diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index cbef09b..69ddf9f 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -16,6 +16,9 @@
      performs the same operation).
 	"marvell,"aurora-outer-cache: Marvell Controller designed to be
 	 compatible with the ARM one with outer cache mode.
+	"bcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
+	offset needs to be added to the address before passing down to the L2
+	cache controller
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 136f263..5a326f9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -175,6 +175,9 @@
 	  and that the relevant menu configurations are displayed for
 	  it.
 
+config ARCH_HAS_BANDGAP
+	bool
+
 config GENERIC_HWEIGHT
 	bool
 	default y
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 1ba358b..de4e1cb 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -59,37 +59,43 @@
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
-arch-$(CONFIG_CPU_32v7)		:=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
-arch-$(CONFIG_CPU_32v6)		:=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
+arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
+arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
 # Only override the compiler option if ARMv6. The ARMv6K extensions are
 # always available in ARMv7
 ifeq ($(CONFIG_CPU_32v6),y)
-arch-$(CONFIG_CPU_32v6K)	:=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k)
+arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k)
 endif
-arch-$(CONFIG_CPU_32v5)		:=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
-arch-$(CONFIG_CPU_32v4T)	:=-D__LINUX_ARM_ARCH__=4 -march=armv4t
-arch-$(CONFIG_CPU_32v4)		:=-D__LINUX_ARM_ARCH__=4 -march=armv4
-arch-$(CONFIG_CPU_32v3)		:=-D__LINUX_ARM_ARCH__=3 -march=armv3
+arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
+arch-$(CONFIG_CPU_32v4T)	=-D__LINUX_ARM_ARCH__=4 -march=armv4t
+arch-$(CONFIG_CPU_32v4)		=-D__LINUX_ARM_ARCH__=4 -march=armv4
+arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3
+
+# Evaluate arch cc-option calls now
+arch-y := $(arch-y)
 
 # This selects how we optimise for the processor.
-tune-$(CONFIG_CPU_ARM7TDMI)	:=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM720T)	:=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM740T)	:=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM9TDMI)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM940T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM946E)	:=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
-tune-$(CONFIG_CPU_ARM920T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM922T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM925T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM926T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_FA526)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_SA110)	:=-mtune=strongarm110
-tune-$(CONFIG_CPU_SA1100)	:=-mtune=strongarm1100
-tune-$(CONFIG_CPU_XSCALE)	:=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_XSC3)		:=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_FEROCEON)	:=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
-tune-$(CONFIG_CPU_V6)		:=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
-tune-$(CONFIG_CPU_V6K)		:=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_ARM7TDMI)	=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM720T)	=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM740T)	=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM9TDMI)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM940T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM946E)	=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
+tune-$(CONFIG_CPU_ARM920T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM922T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM925T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM926T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_FA526)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_SA110)	=-mtune=strongarm110
+tune-$(CONFIG_CPU_SA1100)	=-mtune=strongarm1100
+tune-$(CONFIG_CPU_XSCALE)	=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
+tune-$(CONFIG_CPU_XSC3)		=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
+tune-$(CONFIG_CPU_FEROCEON)	=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
+tune-$(CONFIG_CPU_V6)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+
+# Evaluate tune cc-option calls now
+tune-y := $(tune-y)
 
 ifeq ($(CONFIG_AEABI),y)
 CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork
@@ -289,9 +295,10 @@
 zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
-%.dtb: scripts
+%.dtb: | scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) $(boot)/dts/$@
 
+PHONY += dtbs
 dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) dtbs
 
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index aabc02a..d1153c8 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -53,6 +53,17 @@
 	return fdt_getprop(fdt, offset, property, len);
 }
 
+static uint32_t get_cell_size(const void *fdt)
+{
+	int len;
+	uint32_t cell_size = 1;
+	const uint32_t *size_len =  getprop(fdt, "/", "#size-cells", &len);
+
+	if (size_len)
+		cell_size = fdt32_to_cpu(*size_len);
+	return cell_size;
+}
+
 static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
 {
 	char cmdline[COMMAND_LINE_SIZE];
@@ -95,9 +106,11 @@
 int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 {
 	struct tag *atag = atag_list;
-	uint32_t mem_reg_property[2 * NR_BANKS];
+	/* In the case of 64 bits memory size, need to reserve 2 cells for
+	 * address and size for each bank */
+	uint32_t mem_reg_property[2 * 2 * NR_BANKS];
 	int memcount = 0;
-	int ret;
+	int ret, memsize;
 
 	/* make sure we've got an aligned pointer */
 	if ((u32)atag_list & 0x3)
@@ -137,8 +150,25 @@
 				continue;
 			if (!atag->u.mem.size)
 				continue;
-			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
-			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+			memsize = get_cell_size(fdt);
+
+			if (memsize == 2) {
+				/* if memsize is 2, that means that
+				 * each data needs 2 cells of 32 bits,
+				 * so the data are 64 bits */
+				uint64_t *mem_reg_prop64 =
+					(uint64_t *)mem_reg_property;
+				mem_reg_prop64[memcount++] =
+					cpu_to_fdt64(atag->u.mem.start);
+				mem_reg_prop64[memcount++] =
+					cpu_to_fdt64(atag->u.mem.size);
+			} else {
+				mem_reg_property[memcount++] =
+					cpu_to_fdt32(atag->u.mem.start);
+				mem_reg_property[memcount++] =
+					cpu_to_fdt32(atag->u.mem.size);
+			}
+
 		} else if (atag->hdr.tag == ATAG_INITRD2) {
 			uint32_t initrd_start, initrd_size;
 			initrd_start = atag->u.initrd.start;
@@ -150,8 +180,10 @@
 		}
 	}
 
-	if (memcount)
-		setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+	if (memcount) {
+		setprop(fdt, "/memory", "reg", mem_reg_property,
+			4 * memcount * memsize);
+	}
 
 	return fdt_pack(fdt);
 }
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 032a8d9..75189f1 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -142,7 +142,6 @@
 		mov	r7, r1			@ save architecture ID
 		mov	r8, r2			@ save atags pointer
 
-#ifndef __ARM_ARCH_2__
 		/*
 		 * Booting from Angel - need to enter SVC mode and disable
 		 * FIQs/IRQs (numeric definitions from angel arm.h source).
@@ -158,10 +157,6 @@
 		safe_svcmode_maskall r0
 		msr	spsr_cxsf, r9		@ Save the CPU boot mode in
 						@ SPSR
-#else
-		teqp	pc, #0x0c000003		@ turn off interrupts
-#endif
-
 		/*
 		 * Note that some cache flushing and other stuff may
 		 * be needed here - is there an Angel SWI call for this?
@@ -183,7 +178,19 @@
 		ldr	r4, =zreladdr
 #endif
 
-		bl	cache_on
+		/*
+		 * Set up a page table only if it won't overwrite ourself.
+		 * That means r4 < pc && r4 - 16k page directory > &_end.
+		 * Given that r4 > &_end is most unfrequent, we add a rough
+		 * additional 1MB of room for a possible appended DTB.
+		 */
+		mov	r0, pc
+		cmp	r0, r4
+		ldrcc	r0, LC0+32
+		addcc	r0, r0, pc
+		cmpcc	r4, r0
+		orrcc	r4, r4, #1		@ remember we skipped cache_on
+		blcs	cache_on
 
 restart:	adr	r0, LC0
 		ldmia	r0, {r1, r2, r3, r6, r10, r11, r12}
@@ -229,7 +236,7 @@
  *   r0  = delta
  *   r2  = BSS start
  *   r3  = BSS end
- *   r4  = final kernel address
+ *   r4  = final kernel address (possibly with LSB set)
  *   r5  = appended dtb size (still unknown)
  *   r6  = _edata
  *   r7  = architecture ID
@@ -277,6 +284,7 @@
 		 */
 		cmp	r0, #1
 		sub	r0, r4, #TEXT_OFFSET
+		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
 		sub	r2, sp, r6
@@ -323,12 +331,13 @@
 
 /*
  * Check to see if we will overwrite ourselves.
- *   r4  = final kernel address
+ *   r4  = final kernel address (possibly with LSB set)
  *   r9  = size of decompressed image
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
  * We basically want:
  *   r4 - 16k page directory >= r10 -> OK
  *   r4 + image length <= address of wont_overwrite -> OK
+ * Note: the possible LSB in r4 is harmless here.
  */
 		add	r10, r10, #16384
 		cmp	r4, r10
@@ -390,7 +399,8 @@
 		add	sp, sp, r6
 #endif
 
-		bl	cache_clean_flush
+		tst	r4, #1
+		bleq	cache_clean_flush
 
 		adr	r0, BSYM(restart)
 		add	r0, r0, r6
@@ -402,7 +412,7 @@
  *   r0  = delta
  *   r2  = BSS start
  *   r3  = BSS end
- *   r4  = kernel execution address
+ *   r4  = kernel execution address (possibly with LSB set)
  *   r5  = appended dtb size (0 if not present)
  *   r7  = architecture ID
  *   r8  = atags pointer
@@ -465,6 +475,15 @@
 		cmp	r2, r3
 		blo	1b
 
+		/*
+		 * Did we skip the cache setup earlier?
+		 * That is indicated by the LSB in r4.
+		 * Do it now if so.
+		 */
+		tst	r4, #1
+		bic	r4, r4, #1
+		blne	cache_on
+
 /*
  * The C runtime environment should now be setup sufficiently.
  * Set up some pointers, and start decompressing.
@@ -513,6 +532,7 @@
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
 		.word	.L_user_stack_end	@ sp
+		.word	_end - restart + 16384 + 1024*1024
 		.size	LC0, . - LC0
 
 #ifdef CONFIG_ARCH_RPC
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index 41b2c6c..5e48c85 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -47,10 +47,10 @@
 	};
 
 	L2: l2-cache {
-		    compatible = "arm,pl310-cache";
-		    reg = <0x3ff20000 0x1000>;
-		    cache-unified;
-		    cache-level = <2>;
+		compatible = "bcm,bcm11351-a2-pl310-cache";
+		reg = <0x3ff20000 0x1000>;
+		cache-unified;
+		cache-level = <2>;
 	};
 
 	timer@35006000 {
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 8178705..80f033614 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -32,11 +32,11 @@
 1901:	adr	r0, 1902b
 	bl	printascii
 	mov	r0, r9
-	bl	printhex8
+	bl	printhex2
 	adr	r0, 1903b
 	bl	printascii
 	mov	r0, r10
-	bl	printhex8
+	bl	printhex2
 	adr	r0, 1904b
 	bl	printascii
 #endif
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 3caed0d..510e5b1 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -19,10 +19,6 @@
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
 
-static void __init simple_smp_init_cpus(void)
-{
-}
-
 static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	unsigned int mpidr, pcpu, pcluster, ret;
@@ -74,7 +70,6 @@
 #endif
 
 static struct smp_operations __initdata mcpm_smp_ops = {
-	.smp_init_cpus		= simple_smp_init_cpus,
 	.smp_boot_secondary	= mcpm_boot_secondary,
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index fe92ccf..191ada6 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -46,7 +46,7 @@
 	__rem;							\
 })
 
-#if __GNUC__ < 4
+#if __GNUC__ < 4 || !defined(CONFIG_AEABI)
 
 /*
  * gcc versions earlier than 4.0 are simply too problematic for the
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 652b560..d070741 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -130,16 +130,16 @@
  */
 extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
 	size_t, unsigned int, void *);
-extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int,
+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(unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached);
+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)(unsigned long, size_t,
+extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
 extern void (*arch_iounmap)(volatile void __iomem *);
 
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index a7b85e0..b5792b7 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
+#include <asm/smp_plat.h>
 #include <asm-generic/mm_hooks.h>
 
 void __check_vmalloc_seq(struct mm_struct *mm);
@@ -27,7 +28,15 @@
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
 #define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
 
-DECLARE_PER_CPU(atomic64_t, active_asids);
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask);
+#else  /* !CONFIG_ARM_ERRATA_798181 */
+static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+					   cpumask_t *mask)
+{
+}
+#endif /* CONFIG_ARM_ERRATA_798181 */
 
 #else	/* !CONFIG_CPU_HAS_ASID */
 
@@ -98,12 +107,16 @@
 #ifdef CONFIG_MMU
 	unsigned int cpu = smp_processor_id();
 
-#ifdef CONFIG_SMP
-	/* check for possible thread migration */
-	if (!cpumask_empty(mm_cpumask(next)) &&
+	/*
+	 * __sync_icache_dcache doesn't broadcast the I-cache invalidation,
+	 * so check for possible thread migration and invalidate the I-cache
+	 * if we're new to this CPU.
+	 */
+	if (cache_ops_need_broadcast() &&
+	    !cpumask_empty(mm_cpumask(next)) &&
 	    !cpumask_test_cpu(cpu, mm_cpumask(next)))
 		__flush_icache_all();
-#endif
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
 		check_and_switch_context(next, tsk);
 		if (cache_is_vivt())
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 6220e9f..f8b8965 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -97,19 +97,22 @@
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned long tmp;
+	unsigned long contended, res;
 	u32 slock;
 
-	__asm__ __volatile__(
-"	ldrex	%0, [%2]\n"
-"	subs	%1, %0, %0, ror #16\n"
-"	addeq	%0, %0, %3\n"
-"	strexeq	%1, %0, [%2]"
-	: "=&r" (slock), "=&r" (tmp)
-	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
-	: "cc");
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%3]\n"
+		"	mov	%2, #0\n"
+		"	subs	%1, %0, %0, ror #16\n"
+		"	addeq	%0, %0, %4\n"
+		"	strexeq	%2, %0, [%3]"
+		: "=&r" (slock), "=&r" (contended), "=r" (res)
+		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
+		: "cc");
+	} while (res);
 
-	if (tmp == 0) {
+	if (!contended) {
 		smp_mb();
 		return 1;
 	} else {
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 1995d1a..214d415 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -58,7 +58,7 @@
 	struct cpu_context_save	cpu_context;	/* cpu context */
 	__u32			syscall;	/* syscall number */
 	__u8			used_cp[16];	/* thread used copro */
-	unsigned long		tp_value;
+	unsigned long		tp_value[2];	/* TLS registers */
 #ifdef CONFIG_CRUNCH
 	struct crunch_state	crunchstate;
 #endif
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 73409e6..83259b8 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -2,27 +2,30 @@
 #define __ASMARM_TLS_H
 
 #ifdef __ASSEMBLY__
-	.macro set_tls_none, tp, tmp1, tmp2
+#include <asm/asm-offsets.h>
+	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
 	.endm
 
-	.macro set_tls_v6k, tp, tmp1, tmp2
+	.macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2
+	mrc	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
 	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
-	mov	\tmp1, #0
-	mcr	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
+	mcr	p15, 0, \tpuser, c13, c0, 2	@ and the user r/w register
+	str	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm
 
-	.macro set_tls_v6, tp, tmp1, tmp2
+	.macro switch_tls_v6, base, tp, tpuser, 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
-	movne	\tmp1, #0
-	mcrne	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
+	mrcne	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
+	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	mcrne	p15, 0, \tpuser, c13, c0, 2	@ set user r/w register
+	strne	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm
 
-	.macro set_tls_software, tp, tmp1, tmp2
+	.macro switch_tls_software, base, tp, tpuser, tmp1, tmp2
 	mov	\tmp1, #0xffff0fff
 	str	\tp, [\tmp1, #-15]		@ set TLS value at 0xffff0ff0
 	.endm
@@ -31,19 +34,30 @@
 #ifdef CONFIG_TLS_REG_EMUL
 #define tls_emu		1
 #define has_tls_reg		1
-#define set_tls		set_tls_none
+#define switch_tls	switch_tls_none
 #elif defined(CONFIG_CPU_V6)
 #define tls_emu		0
 #define has_tls_reg		(elf_hwcap & HWCAP_TLS)
-#define set_tls		set_tls_v6
+#define switch_tls	switch_tls_v6
 #elif defined(CONFIG_CPU_32v6K)
 #define tls_emu		0
 #define has_tls_reg		1
-#define set_tls		set_tls_v6k
+#define switch_tls	switch_tls_v6k
 #else
 #define tls_emu		0
 #define has_tls_reg		0
-#define set_tls		set_tls_software
+#define switch_tls	switch_tls_software
 #endif
 
+#ifndef __ASSEMBLY__
+static inline unsigned long get_tpuser(void)
+{
+	unsigned long reg = 0;
+
+	if (has_tls_reg && !tls_emu)
+		__asm__("mrc p15, 0, %0, c13, c0, 2" : "=r" (reg));
+
+	return reg;
+}
+#endif
 #endif	/* __ASMARM_TLS_H */
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 582b405..a39cfc2a1 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -685,15 +685,16 @@
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	add	ip, r1, #TI_CPU_SAVE
-	ldr	r3, [r2, #TI_TP_VALUE]
  ARM(	stmia	ip!, {r4 - sl, fp, sp, lr} )	@ Store most regs on stack
  THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
  THUMB(	str	sp, [ip], #4		   )
  THUMB(	str	lr, [ip], #4		   )
+	ldr	r4, [r2, #TI_TP_VALUE]
+	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-	set_tls	r3, r4, r5
+	switch_tls r1, r4, r5, r3, r7
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
 	ldr	r7, [r2, #TI_TASK]
 	ldr	r8, =__stack_chk_guard
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index bc5bc0a..4bc816a 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -362,6 +362,16 @@
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
 	zero_fp
 
+#ifdef CONFIG_ALIGNMENT_TRAP
+	ldr	ip, __cr_alignment
+	ldr	ip, [ip]
+	mcr	p15, 0, ip, c1, c0		@ update control register
+#endif
+
+	enable_irq
+	ct_user_exit
+	get_thread_info tsk
+
 	/*
 	 * Get the system call number.
 	 */
@@ -375,9 +385,9 @@
 #ifdef CONFIG_ARM_THUMB
 	tst	r8, #PSR_T_BIT
 	movne	r10, #0				@ no thumb OABI emulation
-	ldreq	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldreq	r10, [lr, #-4]		)	@ get SWI instruction
 #else
-	ldr	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
 #endif
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	rev	r10, r10			@ little endian instruction
@@ -392,22 +402,13 @@
 	/* Legacy ABI only, possibly thumb mode. */
 	tst	r8, #PSR_T_BIT			@ this is SPSR from save_user_regs
 	addne	scno, r7, #__NR_SYSCALL_BASE	@ put OS number in
-	ldreq	scno, [lr, #-4]
+ USER(	ldreq	scno, [lr, #-4]		)
 
 #else
 	/* Legacy ABI only. */
-	ldr	scno, [lr, #-4]			@ get SWI instruction
+ USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldr	ip, __cr_alignment
-	ldr	ip, [ip]
-	mcr	p15, 0, ip, c1, c0		@ update control register
-#endif
-	enable_irq
-	ct_user_exit
-
-	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -442,6 +443,21 @@
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall	
 	b	sys_ni_syscall			@ not private func
+
+#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
+	/*
+	 * We failed to handle a fault trying to access the page
+	 * containing the swi instruction, but we're not really in a
+	 * position to return -EFAULT. Instead, return back to the
+	 * instruction and re-enter the user fault handling path trying
+	 * to page it in. This will likely result in sending SEGV to the
+	 * current task.
+	 */
+9001:
+	sub	lr, lr, #4
+	str	lr, [sp, #S_PC]
+	b	ret_fast_syscall
+#endif
 ENDPROC(vector_swi)
 
 	/*
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 8c3094d..d9f5cd4 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -569,6 +569,7 @@
 		return;
 	}
 
+	perf_callchain_store(entry, regs->ARM_pc);
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
 	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 6e8931c..7f1efcd 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -39,6 +39,7 @@
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/time.h>
+#include <asm/tls.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -374,7 +375,8 @@
 	clear_ptrace_hw_breakpoint(p);
 
 	if (clone_flags & CLONE_SETTLS)
-		thread->tp_value = childregs->ARM_r3;
+		thread->tp_value[0] = childregs->ARM_r3;
+	thread->tp_value[1] = get_tpuser();
 
 	thread_notify(THREAD_NOTIFY_COPY, thread);
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 03deeff..2bc1514 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -849,7 +849,7 @@
 #endif
 
 		case PTRACE_GET_THREAD_AREA:
-			ret = put_user(task_thread_info(child)->tp_value,
+			ret = put_user(task_thread_info(child)->tp_value[0],
 				       datap);
 			break;
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b4b1d39..0cde326 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -456,6 +456,13 @@
 	for (i = 1; i < nr_cpu_ids; ++i)
 		cpu_logical_map(i) = i == cpu ? 0 : i;
 
+	/*
+	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
+	 * using percpu variable early, for example, lockdep will
+	 * access percpu variable inside lock_release
+	 */
+	set_my_cpu_offset(0);
+
 	printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
 }
 
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 9a52a07..a98b62d 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -103,7 +103,7 @@
 
 static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 {
-	int cpu, this_cpu;
+	int this_cpu;
 	cpumask_t mask = { CPU_BITS_NONE };
 
 	if (!erratum_a15_798181())
@@ -111,21 +111,7 @@
 
 	dummy_flush_tlb_a15_erratum();
 	this_cpu = get_cpu();
-	for_each_online_cpu(cpu) {
-		if (cpu == this_cpu)
-			continue;
-		/*
-		 * We only need to send an IPI if the other CPUs are running
-		 * the same ASID as the one being invalidated. There is no
-		 * need for locking around the active_asids check since the
-		 * switch_mm() function has at least one dmb() (as required by
-		 * this workaround) in case a context switch happens on
-		 * another CPU after the condition below.
-		 */
-		if (atomic64_read(&mm->context.id) ==
-		    atomic64_read(&per_cpu(active_asids, cpu)))
-			cpumask_set_cpu(cpu, &mask);
-	}
+	a15_erratum_get_cpumask(this_cpu, mm, &mask);
 	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
 	put_cpu();
 }
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 18b32e8..517bfd4 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -581,7 +581,7 @@
 		return regs->ARM_r0;
 
 	case NR(set_tls):
-		thread->tp_value = regs->ARM_r0;
+		thread->tp_value[0] = regs->ARM_r0;
 		if (tls_emu)
 			return 0;
 		if (has_tls_reg) {
@@ -699,7 +699,7 @@
 	int reg = (instr >> 12) & 15;
 	if (reg == 15)
 		return 1;
-	regs->uregs[reg] = current_thread_info()->tp_value;
+	regs->uregs[reg] = current_thread_info()->tp_value[0];
 	regs->ARM_pc += 4;
 	return 0;
 }
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index b13cc74..8a53f34 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -116,7 +116,7 @@
 	iotable_init(ebsa110_io_desc, ARRAY_SIZE(ebsa110_io_desc));
 }
 
-static void __iomem *ebsa110_ioremap_caller(unsigned long cookie, size_t size,
+static void __iomem *ebsa110_ioremap_caller(phys_addr_t cookie, size_t size,
 					    unsigned int flags, void *caller)
 {
 	return (void __iomem *)cookie;
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index e0e69a6..eed32ca 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -65,7 +65,7 @@
 		: "=r" (reg));
 }
 
-static void __iomem *imx3_ioremap_caller(unsigned long phys_addr, size_t size,
+static void __iomem *imx3_ioremap_caller(phys_addr_t phys_addr, size_t size,
 					 unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
diff --git a/arch/arm/mach-iop13xx/io.c b/arch/arm/mach-iop13xx/io.c
index 183dc8b..faaf7d4 100644
--- a/arch/arm/mach-iop13xx/io.c
+++ b/arch/arm/mach-iop13xx/io.c
@@ -23,7 +23,7 @@
 
 #include "pci.h"
 
-static void __iomem *__iop13xx_ioremap_caller(unsigned long cookie,
+static void __iomem *__iop13xx_ioremap_caller(phys_addr_t cookie,
 	size_t size, unsigned int mtype, void *caller)
 {
 	void __iomem * retval;
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 6600cff..d7223b3 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -559,7 +559,7 @@
  * fallback to the default.
  */
 
-static void __iomem *ixp4xx_ioremap_caller(unsigned long addr, size_t size,
+static void __iomem *ixp4xx_ioremap_caller(phys_addr_t addr, size_t size,
 					   unsigned int mtype, void *caller)
 {
 	if (!is_pci_memory(addr))
diff --git a/arch/arm/mach-msm/common.h b/arch/arm/mach-msm/common.h
index ce8215a..421cf77 100644
--- a/arch/arm/mach-msm/common.h
+++ b/arch/arm/mach-msm/common.h
@@ -23,7 +23,7 @@
 extern void msm_map_msm8960_io(void);
 extern void msm_map_qsd8x50_io(void);
 
-extern void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+extern void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 					  unsigned int mtype, void *caller);
 
 extern struct smp_operations msm_smp_ops;
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 123ef9cb..fd65b6d 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -172,7 +172,7 @@
 }
 #endif /* CONFIG_ARCH_MSM7X30 */
 
-void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index f49cd51..8620ab5 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -4,6 +4,7 @@
 config ARCH_OMAP2PLUS
 	bool "TI OMAP2/3/4/5 SoCs with device tree support" if (ARCH_MULTI_V6 || ARCH_MULTI_V7)
 	select ARCH_HAS_CPUFREQ
+	select ARCH_HAS_BANDGAP
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c465fac..d70e0ab 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -523,6 +523,147 @@
 	}
 }
 
+/*
+ * For certain Broadcom SoCs, depending on the address range, different offsets
+ * need to be added to the address before passing it to L2 for
+ * invalidation/clean/flush
+ *
+ * Section Address Range              Offset        EMI
+ *   1     0x00000000 - 0x3FFFFFFF    0x80000000    VC
+ *   2     0x40000000 - 0xBFFFFFFF    0x40000000    SYS
+ *   3     0xC0000000 - 0xFFFFFFFF    0x80000000    VC
+ *
+ * When the start and end addresses have crossed two different sections, we
+ * need to break the L2 operation into two, each within its own section.
+ * For example, if we need to invalidate addresses starts at 0xBFFF0000 and
+ * ends at 0xC0001000, we need do invalidate 1) 0xBFFF0000 - 0xBFFFFFFF and 2)
+ * 0xC0000000 - 0xC0001000
+ *
+ * Note 1:
+ * By breaking a single L2 operation into two, we may potentially suffer some
+ * performance hit, but keep in mind the cross section case is very rare
+ *
+ * Note 2:
+ * We do not need to handle the case when the start address is in
+ * Section 1 and the end address is in Section 3, since it is not a valid use
+ * case
+ *
+ * Note 3:
+ * Section 1 in practical terms can no longer be used on rev A2. Because of
+ * that the code does not need to handle section 1 at all.
+ *
+ */
+#define BCM_SYS_EMI_START_ADDR        0x40000000UL
+#define BCM_VC_EMI_SEC3_START_ADDR    0xC0000000UL
+
+#define BCM_SYS_EMI_OFFSET            0x40000000UL
+#define BCM_VC_EMI_OFFSET             0x80000000UL
+
+static inline int bcm_addr_is_sys_emi(unsigned long addr)
+{
+	return (addr >= BCM_SYS_EMI_START_ADDR) &&
+		(addr < BCM_VC_EMI_SEC3_START_ADDR);
+}
+
+static inline unsigned long bcm_l2_phys_addr(unsigned long addr)
+{
+	if (bcm_addr_is_sys_emi(addr))
+		return addr + BCM_SYS_EMI_OFFSET;
+	else
+		return addr + BCM_VC_EMI_OFFSET;
+}
+
+static void bcm_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long new_start, new_end;
+
+	BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+	if (unlikely(end <= start))
+		return;
+
+	new_start = bcm_l2_phys_addr(start);
+	new_end = bcm_l2_phys_addr(end);
+
+	/* normal case, no cross section between start and end */
+	if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+		l2x0_inv_range(new_start, new_end);
+		return;
+	}
+
+	/* They cross sections, so it can only be a cross from section
+	 * 2 to section 3
+	 */
+	l2x0_inv_range(new_start,
+		bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+	l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+		new_end);
+}
+
+static void bcm_clean_range(unsigned long start, unsigned long end)
+{
+	unsigned long new_start, new_end;
+
+	BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+	if (unlikely(end <= start))
+		return;
+
+	if ((end - start) >= l2x0_size) {
+		l2x0_clean_all();
+		return;
+	}
+
+	new_start = bcm_l2_phys_addr(start);
+	new_end = bcm_l2_phys_addr(end);
+
+	/* normal case, no cross section between start and end */
+	if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+		l2x0_clean_range(new_start, new_end);
+		return;
+	}
+
+	/* They cross sections, so it can only be a cross from section
+	 * 2 to section 3
+	 */
+	l2x0_clean_range(new_start,
+		bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+	l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+		new_end);
+}
+
+static void bcm_flush_range(unsigned long start, unsigned long end)
+{
+	unsigned long new_start, new_end;
+
+	BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+	if (unlikely(end <= start))
+		return;
+
+	if ((end - start) >= l2x0_size) {
+		l2x0_flush_all();
+		return;
+	}
+
+	new_start = bcm_l2_phys_addr(start);
+	new_end = bcm_l2_phys_addr(end);
+
+	/* normal case, no cross section between start and end */
+	if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+		l2x0_flush_range(new_start, new_end);
+		return;
+	}
+
+	/* They cross sections, so it can only be a cross from section
+	 * 2 to section 3
+	 */
+	l2x0_flush_range(new_start,
+		bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+	l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+		new_end);
+}
+
 static void __init l2x0_of_setup(const struct device_node *np,
 				 u32 *aux_val, u32 *aux_mask)
 {
@@ -765,6 +906,21 @@
 	},
 };
 
+static const struct l2x0_of_data bcm_l2x0_data = {
+	.setup = pl310_of_setup,
+	.save  = pl310_save,
+	.outer_cache = {
+		.resume      = pl310_resume,
+		.inv_range   = bcm_inv_range,
+		.clean_range = bcm_clean_range,
+		.flush_range = bcm_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
+};
+
 static const struct of_device_id l2x0_ids[] __initconst = {
 	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
 	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
@@ -773,6 +929,8 @@
 	  .data = (void *)&aurora_no_outer_data},
 	{ .compatible = "marvell,aurora-outer-cache",
 	  .data = (void *)&aurora_with_outer_data},
+	{ .compatible = "bcm,bcm11351-a2-pl310-cache",
+	  .data = (void *)&bcm_l2x0_data},
 	{}
 };
 
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 2ac3737..eeab06e 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -39,19 +39,43 @@
  * non 64-bit operations.
  */
 #define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
-#define NUM_USER_ASIDS		(ASID_FIRST_VERSION - 1)
-
-#define ASID_TO_IDX(asid)	((asid & ~ASID_MASK) - 1)
-#define IDX_TO_ASID(idx)	((idx + 1) & ~ASID_MASK)
+#define NUM_USER_ASIDS		ASID_FIRST_VERSION
 
 static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
 static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
 
-DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask)
+{
+	int cpu;
+	unsigned long flags;
+	u64 context_id, asid;
+
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+	context_id = mm->context.id.counter;
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		/*
+		 * We only need to send an IPI if the other CPUs are
+		 * running the same ASID as the one being invalidated.
+		 */
+		asid = per_cpu(active_asids, cpu).counter;
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, cpu);
+		if (context_id == asid)
+			cpumask_set_cpu(cpu, mask);
+	}
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+#endif
+
 #ifdef CONFIG_ARM_LPAE
 static void cpu_set_reserved_ttbr0(void)
 {
@@ -128,7 +152,16 @@
 			asid = 0;
 		} else {
 			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			__set_bit(ASID_TO_IDX(asid), asid_map);
+			/*
+			 * If this CPU has already been through a
+			 * rollover, but hasn't run another task in
+			 * the meantime, we must preserve its reserved
+			 * ASID, as this is the only trace we have of
+			 * the process it is still running.
+			 */
+			if (asid == 0)
+				asid = per_cpu(reserved_asids, i);
+			__set_bit(asid & ~ASID_MASK, asid_map);
 		}
 		per_cpu(reserved_asids, i) = asid;
 	}
@@ -167,17 +200,19 @@
 		/*
 		 * Allocate a free ASID. If we can't find one, take a
 		 * note of the currently active ASIDs and mark the TLBs
-		 * as requiring flushes.
+		 * as requiring flushes. We always count from ASID #1,
+		 * as we reserve ASID #0 to switch via TTBR0 and indicate
+		 * rollover events.
 		 */
-		asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+		asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		if (asid == NUM_USER_ASIDS) {
 			generation = atomic64_add_return(ASID_FIRST_VERSION,
 							 &asid_generation);
 			flush_context(cpu);
-			asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+			asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		}
 		__set_bit(asid, asid_map);
-		asid = generation | IDX_TO_ASID(asid);
+		asid |= generation;
 		cpumask_clear(mm_cpumask(mm));
 	}
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3..c038ec0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -880,10 +880,24 @@
 	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
 
 	/*
-	 * Mark the D-cache clean for this page to avoid extra flushing.
+	 * Mark the D-cache clean for these pages to avoid extra flushing.
 	 */
-	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
-		set_bit(PG_dcache_clean, &page->flags);
+	if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+		unsigned long pfn;
+		size_t left = size;
+
+		pfn = page_to_pfn(page) + off / PAGE_SIZE;
+		off %= PAGE_SIZE;
+		if (off) {
+			pfn++;
+			left -= PAGE_SIZE - off;
+		}
+		while (left >= PAGE_SIZE) {
+			page = pfn_to_page(pfn++);
+			set_bit(PG_dcache_clean, &page->flags);
+			left -= PAGE_SIZE;
+		}
+	}
 }
 
 /**
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 32aa586..e4ac5d8 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -287,7 +287,7 @@
 	mapping = page_mapping(page);
 
 	if (!cache_ops_need_broadcast() &&
-	    mapping && !mapping_mapped(mapping))
+	    mapping && !page_mapped(page))
 		clear_bit(PG_dcache_clean, &page->flags);
 	else {
 		__flush_dcache_page(mapping, page);
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 04d9006..f123d6e 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -331,10 +331,10 @@
 	return (void __iomem *) (offset + addr);
 }
 
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 	unsigned int mtype, void *caller)
 {
-	unsigned long last_addr;
+	phys_addr_t last_addr;
  	unsigned long offset = phys_addr & ~PAGE_MASK;
  	unsigned long pfn = __phys_to_pfn(phys_addr);
 
@@ -367,12 +367,12 @@
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 				      unsigned int, void *) =
 	__arm_ioremap_caller;
 
 void __iomem *
-__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
 {
 	return arch_ioremap_caller(phys_addr, size, mtype,
 		__builtin_return_address(0));
@@ -387,7 +387,7 @@
  * CONFIG_GENERIC_ALLOCATOR for allocating external memory.
  */
 void __iomem *
-__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
+__arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
 {
 	unsigned int mtype;
 
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index eb5293a..7fe0524 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -87,16 +87,16 @@
 	return __arm_ioremap_pfn(pfn, offset, size, mtype);
 }
 
-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
 			    unsigned int mtype)
 {
 	return (void __iomem *)phys_addr;
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
 
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);
diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S
index b178d44..2677bc3 100644
--- a/arch/arm/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@@ -11,8 +11,6 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-	__INIT
-
 /*
  * Realview/Versatile Express specific entry point for secondary CPUs.
  * This provides a "holding pen" into which all secondary cores are held
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index f4f3038..c3785ed 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -61,6 +61,7 @@
  * @pwrreg_powerup: power up value for MMCIPOWER register
  * @signal_direction: input/out direction of bus signals can be indicated
  * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock
+ * @busy_detect: true if busy detection on dat0 is supported
  */
 struct variant_data {
 	unsigned int		clkreg;
@@ -74,6 +75,7 @@
 	u32			pwrreg_powerup;
 	bool			signal_direction;
 	bool			pwrreg_clkgate;
+	bool			busy_detect;
 };
 
 static struct variant_data variant_arm = {
@@ -132,6 +134,7 @@
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.busy_detect		= true,
 };
 
 static struct variant_data variant_ux500v2 = {
@@ -146,8 +149,28 @@
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.busy_detect		= true,
 };
 
+static int mmci_card_busy(struct mmc_host *mmc)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int busy = 0;
+
+	pm_runtime_get_sync(mmc_dev(mmc));
+
+	spin_lock_irqsave(&host->lock, flags);
+	if (readl(host->base + MMCISTATUS) & MCI_ST_CARDBUSY)
+		busy = 1;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc_dev(mmc));
+	pm_runtime_put_autosuspend(mmc_dev(mmc));
+
+	return busy;
+}
+
 /*
  * Validate mmc prerequisites
  */
@@ -191,11 +214,28 @@
 /*
  * This must be called with host->lock held
  */
+static void mmci_write_datactrlreg(struct mmci_host *host, u32 datactrl)
+{
+	/* Keep ST Micro busy mode if enabled */
+	datactrl |= host->datactrl_reg & MCI_ST_DPSM_BUSYMODE;
+
+	if (host->datactrl_reg != datactrl) {
+		host->datactrl_reg = datactrl;
+		writel(datactrl, host->base + MMCIDATACTRL);
+	}
+}
+
+/*
+ * This must be called with host->lock held
+ */
 static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 {
 	struct variant_data *variant = host->variant;
 	u32 clk = variant->clkreg;
 
+	/* Make sure cclk reflects the current calculated clock */
+	host->cclk = 0;
+
 	if (desired) {
 		if (desired >= host->mclk) {
 			clk = MCI_CLK_BYPASS;
@@ -230,6 +270,9 @@
 		/* clk |= MCI_CLK_PWRSAVE; */
 	}
 
+	/* Set actual clock for debug */
+	host->mmc->actual_clock = host->cclk;
+
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4)
 		clk |= MCI_4BIT_BUS;
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
@@ -275,7 +318,7 @@
 
 static void mmci_stop_data(struct mmci_host *host)
 {
-	writel(0, host->base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, 0);
 	mmci_set_mask1(host, 0);
 	host->data = NULL;
 }
@@ -304,10 +347,8 @@
 	const char *rxname, *txname;
 	dma_cap_mask_t mask;
 
-	if (!plat || !plat->dma_filter) {
-		dev_info(mmc_dev(host->mmc), "no DMA platform data\n");
-		return;
-	}
+	host->dma_rx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "rx");
+	host->dma_tx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "tx");
 
 	/* initialize pre request cookie */
 	host->next_data.cookie = 1;
@@ -316,29 +357,32 @@
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
+	if (plat && plat->dma_filter) {
+		if (!host->dma_rx_channel && plat->dma_rx_param) {
+			host->dma_rx_channel = dma_request_channel(mask,
+							   plat->dma_filter,
+							   plat->dma_rx_param);
+			/* E.g if no DMA hardware is present */
+			if (!host->dma_rx_channel)
+				dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
+		}
+
+		if (!host->dma_tx_channel && plat->dma_tx_param) {
+			host->dma_tx_channel = dma_request_channel(mask,
+							   plat->dma_filter,
+							   plat->dma_tx_param);
+			if (!host->dma_tx_channel)
+				dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
+		}
+	}
+
 	/*
 	 * If only an RX channel is specified, the driver will
 	 * attempt to use it bidirectionally, however if it is
 	 * is specified but cannot be located, DMA will be disabled.
 	 */
-	if (plat->dma_rx_param) {
-		host->dma_rx_channel = dma_request_channel(mask,
-							   plat->dma_filter,
-							   plat->dma_rx_param);
-		/* E.g if no DMA hardware is present */
-		if (!host->dma_rx_channel)
-			dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
-	}
-
-	if (plat->dma_tx_param) {
-		host->dma_tx_channel = dma_request_channel(mask,
-							   plat->dma_filter,
-							   plat->dma_tx_param);
-		if (!host->dma_tx_channel)
-			dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
-	} else {
+	if (host->dma_rx_channel && !host->dma_tx_channel)
 		host->dma_tx_channel = host->dma_rx_channel;
-	}
 
 	if (host->dma_rx_channel)
 		rxname = dma_chan_name(host->dma_rx_channel);
@@ -552,7 +596,7 @@
 	datactrl |= MCI_DPSM_DMAENABLE;
 
 	/* Trigger the DMA transfer */
-	writel(datactrl, host->base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, datactrl);
 
 	/*
 	 * Let the MMCI say when the data is ended and it's time
@@ -750,7 +794,7 @@
 		irqmask = MCI_TXFIFOHALFEMPTYMASK;
 	}
 
-	writel(datactrl, base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, datactrl);
 	writel(readl(base + MMCIMASK0) & ~MCI_DATAENDMASK, base + MMCIMASK0);
 	mmci_set_mask1(host, irqmask);
 }
@@ -842,7 +886,7 @@
 			/* The error clause is handled above, success! */
 			data->bytes_xfered = data->blksz * data->blocks;
 
-		if (!data->stop) {
+		if (!data->stop || host->mrq->sbc) {
 			mmci_request_end(host, data->mrq);
 		} else {
 			mmci_start_command(host, data->stop, 0);
@@ -855,6 +899,7 @@
 	     unsigned int status)
 {
 	void __iomem *base = host->base;
+	bool sbc = (cmd == host->mrq->sbc);
 
 	host->cmd = NULL;
 
@@ -869,7 +914,7 @@
 		cmd->resp[3] = readl(base + MMCIRESPONSE3);
 	}
 
-	if (!cmd->data || cmd->error) {
+	if ((!sbc && !cmd->data) || cmd->error) {
 		if (host->data) {
 			/* Terminate the DMA transfer */
 			if (dma_inprogress(host)) {
@@ -878,7 +923,9 @@
 			}
 			mmci_stop_data(host);
 		}
-		mmci_request_end(host, cmd->mrq);
+		mmci_request_end(host, host->mrq);
+	} else if (sbc) {
+		mmci_start_command(host, host->mrq->cmd, 0);
 	} else if (!(cmd->data->flags & MMC_DATA_READ)) {
 		mmci_start_data(host, cmd->data);
 	}
@@ -1119,7 +1166,10 @@
 	if (mrq->data && mrq->data->flags & MMC_DATA_READ)
 		mmci_start_data(host, mrq->data);
 
-	mmci_start_command(host, mrq->cmd, 0);
+	if (mrq->sbc)
+		mmci_start_command(host, mrq->sbc, 0);
+	else
+		mmci_start_command(host, mrq->cmd, 0);
 
 	spin_unlock_irqrestore(&host->lock, flags);
 }
@@ -1143,9 +1193,10 @@
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
 
-		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    regulator_is_enabled(mmc->supply.vqmmc))
+		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled) {
 			regulator_disable(mmc->supply.vqmmc);
+			host->vqmmc_enabled = false;
+		}
 
 		break;
 	case MMC_POWER_UP:
@@ -1161,12 +1212,13 @@
 
 		break;
 	case MMC_POWER_ON:
-		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    !regulator_is_enabled(mmc->supply.vqmmc)) {
+		if (!IS_ERR(mmc->supply.vqmmc) && !host->vqmmc_enabled) {
 			ret = regulator_enable(mmc->supply.vqmmc);
 			if (ret < 0)
 				dev_err(mmc_dev(mmc),
 					"failed to enable vqmmc regulator\n");
+			else
+				host->vqmmc_enabled = true;
 		}
 
 		pwr |= MCI_PWR_ON;
@@ -1251,6 +1303,39 @@
 	return status;
 }
 
+static int mmci_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	int ret = 0;
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+
+		pm_runtime_get_sync(mmc_dev(mmc));
+
+		switch (ios->signal_voltage) {
+		case MMC_SIGNAL_VOLTAGE_330:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						2700000, 3600000);
+			break;
+		case MMC_SIGNAL_VOLTAGE_180:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						1700000, 1950000);
+			break;
+		case MMC_SIGNAL_VOLTAGE_120:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						1100000, 1300000);
+			break;
+		}
+
+		if (ret)
+			dev_warn(mmc_dev(mmc), "Voltage switch failed\n");
+
+		pm_runtime_mark_last_busy(mmc_dev(mmc));
+		pm_runtime_put_autosuspend(mmc_dev(mmc));
+	}
+
+	return ret;
+}
+
 static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
 {
 	struct mmci_host *host = dev_id;
@@ -1260,13 +1345,14 @@
 	return IRQ_HANDLED;
 }
 
-static const struct mmc_host_ops mmci_ops = {
+static struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
 	.pre_req	= mmci_pre_request,
 	.post_req	= mmci_post_request,
 	.set_ios	= mmci_set_ios,
 	.get_ro		= mmci_get_ro,
 	.get_cd		= mmci_get_cd,
+	.start_signal_voltage_switch = mmci_sig_volt_switch,
 };
 
 #ifdef CONFIG_OF
@@ -1362,16 +1448,15 @@
 	dev_dbg(mmc_dev(mmc), "designer ID = 0x%02x\n", host->hw_designer);
 	dev_dbg(mmc_dev(mmc), "revision = 0x%01x\n", host->hw_revision);
 
-	host->clk = clk_get(&dev->dev, NULL);
+	host->clk = devm_clk_get(&dev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
-		host->clk = NULL;
 		goto host_free;
 	}
 
 	ret = clk_prepare_enable(host->clk);
 	if (ret)
-		goto clk_free;
+		goto host_free;
 
 	host->plat = plat;
 	host->variant = variant;
@@ -1396,6 +1481,11 @@
 		goto clk_disable;
 	}
 
+	if (variant->busy_detect) {
+		mmci_ops.card_busy = mmci_card_busy;
+		mmci_write_datactrlreg(host, MCI_ST_DPSM_BUSYMODE);
+	}
+
 	mmc->ops = &mmci_ops;
 	/*
 	 * The ARM and ST versions of the block have slightly different
@@ -1576,8 +1666,6 @@
 	iounmap(host->base);
  clk_disable:
 	clk_disable_unprepare(host->clk);
- clk_free:
-	clk_put(host->clk);
  host_free:
 	mmc_free_host(mmc);
  rel_regions:
@@ -1623,7 +1711,6 @@
 
 		iounmap(host->base);
 		clk_disable_unprepare(host->clk);
-		clk_put(host->clk);
 
 		mmc_free_host(mmc);
 
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 1f33ad5..69080fa 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -94,6 +94,7 @@
 /* Extended status bits for the ST Micro variants */
 #define MCI_ST_SDIOIT		(1 << 22)
 #define MCI_ST_CEATAEND		(1 << 23)
+#define MCI_ST_CARDBUSY		(1 << 24)
 
 #define MMCICLEAR		0x038
 #define MCI_CMDCRCFAILCLR	(1 << 0)
@@ -110,6 +111,7 @@
 /* Extended status bits for the ST Micro variants */
 #define MCI_ST_SDIOITC		(1 << 22)
 #define MCI_ST_CEATAENDC	(1 << 23)
+#define MCI_ST_BUSYENDC		(1 << 24)
 
 #define MMCIMASK0		0x03c
 #define MCI_CMDCRCFAILMASK	(1 << 0)
@@ -183,6 +185,8 @@
 	unsigned int		cclk;
 	u32			pwr_reg;
 	u32			clk_reg;
+	u32			datactrl_reg;
+	bool			vqmmc_enabled;
 	struct mmci_platform_data *plat;
 	struct variant_data	*variant;