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

Pull ARM updates from Russell King:

 - An improvement from Ard Biesheuvel, who noted that the identity map
   setup was taking a long time due to flush_cache_louis().

 - Update a comment about dma_ops from Wolfram Sang.

 - Remove use of "-p" with ld, where this flag has been a no-op since
   2004.

 - Remove the printing of the virtual memory layout, which is no longer
   useful since we hide pointers.

 - Correct SCU help text.

 - Remove legacy TWD registration method.

 - Add pgprot_device() implementation for mapping PCI sysfs resource
   files.

 - Initialise PFN limits earlier for kmemleak.

 - Fix argument count to match macro definition (affects clang builds)

 - Use unified assembler language almost everywhere for clang, and other
   clang improvements (from Stefan Agner, Nathan Chancellor).

 - Support security extension for noMMU and other noMMU cleanups (from
   Vladimir Murzin).

 - Remove unnecessary SMP bringup code (which was incorrectly copy'n'
   pasted from the ARM platform implementations) and remove it from the
   arch code to discourge further copys of it appearing.

 - Add Cortex A9 erratum preventing kexec working on some SoCs.

 - AMBA bus identification updates from Mike Leach.

 - More use of raw spinlocks to avoid -RT kernel issues (from Yang Shi
   and Sebastian Andrzej Siewior).

 - MCPM hyp/svc mode mismatch fixes from Marek Szyprowski.

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (32 commits)
  ARM: 8849/1: NOMMU: Fix encodings for PMSAv8's PRBAR4/PRLAR4
  ARM: 8848/1: virt: Align GIC version check with arm64 counterpart
  ARM: 8847/1: pm: fix HYP/SVC mode mismatch when MCPM is used
  ARM: 8845/1: use unified assembler in c files
  ARM: 8844/1: use unified assembler in assembly files
  ARM: 8843/1: use unified assembler in headers
  ARM: 8841/1: use unified assembler in macros
  ARM: 8840/1: use a raw_spinlock_t in unwind
  ARM: 8839/1: kprobe: make patch_lock a raw_spinlock_t
  ARM: 8837/1: coresight: etmv4: Update ID register table to add UCI support
  ARM: 8836/1: drivers: amba: Update component matching to use the CoreSight UCI values.
  ARM: 8838/1: drivers: amba: Updates to component identification for driver matching.
  ARM: 8833/1: Ensure that NEON code always compiles with Clang
  ARM: avoid Cortex-A9 livelock on tight dmb loops
  ARM: smp: remove arch-provided "pen_release"
  ARM: actions: remove boot_lock and pen_release
  ARM: oxnas: remove CPU hotplug implementation
  ARM: qcom: remove unnecessary boot_lock
  ARM: 8832/1: NOMMU: Limit visibility for CONFIG_FLASH_{MEM_BASE,SIZE}
  ARM: 8831/1: NOMMU: pmsa-v8: remove unneeded semicolon
  ...

86 files changed, 284 insertions, 526 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5085a1eab9fc5..054ead960f983 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1310,7 +1310,7 @@ config SCHED_SMT
 config HAVE_ARM_SCU
 	bool
 	help
-	  This option enables support for the ARM system coherency unit
+	  This option enables support for the ARM snoop control unit
 
 config HAVE_ARM_ARCH_TIMER
 	bool "Architected timer support"
@@ -1322,7 +1322,6 @@ config HAVE_ARM_ARCH_TIMER
 
 config HAVE_ARM_TWD
 	bool
-	select TIMER_OF if OF
 	help
 	  This options enables support for the ARM timer and watchdog unit
 
diff --git a/arch/arm/Kconfig-nommu b/arch/arm/Kconfig-nommu
index 1168a03c85255..36c80d3dd93f2 100644
--- a/arch/arm/Kconfig-nommu
+++ b/arch/arm/Kconfig-nommu
@@ -20,10 +20,12 @@ config DRAM_SIZE
 
 config FLASH_MEM_BASE
 	hex 'FLASH Base Address' if SET_MEM_PARAM
+	depends on CPU_ARM740T || CPU_ARM946E || CPU_ARM940T
 	default 0x00400000
 
 config FLASH_SIZE
 	hex 'FLASH Size' if SET_MEM_PARAM
+	depends on CPU_ARM740T || CPU_ARM946E || CPU_ARM940T
 	default 0x00400000
 
 config PROCESSOR_ID
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 00000e91ad652..807a7d06c2a08 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:=-p --no-undefined -X --pic-veneer
+LDFLAGS_vmlinux	:= --no-undefined -X --pic-veneer
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
 KBUILD_LDFLAGS_MODULE	+= --be8
diff --git a/arch/arm/boot/bootp/Makefile b/arch/arm/boot/bootp/Makefile
index 83e1a076a5d64..981a8d03f064c 100644
--- a/arch/arm/boot/bootp/Makefile
+++ b/arch/arm/boot/bootp/Makefile
@@ -8,7 +8,7 @@
 
 GCOV_PROFILE	:= n
 
-LDFLAGS_bootp	:=-p --no-undefined -X \
+LDFLAGS_bootp	:= --no-undefined -X \
 		 --defsym initrd_phys=$(INITRD_PHYS) \
 		 --defsym params_phys=$(PARAMS_PHYS) -T
 AFLAGS_initrd.o :=-DINITRD=\"$(INITRD)\"
diff --git a/arch/arm/boot/bootp/init.S b/arch/arm/boot/bootp/init.S
index 78b508075161f..142927e5f485a 100644
--- a/arch/arm/boot/bootp/init.S
+++ b/arch/arm/boot/bootp/init.S
@@ -44,7 +44,7 @@ _start:		add	lr, pc, #-0x8		@ lr = current load addr
  */
 		movne	r10, #0			@ terminator
 		movne	r4, #2			@ Size of this entry (2 words)
-		stmneia	r9, {r4, r5, r10}	@ Size, ATAG_CORE, terminator
+		stmiane	r9, {r4, r5, r10}	@ Size, ATAG_CORE, terminator
 
 /*
  * find the end of the tag list, and then add an INITRD tag on the end.
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 6114ae6ea4666..9219389bbe612 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -132,8 +132,6 @@ endif
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux += --be8
 endif
-# ?
-LDFLAGS_vmlinux += -p
 # Report unresolved symbol references
 LDFLAGS_vmlinux += --no-undefined
 # Delete all temporary local symbols
diff --git a/arch/arm/boot/compressed/ll_char_wr.S b/arch/arm/boot/compressed/ll_char_wr.S
index 8517c8606b4a7..b1dcdb9f4030e 100644
--- a/arch/arm/boot/compressed/ll_char_wr.S
+++ b/arch/arm/boot/compressed/ll_char_wr.S
@@ -75,7 +75,7 @@ Lrow4bpplp:
 	tst	r1, #7				@ avoid using r7 directly after
 	str	r7, [r0, -r5]!
 	subne	r1, r1, #1
-	ldrneb	r7, [r6, r1]
+	ldrbne	r7, [r6, r1]
 	bne	Lrow4bpplp
 	ldmfd	sp!, {r4 - r7, pc}
 
@@ -103,7 +103,7 @@ Lrow8bpplp:
 	sub	r0, r0, r5			@ avoid ip
 	stmia	r0, {r4, ip}
 	subne	r1, r1, #1
-	ldrneb	r7, [r6, r1]
+	ldrbne	r7, [r6, r1]
 	bne	Lrow8bpplp
 	ldmfd	sp!, {r4 - r7, pc}
 
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index ad574d20415c2..1b1b82b37ce03 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -381,7 +381,7 @@ static int __init nocache_trampoline(unsigned long _arg)
 	unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 	phys_reset_t phys_reset;
 
-	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume_no_hyp);
 	setup_mm_for_reboot();
 
 	__mcpm_cpu_going_down(cpu, cluster);
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 28a48e0d4cca0..b59921a560da3 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -376,9 +376,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER()
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
+	\instr\()b\t\cond\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()\t\().w \reg, [\ptr, #\off]
+	\instr\t\cond\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -417,9 +417,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t \reg, [\ptr], #\inc
+	\instr\()b\t\cond \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()\t \reg, [\ptr], #\inc
+	\instr\t\cond \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -460,7 +460,7 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
 #ifndef CONFIG_CPU_USE_DOMAINS
 	adds	\tmp, \addr, #\size - 1
-	sbcccs	\tmp, \tmp, \limit
+	sbcscc	\tmp, \tmp, \limit
 	bcs	\bad
 #ifdef CONFIG_CPU_SPECTRE
 	movcs	\addr, #0
@@ -474,7 +474,7 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	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) }
+	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
 	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
 	csdb
 #endif
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 69772e742a0ac..83ae97c049d9b 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -11,6 +11,8 @@
 #define sev()	__asm__ __volatile__ ("sev" : : : "memory")
 #define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
 #define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#else
+#define wfe()	do { } while (0)
 #endif
 
 #if __LINUX_ARM_ARCH__ >= 7
diff --git a/arch/arm/include/asm/hardware/entry-macro-iomd.S b/arch/arm/include/asm/hardware/entry-macro-iomd.S
index 8c215acd9b573..f7692731e5143 100644
--- a/arch/arm/include/asm/hardware/entry-macro-iomd.S
+++ b/arch/arm/include/asm/hardware/entry-macro-iomd.S
@@ -16,25 +16,25 @@
 		ldr	\tmp, =irq_prio_h
 		teq	\irqstat, #0
 #ifdef IOMD_BASE
-		ldreqb	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
+		ldrbeq	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
 		addeq	\tmp, \tmp, #256		@ irq_prio_h table size
 		teqeq	\irqstat, #0
 		bne	2406f
 #endif
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
 		addeq	\tmp, \tmp, #256		@ irq_prio_d table size
 		teqeq	\irqstat, #0
 #ifdef IOMD_IRQREQC
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQC]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQC]
 		addeq	\tmp, \tmp, #256		@ irq_prio_l table size
 		teqeq	\irqstat, #0
 #endif
 #ifdef IOMD_IRQREQD
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQD]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQD]
 		addeq	\tmp, \tmp, #256		@ irq_prio_lc table size
 		teqeq	\irqstat, #0
 #endif
-2406:		ldrneb	\irqnr, [\tmp, \irqstat]	@ get IRQ number
+2406:		ldrbne	\irqnr, [\tmp, \irqstat]	@ get IRQ number
 		.endm
 
 /*
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index a757401129f95..48ce1b19069b6 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -125,6 +125,9 @@ extern pgprot_t		pgprot_s2_device;
 #define pgprot_stronglyordered(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
 
+#define pgprot_device(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_DEV_SHARED | L_PTE_SHARED | L_PTE_DIRTY | L_PTE_XN)
+
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 120f4c9bbfde2..57fe73ea0f725 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -89,7 +89,11 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
-#define cpu_relax()			smp_mb()
+#define cpu_relax()						\
+	do {							\
+		smp_mb();					\
+		__asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;");	\
+	} while (0)
 #else
 #define cpu_relax()			barrier()
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 709a55989cb06..451ae684aaf48 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -67,7 +67,6 @@ struct secondary_data {
 	void *stack;
 };
 extern struct secondary_data secondary_data;
-extern volatile int pen_release;
 extern void secondary_startup(void);
 extern void secondary_startup_arm(void);
 
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index 312784ee9936a..c729d2113a245 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -19,20 +19,4 @@
 #define TWD_TIMER_CONTROL_PERIODIC	(1 << 1)
 #define TWD_TIMER_CONTROL_IT_ENABLE	(1 << 2)
 
-#include <linux/ioport.h>
-
-struct twd_local_timer {
-	struct resource	res[2];
-};
-
-#define DEFINE_TWD_LOCAL_TIMER(name,base,irq)	\
-struct twd_local_timer name __initdata = {	\
-	.res	= {				\
-		DEFINE_RES_MEM(base, 0x10),	\
-		DEFINE_RES_IRQ(irq),		\
-	},					\
-};
-
-int twd_local_timer_register(struct twd_local_timer *);
-
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 099c78fcf62d4..8f009e788ad40 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -210,11 +210,12 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 
 	prefetchw(&rw->lock);
 	__asm__ __volatile__(
+"	.syntax unified\n"
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
 "	strexpl	%1, %0, [%2]\n"
 	WFE("mi")
-"	rsbpls	%0, %1, #0\n"
+"	rsbspl	%0, %1, #0\n"
 "	bmi	1b"
 	: "=&r" (tmp), "=&r" (tmp2)
 	: "r" (&rw->lock)
diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h
index 452bbdcbcc835..506314265c6f1 100644
--- a/arch/arm/include/asm/suspend.h
+++ b/arch/arm/include/asm/suspend.h
@@ -10,6 +10,7 @@ struct sleep_save_sp {
 };
 
 extern void cpu_resume(void);
+extern void cpu_resume_no_hyp(void);
 extern void cpu_resume_arm(void);
 extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index ae5a0df5316e5..dff49845eb876 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -85,7 +85,8 @@ static inline void set_fs(mm_segment_t fs)
 #define __range_ok(addr, size) ({ \
 	unsigned long flag, roksum; \
 	__chk_user_ptr(addr);	\
-	__asm__("adds %1, %2, %3; sbcccs %1, %1, %0; movcc %0, #0" \
+	__asm__(".syntax unified\n" \
+		"adds %1, %2, %3; sbcscc %1, %1, %0; movcc %0, #0" \
 		: "=&r" (flag), "=&r" (roksum) \
 		: "r" (addr), "Ir" (size), "0" (current_thread_info()->addr_limit) \
 		: "cc"); \
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index 187ccf6496ad6..2cb00d15831b9 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -49,7 +49,7 @@
  * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01.
  */
 #define EXC_RET_STACK_MASK			0x00000004
-#define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
+#define EXC_RET_THREADMODE_PROCESSSTACK		(3 << 2)
 
 /* Cache related definitions */
 
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index ef5dfedacd8d6..628c336e8e3b2 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -29,13 +29,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldclne	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldcleq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
@@ -53,13 +53,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stclne	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stcleq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
diff --git a/arch/arm/include/debug/tegra.S b/arch/arm/include/debug/tegra.S
index 3bc80599c0225..4a5a645c76e2f 100644
--- a/arch/arm/include/debug/tegra.S
+++ b/arch/arm/include/debug/tegra.S
@@ -173,7 +173,7 @@
 
 		.macro	senduart, rd, rx
 		cmp	\rx, #0
-		strneb	\rd, [\rx, #UART_TX << UART_SHIFT]
+		strbne	\rd, [\rx, #UART_TX << UART_SHIFT]
 1001:
 		.endm
 
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index b795dc2408c05..b9f94e03d916a 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -86,7 +86,7 @@ hexbuf_rel:	.long	hexbuf_addr - .
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 1:		teq	r0, #0
-		ldrneb	r1, [r0], #1
+		ldrbne	r1, [r0], #1
 		teqne	r1, #0
 		reteq	lr
 2:		teq     r1, #'\n'
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index e85a3af9ddeb5..ce4aea57130af 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -636,7 +636,7 @@ call_fpe:
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
 	rsbs	r7, r8, #(1 << 8)		@ CP 0 or 1 only
-	movcss	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
+	movscs	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
 	bcs	iwmmxt_task_enable
 #endif
  ARM(	add	pc, pc, r8, lsr #6	)
@@ -872,7 +872,7 @@ __kuser_cmpxchg64:				@ 0xffff0f60
 	smp_dmb	arm
 1:	ldrexd	r0, r1, [r2]			@ load current val
 	eors	r3, r0, r4			@ compare with oldval (1)
-	eoreqs	r3, r1, r5			@ compare with oldval (2)
+	eorseq	r3, r1, r5			@ compare with oldval (2)
 	strexdeq r3, r6, r7, [r2]		@ store newval if eq
 	teqeq	r3, #1				@ success?
 	beq	1b				@ if no then retry
@@ -896,8 +896,8 @@ __kuser_cmpxchg64:				@ 0xffff0f60
 	ldmia	r1, {r6, lr}			@ load new val
 1:	ldmia	r2, {r0, r1}			@ load current val
 	eors	r3, r0, r4			@ compare with oldval (1)
-	eoreqs	r3, r1, r5			@ compare with oldval (2)
-2:	stmeqia	r2, {r6, lr}			@ store newval if eq
+	eorseq	r3, r1, r5			@ compare with oldval (2)
+2:	stmiaeq	r2, {r6, lr}			@ store newval if eq
 	rsbs	r0, r3, #0			@ set return val and C flag
 	ldmfd	sp!, {r4, r5, r6, pc}
 
@@ -911,7 +911,7 @@ kuser_cmpxchg64_fixup:
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64)))
 	subs	r8, r4, r7
-	rsbcss	r8, r8, #(2b - 1b)
+	rsbscs	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 #if __LINUX_ARM_ARCH__ < 6
 	bcc	kuser_cmpxchg32_fixup
@@ -969,7 +969,7 @@ kuser_cmpxchg32_fixup:
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
 	subs	r8, r4, r7
-	rsbcss	r8, r8, #(2b - 1b)
+	rsbscs	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 	ret	lr
 	.previous
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 0465d65d23de5..f7649adef505e 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -373,7 +373,7 @@ sys_syscall:
 		movhs	scno, #0
 		csdb
 #endif
-		stmloia	sp, {r5, r6}		@ shuffle args
+		stmialo	sp, {r5, r6}		@ shuffle args
 		movlo	r0, r1
 		movlo	r1, r2
 		movlo	r2, r3
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 773424843d6ef..32051ec5b33fa 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -127,7 +127,8 @@
          */
 	.macro	v7m_exception_slow_exit ret_r0
 	cpsid	i
-	ldr	lr, =EXC_RET_THREADMODE_PROCESSSTACK
+	ldr	lr, =exc_ret
+	ldr	lr, [lr]
 
 	@ read original r12, sp, lr, pc and xPSR
 	add	r12, sp, #S_IP
@@ -387,8 +388,8 @@
 	badr	lr, \ret			@ return address
 	.if	\reload
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	ldmccia	r1, {r0 - r6}			@ reload r0-r6
-	stmccia	sp, {r4, r5}			@ update stack arguments
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
+	stmiacc	sp, {r4, r5}			@ update stack arguments
 	.endif
 	ldrcc	pc, [\table, \tmp, lsl #2]	@ call sys_* routine
 #else
@@ -396,8 +397,8 @@
 	badr	lr, \ret			@ return address
 	.if	\reload
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	ldmccia	r1, {r0 - r6}			@ reload r0-r6
-	stmccia	sp, {r4, r5}			@ update stack arguments
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
+	stmiacc	sp, {r4, r5}			@ update stack arguments
 	.endif
 	ldrcc	pc, [\table, \nr, lsl #2]	@ call sys_* routine
 #endif
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index abcf478485259..19d2dcd6530dc 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -146,3 +146,7 @@ ENTRY(vector_table)
 	.rept	CONFIG_CPU_V7M_NUM_IRQ
 	.long	__irq_entry		@ External Interrupts
 	.endr
+	.align	2
+	.globl	exc_ret
+exc_ret:
+	.space	4
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index ec29de2500764..c08d2d890f7b9 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -439,8 +439,8 @@ M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(3)])
 	str	r5, [r12, #PMSAv8_RBAR_A(0)]
 	str	r6, [r12, #PMSAv8_RLAR_A(0)]
 #else
-	mcr	p15, 0, r5, c6, c10, 1			@ PRBAR4
-	mcr	p15, 0, r6, c6, c10, 2			@ PRLAR4
+	mcr	p15, 0, r5, c6, c10, 0			@ PRBAR4
+	mcr	p15, 0, r6, c6, c10, 1			@ PRLAR4
 #endif
 #endif
 	ret	lr
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 60146e32619a5..82a942894fc04 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -180,8 +180,8 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 	@ Check whether GICv3 system registers are available
 	mrc	p15, 0, r7, c0, c1, 1	@ ID_PFR1
 	ubfx	r7, r7, #28, #4
-	cmp	r7, #1
-	bne	2f
+	teq	r7, #0
+	beq	2f
 
 	@ Enable system register accesses
 	mrc	p15, 4, r7, c12, c9, 5	@ ICC_HSRE
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index dd2eb5f76b9f0..76300f3813e89 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -91,8 +91,11 @@ void machine_crash_nonpanic_core(void *unused)
 
 	set_cpu_online(smp_processor_id(), false);
 	atomic_dec(&waiting_for_crash_ipi);
-	while (1)
+
+	while (1) {
 		cpu_relax();
+		wfe();
+	}
 }
 
 void crash_smp_send_stop(void)
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index a50dc00d79a27..d0a05a3bdb965 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,7 +16,7 @@ struct patch {
 	unsigned int insn;
 };
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 	__acquires(&patch_lock)
@@ -33,7 +33,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 		return addr;
 
 	if (flags)
-		spin_lock_irqsave(&patch_lock, *flags);
+		raw_spin_lock_irqsave(&patch_lock, *flags);
 	else
 		__acquire(&patch_lock);
 
@@ -48,7 +48,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
 	clear_fixmap(fixmap);
 
 	if (flags)
-		spin_unlock_irqrestore(&patch_lock, *flags);
+		raw_spin_unlock_irqrestore(&patch_lock, *flags);
 	else
 		__release(&patch_lock);
 }
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index a8257fc9cf2a9..5dc8b80bb6938 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -120,6 +120,14 @@ ENDPROC(cpu_resume_after_mmu)
 	.text
 	.align
 
+#ifdef CONFIG_MCPM
+	.arm
+THUMB(	.thumb			)
+ENTRY(cpu_resume_no_hyp)
+ARM_BE8(setend be)			@ ensure we are in BE mode
+	b	no_hyp
+#endif
+
 #ifdef CONFIG_MMU
 	.arm
 ENTRY(cpu_resume_arm)
@@ -135,6 +143,7 @@ ARM_BE8(setend be)			@ ensure we are in BE mode
 	bl	__hyp_stub_install_secondary
 #endif
 	safe_svcmode_maskall r1
+no_hyp:
 	mov	r1, #0
 	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
 	ALT_UP_B(1f)
@@ -164,6 +173,9 @@ ENDPROC(cpu_resume)
 #ifdef CONFIG_MMU
 ENDPROC(cpu_resume_arm)
 #endif
+#ifdef CONFIG_MCPM
+ENDPROC(cpu_resume_no_hyp)
+#endif
 
 	.align 2
 _sleep_save_sp:
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 1d6f5ea522f49..facd4240ca02c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -62,12 +62,6 @@
  */
 struct secondary_data secondary_data;
 
-/*
- * control for which core is the next to come out of the secondary
- * boot "holding pen"
- */
-volatile int pen_release = -1;
-
 enum ipi_msg_type {
 	IPI_WAKEUP,
 	IPI_TIMER,
@@ -604,8 +598,10 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
-	while (1)
+	while (1) {
 		cpu_relax();
+		wfe();
+	}
 }
 
 static DEFINE_PER_CPU(struct completion *, cpu_completion);
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index b30eafeef0963..3cdc399b9fc32 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -100,8 +100,6 @@ static void twd_timer_stop(void)
 	disable_percpu_irq(clk->irq);
 }
 
-#ifdef CONFIG_COMMON_CLK
-
 /*
  * Updates clockevent frequency when the cpu frequency changes.
  * Called on the cpu that is changing frequency with interrupts disabled.
@@ -143,54 +141,6 @@ static int twd_clk_init(void)
 }
 core_initcall(twd_clk_init);
 
-#elif defined (CONFIG_CPU_FREQ)
-
-#include <linux/cpufreq.h>
-
-/*
- * Updates clockevent frequency when the cpu frequency changes.
- * Called on the cpu that is changing frequency with interrupts disabled.
- */
-static void twd_update_frequency(void *data)
-{
-	twd_timer_rate = clk_get_rate(twd_clk);
-
-	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
-}
-
-static int twd_cpufreq_transition(struct notifier_block *nb,
-	unsigned long state, void *data)
-{
-	struct cpufreq_freqs *freqs = data;
-
-	/*
-	 * The twd clock events must be reprogrammed to account for the new
-	 * frequency.  The timer is local to a cpu, so cross-call to the
-	 * changing cpu.
-	 */
-	if (state == CPUFREQ_POSTCHANGE)
-		smp_call_function_single(freqs->cpu, twd_update_frequency,
-			NULL, 1);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block twd_cpufreq_nb = {
-	.notifier_call = twd_cpufreq_transition,
-};
-
-static int twd_cpufreq_init(void)
-{
-	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
-		return cpufreq_register_notifier(&twd_cpufreq_nb,
-			CPUFREQ_TRANSITION_NOTIFIER);
-
-	return 0;
-}
-core_initcall(twd_cpufreq_init);
-
-#endif
-
 static void twd_calibrate_rate(void)
 {
 	unsigned long count;
@@ -366,21 +316,6 @@ out_free:
 	return err;
 }
 
-int __init twd_local_timer_register(struct twd_local_timer *tlt)
-{
-	if (twd_base || twd_evt)
-		return -EBUSY;
-
-	twd_ppi	= tlt->res[1].start;
-
-	twd_base = ioremap(tlt->res[0].start, resource_size(&tlt->res[0]));
-	if (!twd_base)
-		return -ENOMEM;
-
-	return twd_local_timer_common_register(NULL);
-}
-
-#ifdef CONFIG_OF
 static int __init twd_local_timer_of_register(struct device_node *np)
 {
 	int err;
@@ -406,4 +341,3 @@ out:
 TIMER_OF_DECLARE(arm_twd_a9, "arm,cortex-a9-twd-timer", twd_local_timer_of_register);
 TIMER_OF_DECLARE(arm_twd_a5, "arm,cortex-a5-twd-timer", twd_local_timer_of_register);
 TIMER_OF_DECLARE(arm_twd_11mp, "arm,arm11mp-twd-timer", twd_local_timer_of_register);
-#endif
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 0bee233fef9a3..314cfb232a635 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
 static const struct unwind_idx *__origin_unwind_idx;
 extern const struct unwind_idx __stop_unwind_idx[];
 
-static DEFINE_SPINLOCK(unwind_lock);
+static DEFINE_RAW_SPINLOCK(unwind_lock);
 static LIST_HEAD(unwind_tables);
 
 /* Convert a prel31 symbol to an absolute address */
@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
 		/* module unwind tables */
 		struct unwind_table *table;
 
-		spin_lock_irqsave(&unwind_lock, flags);
+		raw_spin_lock_irqsave(&unwind_lock, flags);
 		list_for_each_entry(table, &unwind_tables, list) {
 			if (addr >= table->begin_addr &&
 			    addr < table->end_addr) {
@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&unwind_lock, flags);
+		raw_spin_unlock_irqrestore(&unwind_lock, flags);
 	}
 
 	pr_debug("%s: idx = %p\n", __func__, idx);
@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
 	tab->begin_addr = text_addr;
 	tab->end_addr = text_addr + text_size;
 
-	spin_lock_irqsave(&unwind_lock, flags);
+	raw_spin_lock_irqsave(&unwind_lock, flags);
 	list_add_tail(&tab->list, &unwind_tables);
-	spin_unlock_irqrestore(&unwind_lock, flags);
+	raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
 	return tab;
 }
@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_table *tab)
 	if (!tab)
 		return;
 
-	spin_lock_irqsave(&unwind_lock, flags);
+	raw_spin_lock_irqsave(&unwind_lock, flags);
 	list_del(&tab->list);
-	spin_unlock_irqrestore(&unwind_lock, flags);
+	raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
 	kfree(tab);
 }
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index ad25fd1872c7d..0bff0176db2c4 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -39,7 +39,7 @@ $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  NEON_FLAGS			:= -march=armv7-a -mfloat-abi=softfp -mfpu=neon
   CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 93cddab73072c..95bd359912889 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -7,7 +7,7 @@
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -32,7 +32,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -62,7 +62,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r2, r0, #31
 	mov	r0, r0, lsr #5
 	mov	r3, #1
@@ -89,7 +89,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r3, r0, #31
 	mov	r0, r0, lsr #5
 	save_and_disable_irqs ip
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index e936352ccb001..55946e3fa2ba8 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -44,7 +44,7 @@ UNWIND(.save {r1, lr})
 		strusr	r2, r0, 1, ne, rept=2
 		tst	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
 		it	ne			@ explicit IT needed for the label
-USER(		strnebt	r2, [r0])
+USER(		strbtne	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
 UNWIND(.fnend)
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 0d4c189c7f4f0..6a3419e2c6d86 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -91,7 +91,7 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
-	str\cond\()b \reg, [\ptr], #1
+	strb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro enter reg1 reg2
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
index 6ee2f6706f869..b84ce17920439 100644
--- a/arch/arm/lib/copy_page.S
+++ b/arch/arm/lib/copy_page.S
@@ -39,9 +39,9 @@ ENTRY(copy_page)
 	.endr
 		subs	r2, r2, #1			@	1
 		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmgtia	r1!, {r3, r4, ip, lr}		@	4
+		ldmiagt	r1!, {r3, r4, ip, lr}		@	4
 		bgt	1b				@	1
-	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
+	PLD(	ldmiaeq r1!, {r3, r4, ip, lr}	)
 	PLD(	beq	2b			)
 		ldmfd	sp!, {r4, pc}			@	3
 ENDPROC(copy_page)
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 652e4d98cd47b..a11f2c25e03a7 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -99,7 +99,7 @@
 
 	CALGN(	ands	ip, r0, #31		)
 	CALGN(	rsb	r3, ip, #32		)
-	CALGN(	sbcnes	r4, r3, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, r3, r2		)  @ C is always set here
 	CALGN(	bcs	2f			)
 	CALGN(	adr	r4, 6f			)
 	CALGN(	subs	r2, r2, r3		)  @ C gets set
@@ -204,7 +204,7 @@
 
 	CALGN(	ands	ip, r0, #31		)
 	CALGN(	rsb	ip, ip, #32		)
-	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
 
@@ -241,7 +241,7 @@
 		orr	r9, r9, ip, lspush #\push
 		mov	ip, ip, lspull #\pull
 		orr	ip, ip, lr, lspush #\push
-		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
+		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
 	PLD(	bge	13b			)
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 97a6ff4b7e3ca..c7d08096e3545 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -49,7 +49,7 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
-	ldr\cond\()b \reg, [\ptr], #1
+	ldrb\cond \reg, [\ptr], #1
 	.endm
 
 #ifdef CONFIG_CPU_USE_DOMAINS
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
index 984e0f29d548b..bd84e2db353b1 100644
--- a/arch/arm/lib/csumpartial.S
+++ b/arch/arm/lib/csumpartial.S
@@ -40,9 +40,9 @@ td3	.req	lr
 		/* we must have at least one byte. */
 		tst	buf, #1			@ odd address?
 		movne	sum, sum, ror #8
-		ldrneb	td0, [buf], #1
+		ldrbne	td0, [buf], #1
 		subne	len, len, #1
-		adcnes	sum, sum, td0, put_byte_1
+		adcsne	sum, sum, td0, put_byte_1
 
 .Lless4:		tst	len, #6
 		beq	.Lless8_byte
@@ -68,8 +68,8 @@ td3	.req	lr
 		bne	.Lless8_wordlp
 
 .Lless8_byte:	tst	len, #1			@ odd number of bytes
-		ldrneb	td0, [buf], #1		@ include last byte
-		adcnes	sum, sum, td0, put_byte_0	@ update checksum
+		ldrbne	td0, [buf], #1		@ include last byte
+		adcsne	sum, sum, td0, put_byte_0	@ update checksum
 
 .Ldone:		adc	r0, sum, #0		@ collect up the last carry
 		ldr	td0, [sp], #4
@@ -78,17 +78,17 @@ td3	.req	lr
 		ldr	pc, [sp], #4		@ return
 
 .Lnot_aligned:	tst	buf, #1			@ odd address
-		ldrneb	td0, [buf], #1		@ make even
+		ldrbne	td0, [buf], #1		@ make even
 		subne	len, len, #1
-		adcnes	sum, sum, td0, put_byte_1	@ update checksum
+		adcsne	sum, sum, td0, put_byte_1	@ update checksum
 
 		tst	buf, #2			@ 32-bit aligned?
 #if __LINUX_ARM_ARCH__ >= 4
-		ldrneh	td0, [buf], #2		@ make 32-bit aligned
+		ldrhne	td0, [buf], #2		@ make 32-bit aligned
 		subne	len, len, #2
 #else
-		ldrneb	td0, [buf], #1
-		ldrneb	ip, [buf], #1
+		ldrbne	td0, [buf], #1
+		ldrbne	ip, [buf], #1
 		subne	len, len, #2
 #ifndef __ARMEB__
 		orrne	td0, td0, ip, lsl #8
@@ -96,7 +96,7 @@ td3	.req	lr
 		orrne	td0, ip, td0, lsl #8
 #endif
 #endif
-		adcnes	sum, sum, td0		@ update checksum
+		adcsne	sum, sum, td0		@ update checksum
 		ret	lr
 
 ENTRY(csum_partial)
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index 10b45909610ca..08e17758cbea9 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -148,9 +148,9 @@ FN_ENTRY
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_2
 .Lexit:		tst	len, #1
-		strneb	r5, [dst], #1
+		strbne	r5, [dst], #1
 		andne	r5, r5, #255
-		adcnes	sum, sum, r5, put_byte_0
+		adcsne	sum, sum, r5, put_byte_0
 
 		/*
 		 * If the dst pointer was not 16-bit aligned, we
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index b83fdc06286a6..f4716d98e0b4a 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -95,7 +95,7 @@
 		add	r2, r2, r1
 		mov	r0, #0			@ zero the buffer
 9002:		teq	r2, r1
-		strneb	r0, [r1], #1
+		strbne	r0, [r1], #1
 		bne	9002b
 		load_regs
 		.popsection
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index a9eafe4981eb8..4d80f690c48bf 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -88,8 +88,8 @@ UNWIND(.fnstart)
  	@ Break out early if dividend reaches 0.
 2:	cmp	xh, yl
 	orrcs	yh, yh, ip
-	subcss	xh, xh, yl
-	movnes	ip, ip, lsr #1
+	subscs	xh, xh, yl
+	movsne	ip, ip, lsr #1
 	mov	yl, yl, lsr #1
 	bne	2b
 
diff --git a/arch/arm/lib/floppydma.S b/arch/arm/lib/floppydma.S
index 617150b1baef0..de68d3b343e30 100644
--- a/arch/arm/lib/floppydma.S
+++ b/arch/arm/lib/floppydma.S
@@ -14,8 +14,8 @@
 		.global	floppy_fiqin_end
 ENTRY(floppy_fiqin_start)
 		subs	r9, r9, #1
-		ldrgtb	r12, [r11, #-4]
-		ldrleb	r12, [r11], #0
+		ldrbgt	r12, [r11, #-4]
+		ldrble	r12, [r11], #0
 		strb	r12, [r10], #1
 		subs	pc, lr, #4
 floppy_fiqin_end:
@@ -23,10 +23,10 @@ floppy_fiqin_end:
 		.global	floppy_fiqout_end
 ENTRY(floppy_fiqout_start)
 		subs	r9, r9, #1
-		ldrgeb	r12, [r10], #1
+		ldrbge	r12, [r10], #1
 		movlt	r12, #0
-		strleb	r12, [r11], #0
-		subles	pc, lr, #4
+		strble	r12, [r11], #0
+		subsle	pc, lr, #4
 		strb	r12, [r11, #-4]
 		subs	pc, lr, #4
 floppy_fiqout_end:
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
index c31b2f3153f17..91038a0a77b57 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib/io-readsb.S
@@ -16,10 +16,10 @@
 		cmp	ip, #2
 		ldrb	r3, [r0]
 		strb	r3, [r1], #1
-		ldrgeb	r3, [r0]
-		strgeb	r3, [r1], #1
-		ldrgtb	r3, [r0]
-		strgtb	r3, [r1], #1
+		ldrbge	r3, [r0]
+		strbge	r3, [r1], #1
+		ldrbgt	r3, [r0]
+		strbgt	r3, [r1], #1
 		subs	r2, r2, ip
 		bne	.Linsb_aligned
 
@@ -72,7 +72,7 @@ ENTRY(__raw_readsb)
 		bpl	.Linsb_16_lp
 
 		tst	r2, #15
-		ldmeqfd	sp!, {r4 - r6, pc}
+		ldmfdeq	sp!, {r4 - r6, pc}
 
 .Linsb_no_16:	tst	r2, #8
 		beq	.Linsb_no_8
@@ -109,15 +109,15 @@ ENTRY(__raw_readsb)
 		str	r3, [r1], #4
 
 .Linsb_no_4:	ands	r2, r2, #3
-		ldmeqfd	sp!, {r4 - r6, pc}
+		ldmfdeq	sp!, {r4 - r6, pc}
 
 		cmp	r2, #2
 		ldrb	r3, [r0]
 		strb	r3, [r1], #1
-		ldrgeb	r3, [r0]
-		strgeb	r3, [r1], #1
-		ldrgtb	r3, [r0]
-		strgtb	r3, [r1]
+		ldrbge	r3, [r0]
+		strbge	r3, [r1], #1
+		ldrbgt	r3, [r0]
+		strbgt	r3, [r1]
 
 		ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(__raw_readsb)
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 2ed86fa5465f7..f2e2064318d21 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -30,7 +30,7 @@ ENTRY(__raw_readsl)
 2:		movs	r2, r2, lsl #31
 		ldrcs	r3, [r0, #0]
 		ldrcs	ip, [r0, #0]
-		stmcsia	r1!, {r3, ip}
+		stmiacs	r1!, {r3, ip}
 		ldrne	r3, [r0, #0]
 		strne	r3, [r1, #0]
 		ret	lr
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
index 413da99145292..8b25b69c516e7 100644
--- a/arch/arm/lib/io-readsw-armv3.S
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -68,7 +68,7 @@ ENTRY(__raw_readsw)
 		bpl	.Linsw_8_lp
 
 		tst	r2, #7
-		ldmeqfd	sp!, {r4, r5, r6, pc}
+		ldmfdeq	sp!, {r4, r5, r6, pc}
 
 .Lno_insw_8:	tst	r2, #4
 		beq	.Lno_insw_4
@@ -97,9 +97,9 @@ ENTRY(__raw_readsw)
 
 .Lno_insw_2:	tst	r2, #1
 		ldrne	r3, [r0]
-		strneb	r3, [r1], #1
+		strbne	r3, [r1], #1
 		movne	r3, r3, lsr #8
-		strneb	r3, [r1]
+		strbne	r3, [r1]
 
 		ldmfd	sp!, {r4, r5, r6, pc}
 
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
index d9a45e9692aee..5efdd66f5dcd6 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -76,8 +76,8 @@ ENTRY(__raw_readsw)
 		pack	r3, r3, ip
 		str	r3, [r1], #4
 
-.Lno_insw_2:	ldrneh	r3, [r0]
-		strneh	r3, [r1]
+.Lno_insw_2:	ldrhne	r3, [r0]
+		strhne	r3, [r1]
 
 		ldmfd	sp!, {r4, r5, pc}
 
@@ -94,7 +94,7 @@ ENTRY(__raw_readsw)
 #endif
 
 .Linsw_noalign:	stmfd	sp!, {r4, lr}
-		ldrccb	ip, [r1, #-1]!
+		ldrbcc	ip, [r1, #-1]!
 		bcc	1f
 
 		ldrh	ip, [r0]
@@ -121,11 +121,11 @@ ENTRY(__raw_readsw)
 
 3:		tst	r2, #1
 		strb	ip, [r1], #1
-		ldrneh	ip, [r0]
+		ldrhne	ip, [r0]
    _BE_ONLY_(	movne	ip, ip, ror #8		)
-		strneb	ip, [r1], #1
+		strbne	ip, [r1], #1
    _LE_ONLY_(	movne	ip, ip, lsr #8		)
    _BE_ONLY_(	movne	ip, ip, lsr #24		)
-		strneb	ip, [r1]
+		strbne	ip, [r1]
 		ldmfd	sp!, {r4, pc}
 ENDPROC(__raw_readsw)
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S
index a46bbc9b168b4..7d2881a2381eb 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib/io-writesb.S
@@ -36,10 +36,10 @@
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
 		strb	r3, [r0]
-		ldrgeb	r3, [r1], #1
-		strgeb	r3, [r0]
-		ldrgtb	r3, [r1], #1
-		strgtb	r3, [r0]
+		ldrbge	r3, [r1], #1
+		strbge	r3, [r0]
+		ldrbgt	r3, [r1], #1
+		strbgt	r3, [r0]
 		subs	r2, r2, ip
 		bne	.Loutsb_aligned
 
@@ -64,7 +64,7 @@ ENTRY(__raw_writesb)
 		bpl	.Loutsb_16_lp
 
 		tst	r2, #15
-		ldmeqfd	sp!, {r4, r5, pc}
+		ldmfdeq	sp!, {r4, r5, pc}
 
 .Loutsb_no_16:	tst	r2, #8
 		beq	.Loutsb_no_8
@@ -80,15 +80,15 @@ ENTRY(__raw_writesb)
 		outword	r3
 
 .Loutsb_no_4:	ands	r2, r2, #3
-		ldmeqfd	sp!, {r4, r5, pc}
+		ldmfdeq	sp!, {r4, r5, pc}
 
 		cmp	r2, #2
 		ldrb	r3, [r1], #1
 		strb	r3, [r0]
-		ldrgeb	r3, [r1], #1
-		strgeb	r3, [r0]
-		ldrgtb	r3, [r1]
-		strgtb	r3, [r0]
+		ldrbge	r3, [r1], #1
+		strbge	r3, [r0]
+		ldrbgt	r3, [r1]
+		strbgt	r3, [r0]
 
 		ldmfd	sp!, {r4, r5, pc}
 ENDPROC(__raw_writesb)
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 4ea2435988c1f..7596ac0c90b05 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -28,7 +28,7 @@ ENTRY(__raw_writesl)
 		bpl	1b
 		ldmfd	sp!, {r4, lr}
 2:		movs	r2, r2, lsl #31
-		ldmcsia	r1!, {r3, ip}
+		ldmiacs	r1!, {r3, ip}
 		strcs	r3, [r0, #0]
 		ldrne	r3, [r1, #0]
 		strcs	ip, [r0, #0]
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
index 121789eb68023..cb94b9b494056 100644
--- a/arch/arm/lib/io-writesw-armv3.S
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -79,7 +79,7 @@ ENTRY(__raw_writesw)
 		bpl	.Loutsw_8_lp
 
 		tst	r2, #7
-		ldmeqfd	sp!, {r4, r5, r6, pc}
+		ldmfdeq	sp!, {r4, r5, r6, pc}
 
 .Lno_outsw_8:	tst	r2, #4
 		beq	.Lno_outsw_4
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index 269f90c51ad27..e6645b2f249ef 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -61,8 +61,8 @@ ENTRY(__raw_writesw)
 		ldr	r3, [r1], #4
 		outword	r3
 
-.Lno_outsw_2:	ldrneh	r3, [r1]
-		strneh	r3, [r0]
+.Lno_outsw_2:	ldrhne	r3, [r1]
+		strhne	r3, [r0]
 
 		ldmfd	sp!, {r4, r5, pc}
 
@@ -95,6 +95,6 @@ ENTRY(__raw_writesw)
 
 		tst	r2, #1
 3:		movne	ip, r3, lsr #8
-		strneh	ip, [r0]
+		strhne	ip, [r0]
 		ret	lr
 ENDPROC(__raw_writesw)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 9397b2e532afa..c23f9d9e29704 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -96,7 +96,7 @@ Boston, MA 02111-1307, USA.  */
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	orrhs	\result,   \result,   \curbit,  lsr #3
 	cmp	\dividend, #0			@ Early termination?
-	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movsne	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
 	movne	\divisor,  \divisor, lsr #4
 	bne	1b
 
@@ -182,7 +182,7 @@ Boston, MA 02111-1307, USA.  */
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	cmp	\dividend, #1
 	mov	\divisor, \divisor, lsr #4
-	subges	\order, \order, #4
+	subsge	\order, \order, #4
 	bge	1b
 
 	tst	\order, #3
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 64111bd4440b1..4a6997bb44043 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -30,7 +30,7 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
-	ldr\cond\()b \reg, [\ptr], #1
+	ldrb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro str1w ptr reg abort
@@ -42,7 +42,7 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
-	str\cond\()b \reg, [\ptr], #1
+	strb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro enter reg1 reg2
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 69a9d47fc5abd..d70304cb2cd0d 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -59,7 +59,7 @@ ENTRY(memmove)
 		blt	5f
 
 	CALGN(	ands	ip, r0, #31		)
-	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
 	CALGN(	bcs	2f			)
 	CALGN(	adr	r4, 6f			)
 	CALGN(	subs	r2, r2, ip		)  @ C is set here
@@ -114,20 +114,20 @@ ENTRY(memmove)
 	UNWIND(	.save	{r0, r4, lr}		) @ still in first stmfd block
 
 8:		movs	r2, r2, lsl #31
-		ldrneb	r3, [r1, #-1]!
-		ldrcsb	r4, [r1, #-1]!
-		ldrcsb	ip, [r1, #-1]
-		strneb	r3, [r0, #-1]!
-		strcsb	r4, [r0, #-1]!
-		strcsb	ip, [r0, #-1]
+		ldrbne	r3, [r1, #-1]!
+		ldrbcs	r4, [r1, #-1]!
+		ldrbcs	ip, [r1, #-1]
+		strbne	r3, [r0, #-1]!
+		strbcs	r4, [r0, #-1]!
+		strbcs	ip, [r0, #-1]
 		ldmfd	sp!, {r0, r4, pc}
 
 9:		cmp	ip, #2
-		ldrgtb	r3, [r1, #-1]!
-		ldrgeb	r4, [r1, #-1]!
+		ldrbgt	r3, [r1, #-1]!
+		ldrbge	r4, [r1, #-1]!
 		ldrb	lr, [r1, #-1]!
-		strgtb	r3, [r0, #-1]!
-		strgeb	r4, [r0, #-1]!
+		strbgt	r3, [r0, #-1]!
+		strbge	r4, [r0, #-1]!
 		subs	r2, r2, ip
 		strb	lr, [r0, #-1]!
 		blt	8b
@@ -150,7 +150,7 @@ ENTRY(memmove)
 		blt	14f
 
 	CALGN(	ands	ip, r0, #31		)
-	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
 
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index ed6d35d9cdb5a..5593a45e0a8c6 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -44,20 +44,20 @@ UNWIND( .save {r8, lr}      )
 	mov	lr, r3
 
 2:	subs	r2, r2, #64
-	stmgeia	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
-	stmgeia	ip!, {r1, r3, r8, lr}
-	stmgeia	ip!, {r1, r3, r8, lr}
-	stmgeia	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
 	bgt	2b
-	ldmeqfd	sp!, {r8, pc}		@ Now <64 bytes to go.
+	ldmfdeq	sp!, {r8, pc}		@ Now <64 bytes to go.
 /*
  * No need to correct the count; we're only testing bits from now on
  */
 	tst	r2, #32
-	stmneia	ip!, {r1, r3, r8, lr}
-	stmneia	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
 	tst	r2, #16
-	stmneia	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
 	ldmfd	sp!, {r8, lr}
 UNWIND( .fnend              )
 
@@ -87,22 +87,22 @@ UNWIND( .save {r4-r8, lr}      )
 	rsb	r8, r8, #32
 	sub	r2, r2, r8
 	movs	r8, r8, lsl #(32 - 4)
-	stmcsia	ip!, {r4, r5, r6, r7}
-	stmmiia	ip!, {r4, r5}
+	stmiacs	ip!, {r4, r5, r6, r7}
+	stmiami	ip!, {r4, r5}
 	tst	r8, #(1 << 30)
 	mov	r8, r1
 	strne	r1, [ip], #4
 
 3:	subs	r2, r2, #64
-	stmgeia	ip!, {r1, r3-r8, lr}
-	stmgeia	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
 	bgt	3b
-	ldmeqfd	sp!, {r4-r8, pc}
+	ldmfdeq	sp!, {r4-r8, pc}
 
 	tst	r2, #32
-	stmneia	ip!, {r1, r3-r8, lr}
+	stmiane	ip!, {r1, r3-r8, lr}
 	tst	r2, #16
-	stmneia	ip!, {r4-r7}
+	stmiane	ip!, {r4-r7}
 	ldmfd	sp!, {r4-r8, lr}
 UNWIND( .fnend                 )
 
@@ -110,7 +110,7 @@ UNWIND( .fnend                 )
 
 UNWIND( .fnstart            )
 4:	tst	r2, #8
-	stmneia	ip!, {r1, r3}
+	stmiane	ip!, {r1, r3}
 	tst	r2, #4
 	strne	r1, [ip], #4
 /*
@@ -118,17 +118,17 @@ UNWIND( .fnstart            )
  * may have an unaligned pointer as well.
  */
 5:	tst	r2, #2
-	strneb	r1, [ip], #1
-	strneb	r1, [ip], #1
+	strbne	r1, [ip], #1
+	strbne	r1, [ip], #1
 	tst	r2, #1
-	strneb	r1, [ip], #1
+	strbne	r1, [ip], #1
 	ret	lr
 
 6:	subs	r2, r2, #4		@ 1 do we have enough
 	blt	5b			@ 1 bytes to align with?
 	cmp	r3, #2			@ 1
-	strltb	r1, [ip], #1		@ 1
-	strleb	r1, [ip], #1		@ 1
+	strblt	r1, [ip], #1		@ 1
+	strble	r1, [ip], #1		@ 1
 	strb	r1, [ip], #1		@ 1
 	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
 	b	1b
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index 2c40aeab3eaae..c691b901092f5 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -14,7 +14,7 @@
 MODULE_LICENSE("GPL");
 
 #ifndef __ARM_NEON__
-#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
 #endif
 
 /*
diff --git a/arch/arm/mach-actions/platsmp.c b/arch/arm/mach-actions/platsmp.c
index 3efaa10efc439..4fd479c948e67 100644
--- a/arch/arm/mach-actions/platsmp.c
+++ b/arch/arm/mach-actions/platsmp.c
@@ -39,10 +39,6 @@ static void __iomem *sps_base_addr;
 static void __iomem *timer_base_addr;
 static int ncores;
 
-static DEFINE_SPINLOCK(boot_lock);
-
-void owl_secondary_startup(void);
-
 static int s500_wakeup_secondary(unsigned int cpu)
 {
 	int ret;
@@ -84,7 +80,6 @@ static int s500_wakeup_secondary(unsigned int cpu)
 
 static int s500_smp_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	unsigned long timeout;
 	int ret;
 
 	ret = s500_wakeup_secondary(cpu);
@@ -93,21 +88,11 @@ static int s500_smp_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 	udelay(10);
 
-	spin_lock(&boot_lock);
-
 	smp_send_reschedule(cpu);
 
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (pen_release == -1)
-			break;
-	}
-
 	writel(0, timer_base_addr + OWL_CPU1_ADDR + (cpu - 1) * 4);
 	writel(0, timer_base_addr + OWL_CPU1_FLAG + (cpu - 1) * 4);
 
-	spin_unlock(&boot_lock);
-
 	return 0;
 }
 
diff --git a/arch/arm/mach-exynos/headsmp.S b/arch/arm/mach-exynos/headsmp.S
index 005695c9bf400..0ac2cb9a73556 100644
--- a/arch/arm/mach-exynos/headsmp.S
+++ b/arch/arm/mach-exynos/headsmp.S
@@ -36,4 +36,4 @@ ENDPROC(exynos4_secondary_startup)
 
 	.align 2
 1:	.long	.
-	.long	pen_release
+	.long	exynos_pen_release
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index b6da7edbbd2fd..abcac61642331 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -28,6 +28,9 @@
 
 extern void exynos4_secondary_startup(void);
 
+/* XXX exynos_pen_release is cargo culted code - DO NOT COPY XXX */
+volatile int exynos_pen_release = -1;
+
 #ifdef CONFIG_HOTPLUG_CPU
 static inline void cpu_leave_lowpower(u32 core_id)
 {
@@ -57,7 +60,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 
 		wfi();
 
-		if (pen_release == core_id) {
+		if (exynos_pen_release == core_id) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */
@@ -228,15 +231,17 @@ void exynos_core_restart(u32 core_id)
 }
 
 /*
- * Write pen_release in a way that is guaranteed to be visible to all
- * observers, irrespective of whether they're taking part in coherency
+ * XXX CARGO CULTED CODE - DO NOT COPY XXX
+ *
+ * Write exynos_pen_release in a way that is guaranteed to be visible to
+ * all observers, irrespective of whether they're taking part in coherency
  * or not.  This is necessary for the hotplug code to work reliably.
  */
-static void write_pen_release(int val)
+static void exynos_write_pen_release(int val)
 {
-	pen_release = val;
+	exynos_pen_release = val;
 	smp_wmb();
-	sync_cache_w(&pen_release);
+	sync_cache_w(&exynos_pen_release);
 }
 
 static DEFINE_SPINLOCK(boot_lock);
@@ -247,7 +252,7 @@ static void exynos_secondary_init(unsigned int cpu)
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	write_pen_release(-1);
+	exynos_write_pen_release(-1);
 
 	/*
 	 * Synchronise with the boot thread.
@@ -322,12 +327,12 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	/*
 	 * The secondary processor is waiting to be released from
 	 * the holding pen - release it, then wait for it to flag
-	 * that it has been released by resetting pen_release.
+	 * that it has been released by resetting exynos_pen_release.
 	 *
-	 * Note that "pen_release" is the hardware CPU core ID, whereas
+	 * Note that "exynos_pen_release" is the hardware CPU core ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	write_pen_release(core_id);
+	exynos_write_pen_release(core_id);
 
 	if (!exynos_cpu_power_state(core_id)) {
 		exynos_cpu_power_up(core_id);
@@ -376,13 +381,13 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		else
 			arch_send_wakeup_ipi_mask(cpumask_of(cpu));
 
-		if (pen_release == -1)
+		if (exynos_pen_release == -1)
 			break;
 
 		udelay(10);
 	}
 
-	if (pen_release != -1)
+	if (exynos_pen_release != -1)
 		ret = -ETIMEDOUT;
 
 	/*
@@ -392,7 +397,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 fail:
 	spin_unlock(&boot_lock);
 
-	return pen_release != -1 ? ret : 0;
+	return exynos_pen_release != -1 ? ret : 0;
 }
 
 static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/arm/mach-ks8695/include/mach/entry-macro.S b/arch/arm/mach-ks8695/include/mach/entry-macro.S
index 8315b34f32ff0..7ff812cb010bb 100644
--- a/arch/arm/mach-ks8695/include/mach/entry-macro.S
+++ b/arch/arm/mach-ks8695/include/mach/entry-macro.S
@@ -42,6 +42,6 @@
 		moveq	\irqstat, \irqstat, lsr #2
 		addeq	\irqnr, \irqnr, #2
 		tst	\irqstat, #0x01
-		addeqs	\irqnr, \irqnr, #1
+		addseq	\irqnr, \irqnr, #1
 1001:
 	.endm
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 058a37e6d11c3..fd6e0671f9573 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -523,8 +523,10 @@ void omap_prm_reset_system(void)
 
 	prm_ll_data->reset_system();
 
-	while (1)
+	while (1) {
 		cpu_relax();
+		wfe();
+	}
 }
 
 /**
diff --git a/arch/arm/mach-oxnas/Makefile b/arch/arm/mach-oxnas/Makefile
index b625906a99702..61a34e1c0f221 100644
--- a/arch/arm/mach-oxnas/Makefile
+++ b/arch/arm/mach-oxnas/Makefile
@@ -1,2 +1 @@
 obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o
-obj-$(CONFIG_HOTPLUG_CPU) 	+= hotplug.o
diff --git a/arch/arm/mach-oxnas/hotplug.c b/arch/arm/mach-oxnas/hotplug.c
deleted file mode 100644
index 854f29b8cba6e..0000000000000
--- a/arch/arm/mach-oxnas/hotplug.c
+++ /dev/null
@@ -1,109 +0,0 @@
-/*
- *  Copyright (C) 2002 ARM Ltd.
- *  All Rights Reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/smp.h>
-
-#include <asm/cp15.h>
-#include <asm/smp_plat.h>
-
-static inline void cpu_enter_lowpower(void)
-{
-	unsigned int v;
-
-	asm volatile(
-	"	mcr	p15, 0, %1, c7, c5, 0\n"
-	"	mcr	p15, 0, %1, c7, c10, 4\n"
-	/*
-	 * Turn off coherency
-	 */
-	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	bic	%0, %0, #0x20\n"
-	"	mcr	p15, 0, %0, c1, c0, 1\n"
-	"	mrc	p15, 0, %0, c1, c0, 0\n"
-	"	bic	%0, %0, %2\n"
-	"	mcr	p15, 0, %0, c1, c0, 0\n"
-	  : "=&r" (v)
-	  : "r" (0), "Ir" (CR_C)
-	  : "cc");
-}
-
-static inline void cpu_leave_lowpower(void)
-{
-	unsigned int v;
-
-	asm volatile(	"mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, %1\n"
-	"	mcr	p15, 0, %0, c1, c0, 0\n"
-	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	orr	%0, %0, #0x20\n"
-	"	mcr	p15, 0, %0, c1, c0, 1\n"
-	  : "=&r" (v)
-	  : "Ir" (CR_C)
-	  : "cc");
-}
-
-static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
-{
-	/*
-	 * there is no power-control hardware on this platform, so all
-	 * we can do is put the core into WFI; this is safe as the calling
-	 * code will have already disabled interrupts
-	 */
-	for (;;) {
-		/*
-		 * here's the WFI
-		 */
-		asm(".word	0xe320f003\n"
-		    :
-		    :
-		    : "memory", "cc");
-
-		if (pen_release == cpu_logical_map(cpu)) {
-			/*
-			 * OK, proper wakeup, we're done
-			 */
-			break;
-		}
-
-		/*
-		 * Getting here, means that we have come out of WFI without
-		 * having been woken up - this shouldn't happen
-		 *
-		 * Just note it happening - when we're woken, we can report
-		 * its occurrence.
-		 */
-		(*spurious)++;
-	}
-}
-
-/*
- * platform-specific code to shutdown a CPU
- *
- * Called with IRQs disabled
- */
-void ox820_cpu_die(unsigned int cpu)
-{
-	int spurious = 0;
-
-	/*
-	 * we're ready for shutdown now, so do it
-	 */
-	cpu_enter_lowpower();
-	platform_do_lowpower(cpu, &spurious);
-
-	/*
-	 * bring this CPU back into the world of cache
-	 * coherency, and then restore interrupts
-	 */
-	cpu_leave_lowpower();
-
-	if (spurious)
-		pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious);
-}
diff --git a/arch/arm/mach-oxnas/platsmp.c b/arch/arm/mach-oxnas/platsmp.c
index 442cc8a2f7dc8..735141c0e3a37 100644
--- a/arch/arm/mach-oxnas/platsmp.c
+++ b/arch/arm/mach-oxnas/platsmp.c
@@ -19,7 +19,6 @@
 #include <asm/smp_scu.h>
 
 extern void ox820_secondary_startup(void);
-extern void ox820_cpu_die(unsigned int cpu);
 
 static void __iomem *cpu_ctrl;
 static void __iomem *gic_cpu_ctrl;
@@ -94,9 +93,6 @@ unmap_scu:
 static const struct smp_operations ox820_smp_ops __initconst = {
 	.smp_prepare_cpus	= ox820_smp_prepare_cpus,
 	.smp_boot_secondary	= ox820_boot_secondary,
-#ifdef CONFIG_HOTPLUG_CPU
-	.cpu_die		= ox820_cpu_die,
-#endif
 };
 
 CPU_METHOD_OF_DECLARE(ox820_smp, "oxsemi,ox820-smp", &ox820_smp_ops);
diff --git a/arch/arm/mach-prima2/common.h b/arch/arm/mach-prima2/common.h
index 6d77b622d1685..457eb7b181600 100644
--- a/arch/arm/mach-prima2/common.h
+++ b/arch/arm/mach-prima2/common.h
@@ -15,6 +15,8 @@
 #include <asm/mach/time.h>
 #include <asm/exception.h>
 
+extern volatile int prima2_pen_release;
+
 extern const struct smp_operations sirfsoc_smp_ops;
 extern void sirfsoc_secondary_startup(void);
 extern void sirfsoc_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-prima2/headsmp.S b/arch/arm/mach-prima2/headsmp.S
index 209d9fc5c16cf..6cf4fc60347b5 100644
--- a/arch/arm/mach-prima2/headsmp.S
+++ b/arch/arm/mach-prima2/headsmp.S
@@ -34,4 +34,4 @@ ENDPROC(sirfsoc_secondary_startup)
 
         .align
 1:      .long   .
-        .long   pen_release
+        .long   prima2_pen_release
diff --git a/arch/arm/mach-prima2/hotplug.c b/arch/arm/mach-prima2/hotplug.c
index a728c78b996f7..b6cf1527e3309 100644
--- a/arch/arm/mach-prima2/hotplug.c
+++ b/arch/arm/mach-prima2/hotplug.c
@@ -11,6 +11,7 @@
 #include <linux/smp.h>
 
 #include <asm/smp_plat.h>
+#include "common.h"
 
 static inline void platform_do_lowpower(unsigned int cpu)
 {
@@ -18,7 +19,7 @@ static inline void platform_do_lowpower(unsigned int cpu)
 	for (;;) {
 		__asm__ __volatile__("dsb\n\t" "wfi\n\t"
 			: : : "memory");
-		if (pen_release == cpu_logical_map(cpu)) {
+		if (prima2_pen_release == cpu_logical_map(cpu)) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */
diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c
index 75ef5d4be554c..d1f8b5168083c 100644
--- a/arch/arm/mach-prima2/platsmp.c
+++ b/arch/arm/mach-prima2/platsmp.c
@@ -24,13 +24,16 @@ static void __iomem *clk_base;
 
 static DEFINE_SPINLOCK(boot_lock);
 
+/* XXX prima2_pen_release is cargo culted code - DO NOT COPY XXX */
+volatile int prima2_pen_release = -1;
+
 static void sirfsoc_secondary_init(unsigned int cpu)
 {
 	/*
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	pen_release = -1;
+	prima2_pen_release = -1;
 	smp_wmb();
 
 	/*
@@ -80,13 +83,13 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	/*
 	 * The secondary processor is waiting to be released from
 	 * the holding pen - release it, then wait for it to flag
-	 * that it has been released by resetting pen_release.
+	 * that it has been released by resetting prima2_pen_release.
 	 *
-	 * Note that "pen_release" is the hardware CPU ID, whereas
+	 * Note that "prima2_pen_release" is the hardware CPU ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	pen_release = cpu_logical_map(cpu);
-	sync_cache_w(&pen_release);
+	prima2_pen_release = cpu_logical_map(cpu);
+	sync_cache_w(&prima2_pen_release);
 
 	/*
 	 * Send the secondary CPU SEV, thereby causing the boot monitor to read
@@ -97,7 +100,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
 		smp_rmb();
-		if (pen_release == -1)
+		if (prima2_pen_release == -1)
 			break;
 
 		udelay(10);
@@ -109,7 +112,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 */
 	spin_unlock(&boot_lock);
 
-	return pen_release != -1 ? -ENOSYS : 0;
+	return prima2_pen_release != -1 ? -ENOSYS : 0;
 }
 
 const struct smp_operations sirfsoc_smp_ops __initconst = {
diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c
index 5494c9e0c909b..99a6a5e809e0e 100644
--- a/arch/arm/mach-qcom/platsmp.c
+++ b/arch/arm/mach-qcom/platsmp.c
@@ -46,8 +46,6 @@
 
 extern void secondary_startup_arm(void);
 
-static DEFINE_SPINLOCK(boot_lock);
-
 #ifdef CONFIG_HOTPLUG_CPU
 static void qcom_cpu_die(unsigned int cpu)
 {
@@ -55,15 +53,6 @@ static void qcom_cpu_die(unsigned int cpu)
 }
 #endif
 
-static void qcom_secondary_init(unsigned int cpu)
-{
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
-}
-
 static int scss_release_secondary(unsigned int cpu)
 {
 	struct device_node *node;
@@ -281,24 +270,12 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int))
 	}
 
 	/*
-	 * set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	spin_lock(&boot_lock);
-
-	/*
 	 * Send the secondary CPU a soft interrupt, thereby causing
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
 	arch_send_wakeup_ipi_mask(cpumask_of(cpu));
 
-	/*
-	 * now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	spin_unlock(&boot_lock);
-
 	return ret;
 }
 
@@ -334,7 +311,6 @@ static void __init qcom_smp_prepare_cpus(unsigned int max_cpus)
 
 static const struct smp_operations smp_msm8660_ops __initconst = {
 	.smp_prepare_cpus	= qcom_smp_prepare_cpus,
-	.smp_secondary_init	= qcom_secondary_init,
 	.smp_boot_secondary	= msm8660_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= qcom_cpu_die,
@@ -344,7 +320,6 @@ CPU_METHOD_OF_DECLARE(qcom_smp, "qcom,gcc-msm8660", &smp_msm8660_ops);
 
 static const struct smp_operations qcom_smp_kpssv1_ops __initconst = {
 	.smp_prepare_cpus	= qcom_smp_prepare_cpus,
-	.smp_secondary_init	= qcom_secondary_init,
 	.smp_boot_secondary	= kpssv1_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= qcom_cpu_die,
@@ -354,7 +329,6 @@ CPU_METHOD_OF_DECLARE(qcom_smp_kpssv1, "qcom,kpss-acc-v1", &qcom_smp_kpssv1_ops)
 
 static const struct smp_operations qcom_smp_kpssv2_ops __initconst = {
 	.smp_prepare_cpus	= qcom_smp_prepare_cpus,
-	.smp_secondary_init	= qcom_secondary_init,
 	.smp_boot_secondary	= kpssv2_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= qcom_cpu_die,
diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h
index 909b97c0b2371..25b4c5e66e396 100644
--- a/arch/arm/mach-spear/generic.h
+++ b/arch/arm/mach-spear/generic.h
@@ -20,6 +20,8 @@
 
 #include <asm/mach/time.h>
 
+extern volatile int spear_pen_release;
+
 extern void spear13xx_timer_init(void);
 extern void spear3xx_timer_init(void);
 extern struct pl022_ssp_controller pl022_plat_data;
diff --git a/arch/arm/mach-spear/headsmp.S b/arch/arm/mach-spear/headsmp.S
index c52192dc3d9f9..6e250b6c0aa23 100644
--- a/arch/arm/mach-spear/headsmp.S
+++ b/arch/arm/mach-spear/headsmp.S
@@ -43,5 +43,5 @@ pen:	ldr	r7, [r6]
 
 	.align
 1:	.long	.
-	.long	pen_release
+	.long	spear_pen_release
 ENDPROC(spear13xx_secondary_startup)
diff --git a/arch/arm/mach-spear/hotplug.c b/arch/arm/mach-spear/hotplug.c
index 12edd1cf8a12f..0dd84f609627a 100644
--- a/arch/arm/mach-spear/hotplug.c
+++ b/arch/arm/mach-spear/hotplug.c
@@ -16,6 +16,8 @@
 #include <asm/cp15.h>
 #include <asm/smp_plat.h>
 
+#include "generic.h"
+
 static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
@@ -57,7 +59,7 @@ static inline void spear13xx_do_lowpower(unsigned int cpu, int *spurious)
 	for (;;) {
 		wfi();
 
-		if (pen_release == cpu) {
+		if (spear_pen_release == cpu) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */
diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
index 39038a03836ac..b1ff4bb86f6d8 100644
--- a/arch/arm/mach-spear/platsmp.c
+++ b/arch/arm/mach-spear/platsmp.c
@@ -20,16 +20,21 @@
 #include <mach/spear.h>
 #include "generic.h"
 
+/* XXX spear_pen_release is cargo culted code - DO NOT COPY XXX */
+volatile int spear_pen_release = -1;
+
 /*
- * Write pen_release in a way that is guaranteed to be visible to all
- * observers, irrespective of whether they're taking part in coherency
+ * XXX CARGO CULTED CODE - DO NOT COPY XXX
+ *
+ * Write spear_pen_release in a way that is guaranteed to be visible to
+ * all observers, irrespective of whether they're taking part in coherency
  * or not.  This is necessary for the hotplug code to work reliably.
  */
-static void write_pen_release(int val)
+static void spear_write_pen_release(int val)
 {
-	pen_release = val;
+	spear_pen_release = val;
 	smp_wmb();
-	sync_cache_w(&pen_release);
+	sync_cache_w(&spear_pen_release);
 }
 
 static DEFINE_SPINLOCK(boot_lock);
@@ -42,7 +47,7 @@ static void spear13xx_secondary_init(unsigned int cpu)
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	write_pen_release(-1);
+	spear_write_pen_release(-1);
 
 	/*
 	 * Synchronise with the boot thread.
@@ -64,17 +69,17 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	/*
 	 * The secondary processor is waiting to be released from
 	 * the holding pen - release it, then wait for it to flag
-	 * that it has been released by resetting pen_release.
+	 * that it has been released by resetting spear_pen_release.
 	 *
-	 * Note that "pen_release" is the hardware CPU ID, whereas
+	 * Note that "spear_pen_release" is the hardware CPU ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	write_pen_release(cpu);
+	spear_write_pen_release(cpu);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
 		smp_rmb();
-		if (pen_release == -1)
+		if (spear_pen_release == -1)
 			break;
 
 		udelay(10);
@@ -86,7 +91,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 */
 	spin_unlock(&boot_lock);
 
-	return pen_release != -1 ? -ENOSYS : 0;
+	return spear_pen_release != -1 ? -ENOSYS : 0;
 }
 
 /*
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 805f306fa6f70..e22ccf87eded3 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -172,7 +172,7 @@ after_errata:
 	mov32	r5, TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET
 	mov	r0, #CPU_NOT_RESETTABLE
 	cmp	r10, #0
-	strneb	r0, [r5, #__tegra20_cpu1_resettable_status_offset]
+	strbne	r0, [r5, #__tegra20_cpu1_resettable_status_offset]
 1:
 #endif
 
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 24659952c2784..be68d62566c7c 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -215,8 +215,8 @@ v6_dma_inv_range:
 #endif
 	tst	r1, #D_CACHE_LINE_SIZE - 1
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldrneb	r2, [r1, #-1]			@ read for ownership
-	strneb	r2, [r1, #-1]			@ write for ownership
+	ldrbne	r2, [r1, #-1]			@ read for ownership
+	strbne	r2, [r1, #-1]			@ write for ownership
 #endif
 	bic	r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -284,8 +284,8 @@ ENTRY(v6_dma_flush_range)
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldrlob	r2, [r0]			@ read for ownership
-	strlob	r2, [r0]			@ write for ownership
+	ldrblo	r2, [r0]			@ read for ownership
+	strblo	r2, [r0]			@ write for ownership
 #endif
 	blo	1b
 	mov	r0, #0
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index b03202cddddb2..f74cdce6d4dad 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -45,6 +45,7 @@ static void mc_copy_user_page(void *from, void *to)
 	int tmp;
 
 	asm volatile ("\
+	.syntax unified\n\
 	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
 1:	mcr	p15, 0, %1, c7, c6, 1		@ 1   invalidate D line\n\
 	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
@@ -56,7 +57,7 @@ static void mc_copy_user_page(void *from, void *to)
 	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
 	subs	%2, %2, #1			@ 1\n\
 	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
-	ldmneia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	ldmiane	%0!, {r2, r3, ip, lr}		@ 4\n\
 	bne	1b				@ "
 	: "+&r" (from), "+&r" (to), "=&r" (tmp)
 	: "2" (PAGE_SIZE / 64)
diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c
index cd3e165afeede..6d336740aae49 100644
--- a/arch/arm/mm/copypage-v4wb.c
+++ b/arch/arm/mm/copypage-v4wb.c
@@ -27,6 +27,7 @@ static void v4wb_copy_user_page(void *kto, const void *kfrom)
 	int tmp;
 
 	asm volatile ("\
+	.syntax unified\n\
 	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
 1:	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
 	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
@@ -38,7 +39,7 @@ static void v4wb_copy_user_page(void *kto, const void *kfrom)
 	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
 	subs	%2, %2, #1			@ 1\n\
 	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmneia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	ldmiane	%1!, {r3, r4, ip, lr}		@ 4\n\
 	bne	1b				@ 1\n\
 	mcr	p15, 0, %1, c7, c10, 4		@ 1   drain WB"
 	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c
index 8614572e1296b..3851bb3964428 100644
--- a/arch/arm/mm/copypage-v4wt.c
+++ b/arch/arm/mm/copypage-v4wt.c
@@ -25,6 +25,7 @@ static void v4wt_copy_user_page(void *kto, const void *kfrom)
 	int tmp;
 
 	asm volatile ("\
+	.syntax unified\n\
 	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
 1:	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
 	ldmia	%1!, {r3, r4, ip, lr}		@ 4+1\n\
@@ -34,7 +35,7 @@ static void v4wt_copy_user_page(void *kto, const void *kfrom)
 	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
 	subs	%2, %2, #1			@ 1\n\
 	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmneia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	ldmiane	%1!, {r3, r4, ip, lr}		@ 4\n\
 	bne	1b				@ 1\n\
 	mcr	p15, 0, %2, c7, c7, 0		@ flush ID cache"
 	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c6aab9c36ff18..43f46aa7ef335 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2279,7 +2279,7 @@ EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
  * @dev: valid struct device pointer
  *
  * Detaches the provided device from a previously attached map.
- * This voids the dma operations (dma_map_ops pointer)
+ * This overwrites the dma_ops pointer with appropriate non-IOMMU ops.
  */
 void arm_iommu_detach_device(struct device *dev)
 {
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 1d1edd0641995..a033f6134a649 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -6,6 +6,7 @@
 
 #include <asm/cputype.h>
 #include <asm/idmap.h>
+#include <asm/hwcap.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
@@ -110,7 +111,8 @@ static int __init init_static_idmap(void)
 			     __idmap_text_end, 0);
 
 	/* Flush L1 for the hardware to see this page table content */
-	flush_cache_louis();
+	if (!(elf_hwcap & HWCAP_LPAE))
+		flush_cache_louis();
 
 	return 0;
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 15dddfe433195..c2daabbe0af05 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -282,15 +282,12 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
 
 void __init bootmem_init(void)
 {
-	unsigned long min, max_low, max_high;
-
 	memblock_allow_resize();
-	max_low = max_high = 0;
 
-	find_limits(&min, &max_low, &max_high);
+	find_limits(&min_low_pfn, &max_low_pfn, &max_pfn);
 
-	early_memtest((phys_addr_t)min << PAGE_SHIFT,
-		      (phys_addr_t)max_low << PAGE_SHIFT);
+	early_memtest((phys_addr_t)min_low_pfn << PAGE_SHIFT,
+		      (phys_addr_t)max_low_pfn << PAGE_SHIFT);
 
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(),
@@ -308,16 +305,7 @@ void __init bootmem_init(void)
 	 * the sparse mem_map arrays initialized by sparse_init()
 	 * for memmap_init_zone(), otherwise all PFNs are invalid.
 	 */
-	zone_sizes_init(min, max_low, max_high);
-
-	/*
-	 * This doesn't seem to be used by the Linux memory manager any
-	 * more, but is used by ll_rw_block.  If we can get rid of it, we
-	 * also get rid of some of the stuff above as well.
-	 */
-	min_low_pfn = min;
-	max_low_pfn = max_low;
-	max_pfn = max_high;
+	zone_sizes_init(min_low_pfn, max_low_pfn, max_pfn);
 }
 
 /*
@@ -498,55 +486,6 @@ void __init mem_init(void)
 
 	mem_init_print_info(NULL);
 
-#define MLK(b, t) b, t, ((t) - (b)) >> 10
-#define MLM(b, t) b, t, ((t) - (b)) >> 20
-#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
-
-	pr_notice("Virtual kernel memory layout:\n"
-			"    vector  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#ifdef CONFIG_HAVE_TCM
-			"    DTCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-			"    ITCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#endif
-			"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-			"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-			"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#ifdef CONFIG_HIGHMEM
-			"    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#endif
-#ifdef CONFIG_MODULES
-			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#endif
-			"      .text : 0x%p" " - 0x%p" "   (%4td kB)\n"
-			"      .init : 0x%p" " - 0x%p" "   (%4td kB)\n"
-			"      .data : 0x%p" " - 0x%p" "   (%4td kB)\n"
-			"       .bss : 0x%p" " - 0x%p" "   (%4td kB)\n",
-
-			MLK(VECTORS_BASE, VECTORS_BASE + PAGE_SIZE),
-#ifdef CONFIG_HAVE_TCM
-			MLK(DTCM_OFFSET, (unsigned long) dtcm_end),
-			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
-#endif
-			MLK(FIXADDR_START, FIXADDR_END),
-			MLM(VMALLOC_START, VMALLOC_END),
-			MLM(PAGE_OFFSET, (unsigned long)high_memory),
-#ifdef CONFIG_HIGHMEM
-			MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) *
-				(PAGE_SIZE)),
-#endif
-#ifdef CONFIG_MODULES
-			MLM(MODULES_VADDR, MODULES_END),
-#endif
-
-			MLK_ROUNDUP(_text, _etext),
-			MLK_ROUNDUP(__init_begin, __init_end),
-			MLK_ROUNDUP(_sdata, _edata),
-			MLK_ROUNDUP(__bss_start, __bss_stop));
-
-#undef MLK
-#undef MLM
-#undef MLK_ROUNDUP
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can
 	 * be detected at build time already.
diff --git a/arch/arm/mm/pmsa-v8.c b/arch/arm/mm/pmsa-v8.c
index 617a83def88a9..0d7d5fb59247d 100644
--- a/arch/arm/mm/pmsa-v8.c
+++ b/arch/arm/mm/pmsa-v8.c
@@ -165,7 +165,7 @@ static int __init pmsav8_setup_ram(unsigned int number, phys_addr_t start,phys_a
 		return -EINVAL;
 
 	bar = start;
-	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);
 
 	bar |= PMSAv8_AP_PL1RW_PL0RW | PMSAv8_RGN_SHARED;
 	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN;
@@ -181,7 +181,7 @@ static int __init pmsav8_setup_io(unsigned int number, phys_addr_t start,phys_ad
 		return -EINVAL;
 
 	bar = start;
-	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);
 
 	bar |= PMSAv8_AP_PL1RW_PL0RW | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN;
 	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN;
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 47a5acc644333..acd5a66dfc23b 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -139,6 +139,9 @@ __v7m_setup_cont:
 	cpsie	i
 	svc	#0
 1:	cpsid	i
+	ldr	r0, =exc_ret
+	orr	lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK
+	str	lr, [r0]
 	ldmia	sp, {r0-r3, r12}
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
@@ -149,10 +152,10 @@ __v7m_setup_cont:
 
 	@ Configure caches (if implemented)
 	teq     r8, #0
-	stmneia	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
+	stmiane	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
 	blne	v7m_invalidate_l1
 	teq     r8, #0			@ re-evalutae condition
-	ldmneia	sp, {r0-r6, lr}
+	ldmiane	sp, {r0-r6, lr}
 
 	@ Configure the System Control Register to ensure 8-byte stack alignment
 	@ Note the STKALIGN bit is either RW or RAO.