Merge branch 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "The main item in this pull request are the Spectre variant 1.1 fixes
  from Julien Thierry.

  A few other patches to improve various areas, and removal of some
  obsolete mcount bits and a redundant kbuild conditional"

* 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm:
  ARM: 8802/1: Call syscall_trace_exit even when system call skipped
  ARM: 8797/1: spectre-v1.1: harden __copy_to_user
  ARM: 8796/1: spectre-v1,v1.1: provide helpers for address sanitization
  ARM: 8795/1: spectre-v1.1: use put_user() for __put_user()
  ARM: 8794/1: uaccess: Prevent speculative use of the current addr_limit
  ARM: 8793/1: signal: replace __put_user_error with __put_user
  ARM: 8792/1: oabi-compat: copy oabi events using __copy_to_user()
  ARM: 8791/1: vfp: use __copy_to_user() when saving VFP state
  ARM: 8790/1: signal: always use __copy_to_user to save iwmmxt context
  ARM: 8789/1: signal: copy registers using __copy_to_user()
  ARM: 8801/1: makefile: use ARMv3M mode for RiscPC
  ARM: 8800/1: use choice for kernel unwinders
  ARM: 8798/1: remove unnecessary KBUILD_SRC ifeq conditional
  ARM: 8788/1: ftrace: remove old mcount support
  ARM: 8786/1: Debug kernel copy by printing

17 files changed, 200 insertions, 222 deletions

diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f6fcb8a79889..a810fa8ba404 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -45,35 +45,42 @@ config DEBUG_WX
 
 		If in doubt, say "Y".
 
-# RMK wants arm kernels compiled with frame pointers or stack unwinding.
-# If you know what you are doing and are willing to live without stack
-# traces, you can get a slightly smaller kernel by setting this option to
-# n, but then RMK will have to kill you ;).
-config FRAME_POINTER
-	bool
-	depends on !THUMB2_KERNEL
-	default y if !ARM_UNWIND || FUNCTION_GRAPH_TRACER
+choice
+	prompt "Choose kernel unwinder"
+	default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
+	default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
 	help
-	  If you say N here, the resulting kernel will be slightly smaller and
-	  faster. However, if neither FRAME_POINTER nor ARM_UNWIND are enabled,
-	  when a problem occurs with the kernel, the information that is
-	  reported is severely limited.
+	  This determines which method will be used for unwinding kernel stack
+	  traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
+	  livepatch, lockdep, and more.
+
+config UNWINDER_FRAME_POINTER
+	bool "Frame pointer unwinder"
+	depends on !THUMB2_KERNEL && !CC_IS_CLANG
+	select ARCH_WANT_FRAME_POINTERS
+	select FRAME_POINTER
+	help
+	  This option enables the frame pointer unwinder for unwinding
+	  kernel stack traces.
 
-config ARM_UNWIND
-	bool "Enable stack unwinding support (EXPERIMENTAL)"
+config UNWINDER_ARM
+	bool "ARM EABI stack unwinder"
 	depends on AEABI
-	default y
+	select ARM_UNWIND
 	help
 	  This option enables stack unwinding support in the kernel
 	  using the information automatically generated by the
 	  compiler. The resulting kernel image is slightly bigger but
 	  the performance is not affected. Currently, this feature
-	  only works with EABI compilers. If unsure say Y.
+	  only works with EABI compilers.
 
-config OLD_MCOUNT
+endchoice
+
+config ARM_UNWIND
+	bool
+
+config FRAME_POINTER
 	bool
-	depends on FUNCTION_TRACER && FRAME_POINTER
-	default y
 
 config DEBUG_USER
 	bool "Verbose user fault messages"
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index d1516f85f25d..5c91e0093ee8 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -74,7 +74,7 @@ endif
 arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
 arch-$(CONFIG_CPU_32v4T)	=-D__LINUX_ARM_ARCH__=4 -march=armv4t
 arch-$(CONFIG_CPU_32v4)		=-D__LINUX_ARM_ARCH__=4 -march=armv4
-arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3
+arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3m
 
 # Evaluate arch cc-option calls now
 arch-y := $(arch-y)
@@ -264,13 +264,9 @@ platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y)))
 
 ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y)
 ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y)
-ifeq ($(KBUILD_SRC),)
-KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs))
-else
 KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs))
 endif
 endif
-endif
 
 export	TEXT_OFFSET GZFLAGS MMUEXT
 
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 517e0e18f0b8..6c7ccb428c07 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -114,6 +114,35 @@
 #endif
 		.endm
 
+		/*
+		 * Debug kernel copy by printing the memory addresses involved
+		 */
+		.macro dbgkc, begin, end, cbegin, cend
+#ifdef DEBUG
+		kputc   #'\n'
+		kputc   #'C'
+		kputc   #':'
+		kputc   #'0'
+		kputc   #'x'
+		kphex   \begin, 8	/* Start of compressed kernel */
+		kputc	#'-'
+		kputc	#'0'
+		kputc	#'x'
+		kphex	\end, 8		/* End of compressed kernel */
+		kputc	#'-'
+		kputc	#'>'
+		kputc   #'0'
+		kputc   #'x'
+		kphex   \cbegin, 8	/* Start of kernel copy */
+		kputc	#'-'
+		kputc	#'0'
+		kputc	#'x'
+		kphex	\cend, 8	/* End of kernel copy */
+		kputc	#'\n'
+		kputc	#'\r'
+#endif
+		.endm
+
 		.section ".start", #alloc, #execinstr
 /*
  * sort out different calling conventions
@@ -450,6 +479,20 @@ dtb_check_done:
 		add	r6, r9, r5
 		add	r9, r9, r10
 
+#ifdef DEBUG
+		sub     r10, r6, r5
+		sub     r10, r9, r10
+		/*
+		 * We are about to copy the kernel to a new memory area.
+		 * The boundaries of the new memory area can be found in
+		 * r10 and r9, whilst r5 and r6 contain the boundaries
+		 * of the memory we are going to copy.
+		 * Calling dbgkc will help with the printing of this
+		 * information.
+		 */
+		dbgkc	r5, r6, r10, r9
+#endif
+
 1:		ldmdb	r6!, {r0 - r3, r10 - r12, lr}
 		cmp	r6, r5
 		stmdb	r9!, {r0 - r3, r10 - r12, lr}
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index b17ee03d280b..88286dd483ff 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -467,6 +467,17 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
+#ifdef CONFIG_CPU_SPECTRE
+	sub	\tmp, \limit, #1
+	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
+	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
+	subhss	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
+	csdb
+#endif
+	.endm
+
 	.macro	uaccess_disable, tmp, isb=1
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	/*
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index 9e842ff41768..18b0197f2384 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -16,9 +16,6 @@ extern void __gnu_mcount_nc(void);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 struct dyn_arch_ftrace {
-#ifdef CONFIG_OLD_MCOUNT
-	bool	old_mcount;
-#endif
 };
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 9b37b6ab27fe..8f55dc520a3e 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -121,8 +121,8 @@ extern void vfp_flush_hwstate(struct thread_info *);
 struct user_vfp;
 struct user_vfp_exc;
 
-extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
-					   struct user_vfp_exc __user *);
+extern int vfp_preserve_user_clear_hwstate(struct user_vfp *,
+					   struct user_vfp_exc *);
 extern int vfp_restore_user_hwstate(struct user_vfp *,
 				    struct user_vfp_exc *);
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 5451e1f05a19..c136eef8f690 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -69,6 +69,14 @@ extern int __put_user_bad(void);
 static inline void set_fs(mm_segment_t fs)
 {
 	current_thread_info()->addr_limit = fs;
+
+	/*
+	 * Prevent a mispredicted conditional call to set_fs from forwarding
+	 * the wrong address limit to access_ok under speculation.
+	 */
+	dsb(nsh);
+	isb();
+
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
 }
 
@@ -92,6 +100,32 @@ static inline void set_fs(mm_segment_t fs)
 	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
 /*
+ * Sanitise a uaccess pointer such that it becomes NULL if addr+size
+ * is above the current addr_limit.
+ */
+#define uaccess_mask_range_ptr(ptr, size)			\
+	((__typeof__(ptr))__uaccess_mask_range_ptr(ptr, size))
+static inline void __user *__uaccess_mask_range_ptr(const void __user *ptr,
+						    size_t size)
+{
+	void __user *safe_ptr = (void __user *)ptr;
+	unsigned long tmp;
+
+	asm volatile(
+	"	sub	%1, %3, #1\n"
+	"	subs	%1, %1, %0\n"
+	"	addhs	%1, %1, #1\n"
+	"	subhss	%1, %1, %2\n"
+	"	movlo	%0, #0\n"
+	: "+r" (safe_ptr), "=&r" (tmp)
+	: "r" (size), "r" (current_thread_info()->addr_limit)
+	: "cc");
+
+	csdb();
+	return safe_ptr;
+}
+
+/*
  * Single-value transfer routines.  They automatically use the right
  * size if we just have the right pointer type.  Note that the functions
  * which read from user space (*get_*) need to take care not to leak
@@ -362,6 +396,14 @@ do {									\
 	__pu_err;							\
 })
 
+#ifdef CONFIG_CPU_SPECTRE
+/*
+ * When mitigating Spectre variant 1.1, all accessors need to include
+ * verification of the address space.
+ */
+#define __put_user(x, ptr) put_user(x, ptr)
+
+#else
 #define __put_user(x, ptr)						\
 ({									\
 	long __pu_err = 0;						\
@@ -369,12 +411,6 @@ do {									\
 	__pu_err;							\
 })
 
-#define __put_user_error(x, ptr, err)					\
-({									\
-	__put_user_switch((x), (ptr), (err), __put_user_nocheck);	\
-	(void) 0;							\
-})
-
 #define __put_user_nocheck(x, __pu_ptr, __err, __size)			\
 	do {								\
 		unsigned long __pu_addr = (unsigned long)__pu_ptr;	\
@@ -454,6 +490,7 @@ do {									\
 	: "r" (x), "i" (-EFAULT)				\
 	: "cc")
 
+#endif /* !CONFIG_CPU_SPECTRE */
 
 #ifdef CONFIG_MMU
 extern unsigned long __must_check
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 783fbb4de5f9..8fa2dc21d332 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -167,9 +167,6 @@ EXPORT_SYMBOL(_find_next_bit_be);
 #endif
 
 #ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_OLD_MCOUNT
-EXPORT_SYMBOL(mcount);
-#endif
 EXPORT_SYMBOL(__gnu_mcount_nc);
 #endif
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 746565a876dc..0465d65d23de 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -296,16 +296,15 @@ __sys_trace:
 	cmp	scno, #-1			@ skip the syscall?
 	bne	2b
 	add	sp, sp, #S_OFF			@ restore stack
-	b	ret_slow_syscall
 
-__sys_trace_return:
-	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
+__sys_trace_return_nosave:
+	enable_irq_notrace
 	mov	r0, sp
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
-__sys_trace_return_nosave:
-	enable_irq_notrace
+__sys_trace_return:
+	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
 	mov	r0, sp
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S
index efcd9f25a14b..0be69e551a64 100644
--- a/arch/arm/kernel/entry-ftrace.S
+++ b/arch/arm/kernel/entry-ftrace.S
@@ -15,23 +15,8 @@
  * start of every function.  In mcount, apart from the function's address (in
  * lr), we need to get hold of the function's caller's address.
  *
- * Older GCCs (pre-4.4) inserted a call to a routine called mcount like this:
- *
- *	bl	mcount
- *
- * These versions have the limitation that in order for the mcount routine to
- * be able to determine the function's caller's address, an APCS-style frame
- * pointer (which is set up with something like the code below) is required.
- *
- *	mov     ip, sp
- *	push    {fp, ip, lr, pc}
- *	sub     fp, ip, #4
- *
- * With EABI, these frame pointers are not available unless -mapcs-frame is
- * specified, and if building as Thumb-2, not even then.
- *
- * Newer GCCs (4.4+) solve this problem by introducing a new version of mcount,
- * with call sites like:
+ * Newer GCCs (4.4+) solve this problem by using a version of mcount with call
+ * sites like:
  *
  *	push	{lr}
  *	bl	__gnu_mcount_nc
@@ -46,17 +31,10 @@
  * allows it to be clobbered in subroutines and doesn't use it to hold
  * parameters.)
  *
- * When using dynamic ftrace, we patch out the mcount call by a "mov r0, r0"
- * for the mcount case, and a "pop {lr}" for the __gnu_mcount_nc case (see
- * arch/arm/kernel/ftrace.c).
+ * When using dynamic ftrace, we patch out the mcount call by a "pop {lr}"
+ * instead of the __gnu_mcount_nc call (see arch/arm/kernel/ftrace.c).
  */
 
-#ifndef CONFIG_OLD_MCOUNT
-#if (__GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 4))
-#error Ftrace requires CONFIG_FRAME_POINTER=y with GCC older than 4.4.0.
-#endif
-#endif
-
 .macro mcount_adjust_addr rd, rn
 	bic	\rd, \rn, #1		@ clear the Thumb bit if present
 	sub	\rd, \rd, #MCOUNT_INSN_SIZE
@@ -209,51 +187,6 @@ ftrace_graph_call\suffix:
 	mcount_exit
 .endm
 
-#ifdef CONFIG_OLD_MCOUNT
-/*
- * mcount
- */
-
-.macro mcount_enter
-	stmdb	sp!, {r0-r3, lr}
-.endm
-
-.macro mcount_get_lr reg
-	ldr	\reg, [fp, #-4]
-.endm
-
-.macro mcount_exit
-	ldr	lr, [fp, #-4]
-	ldmia	sp!, {r0-r3, pc}
-.endm
-
-ENTRY(mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
-	stmdb	sp!, {lr}
-	ldr	lr, [fp, #-4]
-	ldmia	sp!, {pc}
-#else
-	__mcount _old
-#endif
-ENDPROC(mcount)
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(ftrace_caller_old)
-	__ftrace_caller _old
-ENDPROC(ftrace_caller_old)
-#endif
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller_old)
-	__ftrace_graph_caller
-ENDPROC(ftrace_graph_caller_old)
-#endif
-
-.purgem mcount_enter
-.purgem mcount_get_lr
-.purgem mcount_exit
-#endif
-
 /*
  * __gnu_mcount_nc
  */
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 5617932a83df..0142fcfcc3d3 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -47,30 +47,6 @@ void arch_ftrace_update_code(int command)
 	stop_machine(__ftrace_modify_code, &command, NULL);
 }
 
-#ifdef CONFIG_OLD_MCOUNT
-#define OLD_MCOUNT_ADDR	((unsigned long) mcount)
-#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
-
-#define	OLD_NOP		0xe1a00000	/* mov r0, r0 */
-
-static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
-{
-	return rec->arch.old_mcount ? OLD_NOP : NOP;
-}
-
-static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
-{
-	if (!rec->arch.old_mcount)
-		return addr;
-
-	if (addr == MCOUNT_ADDR)
-		addr = OLD_MCOUNT_ADDR;
-	else if (addr == FTRACE_ADDR)
-		addr = OLD_FTRACE_ADDR;
-
-	return addr;
-}
-#else
 static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
 {
 	return NOP;
@@ -80,7 +56,6 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 {
 	return addr;
 }
-#endif
 
 int ftrace_arch_code_modify_prepare(void)
 {
@@ -150,15 +125,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	}
 #endif
 
-#ifdef CONFIG_OLD_MCOUNT
-	if (!ret) {
-		pc = (unsigned long)&ftrace_call_old;
-		new = ftrace_call_replace(pc, (unsigned long)func);
-
-		ret = ftrace_modify_code(pc, 0, new, false);
-	}
-#endif
-
 	return ret;
 }
 
@@ -203,16 +169,6 @@ int ftrace_make_nop(struct module *mod,
 	new = ftrace_nop_replace(rec);
 	ret = ftrace_modify_code(ip, old, new, true);
 
-#ifdef CONFIG_OLD_MCOUNT
-	if (ret == -EINVAL && addr == MCOUNT_ADDR) {
-		rec->arch.old_mcount = true;
-
-		old = ftrace_call_replace(ip, adjust_address(rec, addr));
-		new = ftrace_nop_replace(rec);
-		ret = ftrace_modify_code(ip, old, new, true);
-	}
-#endif
-
 	return ret;
 }
 
@@ -290,13 +246,6 @@ static int ftrace_modify_graph_caller(bool enable)
 #endif
 
 
-#ifdef CONFIG_OLD_MCOUNT
-	if (!ret)
-		ret = __ftrace_modify_caller(&ftrace_graph_call_old,
-					     ftrace_graph_caller_old,
-					     enable);
-#endif
-
 	return ret;
 }
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index b8f766cf3a90..b908382b69ff 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -77,8 +77,6 @@ static int preserve_iwmmxt_context(struct iwmmxt_sigframe __user *frame)
 		kframe->magic = IWMMXT_MAGIC;
 		kframe->size = IWMMXT_STORAGE_SIZE;
 		iwmmxt_task_copy(current_thread_info(), &kframe->storage);
-
-		err = __copy_to_user(frame, kframe, sizeof(*frame));
 	} else {
 		/*
 		 * For bug-compatibility with older kernels, some space
@@ -86,10 +84,14 @@ static int preserve_iwmmxt_context(struct iwmmxt_sigframe __user *frame)
 		 * Set the magic and size appropriately so that properly
 		 * written userspace can skip it reliably:
 		 */
-		__put_user_error(DUMMY_MAGIC, &frame->magic, err);
-		__put_user_error(IWMMXT_STORAGE_SIZE, &frame->size, err);
+		*kframe = (struct iwmmxt_sigframe) {
+			.magic = DUMMY_MAGIC,
+			.size  = IWMMXT_STORAGE_SIZE,
+		};
 	}
 
+	err = __copy_to_user(frame, kframe, sizeof(*kframe));
+
 	return err;
 }
 
@@ -135,17 +137,18 @@ static int restore_iwmmxt_context(char __user **auxp)
 
 static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 {
-	const unsigned long magic = VFP_MAGIC;
-	const unsigned long size = VFP_STORAGE_SIZE;
+	struct vfp_sigframe kframe;
 	int err = 0;
 
-	__put_user_error(magic, &frame->magic, err);
-	__put_user_error(size, &frame->size, err);
+	memset(&kframe, 0, sizeof(kframe));
+	kframe.magic = VFP_MAGIC;
+	kframe.size = VFP_STORAGE_SIZE;
 
+	err = vfp_preserve_user_clear_hwstate(&kframe.ufp, &kframe.ufp_exc);
 	if (err)
-		return -EFAULT;
+		return err;
 
-	return vfp_preserve_user_clear_hwstate(&frame->ufp, &frame->ufp_exc);
+	return __copy_to_user(frame, &kframe, sizeof(kframe));
 }
 
 static int restore_vfp_context(char __user **auxp)
@@ -288,30 +291,35 @@ static int
 setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 {
 	struct aux_sigframe __user *aux;
+	struct sigcontext context;
 	int err = 0;
 
-	__put_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
-	__put_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err);
-	__put_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err);
-	__put_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err);
-	__put_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err);
-	__put_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err);
-	__put_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err);
-	__put_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err);
-	__put_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err);
-	__put_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err);
-	__put_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err);
-	__put_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err);
-	__put_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err);
-	__put_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err);
-	__put_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err);
-	__put_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__put_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err);
-
-	__put_user_error(current->thread.trap_no, &sf->uc.uc_mcontext.trap_no, err);
-	__put_user_error(current->thread.error_code, &sf->uc.uc_mcontext.error_code, err);
-	__put_user_error(current->thread.address, &sf->uc.uc_mcontext.fault_address, err);
-	__put_user_error(set->sig[0], &sf->uc.uc_mcontext.oldmask, err);
+	context = (struct sigcontext) {
+		.arm_r0        = regs->ARM_r0,
+		.arm_r1        = regs->ARM_r1,
+		.arm_r2        = regs->ARM_r2,
+		.arm_r3        = regs->ARM_r3,
+		.arm_r4        = regs->ARM_r4,
+		.arm_r5        = regs->ARM_r5,
+		.arm_r6        = regs->ARM_r6,
+		.arm_r7        = regs->ARM_r7,
+		.arm_r8        = regs->ARM_r8,
+		.arm_r9        = regs->ARM_r9,
+		.arm_r10       = regs->ARM_r10,
+		.arm_fp        = regs->ARM_fp,
+		.arm_ip        = regs->ARM_ip,
+		.arm_sp        = regs->ARM_sp,
+		.arm_lr        = regs->ARM_lr,
+		.arm_pc        = regs->ARM_pc,
+		.arm_cpsr      = regs->ARM_cpsr,
+
+		.trap_no       = current->thread.trap_no,
+		.error_code    = current->thread.error_code,
+		.fault_address = current->thread.address,
+		.oldmask       = set->sig[0],
+	};
+
+	err |= __copy_to_user(&sf->uc.uc_mcontext, &context, sizeof(context));
 
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
@@ -328,7 +336,7 @@ setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 	if (err == 0)
 		err |= preserve_vfp_context(&aux->vfp);
 #endif
-	__put_user_error(0, &aux->end_magic, err);
+	err |= __put_user(0, &aux->end_magic);
 
 	return err;
 }
@@ -491,7 +499,7 @@ setup_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 	/*
 	 * Set uc.uc_flags to a value which sc.trap_no would never have.
 	 */
-	__put_user_error(0x5ac3c35a, &frame->uc.uc_flags, err);
+	err = __put_user(0x5ac3c35a, &frame->uc.uc_flags);
 
 	err |= setup_sigframe(frame, regs, set);
 	if (err == 0)
@@ -511,8 +519,8 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 
 	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
 
-	__put_user_error(0, &frame->sig.uc.uc_flags, err);
-	__put_user_error(NULL, &frame->sig.uc.uc_link, err);
+	err |= __put_user(0, &frame->sig.uc.uc_flags);
+	err |= __put_user(NULL, &frame->sig.uc.uc_link);
 
 	err |= __save_altstack(&frame->sig.uc.uc_stack, regs->ARM_sp);
 	err |= setup_sigframe(&frame->sig, regs, set);
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index f0dd4b6ebb63..40da0872170f 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -277,6 +277,7 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
 				    int maxevents, int timeout)
 {
 	struct epoll_event *kbuf;
+	struct oabi_epoll_event e;
 	mm_segment_t fs;
 	long ret, err, i;
 
@@ -295,8 +296,11 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
 	set_fs(fs);
 	err = 0;
 	for (i = 0; i < ret; i++) {
-		__put_user_error(kbuf[i].events, &events->events, err);
-		__put_user_error(kbuf[i].data,   &events->data,   err);
+		e.events = kbuf[i].events;
+		e.data = kbuf[i].data;
+		err = __copy_to_user(events, &e, sizeof(e));
+		if (err)
+			break;
 		events++;
 	}
 	kfree(kbuf);
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index a826df3d3814..6709a8d33963 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -93,11 +93,7 @@ ENTRY(arm_copy_from_user)
 #ifdef CONFIG_CPU_SPECTRE
 	get_thread_info r3
 	ldr	r3, [r3, #TI_ADDR_LIMIT]
-	adds	ip, r1, r2	@ ip=addr+size
-	sub	r3, r3, #1	@ addr_limit - 1
-	cmpcc	ip, r3		@ if (addr+size > addr_limit - 1)
-	movcs	r1, #0		@ addr = NULL
-	csdb
+	uaccess_mask_range_ptr r1, r2, r3, ip
 #endif
 
 #include "copy_template.S"
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index caf5019d8161..970abe521197 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -94,6 +94,11 @@
 
 ENTRY(__copy_to_user_std)
 WEAK(arm_copy_to_user)
+#ifdef CONFIG_CPU_SPECTRE
+	get_thread_info r3
+	ldr	r3, [r3, #TI_ADDR_LIMIT]
+	uaccess_mask_range_ptr r0, r2, r3, ip
+#endif
 
 #include "copy_template.S"
 
@@ -108,4 +113,3 @@ ENDPROC(__copy_to_user_std)
 	rsb	r0, r0, r2
 	copy_abort_end
 	.popsection
-
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 9b4ed1728616..73dc7360cbdd 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -152,7 +152,8 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 		n = __copy_to_user_std(to, from, n);
 		uaccess_restore(ua_flags);
 	} else {
-		n = __copy_to_user_memcpy(to, from, n);
+		n = __copy_to_user_memcpy(uaccess_mask_range_ptr(to, n),
+					  from, n);
 	}
 	return n;
 }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index dc7e6b50ef67..2b287d0d6bc2 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -553,12 +553,11 @@ void vfp_flush_hwstate(struct thread_info *thread)
  * Save the current VFP state into the provided structures and prepare
  * for entry into a new function (signal handler).
  */
-int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
-				    struct user_vfp_exc __user *ufp_exc)
+int vfp_preserve_user_clear_hwstate(struct user_vfp *ufp,
+				    struct user_vfp_exc *ufp_exc)
 {
 	struct thread_info *thread = current_thread_info();
 	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
-	int err = 0;
 
 	/* Ensure that the saved hwstate is up-to-date. */
 	vfp_sync_hwstate(thread);
@@ -567,22 +566,19 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
 	 */
-	err |= __copy_to_user(&ufp->fpregs, &hwstate->fpregs,
-			      sizeof(hwstate->fpregs));
+	memcpy(&ufp->fpregs, &hwstate->fpregs, sizeof(hwstate->fpregs));
+
 	/*
 	 * Copy the status and control register.
 	 */
-	__put_user_error(hwstate->fpscr, &ufp->fpscr, err);
+	ufp->fpscr = hwstate->fpscr;
 
 	/*
 	 * Copy the exception registers.
 	 */
-	__put_user_error(hwstate->fpexc, &ufp_exc->fpexc, err);
-	__put_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
-	__put_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
-
-	if (err)
-		return -EFAULT;
+	ufp_exc->fpexc = hwstate->fpexc;
+	ufp_exc->fpinst = hwstate->fpinst;
+	ufp_exc->fpinst2 = ufp_exc->fpinst2;
 
 	/* Ensure that VFP is disabled. */
 	vfp_flush_hwstate(thread);