diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index cf006d40342c..36586dba6fa6 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1186,6 +1186,15 @@ if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
 
+config ARM_ERRATA_326103
+	bool "ARM errata: FSR write bit incorrect on a SWP to read-only memory"
+	depends on CPU_V6
+	help
+	  Executing a SWP instruction to read-only memory does not set bit 11
+	  of the FSR on the ARM 1136 prior to r1p0. This causes the kernel to
+	  treat the access as a read, preventing a COW from occurring and
+	  causing the faulting task to livelock.
+
 config ARM_ERRATA_411920
 	bool "ARM errata: Invalidation of the Instruction Cache operation can fail"
 	depends on CPU_V6 || CPU_V6K
diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts
index 0b32925f2147..e2fe3195c0d1 100644
--- a/arch/arm/boot/dts/versatile-ab.dts
+++ b/arch/arm/boot/dts/versatile-ab.dts
@@ -173,7 +173,7 @@
 			mmc@5000 {
 				compatible = "arm,primecell";
 				reg = < 0x5000 0x1000>;
-				interrupts = <22>;
+				interrupts = <22 34>;
 			};
 			kmi@6000 {
 				compatible = "arm,pl050", "arm,primecell";
diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts
index 166461073b78..7e8175269064 100644
--- a/arch/arm/boot/dts/versatile-pb.dts
+++ b/arch/arm/boot/dts/versatile-pb.dts
@@ -41,7 +41,7 @@
 			mmc@b000 {
 				compatible = "arm,primecell";
 				reg = <0xb000 0x1000>;
-				interrupts = <23>;
+				interrupts = <23 34>;
 			};
 		};
 	};
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index d4c24d412a8d..0f04d84582e1 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -118,6 +118,13 @@ extern void iwmmxt_task_switch(struct thread_info *);
 extern void vfp_sync_hwstate(struct thread_info *);
 extern void vfp_flush_hwstate(struct thread_info *);
 
+struct user_vfp;
+struct user_vfp_exc;
+
+extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
+					   struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp __user *,
+				    struct user_vfp_exc __user *);
 #endif
 
 /*
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 60843eb0f61c..73409e6c0251 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -7,6 +7,8 @@
 
 	.macro set_tls_v6k, tp, tmp1, tmp2
 	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
 	.endm
 
 	.macro set_tls_v6, tp, tmp1, tmp2
@@ -15,6 +17,8 @@
 	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
 	.endm
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 71ccdbfed662..8349d4e97e2b 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -155,10 +155,10 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	}
 
 	c = irq_data_get_irq_chip(d);
-	if (c->irq_set_affinity)
-		c->irq_set_affinity(d, affinity, true);
-	else
+	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 7cb532fc8aa4..d68d1b694680 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -180,44 +180,23 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)
 
 static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 {
-	struct thread_info *thread = current_thread_info();
-	struct vfp_hard_struct *h = &thread->vfpstate.hard;
 	const unsigned long magic = VFP_MAGIC;
 	const unsigned long size = VFP_STORAGE_SIZE;
 	int err = 0;
 
-	vfp_sync_hwstate(thread);
 	__put_user_error(magic, &frame->magic, err);
 	__put_user_error(size, &frame->size, err);
 
-	/*
-	 * Copy the floating point registers. There can be unused
-	 * registers see asm/hwcap.h for details.
-	 */
-	err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs,
-			      sizeof(h->fpregs));
-	/*
-	 * Copy the status and control register.
-	 */
-	__put_user_error(h->fpscr, &frame->ufp.fpscr, err);
+	if (err)
+		return -EFAULT;
 
-	/*
-	 * Copy the exception registers.
-	 */
-	__put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err);
-	__put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
-	__put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
-
-	return err ? -EFAULT : 0;
+	return vfp_preserve_user_clear_hwstate(&frame->ufp, &frame->ufp_exc);
 }
 
 static int restore_vfp_context(struct vfp_sigframe __user *frame)
 {
-	struct thread_info *thread = current_thread_info();
-	struct vfp_hard_struct *h = &thread->vfpstate.hard;
 	unsigned long magic;
 	unsigned long size;
-	unsigned long fpexc;
 	int err = 0;
 
 	__get_user_error(magic, &frame->magic, err);
@@ -228,33 +207,7 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	vfp_flush_hwstate(thread);
-
-	/*
-	 * Copy the floating point registers. There can be unused
-	 * registers see asm/hwcap.h for details.
-	 */
-	err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs,
-				sizeof(h->fpregs));
-	/*
-	 * Copy the status and control register.
-	 */
-	__get_user_error(h->fpscr, &frame->ufp.fpscr, err);
-
-	/*
-	 * Sanitise and restore the exception registers.
-	 */
-	__get_user_error(fpexc, &frame->ufp_exc.fpexc, err);
-	/* Ensure the VFP is enabled. */
-	fpexc |= FPEXC_EN;
-	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
-	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
-	h->fpexc = fpexc;
-
-	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
-	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
-
-	return err ? -EFAULT : 0;
+	return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
 }
 
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index addbbe8028c2..f6a4d32b0421 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -510,10 +510,6 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	platform_cpu_kill(cpu);
-#endif
-
 	while (1)
 		cpu_relax();
 }
@@ -576,17 +572,25 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static void smp_kill_cpus(cpumask_t *mask)
+{
+	unsigned int cpu;
+	for_each_cpu(cpu, mask)
+		platform_cpu_kill(cpu);
+}
+#else
+static void smp_kill_cpus(cpumask_t *mask) { }
+#endif
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
+	struct cpumask mask;
 
-	if (num_online_cpus() > 1) {
-		struct cpumask mask;
-		cpumask_copy(&mask, cpu_online_mask);
-		cpumask_clear_cpu(smp_processor_id(), &mask);
-
-		smp_cross_call(&mask, IPI_CPU_STOP);
-	}
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+	smp_cross_call(&mask, IPI_CPU_STOP);
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
@@ -595,6 +599,8 @@ void smp_send_stop(void)
 
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
+
+	smp_kill_cpus(&mask);
 }
 
 /*
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index ff1f7cc11f87..80741992a9fc 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,18 +26,23 @@ ENTRY(v6_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
- * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR (erratum 326103).
- * The test below covers all the write situations, including Java bytecodes
+ * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR.
  */
-	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
-	tst	r5, #PSR_J_BIT			@ Java?
+#ifdef CONFIG_ARM_ERRATA_326103
+	ldr	ip, =0x4107b36
+	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
+	teq	ip, r3, lsr #4			@ r0 ARM1136?
 	bne	do_DataAbort
-	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
-	ldreq	r3, [r4]			@ read aborted ARM instruction
+	tst	r5, #PSR_J_BIT			@ Java?
+	tsteq	r5, #PSR_T_BIT			@ Thumb?
+	bne	do_DataAbort
+	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
+	ldr	r3, [r4]			@ read aborted ARM instruction
 #ifdef CONFIG_CPU_ENDIAN_BE8
-	reveq	r3, r3
+	rev	r3, r3
 #endif
 	do_ldrd_abort tmp=ip, insn=r3
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
+#endif
 	b	do_DataAbort
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index a53fd2aaa2f4..2a8e380501e8 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -32,6 +32,7 @@ static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
 static u32 l2x0_way_mask;	/* Bitmask of active ways */
 static u32 l2x0_size;
+static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
 
 struct l2x0_regs l2x0_saved_regs;
 
@@ -61,12 +62,7 @@ static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
 
-#ifdef CONFIG_PL310_ERRATA_753970
-	/* write to an unmmapped register */
-	writel_relaxed(0, base + L2X0_DUMMY_REG);
-#else
-	writel_relaxed(0, base + L2X0_CACHE_SYNC);
-#endif
+	writel_relaxed(0, base + sync_reg_offset);
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
@@ -85,10 +81,13 @@ static inline void l2x0_inv_line(unsigned long addr)
 }
 
 #if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
+static inline void debug_writel(unsigned long val)
+{
+	if (outer_cache.set_debug)
+		outer_cache.set_debug(val);
+}
 
-#define debug_writel(val)	outer_cache.set_debug(val)
-
-static void l2x0_set_debug(unsigned long val)
+static void pl310_set_debug(unsigned long val)
 {
 	writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL);
 }
@@ -98,7 +97,7 @@ static inline void debug_writel(unsigned long val)
 {
 }
 
-#define l2x0_set_debug	NULL
+#define pl310_set_debug	NULL
 #endif
 
 #ifdef CONFIG_PL310_ERRATA_588369
@@ -331,6 +330,11 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		else
 			ways = 8;
 		type = "L310";
+#ifdef CONFIG_PL310_ERRATA_753970
+		/* Unmapped register. */
+		sync_reg_offset = L2X0_DUMMY_REG;
+#endif
+		outer_cache.set_debug = pl310_set_debug;
 		break;
 	case L2X0_CACHE_ID_PART_L210:
 		ways = (aux >> 13) & 0xf;
@@ -379,7 +383,6 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	outer_cache.flush_all = l2x0_flush_all;
 	outer_cache.inv_all = l2x0_inv_all;
 	outer_cache.disable = l2x0_disable;
-	outer_cache.set_debug = l2x0_set_debug;
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 595079fa9d1d..8f5813bbffb5 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -293,11 +293,11 @@ EXPORT_SYMBOL(pfn_valid);
 #endif
 
 #ifndef CONFIG_SPARSEMEM
-static void arm_memory_present(void)
+static void __init arm_memory_present(void)
 {
 }
 #else
-static void arm_memory_present(void)
+static void __init arm_memory_present(void)
 {
 	struct memblock_region *reg;
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index b86f8933ff91..2c7cf2f9c837 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -618,8 +618,8 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 	}
 }
 
-static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
-	unsigned long phys, const struct mem_type *type)
+static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
+	unsigned long end, unsigned long phys, const struct mem_type *type)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index ecdb3da0dea9..c58d896cd5c3 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -916,6 +916,13 @@ void omap_start_dma(int lch)
 			l |= OMAP_DMA_CCR_BUFFERING_DISABLE;
 	l |= OMAP_DMA_CCR_EN;
 
+	/*
+	 * As dma_write() uses IO accessors which are weakly ordered, there
+	 * is no guarantee that data in coherent DMA memory will be visible
+	 * to the DMA device.  Add a memory barrier here to ensure that any
+	 * such data is visible prior to enabling DMA.
+	 */
+	mb();
 	p->dma_write(l, CCR, lch);
 
 	dma_chan[lch].flags |= OMAP_DMA_ACTIVE;
@@ -965,6 +972,13 @@ void omap_stop_dma(int lch)
 		p->dma_write(l, CCR, lch);
 	}
 
+	/*
+	 * Ensure that data transferred by DMA is visible to any access
+	 * after DMA has been disabled.  This is important for coherent
+	 * DMA regions.
+	 */
+	mb();
+
 	if (!omap_dma_in_1510_mode() && dma_chan[lch].next_lch != -1) {
 		int next_lch, cur_lch = lch;
 		char dma_chan_link_map[dma_lch_count];
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 858748eaa144..bc683b8219b5 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -17,6 +17,8 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/uaccess.h>
+#include <linux/user.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
@@ -528,6 +530,103 @@ void vfp_flush_hwstate(struct thread_info *thread)
 	put_cpu();
 }
 
+/*
+ * Save the current VFP state into the provided structures and prepare
+ * for entry into a new function (signal handler).
+ */
+int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
+				    struct user_vfp_exc __user *ufp_exc)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
+	int err = 0;
+
+	/* Ensure that the saved hwstate is up-to-date. */
+	vfp_sync_hwstate(thread);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_to_user(&ufp->fpregs, &hwstate->fpregs,
+			      sizeof(hwstate->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__put_user_error(hwstate->fpscr, &ufp->fpscr, err);
+
+	/*
+	 * Copy the exception registers.
+	 */
+	__put_user_error(hwstate->fpexc, &ufp_exc->fpexc, err);
+	__put_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
+	__put_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Ensure that VFP is disabled. */
+	vfp_flush_hwstate(thread);
+
+	/*
+	 * As per the PCS, clear the length and stride bits for function
+	 * entry.
+	 */
+	hwstate->fpscr &= ~(FPSCR_LENGTH_MASK | FPSCR_STRIDE_MASK);
+
+	/*
+	 * Disable VFP in the hwstate so that we can detect if it gets
+	 * used.
+	 */
+	hwstate->fpexc &= ~FPEXC_EN;
+	return 0;
+}
+
+/* Sanitise and restore the current VFP state from the provided structures. */
+int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
+			     struct user_vfp_exc __user *ufp_exc)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
+	unsigned long fpexc;
+	int err = 0;
+
+	/*
+	 * If VFP has been used, then disable it to avoid corrupting
+	 * the new thread state.
+	 */
+	if (hwstate->fpexc & FPEXC_EN)
+		vfp_flush_hwstate(thread);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs,
+				sizeof(hwstate->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__get_user_error(hwstate->fpscr, &ufp->fpscr, err);
+
+	/*
+	 * Sanitise and restore the exception registers.
+	 */
+	__get_user_error(fpexc, &ufp_exc->fpexc, err);
+
+	/* Ensure the VFP is enabled. */
+	fpexc |= FPEXC_EN;
+
+	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
+	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
+	hwstate->fpexc = fpexc;
+
+	__get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
+	__get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+
+	return err ? -EFAULT : 0;
+}
+
 /*
  * VFP hardware can lose all context when a CPU goes offline.
  * As we will be running in SMP mode with CPU hotplug, we will save the