Merge branch '3.10/fb-mmap' into for-next

Merge topic branch to get vm_iomap_memory into use.

Conflicts:
	drivers/video/fbmon.c

79 files changed, 457 insertions, 355 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 13b739469c5..1cacda426a0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1183,9 +1183,9 @@ config ARM_NR_BANKS
 	default 8
 
 config IWMMXT
-	bool "Enable iWMMXt support"
+	bool "Enable iWMMXt support" if !CPU_PJ4
 	depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4
-	default y if PXA27x || PXA3xx || ARCH_MMP
+	default y if PXA27x || PXA3xx || ARCH_MMP || CPU_PJ4
 	help
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
@@ -1439,6 +1439,16 @@ config ARM_ERRATA_775420
 	 to deadlock. This workaround puts DSB before executing ISB if
 	 an abort may occur on cache maintenance.
 
+config ARM_ERRATA_798181
+	bool "ARM errata: TLBI/DSB failure on Cortex-A15"
+	depends on CPU_V7 && SMP
+	help
+	  On Cortex-A15 (r0p0..r3p2) the TLBI*IS/DSB operations are not
+	  adequately shooting down all use of the old entries. This
+	  option enables the Linux kernel workaround for this erratum
+	  which sends an IPI to the CPUs that are running the same ASID
+	  as the one being invalidated.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/boot/dts/armada-370-mirabox.dts b/arch/arm/boot/dts/armada-370-mirabox.dts
index dd0c57dd9f3..3234875824d 100644
--- a/arch/arm/boot/dts/armada-370-mirabox.dts
+++ b/arch/arm/boot/dts/armada-370-mirabox.dts
@@ -54,7 +54,7 @@
 		};
 
 		mvsdio@d00d4000 {
-			pinctrl-0 = <&sdio_pins2>;
+			pinctrl-0 = <&sdio_pins3>;
 			pinctrl-names = "default";
 			status = "okay";
 			/*
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 8188d138020..a195debb67d 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -59,6 +59,12 @@
 					     "mpp50", "mpp51", "mpp52";
 			      marvell,function = "sd0";
 			};
+
+			sdio_pins3: sdio-pins3 {
+			      marvell,pins = "mpp48", "mpp49", "mpp50",
+					     "mpp51", "mpp52", "mpp53";
+			      marvell,function = "sd0";
+			};
 	        };
 
 		gpio0: gpio@d0018100 {
diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi
index 9de93096601..aaa63d0a809 100644
--- a/arch/arm/boot/dts/dbx5x0.dtsi
+++ b/arch/arm/boot/dts/dbx5x0.dtsi
@@ -191,8 +191,8 @@
 
 		prcmu: prcmu@80157000 {
 			compatible = "stericsson,db8500-prcmu";
-			reg = <0x80157000 0x1000>;
-			reg-names = "prcmu";
+			reg = <0x80157000 0x1000>, <0x801b0000 0x8000>, <0x801b8000 0x1000>;
+			reg-names = "prcmu", "prcmu-tcpm", "prcmu-tcdm";
 			interrupts = <0 47 0x4>;
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts
index 6ce3d17c3a2..fd36e1cca10 100644
--- a/arch/arm/boot/dts/imx28-m28evk.dts
+++ b/arch/arm/boot/dts/imx28-m28evk.dts
@@ -152,7 +152,6 @@
 			i2c0: i2c@80058000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&i2c0_pins_a>;
-				clock-frequency = <400000>;
 				status = "okay";
 
 				sgtl5000: codec@0a {
diff --git a/arch/arm/boot/dts/imx28-sps1.dts b/arch/arm/boot/dts/imx28-sps1.dts
index e6cde8aa7ff..6c6a5442800 100644
--- a/arch/arm/boot/dts/imx28-sps1.dts
+++ b/arch/arm/boot/dts/imx28-sps1.dts
@@ -70,7 +70,6 @@
 			i2c0: i2c@80058000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&i2c0_pins_a>;
-				clock-frequency = <400000>;
 				status = "okay";
 
 				rtc: rtc@51 {
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 06ec460b458..281a223591f 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -91,6 +91,7 @@
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x00a00600 0x20>;
 			interrupts = <1 13 0xf01>;
+			clocks = <&clks 15>;
 		};
 
 		L2: l2-cache@00a02000 {
diff --git a/arch/arm/boot/dts/kirkwood-goflexnet.dts b/arch/arm/boot/dts/kirkwood-goflexnet.dts
index bd83b8fc7c8..c3573be7b92 100644
--- a/arch/arm/boot/dts/kirkwood-goflexnet.dts
+++ b/arch/arm/boot/dts/kirkwood-goflexnet.dts
@@ -77,6 +77,7 @@
 		};
 
 		nand@3000000 {
+			chip-delay = <40>;
 			status = "okay";
 
 			partition@0 {
diff --git a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
index 93c3afbef9e..3694e94f6e9 100644
--- a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
+++ b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
@@ -96,11 +96,11 @@
 				marvell,function = "gpio";
 			};
 			pmx_led_rebuild_brt_ctrl_1: pmx-led-rebuild-brt-ctrl-1 {
-				marvell,pins = "mpp44";
+				marvell,pins = "mpp46";
 				marvell,function = "gpio";
 			};
 			pmx_led_rebuild_brt_ctrl_2: pmx-led-rebuild-brt-ctrl-2 {
-				marvell,pins = "mpp45";
+				marvell,pins = "mpp47";
 				marvell,function = "gpio";
 			};
 
@@ -157,14 +157,14 @@
 			gpios = <&gpio0 16 0>;
 			linux,default-trigger = "default-on";
 		};
-		health_led1 {
+		rebuild_led {
+			label = "status:white:rebuild_led";
+			gpios = <&gpio1 4 0>;
+		};
+		health_led {
 			label = "status:red:health_led";
 			gpios = <&gpio1 5 0>;
 		};
-		health_led2 {
-			label = "status:white:health_led";
-			gpios = <&gpio1 4 0>;
-		};
 		backup_led {
 			label = "status:blue:backup_led";
 			gpios = <&gpio0 15 0>;
diff --git a/arch/arm/boot/dts/orion5x.dtsi b/arch/arm/boot/dts/orion5x.dtsi
index 8aad00f81ed..f7bec3b1ba3 100644
--- a/arch/arm/boot/dts/orion5x.dtsi
+++ b/arch/arm/boot/dts/orion5x.dtsi
@@ -13,6 +13,9 @@
 	compatible = "marvell,orion5x";
 	interrupt-parent = <&intc>;
 
+	aliases {
+		gpio0 = &gpio0;
+	};
 	intc: interrupt-controller {
 		compatible = "marvell,orion-intc", "marvell,intc";
 		interrupt-controller;
@@ -32,7 +35,9 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			reg = <0x10100 0x40>;
-			ngpio = <32>;
+			ngpios = <32>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <6>, <7>, <8>, <9>;
 		};
 
@@ -91,7 +96,7 @@
 			reg = <0x90000 0x10000>,
 			      <0xf2200000 0x800>;
 			reg-names = "regs", "sram";
-			interrupts = <22>;
+			interrupts = <28>;
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index 720799fd3a8..dff714d886d 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -24,7 +24,7 @@ extern struct arm_delay_ops {
 	void (*delay)(unsigned long);
 	void (*const_udelay)(unsigned long);
 	void (*udelay)(unsigned long);
-	bool const_clock;
+	unsigned long ticks_per_jiffy;
 } arm_delay_ops;
 
 #define __delay(n)		arm_delay_ops.delay(n)
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index cca9f15704e..ea289e1435e 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -19,14 +19,6 @@
 #undef _CACHE
 #undef MULTI_CACHE
 
-#if defined(CONFIG_CPU_CACHE_V3)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v3
-# endif
-#endif
-
 #if defined(CONFIG_CPU_CACHE_V4)
 # ifdef _CACHE
 #  define MULTI_CACHE 1
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
index 02fe2fbe247..ed94b1a366a 100644
--- a/arch/arm/include/asm/hardware/iop3xx.h
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void);
  * IOP3XX processor registers
  */
 #define IOP3XX_PERIPHERAL_PHYS_BASE	0xffffe000
-#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfeffe000
+#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfedfe000
 #define IOP3XX_PERIPHERAL_SIZE		0x00002000
 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\
 					IOP3XX_PERIPHERAL_SIZE - 1)
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 8c5e828f484..91b99abe7a9 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -41,6 +41,13 @@ extern void kunmap_high(struct page *page);
 #endif
 #endif
 
+/*
+ * Needed to be able to broadcast the TLB invalidation for kmap.
+ */
+#ifdef CONFIG_ARM_ERRATA_798181
+#undef ARCH_NEEDS_KMAP_HIGH_GET
+#endif
+
 #ifdef ARCH_NEEDS_KMAP_HIGH_GET
 extern void *kmap_high_get(struct page *page);
 #else
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 863a6611323..a7b85e0d0cc 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -27,6 +27,8 @@ void __check_vmalloc_seq(struct mm_struct *mm);
 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);
+
 #else	/* !CONFIG_CPU_HAS_ASID */
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 6ef8afd1b64..86b8fe398b9 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -111,7 +111,7 @@
 #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */
 #define L_PTE_S2_MT_WRITEBACK	 (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */
 #define L_PTE_S2_RDONLY		 (_AT(pteval_t, 1) << 6)   /* HAP[1]   */
-#define L_PTE_S2_RDWR		 (_AT(pteval_t, 2) << 6)   /* HAP[2:1] */
+#define L_PTE_S2_RDWR		 (_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 
 /*
  * Hyp-mode PL2 PTE definitions for LPAE.
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 4db8c8820f0..ab865e65a84 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -14,7 +14,6 @@
 
 #include <asm/glue.h>
 
-#define TLB_V3_PAGE	(1 << 0)
 #define TLB_V4_U_PAGE	(1 << 1)
 #define TLB_V4_D_PAGE	(1 << 2)
 #define TLB_V4_I_PAGE	(1 << 3)
@@ -22,7 +21,6 @@
 #define TLB_V6_D_PAGE	(1 << 5)
 #define TLB_V6_I_PAGE	(1 << 6)
 
-#define TLB_V3_FULL	(1 << 8)
 #define TLB_V4_U_FULL	(1 << 9)
 #define TLB_V4_D_FULL	(1 << 10)
 #define TLB_V4_I_FULL	(1 << 11)
@@ -52,7 +50,6 @@
  *	=============
  *
  *	We have the following to choose from:
- *	  v3    - ARMv3
  *	  v4    - ARMv4 without write buffer
  *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
  *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
@@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
 	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
 	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
 	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
@@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
 		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-			tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
 			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
 			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
 			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
@@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
 	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-		tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
 		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
 		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
 		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
@@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
 	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
@@ -450,6 +443,21 @@ static inline void local_flush_bp_all(void)
 		isb();
 }
 
+#ifdef CONFIG_ARM_ERRATA_798181
+static inline void dummy_flush_tlb_a15_erratum(void)
+{
+	/*
+	 * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
+	 */
+	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
+	dsb();
+}
+#else
+static inline void dummy_flush_tlb_a15_erratum(void)
+{
+}
+#endif
+
 /*
  *	flush_pmd_entry
  *
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 3248cde504e..fefd7f97143 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -276,7 +276,13 @@ ENDPROC(ftrace_graph_caller_old)
  */
 
 .macro mcount_enter
+/*
+ * This pad compensates for the push {lr} at the call site.  Note that we are
+ * unable to unwind through a function which does not otherwise save its lr.
+ */
+ UNWIND(.pad	#4)
 	stmdb	sp!, {r0-r3, lr}
+ UNWIND(.save	{r0-r3, lr})
 .endm
 
 .macro mcount_get_lr reg
@@ -289,6 +295,7 @@ ENDPROC(ftrace_graph_caller_old)
 .endm
 
 ENTRY(__gnu_mcount_nc)
+UNWIND(.fnstart)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	mov	ip, lr
 	ldmia	sp!, {lr}
@@ -296,17 +303,22 @@ ENTRY(__gnu_mcount_nc)
 #else
 	__mcount
 #endif
+UNWIND(.fnend)
 ENDPROC(__gnu_mcount_nc)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(ftrace_caller)
+UNWIND(.fnstart)
 	__ftrace_caller
+UNWIND(.fnend)
 ENDPROC(ftrace_caller)
 #endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 ENTRY(ftrace_graph_caller)
+UNWIND(.fnstart)
 	__ftrace_graph_caller
+UNWIND(.fnend)
 ENDPROC(ftrace_graph_caller)
 #endif
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index e0eb9a1cae7..8bac553fe21 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -267,7 +267,7 @@ __create_page_tables:
 	addne	r6, r6, #1 << SECTION_SHIFT
 	strne	r6, [r3]
 
-#if defined(CONFIG_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8)
+#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8)
 	sub	r4, r4, #4			@ Fixup page table pointer
 						@ for 64-bit descriptors
 #endif
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 96093b75ab9..1fd749ee4a1 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -966,7 +966,7 @@ static void reset_ctrl_regs(void *unused)
 	}
 
 	if (err) {
-		pr_warning("CPU %d debug is powered down!\n", cpu);
+		pr_warn_once("CPU %d debug is powered down!\n", cpu);
 		cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu));
 		return;
 	}
@@ -987,7 +987,7 @@ clear_vcr:
 	isb();
 
 	if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) {
-		pr_warning("CPU %d failed to disable vector catch\n", cpu);
+		pr_warn_once("CPU %d failed to disable vector catch\n", cpu);
 		return;
 	}
 
@@ -1007,7 +1007,7 @@ clear_vcr:
 	}
 
 	if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) {
-		pr_warning("CPU %d failed to clear debug register pairs\n", cpu);
+		pr_warn_once("CPU %d failed to clear debug register pairs\n", cpu);
 		return;
 	}
 
@@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = {
+static struct notifier_block dbg_cpu_pm_nb = {
 	.notifier_call = dbg_cpu_pm_notify,
 };
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 146157dfe27..8c3094d0f7b 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, event) >= 0;
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index bd6f56b9ec2..59d2adb764a 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void)
 
 static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
 
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 {
 	u64 epoch_ns;
 	u32 epoch_cyc;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 3f6cbb2e3ed..234e339196c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -56,7 +56,6 @@
 #include <asm/virt.h>
 
 #include "atags.h"
-#include "tcm.h"
 
 
 #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE)
@@ -353,6 +352,23 @@ void __init early_print(const char *str, ...)
 	printk("%s", buf);
 }
 
+static void __init cpuid_init_hwcaps(void)
+{
+	unsigned int divide_instrs;
+
+	if (cpu_architecture() < CPU_ARCH_ARMv7)
+		return;
+
+	divide_instrs = (read_cpuid_ext(CPUID_EXT_ISAR0) & 0x0f000000) >> 24;
+
+	switch (divide_instrs) {
+	case 2:
+		elf_hwcap |= HWCAP_IDIVA;
+	case 1:
+		elf_hwcap |= HWCAP_IDIVT;
+	}
+}
+
 static void __init feat_v6_fixup(void)
 {
 	int id = read_cpuid_id();
@@ -483,8 +499,11 @@ static void __init setup_processor(void)
 	snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c",
 		 list->elf_name, ENDIANNESS);
 	elf_hwcap = list->elf_hwcap;
+
+	cpuid_init_hwcaps();
+
 #ifndef CONFIG_ARM_THUMB
-	elf_hwcap &= ~HWCAP_THUMB;
+	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
 #endif
 
 	feat_v6_fixup();
@@ -524,7 +543,7 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 	size -= start & ~PAGE_MASK;
 	bank->start = PAGE_ALIGN(start);
 
-#ifndef CONFIG_LPAE
+#ifndef CONFIG_ARM_LPAE
 	if (bank->start + size < bank->start) {
 		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
 			"32-bit physical address space\n", (long long)start);
@@ -778,8 +797,6 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-	tcm_init();
-
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 79078edbb9b..1f2ccccaf00 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -673,9 +673,6 @@ static int cpufreq_callback(struct notifier_block *nb,
 	if (freq->flags & CPUFREQ_CONST_LOOPS)
 		return NOTIFY_OK;
 
-	if (arm_delay_ops.const_clock)
-		return NOTIFY_OK;
-
 	if (!per_cpu(l_p_j_ref, cpu)) {
 		per_cpu(l_p_j_ref, cpu) =
 			per_cpu(cpu_data, cpu).loops_per_jiffy;
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index bd030053139..e82e1d24877 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -12,6 +12,7 @@
 
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
 
 /**********************************************************************/
 
@@ -69,12 +70,72 @@ static inline void ipi_flush_bp_all(void *ignored)
 	local_flush_bp_all();
 }
 
+#ifdef CONFIG_ARM_ERRATA_798181
+static int erratum_a15_798181(void)
+{
+	unsigned int midr = read_cpuid_id();
+
+	/* Cortex-A15 r0p0..r3p2 affected */
+	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2)
+		return 0;
+	return 1;
+}
+#else
+static int erratum_a15_798181(void)
+{
+	return 0;
+}
+#endif
+
+static void ipi_flush_tlb_a15_erratum(void *arg)
+{
+	dmb();
+}
+
+static void broadcast_tlb_a15_erratum(void)
+{
+	if (!erratum_a15_798181())
+		return;
+
+	dummy_flush_tlb_a15_erratum();
+	smp_call_function_many(cpu_online_mask, ipi_flush_tlb_a15_erratum,
+			       NULL, 1);
+}
+
+static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
+{
+	int cpu;
+	cpumask_t mask = { CPU_BITS_NONE };
+
+	if (!erratum_a15_798181())
+		return;
+
+	dummy_flush_tlb_a15_erratum();
+	for_each_online_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			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);
+	}
+	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
+}
+
 void flush_tlb_all(void)
 {
 	if (tlb_ops_need_broadcast())
 		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
 	else
 		local_flush_tlb_all();
+	broadcast_tlb_a15_erratum();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
@@ -83,6 +144,7 @@ void flush_tlb_mm(struct mm_struct *mm)
 		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
 		local_flush_tlb_mm(mm);
+	broadcast_tlb_mm_a15_erratum(mm);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
@@ -95,6 +157,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 					&ta, 1);
 	} else
 		local_flush_tlb_page(vma, uaddr);
+	broadcast_tlb_mm_a15_erratum(vma->vm_mm);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
@@ -105,6 +168,7 @@ void flush_tlb_kernel_page(unsigned long kaddr)
 		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
 	} else
 		local_flush_tlb_kernel_page(kaddr);
+	broadcast_tlb_a15_erratum();
 }
 
 void flush_tlb_range(struct vm_area_struct *vma,
@@ -119,6 +183,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
 					&ta, 1);
 	} else
 		local_flush_tlb_range(vma, start, end);
+	broadcast_tlb_mm_a15_erratum(vma->vm_mm);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
@@ -130,6 +195,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 		on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
 	} else
 		local_flush_tlb_kernel_range(start, end);
+	broadcast_tlb_a15_erratum();
 }
 
 void flush_bp_all(void)
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 30ae6bb4a31..f50f19e5c13 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -17,7 +17,6 @@
 #include <asm/mach/map.h>
 #include <asm/memory.h>
 #include <asm/system_info.h>
-#include "tcm.h"
 
 static struct gen_pool *tcm_pool;
 static bool dtcm_present;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 5a936988eb2..c1fe498983a 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		break;
 	case KVM_CAP_ARM_SET_DEVICE_ADDR:
 		r = 1;
+		break;
 	case KVM_CAP_NR_VCPUS:
 		r = num_online_cpus();
 		break;
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 4ea9a982269..7bed7556077 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 	u32 val;
 	int cpu;
 
-	cpu = get_cpu();
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
+	cpu = get_cpu();
+
 	cpumask_setall(&vcpu->arch.require_dcache_flush);
 	cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
 
diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c
index c9a17316e9f..0e4cfe123b3 100644
--- a/arch/arm/kvm/vgic.c
+++ b/arch/arm/kvm/vgic.c
@@ -883,8 +883,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 			  lr, irq, vgic_cpu->vgic_lr[lr]);
 		BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
 		vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
-
-		goto out;
+		return true;
 	}
 
 	/* Try to use another LR for this interrupt */
@@ -898,7 +897,6 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 	vgic_cpu->vgic_irq_lr_map[irq] = lr;
 	set_bit(lr, vgic_cpu->lr_used);
 
-out:
 	if (!vgic_irq_is_edge(vcpu, irq))
 		vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
 
@@ -1018,21 +1016,6 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 
 	kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
 
-	/*
-	 * We do not need to take the distributor lock here, since the only
-	 * action we perform is clearing the irq_active_bit for an EOIed
-	 * level interrupt.  There is a potential race with
-	 * the queuing of an interrupt in __kvm_vgic_flush_hwstate(), where we
-	 * check if the interrupt is already active. Two possibilities:
-	 *
-	 * - The queuing is occurring on the same vcpu: cannot happen,
-	 *   as we're already in the context of this vcpu, and
-	 *   executing the handler
-	 * - The interrupt has been migrated to another vcpu, and we
-	 *   ignore this interrupt for this run. Big deal. It is still
-	 *   pending though, and will get considered when this vcpu
-	 *   exits.
-	 */
 	if (vgic_cpu->vgic_misr & GICH_MISR_EOI) {
 		/*
 		 * Some level interrupts have been EOIed. Clear their
@@ -1054,6 +1037,13 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 			} else {
 				vgic_cpu_irq_clear(vcpu, irq);
 			}
+
+			/*
+			 * Despite being EOIed, the LR may not have
+			 * been marked as empty.
+			 */
+			set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
+			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT;
 		}
 	}
 
@@ -1064,9 +1054,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Sync back the VGIC state after a guest run. We do not really touch
- * the distributor here (the irq_pending_on_cpu bit is safe to set),
- * so there is no need for taking its lock.
+ * Sync back the VGIC state after a guest run. The distributor lock is
+ * needed so we don't get preempted in the middle of the state processing.
  */
 static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
@@ -1112,10 +1101,14 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return;
 
+	spin_lock(&dist->lock);
 	__kvm_vgic_sync_hwstate(vcpu);
+	spin_unlock(&dist->lock);
 }
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index 6b93f6a1a3c..64dbfa57204 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -58,7 +58,7 @@ static void __timer_delay(unsigned long cycles)
 static void __timer_const_udelay(unsigned long xloops)
 {
 	unsigned long long loops = xloops;
-	loops *= loops_per_jiffy;
+	loops *= arm_delay_ops.ticks_per_jiffy;
 	__timer_delay(loops >> UDELAY_SHIFT);
 }
 
@@ -73,11 +73,13 @@ void __init register_current_timer_delay(const struct delay_timer *timer)
 		pr_info("Switching to timer-based delay loop\n");
 		delay_timer			= timer;
 		lpj_fine			= timer->freq / HZ;
-		loops_per_jiffy			= lpj_fine;
+
+		/* cpufreq may scale loops_per_jiffy, so keep a private copy */
+		arm_delay_ops.ticks_per_jiffy	= lpj_fine;
 		arm_delay_ops.delay		= __timer_delay;
 		arm_delay_ops.const_udelay	= __timer_const_udelay;
 		arm_delay_ops.udelay		= __timer_udelay;
-		arm_delay_ops.const_clock	= true;
+
 		delay_calibrated		= true;
 	} else {
 		pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index e698f26cc0c..52e4bb5cf12 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -22,19 +22,9 @@
 
 static struct map_desc cns3xxx_io_desc[] __initdata = {
 	{
-		.virtual	= CNS3XXX_TC11MP_TWD_BASE_VIRT,
-		.pfn		= __phys_to_pfn(CNS3XXX_TC11MP_TWD_BASE),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT,
-		.pfn		= __phys_to_pfn(CNS3XXX_TC11MP_GIC_CPU_BASE),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT,
-		.pfn		= __phys_to_pfn(CNS3XXX_TC11MP_GIC_DIST_BASE),
-		.length		= SZ_4K,
+		.virtual	= CNS3XXX_TC11MP_SCU_BASE_VIRT,
+		.pfn		= __phys_to_pfn(CNS3XXX_TC11MP_SCU_BASE),
+		.length		= SZ_8K,
 		.type		= MT_DEVICE,
 	}, {
 		.virtual	= CNS3XXX_TIMER1_2_3_BASE_VIRT,
diff --git a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h
index 191c8e57f28..b1021aafa48 100644
--- a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h
+++ b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h
@@ -94,10 +94,10 @@
 #define RTC_INTR_STS_OFFSET			0x34
 
 #define CNS3XXX_MISC_BASE			0x76000000	/* Misc Control */
-#define CNS3XXX_MISC_BASE_VIRT			0xFFF07000	/* Misc Control */
+#define CNS3XXX_MISC_BASE_VIRT			0xFB000000	/* Misc Control */
 
 #define CNS3XXX_PM_BASE				0x77000000	/* Power Management Control */
-#define CNS3XXX_PM_BASE_VIRT			0xFFF08000
+#define CNS3XXX_PM_BASE_VIRT			0xFB001000
 
 #define PM_CLK_GATE_OFFSET			0x00
 #define PM_SOFT_RST_OFFSET			0x04
@@ -109,7 +109,7 @@
 #define PM_PLL_HM_PD_OFFSET			0x1C
 
 #define CNS3XXX_UART0_BASE			0x78000000	/* UART 0 */
-#define CNS3XXX_UART0_BASE_VIRT			0xFFF09000
+#define CNS3XXX_UART0_BASE_VIRT			0xFB002000
 
 #define CNS3XXX_UART1_BASE			0x78400000	/* UART 1 */
 #define CNS3XXX_UART1_BASE_VIRT			0xFFF0A000
@@ -130,7 +130,7 @@
 #define CNS3XXX_I2S_BASE_VIRT			0xFFF10000
 
 #define CNS3XXX_TIMER1_2_3_BASE			0x7C800000	/* Timer */
-#define CNS3XXX_TIMER1_2_3_BASE_VIRT		0xFFF10800
+#define CNS3XXX_TIMER1_2_3_BASE_VIRT		0xFB003000
 
 #define TIMER1_COUNTER_OFFSET			0x00
 #define TIMER1_AUTO_RELOAD_OFFSET		0x04
@@ -227,16 +227,16 @@
  * Testchip peripheral and fpga gic regions
  */
 #define CNS3XXX_TC11MP_SCU_BASE			0x90000000	/* IRQ, Test chip */
-#define CNS3XXX_TC11MP_SCU_BASE_VIRT		0xFF000000
+#define CNS3XXX_TC11MP_SCU_BASE_VIRT		0xFB004000
 
 #define CNS3XXX_TC11MP_GIC_CPU_BASE		0x90000100	/* Test chip interrupt controller CPU interface */
-#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT	0xFF000100
+#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT	(CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x100)
 
 #define CNS3XXX_TC11MP_TWD_BASE			0x90000600
-#define CNS3XXX_TC11MP_TWD_BASE_VIRT		0xFF000600
+#define CNS3XXX_TC11MP_TWD_BASE_VIRT		(CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x600)
 
 #define CNS3XXX_TC11MP_GIC_DIST_BASE		0x90001000	/* Test chip interrupt controller distributor */
-#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT	0xFF001000
+#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT	(CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x1000)
 
 #define CNS3XXX_TC11MP_L220_BASE		0x92002000	/* L220 registers */
 #define CNS3XXX_TC11MP_L220_BASE_VIRT		0xFF002000
diff --git a/arch/arm/mach-ep93xx/include/mach/uncompress.h b/arch/arm/mach-ep93xx/include/mach/uncompress.h
index d2afb4dd82a..b5cc77d2380 100644
--- a/arch/arm/mach-ep93xx/include/mach/uncompress.h
+++ b/arch/arm/mach-ep93xx/include/mach/uncompress.h
@@ -47,9 +47,13 @@ static void __raw_writel(unsigned int value, unsigned int ptr)
 
 static inline void putc(int c)
 {
-	/* Transmit fifo not full?  */
-	while (__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF)
-		;
+	int i;
+
+	for (i = 0; i < 10000; i++) {
+		/* Transmit fifo not full? */
+		if (!(__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF))
+			break;
+	}
 
 	__raw_writeb(c, PHYS_UART_DATA);
 }
diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c
index f30c5284339..890cae23c12 100644
--- a/arch/arm/mach-highbank/hotplug.c
+++ b/arch/arm/mach-highbank/hotplug.c
@@ -28,13 +28,11 @@ extern void secondary_startup(void);
  */
 void __ref highbank_cpu_die(unsigned int cpu)
 {
-	flush_cache_all();
-
 	highbank_set_cpu_jump(cpu, phys_to_virt(0));
-	highbank_set_core_pwr();
 
-	cpu_do_idle();
+	flush_cache_louis();
+	highbank_set_core_pwr();
 
-	/* We should never return from idle */
-	panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu);
+	while (1)
+		cpu_do_idle();
 }
diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c
index e13a8fa5e62..2193c834f55 100644
--- a/arch/arm/mach-imx/clk-imx35.c
+++ b/arch/arm/mach-imx/clk-imx35.c
@@ -257,6 +257,7 @@ int __init mx35_clocks_init(void)
 	clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0");
 	clk_register_clkdev(clk[nfc_div], NULL, "imx25-nand.0");
 	clk_register_clkdev(clk[csi_gate], NULL, "mx3-camera.0");
+	clk_register_clkdev(clk[admux_gate], "audmux", NULL);
 
 	clk_prepare_enable(clk[spba_gate]);
 	clk_prepare_enable(clk[gpio1_gate]);
@@ -265,6 +266,7 @@ int __init mx35_clocks_init(void)
 	clk_prepare_enable(clk[iim_gate]);
 	clk_prepare_enable(clk[emi_gate]);
 	clk_prepare_enable(clk[max_gate]);
+	clk_prepare_enable(clk[iomuxc_gate]);
 
 	/*
 	 * SCC is needed to boot via mmc after a watchdog reset. The clock code
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 2f9ff93a4e6..d38e54f5b6d 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -115,7 +115,7 @@ static const char *gpu2d_core_sels[]	= { "axi", "pll3_usb_otg", "pll2_pfd0_352m"
 static const char *gpu3d_core_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", };
 static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", };
 static const char *ipu_sels[]		= { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", };
-static const char *ldb_di_sels[]	= { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_pfd1_540m", };
+static const char *ldb_di_sels[]	= { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", };
 static const char *ipu_di_pre_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", };
 static const char *ipu1_di0_sels[]	= { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
 static const char *ipu1_di1_sels[]	= { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
@@ -443,7 +443,6 @@ int __init mx6q_clocks_init(void)
 
 	clk_register_clkdev(clk[gpt_ipg], "ipg", "imx-gpt.0");
 	clk_register_clkdev(clk[gpt_ipg_per], "per", "imx-gpt.0");
-	clk_register_clkdev(clk[twd], NULL, "smp_twd");
 	clk_register_clkdev(clk[cko1_sel], "cko1_sel", NULL);
 	clk_register_clkdev(clk[ahb], "ahb", NULL);
 	clk_register_clkdev(clk[cko1], "cko1", NULL);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 5a800bfcec5..5bf4a97ab24 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -110,6 +110,8 @@ void tzic_handle_irq(struct pt_regs *);
 
 extern void imx_enable_cpu(int cpu, bool enable);
 extern void imx_set_cpu_jump(int cpu, void *jump_addr);
+extern u32 imx_get_cpu_arg(int cpu);
+extern void imx_set_cpu_arg(int cpu, u32 arg);
 extern void v7_cpu_resume(void);
 extern u32 *pl310_get_save_ptr(void);
 #ifdef CONFIG_SMP
diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c
index 7bc5fe15dda..361a253e2b6 100644
--- a/arch/arm/mach-imx/hotplug.c
+++ b/arch/arm/mach-imx/hotplug.c
@@ -46,11 +46,23 @@ static inline void cpu_enter_lowpower(void)
 void imx_cpu_die(unsigned int cpu)
 {
 	cpu_enter_lowpower();
+	/*
+	 * We use the cpu jumping argument register to sync with
+	 * imx_cpu_kill() which is running on cpu0 and waiting for
+	 * the register being cleared to kill the cpu.
+	 */
+	imx_set_cpu_arg(cpu, ~0);
 	cpu_do_idle();
 }
 
 int imx_cpu_kill(unsigned int cpu)
 {
+	unsigned long timeout = jiffies + msecs_to_jiffies(50);
+
+	while (imx_get_cpu_arg(cpu) == 0)
+		if (time_after(jiffies, timeout))
+			return 0;
 	imx_enable_cpu(cpu, false);
+	imx_set_cpu_arg(cpu, 0);
 	return 1;
 }
diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c
index e15f1555c59..09a742f8c7a 100644
--- a/arch/arm/mach-imx/src.c
+++ b/arch/arm/mach-imx/src.c
@@ -43,6 +43,18 @@ void imx_set_cpu_jump(int cpu, void *jump_addr)
 		       src_base + SRC_GPR1 + cpu * 8);
 }
 
+u32 imx_get_cpu_arg(int cpu)
+{
+	cpu = cpu_logical_map(cpu);
+	return readl_relaxed(src_base + SRC_GPR1 + cpu * 8 + 4);
+}
+
+void imx_set_cpu_arg(int cpu, u32 arg)
+{
+	cpu = cpu_logical_map(cpu);
+	writel_relaxed(arg, src_base + SRC_GPR1 + cpu * 8 + 4);
+}
+
 void imx_src_prepare_restart(void)
 {
 	u32 val;
diff --git a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
index f655b2637b0..e5f70415905 100644
--- a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
+++ b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
@@ -20,10 +20,15 @@ static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = {
 	.duplex         = DUPLEX_FULL,
 };
 
+static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = {
+        .phy_addr       = MV643XX_ETH_PHY_ADDR(11),
+};
+
 void __init iomega_ix2_200_init(void)
 {
 	/*
 	 * Basic setup. Needs to be called early.
 	 */
-	kirkwood_ge01_init(&iomega_ix2_200_ge00_data);
+	kirkwood_ge00_init(&iomega_ix2_200_ge00_data);
+	kirkwood_ge01_init(&iomega_ix2_200_ge01_data);
 }
diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c
index 1c6e736cbbf..08dd739aa70 100644
--- a/arch/arm/mach-kirkwood/guruplug-setup.c
+++ b/arch/arm/mach-kirkwood/guruplug-setup.c
@@ -53,6 +53,8 @@ static struct mv_sata_platform_data guruplug_sata_data = {
 
 static struct mvsdio_platform_data guruplug_mvsdio_data = {
 	/* unfortunately the CD signal has not been connected */
+	.gpio_card_detect = -1,
+	.gpio_write_protect = -1,
 };
 
 static struct gpio_led guruplug_led_pins[] = {
diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c
index 8ddd69fdc93..6a6eb548307 100644
--- a/arch/arm/mach-kirkwood/openrd-setup.c
+++ b/arch/arm/mach-kirkwood/openrd-setup.c
@@ -55,6 +55,7 @@ static struct mv_sata_platform_data openrd_sata_data = {
 
 static struct mvsdio_platform_data openrd_mvsdio_data = {
 	.gpio_card_detect = 29,	/* MPP29 used as SD card detect */
+	.gpio_write_protect = -1,
 };
 
 static unsigned int openrd_mpp_config[] __initdata = {
diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c
index c7d93b48926..d24223166e0 100644
--- a/arch/arm/mach-kirkwood/rd88f6281-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c
@@ -69,6 +69,7 @@ static struct mv_sata_platform_data rd88f6281_sata_data = {
 
 static struct mvsdio_platform_data rd88f6281_mvsdio_data = {
 	.gpio_card_detect = 28,
+	.gpio_write_protect = -1,
 };
 
 static unsigned int rd88f6281_mpp_config[] __initdata = {
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 2969027f02f..f9fd77e8f1f 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -62,7 +62,10 @@ static int msm_timer_set_next_event(unsigned long cycles,
 {
 	u32 ctrl = readl_relaxed(event_base + TIMER_ENABLE);
 
-	writel_relaxed(0, event_base + TIMER_CLEAR);
+	ctrl &= ~TIMER_ENABLE_EN;
+	writel_relaxed(ctrl, event_base + TIMER_ENABLE);
+
+	writel_relaxed(ctrl, event_base + TIMER_CLEAR);
 	writel_relaxed(cycles, event_base + TIMER_MATCH_VAL);
 	writel_relaxed(ctrl | TIMER_ENABLE_EN, event_base + TIMER_ENABLE);
 	return 0;
diff --git a/arch/arm/mach-mvebu/irq-armada-370-xp.c b/arch/arm/mach-mvebu/irq-armada-370-xp.c
index 274ff58271d..d5970f5a1e8 100644
--- a/arch/arm/mach-mvebu/irq-armada-370-xp.c
+++ b/arch/arm/mach-mvebu/irq-armada-370-xp.c
@@ -44,6 +44,8 @@
 
 #define ARMADA_370_XP_MAX_PER_CPU_IRQS		(28)
 
+#define ARMADA_370_XP_TIMER0_PER_CPU_IRQ	(5)
+
 #define ACTIVE_DOORBELLS			(8)
 
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
@@ -59,36 +61,26 @@ static struct irq_domain *armada_370_xp_mpic_domain;
  */
 static void armada_370_xp_irq_mask(struct irq_data *d)
 {
-#ifdef CONFIG_SMP
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
-	if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS)
+	if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
 		writel(hwirq, main_int_base +
 				ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS);
 	else
 		writel(hwirq, per_cpu_int_base +
 				ARMADA_370_XP_INT_SET_MASK_OFFS);
-#else
-	writel(irqd_to_hwirq(d),
-	       per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
-#endif
 }
 
 static void armada_370_xp_irq_unmask(struct irq_data *d)
 {
-#ifdef CONFIG_SMP
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
-	if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS)
+	if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
 		writel(hwirq, main_int_base +
 				ARMADA_370_XP_INT_SET_ENABLE_OFFS);
 	else
 		writel(hwirq, per_cpu_int_base +
 				ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-#else
-	writel(irqd_to_hwirq(d),
-	       per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-#endif
 }
 
 #ifdef CONFIG_SMP
@@ -144,10 +136,14 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
 				      unsigned int virq, irq_hw_number_t hw)
 {
 	armada_370_xp_irq_mask(irq_get_irq_data(virq));
-	writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
+	if (hw != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
+		writel(hw, per_cpu_int_base +
+			ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+	else
+		writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
 	irq_set_status_flags(virq, IRQ_LEVEL);
 
-	if (hw < ARMADA_370_XP_MAX_PER_CPU_IRQS) {
+	if (hw == ARMADA_370_XP_TIMER0_PER_CPU_IRQ) {
 		irq_set_percpu_devid(virq);
 		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
 					handle_percpu_devid_irq);
diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c
index cb7c6ae2e3f..6c4f766365a 100644
--- a/arch/arm/mach-omap1/clock_data.c
+++ b/arch/arm/mach-omap1/clock_data.c
@@ -543,15 +543,6 @@ static struct clk usb_dc_ck = {
 	/* Direct from ULPD, no parent */
 	.rate		= 48000000,
 	.enable_reg	= OMAP1_IO_ADDRESS(SOFT_REQ_REG),
-	.enable_bit	= USB_REQ_EN_SHIFT,
-};
-
-static struct clk usb_dc_ck7xx = {
-	.name		= "usb_dc_ck",
-	.ops		= &clkops_generic,
-	/* Direct from ULPD, no parent */
-	.rate		= 48000000,
-	.enable_reg	= OMAP1_IO_ADDRESS(SOFT_REQ_REG),
 	.enable_bit	= SOFT_USB_OTG_DPLL_REQ_SHIFT,
 };
 
@@ -727,8 +718,7 @@ static struct omap_clk omap_clks[] = {
 	CLK(NULL,	"usb_clko",	&usb_clko,	CK_16XX | CK_1510 | CK_310),
 	CLK(NULL,	"usb_hhc_ck",	&usb_hhc_ck1510, CK_1510 | CK_310),
 	CLK(NULL,	"usb_hhc_ck",	&usb_hhc_ck16xx, CK_16XX),
-	CLK(NULL,	"usb_dc_ck",	&usb_dc_ck,	CK_16XX),
-	CLK(NULL,	"usb_dc_ck",	&usb_dc_ck7xx,	CK_7XX),
+	CLK(NULL,	"usb_dc_ck",	&usb_dc_ck,	CK_16XX | CK_7XX),
 	CLK(NULL,	"mclk",		&mclk_1510,	CK_1510 | CK_310),
 	CLK(NULL,	"mclk",		&mclk_16xx,	CK_16XX),
 	CLK(NULL,	"bclk",		&bclk_1510,	CK_1510 | CK_310),
diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c
index 3d58f335f17..0c6834ae1fc 100644
--- a/arch/arm/mach-omap2/cclock44xx_data.c
+++ b/arch/arm/mach-omap2/cclock44xx_data.c
@@ -52,6 +52,13 @@
  */
 #define OMAP4_DPLL_ABE_DEFFREQ				98304000
 
+/*
+ * OMAP4 USB DPLL default frequency. In OMAP4430 TRM version V, section
+ * "3.6.3.9.5 DPLL_USB Preferred Settings" shows that the preferred
+ * locked frequency for the USB DPLL is 960MHz.
+ */
+#define OMAP4_DPLL_USB_DEFFREQ				960000000
+
 /* Root clocks */
 
 DEFINE_CLK_FIXED_RATE(extalt_clkin_ck, CLK_IS_ROOT, 59000000, 0x0);
@@ -1011,6 +1018,10 @@ DEFINE_CLK_OMAP_MUX(hsmmc2_fclk, "l3_init_clkdm", hsmmc1_fclk_sel,
 		    OMAP4430_CM_L3INIT_MMC2_CLKCTRL, OMAP4430_CLKSEL_MASK,
 		    hsmmc1_fclk_parents, func_dmic_abe_gfclk_ops);
 
+DEFINE_CLK_GATE(ocp2scp_usb_phy_phy_48m, "func_48m_fclk", &func_48m_fclk, 0x0,
+		OMAP4430_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL,
+		OMAP4430_OPTFCLKEN_PHY_48M_SHIFT, 0x0, NULL);
+
 DEFINE_CLK_GATE(sha2md5_fck, "l3_div_ck", &l3_div_ck, 0x0,
 		OMAP4430_CM_L4SEC_SHA2MD51_CLKCTRL,
 		OMAP4430_MODULEMODE_SWCTRL_SHIFT, 0x0, NULL);
@@ -1538,6 +1549,7 @@ static struct omap_clk omap44xx_clks[] = {
 	CLK(NULL,	"per_mcbsp4_gfclk",			&per_mcbsp4_gfclk,	CK_443X),
 	CLK(NULL,	"hsmmc1_fclk",			&hsmmc1_fclk,	CK_443X),
 	CLK(NULL,	"hsmmc2_fclk",			&hsmmc2_fclk,	CK_443X),
+	CLK(NULL,	"ocp2scp_usb_phy_phy_48m",	&ocp2scp_usb_phy_phy_48m,	CK_443X),
 	CLK(NULL,	"sha2md5_fck",			&sha2md5_fck,	CK_443X),
 	CLK(NULL,	"slimbus1_fclk_1",		&slimbus1_fclk_1,	CK_443X),
 	CLK(NULL,	"slimbus1_fclk_0",		&slimbus1_fclk_0,	CK_443X),
@@ -1705,5 +1717,13 @@ int __init omap4xxx_clk_init(void)
 	if (rc)
 		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
+	/*
+	 * Lock USB DPLL on OMAP4 devices so that the L3INIT power
+	 * domain can transition to retention state when not in use.
+	 */
+	rc = clk_set_rate(&dpll_usb_ck, OMAP4_DPLL_USB_DEFFREQ);
+	if (rc)
+		pr_err("%s: failed to configure USB DPLL!\n", __func__);
+
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index 40f4a03d728..d6ba13e1c54 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -293,5 +293,8 @@ extern void omap_reserve(void);
 struct omap_hwmod;
 extern int omap_dss_reset(struct omap_hwmod *);
 
+/* SoC specific clock initializer */
+extern int (*omap_clk_init)(void);
+
 #endif /* __ASSEMBLER__ */
 #endif /* __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H */
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 2c3fdd65387..5c445ca1e27 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -55,6 +55,12 @@
 #include "prm44xx.h"
 
 /*
+ * omap_clk_init: points to a function that does the SoC-specific
+ * clock initializations
+ */
+int (*omap_clk_init)(void);
+
+/*
  * The machine specific code may provide the extra mapping besides the
  * default mapping provided here.
  */
@@ -397,7 +403,7 @@ void __init omap2420_init_early(void)
 	omap242x_clockdomains_init();
 	omap2420_hwmod_init();
 	omap_hwmod_init_postsetup();
-	omap2420_clk_init();
+	omap_clk_init = omap2420_clk_init;
 }
 
 void __init omap2420_init_late(void)
@@ -427,7 +433,7 @@ void __init omap2430_init_early(void)
 	omap243x_clockdomains_init();
 	omap2430_hwmod_init();
 	omap_hwmod_init_postsetup();
-	omap2430_clk_init();
+	omap_clk_init = omap2430_clk_init;
 }
 
 void __init omap2430_init_late(void)
@@ -462,7 +468,7 @@ void __init omap3_init_early(void)
 	omap3xxx_clockdomains_init();
 	omap3xxx_hwmod_init();
 	omap_hwmod_init_postsetup();
-	omap3xxx_clk_init();
+	omap_clk_init = omap3xxx_clk_init;
 }
 
 void __init omap3430_init_early(void)
@@ -500,7 +506,7 @@ void __init ti81xx_init_early(void)
 	omap3xxx_clockdomains_init();
 	omap3xxx_hwmod_init();
 	omap_hwmod_init_postsetup();
-	omap3xxx_clk_init();
+	omap_clk_init = omap3xxx_clk_init;
 }
 
 void __init omap3_init_late(void)
@@ -568,7 +574,7 @@ void __init am33xx_init_early(void)
 	am33xx_clockdomains_init();
 	am33xx_hwmod_init();
 	omap_hwmod_init_postsetup();
-	am33xx_clk_init();
+	omap_clk_init = am33xx_clk_init;
 }
 #endif
 
@@ -593,7 +599,7 @@ void __init omap4430_init_early(void)
 	omap44xx_clockdomains_init();
 	omap44xx_hwmod_init();
 	omap_hwmod_init_postsetup();
-	omap4xxx_clk_init();
+	omap_clk_init = omap4xxx_clk_init;
 }
 
 void __init omap4430_init_late(void)
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index c2c798c08c2..a202a478510 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1368,7 +1368,9 @@ static void _enable_sysc(struct omap_hwmod *oh)
 	}
 
 	if (sf & SYSC_HAS_MIDLEMODE) {
-		if (oh->flags & HWMOD_SWSUP_MSTANDBY) {
+		if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+			idlemode = HWMOD_IDLEMODE_FORCE;
+		} else if (oh->flags & HWMOD_SWSUP_MSTANDBY) {
 			idlemode = HWMOD_IDLEMODE_NO;
 		} else {
 			if (sf & SYSC_HAS_ENAWAKEUP)
@@ -1440,7 +1442,8 @@ static void _idle_sysc(struct omap_hwmod *oh)
 	}
 
 	if (sf & SYSC_HAS_MIDLEMODE) {
-		if (oh->flags & HWMOD_SWSUP_MSTANDBY) {
+		if ((oh->flags & HWMOD_SWSUP_MSTANDBY) ||
+		    (oh->flags & HWMOD_FORCE_MSTANDBY)) {
 			idlemode = HWMOD_IDLEMODE_FORCE;
 		} else {
 			if (sf & SYSC_HAS_ENAWAKEUP)
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index d43d9b608ed..d5dc935f606 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -427,8 +427,8 @@ struct omap_hwmod_omap4_prcm {
  *
  * HWMOD_SWSUP_SIDLE: omap_hwmod code should manually bring module in and out
  *     of idle, rather than relying on module smart-idle
- * HWMOD_SWSUP_MSTDBY: omap_hwmod code should manually bring module in and out
- *     of standby, rather than relying on module smart-standby
+ * HWMOD_SWSUP_MSTANDBY: omap_hwmod code should manually bring module in and
+ *     out of standby, rather than relying on module smart-standby
  * HWMOD_INIT_NO_RESET: don't reset this module at boot - important for
  *     SDRAM controller, etc. XXX probably belongs outside the main hwmod file
  *     XXX Should be HWMOD_SETUP_NO_RESET
@@ -459,6 +459,10 @@ struct omap_hwmod_omap4_prcm {
  *     correctly, or this is being abused to deal with some PM latency
  *     issues -- but we're currently suffering from a shortage of
  *     folks who are able to track these issues down properly.
+ * HWMOD_FORCE_MSTANDBY: Always keep MIDLEMODE bits cleared so that device
+ *     is kept in force-standby mode. Failing to do so causes PM problems
+ *     with musb on OMAP3630 at least. Note that musb has a dedicated register
+ *     to control MSTANDBY signal when MIDLEMODE is set to force-standby.
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -471,6 +475,7 @@ struct omap_hwmod_omap4_prcm {
 #define HWMOD_16BIT_REG				(1 << 8)
 #define HWMOD_EXT_OPT_MAIN_CLK			(1 << 9)
 #define HWMOD_BLOCK_WFI				(1 << 10)
+#define HWMOD_FORCE_MSTANDBY			(1 << 11)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index ac7e03ec952..5112d04e7b7 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1707,9 +1707,14 @@ static struct omap_hwmod omap3xxx_usbhsotg_hwmod = {
 	 * Erratum ID: i479  idle_req / idle_ack mechanism potentially
 	 * broken when autoidle is enabled
 	 * workaround is to disable the autoidle bit at module level.
+	 *
+	 * Enabling the device in any other MIDLEMODE setting but force-idle
+	 * causes core_pwrdm not enter idle states at least on OMAP3630.
+	 * Note that musb has OTG_FORCESTDBY register that controls MSTANDBY
+	 * signal when MIDLEMODE is set to force-idle.
 	 */
 	.flags		= HWMOD_NO_OCP_AUTOIDLE | HWMOD_SWSUP_SIDLE
-				| HWMOD_SWSUP_MSTANDBY,
+				| HWMOD_FORCE_MSTANDBY,
 };
 
 /* usb_otg_hs */
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 0e47d2e1687..9e0576569e0 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2714,6 +2714,10 @@ static struct omap_ocp2scp_dev ocp2scp_dev_attr[] = {
 	{ }
 };
 
+static struct omap_hwmod_opt_clk ocp2scp_usb_phy_opt_clks[] = {
+	{ .role = "48mhz", .clk = "ocp2scp_usb_phy_phy_48m" },
+};
+
 /* ocp2scp_usb_phy */
 static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = {
 	.name		= "ocp2scp_usb_phy",
@@ -2728,6 +2732,8 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = {
 		},
 	},
 	.dev_attr	= ocp2scp_dev_attr,
+	.opt_clks	= ocp2scp_usb_phy_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(ocp2scp_usb_phy_opt_clks),
 };
 
 /*
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 2bdd4cf17a8..f62b509ed08 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -547,6 +547,8 @@ static inline void __init realtime_counter_init(void)
 			       clksrc_nr, clksrc_src)			\
 void __init omap##name##_gptimer_timer_init(void)			\
 {									\
+	if (omap_clk_init)						\
+		omap_clk_init();					\
 	omap_dmtimer_init();						\
 	omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop);	\
 	omap2_gptimer_clocksource_init((clksrc_nr), clksrc_src);	\
@@ -556,6 +558,8 @@ void __init omap##name##_gptimer_timer_init(void)			\
 				clksrc_nr, clksrc_src)			\
 void __init omap##name##_sync32k_timer_init(void)		\
 {									\
+	if (omap_clk_init)						\
+		omap_clk_init();					\
 	omap_dmtimer_init();						\
 	omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop);	\
 	/* Enable the use of clocksource="gp_timer" kernel parameter */	\
diff --git a/arch/arm/mach-s3c24xx/include/mach/irqs.h b/arch/arm/mach-s3c24xx/include/mach/irqs.h
index b7a9f4d469e..1e73f5fa865 100644
--- a/arch/arm/mach-s3c24xx/include/mach/irqs.h
+++ b/arch/arm/mach-s3c24xx/include/mach/irqs.h
@@ -188,10 +188,8 @@
 
 #if defined(CONFIG_CPU_S3C2416)
 #define NR_IRQS (IRQ_S3C2416_I2S1 + 1)
-#elif defined(CONFIG_CPU_S3C2443)
-#define NR_IRQS (IRQ_S3C2443_AC97+1)
 #else
-#define NR_IRQS (IRQ_S3C2440_AC97+1)
+#define NR_IRQS (IRQ_S3C2443_AC97 + 1)
 #endif
 
 /* compatibility define. */
diff --git a/arch/arm/mach-s3c24xx/irq.c b/arch/arm/mach-s3c24xx/irq.c
index cb9f5e011e7..d8ba9bee4c7 100644
--- a/arch/arm/mach-s3c24xx/irq.c
+++ b/arch/arm/mach-s3c24xx/irq.c
@@ -500,7 +500,7 @@ struct s3c_irq_intc *s3c24xx_init_intc(struct device_node *np,
 		base = (void *)0xfd000000;
 
 		intc->reg_mask = base + 0xa4;
-		intc->reg_pending = base + 0x08;
+		intc->reg_pending = base + 0xa8;
 		irq_num = 20;
 		irq_start = S3C2410_IRQ(32);
 		irq_offset = 4;
diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c
index 051b62c2710..7f2cb6c5e2c 100644
--- a/arch/arm/mach-ux500/board-mop500-sdi.c
+++ b/arch/arm/mach-ux500/board-mop500-sdi.c
@@ -81,7 +81,6 @@ static struct stedma40_chan_cfg mop500_sdi0_dma_cfg_tx = {
 #endif
 
 struct mmci_platform_data mop500_sdi0_data = {
-	.ios_handler	= mop500_sdi0_ios_handler,
 	.ocr_mask	= MMC_VDD_29_30,
 	.f_max		= 50000000,
 	.capabilities	= MMC_CAP_4_BIT_DATA |
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index b03457881c4..87d2d7b38ce 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/i2c.h>
 #include <linux/platform_data/i2c-nomadik.h>
@@ -439,6 +440,15 @@ static void mop500_prox_deactivate(struct device *dev)
 	regulator_put(prox_regulator);
 }
 
+void mop500_snowball_ethernet_clock_enable(void)
+{
+	struct clk *clk;
+
+	clk = clk_get_sys("fsmc", NULL);
+	if (!IS_ERR(clk))
+		clk_prepare_enable(clk);
+}
+
 static struct cryp_platform_data u8500_cryp1_platform_data = {
 		.mem_to_engine = {
 				.dir = STEDMA40_MEM_TO_PERIPH,
@@ -683,6 +693,8 @@ static void __init snowball_init_machine(void)
 	mop500_audio_init(parent);
 	mop500_uart_init(parent);
 
+	mop500_snowball_ethernet_clock_enable();
+
 	/* This board has full regulator constraints */
 	regulator_has_full_constraints();
 }
diff --git a/arch/arm/mach-ux500/board-mop500.h b/arch/arm/mach-ux500/board-mop500.h
index eaa605f5d90..d38951be70d 100644
--- a/arch/arm/mach-ux500/board-mop500.h
+++ b/arch/arm/mach-ux500/board-mop500.h
@@ -104,6 +104,7 @@ void __init mop500_pinmaps_init(void);
 void __init snowball_pinmaps_init(void);
 void __init hrefv60_pinmaps_init(void);
 void mop500_audio_init(struct device *parent);
+void mop500_snowball_ethernet_clock_enable(void);
 
 int __init mop500_uib_init(void);
 void mop500_uib_i2c_add(int busnum, struct i2c_board_info *info,
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 19235cf7bbe..f1a58184437 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -312,9 +312,10 @@ static void __init u8500_init_machine(void)
 	/* Pinmaps must be in place before devices register */
 	if (of_machine_is_compatible("st-ericsson,mop500"))
 		mop500_pinmaps_init();
-	else if (of_machine_is_compatible("calaosystems,snowball-a9500"))
+	else if (of_machine_is_compatible("calaosystems,snowball-a9500")) {
 		snowball_pinmaps_init();
-	else if (of_machine_is_compatible("st-ericsson,hrefv60+"))
+		mop500_snowball_ethernet_clock_enable();
+	} else if (of_machine_is_compatible("st-ericsson,hrefv60+"))
 		hrefv60_pinmaps_init();
 	else if (of_machine_is_compatible("st-ericsson,ccu9540")) {}
 		/* TODO: Add pinmaps for ccu9540 board. */
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 025d1732873..4045c4931a3 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -43,7 +43,7 @@ config CPU_ARM740T
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_CACHE_V3	# although the core is v4t
+	select CPU_CACHE_V4
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
 	help
@@ -469,9 +469,6 @@ config CPU_PABRT_V7
 	bool
 
 # The cache model
-config CPU_CACHE_V3
-	bool
-
 config CPU_CACHE_V4
 	bool
 
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 4e333fa2756..9e51be96f63 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)	+= pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)	+= pabort-v7.o
 
-obj-$(CONFIG_CPU_CACHE_V3)	+= cache-v3.o
 obj-$(CONFIG_CPU_CACHE_V4)	+= cache-v4.o
 obj-$(CONFIG_CPU_CACHE_V4WT)	+= cache-v4wt.o
 obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index dd3d59122cc..48bc3c0a87c 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c2f37390308..c465faca51b 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -299,7 +299,7 @@ static void l2x0_unlock(u32 cache_id)
 	int lockregs;
 	int i;
 
-	switch (cache_id) {
+	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
 	case L2X0_CACHE_ID_PART_L310:
 		lockregs = 8;
 		break;
@@ -333,15 +333,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	if (cache_id_part_number_from_dt)
 		cache_id = cache_id_part_number_from_dt;
 	else
-		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID)
-			& L2X0_CACHE_ID_PART_MASK;
+		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
 	aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 
 	aux &= aux_mask;
 	aux |= aux_val;
 
 	/* Determine the number of ways */
-	switch (cache_id) {
+	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
 	case L2X0_CACHE_ID_PART_L310:
 		if (aux & (1 << 16))
 			ways = 16;
@@ -725,7 +724,6 @@ static const struct l2x0_of_data pl310_data = {
 		.flush_all   = l2x0_flush_all,
 		.inv_all     = l2x0_inv_all,
 		.disable     = l2x0_disable,
-		.set_debug   = pl310_set_debug,
 	},
 };
 
@@ -814,9 +812,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 		data->save();
 
 	of_init = true;
-	l2x0_init(l2x0_base, aux_val, aux_mask);
-
 	memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache));
+	l2x0_init(l2x0_base, aux_val, aux_mask);
 
 	return 0;
 }
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
deleted file mode 100644
index 8a3fadece8d..00000000000
--- a/arch/arm/mm/cache-v3.S
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *  linux/arch/arm/mm/cache-v3.S
- *
- *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/page.h>
-#include "proc-macros.S"
-
-/*
- *	flush_icache_all()
- *
- *	Unconditionally clean and invalidate the entire icache.
- */
-ENTRY(v3_flush_icache_all)
-	mov	pc, lr
-ENDPROC(v3_flush_icache_all)
-
-/*
- *	flush_user_cache_all()
- *
- *	Invalidate all cache entries in a particular address
- *	space.
- *
- *	- mm	- mm_struct describing address space
- */
-ENTRY(v3_flush_user_cache_all)
-	/* FALLTHROUGH */
-/*
- *	flush_kern_cache_all()
- *
- *	Clean and invalidate the entire cache.
- */
-ENTRY(v3_flush_kern_cache_all)
-	/* FALLTHROUGH */
-
-/*
- *	flush_user_cache_range(start, end, flags)
- *
- *	Invalidate a range of cache entries in the specified
- *	address space.
- *
- *	- start - start address (may not be aligned)
- *	- end	- end address (exclusive, may not be aligned)
- *	- flags	- vma_area_struct flags describing address space
- */
-ENTRY(v3_flush_user_cache_range)
-	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	coherent_kern_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_kern_range)
-	/* FALLTHROUGH */
-
-/*
- *	coherent_user_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_user_range)
-	mov	r0, #0
-	mov	pc, lr
-
-/*
- *	flush_kern_dcache_area(void *page, size_t size)
- *
- *	Ensure no D cache aliasing occurs, either with itself or
- *	the I cache
- *
- *	- addr	- kernel address
- *	- size	- region size
- */
-ENTRY(v3_flush_kern_dcache_area)
-	/* FALLTHROUGH */
-
-/*
- *	dma_flush_range(start, end)
- *
- *	Clean and invalidate the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_dma_flush_range)
-	mov	r0, #0
-	mcr	p15, 0, r0, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	dma_unmap_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_unmap_area)
-	teq	r2, #DMA_TO_DEVICE
-	bne	v3_dma_flush_range
-	/* FALLTHROUGH */
-
-/*
- *	dma_map_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_map_area)
-	mov	pc, lr
-ENDPROC(v3_dma_unmap_area)
-ENDPROC(v3_dma_map_area)
-
-	.globl	v3_flush_kern_cache_louis
-	.equ	v3_flush_kern_cache_louis, v3_flush_kern_cache_all
-
-	__INITDATA
-
-	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
-	define_cache_functions v3
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 43e5d77be67..a7ba68f59f0 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all)
 ENTRY(v4_flush_user_cache_range)
 #ifdef CONFIG_CPU_CP15
 	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c7, 0		@ flush ID cache
+	mcr	p15, 0, ip, c7, c7, 0		@ flush ID cache
 	mov	pc, lr
 #else
 	/* FALLTHROUGH */
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index a5a4b2bc42b..2ac37372ef5 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -48,7 +48,7 @@ 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);
 
-static DEFINE_PER_CPU(atomic64_t, active_asids);
+DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
@@ -215,6 +215,7 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
 		local_flush_bp_all();
 		local_flush_tlb_all();
+		dummy_flush_tlb_a15_erratum();
 	}
 
 	atomic64_set(&per_cpu(active_asids, cpu), asid);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e95a996ab78..a84ff763ac3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -34,6 +34,7 @@
 #include <asm/mach/pci.h>
 
 #include "mm.h"
+#include "tcm.h"
 
 /*
  * empty_zero_page is a special page that is used for
@@ -598,39 +599,60 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init alloc_init_section(pud_t *pud, unsigned long addr,
-				      unsigned long end, phys_addr_t phys,
-				      const struct mem_type *type)
+static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+			unsigned long end, phys_addr_t phys,
+			const struct mem_type *type)
 {
-	pmd_t *pmd = pmd_offset(pud, addr);
-
+#ifndef CONFIG_ARM_LPAE
 	/*
-	 * Try a section mapping - end, addr and phys must all be aligned
-	 * to a section boundary.  Note that PMDs refer to the individual
-	 * L1 entries, whereas PGDs refer to a group of L1 entries making
-	 * up one logical pointer to an L2 table.
+	 * In classic MMU format, puds and pmds are folded in to
+	 * the pgds. pmd_offset gives the PGD entry. PGDs refer to a
+	 * group of L1 entries making up one logical pointer to
+	 * an L2 table (2MB), where as PMDs refer to the individual
+	 * L1 entries (1MB). Hence increment to get the correct
+	 * offset for odd 1MB sections.
+	 * (See arch/arm/include/asm/pgtable-2level.h)
 	 */
-	if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) {
-		pmd_t *p = pmd;
-
-#ifndef CONFIG_ARM_LPAE
-		if (addr & SECTION_SIZE)
-			pmd++;
+	if (addr & SECTION_SIZE)
+		pmd++;
 #endif
+	do {
+		*pmd = __pmd(phys | type->prot_sect);
+		phys += SECTION_SIZE;
+	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
-		do {
-			*pmd = __pmd(phys | type->prot_sect);
-			phys += SECTION_SIZE;
-		} while (pmd++, addr += SECTION_SIZE, addr != end);
+	flush_pmd_entry(pmd);
+}
 
-		flush_pmd_entry(p);
-	} else {
+static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
+				      unsigned long end, phys_addr_t phys,
+				      const struct mem_type *type)
+{
+	pmd_t *pmd = pmd_offset(pud, addr);
+	unsigned long next;
+
+	do {
 		/*
-		 * No need to loop; pte's aren't interested in the
-		 * individual L1 entries.
+		 * With LPAE, we must loop over to map
+		 * all the pmds for the given range.
 		 */
-		alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type);
-	}
+		next = pmd_addr_end(addr, end);
+
+		/*
+		 * Try a section mapping - addr, next and phys must all be
+		 * aligned to a section boundary.
+		 */
+		if (type->prot_sect &&
+				((addr | next | phys) & ~SECTION_MASK) == 0) {
+			map_init_section(pmd, addr, next, phys, type);
+		} else {
+			alloc_init_pte(pmd, addr, next,
+						__phys_to_pfn(phys), type);
+		}
+
+		phys += next - addr;
+
+	} while (pmd++, addr = next, addr != end);
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
@@ -641,7 +663,7 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 
 	do {
 		next = pud_addr_end(addr, end);
-		alloc_init_section(pud, addr, next, phys, type);
+		alloc_init_pmd(pud, addr, next, phys, type);
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
 }
@@ -1256,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc)
 	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
+	tcm_init();
 
 	top_pmd = pmd_off_k(0xffff0000);
 
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index dc5de5d53f2..fde2d2a794c 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -77,24 +77,27 @@ __arm740_setup:
 	mcr	p15, 0, r0, c6,	c0		@ set area 0, default
 
 	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
 	mcr	p15, 0, r0, c6,	c1		@ set area 1, RAM
 
 	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
+	cmp	r3, #0
+	moveq	r0, #0
+	beq	2f
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
+2:	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
 
 	mov	r0, #0x06
 	mcr	p15, 0, r0, c2, c0		@ Region 1&2 cacheable
@@ -137,13 +140,14 @@ __arm740_proc_info:
 	.long	0x41807400
 	.long	0xfffffff0
 	.long	0
+	.long	0
 	b	__arm740_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT
+	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
 	.long	cpu_arm740_name
 	.long	arm740_processor_functions
 	.long	0
 	.long	0
-	.long	v3_cache_fns			@ cache model
+	.long	v4_cache_fns			@ cache model
 	.size	__arm740_proc_info, . - __arm740_proc_info
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 2c3b9421ab5..2556cf1c2da 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
 .equ	cpu_arm920_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index f1803f7e297..344c8a548cc 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
 .equ	cpu_arm926_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 82f9cdc751d..0b60dd3d742 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext)
 
 .globl	cpu_mohawk_suspend_size
 .equ	cpu_mohawk_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_mohawk_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 3aa0da11fd8..d92dfd08142 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext)
 
 .globl	cpu_sa1100_suspend_size
 .equ	cpu_sa1100_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_sa1100_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c3, c0, 0		@ domain ID
diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c
index 3e6210b4d6d..054b491ff76 100644
--- a/arch/arm/mm/proc-syms.c
+++ b/arch/arm/mm/proc-syms.c
@@ -17,7 +17,9 @@
 
 #ifndef MULTI_CPU
 EXPORT_SYMBOL(cpu_dcache_clean_area);
+#ifdef CONFIG_MMU
 EXPORT_SYMBOL(cpu_set_pte_ext);
+#endif
 #else
 EXPORT_SYMBOL(processor);
 #endif
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index bcaaa8de932..5c07ee4fe3e 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
 .globl	cpu_v6_suspend_size
 .equ	cpu_v6_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v6_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3a3c015f8d5..f584d3f5b37 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -420,7 +420,7 @@ __v7_pj4b_proc_info:
 __v7_ca7mp_proc_info:
 	.long	0x410fc070
 	.long	0xff0ffff0
-	__v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV
+	__v7_proc __v7_ca7mp_setup
 	.size	__v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info
 
 	/*
@@ -430,10 +430,25 @@ __v7_ca7mp_proc_info:
 __v7_ca15mp_proc_info:
 	.long	0x410fc0f0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV
+	__v7_proc __v7_ca15mp_setup
 	.size	__v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
 	/*
+	 * Qualcomm Inc. Krait processors.
+	 */
+	.type	__krait_proc_info, #object
+__krait_proc_info:
+	.long	0x510f0400		@ Required ID value
+	.long	0xff0ffc00		@ Mask for ID
+	/*
+	 * Some Krait processors don't indicate support for SDIV and UDIV
+	 * instructions in the ARM instruction set, even though they actually
+	 * do support them.
+	 */
+	__v7_proc __v7_setup, hwcaps = HWCAP_IDIV
+	.size	__krait_proc_info, . - __krait_proc_info
+
+	/*
 	 * Match any ARMv7 processor core.
 	 */
 	.type	__v7_proc_info, #object
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index eb93d6487f3..e8efd83b6f2 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 
 .globl	cpu_xsc3_suspend_size
 .equ	cpu_xsc3_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 25510361aa1..e766f889bfd 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext)
 
 .globl	cpu_xscale_suspend_size
 .equ	cpu_xscale_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xscale_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h
index 8015ad434a4..8015ad434a4 100644
--- a/arch/arm/kernel/tcm.h
+++ b/arch/arm/mm/tcm.h