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

Pull arm64 updates from Will Deacon:

 - RAS reporting via GHES/APEI (ACPI)

 - Indirect ftrace trampolines for modules

 - Improvements to kernel fault reporting

 - Page poisoning

 - Sigframe cleanups and preparation for SVE context

 - Core dump fixes

 - Sparse fixes (mainly relating to endianness)

 - xgene SoC PMU v3 driver

 - Misc cleanups and non-critical fixes

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (75 commits)
  arm64: fix endianness annotation for 'struct jit_ctx' and friends
  arm64: cpuinfo: constify attribute_group structures.
  arm64: ptrace: Fix incorrect get_user() use in compat_vfp_set()
  arm64: ptrace: Remove redundant overrun check from compat_vfp_set()
  arm64: ptrace: Avoid setting compat FP[SC]R to garbage if get_user fails
  arm64: fix endianness annotation for __apply_alternatives()/get_alt_insn()
  arm64: fix endianness annotation in get_kaslr_seed()
  arm64: add missing conversion to __wsum in ip_fast_csum()
  arm64: fix endianness annotation in acpi_parking_protocol.c
  arm64: use readq() instead of readl() to read 64bit entry_point
  arm64: fix endianness annotation for reloc_insn_movw() & reloc_insn_imm()
  arm64: fix endianness annotation for aarch64_insn_write()
  arm64: fix endianness annotation in aarch64_insn_read()
  arm64: fix endianness annotation in call_undef_hook()
  arm64: fix endianness annotation for debug-monitors.c
  ras: mark stub functions as 'inline'
  arm64: pass endianness info to sparse
  arm64: ftrace: fix !CONFIG_ARM64_MODULE_PLTS kernels
  arm64: signal: Allow expansion of the signal frame
  acpi: apei: check for pending errors when probing GHES entries
  ...

41 files changed, 896 insertions, 206 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 300146dc8433..9f7a934ff707 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -3,6 +3,7 @@ config ARM64
 	select ACPI_CCA_REQUIRED if ACPI
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_GTDT if ACPI
+	select ACPI_IORT if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
 	select ACPI_MCFG if ACPI
 	select ACPI_SPCR_TABLE if ACPI
@@ -19,7 +20,9 @@ config ARM64
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
@@ -93,6 +96,7 @@ config ARM64
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP if NUMA
+	select HAVE_NMI if ACPI_APEI_SEA
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -245,6 +249,9 @@ config PGTABLE_LEVELS
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -983,7 +990,7 @@ config RANDOMIZE_BASE
 
 config RANDOMIZE_MODULE_REGION_FULL
 	bool "Randomize the module region independently from the core kernel"
-	depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
+	depends on RANDOMIZE_BASE
 	default y
 	help
 	  Randomizes the location of the module region without considering the
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index f839ecd919f9..9b41f1e3b1a0 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -52,17 +52,19 @@ KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst)
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
+CHECKFLAGS	+= -D__AARCH64EB__
 AS		+= -EB
 LD		+= -EB
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
+CHECKFLAGS	+= -D__AARCH64EL__
 AS		+= -EL
 LD		+= -EL
 UTS_MACHINE	:= aarch64
 endif
 
-CHECKFLAGS	+= -D__aarch64__
+CHECKFLAGS	+= -D__aarch64__ -m64
 
 ifeq ($(CONFIG_ARM64_MODULE_CMODEL_LARGE), y)
 KBUILD_CFLAGS_MODULE	+= -mcmodel=large
@@ -70,6 +72,9 @@ endif
 
 ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDFLAGS_MODULE	+= -T $(srctree)/arch/arm64/kernel/module.lds
+ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
+KBUILD_LDFLAGS_MODULE	+= $(objtree)/arch/arm64/kernel/ftrace-mod.o
+endif
 endif
 
 # Default value
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 09f65339d66d..0b6f5a7d4027 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -42,7 +42,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	} while (--ihl);
 
 	sum += ((sum >> 32) | (sum << 32));
-	return csum_fold(sum >> 32);
+	return csum_fold((__force u32)(sum >> 32));
 }
 #define ip_fast_csum ip_fast_csum
 
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 5392dbeffa45..f72779aad276 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -48,8 +48,6 @@ void arch_teardown_dma_ops(struct device *dev);
 /* do not use this function in a driver */
 static inline bool is_device_dma_coherent(struct device *dev)
 {
-	if (!dev)
-		return false;
 	return dev->archdata.dma_coherent;
 }
 
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 5d1700425efe..ac3fb7441510 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -142,6 +142,7 @@ typedef struct user_fpsimd_state elf_fpregset_t;
 ({									\
 	clear_bit(TIF_32BIT, &current->mm->context.flags);		\
 	clear_thread_flag(TIF_32BIT);					\
+	current->personality &= ~READ_IMPLIES_EXEC;			\
 })
 
 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
@@ -187,6 +188,11 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 					 ((x)->e_flags & EF_ARM_EABI_MASK))
 
 #define compat_start_thread		compat_start_thread
+/*
+ * Unlike the native SET_PERSONALITY macro, the compat version inherits
+ * READ_IMPLIES_EXEC across a fork() since this is the behaviour on
+ * arch/arm/.
+ */
 #define COMPAT_SET_PERSONALITY(ex)					\
 ({									\
 	set_bit(TIF_32BIT, &current->mm->context.flags);		\
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 85997c0e5443..28bf02efce76 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -83,6 +83,7 @@
 #define ESR_ELx_WNR		(UL(1) << 6)
 
 /* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_FnV		(UL(1) << 10)
 #define ESR_ELx_EA		(UL(1) << 9)
 #define ESR_ELx_S1PTW		(UL(1) << 7)
 
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 85c4a8981d47..f32b42e8725d 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -48,16 +48,16 @@ do {									\
 } while (0)
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
+	int oparg = (int)(encoded_op << 8) >> 20;
+	int cmparg = (int)(encoded_op << 20) >> 20;
 	int oldval = 0, ret, tmp;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
+		oparg = 1U << (oparg & 0x1f);
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6e99978e83bd..61d694c2eae5 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -204,6 +204,16 @@
 #define FSC_FAULT	ESR_ELx_FSC_FAULT
 #define FSC_ACCESS	ESR_ELx_FSC_ACCESS
 #define FSC_PERM	ESR_ELx_FSC_PERM
+#define FSC_SEA		ESR_ELx_FSC_EXTABT
+#define FSC_SEA_TTW0	(0x14)
+#define FSC_SEA_TTW1	(0x15)
+#define FSC_SEA_TTW2	(0x16)
+#define FSC_SEA_TTW3	(0x17)
+#define FSC_SECC	(0x18)
+#define FSC_SECC_TTW0	(0x1c)
+#define FSC_SECC_TTW1	(0x1d)
+#define FSC_SECC_TTW2	(0x1e)
+#define FSC_SECC_TTW3	(0x1f)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index d57693f5d4ec..19bd97671bb8 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -30,6 +30,9 @@ struct mod_plt_sec {
 struct mod_arch_specific {
 	struct mod_plt_sec	core;
 	struct mod_plt_sec	init;
+
+	/* for CONFIG_DYNAMIC_FTRACE */
+	void			*ftrace_trampoline;
 };
 #endif
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index c213fdbd056c..6eae342ced6b 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -441,7 +441,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 
 #define pud_none(pud)		(!pud_val(pud))
 #define pud_bad(pud)		(!(pud_val(pud) & PUD_TABLE_BIT))
-#define pud_present(pud)	(pud_val(pud))
+#define pud_present(pud)	pte_present(pud_pte(pud))
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 9428b93fefb2..64c9e78f9882 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -104,6 +104,9 @@ struct thread_struct {
 #define task_user_tls(t)	(&(t)->thread.tp_value)
 #endif
 
+/* Sync TPIDR_EL0 back to thread_struct for current */
+void tls_preserve_current_state(void);
+
 #define INIT_THREAD  {	}
 
 static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 801a16dbbdf6..5b6eafccc5d8 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -30,5 +30,6 @@ struct stackframe {
 extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
 extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);
+extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk);
 
 #endif	/* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index bc812435bc76..07aa8e3c5630 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -40,7 +40,7 @@ void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 			   int sig, int code, const char *name);
 
 struct mm_struct;
-extern void show_pte(struct mm_struct *mm, unsigned long addr);
+extern void show_pte(unsigned long addr);
 extern void __show_regs(struct pt_regs *);
 
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
@@ -56,6 +56,8 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 	__show_ratelimited;						\
 })
 
+int handle_guest_sea(phys_addr_t addr, unsigned int esr);
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index ee469be1ae1d..f0a76b9fcd6e 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -34,6 +34,26 @@ struct sigcontext {
 };
 
 /*
+ * Allocation of __reserved[]:
+ * (Note: records do not necessarily occur in the order shown here.)
+ *
+ *	size		description
+ *
+ *	0x210		fpsimd_context
+ *	 0x10		esr_context
+ *	 0x20		extra_context (optional)
+ *	 0x10		terminator (null _aarch64_ctx)
+ *
+ *	0xdb0		(reserved for future allocation)
+ *
+ * New records that can exceed this space need to be opt-in for userspace, so
+ * that an expanded signal frame is not generated unexpectedly.  The mechanism
+ * for opting in will depend on the extension that generates each new record.
+ * The above table documents the maximum set and sizes of records than can be
+ * generated when userspace does not opt in for any such extension.
+ */
+
+/*
  * Header to be used at the beginning of structures extending the user
  * context. Such structures must be placed after the rt_sigframe on the stack
  * and be 16-byte aligned. The last structure must be a dummy one with the
@@ -61,4 +81,39 @@ struct esr_context {
 	__u64 esr;
 };
 
+/*
+ * extra_context: describes extra space in the signal frame for
+ * additional structures that don't fit in sigcontext.__reserved[].
+ *
+ * Note:
+ *
+ * 1) fpsimd_context, esr_context and extra_context must be placed in
+ * sigcontext.__reserved[] if present.  They cannot be placed in the
+ * extra space.  Any other record can be placed either in the extra
+ * space or in sigcontext.__reserved[], unless otherwise specified in
+ * this file.
+ *
+ * 2) There must not be more than one extra_context.
+ *
+ * 3) If extra_context is present, it must be followed immediately in
+ * sigcontext.__reserved[] by the terminating null _aarch64_ctx.
+ *
+ * 4) The extra space to which datap points must start at the first
+ * 16-byte aligned address immediately after the terminating null
+ * _aarch64_ctx that follows the extra_context structure in
+ * __reserved[].  The extra space may overrun the end of __reserved[],
+ * as indicated by a sufficiently large value for the size field.
+ *
+ * 5) The extra space must itself be terminated with a null
+ * _aarch64_ctx.
+ */
+#define EXTRA_MAGIC	0x45585401
+
+struct extra_context {
+	struct _aarch64_ctx head;
+	__u64 datap; /* 16-byte aligned pointer to extra space cast to __u64 */
+	__u32 size; /* size in bytes of the extra space */
+	__u32 __reserved[3];
+};
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 1dcb69d3d0e5..f2b4e816b6de 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -62,3 +62,6 @@ extra-y					+= $(head-y) vmlinux.lds
 ifeq ($(CONFIG_DEBUG_EFI),y)
 AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
 endif
+
+# will be included by each individual module but not by the core kernel itself
+extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o
diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c
index 1f5655cd9cc9..98a20e58758b 100644
--- a/arch/arm64/kernel/acpi_parking_protocol.c
+++ b/arch/arm64/kernel/acpi_parking_protocol.c
@@ -71,7 +71,7 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu)
 {
 	struct cpu_mailbox_entry *cpu_entry = &cpu_mailbox_entries[cpu];
 	struct parking_protocol_mailbox __iomem *mailbox;
-	__le32 cpu_id;
+	u32 cpu_id;
 
 	/*
 	 * Map mailbox memory with attribute device nGnRE (ie ioremap -
@@ -123,9 +123,9 @@ static void acpi_parking_protocol_cpu_postboot(void)
 	int cpu = smp_processor_id();
 	struct cpu_mailbox_entry *cpu_entry = &cpu_mailbox_entries[cpu];
 	struct parking_protocol_mailbox __iomem *mailbox = cpu_entry->mailbox;
-	__le64 entry_point;
+	u64 entry_point;
 
-	entry_point = readl_relaxed(&mailbox->entry_point);
+	entry_point = readq_relaxed(&mailbox->entry_point);
 	/*
 	 * Check if firmware has cleared the entry_point as expected
 	 * by the protocol specification.
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 8840c109c5d6..6dd0a3a3e5c9 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -28,7 +28,7 @@
 #include <asm/sections.h>
 #include <linux/stop_machine.h>
 
-#define __ALT_PTR(a,f)		(u32 *)((void *)&(a)->f + (a)->f)
+#define __ALT_PTR(a,f)		((void *)&(a)->f + (a)->f)
 #define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
 #define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
 
@@ -60,7 +60,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
 
-static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
+static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr)
 {
 	u32 insn;
 
@@ -109,7 +109,7 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
-	u32 *origptr, *replptr, *updptr;
+	__le32 *origptr, *replptr, *updptr;
 
 	for (alt = region->begin; alt < region->end; alt++) {
 		u32 insn;
@@ -124,7 +124,7 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias)
 
 		origptr = ALT_ORIG_PTR(alt);
 		replptr = ALT_REPL_PTR(alt);
-		updptr = use_linear_alias ? (u32 *)lm_alias(origptr) : origptr;
+		updptr = use_linear_alias ? lm_alias(origptr) : origptr;
 		nr_inst = alt->alt_len / sizeof(insn);
 
 		for (i = 0; i < nr_inst; i++) {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 817ce3365e20..9f9e0064c8c1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -51,6 +51,25 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcaps);
 
+static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p)
+{
+	/* file-wide pr_fmt adds "CPU features: " prefix */
+	pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps);
+	return 0;
+}
+
+static struct notifier_block cpu_hwcaps_notifier = {
+	.notifier_call = dump_cpu_hwcaps
+};
+
+static int __init register_cpu_hwcaps_dumper(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &cpu_hwcaps_notifier);
+	return 0;
+}
+__initcall(register_cpu_hwcaps_dumper);
+
 DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcap_keys);
 
@@ -639,8 +658,10 @@ void update_cpu_features(int cpu,
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
 	 */
-	WARN_TAINT_ONCE(taint, TAINT_CPU_OUT_OF_SPEC,
-			"Unsupported CPU feature variation.\n");
+	if (taint) {
+		pr_warn_once("Unsupported CPU feature variation detected.\n");
+		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	}
 }
 
 u64 read_sanitised_ftr_reg(u32 id)
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 68b1f364c515..f495ee5049fd 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -227,7 +227,7 @@ static struct attribute *cpuregs_id_attrs[] = {
 	NULL
 };
 
-static struct attribute_group cpuregs_attr_group = {
+static const struct attribute_group cpuregs_attr_group = {
 	.attrs = cpuregs_id_attrs,
 	.name = "identification"
 };
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index d618e25c3de1..c7ef99904934 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -341,20 +341,22 @@ int aarch32_break_handler(struct pt_regs *regs)
 
 	if (compat_thumb_mode(regs)) {
 		/* get 16-bit Thumb instruction */
-		get_user(thumb_instr, (u16 __user *)pc);
-		thumb_instr = le16_to_cpu(thumb_instr);
+		__le16 instr;
+		get_user(instr, (__le16 __user *)pc);
+		thumb_instr = le16_to_cpu(instr);
 		if (thumb_instr == AARCH32_BREAK_THUMB2_LO) {
 			/* get second half of 32-bit Thumb-2 instruction */
-			get_user(thumb_instr, (u16 __user *)(pc + 2));
-			thumb_instr = le16_to_cpu(thumb_instr);
+			get_user(instr, (__le16 __user *)(pc + 2));
+			thumb_instr = le16_to_cpu(instr);
 			bp = thumb_instr == AARCH32_BREAK_THUMB2_HI;
 		} else {
 			bp = thumb_instr == AARCH32_BREAK_THUMB;
 		}
 	} else {
 		/* 32-bit ARM instruction */
-		get_user(arm_instr, (u32 __user *)pc);
-		arm_instr = le32_to_cpu(arm_instr);
+		__le32 instr;
+		get_user(instr, (__le32 __user *)pc);
+		arm_instr = le32_to_cpu(instr);
 		bp = (arm_instr & ~0xf0000000) == AARCH32_BREAK_ARM;
 	}
 
diff --git a/arch/arm64/kernel/ftrace-mod.S b/arch/arm64/kernel/ftrace-mod.S
new file mode 100644
index 000000000000..00c4025be4ff
--- /dev/null
+++ b/arch/arm64/kernel/ftrace-mod.S
@@ -0,0 +1,18 @@
+/*
+ * 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>
+#include <asm/assembler.h>
+
+	.section	".text.ftrace_trampoline", "ax"
+	.align		3
+0:	.quad		0
+__ftrace_trampoline:
+	ldr		x16, 0b
+	br		x16
+ENDPROC(__ftrace_trampoline)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 40ad08ac569a..c13b1fca0e5b 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -10,10 +10,12 @@
  */
 
 #include <linux/ftrace.h>
+#include <linux/module.h>
 #include <linux/swab.h>
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
+#include <asm/debug-monitors.h>
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 
@@ -70,6 +72,58 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned long pc = rec->ip;
 	u32 old, new;
+	long offset = (long)pc - (long)addr;
+
+	if (offset < -SZ_128M || offset >= SZ_128M) {
+#ifdef CONFIG_ARM64_MODULE_PLTS
+		unsigned long *trampoline;
+		struct module *mod;
+
+		/*
+		 * On kernels that support module PLTs, the offset between the
+		 * branch instruction and its target may legally exceed the
+		 * range of an ordinary relative 'bl' opcode. In this case, we
+		 * need to branch via a trampoline in the module.
+		 *
+		 * NOTE: __module_text_address() must be called with preemption
+		 * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+		 * retains its validity throughout the remainder of this code.
+		 */
+		preempt_disable();
+		mod = __module_text_address(pc);
+		preempt_enable();
+
+		if (WARN_ON(!mod))
+			return -EINVAL;
+
+		/*
+		 * There is only one ftrace trampoline per module. For now,
+		 * this is not a problem since on arm64, all dynamic ftrace
+		 * invocations are routed via ftrace_caller(). This will need
+		 * to be revisited if support for multiple ftrace entry points
+		 * is added in the future, but for now, the pr_err() below
+		 * deals with a theoretical issue only.
+		 */
+		trampoline = (unsigned long *)mod->arch.ftrace_trampoline;
+		if (trampoline[0] != addr) {
+			if (trampoline[0] != 0) {
+				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);
+			trampoline[0] = addr;
+			module_enable_ro(mod, true);
+
+			/* update trampoline before patching in the branch */
+			smp_wmb();
+		}
+		addr = (unsigned long)&trampoline[1];
+#else /* CONFIG_ARM64_MODULE_PLTS */
+		return -EINVAL;
+#endif /* CONFIG_ARM64_MODULE_PLTS */
+	}
 
 	old = aarch64_insn_gen_nop();
 	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
@@ -84,12 +138,55 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
 	unsigned long pc = rec->ip;
-	u32 old, new;
+	bool validate = true;
+	u32 old = 0, new;
+	long offset = (long)pc - (long)addr;
+
+	if (offset < -SZ_128M || offset >= SZ_128M) {
+#ifdef CONFIG_ARM64_MODULE_PLTS
+		u32 replaced;
+
+		/*
+		 * 'mod' is only set at module load time, but if we end up
+		 * dealing with an out-of-range condition, we can assume it
+		 * is due to a module being loaded far away from the kernel.
+		 */
+		if (!mod) {
+			preempt_disable();
+			mod = __module_text_address(pc);
+			preempt_enable();
+
+			if (WARN_ON(!mod))
+				return -EINVAL;
+		}
+
+		/*
+		 * The instruction we are about to patch may be a branch and
+		 * link instruction that was redirected via a PLT entry. In
+		 * this case, the normal validation will fail, but we can at
+		 * least check that we are dealing with a branch and link
+		 * instruction that points into the right module.
+		 */
+		if (aarch64_insn_read((void *)pc, &replaced))
+			return -EFAULT;
+
+		if (!aarch64_insn_is_bl(replaced) ||
+		    !within_module(pc + aarch64_get_branch_offset(replaced),
+				   mod))
+			return -EINVAL;
+
+		validate = false;
+#else /* CONFIG_ARM64_MODULE_PLTS */
+		return -EINVAL;
+#endif /* CONFIG_ARM64_MODULE_PLTS */
+	} else {
+		old = aarch64_insn_gen_branch_imm(pc, addr,
+						  AARCH64_INSN_BRANCH_LINK);
+	}
 
-	old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
 	new = aarch64_insn_gen_nop();
 
-	return ftrace_modify_code(pc, old, new, true);
+	return ftrace_modify_code(pc, old, new, validate);
 }
 
 void arch_ftrace_update_code(int command)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index cd872133e88e..2718a77da165 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -117,7 +117,7 @@ static void __kprobes patch_unmap(int fixmap)
 int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
 {
 	int ret;
-	u32 val;
+	__le32 val;
 
 	ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE);
 	if (!ret)
@@ -126,7 +126,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
 	return ret;
 }
 
-static int __kprobes __aarch64_insn_write(void *addr, u32 insn)
+static int __kprobes __aarch64_insn_write(void *addr, __le32 insn)
 {
 	void *waddr = addr;
 	unsigned long flags = 0;
@@ -145,8 +145,7 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn)
 
 int __kprobes aarch64_insn_write(void *addr, u32 insn)
 {
-	insn = cpu_to_le32(insn);
-	return __aarch64_insn_write(addr, insn);
+	return __aarch64_insn_write(addr, cpu_to_le32(insn));
 }
 
 static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index d7e90d97f5c4..a9710efb8c01 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -27,7 +27,7 @@ u16 __initdata memstart_offset_seed;
 static __init u64 get_kaslr_seed(void *fdt)
 {
 	int node, len;
-	u64 *prop;
+	fdt64_t *prop;
 	u64 ret;
 
 	node = fdt_path_offset(fdt, "/chosen");
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index f035ff6fb223..f469e0435903 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -74,7 +74,7 @@ enum aarch64_reloc_op {
 	RELOC_OP_PAGE,
 };
 
-static u64 do_reloc(enum aarch64_reloc_op reloc_op, void *place, u64 val)
+static u64 do_reloc(enum aarch64_reloc_op reloc_op, __le32 *place, u64 val)
 {
 	switch (reloc_op) {
 	case RELOC_OP_ABS:
@@ -121,12 +121,12 @@ enum aarch64_insn_movw_imm_type {
 	AARCH64_INSN_IMM_MOVKZ,
 };
 
-static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
+static int reloc_insn_movw(enum aarch64_reloc_op op, __le32 *place, u64 val,
 			   int lsb, enum aarch64_insn_movw_imm_type imm_type)
 {
 	u64 imm;
 	s64 sval;
-	u32 insn = le32_to_cpu(*(u32 *)place);
+	u32 insn = le32_to_cpu(*place);
 
 	sval = do_reloc(op, place, val);
 	imm = sval >> lsb;
@@ -154,7 +154,7 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
 
 	/* Update the instruction with the new encoding. */
 	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm);
-	*(u32 *)place = cpu_to_le32(insn);
+	*place = cpu_to_le32(insn);
 
 	if (imm > U16_MAX)
 		return -ERANGE;
@@ -162,12 +162,12 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
 	return 0;
 }
 
-static int reloc_insn_imm(enum aarch64_reloc_op op, void *place, u64 val,
+static int reloc_insn_imm(enum aarch64_reloc_op op, __le32 *place, u64 val,
 			  int lsb, int len, enum aarch64_insn_imm_type imm_type)
 {
 	u64 imm, imm_mask;
 	s64 sval;
-	u32 insn = le32_to_cpu(*(u32 *)place);
+	u32 insn = le32_to_cpu(*place);
 
 	/* Calculate the relocation value. */
 	sval = do_reloc(op, place, val);
@@ -179,7 +179,7 @@ static int reloc_insn_imm(enum aarch64_reloc_op op, void *place, u64 val,
 
 	/* Update the instruction's immediate field. */
 	insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
-	*(u32 *)place = cpu_to_le32(insn);
+	*place = cpu_to_le32(insn);
 
 	/*
 	 * Extract the upper value bits (including the sign bit) and
@@ -420,8 +420,12 @@ int module_finalize(const Elf_Ehdr *hdr,
 	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
 		if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) {
 			apply_alternatives((void *)s->sh_addr, s->sh_size);
-			return 0;
 		}
+#ifdef CONFIG_ARM64_MODULE_PLTS
+		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
+		    !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
+			me->arch.ftrace_trampoline = (void *)s->sh_addr;
+#endif
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index c7e3e6387a49..a7f6c01c13b9 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -108,7 +108,10 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 	if (!acpi_disabled) {
 		struct pci_config_window *cfg = bridge->bus->sysdata;
 		struct acpi_device *adev = to_acpi_device(cfg->parent);
+		struct device *bus_dev = &bridge->bus->dev;
+
 		ACPI_COMPANION_SET(&bridge->dev, adev);
+		set_dev_node(bus_dev, acpi_get_node(acpi_device_handle(adev)));
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 83a1b1ad189f..b5798ba21189 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -529,7 +529,7 @@ static struct attribute_group armv8_pmuv3_events_attr_group = {
 	.is_visible = armv8pmu_event_attr_is_visible,
 };
 
-PMU_FORMAT_ATTR(event, "config:0-9");
+PMU_FORMAT_ATTR(event, "config:0-15");
 
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c5c45942fb6e..d849d9804011 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -522,9 +522,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 		pr_err("current sp %lx does not match saved sp %lx\n",
 		       orig_sp, stack_addr);
 		pr_err("Saved registers for jprobe %p\n", jp);
-		show_regs(saved_regs);
+		__show_regs(saved_regs);
 		pr_err("Current registers\n");
-		show_regs(regs);
+		__show_regs(regs);
 		BUG();
 	}
 	unpause_graph_tracing();
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index ae2a835898d7..659ae8094ed5 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -210,6 +210,7 @@ void __show_regs(struct pt_regs *regs)
 void show_regs(struct pt_regs * regs)
 {
 	__show_regs(regs);
+	dump_backtrace(regs, NULL);
 }
 
 static void tls_thread_flush(void)
@@ -297,12 +298,16 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	return 0;
 }
 
+void tls_preserve_current_state(void)
+{
+	*task_user_tls(current) = read_sysreg(tpidr_el0);
+}
+
 static void tls_thread_switch(struct task_struct *next)
 {
 	unsigned long tpidr, tpidrro;
 
-	tpidr = read_sysreg(tpidr_el0);
-	*task_user_tls(current) = tpidr;
+	tls_preserve_current_state();
 
 	tpidr = *task_user_tls(next);
 	tpidrro = is_compat_thread(task_thread_info(next)) ?
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index c142459a88f3..1b38c0150aec 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -623,6 +623,10 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 {
 	struct user_fpsimd_state *uregs;
 	uregs = &target->thread.fpsimd_state.user_fpsimd;
+
+	if (target == current)
+		fpsimd_preserve_current_state();
+
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, -1);
 }
 
@@ -648,6 +652,10 @@ static int tls_get(struct task_struct *target, const struct user_regset *regset,
 		   void *kbuf, void __user *ubuf)
 {
 	unsigned long *tls = &target->thread.tp_value;
+
+	if (target == current)
+		tls_preserve_current_state();
+
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, tls, 0, -1);
 }
 
@@ -894,21 +902,27 @@ static int compat_vfp_get(struct task_struct *target,
 {
 	struct user_fpsimd_state *uregs;
 	compat_ulong_t fpscr;
-	int ret;
+	int ret, vregs_end_pos;
 
 	uregs = &target->thread.fpsimd_state.user_fpsimd;
 
+	if (target == current)
+		fpsimd_preserve_current_state();
+
 	/*
 	 * The VFP registers are packed into the fpsimd_state, so they all sit
 	 * nicely together for us. We just need to create the fpscr separately.
 	 */
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
-				  VFP_STATE_SIZE - sizeof(compat_ulong_t));
+	vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t);
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs,
+				  0, vregs_end_pos);
 
 	if (count && !ret) {
 		fpscr = (uregs->fpsr & VFP_FPSCR_STAT_MASK) |
 			(uregs->fpcr & VFP_FPSCR_CTRL_MASK);
-		ret = put_user(fpscr, (compat_ulong_t *)ubuf);
+
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fpscr,
+					  vregs_end_pos, VFP_STATE_SIZE);
 	}
 
 	return ret;
@@ -921,20 +935,21 @@ static int compat_vfp_set(struct task_struct *target,
 {
 	struct user_fpsimd_state *uregs;
 	compat_ulong_t fpscr;
-	int ret;
-
-	if (pos + count > VFP_STATE_SIZE)
-		return -EIO;
+	int ret, vregs_end_pos;
 
 	uregs = &target->thread.fpsimd_state.user_fpsimd;
 
+	vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t);
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
-				 VFP_STATE_SIZE - sizeof(compat_ulong_t));
+				 vregs_end_pos);
 
 	if (count && !ret) {
-		ret = get_user(fpscr, (compat_ulong_t *)ubuf);
-		uregs->fpsr = fpscr & VFP_FPSCR_STAT_MASK;
-		uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpscr,
+					 vregs_end_pos, VFP_STATE_SIZE);
+		if (!ret) {
+			uregs->fpsr = fpscr & VFP_FPSCR_STAT_MASK;
+			uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
+		}
 	}
 
 	fpsimd_flush_task_state(target);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 2c822ef94f34..d4b740538ad5 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -194,6 +194,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 	}
 
 	name = of_flat_dt_get_machine_name();
+	if (!name)
+		return;
+
 	pr_info("Machine model: %s\n", name);
 	dump_stack_set_arch_desc("%s (DT)", name);
 }
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index c7b6de62f9d3..089c3747995d 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -19,10 +19,14 @@
 
 #include <linux/compat.h>
 #include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/freezer.h>
+#include <linux/stddef.h>
 #include <linux/uaccess.h>
+#include <linux/sizes.h>
+#include <linux/string.h>
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>
 
@@ -41,10 +45,133 @@
 struct rt_sigframe {
 	struct siginfo info;
 	struct ucontext uc;
+};
+
+struct frame_record {
 	u64 fp;
 	u64 lr;
 };
 
+struct rt_sigframe_user_layout {
+	struct rt_sigframe __user *sigframe;
+	struct frame_record __user *next_frame;
+
+	unsigned long size;	/* size of allocated sigframe data */
+	unsigned long limit;	/* largest allowed size */
+
+	unsigned long fpsimd_offset;
+	unsigned long esr_offset;
+	unsigned long extra_offset;
+	unsigned long end_offset;
+};
+
+#define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
+#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
+#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
+
+static void init_user_layout(struct rt_sigframe_user_layout *user)
+{
+	const size_t reserved_size =
+		sizeof(user->sigframe->uc.uc_mcontext.__reserved);
+
+	memset(user, 0, sizeof(*user));
+	user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved);
+
+	user->limit = user->size + reserved_size;
+
+	user->limit -= TERMINATOR_SIZE;
+	user->limit -= EXTRA_CONTEXT_SIZE;
+	/* Reserve space for extension and terminator ^ */
+}
+
+static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
+{
+	return round_up(max(user->size, sizeof(struct rt_sigframe)), 16);
+}
+
+/*
+ * Sanity limit on the approximate maximum size of signal frame we'll
+ * try to generate.  Stack alignment padding and the frame record are
+ * not taken into account.  This limit is not a guarantee and is
+ * NOT ABI.
+ */
+#define SIGFRAME_MAXSZ SZ_64K
+
+static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
+			    unsigned long *offset, size_t size, bool extend)
+{
+	size_t padded_size = round_up(size, 16);
+
+	if (padded_size > user->limit - user->size &&
+	    !user->extra_offset &&
+	    extend) {
+		int ret;
+
+		user->limit += EXTRA_CONTEXT_SIZE;
+		ret = __sigframe_alloc(user, &user->extra_offset,
+				       sizeof(struct extra_context), false);
+		if (ret) {
+			user->limit -= EXTRA_CONTEXT_SIZE;
+			return ret;
+		}
+
+		/* Reserve space for the __reserved[] terminator */
+		user->size += TERMINATOR_SIZE;
+
+		/*
+		 * Allow expansion up to SIGFRAME_MAXSZ, ensuring space for
+		 * the terminator:
+		 */
+		user->limit = SIGFRAME_MAXSZ - TERMINATOR_SIZE;
+	}
+
+	/* Still not enough space?  Bad luck! */
+	if (padded_size > user->limit - user->size)
+		return -ENOMEM;
+
+	*offset = user->size;
+	user->size += padded_size;
+
+	return 0;
+}
+
+/*
+ * Allocate space for an optional record of <size> bytes in the user
+ * signal frame.  The offset from the signal frame base address to the
+ * allocated block is assigned to *offset.
+ */
+static int sigframe_alloc(struct rt_sigframe_user_layout *user,
+			  unsigned long *offset, size_t size)
+{
+	return __sigframe_alloc(user, offset, size, true);
+}
+
+/* Allocate the null terminator record and prevent further allocations */
+static int sigframe_alloc_end(struct rt_sigframe_user_layout *user)
+{
+	int ret;
+
+	/* Un-reserve the space reserved for the terminator: */
+	user->limit += TERMINATOR_SIZE;
+
+	ret = sigframe_alloc(user, &user->end_offset,
+			     sizeof(struct _aarch64_ctx));
+	if (ret)
+		return ret;
+
+	/* Prevent further allocation: */
+	user->limit = user->size;
+	return 0;
+}
+
+static void __user *apply_user_offset(
+	struct rt_sigframe_user_layout const *user, unsigned long offset)
+{
+	char __user *base = (char __user *)user->sigframe;
+
+	return base + offset;
+}
+
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 {
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
@@ -92,12 +219,159 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
+struct user_ctxs {
+	struct fpsimd_context __user *fpsimd;
+};
+
+static int parse_user_sigframe(struct user_ctxs *user,
+			       struct rt_sigframe __user *sf)
+{
+	struct sigcontext __user *const sc = &sf->uc.uc_mcontext;
+	struct _aarch64_ctx __user *head;
+	char __user *base = (char __user *)&sc->__reserved;
+	size_t offset = 0;
+	size_t limit = sizeof(sc->__reserved);
+	bool have_extra_context = false;
+	char const __user *const sfp = (char const __user *)sf;
+
+	user->fpsimd = NULL;
+
+	if (!IS_ALIGNED((unsigned long)base, 16))
+		goto invalid;
+
+	while (1) {
+		int err = 0;
+		u32 magic, size;
+		char const __user *userp;
+		struct extra_context const __user *extra;
+		u64 extra_datap;
+		u32 extra_size;
+		struct _aarch64_ctx const __user *end;
+		u32 end_magic, end_size;
+
+		if (limit - offset < sizeof(*head))
+			goto invalid;
+
+		if (!IS_ALIGNED(offset, 16))
+			goto invalid;
+
+		head = (struct _aarch64_ctx __user *)(base + offset);
+		__get_user_error(magic, &head->magic, err);
+		__get_user_error(size, &head->size, err);
+		if (err)
+			return err;
+
+		if (limit - offset < size)
+			goto invalid;
+
+		switch (magic) {
+		case 0:
+			if (size)
+				goto invalid;
+
+			goto done;
+
+		case FPSIMD_MAGIC:
+			if (user->fpsimd)
+				goto invalid;
+
+			if (size < sizeof(*user->fpsimd))
+				goto invalid;
+
+			user->fpsimd = (struct fpsimd_context __user *)head;
+			break;
+
+		case ESR_MAGIC:
+			/* ignore */
+			break;
+
+		case EXTRA_MAGIC:
+			if (have_extra_context)
+				goto invalid;
+
+			if (size < sizeof(*extra))
+				goto invalid;
+
+			userp = (char const __user *)head;
+
+			extra = (struct extra_context const __user *)userp;
+			userp += size;
+
+			__get_user_error(extra_datap, &extra->datap, err);
+			__get_user_error(extra_size, &extra->size, err);
+			if (err)
+				return err;
+
+			/* Check for the dummy terminator in __reserved[]: */
+
+			if (limit - offset - size < TERMINATOR_SIZE)
+				goto invalid;
+
+			end = (struct _aarch64_ctx const __user *)userp;
+			userp += TERMINATOR_SIZE;
+
+			__get_user_error(end_magic, &end->magic, err);
+			__get_user_error(end_size, &end->size, err);
+			if (err)
+				return err;
+
+			if (end_magic || end_size)
+				goto invalid;
+
+			/* Prevent looping/repeated parsing of extra_context */
+			have_extra_context = true;
+
+			base = (__force void __user *)extra_datap;
+			if (!IS_ALIGNED((unsigned long)base, 16))
+				goto invalid;
+
+			if (!IS_ALIGNED(extra_size, 16))
+				goto invalid;
+
+			if (base != userp)
+				goto invalid;
+
+			/* Reject "unreasonably large" frames: */
+			if (extra_size > sfp + SIGFRAME_MAXSZ - userp)
+				goto invalid;
+
+			/*
+			 * Ignore trailing terminator in __reserved[]
+			 * and start parsing extra data:
+			 */
+			offset = 0;
+			limit = extra_size;
+			continue;
+
+		default:
+			goto invalid;
+		}
+
+		if (size < sizeof(*head))
+			goto invalid;
+
+		if (limit - offset < size)
+			goto invalid;
+
+		offset += size;
+	}
+
+done:
+	if (!user->fpsimd)
+		goto invalid;
+
+	return 0;
+
+invalid:
+	return -EINVAL;
+}
+
 static int restore_sigframe(struct pt_regs *regs,
 			    struct rt_sigframe __user *sf)
 {
 	sigset_t set;
 	int i, err;
-	void *aux = sf->uc.uc_mcontext.__reserved;
+	struct user_ctxs user;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0)
@@ -116,12 +390,11 @@ static int restore_sigframe(struct pt_regs *regs,
 	regs->syscallno = ~0UL;
 
 	err |= !valid_user_regs(&regs->user_regs, current);
+	if (err == 0)
+		err = parse_user_sigframe(&user, sf);
 
-	if (err == 0) {
-		struct fpsimd_context *fpsimd_ctx =
-			container_of(aux, struct fpsimd_context, head);
-		err |= restore_fpsimd_context(fpsimd_ctx);
-	}
+	if (err == 0)
+		err = restore_fpsimd_context(user.fpsimd);
 
 	return err;
 }
@@ -162,16 +435,37 @@ badframe:
 	return 0;
 }
 
-static int setup_sigframe(struct rt_sigframe __user *sf,
+/* Determine the layout of optional records in the signal frame */
+static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
+{
+	int err;
+
+	err = sigframe_alloc(user, &user->fpsimd_offset,
+			     sizeof(struct fpsimd_context));
+	if (err)
+		return err;
+
+	/* fault information, if valid */
+	if (current->thread.fault_code) {
+		err = sigframe_alloc(user, &user->esr_offset,
+				     sizeof(struct esr_context));
+		if (err)
+			return err;
+	}
+
+	return sigframe_alloc_end(user);
+}
+
+
+static int setup_sigframe(struct rt_sigframe_user_layout *user,
 			  struct pt_regs *regs, sigset_t *set)
 {
 	int i, err = 0;
-	void *aux = sf->uc.uc_mcontext.__reserved;
-	struct _aarch64_ctx *end;
+	struct rt_sigframe __user *sf = user->sigframe;
 
 	/* set up the stack frame for unwinding */
-	__put_user_error(regs->regs[29], &sf->fp, err);
-	__put_user_error(regs->regs[30], &sf->lr, err);
+	__put_user_error(regs->regs[29], &user->next_frame->fp, err);
+	__put_user_error(regs->regs[30], &user->next_frame->lr, err);
 
 	for (i = 0; i < 31; i++)
 		__put_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i],
@@ -185,58 +479,103 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
 	if (err == 0) {
-		struct fpsimd_context *fpsimd_ctx =
-			container_of(aux, struct fpsimd_context, head);
+		struct fpsimd_context __user *fpsimd_ctx =
+			apply_user_offset(user, user->fpsimd_offset);
 		err |= preserve_fpsimd_context(fpsimd_ctx);
-		aux += sizeof(*fpsimd_ctx);
 	}
 
 	/* fault information, if valid */
-	if (current->thread.fault_code) {
-		struct esr_context *esr_ctx =
-			container_of(aux, struct esr_context, head);
+	if (err == 0 && user->esr_offset) {
+		struct esr_context __user *esr_ctx =
+			apply_user_offset(user, user->esr_offset);
+
 		__put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err);
 		__put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err);
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
-		aux += sizeof(*esr_ctx);
+	}
+
+	if (err == 0 && user->extra_offset) {
+		char __user *sfp = (char __user *)user->sigframe;
+		char __user *userp =
+			apply_user_offset(user, user->extra_offset);
+
+		struct extra_context __user *extra;
+		struct _aarch64_ctx __user *end;
+		u64 extra_datap;
+		u32 extra_size;
+
+		extra = (struct extra_context __user *)userp;
+		userp += EXTRA_CONTEXT_SIZE;
+
+		end = (struct _aarch64_ctx __user *)userp;
+		userp += TERMINATOR_SIZE;
+
+		/*
+		 * extra_datap is just written to the signal frame.
+		 * The value gets cast back to a void __user *
+		 * during sigreturn.
+		 */
+		extra_datap = (__force u64)userp;
+		extra_size = sfp + round_up(user->size, 16) - userp;
+
+		__put_user_error(EXTRA_MAGIC, &extra->head.magic, err);
+		__put_user_error(EXTRA_CONTEXT_SIZE, &extra->head.size, err);
+		__put_user_error(extra_datap, &extra->datap, err);
+		__put_user_error(extra_size, &extra->size, err);
+
+		/* Add the terminator */
+		__put_user_error(0, &end->magic, err);
+		__put_user_error(0, &end->size, err);
 	}
 
 	/* set the "end" magic */
-	end = aux;
-	__put_user_error(0, &end->magic, err);
-	__put_user_error(0, &end->size, err);
+	if (err == 0) {
+		struct _aarch64_ctx __user *end =
+			apply_user_offset(user, user->end_offset);
+
+		__put_user_error(0, &end->magic, err);
+		__put_user_error(0, &end->size, err);
+	}
 
 	return err;
 }
 
-static struct rt_sigframe __user *get_sigframe(struct ksignal *ksig,
-					       struct pt_regs *regs)
+static int get_sigframe(struct rt_sigframe_user_layout *user,
+			 struct ksignal *ksig, struct pt_regs *regs)
 {
 	unsigned long sp, sp_top;
-	struct rt_sigframe __user *frame;
+	int err;
+
+	init_user_layout(user);
+	err = setup_sigframe_layout(user);
+	if (err)
+		return err;
 
 	sp = sp_top = sigsp(regs->sp, ksig);
 
-	sp = (sp - sizeof(struct rt_sigframe)) & ~15;
-	frame = (struct rt_sigframe __user *)sp;
+	sp = round_down(sp - sizeof(struct frame_record), 16);
+	user->next_frame = (struct frame_record __user *)sp;
+
+	sp = round_down(sp, 16) - sigframe_size(user);
+	user->sigframe = (struct rt_sigframe __user *)sp;
 
 	/*
 	 * Check that we can actually write to the signal frame.
 	 */
-	if (!access_ok(VERIFY_WRITE, frame, sp_top - sp))
-		frame = NULL;
+	if (!access_ok(VERIFY_WRITE, user->sigframe, sp_top - sp))
+		return -EFAULT;
 
-	return frame;
+	return 0;
 }
 
 static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
-			 void __user *frame, int usig)
+			 struct rt_sigframe_user_layout *user, int usig)
 {
 	__sigrestore_t sigtramp;
 
 	regs->regs[0] = usig;
-	regs->sp = (unsigned long)frame;
-	regs->regs[29] = regs->sp + offsetof(struct rt_sigframe, fp);
+	regs->sp = (unsigned long)user->sigframe;
+	regs->regs[29] = (unsigned long)&user->next_frame->fp;
 	regs->pc = (unsigned long)ka->sa.sa_handler;
 
 	if (ka->sa.sa_flags & SA_RESTORER)
@@ -250,20 +589,22 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
+	struct rt_sigframe_user_layout user;
 	struct rt_sigframe __user *frame;
 	int err = 0;
 
-	frame = get_sigframe(ksig, regs);
-	if (!frame)
+	if (get_sigframe(&user, ksig, regs))
 		return 1;
 
+	frame = user.sigframe;
+
 	__put_user_error(0, &frame->uc.uc_flags, err);
 	__put_user_error(NULL, &frame->uc.uc_link, err);
 
 	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
-	err |= setup_sigframe(frame, regs, set);
+	err |= setup_sigframe(&user, regs, set);
 	if (err == 0) {
-		setup_return(regs, &ksig->ka, frame, usig);
+		setup_return(regs, &ksig->ka, &user, usig);
 		if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
 			err |= copy_siginfo_to_user(&frame->info, &ksig->info);
 			regs->regs[1] = (unsigned long)&frame->info;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index feac80c22f61..09d37d66b630 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -210,6 +210,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 
 	put_task_stack(tsk);
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 void save_stack_trace(struct stack_trace *trace)
 {
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 0805b44f986a..c7c7088097be 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -140,7 +140,7 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 	}
 }
 
-static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
 	unsigned long irq_stack_ptr;
@@ -344,22 +344,24 @@ static int call_undef_hook(struct pt_regs *regs)
 
 	if (compat_thumb_mode(regs)) {
 		/* 16-bit Thumb instruction */
-		if (get_user(instr, (u16 __user *)pc))
+		__le16 instr_le;
+		if (get_user(instr_le, (__le16 __user *)pc))
 			goto exit;
-		instr = le16_to_cpu(instr);
+		instr = le16_to_cpu(instr_le);
 		if (aarch32_insn_is_wide(instr)) {
 			u32 instr2;
 
-			if (get_user(instr2, (u16 __user *)(pc + 2)))
+			if (get_user(instr_le, (__le16 __user *)(pc + 2)))
 				goto exit;
-			instr2 = le16_to_cpu(instr2);
+			instr2 = le16_to_cpu(instr_le);
 			instr = (instr << 16) | instr2;
 		}
 	} else {
 		/* 32-bit ARM instruction */
-		if (get_user(instr, (u32 __user *)pc))
+		__le32 instr_le;
+		if (get_user(instr_le, (__le32 __user *)pc))
 			goto exit;
-		instr = le32_to_cpu(instr);
+		instr = le32_to_cpu(instr_le);
 	}
 
 	raw_spin_lock_irqsave(&undef_lock, flags);
@@ -728,8 +730,6 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
 		break;
 
 	case BUG_TRAP_TYPE_WARN:
-		/* Ideally, report_bug() should backtrace for us... but no. */
-		dump_backtrace(regs, NULL);
 		break;
 
 	default:
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 7492d9009610..e8f759f764f2 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -37,7 +37,7 @@
 #include <asm/vdso.h>
 #include <asm/vdso_datapage.h>
 
-extern char vdso_start, vdso_end;
+extern char vdso_start[], vdso_end[];
 static unsigned long vdso_pages __ro_after_init;
 
 /*
@@ -125,14 +125,14 @@ static int __init vdso_init(void)
 	struct page **vdso_pagelist;
 	unsigned long pfn;
 
-	if (memcmp(&vdso_start, "\177ELF", 4)) {
+	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;
+	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);
+		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 *),
@@ -145,7 +145,7 @@ static int __init vdso_init(void)
 
 
 	/* Grab the vDSO code pages. */
-	pfn = sym_to_pfn(&vdso_start);
+	pfn = sym_to_pfn(vdso_start);
 
 	for (i = 0; i < vdso_pages; i++)
 		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3216e098c058..3e340b625436 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -95,11 +95,6 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  unsigned long attrs)
 {
-	if (dev == NULL) {
-		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
-		return NULL;
-	}
-
 	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA;
@@ -128,10 +123,6 @@ static void __dma_free_coherent(struct device *dev, size_t size,
 	bool freed;
 	phys_addr_t paddr = dma_to_phys(dev, dma_handle);
 
-	if (dev == NULL) {
-		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
-		return;
-	}
 
 	freed = dma_release_from_contiguous(dev,
 					phys_to_page(paddr),
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 37b95dff0b07..c7861c9864e6 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -31,6 +31,7 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 #include <linux/preempt.h>
+#include <linux/hugetlb.h>
 
 #include <asm/bug.h>
 #include <asm/cpufeature.h>
@@ -42,6 +43,8 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+#include <acpi/ghes.h>
+
 struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr,
 		      struct pt_regs *regs);
@@ -80,18 +83,35 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
 #endif
 
 /*
- * Dump out the page tables associated with 'addr' in mm 'mm'.
+ * Dump out the page tables associated with 'addr' in the currently active mm.
  */
-void show_pte(struct mm_struct *mm, unsigned long addr)
+void show_pte(unsigned long addr)
 {
+	struct mm_struct *mm;
 	pgd_t *pgd;
 
-	if (!mm)
+	if (addr < TASK_SIZE) {
+		/* TTBR0 */
+		mm = current->active_mm;
+		if (mm == &init_mm) {
+			pr_alert("[%016lx] user address but active_mm is swapper\n",
+				 addr);
+			return;
+		}
+	} else if (addr >= VA_START) {
+		/* TTBR1 */
 		mm = &init_mm;
+	} else {
+		pr_alert("[%016lx] address between user and kernel address ranges\n",
+			 addr);
+		return;
+	}
 
-	pr_alert("pgd = %p\n", mm->pgd);
+	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n",
+		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
+		 VA_BITS, mm->pgd);
 	pgd = pgd_offset(mm, addr);
-	pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd));
+	pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd));
 
 	do {
 		pud_t *pud;
@@ -196,8 +216,8 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
 /*
  * The kernel tried to access some page that wasn't present.
  */
-static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
-			      unsigned int esr, struct pt_regs *regs)
+static void __do_kernel_fault(unsigned long addr, unsigned int esr,
+			      struct pt_regs *regs)
 {
 	const char *msg;
 
@@ -227,7 +247,7 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
 	pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
 		 addr);
 
-	show_pte(mm, addr);
+	show_pte(addr);
 	die("Oops", regs, esr);
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
@@ -239,18 +259,20 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
  */
 static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 			    unsigned int esr, unsigned int sig, int code,
-			    struct pt_regs *regs)
+			    struct pt_regs *regs, int fault)
 {
 	struct siginfo si;
 	const struct fault_info *inf;
+	unsigned int lsb = 0;
 
 	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
 		inf = esr_to_fault_info(esr);
-		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
+		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x",
 			tsk->comm, task_pid_nr(tsk), inf->name, sig,
 			addr, esr);
-		show_pte(tsk->mm, addr);
-		show_regs(regs);
+		print_vma_addr(KERN_CONT ", in ", regs->pc);
+		pr_cont("\n");
+		__show_regs(regs);
 	}
 
 	tsk->thread.fault_address = addr;
@@ -259,13 +281,23 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	si.si_errno = 0;
 	si.si_code = code;
 	si.si_addr = (void __user *)addr;
+	/*
+	 * Either small page or large page may be poisoned.
+	 * In other words, VM_FAULT_HWPOISON_LARGE and
+	 * VM_FAULT_HWPOISON are mutually exclusive.
+	 */
+	if (fault & VM_FAULT_HWPOISON_LARGE)
+		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+	else if (fault & VM_FAULT_HWPOISON)
+		lsb = PAGE_SHIFT;
+	si.si_addr_lsb = lsb;
+
 	force_sig_info(sig, &si, tsk);
 }
 
 static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->active_mm;
 	const struct fault_info *inf;
 
 	/*
@@ -274,9 +306,9 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 	 */
 	if (user_mode(regs)) {
 		inf = esr_to_fault_info(esr);
-		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs, 0);
 	} else
-		__do_kernel_fault(mm, addr, esr, regs);
+		__do_kernel_fault(addr, esr, regs);
 }
 
 #define VM_FAULT_BADMAP		0x010000
@@ -329,7 +361,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 {
 	struct task_struct *tsk;
 	struct mm_struct *mm;
-	int fault, sig, code;
+	int fault, sig, code, major = 0;
 	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
@@ -368,6 +400,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 			die("Accessing user space memory outside uaccess.h routines", regs, esr);
 	}
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -391,24 +425,42 @@ retry:
 	}
 
 	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
+	major |= fault & VM_FAULT_MAJOR;
 
-	/*
-	 * If we need to retry but a fatal signal is pending, handle the
-	 * signal first. We do not need to release the mmap_sem because it
-	 * would already be released in __lock_page_or_retry in mm/filemap.c.
-	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
-		return 0;
+	if (fault & VM_FAULT_RETRY) {
+		/*
+		 * If we need to retry but a fatal signal is pending,
+		 * handle the signal first. We do not need to release
+		 * the mmap_sem because it would already be released
+		 * in __lock_page_or_retry in mm/filemap.c.
+		 */
+		if (fatal_signal_pending(current))
+			return 0;
+
+		/*
+		 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
+		 * starvation.
+		 */
+		if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
+			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			mm_flags |= FAULT_FLAG_TRIED;
+			goto retry;
+		}
+	}
+	up_read(&mm->mmap_sem);
 
 	/*
-	 * Major/minor page fault accounting is only done on the initial
-	 * attempt. If we go through a retry, it is extremely likely that the
-	 * page will be found in page cache at that point.
+	 * Handle the "normal" (no error) case first.
 	 */
-
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
-	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
+	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
+			      VM_FAULT_BADACCESS)))) {
+		/*
+		 * Major/minor page fault accounting is only done
+		 * once. If we go through a retry, it is extremely
+		 * likely that the page will be found in page cache at
+		 * that point.
+		 */
+		if (major) {
 			tsk->maj_flt++;
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
 				      addr);
@@ -417,25 +469,9 @@ retry:
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
 				      addr);
 		}
-		if (fault & VM_FAULT_RETRY) {
-			/*
-			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
-			 * starvation.
-			 */
-			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			mm_flags |= FAULT_FLAG_TRIED;
-			goto retry;
-		}
-	}
-
-	up_read(&mm->mmap_sem);
 
-	/*
-	 * Handle the "normal" case first - VM_FAULT_MAJOR
-	 */
-	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
-			      VM_FAULT_BADACCESS))))
 		return 0;
+	}
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
@@ -461,6 +497,9 @@ retry:
 		 */
 		sig = SIGBUS;
 		code = BUS_ADRERR;
+	} else if (fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
+		sig = SIGBUS;
+		code = BUS_MCEERR_AR;
 	} else {
 		/*
 		 * Something tried to access memory that isn't in our memory
@@ -471,11 +510,11 @@ retry:
 			SEGV_ACCERR : SEGV_MAPERR;
 	}
 
-	__do_user_fault(tsk, addr, esr, sig, code, regs);
+	__do_user_fault(tsk, addr, esr, sig, code, regs, fault);
 	return 0;
 
 no_context:
-	__do_kernel_fault(mm, addr, esr, regs);
+	__do_kernel_fault(addr, esr, regs);
 	return 0;
 }
 
@@ -522,6 +561,47 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
+/*
+ * This abort handler deals with Synchronous External Abort.
+ * It calls notifiers, and then returns "fault".
+ */
+static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+	struct siginfo info;
+	const struct fault_info *inf;
+	int ret = 0;
+
+	inf = esr_to_fault_info(esr);
+	pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
+		inf->name, esr, addr);
+
+	/*
+	 * Synchronous aborts may interrupt code which had interrupts masked.
+	 * Before calling out into the wider kernel tell the interested
+	 * subsystems.
+	 */
+	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
+		if (interrupts_enabled(regs))
+			nmi_enter();
+
+		ret = ghes_notify_sea();
+
+		if (interrupts_enabled(regs))
+			nmi_exit();
+	}
+
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code  = 0;
+	if (esr & ESR_ELx_FnV)
+		info.si_addr = NULL;
+	else
+		info.si_addr  = (void __user *)addr;
+	arm64_notify_die("", regs, &info, esr);
+
+	return ret;
+}
+
 static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
@@ -539,22 +619,22 @@ static const struct fault_info fault_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
+	{ do_sea,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
+	{ do_sea,		SIGBUS,  0,		"level 0 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 1 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 2 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 3 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },
 	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
@@ -590,6 +670,23 @@ static const struct fault_info fault_info[] = {
 };
 
 /*
+ * Handle Synchronous External Aborts that occur in a guest kernel.
+ *
+ * The return value will be zero if the SEA was successfully handled
+ * and non-zero if there was an error processing the error or there was
+ * no error to process.
+ */
+int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+{
+	int ret = -ENOENT;
+
+	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
+		ret = ghes_notify_sea();
+
+	return ret;
+}
+
+/*
  * Dispatch a data abort to the relevant handler.
  */
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 7514a000e361..69b8200b1cfd 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -136,36 +136,27 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd = NULL;
-	pte_t *pte = NULL;
+	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
 	if (!pgd_present(*pgd))
 		return NULL;
+
 	pud = pud_offset(pgd, addr);
-	if (!pud_present(*pud))
+	if (pud_none(*pud))
 		return NULL;
-
-	if (pud_huge(*pud))
+	/* swap or huge page */
+	if (!pud_present(*pud) || pud_huge(*pud))
 		return (pte_t *)pud;
+	/* table; check the next level */
+
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	if (pmd_none(*pmd))
 		return NULL;
-
-	if (pte_cont(pmd_pte(*pmd))) {
-		pmd = pmd_offset(
-			pud, (addr & CONT_PMD_MASK));
-		return (pte_t *)pmd;
-	}
-	if (pmd_huge(*pmd))
+	if (!pmd_present(*pmd) || pmd_huge(*pmd))
 		return (pte_t *)pmd;
-	pte = pte_offset_kernel(pmd, addr);
-	if (pte_present(*pte) && pte_cont(*pte)) {
-		pte = pte_offset_kernel(
-			pmd, (addr & CONT_PTE_MASK));
-		return pte;
-	}
+
 	return NULL;
 }
 
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 7b0d55756eb1..adc208c2ae9c 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -18,6 +18,7 @@
 
 #include <linux/elf.h>
 #include <linux/fs.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/export.h>
@@ -103,12 +104,18 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
  */
 int valid_phys_addr_range(phys_addr_t addr, size_t size)
 {
-	if (addr < PHYS_OFFSET)
-		return 0;
-	if (addr + size > __pa(high_memory - 1) + 1)
-		return 0;
-
-	return 1;
+	/*
+	 * Check whether addr is covered by a memory region without the
+	 * MEMBLOCK_NOMAP attribute, and whether that region covers the
+	 * entire range. In theory, this could lead to false negatives
+	 * if the range is covered by distinct but adjacent memory regions
+	 * that only differ in other attributes. However, few of such
+	 * attributes have been defined, and it is debatable whether it
+	 * follows that /dev/mem read() calls should be able traverse
+	 * such boundaries.
+	 */
+	return memblock_is_region_memory(addr, size) &&
+	       memblock_is_map_memory(addr);
 }
 
 /*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 0c429ec6fde8..23c2d89a362e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -31,6 +31,7 @@
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 2f0505b5c240..f32144b2e07f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -70,7 +70,7 @@ struct jit_ctx {
 	int idx;
 	int epilogue_offset;
 	int *offset;
-	u32 *image;
+	__le32 *image;
 	u32 stack_size;
 };
 
@@ -131,7 +131,7 @@ static inline int bpf2a64_offset(int bpf_to, int bpf_from,
 
 static void jit_fill_hole(void *area, unsigned int size)
 {
-	u32 *ptr;
+	__le32 *ptr;
 	/* We are guaranteed to have aligned memory. */
 	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
 		*ptr++ = cpu_to_le32(AARCH64_BREAK_FAULT);
@@ -874,7 +874,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	/* 2. Now, the actual pass. */
 
-	ctx.image = (u32 *)image_ptr;
+	ctx.image = (__le32 *)image_ptr;
 	ctx.idx = 0;
 
 	build_prologue(&ctx);