
-{
-	struct device_node *cpu_node;
-	int cpu;
-
-	cpu_node = of_parse_phandle(node, "cpu", 0);
-	if (!cpu_node)
-		return -1;
-
-	cpu = of_cpu_node_to_id(cpu_node);
-	if (cpu >= 0)
-		topology_parse_cpu_capacity(cpu_node, cpu);
-	else
-		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
-
-	of_node_put(cpu_node);
-	return cpu;
-}
-
-static int __init parse_core(struct device_node *core, int package_id,
-			     int core_id)
-{
-	char name[10];
-	bool leaf = true;
-	int i = 0;
-	int cpu;
-	struct device_node *t;
-
-	do {
-		snprintf(name, sizeof(name), "thread%d", i);
-		t = of_get_child_by_name(core, name);
-		if (t) {
-			leaf = false;
-			cpu = get_cpu_for_node(t);
-			if (cpu >= 0) {
-				cpu_topology[cpu].package_id = package_id;
-				cpu_topology[cpu].core_id = core_id;
-				cpu_topology[cpu].thread_id = i;
-			} else {
-				pr_err("%pOF: Can't get CPU for thread\n",
-				       t);
-				of_node_put(t);
-				return -EINVAL;
-			}
-			of_node_put(t);
-		}
-		i++;
-	} while (t);
-
-	cpu = get_cpu_for_node(core);
-	if (cpu >= 0) {
-		if (!leaf) {
-			pr_err("%pOF: Core has both threads and CPU\n",
-			       core);
-			return -EINVAL;
-		}
-
-		cpu_topology[cpu].package_id = package_id;
-		cpu_topology[cpu].core_id = core_id;
-	} else if (leaf) {
-		pr_err("%pOF: Can't get CPU for leaf core\n", core);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int __init parse_cluster(struct device_node *cluster, int depth)
-{
-	char name[10];
-	bool leaf = true;
-	bool has_cores = false;
-	struct device_node *c;
-	static int package_id __initdata;
-	int core_id = 0;
-	int i, ret;
-
-	/*
-	 * First check for child clusters; we currently ignore any
-	 * information about the nesting of clusters and present the
-	 * scheduler with a flat list of them.
-	 */
-	i = 0;
-	do {
-		snprintf(name, sizeof(name), "cluster%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			leaf = false;
-			ret = parse_cluster(c, depth + 1);
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
-		i++;
-	} while (c);
-
-	/* Now check for cores */
-	i = 0;
-	do {
-		snprintf(name, sizeof(name), "core%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			has_cores = true;
-
-			if (depth == 0) {
-				pr_err("%pOF: cpu-map children should be clusters\n",
-				       c);
-				of_node_put(c);
-				return -EINVAL;
-			}
-
-			if (leaf) {
-				ret = parse_core(c, package_id, core_id++);
-			} else {
-				pr_err("%pOF: Non-leaf cluster with core %s\n",
-				       cluster, name);
-				ret = -EINVAL;
-			}
-
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
-		i++;
-	} while (c);
-
-	if (leaf && !has_cores)
-		pr_warn("%pOF: empty cluster\n", cluster);
-
-	if (leaf)
-		package_id++;
-
-	return 0;
-}
-
-static int __init parse_dt_topology(void)
-{
-	struct device_node *cn, *map;
-	int ret = 0;
-	int cpu;
-
-	cn = of_find_node_by_path("/cpus");
-	if (!cn) {
-		pr_err("No CPU information found in DT\n");
-		return 0;
-	}
-
-	/*
-	 * When topology is provided cpu-map is essentially a root
-	 * cluster with restricted subnodes.
-	 */
-	map = of_get_child_by_name(cn, "cpu-map");
-	if (!map)
-		goto out;
-
-	ret = parse_cluster(map, 0);
-	if (ret != 0)
-		goto out_map;
-
-	topology_normalize_cpu_scale();
-
-	/*
-	 * Check that all cores are in the topology; the SMP code will
-	 * only mark cores described in the DT as possible.
-	 */
-	for_each_possible_cpu(cpu)
-		if (cpu_topology[cpu].package_id == -1)
-			ret = -EINVAL;
-
-out_map:
-	of_node_put(map);
-out:
-	of_node_put(cn);
-	return ret;
-}
-
-/*
- * cpu topology table
- */
-struct cpu_topology cpu_topology[NR_CPUS];
-EXPORT_SYMBOL_GPL(cpu_topology);
-
-const struct cpumask *cpu_coregroup_mask(int cpu)
-{
-	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
-
-	/* Find the smaller of NUMA, core or LLC siblings */
-	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
-		/* not numa in package, lets use the package siblings */
-		core_mask = &cpu_topology[cpu].core_sibling;
-	}
-	if (cpu_topology[cpu].llc_id != -1) {
-		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
-			core_mask = &cpu_topology[cpu].llc_sibling;
-	}
-
-	return core_mask;
-}
-
-static void update_siblings_masks(unsigned int cpuid)
-{
-	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
-	int cpu;
-
-	/* update core and thread sibling masks */
-	for_each_online_cpu(cpu) {
-		cpu_topo = &cpu_topology[cpu];
-
-		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
-			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
-			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
-		}
-
-		if (cpuid_topo->package_id != cpu_topo->package_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
-
-		if (cpuid_topo->core_id != cpu_topo->core_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
-	}
-}
-
 void store_cpu_topology(unsigned int cpuid)
 {
 	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
@@ -296,60 +59,31 @@
 	update_siblings_masks(cpuid);
 }
 
-static void clear_cpu_topology(int cpu)
-{
-	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
-	cpumask_clear(&cpu_topo->llc_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
-
-	cpumask_clear(&cpu_topo->core_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
-	cpumask_clear(&cpu_topo->thread_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
-}
-
-static void __init reset_cpu_topology(void)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
-		cpu_topo->thread_id = -1;
-		cpu_topo->core_id = 0;
-		cpu_topo->package_id = -1;
-		cpu_topo->llc_id = -1;
-
-		clear_cpu_topology(cpu);
-	}
-}
-
-void remove_cpu_topology(unsigned int cpu)
-{
-	int sibling;
-
-	for_each_cpu(sibling, topology_core_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
-	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
-	for_each_cpu(sibling, topology_llc_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
-
-	clear_cpu_topology(cpu);
-}
-
 #ifdef CONFIG_ACPI
+static bool __init acpi_cpu_is_threaded(int cpu)
+{
+	int is_threaded = acpi_pptt_cpu_is_thread(cpu);
+
+	/*
+	 * if the PPTT doesn't have thread information, assume a homogeneous
+	 * machine and return the current CPU's thread state.
+	 */
+	if (is_threaded < 0)
+		is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
+
+	return !!is_threaded;
+}
+
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
-static int __init parse_acpi_topology(void)
+int __init parse_acpi_topology(void)
 {
-	bool is_threaded;
 	int cpu, topology_id;
 
-	is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
+	if (acpi_disabled)
+		return 0;
 
 	for_each_possible_cpu(cpu) {
 		int i, cache_id;
@@ -358,7 +92,7 @@
 		if (topology_id < 0)
 			return topology_id;
 
-		if (is_threaded) {
+		if (acpi_cpu_is_threaded(cpu)) {
 			cpu_topology[cpu].thread_id = topology_id;
 			topology_id = find_acpi_cpu_topology(cpu, 1);
 			cpu_topology[cpu].core_id   = topology_id;
@@ -384,24 +118,6 @@
 
 	return 0;
 }
-
-#else
-static inline int __init parse_acpi_topology(void)
-{
-	return -EINVAL;
-}
 #endif
 
-void __init init_cpu_topology(void)
-{
-	reset_cpu_topology();
 
-	/*
-	 * Discard anything that was parsed if we hit an error so we
-	 * don't use partial information.
-	 */
-	if (!acpi_disabled && parse_acpi_topology())
-		reset_cpu_topology();
-	else if (of_have_populated_dt() && parse_dt_topology())
-		reset_cpu_topology();
-}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index b9da093..34739e8 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -1,26 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on arch/arm/kernel/traps.c
  *
  * Copyright (C) 1995-2009 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/bug.h>
+#include <linux/context_tracking.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
+#include <linux/kprobes.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
@@ -35,6 +26,7 @@
 #include <linux/sizes.h>
 #include <linux/syscalls.h>
 #include <linux/mm_types.h>
+#include <linux/kasan.h>
 
 #include <asm/atomic.h>
 #include <asm/bug.h>
@@ -65,16 +57,19 @@
 	printk(" %pS\n", (void *)where);
 }
 
-static void __dump_instr(const char *lvl, struct pt_regs *regs)
+static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
+	if (user_mode(regs))
+		return;
+
 	for (i = -4; i < 1; i++) {
 		unsigned int val, bad;
 
-		bad = get_user(val, &((u32 *)addr)[i]);
+		bad = aarch64_insn_read(&((u32 *)addr)[i], &val);
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val);
@@ -83,28 +78,23 @@
 			break;
 		}
 	}
-	printk("%sCode: %s\n", lvl, str);
-}
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
-{
-	if (!user_mode(regs)) {
-		mm_segment_t fs = get_fs();
-		set_fs(KERNEL_DS);
-		__dump_instr(lvl, regs);
-		set_fs(fs);
-	} else {
-		__dump_instr(lvl, regs);
-	}
+	printk("%sCode: %s\n", lvl, str);
 }
 
 void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	int skip;
+	int skip = 0;
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
+	if (regs) {
+		if (user_mode(regs))
+			return;
+		skip = 1;
+	}
+
 	if (!tsk)
 		tsk = current;
 
@@ -112,20 +102,18 @@
 		return;
 
 	if (tsk == current) {
-		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.pc = (unsigned long)dump_backtrace;
+		start_backtrace(&frame,
+				(unsigned long)__builtin_frame_address(0),
+				(unsigned long)dump_backtrace);
 	} else {
 		/*
 		 * task blocked in __switch_to
 		 */
-		frame.fp = thread_saved_fp(tsk);
-		frame.pc = thread_saved_pc(tsk);
+		start_backtrace(&frame,
+				thread_saved_fp(tsk),
+				thread_saved_pc(tsk));
 	}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = tsk->curr_ret_stack;
-#endif
 
-	skip = !!regs;
 	printk("Call trace:\n");
 	do {
 		/* skip until specified stack frame */
@@ -162,7 +150,6 @@
 
 static int __die(const char *str, int err, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	static int die_counter;
 	int ret;
 
@@ -175,15 +162,9 @@
 		return ret;
 
 	print_modules();
-	__show_regs(regs);
-	pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
-		 TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
-		 end_of_stack(tsk));
+	show_regs(regs);
 
-	if (!user_mode(regs)) {
-		dump_backtrace(regs, tsk);
-		dump_instr(KERN_EMERG, regs);
-	}
+	dump_kernel_instr(KERN_EMERG, regs);
 
 	return ret;
 }
@@ -224,24 +205,19 @@
 		do_exit(SIGSEGV);
 }
 
-static bool show_unhandled_signals_ratelimited(void)
+static void arm64_show_signal(int signo, const char *str)
 {
 	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
-	return show_unhandled_signals && __ratelimit(&rs);
-}
-
-void arm64_force_sig_info(struct siginfo *info, const char *str,
-			  struct task_struct *tsk)
-{
+	struct task_struct *tsk = current;
 	unsigned int esr = tsk->thread.fault_code;
 	struct pt_regs *regs = task_pt_regs(tsk);
 
-	if (!unhandled_signal(tsk, info->si_signo))
-		goto send_sig;
-
-	if (!show_unhandled_signals_ratelimited())
-		goto send_sig;
+	/* Leave if the signal won't be shown */
+	if (!show_unhandled_signals ||
+	    !unhandled_signal(tsk, signo) ||
+	    !__ratelimit(&rs))
+		return;
 
 	pr_info("%s[%d]: unhandled exception: ", tsk->comm, task_pid_nr(tsk));
 	if (esr)
@@ -251,19 +227,42 @@
 	print_vma_addr(KERN_CONT " in ", regs->pc);
 	pr_cont("\n");
 	__show_regs(regs);
+}
 
-send_sig:
-	force_sig_info(info->si_signo, info, tsk);
+void arm64_force_sig_fault(int signo, int code, void __user *addr,
+			   const char *str)
+{
+	arm64_show_signal(signo, str);
+	if (signo == SIGKILL)
+		force_sig(SIGKILL);
+	else
+		force_sig_fault(signo, code, addr);
+}
+
+void arm64_force_sig_mceerr(int code, void __user *addr, short lsb,
+			    const char *str)
+{
+	arm64_show_signal(SIGBUS, str);
+	force_sig_mceerr(code, addr, lsb);
+}
+
+void arm64_force_sig_ptrace_errno_trap(int errno, void __user *addr,
+				       const char *str)
+{
+	arm64_show_signal(SIGTRAP, str);
+	force_sig_ptrace_errno_trap(errno, addr);
 }
 
 void arm64_notify_die(const char *str, struct pt_regs *regs,
-		      struct siginfo *info, int err)
+		      int signo, int sicode, void __user *addr,
+		      int err)
 {
 	if (user_mode(regs)) {
 		WARN_ON(regs != current_pt_regs());
 		current->thread.fault_address = 0;
 		current->thread.fault_code = err;
-		arm64_force_sig_info(info, str, current);
+
+		arm64_force_sig_fault(signo, sicode, addr, str);
 	} else {
 		die(str, regs, err);
 	}
@@ -350,11 +349,11 @@
 
 void force_signal_inject(int signal, int code, unsigned long address)
 {
-	siginfo_t info;
 	const char *desc;
 	struct pt_regs *regs = current_pt_regs();
 
-	clear_siginfo(&info);
+	if (WARN_ON(!user_mode(regs)))
+		return;
 
 	switch (signal) {
 	case SIGILL:
@@ -374,12 +373,7 @@
 		signal = SIGKILL;
 	}
 
-	info.si_signo = signal;
-	info.si_errno = 0;
-	info.si_code  = code;
-	info.si_addr  = (void __user *)address;
-
-	arm64_notify_die(desc, regs, &info, 0);
+	arm64_notify_die(desc, regs, signal, code, (void __user *)address, 0);
 }
 
 /*
@@ -408,13 +402,8 @@
 	if (call_undef_hook(regs) == 0)
 		return;
 
-	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
 	BUG_ON(!user_mode(regs));
-}
-
-void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
-{
-	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
 }
 
 #define __user_cache_maint(insn, address, res)			\
@@ -440,7 +429,7 @@
 static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {
 	unsigned long address;
-	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
 	int ret = 0;
 
@@ -453,6 +442,9 @@
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAC:	/* DC CVAC, gets promoted */
 		__user_cache_maint("dc civac", address, ret);
 		break;
+	case ESR_ELx_SYS64_ISS_CRM_DC_CVADP:	/* DC CVADP */
+		__user_cache_maint("sys 3, c7, c13, 1", address, ret);
+		break;
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAP:	/* DC CVAP */
 		__user_cache_maint("sys 3, c7, c12, 1", address, ret);
 		break;
@@ -475,7 +467,7 @@
 
 static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 {
-	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
 	pt_regs_write_reg(regs, rt, val);
@@ -485,27 +477,43 @@
 
 static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 {
-	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 
-	pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+	pt_regs_write_reg(regs, rt, arch_timer_read_counter());
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 {
-	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 
 	pt_regs_write_reg(regs, rt, arch_timer_get_rate());
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
+static void mrs_handler(unsigned int esr, struct pt_regs *regs)
+{
+	u32 sysreg, rt;
+
+	rt = ESR_ELx_SYS64_ISS_RT(esr);
+	sysreg = esr_sys64_to_sysreg(esr);
+
+	if (do_emulate_mrs(regs, sysreg, rt) != 0)
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+}
+
+static void wfi_handler(unsigned int esr, struct pt_regs *regs)
+{
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+}
+
 struct sys64_hook {
 	unsigned int esr_mask;
 	unsigned int esr_val;
 	void (*handler)(unsigned int esr, struct pt_regs *regs);
 };
 
-static struct sys64_hook sys64_hooks[] = {
+static const struct sys64_hook sys64_hooks[] = {
 	{
 		.esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK,
 		.esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL,
@@ -529,12 +537,179 @@
 		.esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ,
 		.handler = cntfrq_read_handler,
 	},
+	{
+		/* Trap read access to CPUID registers */
+		.esr_mask = ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK,
+		.esr_val = ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL,
+		.handler = mrs_handler,
+	},
+	{
+		/* Trap WFI instructions executed in userspace */
+		.esr_mask = ESR_ELx_WFx_MASK,
+		.esr_val = ESR_ELx_WFx_WFI_VAL,
+		.handler = wfi_handler,
+	},
 	{},
 };
 
+
+#ifdef CONFIG_COMPAT
+#define PSTATE_IT_1_0_SHIFT	25
+#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
+#define PSTATE_IT_7_2_SHIFT	10
+#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
+
+static u32 compat_get_it_state(struct pt_regs *regs)
+{
+	u32 it, pstate = regs->pstate;
+
+	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
+	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
+
+	return it;
+}
+
+static void compat_set_it_state(struct pt_regs *regs, u32 it)
+{
+	u32 pstate_it;
+
+	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
+	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
+
+	regs->pstate &= ~PSR_AA32_IT_MASK;
+	regs->pstate |= pstate_it;
+}
+
+static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
+{
+	int cond;
+
+	/* Only a T32 instruction can trap without CV being set */
+	if (!(esr & ESR_ELx_CV)) {
+		u32 it;
+
+		it = compat_get_it_state(regs);
+		if (!it)
+			return true;
+
+		cond = it >> 4;
+	} else {
+		cond = (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
+	}
+
+	return aarch32_opcode_cond_checks[cond](regs->pstate);
+}
+
+static void advance_itstate(struct pt_regs *regs)
+{
+	u32 it;
+
+	/* ARM mode */
+	if (!(regs->pstate & PSR_AA32_T_BIT) ||
+	    !(regs->pstate & PSR_AA32_IT_MASK))
+		return;
+
+	it  = compat_get_it_state(regs);
+
+	/*
+	 * If this is the last instruction of the block, wipe the IT
+	 * state. Otherwise advance it.
+	 */
+	if (!(it & 7))
+		it = 0;
+	else
+		it = (it & 0xe0) | ((it << 1) & 0x1f);
+
+	compat_set_it_state(regs, it);
+}
+
+static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs,
+						   unsigned int sz)
+{
+	advance_itstate(regs);
+	arm64_skip_faulting_instruction(regs, sz);
+}
+
+static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+	int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
+
+	pt_regs_write_reg(regs, reg, arch_timer_get_rate());
+	arm64_compat_skip_faulting_instruction(regs, 4);
+}
+
+static const struct sys64_hook cp15_32_hooks[] = {
+	{
+		.esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK,
+		.esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ,
+		.handler = compat_cntfrq_read_handler,
+	},
+	{},
+};
+
+static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+	int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
+	int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
+	u64 val = arch_timer_read_counter();
+
+	pt_regs_write_reg(regs, rt, lower_32_bits(val));
+	pt_regs_write_reg(regs, rt2, upper_32_bits(val));
+	arm64_compat_skip_faulting_instruction(regs, 4);
+}
+
+static const struct sys64_hook cp15_64_hooks[] = {
+	{
+		.esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK,
+		.esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT,
+		.handler = compat_cntvct_read_handler,
+	},
+	{},
+};
+
+asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
+{
+	const struct sys64_hook *hook, *hook_base;
+
+	if (!cp15_cond_valid(esr, regs)) {
+		/*
+		 * There is no T16 variant of a CP access, so we
+		 * always advance PC by 4 bytes.
+		 */
+		arm64_compat_skip_faulting_instruction(regs, 4);
+		return;
+	}
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_CP15_32:
+		hook_base = cp15_32_hooks;
+		break;
+	case ESR_ELx_EC_CP15_64:
+		hook_base = cp15_64_hooks;
+		break;
+	default:
+		do_undefinstr(regs);
+		return;
+	}
+
+	for (hook = hook_base; hook->handler; hook++)
+		if ((hook->esr_mask & esr) == hook->esr_val) {
+			hook->handler(esr, regs);
+			return;
+		}
+
+	/*
+	 * New cp15 instructions may previously have been undefined at
+	 * EL0. Fall back to our usual undefined instruction handler
+	 * so that we handle these consistently.
+	 */
+	do_undefinstr(regs);
+}
+#endif
+
 asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 {
-	struct sys64_hook *hook;
+	const struct sys64_hook *hook;
 
 	for (hook = sys64_hooks; hook->handler; hook++)
 		if ((hook->esr_mask & esr) == hook->esr_val) {
@@ -560,6 +735,7 @@
 	[ESR_ELx_EC_CP14_LS]		= "CP14 LDC/STC",
 	[ESR_ELx_EC_FP_ASIMD]		= "ASIMD",
 	[ESR_ELx_EC_CP10_ID]		= "CP10 MRC/VMRS",
+	[ESR_ELx_EC_PAC]		= "PAC",
 	[ESR_ELx_EC_CP14_64]		= "CP14 MCRR/MRRC",
 	[ESR_ELx_EC_ILL]		= "PSTATE.IL",
 	[ESR_ELx_EC_SVC32]		= "SVC (AArch32)",
@@ -570,6 +746,7 @@
 	[ESR_ELx_EC_SMC64]		= "SMC (AArch64)",
 	[ESR_ELx_EC_SYS64]		= "MSR/MRS (AArch64)",
 	[ESR_ELx_EC_SVE]		= "SVE",
+	[ESR_ELx_EC_ERET]		= "ERET/ERETAA/ERETAB",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",
@@ -608,7 +785,6 @@
 		handler[reason], smp_processor_id(), esr,
 		esr_get_class_string(esr));
 
-	die("Oops - bad mode", regs, 0);
 	local_daif_mask();
 	panic("bad mode");
 }
@@ -619,19 +795,13 @@
  */
 asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
-	siginfo_t info;
 	void __user *pc = (void __user *)instruction_pointer(regs);
 
-	clear_siginfo(&info);
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code  = ILL_ILLOPC;
-	info.si_addr  = pc;
-
 	current->thread.fault_address = 0;
 	current->thread.fault_code = esr;
 
-	arm64_force_sig_info(&info, "Bad EL0 synchronous exception", current);
+	arm64_force_sig_fault(SIGILL, ILL_ILLOPC, pc,
+			      "Bad EL0 synchronous exception");
 }
 
 #ifdef CONFIG_VMAP_STACK
@@ -704,6 +874,10 @@
 		/*
 		 * The CPU can't make progress. The exception may have
 		 * been imprecise.
+		 *
+		 * Neoverse-N1 #1349291 means a non-KVM SError reported as
+		 * Unrecoverable should be treated as Uncontainable. We
+		 * call arm64_serror_panic() in both cases.
 		 */
 		return true;
 
@@ -716,15 +890,26 @@
 
 asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
 {
-	nmi_enter();
+	const bool was_in_nmi = in_nmi();
+
+	if (!was_in_nmi)
+		nmi_enter();
 
 	/* non-RAS errors are not containable */
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
 		arm64_serror_panic(regs, esr);
 
-	nmi_exit();
+	if (!was_in_nmi)
+		nmi_exit();
 }
 
+asmlinkage void enter_from_user_mode(void)
+{
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+}
+NOKPROBE_SYMBOL(enter_from_user_mode);
+
 void __pte_error(const char *file, int line, unsigned long val)
 {
 	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
@@ -761,9 +946,6 @@
 
 static int bug_handler(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	switch (report_bug(regs->pc, regs)) {
 	case BUG_TRAP_TYPE_BUG:
 		die("Oops - BUG", regs, 0);
@@ -783,11 +965,56 @@
 }
 
 static struct break_hook bug_break_hook = {
-	.esr_val = 0xf2000000 | BUG_BRK_IMM,
-	.esr_mask = 0xffffffff,
 	.fn = bug_handler,
+	.imm = BUG_BRK_IMM,
 };
 
+#ifdef CONFIG_KASAN_SW_TAGS
+
+#define KASAN_ESR_RECOVER	0x20
+#define KASAN_ESR_WRITE	0x10
+#define KASAN_ESR_SIZE_MASK	0x0f
+#define KASAN_ESR_SIZE(esr)	(1 << ((esr) & KASAN_ESR_SIZE_MASK))
+
+static int kasan_handler(struct pt_regs *regs, unsigned int esr)
+{
+	bool recover = esr & KASAN_ESR_RECOVER;
+	bool write = esr & KASAN_ESR_WRITE;
+	size_t size = KASAN_ESR_SIZE(esr);
+	u64 addr = regs->regs[0];
+	u64 pc = regs->pc;
+
+	kasan_report(addr, size, write, pc);
+
+	/*
+	 * The instrumentation allows to control whether we can proceed after
+	 * a crash was detected. This is done by passing the -recover flag to
+	 * the compiler. Disabling recovery allows to generate more compact
+	 * code.
+	 *
+	 * Unfortunately disabling recovery doesn't work for the kernel right
+	 * now. KASAN reporting is disabled in some contexts (for example when
+	 * the allocator accesses slab object metadata; this is controlled by
+	 * current->kasan_depth). All these accesses are detected by the tool,
+	 * even though the reports for them are not printed.
+	 *
+	 * This is something that might be fixed at some point in the future.
+	 */
+	if (!recover)
+		die("Oops - KASAN", regs, 0);
+
+	/* If thread survives, skip over the brk instruction and continue: */
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+	return DBG_HOOK_HANDLED;
+}
+
+static struct break_hook kasan_break_hook = {
+	.fn	= kasan_handler,
+	.imm	= KASAN_BRK_IMM,
+	.mask	= KASAN_BRK_MASK,
+};
+#endif
+
 /*
  * Initial handler for AArch64 BRK exceptions
  * This handler only used until debug_traps_init().
@@ -795,11 +1022,20 @@
 int __init early_brk64(unsigned long addr, unsigned int esr,
 		struct pt_regs *regs)
 {
+#ifdef CONFIG_KASAN_SW_TAGS
+	unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+	if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
+		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
+#endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
 }
 
 /* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
-	register_break_hook(&bug_break_hook);
+	register_kernel_break_hook(&bug_break_hook);
+#ifdef CONFIG_KASAN_SW_TAGS
+	register_kernel_break_hook(&kasan_break_hook);
+#endif
 }
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 2d41900..354b11e 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * VDSO implementation for AArch64 and vector page setup for AArch32.
+ * VDSO implementations.
  *
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  */
 
@@ -31,90 +20,74 @@
 #include <linux/slab.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
+#include <vdso/vsyscall.h>
 
 #include <asm/cacheflush.h>
 #include <asm/signal32.h>
 #include <asm/vdso.h>
-#include <asm/vdso_datapage.h>
 
 extern char vdso_start[], vdso_end[];
-static unsigned long vdso_pages __ro_after_init;
+#ifdef CONFIG_COMPAT_VDSO
+extern char vdso32_start[], vdso32_end[];
+#endif /* CONFIG_COMPAT_VDSO */
+
+/* vdso_lookup arch_index */
+enum arch_vdso_type {
+	ARM64_VDSO = 0,
+#ifdef CONFIG_COMPAT_VDSO
+	ARM64_VDSO32 = 1,
+#endif /* CONFIG_COMPAT_VDSO */
+};
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_TYPES		(ARM64_VDSO32 + 1)
+#else
+#define VDSO_TYPES		(ARM64_VDSO + 1)
+#endif /* CONFIG_COMPAT_VDSO */
+
+struct __vdso_abi {
+	const char *name;
+	const char *vdso_code_start;
+	const char *vdso_code_end;
+	unsigned long vdso_pages;
+	/* Data Mapping */
+	struct vm_special_mapping *dm;
+	/* Code Mapping */
+	struct vm_special_mapping *cm;
+};
+
+static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
+	{
+		.name = "vdso",
+		.vdso_code_start = vdso_start,
+		.vdso_code_end = vdso_end,
+	},
+#ifdef CONFIG_COMPAT_VDSO
+	{
+		.name = "vdso32",
+		.vdso_code_start = vdso32_start,
+		.vdso_code_end = vdso32_end,
+	},
+#endif /* CONFIG_COMPAT_VDSO */
+};
 
 /*
  * The vDSO data page.
  */
 static union {
-	struct vdso_data	data;
+	struct vdso_data	data[CS_BASES];
 	u8			page[PAGE_SIZE];
 } vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = vdso_data_store.data;
 
-#ifdef CONFIG_COMPAT
-/*
- * Create and map the vectors page for AArch32 tasks.
- */
-static struct page *vectors_page[1] __ro_after_init;
-
-static int __init alloc_vectors_page(void)
-{
-	extern char __kuser_helper_start[], __kuser_helper_end[];
-	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
-
-	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
-	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
-	unsigned long vpage;
-
-	vpage = get_zeroed_page(GFP_ATOMIC);
-
-	if (!vpage)
-		return -ENOMEM;
-
-	/* kuser helpers */
-	memcpy((void *)vpage + 0x1000 - kuser_sz, __kuser_helper_start,
-		kuser_sz);
-
-	/* sigreturn code */
-	memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
-               __aarch32_sigret_code_start, sigret_sz);
-
-	flush_icache_range(vpage, vpage + PAGE_SIZE);
-	vectors_page[0] = virt_to_page(vpage);
-
-	return 0;
-}
-arch_initcall(alloc_vectors_page);
-
-int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr = AARCH32_VECTORS_BASE;
-	static const struct vm_special_mapping spec = {
-		.name	= "[vectors]",
-		.pages	= vectors_page,
-
-	};
-	void *ret;
-
-	if (down_write_killable(&mm->mmap_sem))
-		return -EINTR;
-	current->mm->context.vdso = (void *)addr;
-
-	/* Map vectors page at the high address. */
-	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
-				       VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
-				       &spec);
-
-	up_write(&mm->mmap_sem);
-
-	return PTR_ERR_OR_ZERO(ret);
-}
-#endif /* CONFIG_COMPAT */
-
-static int vdso_mremap(const struct vm_special_mapping *sm,
-		struct vm_area_struct *new_vma)
+static int __vdso_remap(enum arch_vdso_type arch_index,
+			const struct vm_special_mapping *sm,
+			struct vm_area_struct *new_vma)
 {
 	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
-	unsigned long vdso_size = vdso_end - vdso_start;
+	unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end -
+				  vdso_lookup[arch_index].vdso_code_start;
 
 	if (vdso_size != new_size)
 		return -EINVAL;
@@ -124,7 +97,303 @@
 	return 0;
 }
 
-static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
+static int __vdso_init(enum arch_vdso_type arch_index)
+{
+	int i;
+	struct page **vdso_pagelist;
+	unsigned long pfn;
+
+	if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) {
+		pr_err("vDSO is not a valid ELF object!\n");
+		return -EINVAL;
+	}
+
+	vdso_lookup[arch_index].vdso_pages = (
+			vdso_lookup[arch_index].vdso_code_end -
+			vdso_lookup[arch_index].vdso_code_start) >>
+			PAGE_SHIFT;
+
+	/* Allocate the vDSO pagelist, plus a page for the data. */
+	vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1,
+				sizeof(struct page *),
+				GFP_KERNEL);
+	if (vdso_pagelist == NULL)
+		return -ENOMEM;
+
+	/* Grab the vDSO data page. */
+	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
+
+
+	/* Grab the vDSO code pages. */
+	pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start);
+
+	for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++)
+		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+
+	vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0];
+	vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1];
+
+	return 0;
+}
+
+static int __setup_additional_pages(enum arch_vdso_type arch_index,
+				    struct mm_struct *mm,
+				    struct linux_binprm *bprm,
+				    int uses_interp)
+{
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	void *ret;
+
+	vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT;
+	/* Be sure to map the data page */
+	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+
+	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		ret = ERR_PTR(vdso_base);
+		goto up_fail;
+	}
+
+	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
+				       VM_READ|VM_MAYREAD,
+				       vdso_lookup[arch_index].dm);
+	if (IS_ERR(ret))
+		goto up_fail;
+
+	vdso_base += PAGE_SIZE;
+	mm->context.vdso = (void *)vdso_base;
+	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
+				       VM_READ|VM_EXEC|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       vdso_lookup[arch_index].cm);
+	if (IS_ERR(ret))
+		goto up_fail;
+
+	return 0;
+
+up_fail:
+	mm->context.vdso = NULL;
+	return PTR_ERR(ret);
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * Create and map the vectors page for AArch32 tasks.
+ */
+#ifdef CONFIG_COMPAT_VDSO
+static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
+{
+	return __vdso_remap(ARM64_VDSO32, sm, new_vma);
+}
+#endif /* CONFIG_COMPAT_VDSO */
+
+/*
+ * aarch32_vdso_pages:
+ * 0 - kuser helpers
+ * 1 - sigreturn code
+ * or (CONFIG_COMPAT_VDSO):
+ * 0 - kuser helpers
+ * 1 - vdso data
+ * 2 - vdso code
+ */
+#define C_VECTORS	0
+#ifdef CONFIG_COMPAT_VDSO
+#define C_VVAR		1
+#define C_VDSO		2
+#define C_PAGES		(C_VDSO + 1)
+#else
+#define C_SIGPAGE	1
+#define C_PAGES		(C_SIGPAGE + 1)
+#endif /* CONFIG_COMPAT_VDSO */
+static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
+static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
+	{
+		.name	= "[vectors]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_VECTORS],
+	},
+#ifdef CONFIG_COMPAT_VDSO
+	{
+		.name = "[vvar]",
+	},
+	{
+		.name = "[vdso]",
+		.mremap = aarch32_vdso_mremap,
+	},
+#else
+	{
+		.name	= "[sigpage]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
+	},
+#endif /* CONFIG_COMPAT_VDSO */
+};
+
+static int aarch32_alloc_kuser_vdso_page(void)
+{
+	extern char __kuser_helper_start[], __kuser_helper_end[];
+	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+	unsigned long vdso_page;
+
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
+
+	vdso_page = get_zeroed_page(GFP_ATOMIC);
+	if (!vdso_page)
+		return -ENOMEM;
+
+	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
+	       kuser_sz);
+	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
+	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+	return 0;
+}
+
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+	int ret;
+
+	vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR];
+	vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO];
+
+	ret = __vdso_init(ARM64_VDSO32);
+	if (ret)
+		return ret;
+
+	ret = aarch32_alloc_kuser_vdso_page();
+	if (ret) {
+		unsigned long c_vvar =
+			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]);
+		unsigned long c_vdso =
+			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]);
+
+		free_page(c_vvar);
+		free_page(c_vdso);
+	}
+
+	return ret;
+}
+#else
+static int __aarch32_alloc_vdso_pages(void)
+{
+	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
+	unsigned long sigpage;
+	int ret;
+
+	sigpage = get_zeroed_page(GFP_ATOMIC);
+	if (!sigpage)
+		return -ENOMEM;
+
+	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
+	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
+	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+
+	ret = aarch32_alloc_kuser_vdso_page();
+	if (ret)
+		free_page(sigpage);
+
+	return ret;
+}
+#endif /* CONFIG_COMPAT_VDSO */
+
+static int __init aarch32_alloc_vdso_pages(void)
+{
+	return __aarch32_alloc_vdso_pages();
+}
+arch_initcall(aarch32_alloc_vdso_pages);
+
+static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
+{
+	void *ret;
+
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
+
+	/*
+	 * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's
+	 * not safe to CoW the page containing the CPU exception vectors.
+	 */
+	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
+				       VM_READ | VM_EXEC |
+				       VM_MAYREAD | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_VECTORS]);
+
+	return PTR_ERR_OR_ZERO(ret);
+}
+
+#ifndef CONFIG_COMPAT_VDSO
+static int aarch32_sigreturn_setup(struct mm_struct *mm)
+{
+	unsigned long addr;
+	void *ret;
+
+	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = ERR_PTR(addr);
+		goto out;
+	}
+
+	/*
+	 * VM_MAYWRITE is required to allow gdb to Copy-on-Write and
+	 * set breakpoints.
+	 */
+	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
+				       VM_READ | VM_EXEC | VM_MAYREAD |
+				       VM_MAYWRITE | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_SIGPAGE]);
+	if (IS_ERR(ret))
+		goto out;
+
+	mm->context.vdso = (void *)addr;
+
+out:
+	return PTR_ERR_OR_ZERO(ret);
+}
+#endif /* !CONFIG_COMPAT_VDSO */
+
+int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
+	ret = aarch32_kuser_helpers_setup(mm);
+	if (ret)
+		goto out;
+
+#ifdef CONFIG_COMPAT_VDSO
+	ret = __setup_additional_pages(ARM64_VDSO32,
+				       mm,
+				       bprm,
+				       uses_interp);
+#else
+	ret = aarch32_sigreturn_setup(mm);
+#endif /* CONFIG_COMPAT_VDSO */
+
+out:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+#endif /* CONFIG_COMPAT */
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
+{
+	return __vdso_remap(ARM64_VDSO, sm, new_vma);
+}
+
+/*
+ * aarch64_vdso_pages:
+ * 0 - vvar
+ * 1 - vdso
+ */
+#define A_VVAR		0
+#define A_VDSO		1
+#define A_PAGES		(A_VDSO + 1)
+static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
 	{
 		.name	= "[vvar]",
 	},
@@ -136,39 +405,10 @@
 
 static int __init vdso_init(void)
 {
-	int i;
-	struct page **vdso_pagelist;
-	unsigned long pfn;
+	vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR];
+	vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO];
 
-	if (memcmp(vdso_start, "\177ELF", 4)) {
-		pr_err("vDSO is not a valid ELF object!\n");
-		return -EINVAL;
-	}
-
-	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-	pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
-		vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
-
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
-				GFP_KERNEL);
-	if (vdso_pagelist == NULL)
-		return -ENOMEM;
-
-	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
-	/* Grab the vDSO code pages. */
-	pfn = sym_to_pfn(vdso_start);
-
-	for (i = 0; i < vdso_pages; i++)
-		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
-
-	vdso_spec[0].pages = &vdso_pagelist[0];
-	vdso_spec[1].pages = &vdso_pagelist[1];
-
-	return 0;
+	return __vdso_init(ARM64_VDSO);
 }
 arch_initcall(vdso_init);
 
@@ -176,81 +416,17 @@
 				int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
-	void *ret;
-
-	vdso_text_len = vdso_pages << PAGE_SHIFT;
-	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+	int ret;
 
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
-	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
-	if (IS_ERR_VALUE(vdso_base)) {
-		ret = ERR_PTR(vdso_base);
-		goto up_fail;
-	}
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
-				       &vdso_spec[0]);
-	if (IS_ERR(ret))
-		goto up_fail;
 
-	vdso_base += PAGE_SIZE;
-	mm->context.vdso = (void *)vdso_base;
-	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
-				       VM_READ|VM_EXEC|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &vdso_spec[1]);
-	if (IS_ERR(ret))
-		goto up_fail;
-
+	ret = __setup_additional_pages(ARM64_VDSO,
+				       mm,
+				       bprm,
+				       uses_interp);
 
 	up_write(&mm->mmap_sem);
-	return 0;
 
-up_fail:
-	mm->context.vdso = NULL;
-	up_write(&mm->mmap_sem);
-	return PTR_ERR(ret);
-}
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-void update_vsyscall(struct timekeeper *tk)
-{
-	u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
-
-	++vdso_data->tb_seq_count;
-	smp_wmb();
-
-	vdso_data->use_syscall			= use_syscall;
-	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
-	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
-							tk->tkr_mono.shift;
-	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
-
-	if (!use_syscall) {
-		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
-		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
-		vdso_data->raw_time_sec         = tk->raw_sec;
-		vdso_data->raw_time_nsec        = tk->tkr_raw.xtime_nsec;
-		vdso_data->xtime_clock_sec	= tk->xtime_sec;
-		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
-		vdso_data->cs_mono_mult		= tk->tkr_mono.mult;
-		vdso_data->cs_raw_mult		= tk->tkr_raw.mult;
-		/* tkr_mono.shift == tkr_raw.shift */
-		vdso_data->cs_shift		= tk->tkr_mono.shift;
-	}
-
-	smp_wmb();
-	++vdso_data->tb_seq_count;
-}
-
-void update_vsyscall_tz(void)
-{
-	vdso_data->tz_minuteswest	= sys_tz.tz_minuteswest;
-	vdso_data->tz_dsttime		= sys_tz.tz_dsttime;
+	return ret;
 }
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index b215c71..dd2514b 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -6,23 +6,48 @@
 # Heavily based on the vDSO Makefiles for other archs.
 #
 
-obj-vdso := gettimeofday.o note.o sigreturn.o
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_AARCH64_JUMP_SLOT|R_AARCH64_GLOB_DAT|R_AARCH64_ABS64
+include $(srctree)/lib/vdso/Makefile
+
+obj-vdso := vgettimeofday.o note.o sigreturn.o
 
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
-ccflags-y := -shared -fno-common -fno-builtin
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
-		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
+		--build-id -n -T
+
+ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+
+VDSO_LDFLAGS := -Bsymbolic
+
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+KBUILD_CFLAGS			+= $(DISABLE_LTO)
+KASAN_SANITIZE			:= n
+UBSAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
+KCOV_INSTRUMENT			:= n
+
+CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny
+
+ifneq ($(c-gettimeofday-y),)
+  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+endif
+
+# Clang versions less than 8 do not support -mcmodel=tiny
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+  ifeq ($(shell test $(CONFIG_CLANG_VERSION) -lt 80000; echo $$?),0)
+    CFLAGS_REMOVE_vgettimeofday.o += -mcmodel=tiny
+  endif
+endif
 
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
-# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
-# down to collect2, resulting in silent corruption of the vDSO image.
-ccflags-y += -Wl,-shared
-
 obj-y += vdso.o
 extra-y += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
@@ -31,8 +56,8 @@
 $(obj)/vdso.o : $(obj)/vdso.so
 
 # Link rule for the .so file, .lds has to be first
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
-	$(call if_changed,vdsold)
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,vdsold_and_vdso_check)
 
 # Strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -42,22 +67,14 @@
 # Generate VDSO offsets using helper script
 gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
 quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
-	$(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
-endef
+      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
 
 include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
-# Assembly rules for the .S files
-$(obj-vdso): %.o: %.S FORCE
-	$(call if_changed_dep,vdsoas)
-
 # Actual build commands
-quiet_cmd_vdsold = VDSOL   $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
-quiet_cmd_vdsoas = VDSOA   $@
-      cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
+quiet_cmd_vdsold_and_vdso_check = LD      $@
+      cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check)
 
 # Install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
deleted file mode 100644
index c39872a..0000000
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ /dev/null
@@ -1,328 +0,0 @@
-/*
- * Userspace implementations of gettimeofday() and friends.
- *
- * Copyright (C) 2012 ARM Limited
- *
- * 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/>.
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-
-#define NSEC_PER_SEC_LO16	0xca00
-#define NSEC_PER_SEC_HI16	0x3b9a
-
-vdso_data	.req	x6
-seqcnt		.req	w7
-w_tmp		.req	w8
-x_tmp		.req	x8
-
-/*
- * Conventions for macro arguments:
- * - An argument is write-only if its name starts with "res".
- * - All other arguments are read-only, unless otherwise specified.
- */
-
-	.macro	seqcnt_acquire
-9999:	ldr	seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT]
-	tbnz	seqcnt, #0, 9999b
-	dmb	ishld
-	.endm
-
-	.macro	seqcnt_check fail
-	dmb	ishld
-	ldr	w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT]
-	cmp	w_tmp, seqcnt
-	b.ne	\fail
-	.endm
-
-	.macro	syscall_check fail
-	ldr	w_tmp, [vdso_data, #VDSO_USE_SYSCALL]
-	cbnz	w_tmp, \fail
-	.endm
-
-	.macro get_nsec_per_sec res
-	mov	\res, #NSEC_PER_SEC_LO16
-	movk	\res, #NSEC_PER_SEC_HI16, lsl #16
-	.endm
-
-	/*
-	 * Returns the clock delta, in nanoseconds left-shifted by the clock
-	 * shift.
-	 */
-	.macro	get_clock_shifted_nsec res, cycle_last, mult
-	/* Read the virtual counter. */
-	isb
-	mrs	x_tmp, cntvct_el0
-	/* Calculate cycle delta and convert to ns. */
-	sub	\res, x_tmp, \cycle_last
-	/* We can only guarantee 56 bits of precision. */
-	movn	x_tmp, #0xff00, lsl #48
-	and	\res, x_tmp, \res
-	mul	\res, \res, \mult
-	.endm
-
-	/*
-	 * Returns in res_{sec,nsec} the REALTIME timespec, based on the
-	 * "wall time" (xtime) and the clock_mono delta.
-	 */
-	.macro	get_ts_realtime res_sec, res_nsec, \
-			clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec
-	add	\res_nsec, \clock_nsec, \xtime_nsec
-	udiv	x_tmp, \res_nsec, \nsec_to_sec
-	add	\res_sec, \xtime_sec, x_tmp
-	msub	\res_nsec, x_tmp, \nsec_to_sec, \res_nsec
-	.endm
-
-	/*
-	 * Returns in res_{sec,nsec} the timespec based on the clock_raw delta,
-	 * used for CLOCK_MONOTONIC_RAW.
-	 */
-	.macro	get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec
-	udiv	\res_sec, \clock_nsec, \nsec_to_sec
-	msub	\res_nsec, \res_sec, \nsec_to_sec, \clock_nsec
-	.endm
-
-	/* sec and nsec are modified in place. */
-	.macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec
-	/* Add timespec. */
-	add	\sec, \sec, \ts_sec
-	add	\nsec, \nsec, \ts_nsec
-
-	/* Normalise the new timespec. */
-	cmp	\nsec, \nsec_to_sec
-	b.lt	9999f
-	sub	\nsec, \nsec, \nsec_to_sec
-	add	\sec, \sec, #1
-9999:
-	cmp	\nsec, #0
-	b.ge	9998f
-	add	\nsec, \nsec, \nsec_to_sec
-	sub	\sec, \sec, #1
-9998:
-	.endm
-
-	.macro clock_gettime_return, shift=0
-	.if \shift == 1
-	lsr	x11, x11, x12
-	.endif
-	stp	x10, x11, [x1, #TSPEC_TV_SEC]
-	mov	x0, xzr
-	ret
-	.endm
-
-	.macro jump_slot jumptable, index, label
-	.if (. - \jumptable) != 4 * (\index)
-	.error "Jump slot index mismatch"
-	.endif
-	b	\label
-	.endm
-
-	.text
-
-/* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */
-ENTRY(__kernel_gettimeofday)
-	.cfi_startproc
-	adr	vdso_data, _vdso_data
-	/* If tv is NULL, skip to the timezone code. */
-	cbz	x0, 2f
-
-	/* Compute the time of day. */
-1:	seqcnt_acquire
-	syscall_check fail=4f
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_mono_mult, w12 = cs_shift */
-	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
-	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=1b
-
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	get_ts_realtime res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-
-	/* Convert ns to us. */
-	mov	x13, #1000
-	lsl	x13, x13, x12
-	udiv	x11, x11, x13
-	stp	x10, x11, [x0, #TVAL_TV_SEC]
-2:
-	/* If tz is NULL, return 0. */
-	cbz	x1, 3f
-	ldp	w4, w5, [vdso_data, #VDSO_TZ_MINWEST]
-	stp	w4, w5, [x1, #TZ_MINWEST]
-3:
-	mov	x0, xzr
-	ret
-4:
-	/* Syscall fallback. */
-	mov	x8, #__NR_gettimeofday
-	svc	#0
-	ret
-	.cfi_endproc
-ENDPROC(__kernel_gettimeofday)
-
-#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE
-
-/* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */
-ENTRY(__kernel_clock_gettime)
-	.cfi_startproc
-	cmp	w0, #JUMPSLOT_MAX
-	b.hi	syscall
-	adr	vdso_data, _vdso_data
-	adr	x_tmp, jumptable
-	add	x_tmp, x_tmp, w0, uxtw #2
-	br	x_tmp
-
-	ALIGN
-jumptable:
-	jump_slot jumptable, CLOCK_REALTIME, realtime
-	jump_slot jumptable, CLOCK_MONOTONIC, monotonic
-	b	syscall
-	b	syscall
-	jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw
-	jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse
-	jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse
-
-	.if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1)
-	.error	"Wrong jumptable size"
-	.endif
-
-	ALIGN
-realtime:
-	seqcnt_acquire
-	syscall_check fail=syscall
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_mono_mult, w12 = cs_shift */
-	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
-	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=realtime
-
-	/* All computations are done with left-shifted nsecs. */
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	get_ts_realtime res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-	clock_gettime_return, shift=1
-
-	ALIGN
-monotonic:
-	seqcnt_acquire
-	syscall_check fail=syscall
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_mono_mult, w12 = cs_shift */
-	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
-	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	ldp	x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic
-
-	/* All computations are done with left-shifted nsecs. */
-	lsl	x4, x4, x12
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	get_ts_realtime res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-
-	add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9
-	clock_gettime_return, shift=1
-
-	ALIGN
-monotonic_raw:
-	seqcnt_acquire
-	syscall_check fail=syscall
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_raw_mult, w12 = cs_shift */
-	ldp	w12, w11, [vdso_data, #VDSO_CS_SHIFT]
-	ldp	x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-	seqcnt_check fail=monotonic_raw
-
-	/* All computations are done with left-shifted nsecs. */
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	get_ts_clock_raw res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, nsec_to_sec=x9
-
-	add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
-	clock_gettime_return, shift=1
-
-	ALIGN
-realtime_coarse:
-	seqcnt_acquire
-	ldp	x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
-	seqcnt_check fail=realtime_coarse
-	clock_gettime_return
-
-	ALIGN
-monotonic_coarse:
-	seqcnt_acquire
-	ldp	x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
-	ldp	x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic_coarse
-
-	/* Computations are done in (non-shifted) nsecs. */
-	get_nsec_per_sec res=x9
-	add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
-	clock_gettime_return
-
-	ALIGN
-syscall: /* Syscall fallback. */
-	mov	x8, #__NR_clock_gettime
-	svc	#0
-	ret
-	.cfi_endproc
-ENDPROC(__kernel_clock_gettime)
-
-/* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */
-ENTRY(__kernel_clock_getres)
-	.cfi_startproc
-	cmp	w0, #CLOCK_REALTIME
-	ccmp	w0, #CLOCK_MONOTONIC, #0x4, ne
-	ccmp	w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
-	b.ne	1f
-
-	ldr	x2, 5f
-	b	2f
-1:
-	cmp	w0, #CLOCK_REALTIME_COARSE
-	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
-	b.ne	4f
-	ldr	x2, 6f
-2:
-	cbz	x1, 3f
-	stp	xzr, x2, [x1]
-
-3:	/* res == NULL. */
-	mov	w0, wzr
-	ret
-
-4:	/* Syscall fallback. */
-	mov	x8, #__NR_clock_getres
-	svc	#0
-	ret
-5:
-	.quad	CLOCK_REALTIME_RES
-6:
-	.quad	CLOCK_COARSE_RES
-	.cfi_endproc
-ENDPROC(__kernel_clock_getres)
diff --git a/arch/arm64/kernel/vdso/note.S b/arch/arm64/kernel/vdso/note.S
index e20483b..0ce6ec7 100644
--- a/arch/arm64/kernel/vdso/note.S
+++ b/arch/arm64/kernel/vdso/note.S
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  *
  * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 20d98ef..0723aa3 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -1,21 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Sigreturn trampoline for returning from a signal when the SA_RESTORER
  * flag is not set.
  *
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  */
 
diff --git a/arch/arm64/kernel/vdso/vdso.S b/arch/arm64/kernel/vdso/vdso.S
index 82379a7..d1414fe 100644
--- a/arch/arm64/kernel/vdso/vdso.S
+++ b/arch/arm64/kernel/vdso/vdso.S
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  */
 
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index beca249..7ad2d3a 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * GNU linker script for the VDSO library.
 *
  * Copyright (C) 2012 ARM Limited
  *
- * 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/>.
- *
  * Author: Will Deacon <will.deacon@arm.com>
  * Heavily based on the vDSO linker scripts for other archs.
  */
diff --git a/arch/arm64/kernel/vdso/vgettimeofday.c b/arch/arm64/kernel/vdso/vgettimeofday.c
new file mode 100644
index 0000000..7476355
--- /dev/null
+++ b/arch/arm64/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 userspace implementations of gettimeofday() and similar.
+ *
+ * Copyright (C) 2018 ARM Limited
+ *
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __kernel_clock_gettime(clockid_t clock,
+			   struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __kernel_gettimeofday(struct __kernel_old_timeval *tv,
+			  struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __kernel_clock_getres(clockid_t clock_id,
+			  struct __kernel_timespec *res)
+{
+	return __cvdso_clock_getres(clock_id, res);
+}
diff --git a/arch/arm64/kernel/vdso32/.gitignore b/arch/arm64/kernel/vdso32/.gitignore
new file mode 100644
index 0000000..4fea950
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/.gitignore
@@ -0,0 +1,2 @@
+vdso.lds
+vdso.so.raw
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
new file mode 100644
index 0000000..76b327f
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -0,0 +1,200 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for vdso32
+#
+
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32
+include $(srctree)/lib/vdso/Makefile
+
+# Same as cc-*option, but using CC_COMPAT instead of CC
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+CC_COMPAT ?= $(CC)
+else
+CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc
+endif
+
+cc32-option = $(call try-run,\
+        $(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+cc32-disable-warning = $(call try-run,\
+	$(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+cc32-ldoption = $(call try-run,\
+        $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
+cc32-as-instr = $(call try-run,\
+	printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
+
+# We cannot use the global flags to compile the vDSO files, the main reason
+# being that the 32-bit compiler may be older than the main (64-bit) compiler
+# and therefore may not understand flags set using $(cc-option ...). Besides,
+# arch-specific options should be taken from the arm Makefile instead of the
+# arm64 one.
+# As a result we set our own flags here.
+
+# KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile
+VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include)
+VDSO_CPPFLAGS += $(LINUXINCLUDE)
+
+# Common C and assembly flags
+# From top-level Makefile
+VDSO_CAFLAGS := $(VDSO_CPPFLAGS)
+ifneq ($(shell $(CC_COMPAT) --version 2>&1 | head -n 1 | grep clang),)
+VDSO_CAFLAGS += --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+endif
+
+VDSO_CAFLAGS += $(call cc32-option,-fno-PIE)
+ifdef CONFIG_DEBUG_INFO
+VDSO_CAFLAGS += -g
+endif
+
+# From arm Makefile
+VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm)
+VDSO_CAFLAGS += -mabi=aapcs-linux -mfloat-abi=soft
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+VDSO_CAFLAGS += -mbig-endian
+else
+VDSO_CAFLAGS += -mlittle-endian
+endif
+
+# From arm vDSO Makefile
+VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector
+VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING
+
+
+# Try to compile for ARMv8. If the compiler is too old and doesn't support it,
+# fall back to v7. There is no easy way to check for what architecture the code
+# is being compiled, so define a macro specifying that (see arch/arm/Makefile).
+VDSO_CAFLAGS += $(call cc32-option,-march=armv8-a -D__LINUX_ARM_ARCH__=8,\
+                                   -march=armv7-a -D__LINUX_ARM_ARCH__=7)
+
+VDSO_CFLAGS := $(VDSO_CAFLAGS)
+VDSO_CFLAGS += -DENABLE_COMPAT_VDSO=1
+# KBUILD_CFLAGS from top-level Makefile
+VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
+               -fno-strict-aliasing -fno-common \
+               -Werror-implicit-function-declaration \
+               -Wno-format-security \
+               -std=gnu89
+VDSO_CFLAGS  += -O2
+# Some useful compiler-dependent flags from top-level Makefile
+VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,)
+VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign)
+VDSO_CFLAGS += $(call cc32-option,-fno-strict-overflow)
+VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes)
+VDSO_CFLAGS += $(call cc32-option,-Werror=date-time)
+VDSO_CFLAGS += $(call cc32-option,-Werror=incompatible-pointer-types)
+
+# The 32-bit compiler does not provide 128-bit integers, which are used in
+# some headers that are indirectly included from the vDSO code.
+# This hack makes the compiler happy and should trigger a warning/error if
+# variables of such type are referenced.
+VDSO_CFLAGS += -D__uint128_t='void*'
+# Silence some warnings coming from headers that operate on long's
+# (on GCC 4.8 or older, there is unfortunately no way to silence this warning)
+VDSO_CFLAGS += $(call cc32-disable-warning,shift-count-overflow)
+VDSO_CFLAGS += -Wno-int-to-pointer-cast
+
+VDSO_AFLAGS := $(VDSO_CAFLAGS)
+VDSO_AFLAGS += -D__ASSEMBLY__
+
+# Check for binutils support for dmb ishld
+dmbinstr := $(call cc32-as-instr,dmb ishld,-DCONFIG_AS_DMB_ISHLD=1)
+
+VDSO_CFLAGS += $(dmbinstr)
+VDSO_AFLAGS += $(dmbinstr)
+
+VDSO_LDFLAGS := $(VDSO_CPPFLAGS)
+# From arm vDSO Makefile
+VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
+VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS += -nostdlib -shared -mfloat-abi=soft
+VDSO_LDFLAGS += -Wl,--hash-style=sysv
+VDSO_LDFLAGS += -Wl,--build-id
+VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd)
+
+
+# Borrow vdsomunge.c from the arm vDSO
+# We have to use a relative path because scripts/Makefile.host prefixes
+# $(hostprogs-y) with $(obj)
+munge := ../../../arm/vdso/vdsomunge
+hostprogs-y := $(munge)
+
+c-obj-vdso := note.o
+c-obj-vdso-gettimeofday := vgettimeofday.o
+asm-obj-vdso := sigreturn.o
+
+ifneq ($(c-gettimeofday-y),)
+VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y)
+endif
+
+VDSO_CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
+# Build rules
+targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso.so.dbg vdso.so.raw
+c-obj-vdso := $(addprefix $(obj)/, $(c-obj-vdso))
+c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday))
+asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso))
+obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
+
+obj-y += vdso.o
+extra-y += vdso.lds
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# Force dependency (vdso.s includes vdso.so through incbin)
+$(obj)/vdso.o: $(obj)/vdso.so
+
+include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE
+	$(call if_changed,vdsosym)
+
+# Strip rule for vdso.so
+$(obj)/vdso.so: OBJCOPYFLAGS := -S
+$(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE
+	$(call if_changed,vdsomunge)
+
+# Link rule for the .so file, .lds has to be first
+$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,vdsold_and_vdso_check)
+
+# Compilation rules for the vDSO sources
+$(c-obj-vdso): %.o: %.c FORCE
+	$(call if_changed_dep,vdsocc)
+$(c-obj-vdso-gettimeofday): %.o: %.c FORCE
+	$(call if_changed_dep,vdsocc_gettimeofday)
+$(asm-obj-vdso): %.o: %.S FORCE
+	$(call if_changed_dep,vdsoas)
+
+# Actual build commands
+quiet_cmd_vdsold_and_vdso_check = LD32    $@
+      cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
+
+quiet_cmd_vdsold = LD32    $@
+      cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
+                   -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
+quiet_cmd_vdsocc = CC32    $@
+      cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
+quiet_cmd_vdsocc_gettimeofday = CC32    $@
+      cmd_vdsocc_gettimeofday = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
+quiet_cmd_vdsoas = AS32    $@
+      cmd_vdsoas = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
+
+quiet_cmd_vdsomunge = MUNGE   $@
+      cmd_vdsomunge = $(obj)/$(munge) $< $@
+
+# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO)
+gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh
+quiet_cmd_vdsosym = VDSOSYM $@
+# The AArch64 nm should be able to read an AArch32 binary
+      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
+
+# Install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so
+
+vdso.so: $(obj)/vdso.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/arm64/kernel/vdso32/note.c b/arch/arm64/kernel/vdso32/note.c
new file mode 100644
index 0000000..eff5bf9
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/note.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012-2018 ARM Limited
+ *
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+#include <linux/build-salt.h>
+
+ELFNOTE32("Linux", 0, LINUX_VERSION_CODE);
+BUILD_SALT;
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
new file mode 100644
index 0000000..1a81277
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/sigreturn.S
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file provides both A32 and T32 versions, in accordance with the
+ * arm sigreturn code.
+ *
+ * Copyright (C) 2018 ARM Limited
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+#define ARM_ENTRY(name)		\
+	ENTRY(name)
+
+#define ARM_ENDPROC(name)	\
+	.type name, %function;	\
+	END(name)
+
+	.text
+
+	.arm
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_sigreturn_arm)
+	mov r7, #__NR_compat_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_sigreturn_arm)
+
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_rt_sigreturn_arm)
+	mov r7, #__NR_compat_rt_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_rt_sigreturn_arm)
+
+	.thumb
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_sigreturn_thumb)
+	mov r7, #__NR_compat_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_sigreturn_thumb)
+
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_rt_sigreturn_thumb)
+	mov r7, #__NR_compat_rt_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kernel/vdso32/vdso.S b/arch/arm64/kernel/vdso32/vdso.S
new file mode 100644
index 0000000..e72ac7b
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/vdso.S
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/const.h>
+#include <asm/page.h>
+
+	.globl vdso32_start, vdso32_end
+	.section .rodata
+	.balign PAGE_SIZE
+vdso32_start:
+	.incbin "arch/arm64/kernel/vdso32/vdso.so"
+	.balign PAGE_SIZE
+vdso32_end:
+
+	.previous
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
new file mode 100644
index 0000000..a394492
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Adapted from arm64 version.
+ *
+ * GNU linker script for the VDSO library.
+ * Heavily based on the vDSO linker scripts for other archs.
+ *
+ * Copyright (C) 2012-2018 ARM Limited
+ */
+
+#include <linux/const.h>
+#include <asm/page.h>
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
+OUTPUT_ARCH(arm)
+
+SECTIONS
+{
+	PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE);
+	. = VDSO_LBASE + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.rodata		: { *(.rodata*) }		:text
+
+	.text		: { *(.text*) }			:text	=0xe7f001f2
+
+	.got		: { *(.got) }
+	.rel.plt	: { *(.rel.plt) }
+
+	/DISCARD/	: {
+		*(.note.GNU-stack)
+		*(.data .data.* .gnu.linkonce.d.* .sdata*)
+		*(.bss .sbss .dynbss .dynsbss)
+	}
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+}
+
+VERSION
+{
+	LINUX_2.6 {
+	global:
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_clock_getres;
+		__kernel_sigreturn_arm;
+		__kernel_sigreturn_thumb;
+		__kernel_rt_sigreturn_arm;
+		__kernel_rt_sigreturn_thumb;
+		__vdso_clock_gettime64;
+	local: *;
+	};
+}
+
+/*
+ * Make the sigreturn code visible to the kernel.
+ */
+VDSO_compat_sigreturn_arm	= __kernel_sigreturn_arm;
+VDSO_compat_sigreturn_thumb	= __kernel_sigreturn_thumb;
+VDSO_compat_rt_sigreturn_arm	= __kernel_rt_sigreturn_arm;
+VDSO_compat_rt_sigreturn_thumb	= __kernel_rt_sigreturn_thumb;
diff --git a/arch/arm64/kernel/vdso32/vgettimeofday.c b/arch/arm64/kernel/vdso32/vgettimeofday.c
new file mode 100644
index 0000000..54fc1c2
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/vgettimeofday.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 compat userspace implementations of gettimeofday() and similar.
+ *
+ * Copyright (C) 2018 ARM Limited
+ *
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __vdso_clock_gettime(clockid_t clock,
+			 struct old_timespec32 *ts)
+{
+	/* The checks below are required for ABI consistency with arm */
+	if ((u32)ts >= TASK_SIZE_32)
+		return -EFAULT;
+
+	return __cvdso_clock_gettime32(clock, ts);
+}
+
+int __vdso_clock_gettime64(clockid_t clock,
+			   struct __kernel_timespec *ts)
+{
+	/* The checks below are required for ABI consistency with arm */
+	if ((u32)ts >= TASK_SIZE_32)
+		return -EFAULT;
+
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
+			struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __vdso_clock_getres(clockid_t clock_id,
+			struct old_timespec32 *res)
+{
+	/* The checks below are required for ABI consistency with arm */
+	if ((u32)res >= TASK_SIZE_32)
+		return -EFAULT;
+
+	return __cvdso_clock_getres_time32(clock_id, res);
+}
+
+/* Avoid unresolved references emitted by GCC */
+
+void __aeabi_unwind_cpp_pr0(void)
+{
+}
+
+void __aeabi_unwind_cpp_pr1(void)
+{
+}
+
+void __aeabi_unwind_cpp_pr2(void)
+{
+}
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 605d1b6..aa76f72 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -99,7 +99,8 @@
 		*(.discard)
 		*(.discard.*)
 		*(.interp .dynamic)
-		*(.dynsym .dynstr .hash)
+		*(.dynsym .dynstr .hash .gnu.hash)
+		*(.eh_frame)
 	}
 
 	. = KIMAGE_VADDR + TEXT_OFFSET;
@@ -138,6 +139,23 @@
 	EXCEPTION_TABLE(8)		/* __init_begin will be marked RO NX */
 	NOTES
 
+	. = ALIGN(PAGE_SIZE);
+	idmap_pg_dir = .;
+	. += IDMAP_DIR_SIZE;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	tramp_pg_dir = .;
+	. += PAGE_SIZE;
+#endif
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	reserved_ttbr0 = .;
+	. += RESERVED_TTBR0_SIZE;
+#endif
+	swapper_pg_dir = .;
+	. += PAGE_SIZE;
+	swapper_pg_end = .;
+
 	. = ALIGN(SEGMENT_ALIGN);
 	__init_begin = .;
 	__inittext_begin = .;
@@ -166,7 +184,6 @@
 		INIT_SETUP(16)
 		INIT_CALLS
 		CON_INITCALL
-		SECURITY_INITCALL
 		INIT_RAM_FS
 		*(.init.rodata.* .init.bss)	/* from the EFI stub */
 	}
@@ -176,12 +193,21 @@
 
 	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);
+
+#ifdef CONFIG_RELR
+	.relr.dyn : ALIGN(8) {
+		*(.relr.dyn)
+	}
+
+	__relr_offset	= ABSOLUTE(ADDR(.relr.dyn) - KIMAGE_VADDR);
+	__relr_size	= SIZEOF(.relr.dyn);
+#endif
 
 	. = ALIGN(SEGMENT_ALIGN);
 	__initdata_end = .;
@@ -216,21 +242,9 @@
 	BSS_SECTION(0, 0, 0)
 
 	. = ALIGN(PAGE_SIZE);
-	idmap_pg_dir = .;
-	. += IDMAP_DIR_SIZE;
-
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	tramp_pg_dir = .;
-	. += PAGE_SIZE;
-#endif
-
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-	reserved_ttbr0 = .;
-	. += RESERVED_TTBR0_SIZE;
-#endif
-	swapper_pg_dir = .;
-	. += SWAPPER_DIR_SIZE;
-	swapper_pg_end = .;
+	init_pg_dir = .;
+	. += INIT_DIR_SIZE;
+	init_pg_end = .;
 
 	__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
 	_end = .;
@@ -240,6 +254,8 @@
 	HEAD_SYMBOLS
 }
 
+#include "image-vars.h"
+
 /*
  * The HYP init code and ID map text can't be longer than a page each,
  * and should not cross a page boundary.