Merge branches 'fixes' and 'ioremap' into for-linus

37 files changed, 323 insertions, 245 deletions

diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 3c4596d0ce6c..83c50193626c 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -20,7 +20,6 @@ generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
-generic-y += scatterlist.h
 generic-y += seccomp.h
 generic-y += sections.h
 generic-y += segment.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 186270b3e194..4abe57279c66 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -178,6 +178,21 @@
 	.endm
 
 /*
+ * Assembly version of "adr rd, BSYM(sym)".  This should only be used to
+ * reference local symbols in the same assembly file which are to be
+ * resolved by the assembler.  Other usage is undefined.
+ */
+	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+	.macro	badr\c, rd, sym
+#ifdef CONFIG_THUMB2_KERNEL
+	adr\c	\rd, \sym + 1
+#else
+	adr\c	\rd, \sym
+#endif
+	.endm
+	.endr
+
+/*
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
@@ -326,7 +341,7 @@
 THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	bne	1f
 	orr	\reg, \reg, #PSR_A_BIT
-	adr	lr, BSYM(2f)
+	badr	lr, 2f
 	msr	spsr_cxsf, \reg
 	__MSR_ELR_HYP(14)
 	__ERET
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index d2f81e6b8c1c..6c2327e1c732 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -81,7 +81,7 @@ do {									\
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_mb__before_atomic()	smp_mb()
 #define smp_mb__after_atomic()	smp_mb()
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 2d46862e7bef..4812cda8fd17 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -482,10 +482,17 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
 	      "r9","r10","lr","memory" )
 
+#ifdef CONFIG_MMU
 int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
+#else
+static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
+#endif
 
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index abb2c3769b01..1692a05d3207 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -94,6 +94,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		break;
 #endif
 	default:
+		/* Cause a link-time error, the xchg() size is not supported */
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
@@ -102,8 +103,10 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	return ret;
 }
 
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+#define xchg(ptr, x) ({							\
+	(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr),		\
+				   sizeof(*(ptr)));			\
+})
 
 #include <asm-generic/cmpxchg-local.h>
 
@@ -118,14 +121,16 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
  */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n) ({					\
+	(__typeof(*ptr))__cmpxchg_local_generic((ptr),			\
+					        (unsigned long)(o),	\
+					        (unsigned long)(n),	\
+					        sizeof(*(ptr)));	\
+})
+
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
-#ifndef CONFIG_SMP
 #include <asm-generic/cmpxchg.h>
-#endif
 
 #else	/* min ARCH >= ARMv6 */
 
@@ -201,11 +206,12 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	return ret;
 }
 
-#define cmpxchg(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
-					  (unsigned long)(o),		\
-					  (unsigned long)(n),		\
-					  sizeof(*(ptr))))
+#define cmpxchg(ptr,o,n) ({						\
+	(__typeof__(*(ptr)))__cmpxchg_mb((ptr),				\
+					 (unsigned long)(o),		\
+					 (unsigned long)(n),		\
+					 sizeof(*(ptr)));		\
+})
 
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
 					    unsigned long old,
@@ -227,6 +233,13 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	return ret;
 }
 
+#define cmpxchg_local(ptr, o, n) ({					\
+	(__typeof(*ptr))__cmpxchg_local((ptr),				\
+				        (unsigned long)(o),		\
+				        (unsigned long)(n),		\
+				        sizeof(*(ptr)));		\
+})
+
 static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 					     unsigned long long old,
 					     unsigned long long new)
@@ -252,6 +265,14 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 	return oldval;
 }
 
+#define cmpxchg64_relaxed(ptr, o, n) ({					\
+	(__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n));	\
+})
+
+#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
+
 static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
 						unsigned long long old,
 						unsigned long long new)
@@ -265,23 +286,11 @@ static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
 	return ret;
 }
 
-#define cmpxchg_local(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
-				       (unsigned long)(o),		\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
-
-#define cmpxchg64(ptr, o, n)						\
-	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					(unsigned long long)(o),	\
-					(unsigned long long)(n)))
-
-#define cmpxchg64_relaxed(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
-					(unsigned long long)(o),	\
-					(unsigned long long)(n)))
-
-#define cmpxchg64_local(ptr, o, n)	cmpxchg64_relaxed((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n) ({						\
+	(__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					   (unsigned long long)(o),	\
+					   (unsigned long long)(n));	\
+})
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index 99084431d6ae..bb4fa67da541 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -19,7 +19,7 @@
  * It should not be re-used except for that purpose.
  */
 #include <linux/spinlock.h>
-#include <asm/scatterlist.h>
+#include <linux/scatterlist.h>
 
 #include <mach/isa-dma.h>
 
diff --git a/arch/arm/include/asm/edac.h b/arch/arm/include/asm/edac.h
index 0df7a2c1fc3d..5189fa819b60 100644
--- a/arch/arm/include/asm/edac.h
+++ b/arch/arm/include/asm/edac.h
@@ -18,11 +18,12 @@
 #define ASM_EDAC_H
 /*
  * ECC atomic, DMA, SMP and interrupt safe scrub function.
- * Implements the per arch atomic_scrub() that EDAC use for software
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
  * ECC scrubbing.  It reads memory and then writes back the original
  * value, allowing the hardware to detect and correct memory errors.
  */
-static inline void atomic_scrub(void *va, u32 size)
+
+static inline void edac_atomic_scrub(void *va, u32 size)
 {
 #if __LINUX_ARM_ARCH__ >= 6
 	unsigned int *virt_addr = va;
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index 469a2b30fa27..609184f522ee 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -10,7 +10,7 @@
 	@
 	@ routine called with r0 = irq number, r1 = struct pt_regs *
 	@
-	adrne	lr, BSYM(1b)
+	badrne	lr, 1b
 	bne	asm_do_IRQ
 
 #ifdef CONFIG_SMP
@@ -23,7 +23,7 @@
 	ALT_SMP(test_for_ipi r0, r2, r6, lr)
 	ALT_UP_B(9997f)
 	movne	r1, sp
-	adrne	lr, BSYM(1b)
+	badrne	lr, 1b
 	bne	do_IPI
 #endif
 9997:
diff --git a/arch/arm/include/asm/firmware.h b/arch/arm/include/asm/firmware.h
index 89aefe10d66b..34c1d96ef46d 100644
--- a/arch/arm/include/asm/firmware.h
+++ b/arch/arm/include/asm/firmware.h
@@ -34,6 +34,10 @@ struct firmware_ops {
 	 */
 	int (*set_cpu_boot_addr)(int cpu, unsigned long boot_addr);
 	/*
+	 * Gets boot address of specified physical CPU
+	 */
+	int (*get_cpu_boot_addr)(int cpu, unsigned long *boot_addr);
+	/*
 	 * Boots specified physical CPU
 	 */
 	int (*cpu_boot)(int cpu);
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 4e78065a16aa..5eed82809d82 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	preempt_disable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "cc", "memory");
 
 	*uval = val;
+	preempt_enable();
+
 	return ret;
 }
 
@@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+#ifndef CONFIG_SMP
+	preempt_disable();
+#endif
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
+#ifndef CONFIG_SMP
+	preempt_enable();
+#endif
 
 	if (!ret) {
 		switch (cmp) {
diff --git a/arch/arm/include/asm/hardware/arm_timer.h b/arch/arm/include/asm/hardware/arm_timer.h
deleted file mode 100644
index d6030ff599db..000000000000
--- a/arch/arm/include/asm/hardware/arm_timer.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef __ASM_ARM_HARDWARE_ARM_TIMER_H
-#define __ASM_ARM_HARDWARE_ARM_TIMER_H
-
-/*
- * ARM timer implementation, found in Integrator, Versatile and Realview
- * platforms.  Not all platforms support all registers and bits in these
- * registers, so we mark them with A for Integrator AP, C for Integrator
- * CP, V for Versatile and R for Realview.
- *
- * Integrator AP has 16-bit timers, Integrator CP, Versatile and Realview
- * can have 16-bit or 32-bit selectable via a bit in the control register.
- *
- * Every SP804 contains two identical timers.
- */
-#define TIMER_1_BASE	0x00
-#define TIMER_2_BASE	0x20
-
-#define TIMER_LOAD	0x00			/* ACVR rw */
-#define TIMER_VALUE	0x04			/* ACVR ro */
-#define TIMER_CTRL	0x08			/* ACVR rw */
-#define TIMER_CTRL_ONESHOT	(1 << 0)	/*  CVR */
-#define TIMER_CTRL_32BIT	(1 << 1)	/*  CVR */
-#define TIMER_CTRL_DIV1		(0 << 2)	/* ACVR */
-#define TIMER_CTRL_DIV16	(1 << 2)	/* ACVR */
-#define TIMER_CTRL_DIV256	(2 << 2)	/* ACVR */
-#define TIMER_CTRL_IE		(1 << 5)	/*   VR */
-#define TIMER_CTRL_PERIODIC	(1 << 6)	/* ACVR */
-#define TIMER_CTRL_ENABLE	(1 << 7)	/* ACVR */
-
-#define TIMER_INTCLR	0x0c			/* ACVR wo */
-#define TIMER_RIS	0x10			/*  CVR ro */
-#define TIMER_MIS	0x14			/*  CVR ro */
-#define TIMER_BGLOAD	0x18			/*  CVR rw */
-
-#endif
diff --git a/arch/arm/include/asm/hardware/timer-sp.h b/arch/arm/include/asm/hardware/timer-sp.h
deleted file mode 100644
index bb28af7c32de..000000000000
--- a/arch/arm/include/asm/hardware/timer-sp.h
+++ /dev/null
@@ -1,23 +0,0 @@
-struct clk;
-
-void __sp804_clocksource_and_sched_clock_init(void __iomem *,
-					      const char *, struct clk *, int);
-void __sp804_clockevents_init(void __iomem *, unsigned int,
-			      struct clk *, const char *);
-
-static inline void sp804_clocksource_init(void __iomem *base, const char *name)
-{
-	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 0);
-}
-
-static inline void sp804_clocksource_and_sched_clock_init(void __iomem *base,
-							  const char *name)
-{
-	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 1);
-}
-
-static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq, const char *name)
-{
-	__sp804_clockevents_init(base, irq, NULL, name);
-
-}
diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
index 1f1b1cd112f3..7d26f6c4f0f5 100644
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@@ -53,10 +53,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline int huge_pte_none(pte_t pte)
 {
 	return pte_none(pte);
@@ -67,15 +63,6 @@ static inline pte_t huge_pte_wrprotect(pte_t pte)
 	return pte_wrprotect(pte);
 }
 
-static inline int arch_prepare_hugepage(struct page *page)
-{
-	return 0;
-}
-
-static inline void arch_release_hugepage(struct page *page)
-{
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index db58deb00aa7..485982084fe9 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -23,6 +23,7 @@
 
 #ifdef __KERNEL__
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/blk_types.h>
 #include <asm/byteorder.h>
@@ -73,17 +74,16 @@ void __raw_readsl(const volatile void __iomem *addr, void *data, int longlen);
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %1, %0"
-		     : "+Q" (*(volatile u16 __force *)addr)
-		     : "r" (val));
+		     : : "Q" (*(volatile u16 __force *)addr), "r" (val));
 }
 
 #define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
-	asm volatile("ldrh %1, %0"
-		     : "+Q" (*(volatile u16 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldrh %0, %1"
+		     : "=r" (val)
+		     : "Q" (*(volatile u16 __force *)addr));
 	return val;
 }
 #endif
@@ -92,25 +92,23 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
 	asm volatile("strb %1, %0"
-		     : "+Qo" (*(volatile u8 __force *)addr)
-		     : "r" (val));
+		     : : "Qo" (*(volatile u8 __force *)addr), "r" (val));
 }
 
 #define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
 	asm volatile("str %1, %0"
-		     : "+Qo" (*(volatile u32 __force *)addr)
-		     : "r" (val));
+		     : : "Qo" (*(volatile u32 __force *)addr), "r" (val));
 }
 
 #define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile("ldrb %1, %0"
-		     : "+Qo" (*(volatile u8 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldrb %0, %1"
+		     : "=r" (val)
+		     : "Qo" (*(volatile u8 __force *)addr));
 	return val;
 }
 
@@ -118,9 +116,9 @@ static inline u8 __raw_readb(const volatile void __iomem *addr)
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile("ldr %1, %0"
-		     : "+Qo" (*(volatile u32 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldr %0, %1"
+		     : "=r" (val)
+		     : "Qo" (*(volatile u32 __force *)addr));
 	return val;
 }
 
@@ -142,16 +140,11 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
  * The _caller variety takes a __builtin_return_address(0) value for
  * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
-	size_t, unsigned int, void *);
 extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
-
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
@@ -319,24 +312,95 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define writesw(p,d,l)		__raw_writesw(p,d,l)
 #define writesl(p,d,l)		__raw_writesl(p,d,l)
 
+#ifndef __ARMBE__
+static inline void memset_io(volatile void __iomem *dst, unsigned c,
+	size_t count)
+{
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
+}
+#define memset_io(dst,c,count) memset_io(dst,c,count)
+
+static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
+	size_t count)
+{
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
+}
+#define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
+
+static inline void memcpy_toio(volatile void __iomem *to, const void *from,
+	size_t count)
+{
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
+}
+#define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
+
+#else
 #define memset_io(c,v,l)	_memset_io(c,(v),(l))
 #define memcpy_fromio(a,c,l)	_memcpy_fromio((a),c,(l))
 #define memcpy_toio(c,a,l)	_memcpy_toio(c,(a),(l))
+#endif
 
 #endif	/* readl */
 
 /*
- * ioremap and friends.
+ * ioremap() and friends.
+ *
+ * ioremap() takes a resource address, and size.  Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
+ *
+ * Function		Memory type	Cacheability	Cache hint
+ * ioremap()		Device		n/a		n/a
+ * ioremap_nocache()	Device		n/a		n/a
+ * ioremap_cache()	Normal		Writeback	Read allocate
+ * ioremap_wc()		Normal		Non-cacheable	n/a
+ * ioremap_wt()		Normal		Non-cacheable	n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
  *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different.  This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
  *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ *   instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
  */
-#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define iounmap				__arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
 
 /*
  * io{read,write}{16,32}be() macros
diff --git a/arch/arm/include/asm/irqflags.h b/arch/arm/include/asm/irqflags.h
index 3b763d6652a0..43908146a5cf 100644
--- a/arch/arm/include/asm/irqflags.h
+++ b/arch/arm/include/asm/irqflags.h
@@ -20,6 +20,7 @@
 
 #if __LINUX_ARM_ARCH__ >= 6
 
+#define arch_local_irq_save arch_local_irq_save
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
@@ -31,6 +32,7 @@ static inline unsigned long arch_local_irq_save(void)
 	return flags;
 }
 
+#define arch_local_irq_enable arch_local_irq_enable
 static inline void arch_local_irq_enable(void)
 {
 	asm volatile(
@@ -40,6 +42,7 @@ static inline void arch_local_irq_enable(void)
 		: "memory", "cc");
 }
 
+#define arch_local_irq_disable arch_local_irq_disable
 static inline void arch_local_irq_disable(void)
 {
 	asm volatile(
@@ -56,6 +59,7 @@ static inline void arch_local_irq_disable(void)
 /*
  * Save the current interrupt enable state & disable IRQs
  */
+#define arch_local_irq_save arch_local_irq_save
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags, temp;
@@ -73,6 +77,7 @@ static inline unsigned long arch_local_irq_save(void)
 /*
  * Enable IRQs
  */
+#define arch_local_irq_enable arch_local_irq_enable
 static inline void arch_local_irq_enable(void)
 {
 	unsigned long temp;
@@ -88,6 +93,7 @@ static inline void arch_local_irq_enable(void)
 /*
  * Disable IRQs
  */
+#define arch_local_irq_disable arch_local_irq_disable
 static inline void arch_local_irq_disable(void)
 {
 	unsigned long temp;
@@ -135,6 +141,7 @@ static inline void arch_local_irq_disable(void)
 /*
  * Save the current interrupt enable state.
  */
+#define arch_local_save_flags arch_local_save_flags
 static inline unsigned long arch_local_save_flags(void)
 {
 	unsigned long flags;
@@ -147,6 +154,7 @@ static inline unsigned long arch_local_save_flags(void)
 /*
  * restore saved IRQ & FIQ state
  */
+#define arch_local_irq_restore arch_local_irq_restore
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	asm volatile(
@@ -156,10 +164,13 @@ static inline void arch_local_irq_restore(unsigned long flags)
 		: "memory", "cc");
 }
 
+#define arch_irqs_disabled_flags arch_irqs_disabled_flags
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return flags & IRQMASK_I_BIT;
 }
 
+#include <asm-generic/irqflags.h>
+
 #endif /* ifdef __KERNEL__ */
 #endif /* ifndef __ASM_ARM_IRQFLAGS_H */
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 25410b2d8bc1..194c91b610ff 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -23,7 +23,7 @@
 #define c0_MPIDR	1	/* MultiProcessor ID Register */
 #define c0_CSSELR	2	/* Cache Size Selection Register */
 #define c1_SCTLR	3	/* System Control Register */
-#define c1_ACTLR	4	/* Auxilliary Control Register */
+#define c1_ACTLR	4	/* Auxiliary Control Register */
 #define c1_CPACR	5	/* Coprocessor Access Control */
 #define c2_TTBR0	6	/* Translation Table Base Register 0 */
 #define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index d71607c16601..e896d2c196e6 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -218,11 +218,6 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 	return 0;
 }
 
-static inline void vgic_arch_setup(const struct vgic_params *vgic)
-{
-	BUG_ON(vgic->type != VGIC_V2);
-}
-
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 0406cb3f1af7..cb3a40717edd 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -51,7 +51,7 @@ struct machine_desc {
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
 	void			(*dt_fixup)(void);
-	void			(*init_meminfo)(void);
+	long long		(*pv_fixup)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
 	void			(*init_early)(void);
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 50b378f59e08..acd4983d9b1f 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -137,17 +137,12 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
 /**
  * mcpm_cpu_suspend - bring the calling CPU in a suspended state
  *
- * @expected_residency: duration in microseconds the CPU is expected
- *			to remain suspended, or 0 if unknown/infinity.
- *
- * The calling CPU is suspended.  The expected residency argument is used
- * as a hint by the platform specific backend to implement the appropriate
- * sleep state level according to the knowledge it has on wake-up latency
- * for the given hardware.
+ * The calling CPU is suspended.  This is similar to mcpm_cpu_power_down()
+ * except for possible extra platform specific configuration steps to allow
+ * an asynchronous wake-up e.g. with a pending interrupt.
  *
  * If this CPU is found to be the "last man standing" in the cluster
- * then the cluster may be prepared for power-down too, if the expected
- * residency makes it worthwhile.
+ * then the cluster may be prepared for power-down too.
  *
  * This must be called with interrupts disabled.
  *
@@ -157,7 +152,7 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
  * This will return if mcpm_platform_register() has not been called
  * previously in which case the caller should take appropriate action.
  */
-void mcpm_cpu_suspend(u64 expected_residency);
+void mcpm_cpu_suspend(void);
 
 /**
  * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
@@ -234,12 +229,6 @@ struct mcpm_platform_ops {
 	void (*cpu_is_up)(unsigned int cpu, unsigned int cluster);
 	void (*cluster_is_up)(unsigned int cluster);
 	int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
-
-	/* deprecated callbacks */
-	int (*power_up)(unsigned int cpu, unsigned int cluster);
-	void (*power_down)(void);
-	void (*suspend)(u64);
-	void (*powered_up)(void);
 };
 
 /**
@@ -251,35 +240,6 @@ struct mcpm_platform_ops {
  */
 int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
 
-/* Synchronisation structures for coordinating safe cluster setup/teardown: */
-
-/*
- * When modifying this structure, make sure you update the MCPM_SYNC_ defines
- * to match.
- */
-struct mcpm_sync_struct {
-	/* individual CPU states */
-	struct {
-		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
-	} cpus[MAX_CPUS_PER_CLUSTER];
-
-	/* cluster state */
-	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
-
-	/* inbound-side state */
-	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
-};
-
-struct sync_struct {
-	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
-};
-
-void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
-void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
-void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
-bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
-int __mcpm_cluster_state(unsigned int cluster);
-
 /**
  * mcpm_sync_init - Initialize the cluster synchronization support
  *
@@ -318,6 +278,29 @@ int __init mcpm_loopback(void (*cache_disable)(void));
 
 void __init mcpm_smp_set_ops(void);
 
+/*
+ * Synchronisation structures for coordinating safe cluster setup/teardown.
+ * This is private to the MCPM core code and shared between C and assembly.
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
 #else
 
 /* 
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 063ef314cca9..6f225acc07c5 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -18,8 +18,6 @@
 #include <linux/types.h>
 #include <linux/sizes.h>
 
-#include <asm/cache.h>
-
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
@@ -133,20 +131,6 @@
 #define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
 
 /*
- * Minimum guaranted alignment in pgd_alloc().  The page table pointers passed
- * around in head.S and proc-*.S are shifted by this amount, in order to
- * leave spare high bits for systems with physical address extension.  This
- * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
- * gives us about 38-bits or so.
- */
-#ifdef CONFIG_ARM_LPAE
-#define ARCH_PGD_SHIFT		L1_CACHE_SHIFT
-#else
-#define ARCH_PGD_SHIFT		0
-#endif
-#define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
-
-/*
  * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
  * memory.  This is used for XIP and NoMMU kernels, and on platforms that don't
  * have CONFIG_ARM_PATCH_PHYS_VIRT. Assembly code must always use
diff --git a/arch/arm/include/asm/mm-arch-hooks.h b/arch/arm/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..7056660c7cc4
--- /dev/null
+++ b/arch/arm/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARM_MM_ARCH_HOOKS_H
+#define _ASM_ARM_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARM_MM_ARCH_HOOKS_H */
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index ed690c49ef93..e358b7966c06 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -16,11 +16,21 @@ enum {
 	ARM_SEC_UNLIKELY,
 	ARM_SEC_MAX,
 };
+#endif
 
 struct mod_arch_specific {
+#ifdef CONFIG_ARM_UNWIND
 	struct unwind_table *unwind[ARM_SEC_MAX];
-};
 #endif
+#ifdef CONFIG_ARM_MODULE_PLTS
+	struct elf32_shdr   *core_plt;
+	struct elf32_shdr   *init_plt;
+	int		    core_plt_count;
+	int		    init_plt_count;
+#endif
+};
+
+u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val);
 
 /*
  * Add the ARM architecture version to the version magic string
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 585dc33a7a24..a5635444ca41 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -31,16 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
                                enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index d9cf138fd7d4..4f9dec489931 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -19,4 +19,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
 #endif
 
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->ARM_pc = (__ip); \
+	(regs)->ARM_fp = (unsigned long) __builtin_frame_address(0); \
+	(regs)->ARM_sp = current_stack_pointer; \
+	(regs)->ARM_cpsr = SVC_MODE; \
+}
+
 #endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index bfd662e49a25..aeddd28b3595 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -129,7 +129,36 @@
 
 /*
  * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
+ * UNCACHED		Uncached	Strongly ordered
+ * BUFFERABLE		Bufferable	Normal memory / non-cacheable
+ * WRITETHROUGH		Writethrough	Normal memory / write through
+ * WRITEBACK		Writeback	Normal memory / write back, read alloc
+ * MINICACHE		Minicache	N/A
+ * WRITEALLOC		Writeback	Normal memory / write back, write alloc
+ * DEV_SHARED		Uncached	Device memory (shared)
+ * DEV_NONSHARED	Uncached	Device memory (non-shared)
+ * DEV_WC		Bufferable	Normal memory / non-cacheable
+ * DEV_CACHED		Writeback	Normal memory / write back, read alloc
+ * VECTORS		Variable	Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 675e4ab79f68..3fc87dfd77e6 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -24,22 +24,10 @@
  *	interrupt and passed the address of the low level handler,
  *	and can be used to implement any platform specific handling
  *	before or after calling it.
- * @runtime_resume: an optional handler which will be called by the
- *	runtime PM framework following a call to pm_runtime_get().
- *	Note that if pm_runtime_get() is called more than once in
- *	succession this handler will only be called once.
- * @runtime_suspend: an optional handler which will be called by the
- *	runtime PM framework following a call to pm_runtime_put().
- *	Note that if pm_runtime_get() is called more than once in
- *	succession this handler will only be called following the
- *	final call to pm_runtime_put() that actually disables the
- *	hardware.
  */
 struct arm_pmu_platdata {
 	irqreturn_t (*handle_irq)(int irq, void *dev,
 				  irq_handler_t pmu_handler);
-	int (*runtime_resume)(struct device *dev);
-	int (*runtime_suspend)(struct device *dev);
 };
 
 #ifdef CONFIG_HW_PERF_EVENTS
@@ -92,6 +80,7 @@ struct pmu_hw_events {
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	cpumask_t	supported_cpus;
 	int		*irq_affinity;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
@@ -122,8 +111,6 @@ struct arm_pmu {
 
 #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
 
-extern const struct dev_pm_ops armpmu_dev_pm_ops;
-
 int armpmu_register(struct arm_pmu *armpmu, int type);
 
 u64 armpmu_event_update(struct perf_event *event);
@@ -158,6 +145,10 @@ struct pmu_probe_info {
 #define XSCALE_PMU_PROBE(_version, _fn) \
 	PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn)
 
+int arm_pmu_device_probe(struct platform_device *pdev,
+			 const struct of_device_id *of_table,
+			 const struct pmu_probe_info *probe_table);
+
 #endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 5324c1112f3a..8877ad5ffe10 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -125,13 +125,6 @@ extern void cpu_resume(void);
 		ttbr;						\
 	})
 
-#define cpu_set_ttbr(nr, val)					\
-	do {							\
-		u64 ttbr = val;					\
-		__asm__("mcrr	p15, " #nr ", %Q0, %R0, c2"	\
-			: : "r" (ttbr));			\
-	} while (0)
-
 #define cpu_get_pgd()	\
 	({						\
 		u64 pg = cpu_get_ttbr(0);		\
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 18f5a554134f..2f3ac1ba6fb4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -61,7 +61,7 @@ asmlinkage void secondary_start_kernel(void);
 struct secondary_data {
 	union {
 		unsigned long mpu_rgn_szr;
-		unsigned long pgdir;
+		u64 pgdir;
 	};
 	unsigned long swapper_pg_dir;
 	void *stack;
@@ -69,6 +69,7 @@ struct secondary_data {
 extern struct secondary_data secondary_data;
 extern volatile int pen_release;
 extern void secondary_startup(void);
+extern void secondary_startup_arm(void);
 
 extern int __cpu_disable(void);
 
diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h
index cd20029bcd94..6c7182f32cef 100644
--- a/arch/arm/include/asm/suspend.h
+++ b/arch/arm/include/asm/suspend.h
@@ -7,6 +7,7 @@ struct sleep_save_sp {
 };
 
 extern void cpu_resume(void);
+extern void cpu_resume_arm(void);
 extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 
 #endif
diff --git a/arch/arm/include/asm/system_info.h b/arch/arm/include/asm/system_info.h
index 720ea0320a6d..3860cbd401ec 100644
--- a/arch/arm/include/asm/system_info.h
+++ b/arch/arm/include/asm/system_info.h
@@ -17,6 +17,7 @@
 
 /* information about the system we're running on */
 extern unsigned int system_rev;
+extern const char *system_serial;
 extern unsigned int system_serial_low;
 extern unsigned int system_serial_high;
 extern unsigned int mem_fclk_21285;
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 2fe85fff5cca..370f7a732900 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h
index 200f9a7cd623..a91ae499614c 100644
--- a/arch/arm/include/asm/unified.h
+++ b/arch/arm/include/asm/unified.h
@@ -45,7 +45,6 @@
 #define THUMB(x...)	x
 #ifdef __ASSEMBLY__
 #define W(instr)	instr.w
-#define BSYM(sym)	sym + 1
 #else
 #define WASM(instr)	#instr ".w"
 #endif
@@ -59,7 +58,6 @@
 #define THUMB(x...)
 #ifdef __ASSEMBLY__
 #define W(instr)	instr
-#define BSYM(sym)	sym
 #else
 #define WASM(instr)	#instr
 #endif
diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h
index ee5f3084243c..22e414056a8c 100644
--- a/arch/arm/include/asm/vfp.h
+++ b/arch/arm/include/asm/vfp.h
@@ -5,6 +5,9 @@
  * First, the standard VFP set.
  */
 
+#ifndef __ASM_VFP_H
+#define __ASM_VFP_H
+
 #define FPSID			cr0
 #define FPSCR			cr1
 #define MVFR1			cr6
@@ -87,3 +90,9 @@
 #define VFPOPDESC_UNUSED_BIT	(24)
 #define VFPOPDESC_UNUSED_MASK	(0xFF << VFPOPDESC_UNUSED_BIT)
 #define VFPOPDESC_OPDESC_MASK	(~(VFPOPDESC_LENGTH_MASK | VFPOPDESC_UNUSED_MASK))
+
+#ifndef __ASSEMBLY__
+void vfp_disable(void);
+#endif
+
+#endif /* __ASM_VFP_H */
diff --git a/arch/arm/include/debug/8250.S b/arch/arm/include/debug/8250.S
index 7a2baf913aa0..7f7446f6f806 100644
--- a/arch/arm/include/debug/8250.S
+++ b/arch/arm/include/debug/8250.S
@@ -16,11 +16,14 @@
 
 #ifdef CONFIG_DEBUG_UART_8250_WORD
 		.macro	store, rd, rx:vararg
+	 ARM_BE8(rev \rd, \rd)
 		str	\rd, \rx
+	 ARM_BE8(rev \rd, \rd)
 		.endm
 
 		.macro	load, rd, rx:vararg
 		ldr	\rd, \rx
+	ARM_BE8(rev \rd, \rd)
 		.endm
 #else
 		.macro	store, rd, rx:vararg
diff --git a/arch/arm/include/debug/efm32.S b/arch/arm/include/debug/efm32.S
index 2265a199280c..660fa1e4b77b 100644
--- a/arch/arm/include/debug/efm32.S
+++ b/arch/arm/include/debug/efm32.S
@@ -16,7 +16,7 @@
 
 #define	UARTn_TXDATA		0x0034
 
-		.macro	addruart, rx, tmp
+		.macro	addruart, rx, tmp, tmp2
 		ldr	\rx, =(CONFIG_DEBUG_UART_PHYS)
 
 		/*
diff --git a/arch/arm/include/debug/imx-uart.h b/arch/arm/include/debug/imx-uart.h
index 032a316eb802..66f736f74684 100644
--- a/arch/arm/include/debug/imx-uart.h
+++ b/arch/arm/include/debug/imx-uart.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ * Copyright (C) 2012-2015 Freescale Semiconductor, Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -90,6 +90,16 @@
 #define IMX6SX_UART_BASE_ADDR(n) IMX6SX_UART##n##_BASE_ADDR
 #define IMX6SX_UART_BASE(n)	IMX6SX_UART_BASE_ADDR(n)
 
+#define IMX7D_UART1_BASE_ADDR	0x30860000
+#define IMX7D_UART2_BASE_ADDR	0x30890000
+#define IMX7D_UART3_BASE_ADDR	0x30880000
+#define IMX7D_UART4_BASE_ADDR	0x30a60000
+#define IMX7D_UART5_BASE_ADDR	0x30a70000
+#define IMX7D_UART6_BASE_ADDR	0x30a80000
+#define IMX7D_UART7_BASE_ADDR	0x30a90000
+#define IMX7D_UART_BASE_ADDR(n) IMX7D_UART##n##_BASE_ADDR
+#define IMX7D_UART_BASE(n)	IMX7D_UART_BASE_ADDR(n)
+
 #define IMX_DEBUG_UART_BASE(soc) soc##_UART_BASE(CONFIG_DEBUG_IMX_UART_PORT)
 
 #ifdef CONFIG_DEBUG_IMX1_UART
@@ -114,6 +124,9 @@
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6SL)
 #elif defined(CONFIG_DEBUG_IMX6SX_UART)
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6SX)
+#elif defined(CONFIG_DEBUG_IMX7D_UART)
+#define UART_PADDR	IMX_DEBUG_UART_BASE(IMX7D)
+
 #endif
 
 #endif /* __DEBUG_IMX_UART_H */
diff --git a/arch/arm/include/debug/pl01x.S b/arch/arm/include/debug/pl01x.S
index 92ef808a2337..f7d8323cefcc 100644
--- a/arch/arm/include/debug/pl01x.S
+++ b/arch/arm/include/debug/pl01x.S
@@ -12,6 +12,13 @@
 */
 #include <linux/amba/serial.h>
 
+#ifdef CONFIG_DEBUG_ZTE_ZX
+#undef UART01x_DR
+#undef UART01x_FR
+#define UART01x_DR     0x04
+#define UART01x_FR     0x14
+#endif
+
 #ifdef CONFIG_DEBUG_UART_PHYS
 		.macro	addruart, rp, rv, tmp
 		ldr	\rp, =CONFIG_DEBUG_UART_PHYS