diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5d3b030e78e3..d96209b20736 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -91,7 +91,7 @@ config ARM
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !(THUMB2_KERNEL && CC_IS_CLANG)
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
@@ -126,6 +126,7 @@ config ARM
 	select PERF_USE_VMALLOC
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
+	select THREAD_INFO_IN_TASK if CURRENT_POINTER_IN_TPIDRURO
 	select TRACE_IRQFLAGS_SUPPORT if !CPU_V7M
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.
@@ -265,10 +266,12 @@ config PHYS_OFFSET
 	hex "Physical address of main memory" if MMU
 	depends on !ARM_PATCH_PHYS_VIRT
 	default DRAM_BASE if !MMU
-	default 0x00000000 if ARCH_FOOTBRIDGE
+	default 0x00000000 if ARCH_FOOTBRIDGE || ARCH_IXP4XX
 	default 0x10000000 if ARCH_OMAP1 || ARCH_RPC
-	default 0x20000000 if ARCH_S5PV210
-	default 0xc0000000 if ARCH_SA1100
+	default 0x30000000 if ARCH_S3C24XX
+	default 0xa0000000 if ARCH_IOP32X || ARCH_PXA
+	default 0xc0000000 if ARCH_EP93XX || ARCH_SA1100
+	default 0
 	help
 	  Please provide the physical address corresponding to the
 	  location of main memory in your system.
@@ -433,6 +436,7 @@ config ARCH_PXA
 config ARCH_RPC
 	bool "RiscPC"
 	depends on MMU
+	depends on !CC_IS_CLANG && GCC_VERSION < 90100 && GCC_VERSION >= 60000
 	select ARCH_ACORN
 	select ARCH_MAY_HAVE_PC_FDC
 	select ARCH_SPARSEMEM_ENABLE
@@ -1158,6 +1162,11 @@ config SMP_ON_UP
 
 	  If you don't know what to do here, say Y.
 
+
+config CURRENT_POINTER_IN_TPIDRURO
+	def_bool y
+	depends on SMP && CPU_32v6K && !CPU_V6
+
 config ARM_CPU_TOPOLOGY
 	bool "Support cpu topology definition"
 	depends on SMP && CPU_V7
@@ -1601,7 +1610,7 @@ config XEN
 
 config STACKPROTECTOR_PER_TASK
 	bool "Use a unique stack canary value for each task"
-	depends on GCC_PLUGINS && STACKPROTECTOR && SMP && !XIP_DEFLATED_DATA
+	depends on GCC_PLUGINS && STACKPROTECTOR && THREAD_INFO_IN_TASK && !XIP_DEFLATED_DATA
 	select GCC_PLUGIN_ARM_SSP_PER_TASK
 	default y
 	help
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 847c31e7c368..1c540157e283 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -113,6 +113,10 @@ ifeq ($(CONFIG_CC_IS_CLANG),y)
 CFLAGS_ABI	+= -meabi gnu
 endif
 
+ifeq ($(CONFIG_CURRENT_POINTER_IN_TPIDRURO),y)
+CFLAGS_ABI	+= -mtp=cp15
+endif
+
 # Accept old syntax despite ".syntax unified"
 AFLAGS_NOWARN	:=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
 
@@ -273,11 +277,8 @@ ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
 prepare: stack_protector_prepare
 stack_protector_prepare: prepare0
 	$(eval SSP_PLUGIN_CFLAGS := \
-		-fplugin-arg-arm_ssp_per_task_plugin-tso=$(shell	\
-			awk '{if ($$2 == "THREAD_SZ_ORDER") print $$3;}'\
-				include/generated/asm-offsets.h)	\
 		-fplugin-arg-arm_ssp_per_task_plugin-offset=$(shell	\
-			awk '{if ($$2 == "TI_STACK_CANARY") print $$3;}'\
+			awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}'\
 				include/generated/asm-offsets.h))
 	$(eval KBUILD_CFLAGS += $(SSP_PLUGIN_CFLAGS))
 	$(eval GCC_PLUGINS_CFLAGS += $(SSP_PLUGIN_CFLAGS))
diff --git a/arch/arm/boot/compressed/fdt_check_mem_start.c b/arch/arm/boot/compressed/fdt_check_mem_start.c
index 62450d824c3c..9291a2661bdf 100644
--- a/arch/arm/boot/compressed/fdt_check_mem_start.c
+++ b/arch/arm/boot/compressed/fdt_check_mem_start.c
@@ -55,16 +55,17 @@ static uint64_t get_val(const fdt32_t *cells, uint32_t ncells)
  * DTB, and, if out-of-range, replace it by the real start address.
  * To preserve backwards compatibility (systems reserving a block of memory
  * at the start of physical memory, kdump, ...), the traditional method is
- * always used if it yields a valid address.
+ * used if it yields a valid address, unless the "linux,usable-memory-range"
+ * property is present.
  *
  * Return value: start address of physical memory to use
  */
 uint32_t fdt_check_mem_start(uint32_t mem_start, const void *fdt)
 {
-	uint32_t addr_cells, size_cells, base;
+	uint32_t addr_cells, size_cells, usable_base, base;
 	uint32_t fdt_mem_start = 0xffffffff;
-	const fdt32_t *reg, *endp;
-	uint64_t size, end;
+	const fdt32_t *usable, *reg, *endp;
+	uint64_t size, usable_end, end;
 	const char *type;
 	int offset, len;
 
@@ -80,6 +81,27 @@ uint32_t fdt_check_mem_start(uint32_t mem_start, const void *fdt)
 	if (addr_cells > 2 || size_cells > 2)
 		return mem_start;
 
+	/*
+	 * Usable memory in case of a crash dump kernel
+	 * This property describes a limitation: memory within this range is
+	 * only valid when also described through another mechanism
+	 */
+	usable = get_prop(fdt, "/chosen", "linux,usable-memory-range",
+			  (addr_cells + size_cells) * sizeof(fdt32_t));
+	if (usable) {
+		size = get_val(usable + addr_cells, size_cells);
+		if (!size)
+			return mem_start;
+
+		if (addr_cells > 1 && fdt32_ld(usable)) {
+			/* Outside 32-bit address space */
+			return mem_start;
+		}
+
+		usable_base = fdt32_ld(usable + addr_cells - 1);
+		usable_end = usable_base + size;
+	}
+
 	/* Walk all memory nodes and regions */
 	for (offset = fdt_next_node(fdt, -1, NULL); offset >= 0;
 	     offset = fdt_next_node(fdt, offset, NULL)) {
@@ -107,7 +129,20 @@ uint32_t fdt_check_mem_start(uint32_t mem_start, const void *fdt)
 
 			base = fdt32_ld(reg + addr_cells - 1);
 			end = base + size;
-			if (mem_start >= base && mem_start < end) {
+			if (usable) {
+				/*
+				 * Clip to usable range, which takes precedence
+				 * over mem_start
+				 */
+				if (base < usable_base)
+					base = usable_base;
+
+				if (end > usable_end)
+					end = usable_end;
+
+				if (end <= base)
+					continue;
+			} else if (mem_start >= base && mem_start < end) {
 				/* Calculated address is valid, use it */
 				return mem_start;
 			}
@@ -123,7 +158,8 @@ uint32_t fdt_check_mem_start(uint32_t mem_start, const void *fdt)
 	}
 
 	/*
-	 * The calculated address is not usable.
+	 * The calculated address is not usable, or was overridden by the
+	 * "linux,usable-memory-range" property.
 	 * Use the lowest usable physical memory address from the DTB instead,
 	 * and make sure this is a multiple of 2 MiB for phys/virt patching.
 	 */
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index 6edb961bd6c1..e74c5bfdc6d3 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -240,9 +240,6 @@ static int scoop_remove(struct platform_device *pdev)
 {
 	struct scoop_dev *sdev = platform_get_drvdata(pdev);
 
-	if (!sdev)
-		return -EINVAL;
-
 	if (sdev->gpio.base != -1)
 		gpiochip_remove(&sdev->gpio);
 
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index e2b1fd558bf3..7d23d4bb2168 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -199,14 +199,43 @@
 	.endm
 	.endr
 
+	.macro	get_current, rd
+#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+	mrc	p15, 0, \rd, c13, c0, 3		@ get TPIDRURO register
+#else
+	get_thread_info \rd
+	ldr	\rd, [\rd, #TI_TASK]
+#endif
+	.endm
+
+	.macro	set_current, rn
+#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+	mcr	p15, 0, \rn, c13, c0, 3		@ set TPIDRURO register
+#endif
+	.endm
+
+	.macro	reload_current, t1:req, t2:req
+#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+	adr_l	\t1, __entry_task		@ get __entry_task base address
+	mrc	p15, 0, \t2, c13, c0, 4		@ get per-CPU offset
+	ldr	\t1, [\t1, \t2]			@ load variable
+	mcr	p15, 0, \t1, c13, c0, 3		@ store in TPIDRURO
+#endif
+	.endm
+
 /*
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	/* thread_info is the first member of struct task_struct */
+	get_current \rd
+#else
  ARM(	mov	\rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT	)
  THUMB(	mov	\rd, sp			)
  THUMB(	lsr	\rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT	)
 	mov	\rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
+#endif
 	.endm
 
 /*
diff --git a/arch/arm/include/asm/current.h b/arch/arm/include/asm/current.h
new file mode 100644
index 000000000000..6bf0aad672c3
--- /dev/null
+++ b/arch/arm/include/asm/current.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Keith Packard <keithp@keithp.com>
+ * Copyright (c) 2021 Google, LLC <ardb@kernel.org>
+ */
+
+#ifndef _ASM_ARM_CURRENT_H
+#define _ASM_ARM_CURRENT_H
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+static inline void set_current(struct task_struct *cur)
+{
+	if (!IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO))
+		return;
+
+	/* Set TPIDRURO */
+	asm("mcr p15, 0, %0, c13, c0, 3" :: "r"(cur) : "memory");
+}
+
+#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+
+static inline struct task_struct *get_current(void)
+{
+	struct task_struct *cur;
+
+#if __has_builtin(__builtin_thread_pointer) && \
+    !(defined(CONFIG_THUMB2_KERNEL) && \
+      defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 130001)
+	/*
+	 * Use the __builtin helper when available - this results in better
+	 * code, especially when using GCC in combination with the per-task
+	 * stack protector, as the compiler will recognize that it needs to
+	 * load the TLS register only once in every function.
+	 *
+	 * Clang < 13.0.1 gets this wrong for Thumb2 builds:
+	 * https://github.com/ClangBuiltLinux/linux/issues/1485
+	 */
+	cur = __builtin_thread_pointer();
+#else
+	asm("mrc p15, 0, %0, c13, c0, 3" : "=r"(cur));
+#endif
+	return cur;
+}
+
+#define current get_current()
+#else
+#include <asm-generic/current.h>
+#endif /* CONFIG_CURRENT_POINTER_IN_TPIDRURO */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_ARM_CURRENT_H */
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index f74944c6fe8d..c576fa7d9bf8 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -138,6 +138,7 @@ extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
+void __arm_iomem_set_ro(void __iomem *ptr, size_t size);
 extern void __iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h
index 6bff94b2372b..38e3eabff5c3 100644
--- a/arch/arm/include/asm/opcodes.h
+++ b/arch/arm/include/asm/opcodes.h
@@ -110,12 +110,17 @@ extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr);
 #define __opcode_to_mem_thumb16(x) ___opcode_identity16(x)
 #define ___asm_opcode_to_mem_arm(x) ___asm_opcode_identity32(x)
 #define ___asm_opcode_to_mem_thumb16(x) ___asm_opcode_identity16(x)
-#ifndef CONFIG_CPU_ENDIAN_BE32
+#ifdef CONFIG_CPU_ENDIAN_BE32
+#ifndef __ASSEMBLY__
 /*
  * On BE32 systems, using 32-bit accesses to store Thumb instructions will not
  * work in all cases, due to alignment constraints.  For now, a correct
- * version is not provided for BE32.
+ * version is not provided for BE32, but the prototype needs to be there
+ * to compile patch.c.
  */
+extern __u32 __opcode_to_mem_thumb32(__u32);
+#endif
+#else
 #define __opcode_to_mem_thumb32(x) ___opcode_swahw32(x)
 #define ___asm_opcode_to_mem_thumb32(x) ___asm_opcode_swahw32(x)
 #endif
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 3ae68a1b3de6..ba0872a8dcda 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -19,7 +19,7 @@
 static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
 extern int arm_add_memory(u64 start, u64 size);
-extern void early_print(const char *str, ...);
+extern __printf(1, 2) void early_print(const char *str, ...);
 extern void dump_machine_table(void);
 
 #ifdef CONFIG_ATAGS_PROC
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 5d508f5d56c4..f16cbbd5cda4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -48,7 +48,7 @@ extern void set_smp_ipi_range(int ipi_base, int nr_ipi);
  * Called from platform specific assembly code, this is the
  * secondary CPU entry point.
  */
-asmlinkage void secondary_start_kernel(void);
+asmlinkage void secondary_start_kernel(struct task_struct *task);
 
 
 /*
@@ -61,6 +61,7 @@ struct secondary_data {
 	};
 	unsigned long swapper_pg_dir;
 	void *stack;
+	struct task_struct *task;
 };
 extern struct secondary_data secondary_data;
 extern void secondary_startup(void);
diff --git a/arch/arm/include/asm/stackprotector.h b/arch/arm/include/asm/stackprotector.h
index 72a20c3a0a90..088d03161be5 100644
--- a/arch/arm/include/asm/stackprotector.h
+++ b/arch/arm/include/asm/stackprotector.h
@@ -39,8 +39,6 @@ static __always_inline void boot_init_stack_canary(void)
 	current->stack_canary = canary;
 #ifndef CONFIG_STACKPROTECTOR_PER_TASK
 	__stack_chk_guard = current->stack_canary;
-#else
-	current_thread_info()->stack_canary = current->stack_canary;
 #endif
 }
 
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index 007d8fea7157..b55c7b2755e4 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -23,9 +23,25 @@
  */
 extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);
 
+static inline void set_ti_cpu(struct task_struct *p)
+{
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	/*
+	 * The core code no longer maintains the thread_info::cpu field once
+	 * CONFIG_THREAD_INFO_IN_TASK is in effect, but we rely on it for
+	 * raw_smp_processor_id(), which cannot access struct task_struct*
+	 * directly for reasons of circular #inclusion hell.
+	 */
+	task_thread_info(p)->cpu = task_cpu(p);
+#endif
+}
+
 #define switch_to(prev,next,last)					\
 do {									\
 	__complete_pending_tlbi();					\
+	set_ti_cpu(next);						\
+	if (IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO))		\
+		__this_cpu_write(__entry_task, next);			\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 9a18da3e10cc..164e15f26485 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -29,6 +29,8 @@
 
 struct task_struct;
 
+DECLARE_PER_CPU(struct task_struct *, __entry_task);
+
 #include <asm/types.h>
 
 struct cpu_context_save {
@@ -52,12 +54,11 @@ struct cpu_context_save {
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
+#ifndef CONFIG_THREAD_INFO_IN_TASK
 	struct task_struct	*task;		/* main task structure */
+#endif
 	__u32			cpu;		/* cpu */
 	__u32			cpu_domain;	/* cpu domain */
-#ifdef CONFIG_STACKPROTECTOR_PER_TASK
-	unsigned long		stack_canary;
-#endif
 	struct cpu_context_save	cpu_context;	/* cpu context */
 	__u32			abi_syscall;	/* ABI type and syscall nr */
 	__u8			used_cp[16];	/* thread used copro */
@@ -71,11 +72,27 @@ struct thread_info {
 
 #define INIT_THREAD_INFO(tsk)						\
 {									\
-	.task		= &tsk,						\
+	INIT_THREAD_INFO_TASK(tsk)					\
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 }
 
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+#define INIT_THREAD_INFO_TASK(tsk)
+
+static inline struct task_struct *thread_task(struct thread_info* ti)
+{
+	return (struct task_struct *)ti;
+}
+
+#else
+#define INIT_THREAD_INFO_TASK(tsk)	.task = &(tsk),
+
+static inline struct task_struct *thread_task(struct thread_info* ti)
+{
+	return ti->task;
+}
+
 /*
  * how to get the thread information struct from C
  */
@@ -86,6 +103,7 @@ static inline struct thread_info *current_thread_info(void)
 	return (struct thread_info *)
 		(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
+#endif
 
 #define thread_saved_pc(tsk)	\
 	((unsigned long)(task_thread_info(tsk)->cpu_context.pc))
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 5a66c3b13c92..c3296499176c 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -12,8 +12,8 @@
 
 	.macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2
 	mrc	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
-	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
-	mcr	p15, 0, \tpuser, c13, c0, 2	@ and the user r/w register
+	@ TLS register update is deferred until return to user space
+	mcr	p15, 0, \tpuser, c13, c0, 2	@ set the user r/w register
 	str	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm
 
@@ -38,18 +38,22 @@
 #ifdef CONFIG_TLS_REG_EMUL
 #define tls_emu		1
 #define has_tls_reg		1
+#define defer_tls_reg_update	0
 #define switch_tls	switch_tls_none
 #elif defined(CONFIG_CPU_V6)
 #define tls_emu		0
 #define has_tls_reg		(elf_hwcap & HWCAP_TLS)
+#define defer_tls_reg_update	0
 #define switch_tls	switch_tls_v6
 #elif defined(CONFIG_CPU_32v6K)
 #define tls_emu		0
 #define has_tls_reg		1
+#define defer_tls_reg_update	1
 #define switch_tls	switch_tls_v6k
 #else
 #define tls_emu		0
 #define has_tls_reg		0
+#define defer_tls_reg_update	0
 #define switch_tls	switch_tls_software
 #endif
 
@@ -77,7 +81,7 @@ static inline void set_tls(unsigned long val)
 	 */
 	barrier();
 
-	if (!tls_emu) {
+	if (!tls_emu && !defer_tls_reg_update) {
 		if (has_tls_reg) {
 			asm("mcr p15, 0, %0, c13, c0, 3"
 			    : : "r" (val));
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index a646a3f6440f..645845e4982a 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -43,7 +43,9 @@ int main(void)
   BLANK();
   DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
+#ifndef CONFIG_THREAD_INFO_IN_TASK
   DEFINE(TI_TASK,		offsetof(struct thread_info, task));
+#endif
   DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
   DEFINE(TI_CPU_DOMAIN,		offsetof(struct thread_info, cpu_domain));
   DEFINE(TI_CPU_SAVE,		offsetof(struct thread_info, cpu_context));
@@ -63,10 +65,6 @@ int main(void)
 #ifdef CONFIG_IWMMXT
   DEFINE(TI_IWMMXT_STATE,	offsetof(struct thread_info, fpstate.iwmmxt));
 #endif
-#ifdef CONFIG_STACKPROTECTOR_PER_TASK
-  DEFINE(TI_STACK_CANARY,	offsetof(struct thread_info, stack_canary));
-#endif
-  DEFINE(THREAD_SZ_ORDER,	THREAD_SIZE_ORDER);
   BLANK();
   DEFINE(S_R0,			offsetof(struct pt_regs, ARM_r0));
   DEFINE(S_R1,			offsetof(struct pt_regs, ARM_r1));
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 3d0b6169ab86..deff286eb5ea 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -381,6 +381,8 @@ ENDPROC(__fiq_abt)
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
 
+	reload_current r7, r8
+
 	@
 	@ Clear FP to mark the first stack frame
 	@
@@ -759,6 +761,8 @@ ENTRY(__switch_to)
 	add	r7, r7, #TSK_STACK_CANARY & ~IMM12_MASK
 	.endif
 	ldr	r7, [r7, #TSK_STACK_CANARY & IMM12_MASK]
+#elif defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO)
+	mov	r7, r2				@ Preserve 'next'
 #endif
 #ifdef CONFIG_CPU_USE_DOMAINS
 	mcr	p15, 0, r6, c3, c0, 0		@ Set domain register
@@ -773,6 +777,7 @@ ENTRY(__switch_to)
 #endif
  THUMB(	mov	ip, r4			   )
 	mov	r0, r5
+	set_current r7
  ARM(	ldmia	r4, {r4 - sl, fp, sp, pc}  )	@ Load all regs saved previously
  THUMB(	ldmia	ip!, {r4 - sl, fp}	   )	@ Load all regs saved previously
  THUMB(	ldr	sp, [ip], #4		   )
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index d9c99db50243..ac86c34682bb 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -170,6 +170,7 @@ ENTRY(vector_swi)
 	str	saved_psr, [sp, #S_PSR]		@ Save CPSR
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
 #endif
+	reload_current r10, ip
 	zero_fp
 	alignment_trap r10, ip, __cr_alignment
 	asm_trace_hardirqs_on save=0
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 40db0f9188b6..ae24dd54e9ef 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -292,6 +292,14 @@
 
 
 	.macro	restore_user_regs, fast = 0, offset = 0
+#if defined(CONFIG_CPU_32v6K) && !defined(CONFIG_CPU_V6)
+	@ The TLS register update is deferred until return to user space so we
+	@ can use it for other things while running in the kernel
+	get_thread_info r1
+	ldr	r1, [r1, #TI_TP_VALUE]
+	mcr	p15, 0, r1, c13, c0, 3		@ set TLS register
+#endif
+
 	uaccess_enable r1, isb=0
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 29b2eda136bb..da18e0a17dc2 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -105,6 +105,11 @@ __mmap_switched:
 	mov	r1, #0
 	bl	__memset			@ clear .bss
 
+#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+	adr_l	r0, init_task			@ get swapper task_struct
+	set_current r0
+#endif
+
 	ldmia	r4, {r0, r1, r2, r3}
 	str	r9, [r0]			@ Save processor ID
 	str	r7, [r1]			@ Save machine type
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 0fc814bbc34b..fadfee9e2b45 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -115,6 +115,7 @@ ENTRY(secondary_startup)
 	ret	r12
 1:	bl	__after_proc_init
 	ldr	sp, [r7, #12]			@ set up the stack pointer
+	ldr	r0, [r7, #16]			@ set up task pointer
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(secondary_startup)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 3fc7f9750ce4..c04dd94630c7 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -424,8 +424,9 @@ ENDPROC(secondary_startup)
 ENDPROC(secondary_startup_arm)
 
 ENTRY(__secondary_switched)
-	ldr_l	r7, secondary_data + 12		@ get secondary_data.stack
-	mov	sp, r7
+	adr_l	r7, secondary_data + 12		@ get secondary_data.stack
+	ldr	sp, [r7]
+	ldr	r0, [r7, #4]			@ get secondary_data.task
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 96f577e59595..d47159f3791c 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -36,6 +36,10 @@
 
 #include "signal.h"
 
+#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+DEFINE_PER_CPU(struct task_struct *, __entry_task);
+#endif
+
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
 unsigned long __stack_chk_guard __read_mostly;
@@ -269,10 +273,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	thread_notify(THREAD_NOTIFY_COPY, thread);
 
-#ifdef CONFIG_STACKPROTECTOR_PER_TASK
-	thread->stack_canary = p->stack_canary;
-#endif
-
 	return 0;
 }
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 842427ff2b3c..cde5b6d8bac5 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -153,6 +153,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	secondary_data.pgdir = virt_to_phys(idmap_pgd);
 	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
+	secondary_data.task = idle;
+	if (IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK))
+		task_thread_info(idle)->cpu = cpu;
+
 	sync_cache_w(&secondary_data);
 
 	/*
@@ -375,9 +379,12 @@ void arch_cpu_idle_dead(void)
 	 */
 	__asm__("mov	sp, %0\n"
 	"	mov	fp, #0\n"
+	"	mov	r0, %1\n"
 	"	b	secondary_start_kernel"
 		:
-		: "r" (task_stack_page(current) + THREAD_SIZE - 8));
+		: "r" (task_stack_page(current) + THREAD_SIZE - 8),
+		  "r" (current)
+		: "r0");
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -400,11 +407,13 @@ static void smp_store_cpu_info(unsigned int cpuid)
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
  */
-asmlinkage void secondary_start_kernel(void)
+asmlinkage void secondary_start_kernel(struct task_struct *task)
 {
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu;
 
+	set_current(task);
+
 	secondary_biglittle_init();
 
 	/*
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index f14c2360ea0b..76678732c60d 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -166,7 +166,9 @@ SECTIONS
  * binutils is too old (for other reasons as well)
  */
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
+#ifndef CONFIG_COMPILE_TEST
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
+#endif
 
 #ifdef CONFIG_XIP_DEFLATED_DATA
 /*
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 20c4f6d20c7a..f02d617e3359 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -174,6 +174,8 @@ __start_rodata_section_aligned = ALIGN(__start_rodata, 1 << SECTION_SHIFT);
  * binutils is too old (for other reasons as well)
  */
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
+#ifndef CONFIG_COMPILE_TEST
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
+#endif
 
 #endif /* CONFIG_XIP_KERNEL */
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index f2ecca339910..045b9fdd342d 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -572,6 +572,8 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 		&imx6_suspend,
 		MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info));
 
+	__arm_iomem_set_ro(suspend_ocram_base, MX6Q_SUSPEND_OCRAM_SIZE);
+
 	goto put_device;
 
 pl310_cache_map_failed:
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 2012fa8c28cf..9919e0f32c4b 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -84,7 +84,7 @@ void ASSABET_BCR_frob(unsigned int mask, unsigned int val)
 }
 EXPORT_SYMBOL(ASSABET_BCR_frob);
 
-static int __init assabet_init_gpio(void __iomem *reg, u32 def_val)
+static void __init assabet_init_gpio(void __iomem *reg, u32 def_val)
 {
 	struct gpio_chip *gc;
 
@@ -94,11 +94,9 @@ static int __init assabet_init_gpio(void __iomem *reg, u32 def_val)
 			   assabet_names, NULL, NULL);
 
 	if (IS_ERR(gc))
-		return PTR_ERR(gc);
+		return;
 
 	assabet_bcr_gc = gc;
-
-	return gc->base;
 }
 
 /*
@@ -475,16 +473,23 @@ static struct gpiod_lookup_table assabet_cf_vcc_gpio_table = {
 	},
 };
 
+static struct gpiod_lookup_table assabet_leds_gpio_table = {
+	.dev_id = "leds-gpio",
+	.table = {
+		GPIO_LOOKUP("assabet", 13, NULL, GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("assabet", 14, NULL, GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
 static struct gpio_led assabet_leds[] __initdata = {
 	{
 		.name = "assabet:red",
 		.default_trigger = "cpu0",
-		.active_low = 1,
 		.default_state = LEDS_GPIO_DEFSTATE_KEEP,
 	}, {
 		.name = "assabet:green",
 		.default_trigger = "heartbeat",
-		.active_low = 1,
 		.default_state = LEDS_GPIO_DEFSTATE_KEEP,
 	},
 };
@@ -603,6 +608,7 @@ static void __init assabet_init(void)
 					  &assabet_keys_pdata,
 					  sizeof(assabet_keys_pdata));
 
+	gpiod_add_lookup_table(&assabet_leds_gpio_table);
 	gpio_led_register_device(-1, &assabet_leds_pdata);
 
 #ifndef ASSABET_PAL_VIDEO
@@ -739,7 +745,6 @@ static void __init assabet_map_io(void)
 
 void __init assabet_init_irq(void)
 {
-	unsigned int assabet_gpio_base;
 	u32 def_val;
 
 	sa1100_init_irq();
@@ -754,10 +759,7 @@ void __init assabet_init_irq(void)
 	 *
 	 * This must precede any driver calls to BCR_set() or BCR_clear().
 	 */
-	assabet_gpio_base = assabet_init_gpio((void *)&ASSABET_BCR, def_val);
-
-	assabet_leds[0].gpio = assabet_gpio_base + 13;
-	assabet_leds[1].gpio = assabet_gpio_base + 14;
+	assabet_init_gpio((void *)&ASSABET_BCR, def_val);
 }
 
 MACHINE_START(ASSABET, "Intel-Assabet")
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 8355c3895894..58afba346729 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -675,7 +675,7 @@ config ARM_PV_FIXUP
 
 config ARM_THUMB
 	bool "Support Thumb user binaries" if !CPU_THUMBONLY && EXPERT
-	depends on CPU_THUMB_CAPABLE
+	depends on CPU_THUMB_CAPABLE && !CPU_32v4
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
@@ -750,7 +750,7 @@ config CPU_BIG_ENDIAN
 config CPU_ENDIAN_BE8
 	bool
 	depends on CPU_BIG_ENDIAN
-	default CPU_V6 || CPU_V6K || CPU_V7
+	default CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M
 	help
 	  Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
 
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index b7525b433f3e..48091870db89 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -109,7 +109,7 @@ static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd,
 	if (cmd != THREAD_NOTIFY_SWITCH)
 		return NOTIFY_DONE;
 
-	pid = task_pid_nr(thread->task) << ASID_BITS;
+	pid = task_pid_nr(thread_task(thread)) << ASID_BITS;
 	asm volatile(
 	"	mrc	p15, 0, %0, c13, c0, 1\n"
 	"	and	%0, %0, %2\n"
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index efa402025031..bc8779d54a64 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -37,7 +37,6 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 	if (!mm)
 		mm = &init_mm;
 
-	printk("%spgd = %p\n", lvl, mm->pgd);
 	pgd = pgd_offset(mm, addr);
 	printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
 
@@ -100,6 +99,21 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 { }
 #endif					/* CONFIG_MMU */
 
+static void die_kernel_fault(const char *msg, struct mm_struct *mm,
+			     unsigned long addr, unsigned int fsr,
+			     struct pt_regs *regs)
+{
+	bust_spinlocks(1);
+	pr_alert("8<--- cut here ---\n");
+	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
+		 msg, addr);
+
+	show_pte(KERN_ALERT, mm, addr);
+	die("Oops", regs, fsr);
+	bust_spinlocks(0);
+	do_exit(SIGKILL);
+}
+
 /*
  * Oops.  The kernel tried to access some page that wasn't present.
  */
@@ -107,6 +121,7 @@ static void
 __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 		  struct pt_regs *regs)
 {
+	const char *msg;
 	/*
 	 * Are we prepared to handle this kernel fault?
 	 */
@@ -116,16 +131,12 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 	/*
 	 * No handler, we'll have to terminate things with extreme prejudice.
 	 */
-	bust_spinlocks(1);
-	pr_alert("8<--- cut here ---\n");
-	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
-		 (addr < PAGE_SIZE) ? "NULL pointer dereference" :
-		 "paging request", addr);
+	if (addr < PAGE_SIZE)
+		msg = "NULL pointer dereference";
+	else
+		msg = "paging request";
 
-	show_pte(KERN_ALERT, mm, addr);
-	die("Oops", regs, fsr);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
+	die_kernel_fault(msg, mm, addr, fsr, regs);
 }
 
 /*
@@ -183,73 +194,58 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 #define VM_FAULT_BADMAP		0x010000
 #define VM_FAULT_BADACCESS	0x020000
 
-/*
- * Check that the permissions on the VMA allow for the fault which occurred.
- * If we encountered a write fault, we must have write permission, otherwise
- * we allow any permission.
- */
-static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
+static inline bool is_permission_fault(unsigned int fsr)
 {
-	unsigned int mask = VM_ACCESS_FLAGS;
-
-	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
-		mask = VM_WRITE;
-	if (fsr & FSR_LNX_PF)
-		mask = VM_EXEC;
-
-	return vma->vm_flags & mask ? false : true;
+	int fs = fsr_fs(fsr);
+#ifdef CONFIG_ARM_LPAE
+	if ((fs & FS_PERM_NOLL_MASK) == FS_PERM_NOLL)
+		return true;
+#else
+	if (fs == FS_L1_PERM || fs == FS_L2_PERM)
+		return true;
+#endif
+	return false;
 }
 
 static vm_fault_t __kprobes
-__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		unsigned int flags, struct task_struct *tsk,
-		struct pt_regs *regs)
+__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int flags,
+		unsigned long vma_flags, struct pt_regs *regs)
 {
-	struct vm_area_struct *vma;
-	vm_fault_t fault;
-
-	vma = find_vma(mm, addr);
-	fault = VM_FAULT_BADMAP;
+	struct vm_area_struct *vma = find_vma(mm, addr);
 	if (unlikely(!vma))
-		goto out;
-	if (unlikely(vma->vm_start > addr))
-		goto check_stack;
+		return VM_FAULT_BADMAP;
 
-	/*
-	 * Ok, we have a good vm_area for this
-	 * memory access, so we can handle it.
-	 */
-good_area:
-	if (access_error(fsr, vma)) {
-		fault = VM_FAULT_BADACCESS;
-		goto out;
+	if (unlikely(vma->vm_start > addr)) {
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			return VM_FAULT_BADMAP;
+		if (addr < FIRST_USER_ADDRESS)
+			return VM_FAULT_BADMAP;
+		if (expand_stack(vma, addr))
+			return VM_FAULT_BADMAP;
 	}
 
-	return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
+	/*
+	 * ok, we have a good vm_area for this memory access, check the
+	 * permissions on the VMA allow for the fault which occurred.
+	 */
+	if (!(vma->vm_flags & vma_flags))
+		return VM_FAULT_BADACCESS;
 
-check_stack:
-	/* Don't allow expansion below FIRST_USER_ADDRESS */
-	if (vma->vm_flags & VM_GROWSDOWN &&
-	    addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr))
-		goto good_area;
-out:
-	return fault;
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
 }
 
 static int __kprobes
 do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
-	struct task_struct *tsk;
-	struct mm_struct *mm;
+	struct mm_struct *mm = current->mm;
 	int sig, code;
 	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_DEFAULT;
+	unsigned long vm_flags = VM_ACCESS_FLAGS;
 
 	if (kprobe_page_fault(regs, fsr))
 		return 0;
 
-	tsk = current;
-	mm  = tsk->mm;
 
 	/* Enable interrupts if they were enabled in the parent context. */
 	if (interrupts_enabled(regs))
@@ -264,8 +260,19 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
+
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) {
 		flags |= FAULT_FLAG_WRITE;
+		vm_flags = VM_WRITE;
+	}
+
+	if (fsr & FSR_LNX_PF) {
+		vm_flags = VM_EXEC;
+
+		if (is_permission_fault(fsr) && !user_mode(regs))
+			die_kernel_fault("execution of memory",
+					 mm, addr, fsr, regs);
+	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
@@ -293,7 +300,7 @@ retry:
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs);
+	fault = __do_page_fault(mm, addr, flags, vm_flags, regs);
 
 	/* If we need to retry but a fatal signal is pending, handle the
 	 * signal first. We do not need to release the mmap_lock because
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index 9ecc2097a87a..83b5ab32d7a4 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -14,6 +14,8 @@
 
 #ifdef CONFIG_ARM_LPAE
 #define FSR_FS_AEA		17
+#define FS_PERM_NOLL		0xC
+#define FS_PERM_NOLL_MASK	0x3C
 
 static inline int fsr_fs(unsigned int fsr)
 {
@@ -21,6 +23,8 @@ static inline int fsr_fs(unsigned int fsr)
 }
 #else
 #define FSR_FS_AEA		22
+#define FS_L1_PERM             0xD
+#define FS_L2_PERM             0xF
 
 static inline int fsr_fs(unsigned int fsr)
 {
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 80fb5a4a5c05..6e830b9418c9 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -36,6 +36,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
+#include <asm/set_memory.h>
 #include <asm/system_info.h>
 
 #include <asm/mach/map.h>
@@ -401,6 +402,11 @@ __arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
 			__builtin_return_address(0));
 }
 
+void __arm_iomem_set_ro(void __iomem *ptr, size_t size)
+{
+	set_memory_ro((unsigned long)ptr, PAGE_ALIGN(size) / PAGE_SIZE);
+}
+
 void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
 {
 	return (__force void *)arch_ioremap_caller(phys_addr, size,
diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c
index 9c348042a724..4b1619584b23 100644
--- a/arch/arm/mm/kasan_init.c
+++ b/arch/arm/mm/kasan_init.c
@@ -226,7 +226,7 @@ void __init kasan_init(void)
 	BUILD_BUG_ON(pgd_index(KASAN_SHADOW_START) !=
 		     pgd_index(KASAN_SHADOW_END));
 	memcpy(tmp_pmd_table,
-	       pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_START)),
+	       (void*)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_START)),
 	       sizeof(tmp_pmd_table));
 	set_pgd(&tmp_pgd_table[pgd_index(KASAN_SHADOW_START)],
 		__pgd(__pa(tmp_pmd_table) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index d9f7dfe2a7ed..fa6999e24b07 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -30,8 +30,7 @@
  * act_mm - get current->active_mm
  */
 	.macro	act_mm, rd
-	get_thread_info \rd
-	ldr	\rd, [\rd, #TI_TASK]
+	get_current \rd
 	.if (TSK_ACTIVE_MM > IMM12_MASK)
 	add	\rd, \rd, #TSK_ACTIVE_MM & ~IMM12_MASK
 	.endif
diff --git a/arch/arm/probes/kprobes/test-core.h b/arch/arm/probes/kprobes/test-core.h
index f1d5583e7bbb..56ad3c0aaeea 100644
--- a/arch/arm/probes/kprobes/test-core.h
+++ b/arch/arm/probes/kprobes/test-core.h
@@ -98,7 +98,7 @@ struct test_arg_end {
 #if VERBOSE
 #define verbose(fmt, ...) pr_info(fmt, ##__VA_ARGS__)
 #else
-#define verbose(fmt, ...)
+#define verbose(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 #define TEST_GROUP(title)					\
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 962041148482..720aa6cdd402 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -19,6 +19,7 @@
 #include <linux/clk/clk-conf.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
+#include <linux/of_irq.h>
 
 #include <asm/irq.h>
 
@@ -371,14 +372,37 @@ static void amba_device_release(struct device *dev)
 	kfree(d);
 }
 
+static int of_amba_device_decode_irq(struct amba_device *dev)
+{
+	struct device_node *node = dev->dev.of_node;
+	int i, irq = 0;
+
+	if (IS_ENABLED(CONFIG_OF_IRQ) && node) {
+		/* Decode the IRQs and address ranges */
+		for (i = 0; i < AMBA_NR_IRQS; i++) {
+			irq = of_irq_get(node, i);
+			if (irq < 0) {
+				if (irq == -EPROBE_DEFER)
+					return irq;
+				irq = 0;
+			}
+
+			dev->irq[i] = irq;
+		}
+	}
+
+	return 0;
+}
+
 static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 {
 	u32 size;
 	void __iomem *tmp;
 	int i, ret;
 
-	WARN_ON(dev->irq[0] == (unsigned int)-1);
-	WARN_ON(dev->irq[1] == (unsigned int)-1);
+	ret = of_amba_device_decode_irq(dev);
+	if (ret)
+		goto err_out;
 
 	ret = request_resource(parent, &dev->res);
 	if (ret)
@@ -579,78 +603,6 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 }
 EXPORT_SYMBOL_GPL(amba_device_add);
 
-static struct amba_device *
-amba_aphb_device_add(struct device *parent, const char *name,
-		     resource_size_t base, size_t size, int irq1, int irq2,
-		     void *pdata, unsigned int periphid, u64 dma_mask,
-		     struct resource *resbase)
-{
-	struct amba_device *dev;
-	int ret;
-
-	dev = amba_device_alloc(name, base, size);
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	dev->dev.coherent_dma_mask = dma_mask;
-	dev->irq[0] = irq1;
-	dev->irq[1] = irq2;
-	dev->periphid = periphid;
-	dev->dev.platform_data = pdata;
-	dev->dev.parent = parent;
-
-	ret = amba_device_add(dev, resbase);
-	if (ret) {
-		amba_device_put(dev);
-		return ERR_PTR(ret);
-	}
-
-	return dev;
-}
-
-struct amba_device *
-amba_apb_device_add(struct device *parent, const char *name,
-		    resource_size_t base, size_t size, int irq1, int irq2,
-		    void *pdata, unsigned int periphid)
-{
-	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
-				    periphid, 0, &iomem_resource);
-}
-EXPORT_SYMBOL_GPL(amba_apb_device_add);
-
-struct amba_device *
-amba_ahb_device_add(struct device *parent, const char *name,
-		    resource_size_t base, size_t size, int irq1, int irq2,
-		    void *pdata, unsigned int periphid)
-{
-	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
-				    periphid, ~0ULL, &iomem_resource);
-}
-EXPORT_SYMBOL_GPL(amba_ahb_device_add);
-
-struct amba_device *
-amba_apb_device_add_res(struct device *parent, const char *name,
-			resource_size_t base, size_t size, int irq1,
-			int irq2, void *pdata, unsigned int periphid,
-			struct resource *resbase)
-{
-	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
-				    periphid, 0, resbase);
-}
-EXPORT_SYMBOL_GPL(amba_apb_device_add_res);
-
-struct amba_device *
-amba_ahb_device_add_res(struct device *parent, const char *name,
-			resource_size_t base, size_t size, int irq1,
-			int irq2, void *pdata, unsigned int periphid,
-			struct resource *resbase)
-{
-	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
-				    periphid, ~0ULL, resbase);
-}
-EXPORT_SYMBOL_GPL(amba_ahb_device_add_res);
-
-
 static void amba_device_initialize(struct amba_device *dev, const char *name)
 {
 	device_initialize(&dev->dev);
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 74afbb7a4f5e..32d5ff8df747 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -222,7 +222,7 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 {
 	struct amba_device *dev;
 	const void *prop;
-	int i, ret;
+	int ret;
 
 	pr_debug("Creating amba device %pOF\n", node);
 
@@ -253,10 +253,6 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 	if (prop)
 		dev->periphid = of_read_ulong(prop, 1);
 
-	/* Decode the IRQs and address ranges */
-	for (i = 0; i < AMBA_NR_IRQS; i++)
-		dev->irq[i] = irq_of_parse_and_map(node, i);
-
 	ret = of_address_to_resource(node, 0, &dev->res);
 	if (ret) {
 		pr_err("amba: of_address_to_resource() failed (%d) for %pOF\n",
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index c68d87b87283..edfcf7a14dcd 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -122,24 +122,6 @@ struct amba_device *amba_device_alloc(const char *, resource_size_t, size_t);
 void amba_device_put(struct amba_device *);
 int amba_device_add(struct amba_device *, struct resource *);
 int amba_device_register(struct amba_device *, struct resource *);
-struct amba_device *amba_apb_device_add(struct device *parent, const char *name,
-					resource_size_t base, size_t size,
-					int irq1, int irq2, void *pdata,
-					unsigned int periphid);
-struct amba_device *amba_ahb_device_add(struct device *parent, const char *name,
-					resource_size_t base, size_t size,
-					int irq1, int irq2, void *pdata,
-					unsigned int periphid);
-struct amba_device *
-amba_apb_device_add_res(struct device *parent, const char *name,
-			resource_size_t base, size_t size, int irq1,
-			int irq2, void *pdata, unsigned int periphid,
-			struct resource *resbase);
-struct amba_device *
-amba_ahb_device_add_res(struct device *parent, const char *name,
-			resource_size_t base, size_t size, int irq1,
-			int irq2, void *pdata, unsigned int periphid,
-			struct resource *resbase);
 void amba_device_unregister(struct amba_device *);
 struct amba_device *amba_find_device(const char *, struct device *, unsigned int, unsigned int);
 int amba_request_regions(struct amba_device *, const char *);
diff --git a/scripts/gcc-plugins/arm_ssp_per_task_plugin.c b/scripts/gcc-plugins/arm_ssp_per_task_plugin.c
index 8c1af9bdcb1b..7328d037f975 100644
--- a/scripts/gcc-plugins/arm_ssp_per_task_plugin.c
+++ b/scripts/gcc-plugins/arm_ssp_per_task_plugin.c
@@ -4,7 +4,7 @@
 
 __visible int plugin_is_GPL_compatible;
 
-static unsigned int sp_mask, canary_offset;
+static unsigned int canary_offset;
 
 static unsigned int arm_pertask_ssp_rtl_execute(void)
 {
@@ -13,7 +13,7 @@ static unsigned int arm_pertask_ssp_rtl_execute(void)
 	for (insn = get_insns(); insn; insn = NEXT_INSN(insn)) {
 		const char *sym;
 		rtx body;
-		rtx mask, masked_sp;
+		rtx current;
 
 		/*
 		 * Find a SET insn involving a SYMBOL_REF to __stack_chk_guard
@@ -30,19 +30,13 @@ static unsigned int arm_pertask_ssp_rtl_execute(void)
 
 		/*
 		 * Replace the source of the SET insn with an expression that
-		 * produces the address of the copy of the stack canary value
-		 * stored in struct thread_info
+		 * produces the address of the current task's stack canary value
 		 */
-		mask = GEN_INT(sext_hwi(sp_mask, GET_MODE_PRECISION(Pmode)));
-		masked_sp = gen_reg_rtx(Pmode);
+		current = gen_reg_rtx(Pmode);
 
-		emit_insn_before(gen_rtx_set(masked_sp,
-					     gen_rtx_AND(Pmode,
-							 stack_pointer_rtx,
-							 mask)),
-				 insn);
+		emit_insn_before(gen_load_tp_hard(current), insn);
 
-		SET_SRC(body) = gen_rtx_PLUS(Pmode, masked_sp,
+		SET_SRC(body) = gen_rtx_PLUS(Pmode, current,
 					     GEN_INT(canary_offset));
 	}
 	return 0;
@@ -72,7 +66,6 @@ __visible int plugin_init(struct plugin_name_args *plugin_info,
 	const char * const plugin_name = plugin_info->base_name;
 	const int argc = plugin_info->argc;
 	const struct plugin_argument *argv = plugin_info->argv;
-	int tso = 0;
 	int i;
 
 	if (!plugin_default_version_check(version, &gcc_version)) {
@@ -91,11 +84,6 @@ __visible int plugin_init(struct plugin_name_args *plugin_info,
 			return 1;
 		}
 
-		if (!strcmp(argv[i].key, "tso")) {
-			tso = atoi(argv[i].value);
-			continue;
-		}
-
 		if (!strcmp(argv[i].key, "offset")) {
 			canary_offset = atoi(argv[i].value);
 			continue;
@@ -105,9 +93,6 @@ __visible int plugin_init(struct plugin_name_args *plugin_info,
 		return 1;
 	}
 
-	/* create the mask that produces the base of the stack */
-	sp_mask = ~((1U << (12 + tso)) - 1);
-
 	PASS_INFO(arm_pertask_ssp_rtl, "expand", 1, PASS_POS_INSERT_AFTER);
 
 	register_callback(plugin_info->base_name, PLUGIN_PASS_MANAGER_SETUP,