23 files changed, 308 insertions, 194 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index a0162fa94564..7e79503ab89b 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -40,12 +40,12 @@ static inline void atomic_add(int i, atomic_t *v)
 	int result;
 
 	__asm__ __volatile__("@ atomic_add\n"
-"1:	ldrex	%0, [%2]\n"
-"	add	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }
@@ -58,12 +58,12 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic_add_return\n"
-"1:	ldrex	%0, [%2]\n"
-"	add	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
@@ -78,12 +78,12 @@ static inline void atomic_sub(int i, atomic_t *v)
 	int result;
 
 	__asm__ __volatile__("@ atomic_sub\n"
-"1:	ldrex	%0, [%2]\n"
-"	sub	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }
@@ -96,12 +96,12 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic_sub_return\n"
-"1:	ldrex	%0, [%2]\n"
-"	sub	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
@@ -118,11 +118,11 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
-		"ldrex	%1, [%2]\n"
+		"ldrex	%1, [%3]\n"
 		"mov	%0, #0\n"
-		"teq	%1, %3\n"
-		"strexeq %0, %4, [%2]\n"
-		    : "=&r" (res), "=&r" (oldval)
+		"teq	%1, %4\n"
+		"strexeq %0, %5, [%3]\n"
+		    : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
 		    : "r" (&ptr->counter), "Ir" (old), "r" (new)
 		    : "cc");
 	} while (res);
@@ -137,12 +137,12 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 	unsigned long tmp, tmp2;
 
 	__asm__ __volatile__("@ atomic_clear_mask\n"
-"1:	ldrex	%0, [%2]\n"
-"	bic	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	bic	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (tmp), "=&r" (tmp2)
+	: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
 	: "r" (addr), "Ir" (mask)
 	: "cc");
 }
@@ -249,7 +249,7 @@ static inline u64 atomic64_read(atomic64_t *v)
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrexd	%0, %H0, [%1]"
 	: "=&r" (result)
-	: "r" (&v->counter)
+	: "r" (&v->counter), "Qo" (v->counter)
 	);
 
 	return result;
@@ -260,11 +260,11 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 	u64 tmp;
 
 	__asm__ __volatile__("@ atomic64_set\n"
-"1:	ldrexd	%0, %H0, [%1]\n"
-"	strexd	%0, %2, %H2, [%1]\n"
+"1:	ldrexd	%0, %H0, [%2]\n"
+"	strexd	%0, %3, %H3, [%2]\n"
 "	teq	%0, #0\n"
 "	bne	1b"
-	: "=&r" (tmp)
+	: "=&r" (tmp), "=Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
@@ -275,13 +275,13 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 	unsigned long tmp;
 
 	__asm__ __volatile__("@ atomic64_add\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	adds	%0, %0, %3\n"
-"	adc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	adds	%0, %0, %4\n"
+"	adc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
@@ -294,13 +294,13 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	adds	%0, %0, %3\n"
-"	adc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	adds	%0, %0, %4\n"
+"	adc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 
@@ -315,13 +315,13 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 	unsigned long tmp;
 
 	__asm__ __volatile__("@ atomic64_sub\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	subs	%0, %0, %3\n"
-"	sbc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	subs	%0, %0, %4\n"
+"	sbc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
@@ -334,13 +334,13 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	subs	%0, %0, %3\n"
-"	sbc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	subs	%0, %0, %4\n"
+"	sbc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 
@@ -358,12 +358,12 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
 
 	do {
 		__asm__ __volatile__("@ atomic64_cmpxchg\n"
-		"ldrexd		%1, %H1, [%2]\n"
+		"ldrexd		%1, %H1, [%3]\n"
 		"mov		%0, #0\n"
-		"teq		%1, %3\n"
-		"teqeq		%H1, %H3\n"
-		"strexdeq	%0, %4, %H4, [%2]"
-		: "=&r" (res), "=&r" (oldval)
+		"teq		%1, %4\n"
+		"teqeq		%H1, %H4\n"
+		"strexdeq	%0, %5, %H5, [%3]"
+		: "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
 		: "r" (&ptr->counter), "r" (old), "r" (new)
 		: "cc");
 	} while (res);
@@ -381,11 +381,11 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	strexd	%1, %3, %H3, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	strexd	%1, %4, %H4, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (ptr->counter)
 	: "r" (&ptr->counter), "r" (new)
 	: "cc");
 
@@ -402,16 +402,16 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
 "	subs	%0, %0, #1\n"
 "	sbc	%H0, %H0, #0\n"
 "	teq	%H0, #0\n"
 "	bmi	2f\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter)
 	: "cc");
 
@@ -429,18 +429,18 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_add_unless\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	teq	%0, %4\n"
-"	teqeq	%H0, %H4\n"
+"1:	ldrexd	%0, %H0, [%4]\n"
+"	teq	%0, %5\n"
+"	teqeq	%H0, %H5\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%0, %0, %5\n"
-"	adc	%H0, %H0, %H5\n"
-"	strexd	%2, %0, %H0, [%3]\n"
+"	adds	%0, %0, %6\n"
+"	adc	%H0, %H0, %H6\n"
+"	strexd	%2, %0, %H0, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (val), "=&r" (ret), "=&r" (tmp)
+	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
 
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 51662feb9f1d..6750b8e45a49 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -121,4 +121,8 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
 extern void elf_set_personality(const struct elf32_hdr *);
 #define SET_PERSONALITY(ex)	elf_set_personality(&(ex))
 
+struct mm_struct;
+extern unsigned long arch_randomize_brk(struct mm_struct *mm);
+#define arch_randomize_brk arch_randomize_brk
+
 #endif
diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h
index f7bd52b1c365..c1062c317103 100644
--- a/arch/arm/include/asm/hwcap.h
+++ b/arch/arm/include/asm/hwcap.h
@@ -19,6 +19,7 @@
 #define HWCAP_NEON	4096
 #define HWCAP_VFPv3	8192
 #define HWCAP_VFPv3D16	16384
+#define HWCAP_TLS	32768
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 /*
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index c980156f3263..1261b1f928d9 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/memory.h>
+#include <asm/system.h>
 
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
@@ -179,25 +180,38 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  * IO port primitives for more information.
  */
 #ifdef __mem_pci
-#define readb(c) ({ __u8  __v = __raw_readb(__mem_pci(c)); __v; })
-#define readw(c) ({ __u16 __v = le16_to_cpu((__force __le16) \
+#define readb_relaxed(c) ({ u8  __v = __raw_readb(__mem_pci(c)); __v; })
+#define readw_relaxed(c) ({ u16 __v = le16_to_cpu((__force __le16) \
 					__raw_readw(__mem_pci(c))); __v; })
-#define readl(c) ({ __u32 __v = le32_to_cpu((__force __le32) \
+#define readl_relaxed(c) ({ u32 __v = le32_to_cpu((__force __le32) \
 					__raw_readl(__mem_pci(c))); __v; })
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
+
+#define writeb_relaxed(v,c)	((void)__raw_writeb(v,__mem_pci(c)))
+#define writew_relaxed(v,c)	((void)__raw_writew((__force u16) \
+					cpu_to_le16(v),__mem_pci(c)))
+#define writel_relaxed(v,c)	((void)__raw_writel((__force u32) \
+					cpu_to_le32(v),__mem_pci(c)))
+
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+
+#define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
+#define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
+#define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
 
 #define readsb(p,d,l)		__raw_readsb(__mem_pci(p),d,l)
 #define readsw(p,d,l)		__raw_readsw(__mem_pci(p),d,l)
 #define readsl(p,d,l)		__raw_readsl(__mem_pci(p),d,l)
 
-#define writeb(v,c)		__raw_writeb(v,__mem_pci(c))
-#define writew(v,c)		__raw_writew((__force __u16) \
-					cpu_to_le16(v),__mem_pci(c))
-#define writel(v,c)		__raw_writel((__force __u32) \
-					cpu_to_le32(v),__mem_pci(c))
-
 #define writesb(p,d,l)		__raw_writesb(__mem_pci(p),d,l)
 #define writesw(p,d,l)		__raw_writesw(__mem_pci(p),d,l)
 #define writesl(p,d,l)		__raw_writesl(__mem_pci(p),d,l)
@@ -244,13 +258,13 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  * io{read,write}{8,16,32} macros
  */
 #ifndef ioread8
-#define ioread8(p)	({ unsigned int __v = __raw_readb(p); __v; })
-#define ioread16(p)	({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __v; })
-#define ioread32(p)	({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __v; })
+#define ioread8(p)	({ unsigned int __v = __raw_readb(p); __iormb(); __v; })
+#define ioread16(p)	({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32(p)	({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; })
 
-#define iowrite8(v,p)	__raw_writeb(v, p)
-#define iowrite16(v,p)	__raw_writew((__force __u16)cpu_to_le16(v), p)
-#define iowrite32(v,p)	__raw_writel((__force __u32)cpu_to_le32(v), p)
+#define iowrite8(v,p)	({ __iowmb(); (void)__raw_writeb(v, p); })
+#define iowrite16(v,p)	({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_le16(v), p); })
+#define iowrite32(v,p)	({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_le32(v), p); })
 
 #define ioread8_rep(p,d,c)	__raw_readsb(p,d,c)
 #define ioread16_rep(p,d,c)	__raw_readsw(p,d,c)
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 237282f7c762..2721a5814cb9 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -7,6 +7,8 @@
 #define irq_canonicalize(i)	(i)
 #endif
 
+#define NR_IRQS_LEGACY	16
+
 /*
  * Use this value to indicate lack of interrupt
  * capability
diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h
index df15a0dc228e..8ec9ef5c3c7b 100644
--- a/arch/arm/include/asm/kexec.h
+++ b/arch/arm/include/asm/kexec.h
@@ -19,10 +19,26 @@
 
 #ifndef __ASSEMBLY__
 
-struct kimage;
-/* Provide a dummy definition to avoid build failures. */
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ *
+ * Function copies machine registers from @oldregs to @newregs. If @oldregs is
+ * %NULL then current registers are stored there.
+ */
 static inline void crash_setup_regs(struct pt_regs *newregs,
-                                        struct pt_regs *oldregs) { }
+				    struct pt_regs *oldregs)
+{
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	} else {
+		__asm__ __volatile__ ("stmia %0, {r0 - r15}"
+				      : : "r" (&newregs->ARM_r0));
+		__asm__ __volatile__ ("mrs %0, cpsr"
+				      : "=r" (newregs->ARM_cpsr));
+	}
+}
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 67af4b841984..08265993227f 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -70,11 +70,11 @@ extern int kgdb_fault_expected;
 #define _GP_REGS		16
 #define _FP_REGS		8
 #define _EXTRA_REGS		2
-#define GDB_MAX_REGS		(_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS)
+#define DBG_MAX_REG_NUM		(_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS)
 
 #define KGDB_MAX_NO_CPUS	1
 #define BUFMAX			400
-#define NUMREGBYTES		(GDB_MAX_REGS << 2)
+#define NUMREGBYTES		(DBG_MAX_REG_NUM << 2)
 #define NUMCRITREGBYTES		(32 << 2)
 
 #define _R0			0
@@ -93,7 +93,7 @@ extern int kgdb_fault_expected;
 #define _SPT			13
 #define _LR			14
 #define _PC			15
-#define _CPSR			(GDB_MAX_REGS - 1)
+#define _CPSR			(DBG_MAX_REG_NUM - 1)
 
 /*
  * So that we can denote the end of a frame for tracing,
diff --git a/arch/arm/include/asm/local64.h b/arch/arm/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/arm/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index c59842dc7cb8..8a0dd18ba642 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -20,6 +20,7 @@ struct machine_desc {
 	 * by assembler code in head.S, head-common.S
 	 */
 	unsigned int		nr;		/* architecture number	*/
+	unsigned int		nr_irqs;	/* number of IRQs */
 	unsigned int		phys_io;	/* start of physical io	*/
 	unsigned int		io_pg_offst;	/* byte offset for io 
 						 * page tabe entry	*/
@@ -37,6 +38,7 @@ struct machine_desc {
 	void			(*fixup)(struct machine_desc *,
 					 struct tag *, char **,
 					 struct meminfo *);
+	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
 	void			(*init_irq)(void);
 	struct sys_timer	*timer;		/* system tick timer	*/
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
index 8920b2d6e3b8..ce3eee9fe26c 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -17,6 +17,7 @@ struct seq_file;
 /*
  * This is internal.  Do not use it.
  */
+extern unsigned int arch_nr_irqs;
 extern void (*init_arch_irq)(void);
 extern void init_FIQ(void);
 extern int show_fiq_list(struct seq_file *, void *);
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index 742c2aaeb020..d2fedb5aeb1f 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -27,6 +27,8 @@ struct map_desc {
 #define MT_MEMORY		9
 #define MT_ROM			10
 #define MT_MEMORY_NONCACHED	11
+#define MT_MEMORY_DTCM		12
+#define MT_MEMORY_ITCM		13
 
 #ifdef CONFIG_MMU
 extern void iotable_init(struct map_desc *, int);
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
index 52f0da1e97df..16330bd0657c 100644
--- a/arch/arm/include/asm/mach/pci.h
+++ b/arch/arm/include/asm/mach/pci.h
@@ -46,6 +46,7 @@ struct pci_sys_data {
 					/* IRQ mapping				*/
 	int		(*map_irq)(struct pci_dev *, u8, u8);
 	struct hw_pci	*hw;
+	void		*private_data;	/* platform controller private data	*/
 };
 
 /*
diff --git a/arch/arm/include/asm/mach/udc_pxa2xx.h b/arch/arm/include/asm/mach/udc_pxa2xx.h
index f3eabf1ecec3..833306ee9e7f 100644
--- a/arch/arm/include/asm/mach/udc_pxa2xx.h
+++ b/arch/arm/include/asm/mach/udc_pxa2xx.h
@@ -21,8 +21,8 @@ struct pxa2xx_udc_mach_info {
 	 * here.  Note that sometimes the signals go through inverters...
 	 */
 	bool	gpio_vbus_inverted;
-	u16	gpio_vbus;			/* high == vbus present */
+	int	gpio_vbus;			/* high == vbus present */
 	bool	gpio_pullup_inverted;
-	u16	gpio_pullup;			/* high == pullup activated */
+	int	gpio_pullup;			/* high == pullup activated */
 };
 
diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h
new file mode 100644
index 000000000000..fdbc43b2e6c0
--- /dev/null
+++ b/arch/arm/include/asm/memblock.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_ARM_MEMBLOCK_H
+#define _ASM_ARM_MEMBLOCK_H
+
+#ifdef CONFIG_MMU
+extern phys_addr_t lowmem_end_addr;
+#define MEMBLOCK_REAL_LIMIT	lowmem_end_addr
+#else
+#define MEMBLOCK_REAL_LIMIT	0
+#endif
+
+struct meminfo;
+struct machine_desc;
+
+extern void arm_memblock_init(struct meminfo *, struct machine_desc *);
+
+#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 4312ee5e3d0b..23c2e8e5c0fa 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -124,6 +124,15 @@
 #endif /* !CONFIG_MMU */
 
 /*
+ * We fix the TCM memories max 32 KiB ITCM resp DTCM at these
+ * locations
+ */
+#ifdef CONFIG_HAVE_TCM
+#define ITCM_OFFSET	UL(0xfffe0000)
+#define DTCM_OFFSET	UL(0xfffe8000)
+#endif
+
+/*
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
  * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
@@ -158,7 +167,7 @@
 #endif
 
 #ifndef arch_adjust_zones
-#define arch_adjust_zones(node,size,holes) do { } while (0)
+#define arch_adjust_zones(size,holes) do { } while (0)
 #elif !defined(CONFIG_ZONE_DMA)
 #error "custom arch_adjust_zones() requires CONFIG_ZONE_DMA"
 #endif
@@ -234,76 +243,11 @@ static inline __deprecated void *bus_to_virt(unsigned long x)
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
  *  virt_addr_valid(k)	indicates whether a virtual address is valid
  */
-#ifndef CONFIG_DISCONTIGMEM
-
 #define ARCH_PFN_OFFSET		PHYS_PFN_OFFSET
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define virt_addr_valid(kaddr)	((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
 
-#define PHYS_TO_NID(addr)	(0)
-
-#else /* CONFIG_DISCONTIGMEM */
-
-/*
- * This is more complex.  We have a set of mem_map arrays spread
- * around in memory.
- */
-#include <linux/numa.h>
-
-#define arch_pfn_to_nid(pfn)	PFN_TO_NID(pfn)
-#define arch_local_page_offset(pfn, nid) LOCAL_MAP_NR((pfn) << PAGE_SHIFT)
-
-#define virt_to_page(kaddr)					\
-	(ADDR_TO_MAPBASE(kaddr) + LOCAL_MAP_NR(kaddr))
-
-#define virt_addr_valid(kaddr)	(KVADDR_TO_NID(kaddr) < MAX_NUMNODES)
-
-/*
- * Common discontigmem stuff.
- *  PHYS_TO_NID is used by the ARM kernel/setup.c
- */
-#define PHYS_TO_NID(addr)	PFN_TO_NID((addr) >> PAGE_SHIFT)
-
-/*
- * Given a kaddr, ADDR_TO_MAPBASE finds the owning node of the memory
- * and returns the mem_map of that node.
- */
-#define ADDR_TO_MAPBASE(kaddr)	NODE_MEM_MAP(KVADDR_TO_NID(kaddr))
-
-/*
- * Given a page frame number, find the owning node of the memory
- * and returns the mem_map of that node.
- */
-#define PFN_TO_MAPBASE(pfn)	NODE_MEM_MAP(PFN_TO_NID(pfn))
-
-#ifdef NODE_MEM_SIZE_BITS
-#define NODE_MEM_SIZE_MASK	((1 << NODE_MEM_SIZE_BITS) - 1)
-
-/*
- * Given a kernel address, find the home node of the underlying memory.
- */
-#define KVADDR_TO_NID(addr) \
-	(((unsigned long)(addr) - PAGE_OFFSET) >> NODE_MEM_SIZE_BITS)
-
-/*
- * Given a page frame number, convert it to a node id.
- */
-#define PFN_TO_NID(pfn) \
-	(((pfn) - PHYS_PFN_OFFSET) >> (NODE_MEM_SIZE_BITS - PAGE_SHIFT))
-
-/*
- * Given a kaddr, LOCAL_MEM_MAP finds the owning node of the memory
- * and returns the index corresponding to the appropriate page in the
- * node's mem_map.
- */
-#define LOCAL_MAP_NR(addr) \
-	(((unsigned long)(addr) & NODE_MEM_SIZE_MASK) >> PAGE_SHIFT)
-
-#endif /* NODE_MEM_SIZE_BITS */
-
-#endif /* !CONFIG_DISCONTIGMEM */
-
 /*
  * Optional coherency support.  Currently used only by selected
  * Intel XSC3-based systems.
diff --git a/arch/arm/include/asm/mmzone.h b/arch/arm/include/asm/mmzone.h
deleted file mode 100644
index ae63a4fd28c8..000000000000
--- a/arch/arm/include/asm/mmzone.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- *  arch/arm/include/asm/mmzone.h
- *
- *  1999-12-29	Nicolas Pitre		Created
- *
- * 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_MMZONE_H
-#define __ASM_MMZONE_H
-
-/*
- * Currently defined in arch/arm/mm/discontig.c
- */
-extern pg_data_t discontig_node_data[];
-
-/*
- * Return a pointer to the node data for node n.
- */
-#define NODE_DATA(nid)		(&discontig_node_data[nid])
-
-/*
- * NODE_MEM_MAP gives the kaddr for the mem_map of the node.
- */
-#define NODE_MEM_MAP(nid)	(NODE_DATA(nid)->node_mem_map)
-
-#include <mach/memory.h>
-
-#endif
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 6a89567ffc5b..7bed3daf83b8 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -91,7 +91,11 @@ extern void release_thread(struct task_struct *);
 
 unsigned long get_wchan(struct task_struct *p);
 
+#if __LINUX_ARM_ARCH__ == 6
+#define cpu_relax()			smp_mb()
+#else
 #define cpu_relax()			barrier()
+#endif
 
 /*
  * Create a new kernel thread
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 9dcb11e59026..c974be8913a7 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -184,6 +184,42 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 #define predicate(x)		((x) & 0xf0000000)
 #define PREDICATE_ALWAYS	0xe0000000
 
+/*
+ * kprobe-based event tracer support
+ */
+#include <linux/stddef.h>
+#include <linux/types.h>
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0))
+
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+extern bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+					       unsigned int n);
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	   pt_regs from which register value is gotten
+ * @offset:    offset number of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+					      unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->ARM_sp;
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index f392fb4437af..f1e5a9bca249 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -201,8 +201,7 @@ static struct tagtable __tagtable_##fn __tag = { tag, fn }
 struct membank {
 	unsigned long start;
 	unsigned long size;
-	unsigned short node;
-	unsigned short highmem;
+	unsigned int highmem;
 };
 
 struct meminfo {
@@ -212,9 +211,8 @@ struct meminfo {
 
 extern struct meminfo meminfo;
 
-#define for_each_nodebank(iter,mi,no)			\
-	for (iter = 0; iter < (mi)->nr_banks; iter++)	\
-		if ((mi)->bank[iter].node == no)
+#define for_each_bank(iter,mi)				\
+	for (iter = 0; iter < (mi)->nr_banks; iter++)
 
 #define bank_pfn_start(bank)	__phys_to_pfn((bank)->start)
 #define bank_pfn_end(bank)	__phys_to_pfn((bank)->start + (bank)->size)
diff --git a/arch/arm/include/asm/stackprotector.h b/arch/arm/include/asm/stackprotector.h
new file mode 100644
index 000000000000..de003327be97
--- /dev/null
+++ b/arch/arm/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on ARM.  This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+
+	current->stack_canary = canary;
+	__stack_chk_guard = current->stack_canary;
+}
+
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 5f4f48002734..8ba1ccf82a02 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -83,7 +83,7 @@ void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
 
 void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 				       struct pt_regs *),
-		     int sig, const char *name);
+		     int sig, int code, const char *name);
 
 #define xchg(ptr,x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
new file mode 100644
index 000000000000..e71d6ff8d104
--- /dev/null
+++ b/arch/arm/include/asm/tls.h
@@ -0,0 +1,46 @@
+#ifndef __ASMARM_TLS_H
+#define __ASMARM_TLS_H
+
+#ifdef __ASSEMBLY__
+	.macro set_tls_none, tp, tmp1, tmp2
+	.endm
+
+	.macro set_tls_v6k, tp, tmp1, tmp2
+	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
+	.endm
+
+	.macro set_tls_v6, tp, tmp1, tmp2
+	ldr	\tmp1, =elf_hwcap
+	ldr	\tmp1, [\tmp1, #0]
+	mov	\tmp2, #0xffff0fff
+	tst	\tmp1, #HWCAP_TLS		@ hardware TLS available?
+	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
+	.endm
+
+	.macro set_tls_software, tp, tmp1, tmp2
+	mov	\tmp1, #0xffff0fff
+	str	\tp, [\tmp1, #-15]		@ set TLS value at 0xffff0ff0
+	.endm
+#endif
+
+#ifdef CONFIG_TLS_REG_EMUL
+#define tls_emu		1
+#define has_tls_reg		1
+#define set_tls		set_tls_none
+#elif __LINUX_ARM_ARCH__ >= 7 ||					\
+	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
+#define tls_emu		0
+#define has_tls_reg		1
+#define set_tls		set_tls_v6k
+#elif __LINUX_ARM_ARCH__ == 6
+#define tls_emu		0
+#define has_tls_reg		(elf_hwcap & HWCAP_TLS)
+#define set_tls		set_tls_v6
+#else
+#define tls_emu		0
+#define has_tls_reg		0
+#define set_tls		set_tls_software
+#endif
+
+#endif	/* __ASMARM_TLS_H */
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index 422f3cc204a2..3d5fc41ae8d3 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -3,6 +3,8 @@
  *
  * Assembler-only file containing VFP macros and register definitions.
  */
+#include <asm/hwcap.h>
+
 #include "vfp.h"
 
 @ Macros to allow building with old toolkits (with no VFP support)
@@ -22,12 +24,20 @@
 	LDC	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d0-d15}
 #endif
 #ifdef CONFIG_VFPv3
+#if __LINUX_ARM_ARCH__ <= 6
+	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
+	ldr	\tmp, [\tmp, #0]
+	tst	\tmp, #HWCAP_VFPv3D16
+	ldceq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addne	\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}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
+#endif
 	.endm
 
 	@ write all the working registers out of the VFP
@@ -38,10 +48,18 @@
 	STC	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d0-d15}
 #endif
 #ifdef CONFIG_VFPv3
+#if __LINUX_ARM_ARCH__ <= 6
+	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
+	ldr	\tmp, [\tmp, #0]
+	tst	\tmp, #HWCAP_VFPv3D16
+	stceq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addne	\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}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
+#endif
 	.endm