Merge branch 'for-rmk' of git://linux-arm.org/linux-2.6-wd into devel-stable

Conflicts:
	arch/arm/mach-imx/mach-cpuimx27.c

62 files changed, 1190 insertions, 875 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 73c320ea172c..5a3a78633177 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1271,6 +1271,18 @@ config ARM_ERRATA_754327
 	  This workaround defines cpu_relax() as smp_mb(), preventing correctly
 	  written polling loops from denying visibility of updates to memory.
 
+config ARM_ERRATA_364296
+	bool "ARM errata: Possible cache data corruption with hit-under-miss enabled"
+	depends on CPU_V6 && !SMP
+	help
+	  This options enables the workaround for the 364296 ARM1136
+	  r0p2 erratum (possible cache data corruption with
+	  hit-under-miss enabled). It sets the undocumented bit 31 in
+	  the auxiliary control register and the FI bit in the control
+	  register, thus disabling hit-under-miss without putting the
+	  processor into full low interrupt latency mode. ARM11MPCore
+	  is not affected.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/boot/compressed/mmcif-sh7372.c b/arch/arm/boot/compressed/mmcif-sh7372.c
index b6f61d9a5a1b..672ae95db5c3 100644
--- a/arch/arm/boot/compressed/mmcif-sh7372.c
+++ b/arch/arm/boot/compressed/mmcif-sh7372.c
@@ -82,7 +82,7 @@ asmlinkage void mmc_loader(unsigned char *buf, unsigned long len)
 
 
 	/* Disable clock to MMC hardware block */
-	__raw_writel(__raw_readl(SMSTPCR3) & (1 << 12), SMSTPCR3);
+	__raw_writel(__raw_readl(SMSTPCR3) | (1 << 12), SMSTPCR3);
 
 	mmc_update_progress(MMC_PROGRESS_DONE);
 }
diff --git a/arch/arm/boot/compressed/sdhi-sh7372.c b/arch/arm/boot/compressed/sdhi-sh7372.c
index d403a8b24d7f..d279294f2381 100644
--- a/arch/arm/boot/compressed/sdhi-sh7372.c
+++ b/arch/arm/boot/compressed/sdhi-sh7372.c
@@ -85,7 +85,7 @@ asmlinkage void mmc_loader(unsigned short *buf, unsigned long len)
 		goto err;
 
         /* Disable clock to SDHI1 hardware block */
-        __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3);
+        __raw_writel(__raw_readl(SMSTPCR3) | (1 << 13), SMSTPCR3);
 
 	mmc_update_progress(MMC_PROGRESS_DONE);
 
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 16bd48031583..bfa706ffd968 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -64,7 +64,7 @@
 #define L2X0_AUX_CTRL_MASK			0xc0000fff
 #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT	16
 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT		17
-#define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x3 << 17)
+#define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x7 << 17)
 #define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT	22
 #define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT		26
 #define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT		27
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index f389b2704d82..c190bc992f0e 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -50,6 +50,7 @@ static inline void decode_ctrl_reg(u32 reg,
 #define ARM_DEBUG_ARCH_V6_1	2
 #define ARM_DEBUG_ARCH_V7_ECP14	3
 #define ARM_DEBUG_ARCH_V7_MM	4
+#define ARM_DEBUG_ARCH_V7_1	5
 
 /* Breakpoint */
 #define ARM_BREAKPOINT_EXECUTE	0
@@ -57,6 +58,7 @@ static inline void decode_ctrl_reg(u32 reg,
 /* Watchpoints */
 #define ARM_BREAKPOINT_LOAD	1
 #define ARM_BREAKPOINT_STORE	2
+#define ARM_FSR_ACCESS_MASK	(1 << 11)
 
 /* Privilege Levels */
 #define ARM_BREAKPOINT_PRIV	1
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 67c70a31a1be..71d99b83cdb9 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -13,7 +13,12 @@
 #define __ARM_PMU_H__
 
 #include <linux/interrupt.h>
+#include <linux/perf_event.h>
 
+/*
+ * Types of PMUs that can be accessed directly and require mutual
+ * exclusion between profiling tools.
+ */
 enum arm_pmu_type {
 	ARM_PMU_DEVICE_CPU	= 0,
 	ARM_NUM_PMU_DEVICES,
@@ -37,21 +42,17 @@ struct arm_pmu_platdata {
  * reserve_pmu() - reserve the hardware performance counters
  *
  * Reserve the hardware performance counters in the system for exclusive use.
- * The platform_device for the system is returned on success, ERR_PTR()
- * encoded error on failure.
+ * Returns 0 on success or -EBUSY if the lock is already held.
  */
-extern struct platform_device *
-reserve_pmu(enum arm_pmu_type device);
+extern int
+reserve_pmu(enum arm_pmu_type type);
 
 /**
  * release_pmu() - Relinquish control of the performance counters
  *
  * Release the performance counters and allow someone else to use them.
- * Callers must have disabled the counters and released IRQs before calling
- * this. The platform_device returned from reserve_pmu() must be passed as
- * a cookie.
  */
-extern int
+extern void
 release_pmu(enum arm_pmu_type type);
 
 /**
@@ -62,30 +63,84 @@ release_pmu(enum arm_pmu_type type);
  * the actual hardware initialisation.
  */
 extern int
-init_pmu(enum arm_pmu_type device);
+init_pmu(enum arm_pmu_type type);
 
 #else /* CONFIG_CPU_HAS_PMU */
 
 #include <linux/err.h>
 
-static inline struct platform_device *
-reserve_pmu(enum arm_pmu_type device)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline int
-release_pmu(struct platform_device *pdev)
+reserve_pmu(enum arm_pmu_type type)
 {
 	return -ENODEV;
 }
 
-static inline int
-init_pmu(enum arm_pmu_type device)
-{
-	return -ENODEV;
-}
+static inline void
+release_pmu(enum arm_pmu_type type)	{ }
 
 #endif /* CONFIG_CPU_HAS_PMU */
 
+#ifdef CONFIG_HW_PERF_EVENTS
+
+/* The events for a given PMU register set. */
+struct pmu_hw_events {
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event	**events;
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long           *used_mask;
+
+	/*
+	 * Hardware lock to serialize accesses to PMU registers. Needed for the
+	 * read/modify/write sequences.
+	 */
+	raw_spinlock_t		pmu_lock;
+};
+
+struct arm_pmu {
+	struct pmu	pmu;
+	enum arm_perf_pmu_ids id;
+	enum arm_pmu_type type;
+	cpumask_t	active_irqs;
+	const char	*name;
+	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	void		(*enable)(struct hw_perf_event *evt, int idx);
+	void		(*disable)(struct hw_perf_event *evt, int idx);
+	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
+					 struct hw_perf_event *hwc);
+	int		(*set_event_filter)(struct hw_perf_event *evt,
+					    struct perf_event_attr *attr);
+	u32		(*read_counter)(int idx);
+	void		(*write_counter)(int idx, u32 val);
+	void		(*start)(void);
+	void		(*stop)(void);
+	void		(*reset)(void *);
+	int		(*map_event)(struct perf_event *event);
+	int		num_events;
+	atomic_t	active_events;
+	struct mutex	reserve_mutex;
+	u64		max_period;
+	struct platform_device	*plat_device;
+	struct pmu_hw_events	*(*get_hw_events)(void);
+};
+
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
+
+int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type);
+
+u64 armpmu_event_update(struct perf_event *event,
+			struct hw_perf_event *hwc,
+			int idx, int overflow);
+
+int armpmu_event_set_period(struct perf_event *event,
+			    struct hw_perf_event *hwc,
+			    int idx);
+
+#endif /* CONFIG_HW_PERF_EVENTS */
+
 #endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index a927ca1f5566..5a46225f007e 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -45,7 +45,6 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
 static int core_num_brps;
-static int core_num_reserved_brps;
 static int core_num_wrps;
 
 /* Debug architecture version. */
@@ -137,10 +136,11 @@ static u8 get_debug_arch(void)
 	u32 didr;
 
 	/* Do we implement the extended CPUID interface? */
-	if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf),
-	    "CPUID feature registers not supported. "
-	    "Assuming v6 debug is present.\n"))
+	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+		pr_warning("CPUID feature registers not supported. "
+			   "Assuming v6 debug is present.\n");
 		return ARM_DEBUG_ARCH_V6;
+	}
 
 	ARM_DBG_READ(c0, 0, didr);
 	return (didr >> 16) & 0xf;
@@ -154,10 +154,21 @@ u8 arch_get_debug_arch(void)
 static int debug_arch_supported(void)
 {
 	u8 arch = get_debug_arch();
-	return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14;
+
+	/* We don't support the memory-mapped interface. */
+	return (arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14) ||
+		arch >= ARM_DEBUG_ARCH_V7_1;
+}
+
+/* Determine number of WRP registers available. */
+static int get_num_wrp_resources(void)
+{
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 28) & 0xf) + 1;
 }
 
-/* Determine number of BRP register available. */
+/* Determine number of BRP registers available. */
 static int get_num_brp_resources(void)
 {
 	u32 didr;
@@ -176,9 +187,10 @@ static int core_has_mismatch_brps(void)
 static int get_num_wrps(void)
 {
 	/*
-	 * FIXME: When a watchpoint fires, the only way to work out which
-	 * watchpoint it was is by disassembling the faulting instruction
-	 * and working out the address of the memory access.
+	 * On debug architectures prior to 7.1, when a watchpoint fires, the
+	 * only way to work out which watchpoint it was is by disassembling
+	 * the faulting instruction and working out the address of the memory
+	 * access.
 	 *
 	 * Furthermore, we can only do this if the watchpoint was precise
 	 * since imprecise watchpoints prevent us from calculating register
@@ -192,36 +204,17 @@ static int get_num_wrps(void)
 	 * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
 	 * that it is set on some implementations].
 	 */
+	if (get_debug_arch() < ARM_DEBUG_ARCH_V7_1)
+		return 1;
 
-#if 0
-	int wrps;
-	u32 didr;
-	ARM_DBG_READ(c0, 0, didr);
-	wrps = ((didr >> 28) & 0xf) + 1;
-#endif
-	int wrps = 1;
-
-	if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
-		wrps = get_num_brp_resources() - 1;
-
-	return wrps;
-}
-
-/* We reserve one breakpoint for each watchpoint. */
-static int get_num_reserved_brps(void)
-{
-	if (core_has_mismatch_brps())
-		return get_num_wrps();
-	return 0;
+	return get_num_wrp_resources();
 }
 
 /* Determine number of usable BRPs available. */
 static int get_num_brps(void)
 {
 	int brps = get_num_brp_resources();
-	if (core_has_mismatch_brps())
-		brps -= get_num_reserved_brps();
-	return brps;
+	return core_has_mismatch_brps() ? brps - 1 : brps;
 }
 
 /*
@@ -239,7 +232,7 @@ static int enable_monitor_mode(void)
 
 	/* Ensure that halting mode is disabled. */
 	if (WARN_ONCE(dscr & ARM_DSCR_HDBGEN,
-			"halting debug mode enabled. Unable to access hardware resources.\n")) {
+		"halting debug mode enabled. Unable to access hardware resources.\n")) {
 		ret = -EPERM;
 		goto out;
 	}
@@ -255,6 +248,7 @@ static int enable_monitor_mode(void)
 		ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	case ARM_DEBUG_ARCH_V7_ECP14:
+	case ARM_DEBUG_ARCH_V7_1:
 		ARM_DBG_WRITE(c2, 2, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	default:
@@ -346,24 +340,10 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		val_base = ARM_BASE_BVR;
 		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
 		max_slots = core_num_brps;
-		if (info->step_ctrl.enabled) {
-			/* Override the breakpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		}
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled) {
-			/* Install into the reserved breakpoint region. */
-			ctrl_base = ARM_BASE_BCR + core_num_brps;
-			val_base = ARM_BASE_BVR + core_num_brps;
-			/* Override the watchpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		} else {
-			ctrl_base = ARM_BASE_WCR;
-			val_base = ARM_BASE_WVR;
-		}
+		ctrl_base = ARM_BASE_WCR;
+		val_base = ARM_BASE_WVR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -382,6 +362,17 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		goto out;
 	}
 
+	/* Override the breakpoint data with the step data. */
+	if (info->step_ctrl.enabled) {
+		addr = info->trigger & ~0x3;
+		ctrl = encode_ctrl_reg(info->step_ctrl);
+		if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE) {
+			i = 0;
+			ctrl_base = ARM_BASE_BCR + core_num_brps;
+			val_base = ARM_BASE_BVR + core_num_brps;
+		}
+	}
+
 	/* Setup the address register. */
 	write_wb_reg(val_base + i, addr);
 
@@ -405,10 +396,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled)
-			base = ARM_BASE_BCR + core_num_brps;
-		else
-			base = ARM_BASE_WCR;
+		base = ARM_BASE_WCR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -426,6 +414,13 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot\n"))
 		return;
 
+	/* Ensure that we disable the mismatch breakpoint. */
+	if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE &&
+	    info->step_ctrl.enabled) {
+		i = 0;
+		base = ARM_BASE_BCR + core_num_brps;
+	}
+
 	/* Reset the control register. */
 	write_wb_reg(base + i, 0);
 }
@@ -632,10 +627,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * we can use the mismatch feature as a poor-man's hardware
 	 * single-step, but this only works for per-task breakpoints.
 	 */
-	if (WARN_ONCE(!bp->overflow_handler &&
-		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
-		 || !bp->hw.bp_target),
-			"overflow handler required but none found\n")) {
+	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
+	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
+		pr_warning("overflow handler required but none found\n");
 		ret = -EINVAL;
 	}
 out:
@@ -666,34 +660,62 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
-static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
+static void watchpoint_handler(unsigned long addr, unsigned int fsr,
+			       struct pt_regs *regs)
 {
-	int i;
+	int i, access;
+	u32 val, ctrl_reg, alignment_mask;
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
+	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	/* Without a disassembler, we can only handle 1 watchpoint. */
-	BUG_ON(core_num_wrps > 1);
-
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
 
-		if (wp == NULL) {
-			rcu_read_unlock();
-			continue;
-		}
+		if (wp == NULL)
+			goto unlock;
 
+		info = counter_arch_bp(wp);
 		/*
-		 * The DFAR is an unknown value. Since we only allow a
-		 * single watchpoint, we can set the trigger to the lowest
-		 * possible faulting address.
+		 * The DFAR is an unknown value on debug architectures prior
+		 * to 7.1. Since we only allow a single watchpoint on these
+		 * older CPUs, we can set the trigger to the lowest possible
+		 * faulting address.
 		 */
-		info = counter_arch_bp(wp);
-		info->trigger = wp->attr.bp_addr;
+		if (debug_arch < ARM_DEBUG_ARCH_V7_1) {
+			BUG_ON(i > 0);
+			info->trigger = wp->attr.bp_addr;
+		} else {
+			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+				alignment_mask = 0x7;
+			else
+				alignment_mask = 0x3;
+
+			/* Check if the watchpoint value matches. */
+			val = read_wb_reg(ARM_BASE_WVR + i);
+			if (val != (addr & ~alignment_mask))
+				goto unlock;
+
+			/* Possible match, check the byte address select. */
+			ctrl_reg = read_wb_reg(ARM_BASE_WCR + i);
+			decode_ctrl_reg(ctrl_reg, &ctrl);
+			if (!((1 << (addr & alignment_mask)) & ctrl.len))
+				goto unlock;
+
+			/* Check that the access type matches. */
+			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
+				 HW_BREAKPOINT_R;
+			if (!(access & hw_breakpoint_type(wp)))
+				goto unlock;
+
+			/* We have a winner. */
+			info->trigger = addr;
+		}
+
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
 		perf_bp_event(wp, regs);
 
@@ -705,6 +727,7 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 		if (!wp->overflow_handler)
 			enable_single_step(wp, instruction_pointer(regs));
 
+unlock:
 		rcu_read_unlock();
 	}
 }
@@ -717,7 +740,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	for (i = 0; i < core_num_reserved_brps; ++i) {
+	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
@@ -820,7 +843,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
 	case ARM_ENTRY_SYNC_WATCHPOINT:
-		watchpoint_handler(addr, regs);
+		watchpoint_handler(addr, fsr, regs);
 		break;
 	default:
 		ret = 1; /* Unhandled fault. */
@@ -834,11 +857,31 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 /*
  * One-time initialisation.
  */
-static void reset_ctrl_regs(void *info)
+static cpumask_t debug_err_mask;
+
+static int debug_reg_trap(struct pt_regs *regs, unsigned int instr)
 {
-	int i, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
+
+	pr_warning("Debug register access (0x%x) caused undefined instruction on CPU %d\n",
+		   instr, cpu);
+
+	/* Set the error flag for this CPU and skip the faulting instruction. */
+	cpumask_set_cpu(cpu, &debug_err_mask);
+	instruction_pointer(regs) += 4;
+	return 0;
+}
+
+static struct undef_hook debug_reg_hook = {
+	.instr_mask	= 0x0fe80f10,
+	.instr_val	= 0x0e000e10,
+	.fn		= debug_reg_trap,
+};
+
+static void reset_ctrl_regs(void *unused)
+{
+	int i, raw_num_brps, err = 0, cpu = smp_processor_id();
 	u32 dbg_power;
-	cpumask_t *cpumask = info;
 
 	/*
 	 * v7 debug contains save and restore registers so that debug state
@@ -848,38 +891,52 @@ static void reset_ctrl_regs(void *info)
 	 * Access Register to avoid taking undefined instruction exceptions
 	 * later on.
 	 */
-	if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+	switch (debug_arch) {
+	case ARM_DEBUG_ARCH_V7_ECP14:
 		/*
 		 * Ensure sticky power-down is clear (i.e. debug logic is
 		 * powered up).
 		 */
 		asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power));
-		if ((dbg_power & 0x1) == 0) {
-			pr_warning("CPU %d debug is powered down!\n", cpu);
-			cpumask_or(cpumask, cpumask, cpumask_of(cpu));
-			return;
-		}
-
+		if ((dbg_power & 0x1) == 0)
+			err = -EPERM;
+		break;
+	case ARM_DEBUG_ARCH_V7_1:
 		/*
-		 * Unconditionally clear the lock by writing a value
-		 * other than 0xC5ACCE55 to the access register.
+		 * Ensure the OS double lock is clear.
 		 */
-		asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
-		isb();
+		asm volatile("mrc p14, 0, %0, c1, c3, 4" : "=r" (dbg_power));
+		if ((dbg_power & 0x1) == 1)
+			err = -EPERM;
+		break;
+	}
 
-		/*
-		 * Clear any configured vector-catch events before
-		 * enabling monitor mode.
-		 */
-		asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
-		isb();
+	if (err) {
+		pr_warning("CPU %d debug is powered down!\n", cpu);
+		cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu));
+		return;
 	}
 
+	/*
+	 * Unconditionally clear the lock by writing a value
+	 * other than 0xC5ACCE55 to the access register.
+	 */
+	asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
+	isb();
+
+	/*
+	 * Clear any configured vector-catch events before
+	 * enabling monitor mode.
+	 */
+	asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
+	isb();
+
 	if (enable_monitor_mode())
 		return;
 
 	/* We must also reset any reserved registers. */
-	for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
+	raw_num_brps = get_num_brp_resources();
+	for (i = 0; i < raw_num_brps; ++i) {
 		write_wb_reg(ARM_BASE_BCR + i, 0UL);
 		write_wb_reg(ARM_BASE_BVR + i, 0UL);
 	}
@@ -895,6 +952,7 @@ static int __cpuinit dbg_reset_notify(struct notifier_block *self,
 {
 	if (action == CPU_ONLINE)
 		smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
+
 	return NOTIFY_OK;
 }
 
@@ -905,7 +963,6 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = {
 static int __init arch_hw_breakpoint_init(void)
 {
 	u32 dscr;
-	cpumask_t cpumask = { CPU_BITS_NONE };
 
 	debug_arch = get_debug_arch();
 
@@ -916,28 +973,31 @@ static int __init arch_hw_breakpoint_init(void)
 
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
-	core_num_reserved_brps = get_num_reserved_brps();
 	core_num_wrps = get_num_wrps();
 
-	pr_info("found %d breakpoint and %d watchpoint registers.\n",
-		core_num_brps + core_num_reserved_brps, core_num_wrps);
-
-	if (core_num_reserved_brps)
-		pr_info("%d breakpoint(s) reserved for watchpoint "
-				"single-step.\n", core_num_reserved_brps);
+	/*
+	 * We need to tread carefully here because DBGSWENABLE may be
+	 * driven low on this core and there isn't an architected way to
+	 * determine that.
+	 */
+	register_undef_hook(&debug_reg_hook);
 
 	/*
 	 * Reset the breakpoint resources. We assume that a halting
 	 * debugger will leave the world in a nice state for us.
 	 */
-	on_each_cpu(reset_ctrl_regs, &cpumask, 1);
-	if (!cpumask_empty(&cpumask)) {
+	on_each_cpu(reset_ctrl_regs, NULL, 1);
+	unregister_undef_hook(&debug_reg_hook);
+	if (!cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
-		core_num_reserved_brps = 0;
 		core_num_wrps = 0;
 		return 0;
 	}
 
+	pr_info("found %d " "%s" "breakpoint and %d watchpoint registers.\n",
+		core_num_brps, core_has_mismatch_brps() ? "(+1 reserved) " :
+		"", core_num_wrps);
+
 	ARM_DBG_READ(c1, 0, dscr);
 	if (dscr & ARM_DSCR_HDBGEN) {
 		max_watchpoint_len = 4;
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 53c9c2610cbc..e6e5d7c84f1a 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/bitmap.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -26,16 +27,8 @@
 #include <asm/pmu.h>
 #include <asm/stacktrace.h>
 
-static struct platform_device *pmu_device;
-
-/*
- * Hardware lock to serialize accesses to PMU registers. Needed for the
- * read/modify/write sequences.
- */
-static DEFINE_RAW_SPINLOCK(pmu_lock);
-
 /*
- * ARMv6 supports a maximum of 3 events, starting from index 1. If we add
+ * ARMv6 supports a maximum of 3 events, starting from index 0. If we add
  * another platform that supports more, we need to increase this to be the
  * largest of all platforms.
  *
@@ -43,62 +36,24 @@ static DEFINE_RAW_SPINLOCK(pmu_lock);
  *  cycle counter CCNT + 31 events counters CNT0..30.
  *  Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters.
  */
-#define ARMPMU_MAX_HWEVENTS		33
+#define ARMPMU_MAX_HWEVENTS		32
 
-/* The events for a given CPU. */
-struct cpu_hw_events {
-	/*
-	 * The events that are active on the CPU for the given index. Index 0
-	 * is reserved.
-	 */
-	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];
-
-	/*
-	 * A 1 bit for an index indicates that the counter is being used for
-	 * an event. A 0 means that the counter can be used.
-	 */
-	unsigned long		used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
+static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
+static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
+static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
 
-	/*
-	 * A 1 bit for an index indicates that the counter is actively being
-	 * used.
-	 */
-	unsigned long		active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
-};
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
-
-struct arm_pmu {
-	enum arm_perf_pmu_ids id;
-	const char	*name;
-	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
-	void		(*enable)(struct hw_perf_event *evt, int idx);
-	void		(*disable)(struct hw_perf_event *evt, int idx);
-	int		(*get_event_idx)(struct cpu_hw_events *cpuc,
-					 struct hw_perf_event *hwc);
-	u32		(*read_counter)(int idx);
-	void		(*write_counter)(int idx, u32 val);
-	void		(*start)(void);
-	void		(*stop)(void);
-	void		(*reset)(void *);
-	const unsigned	(*cache_map)[PERF_COUNT_HW_CACHE_MAX]
-				    [PERF_COUNT_HW_CACHE_OP_MAX]
-				    [PERF_COUNT_HW_CACHE_RESULT_MAX];
-	const unsigned	(*event_map)[PERF_COUNT_HW_MAX];
-	u32		raw_event_mask;
-	int		num_events;
-	u64		max_period;
-};
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
 
 /* Set at runtime when we know what CPU type we are. */
-static const struct arm_pmu *armpmu;
+static struct arm_pmu *cpu_pmu;
 
 enum arm_perf_pmu_ids
 armpmu_get_pmu_id(void)
 {
 	int id = -ENODEV;
 
-	if (armpmu != NULL)
-		id = armpmu->id;
+	if (cpu_pmu != NULL)
+		id = cpu_pmu->id;
 
 	return id;
 }
@@ -109,8 +64,8 @@ armpmu_get_max_events(void)
 {
 	int max_events = 0;
 
-	if (armpmu != NULL)
-		max_events = armpmu->num_events;
+	if (cpu_pmu != NULL)
+		max_events = cpu_pmu->num_events;
 
 	return max_events;
 }
@@ -130,7 +85,11 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 #define CACHE_OP_UNSUPPORTED		0xFFFF
 
 static int
-armpmu_map_cache_event(u64 config)
+armpmu_map_cache_event(const unsigned (*cache_map)
+				      [PERF_COUNT_HW_CACHE_MAX]
+				      [PERF_COUNT_HW_CACHE_OP_MAX]
+				      [PERF_COUNT_HW_CACHE_RESULT_MAX],
+		       u64 config)
 {
 	unsigned int cache_type, cache_op, cache_result, ret;
 
@@ -146,7 +105,7 @@ armpmu_map_cache_event(u64 config)
 	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
 		return -EINVAL;
 
-	ret = (int)(*armpmu->cache_map)[cache_type][cache_op][cache_result];
+	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
 
 	if (ret == CACHE_OP_UNSUPPORTED)
 		return -ENOENT;
@@ -155,23 +114,46 @@ armpmu_map_cache_event(u64 config)
 }
 
 static int
-armpmu_map_event(u64 config)
+armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*armpmu->event_map)[config];
-	return mapping == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : mapping;
+	int mapping = (*event_map)[config];
+	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
 static int
-armpmu_map_raw_event(u64 config)
+armpmu_map_raw_event(u32 raw_event_mask, u64 config)
 {
-	return (int)(config & armpmu->raw_event_mask);
+	return (int)(config & raw_event_mask);
 }
 
-static int
+static int map_cpu_event(struct perf_event *event,
+			 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
+			 const unsigned (*cache_map)
+					[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX],
+			 u32 raw_event_mask)
+{
+	u64 config = event->attr.config;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		return armpmu_map_event(event_map, config);
+	case PERF_TYPE_HW_CACHE:
+		return armpmu_map_cache_event(cache_map, config);
+	case PERF_TYPE_RAW:
+		return armpmu_map_raw_event(raw_event_mask, config);
+	}
+
+	return -ENOENT;
+}
+
+int
 armpmu_event_set_period(struct perf_event *event,
 			struct hw_perf_event *hwc,
 			int idx)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
 	int ret = 0;
@@ -202,11 +184,12 @@ armpmu_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static u64
+u64
 armpmu_event_update(struct perf_event *event,
 		    struct hw_perf_event *hwc,
 		    int idx, int overflow)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	u64 delta, prev_raw_count, new_raw_count;
 
 again:
@@ -246,11 +229,9 @@ armpmu_read(struct perf_event *event)
 static void
 armpmu_stop(struct perf_event *event, int flags)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!armpmu)
-		return;
-
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -266,11 +247,9 @@ armpmu_stop(struct perf_event *event, int flags)
 static void
 armpmu_start(struct perf_event *event, int flags)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!armpmu)
-		return;
-
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -293,16 +272,16 @@ armpmu_start(struct perf_event *event, int flags)
 static void
 armpmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
 	WARN_ON(idx < 0);
 
-	clear_bit(idx, cpuc->active_mask);
 	armpmu_stop(event, PERF_EF_UPDATE);
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+	hw_events->events[idx] = NULL;
+	clear_bit(idx, hw_events->used_mask);
 
 	perf_event_update_userpage(event);
 }
@@ -310,7 +289,8 @@ armpmu_del(struct perf_event *event, int flags)
 static int
 armpmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -318,7 +298,7 @@ armpmu_add(struct perf_event *event, int flags)
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
-	idx = armpmu->get_event_idx(cpuc, hwc);
+	idx = armpmu->get_event_idx(hw_events, hwc);
 	if (idx < 0) {
 		err = idx;
 		goto out;
@@ -330,8 +310,7 @@ armpmu_add(struct perf_event *event, int flags)
 	 */
 	event->hw.idx = idx;
 	armpmu->disable(hwc, idx);
-	cpuc->events[idx] = event;
-	set_bit(idx, cpuc->active_mask);
+	hw_events->events[idx] = event;
 
 	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
 	if (flags & PERF_EF_START)
@@ -345,25 +324,25 @@ out:
 	return err;
 }
 
-static struct pmu pmu;
-
 static int
-validate_event(struct cpu_hw_events *cpuc,
+validate_event(struct pmu_hw_events *hw_events,
 	       struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event fake_event = event->hw;
+	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
 		return 1;
 
-	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
+	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
 }
 
 static int
 validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
-	struct cpu_hw_events fake_pmu;
+	struct pmu_hw_events fake_pmu;
 
 	memset(&fake_pmu, 0, sizeof(fake_pmu));
 
@@ -383,110 +362,119 @@ validate_group(struct perf_event *event)
 
 static irqreturn_t armpmu_platform_irq(int irq, void *dev)
 {
-	struct arm_pmu_platdata *plat = dev_get_platdata(&pmu_device->dev);
+	struct arm_pmu *armpmu = (struct arm_pmu *) dev;
+	struct platform_device *plat_device = armpmu->plat_device;
+	struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
 
 	return plat->handle_irq(irq, dev, armpmu->handle_irq);
 }
 
+static void
+armpmu_release_hardware(struct arm_pmu *armpmu)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = armpmu->plat_device;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	for (i = 0; i < irqs; ++i) {
+		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
+			continue;
+		irq = platform_get_irq(pmu_device, i);
+		if (irq >= 0)
+			free_irq(irq, armpmu);
+	}
+
+	release_pmu(armpmu->type);
+}
+
 static int
-armpmu_reserve_hardware(void)
+armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
 	struct arm_pmu_platdata *plat;
 	irq_handler_t handle_irq;
-	int i, err = -ENODEV, irq;
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = armpmu->plat_device;
 
-	pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU);
-	if (IS_ERR(pmu_device)) {
+	err = reserve_pmu(armpmu->type);
+	if (err) {
 		pr_warning("unable to reserve pmu\n");
-		return PTR_ERR(pmu_device);
+		return err;
 	}
 
-	init_pmu(ARM_PMU_DEVICE_CPU);
-
 	plat = dev_get_platdata(&pmu_device->dev);
 	if (plat && plat->handle_irq)
 		handle_irq = armpmu_platform_irq;
 	else
 		handle_irq = armpmu->handle_irq;
 
-	if (pmu_device->num_resources < 1) {
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
 		pr_err("no irqs for PMUs defined\n");
 		return -ENODEV;
 	}
 
-	for (i = 0; i < pmu_device->num_resources; ++i) {
+	for (i = 0; i < irqs; ++i) {
+		err = 0;
 		irq = platform_get_irq(pmu_device, i);
 		if (irq < 0)
 			continue;
 
+		/*
+		 * If we have a single PMU interrupt that we can't shift,
+		 * assume that we're running on a uniprocessor machine and
+		 * continue. Otherwise, continue without this interrupt.
+		 */
+		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+				    irq, i);
+			continue;
+		}
+
 		err = request_irq(irq, handle_irq,
 				  IRQF_DISABLED | IRQF_NOBALANCING,
-				  "armpmu", NULL);
+				  "arm-pmu", armpmu);
 		if (err) {
-			pr_warning("unable to request IRQ%d for ARM perf "
-				"counters\n", irq);
-			break;
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
+				irq);
+			armpmu_release_hardware(armpmu);
+			return err;
 		}
-	}
 
-	if (err) {
-		for (i = i - 1; i >= 0; --i) {
-			irq = platform_get_irq(pmu_device, i);
-			if (irq >= 0)
-				free_irq(irq, NULL);
-		}
-		release_pmu(ARM_PMU_DEVICE_CPU);
-		pmu_device = NULL;
+		cpumask_set_cpu(i, &armpmu->active_irqs);
 	}
 
-	return err;
+	return 0;
 }
 
 static void
-armpmu_release_hardware(void)
+hw_perf_event_destroy(struct perf_event *event)
 {
-	int i, irq;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	atomic_t *active_events	 = &armpmu->active_events;
+	struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
 
-	for (i = pmu_device->num_resources - 1; i >= 0; --i) {
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
-			free_irq(irq, NULL);
+	if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
+		armpmu_release_hardware(armpmu);
+		mutex_unlock(pmu_reserve_mutex);
 	}
-	armpmu->stop();
-
-	release_pmu(ARM_PMU_DEVICE_CPU);
-	pmu_device = NULL;
 }
 
-static atomic_t active_events = ATOMIC_INIT(0);
-static DEFINE_MUTEX(pmu_reserve_mutex);
-
-static void
-hw_perf_event_destroy(struct perf_event *event)
+static int
+event_requires_mode_exclusion(struct perf_event_attr *attr)
 {
-	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
-		armpmu_release_hardware();
-		mutex_unlock(&pmu_reserve_mutex);
-	}
+	return attr->exclude_idle || attr->exclude_user ||
+	       attr->exclude_kernel || attr->exclude_hv;
 }
 
 static int
 __hw_perf_event_init(struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping, err;
 
-	/* Decode the generic type into an ARM event identifier. */
-	if (PERF_TYPE_HARDWARE == event->attr.type) {
-		mapping = armpmu_map_event(event->attr.config);
-	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
-		mapping = armpmu_map_cache_event(event->attr.config);
-	} else if (PERF_TYPE_RAW == event->attr.type) {
-		mapping = armpmu_map_raw_event(event->attr.config);
-	} else {
-		pr_debug("event type %x not supported\n", event->attr.type);
-		return -EOPNOTSUPP;
-	}
+	mapping = armpmu->map_event(event);
 
 	if (mapping < 0) {
 		pr_debug("event %x:%llx not supported\n", event->attr.type,
@@ -495,34 +483,31 @@ __hw_perf_event_init(struct perf_event *event)
 	}
 
 	/*
+	 * We don't assign an index until we actually place the event onto
+	 * hardware. Use -1 to signify that we haven't decided where to put it
+	 * yet. For SMP systems, each core has it's own PMU so we can't do any
+	 * clever allocation or constraints checking at this point.
+	 */
+	hwc->idx		= -1;
+	hwc->config_base	= 0;
+	hwc->config		= 0;
+	hwc->event_base		= 0;
+
+	/*
 	 * Check whether we need to exclude the counter from certain modes.
-	 * The ARM performance counters are on all of the time so if someone
-	 * has asked us for some excludes then we have to fail.
 	 */
-	if (event->attr.exclude_kernel || event->attr.exclude_user ||
-	    event->attr.exclude_hv || event->attr.exclude_idle) {
+	if ((!armpmu->set_event_filter ||
+	     armpmu->set_event_filter(hwc, &event->attr)) &&
+	     event_requires_mode_exclusion(&event->attr)) {
 		pr_debug("ARM performance counters do not support "
 			 "mode exclusion\n");
 		return -EPERM;
 	}
 
 	/*
-	 * We don't assign an index until we actually place the event onto
-	 * hardware. Use -1 to signify that we haven't decided where to put it
-	 * yet. For SMP systems, each core has it's own PMU so we can't do any
-	 * clever allocation or constraints checking at this point.
+	 * Store the event encoding into the config_base field.
 	 */
-	hwc->idx = -1;
-
-	/*
-	 * Store the event encoding into the config_base field. config and
-	 * event_base are unused as the only 2 things we need to know are
-	 * the event mapping and the counter to use. The counter to use is
-	 * also the indx and the config_base is the event type.
-	 */
-	hwc->config_base	    = (unsigned long)mapping;
-	hwc->config		    = 0;
-	hwc->event_base		    = 0;
+	hwc->config_base	    |= (unsigned long)mapping;
 
 	if (!hwc->sample_period) {
 		hwc->sample_period  = armpmu->max_period;
@@ -542,32 +527,23 @@ __hw_perf_event_init(struct perf_event *event)
 
 static int armpmu_event_init(struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	int err = 0;
+	atomic_t *active_events = &armpmu->active_events;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		break;
-
-	default:
+	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
-	}
-
-	if (!armpmu)
-		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
-	if (!atomic_inc_not_zero(&active_events)) {
-		mutex_lock(&pmu_reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
-			err = armpmu_reserve_hardware();
-		}
+	if (!atomic_inc_not_zero(active_events)) {
+		mutex_lock(&armpmu->reserve_mutex);
+		if (atomic_read(active_events) == 0)
+			err = armpmu_reserve_hardware(armpmu);
 
 		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmu_reserve_mutex);
+			atomic_inc(active_events);
+		mutex_unlock(&armpmu->reserve_mutex);
 	}
 
 	if (err)
@@ -582,22 +558,9 @@ static int armpmu_event_init(struct perf_event *event)
 
 static void armpmu_enable(struct pmu *pmu)
 {
-	/* Enable all of the perf events on hardware. */
-	int idx, enabled = 0;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
-	if (!armpmu)
-		return;
-
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
-		struct perf_event *event = cpuc->events[idx];
-
-		if (!event)
-			continue;
-
-		armpmu->enable(&event->hw, idx);
-		enabled = 1;
-	}
+	struct arm_pmu *armpmu = to_arm_pmu(pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
+	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
 
 	if (enabled)
 		armpmu->start();
@@ -605,20 +568,32 @@ static void armpmu_enable(struct pmu *pmu)
 
 static void armpmu_disable(struct pmu *pmu)
 {
-	if (armpmu)
-		armpmu->stop();
+	struct arm_pmu *armpmu = to_arm_pmu(pmu);
+	armpmu->stop();
 }
 
-static struct pmu pmu = {
-	.pmu_enable	= armpmu_enable,
-	.pmu_disable	= armpmu_disable,
-	.event_init	= armpmu_event_init,
-	.add		= armpmu_add,
-	.del		= armpmu_del,
-	.start		= armpmu_start,
-	.stop		= armpmu_stop,
-	.read		= armpmu_read,
-};
+static void __init armpmu_init(struct arm_pmu *armpmu)
+{
+	atomic_set(&armpmu->active_events, 0);
+	mutex_init(&armpmu->reserve_mutex);
+
+	armpmu->pmu = (struct pmu) {
+		.pmu_enable	= armpmu_enable,
+		.pmu_disable	= armpmu_disable,
+		.event_init	= armpmu_event_init,
+		.add		= armpmu_add,
+		.del		= armpmu_del,
+		.start		= armpmu_start,
+		.stop		= armpmu_stop,
+		.read		= armpmu_read,
+	};
+}
+
+int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
+{
+	armpmu_init(armpmu);
+	return perf_pmu_register(&armpmu->pmu, name, type);
+}
 
 /* Include the PMU-specific implementations. */
 #include "perf_event_xscale.c"
@@ -630,14 +605,72 @@ static struct pmu pmu = {
  * This requires SMP to be available, so exists as a separate initcall.
  */
 static int __init
-armpmu_reset(void)
+cpu_pmu_reset(void)
+{
+	if (cpu_pmu && cpu_pmu->reset)
+		return on_each_cpu(cpu_pmu->reset, NULL, 1);
+	return 0;
+}
+arch_initcall(cpu_pmu_reset);
+
+/*
+ * PMU platform driver and devicetree bindings.
+ */
+static struct of_device_id armpmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a9-pmu"},
+	{.compatible = "arm,cortex-a8-pmu"},
+	{.compatible = "arm,arm1136-pmu"},
+	{.compatible = "arm,arm1176-pmu"},
+	{},
+};
+
+static struct platform_device_id armpmu_plat_device_ids[] = {
+	{.name = "arm-pmu"},
+	{},
+};
+
+static int __devinit armpmu_device_probe(struct platform_device *pdev)
 {
-	if (armpmu && armpmu->reset)
-		return on_each_cpu(armpmu->reset, NULL, 1);
+	cpu_pmu->plat_device = pdev;
 	return 0;
 }
-arch_initcall(armpmu_reset);
 
+static struct platform_driver armpmu_driver = {
+	.driver		= {
+		.name	= "arm-pmu",
+		.of_match_table = armpmu_of_device_ids,
+	},
+	.probe		= armpmu_device_probe,
+	.id_table	= armpmu_plat_device_ids,
+};
+
+static int __init register_pmu_driver(void)
+{
+	return platform_driver_register(&armpmu_driver);
+}
+device_initcall(register_pmu_driver);
+
+static struct pmu_hw_events *armpmu_get_cpu_events(void)
+{
+	return &__get_cpu_var(cpu_hw_events);
+}
+
+static void __init cpu_pmu_init(struct arm_pmu *armpmu)
+{
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
+		events->events = per_cpu(hw_events, cpu);
+		events->used_mask = per_cpu(used_mask, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+	}
+	armpmu->get_hw_events = armpmu_get_cpu_events;
+	armpmu->type = ARM_PMU_DEVICE_CPU;
+}
+
+/*
+ * CPU PMU identification and registration.
+ */
 static int __init
 init_hw_perf_events(void)
 {
@@ -651,22 +684,22 @@ init_hw_perf_events(void)
 		case 0xB360:	/* ARM1136 */
 		case 0xB560:	/* ARM1156 */
 		case 0xB760:	/* ARM1176 */
-			armpmu = armv6pmu_init();
+			cpu_pmu = armv6pmu_init();
 			break;
 		case 0xB020:	/* ARM11mpcore */
-			armpmu = armv6mpcore_pmu_init();
+			cpu_pmu = armv6mpcore_pmu_init();
 			break;
 		case 0xC080:	/* Cortex-A8 */
-			armpmu = armv7_a8_pmu_init();
+			cpu_pmu = armv7_a8_pmu_init();
 			break;
 		case 0xC090:	/* Cortex-A9 */
-			armpmu = armv7_a9_pmu_init();
+			cpu_pmu = armv7_a9_pmu_init();
 			break;
 		case 0xC050:	/* Cortex-A5 */
-			armpmu = armv7_a5_pmu_init();
+			cpu_pmu = armv7_a5_pmu_init();
 			break;
 		case 0xC0F0:	/* Cortex-A15 */
-			armpmu = armv7_a15_pmu_init();
+			cpu_pmu = armv7_a15_pmu_init();
 			break;
 		}
 	/* Intel CPUs [xscale]. */
@@ -674,23 +707,23 @@ init_hw_perf_events(void)
 		part_number = (cpuid >> 13) & 0x7;
 		switch (part_number) {
 		case 1:
-			armpmu = xscale1pmu_init();
+			cpu_pmu = xscale1pmu_init();
 			break;
 		case 2:
-			armpmu = xscale2pmu_init();
+			cpu_pmu = xscale2pmu_init();
 			break;
 		}
 	}
 
-	if (armpmu) {
+	if (cpu_pmu) {
 		pr_info("enabled with %s PMU driver, %d counters available\n",
-			armpmu->name, armpmu->num_events);
+			cpu_pmu->name, cpu_pmu->num_events);
+		cpu_pmu_init(cpu_pmu);
+		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
 	} else {
 		pr_info("no hardware support available\n");
 	}
 
-	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
-
 	return 0;
 }
 early_initcall(init_hw_perf_events);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index dd7f3b9f4cb3..e63d8115c01b 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -54,7 +54,7 @@ enum armv6_perf_types {
 };
 
 enum armv6_counters {
-	ARMV6_CYCLE_COUNTER = 1,
+	ARMV6_CYCLE_COUNTER = 0,
 	ARMV6_COUNTER0,
 	ARMV6_COUNTER1,
 };
@@ -433,6 +433,7 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 		      int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= 0;
@@ -454,12 +455,29 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 	 * Mask out the current event and set the counter to count the event
 	 * that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static int counter_is_active(unsigned long pmcr, int idx)
+{
+	unsigned long mask = 0;
+	if (idx == ARMV6_CYCLE_COUNTER)
+		mask = ARMV6_PMCR_CCOUNT_IEN;
+	else if (idx == ARMV6_COUNTER0)
+		mask = ARMV6_PMCR_COUNT0_IEN;
+	else if (idx == ARMV6_COUNTER1)
+		mask = ARMV6_PMCR_COUNT1_IEN;
+
+	if (mask)
+		return pmcr & mask;
+
+	WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+	return 0;
 }
 
 static irqreturn_t
@@ -468,7 +486,7 @@ armv6pmu_handle_irq(int irq_num,
 {
 	unsigned long pmcr = armv6_pmcr_read();
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -487,11 +505,11 @@ armv6pmu_handle_irq(int irq_num,
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!counter_is_active(pmcr, idx))
 			continue;
 
 		/*
@@ -508,7 +526,7 @@ armv6pmu_handle_irq(int irq_num,
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	/*
@@ -527,28 +545,30 @@ static void
 armv6pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val |= ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 armv6pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+armv6pmu_get_event_idx(struct pmu_hw_events *cpuc,
 		       struct hw_perf_event *event)
 {
 	/* Always place a cycle counter into the cycle counter. */
@@ -578,6 +598,7 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
 		       int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= ARMV6_PMCR_CCOUNT_IEN;
@@ -598,12 +619,12 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
 	 * of ETM bus signal assertion cycles. The external reporting should
 	 * be disabled and so this should never increment.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
@@ -611,6 +632,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 			      int idx)
 {
 	unsigned long val, mask, flags, evt = 0;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= ARMV6_PMCR_CCOUNT_IEN;
@@ -627,15 +649,21 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
 	 * simply disable the interrupt reporting.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static int armv6_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6_perf_map,
+				&armv6_perf_cache_map, 0xFF);
 }
 
-static const struct arm_pmu armv6pmu = {
+static struct arm_pmu armv6pmu = {
 	.id			= ARM_PERF_PMU_ID_V6,
 	.name			= "v6",
 	.handle_irq		= armv6pmu_handle_irq,
@@ -646,14 +674,12 @@ static const struct arm_pmu armv6pmu = {
 	.get_event_idx		= armv6pmu_get_event_idx,
 	.start			= armv6pmu_start,
 	.stop			= armv6pmu_stop,
-	.cache_map		= &armv6_perf_cache_map,
-	.event_map		= &armv6_perf_map,
-	.raw_event_mask		= 0xFF,
+	.map_event		= armv6_map_event,
 	.num_events		= 3,
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__init armv6pmu_init(void)
 {
 	return &armv6pmu;
 }
@@ -665,7 +691,14 @@ static const struct arm_pmu *__init armv6pmu_init(void)
  * disable the interrupt reporting and update the event. When unthrottling we
  * reset the period and enable the interrupt reporting.
  */
-static const struct arm_pmu armv6mpcore_pmu = {
+
+static int armv6mpcore_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6mpcore_perf_map,
+				&armv6mpcore_perf_cache_map, 0xFF);
+}
+
+static struct arm_pmu armv6mpcore_pmu = {
 	.id			= ARM_PERF_PMU_ID_V6MP,
 	.name			= "v6mpcore",
 	.handle_irq		= armv6pmu_handle_irq,
@@ -676,24 +709,22 @@ static const struct arm_pmu armv6mpcore_pmu = {
 	.get_event_idx		= armv6pmu_get_event_idx,
 	.start			= armv6pmu_start,
 	.stop			= armv6pmu_stop,
-	.cache_map		= &armv6mpcore_perf_cache_map,
-	.event_map		= &armv6mpcore_perf_map,
-	.raw_event_mask		= 0xFF,
+	.map_event		= armv6mpcore_map_event,
 	.num_events		= 3,
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return &armv6mpcore_pmu;
 }
 #else
-static const struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__init armv6pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4c851834f68e..98b75738345e 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -17,6 +17,9 @@
  */
 
 #ifdef CONFIG_CPU_V7
+
+static struct arm_pmu armv7pmu;
+
 /*
  * Common ARMv7 event types
  *
@@ -676,23 +679,24 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
- * Perf Events counters
+ * Perf Events' indices
  */
-enum armv7_counters {
-	ARMV7_CYCLE_COUNTER		= 1,	/* Cycle counter */
-	ARMV7_COUNTER0			= 2,	/* First event counter */
-};
+#define	ARMV7_IDX_CYCLE_COUNTER	0
+#define	ARMV7_IDX_COUNTER0	1
+#define	ARMV7_IDX_COUNTER_LAST	(ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
+
+#define	ARMV7_MAX_COUNTERS	32
+#define	ARMV7_COUNTER_MASK	(ARMV7_MAX_COUNTERS - 1)
 
 /*
- * The cycle counter is ARMV7_CYCLE_COUNTER.
- * The first event counter is ARMV7_COUNTER0.
- * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
+ * ARMv7 low level PMNC access
  */
-#define	ARMV7_COUNTER_LAST	(ARMV7_COUNTER0 + armpmu->num_events - 1)
 
 /*
- * ARMv7 low level PMNC access
+ * Perf Event to low level counters mapping
  */
+#define	ARMV7_IDX_TO_COUNTER(x)	\
+	(((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK)
 
 /*
  * Per-CPU PMNC: config reg
@@ -708,103 +712,76 @@ enum armv7_counters {
 #define	ARMV7_PMNC_MASK		0x3f	 /* Mask for writable bits */
 
 /*
- * Available counters
- */
-#define ARMV7_CNT0		0	/* First event counter */
-#define ARMV7_CCNT		31	/* Cycle counter */
-
-/* Perf Event to low level counters mapping */
-#define ARMV7_EVENT_CNT_TO_CNTx	(ARMV7_COUNTER0 - ARMV7_CNT0)
-
-/*
- * CNTENS: counters enable reg
- */
-#define ARMV7_CNTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENS_C		(1 << ARMV7_CCNT)
-
-/*
- * CNTENC: counters disable reg
- */
-#define ARMV7_CNTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENC_C		(1 << ARMV7_CCNT)
-
-/*
- * INTENS: counters overflow interrupt enable reg
- */
-#define ARMV7_INTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENS_C		(1 << ARMV7_CCNT)
-
-/*
- * INTENC: counters overflow interrupt disable reg
- */
-#define ARMV7_INTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENC_C		(1 << ARMV7_CCNT)
-
-/*
- * EVTSEL: Event selection reg
+ * FLAG: counters overflow flag status reg
  */
-#define	ARMV7_EVTSEL_MASK	0xff		/* Mask for writable bits */
+#define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
+#define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK
 
 /*
- * SELECT: Counter selection reg
+ * PMXEVTYPER: Event selection reg
  */
-#define	ARMV7_SELECT_MASK	0x1f		/* Mask for writable bits */
+#define	ARMV7_EVTYPE_MASK	0xc00000ff	/* Mask for writable bits */
+#define	ARMV7_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
 
 /*
- * FLAG: counters overflow flag status reg
+ * Event filters for PMUv2
  */
-#define ARMV7_FLAG_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_FLAG_C		(1 << ARMV7_CCNT)
-#define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
-#define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK
+#define	ARMV7_EXCLUDE_PL1	(1 << 31)
+#define	ARMV7_EXCLUDE_USER	(1 << 30)
+#define	ARMV7_INCLUDE_HYP	(1 << 27)
 
-static inline unsigned long armv7_pmnc_read(void)
+static inline u32 armv7_pmnc_read(void)
 {
 	u32 val;
 	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
 	return val;
 }
 
-static inline void armv7_pmnc_write(unsigned long val)
+static inline void armv7_pmnc_write(u32 val)
 {
 	val &= ARMV7_PMNC_MASK;
 	isb();
 	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
 }
 
-static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
+static inline int armv7_pmnc_has_overflowed(u32 pmnc)
 {
 	return pmnc & ARMV7_OVERFLOWED_MASK;
 }
 
-static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
-					enum armv7_counters counter)
+static inline int armv7_pmnc_counter_valid(int idx)
+{
+	return idx >= ARMV7_IDX_CYCLE_COUNTER && idx <= ARMV7_IDX_COUNTER_LAST;
+}
+
+static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx)
 {
 	int ret = 0;
+	u32 counter;
 
-	if (counter == ARMV7_CYCLE_COUNTER)
-		ret = pmnc & ARMV7_FLAG_C;
-	else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
-		ret = pmnc & ARMV7_FLAG_P(counter);
-	else
+	if (!armv7_pmnc_counter_valid(idx)) {
 		pr_err("CPU%u checking wrong counter %d overflow status\n",
-			smp_processor_id(), counter);
+			smp_processor_id(), idx);
+	} else {
+		counter = ARMV7_IDX_TO_COUNTER(idx);
+		ret = pmnc & BIT(counter);
+	}
 
 	return ret;
 }
 
-static inline int armv7_pmnc_select_counter(unsigned int idx)
+static inline int armv7_pmnc_select_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
-		pr_err("CPU%u selecting wrong PMNC counter"
-			" %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u selecting wrong PMNC counter %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
-	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter));
 	isb();
 
 	return idx;
@@ -812,124 +789,95 @@ static inline int armv7_pmnc_select_counter(unsigned int idx)
 
 static inline u32 armv7pmu_read_counter(int idx)
 {
-	unsigned long value = 0;
+	u32 value = 0;
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
-	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-		if (armv7_pmnc_select_counter(idx) == idx)
-			asm volatile("mrc p15, 0, %0, c9, c13, 2"
-				     : "=r" (value));
-	} else
+	if (!armv7_pmnc_counter_valid(idx))
 		pr_err("CPU%u reading wrong counter %d\n",
 			smp_processor_id(), idx);
+	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
+	else if (armv7_pmnc_select_counter(idx) == idx)
+		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value));
 
 	return value;
 }
 
 static inline void armv7pmu_write_counter(int idx, u32 value)
 {
-	if (idx == ARMV7_CYCLE_COUNTER)
-		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
-	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-		if (armv7_pmnc_select_counter(idx) == idx)
-			asm volatile("mcr p15, 0, %0, c9, c13, 2"
-				     : : "r" (value));
-	} else
+	if (!armv7_pmnc_counter_valid(idx))
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
+	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+	else if (armv7_pmnc_select_counter(idx) == idx)
+		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
 }
 
-static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
+static inline void armv7_pmnc_write_evtsel(int idx, u32 val)
 {
 	if (armv7_pmnc_select_counter(idx) == idx) {
-		val &= ARMV7_EVTSEL_MASK;
+		val &= ARMV7_EVTYPE_MASK;
 		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
 	}
 }
 
-static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
+static inline int armv7_pmnc_enable_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u enabling wrong PMNC counter"
-			" %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u enabling wrong PMNC counter %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_CNTENS_C;
-	else
-		val = ARMV7_CNTENS_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter)));
 	return idx;
 }
 
-static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
+static inline int armv7_pmnc_disable_counter(int idx)
 {
-	u32 val;
-
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u disabling wrong PMNC counter"
-			" %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u disabling wrong PMNC counter %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_CNTENC_C;
-	else
-		val = ARMV7_CNTENC_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter)));
 	return idx;
 }
 
-static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
+static inline int armv7_pmnc_enable_intens(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u enabling wrong PMNC counter"
-			" interrupt enable %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_INTENS_C;
-	else
-		val = ARMV7_INTENS_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter)));
 	return idx;
 }
 
-static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
+static inline int armv7_pmnc_disable_intens(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-		pr_err("CPU%u disabling wrong PMNC counter"
-			" interrupt enable %d\n", smp_processor_id(), idx);
-		return -1;
+	if (!armv7_pmnc_counter_valid(idx)) {
+		pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n",
+			smp_processor_id(), idx);
+		return -EINVAL;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
-		val = ARMV7_INTENC_C;
-	else
-		val = ARMV7_INTENC_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
-
+	counter = ARMV7_IDX_TO_COUNTER(idx);
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
 	return idx;
 }
 
@@ -973,14 +921,14 @@ static void armv7_pmnc_dump_regs(void)
 	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
 	printk(KERN_INFO "CCNT  =0x%08x\n", val);
 
-	for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
+	for (cnt = ARMV7_IDX_COUNTER0; cnt <= ARMV7_IDX_COUNTER_LAST; cnt++) {
 		armv7_pmnc_select_counter(cnt);
 		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
 		printk(KERN_INFO "CNT[%d] count =0x%08x\n",
-			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+			ARMV7_IDX_TO_COUNTER(cnt), val);
 		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
 		printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
-			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+			ARMV7_IDX_TO_COUNTER(cnt), val);
 	}
 }
 #endif
@@ -988,12 +936,13 @@ static void armv7_pmnc_dump_regs(void)
 static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -1002,9 +951,10 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 
 	/*
 	 * Set event (if destined for PMNx counters)
-	 * We don't need to set the event if it's a cycle count
+	 * We only need to set the event for the cycle counter if we
+	 * have the ability to perform event filtering.
 	 */
-	if (idx != ARMV7_CYCLE_COUNTER)
+	if (armv7pmu.set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER)
 		armv7_pmnc_write_evtsel(idx, hwc->config_base);
 
 	/*
@@ -1017,17 +967,18 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 	 */
 	armv7_pmnc_enable_counter(idx);
 
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
 	 * Disable counter and interrupt
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -1039,14 +990,14 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	 */
 	armv7_pmnc_disable_intens(idx);
 
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 {
-	unsigned long pmnc;
+	u32 pmnc;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -1069,13 +1020,10 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		/*
 		 * We have a single interrupt for all counters. Check that
 		 * each counter has overflowed before we process it.
@@ -1090,7 +1038,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	/*
@@ -1108,61 +1056,114 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 static void armv7pmu_start(void)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Enable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_stop(void)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Disable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
+static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				  struct hw_perf_event *event)
 {
 	int idx;
+	unsigned long evtype = event->config_base & ARMV7_EVTYPE_EVENT;
 
 	/* Always place a cycle counter into the cycle counter. */
-	if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
-		if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
+	if (evtype == ARMV7_PERFCTR_CPU_CYCLES) {
+		if (test_and_set_bit(ARMV7_IDX_CYCLE_COUNTER, cpuc->used_mask))
 			return -EAGAIN;
 
-		return ARMV7_CYCLE_COUNTER;
-	} else {
-		/*
-		 * For anything other than a cycle counter, try and use
-		 * the events counters
-		 */
-		for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
-			if (!test_and_set_bit(idx, cpuc->used_mask))
-				return idx;
-		}
+		return ARMV7_IDX_CYCLE_COUNTER;
+	}
 
-		/* The counters are all in use. */
-		return -EAGAIN;
+	/*
+	 * For anything other than a cycle counter, try and use
+	 * the events counters
+	 */
+	for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
+		if (!test_and_set_bit(idx, cpuc->used_mask))
+			return idx;
 	}
+
+	/* The counters are all in use. */
+	return -EAGAIN;
+}
+
+/*
+ * Add an event filter to a given event. This will only work for PMUv2 PMUs.
+ */
+static int armv7pmu_set_event_filter(struct hw_perf_event *event,
+				     struct perf_event_attr *attr)
+{
+	unsigned long config_base = 0;
+
+	if (attr->exclude_idle)
+		return -EPERM;
+	if (attr->exclude_user)
+		config_base |= ARMV7_EXCLUDE_USER;
+	if (attr->exclude_kernel)
+		config_base |= ARMV7_EXCLUDE_PL1;
+	if (!attr->exclude_hv)
+		config_base |= ARMV7_INCLUDE_HYP;
+
+	/*
+	 * Install the filter into config_base as this is used to
+	 * construct the event type.
+	 */
+	event->config_base = config_base;
+
+	return 0;
 }
 
 static void armv7pmu_reset(void *info)
 {
-	u32 idx, nb_cnt = armpmu->num_events;
+	u32 idx, nb_cnt = cpu_pmu->num_events;
 
 	/* The counter and interrupt enable registers are unknown at reset. */
-	for (idx = 1; idx < nb_cnt; ++idx)
+	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx)
 		armv7pmu_disable_event(NULL, idx);
 
 	/* Initialize & Reset PMNC: C and P bits */
 	armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
 }
 
+static int armv7_a8_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a8_perf_map,
+				&armv7_a8_perf_cache_map, 0xFF);
+}
+
+static int armv7_a9_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a9_perf_map,
+				&armv7_a9_perf_cache_map, 0xFF);
+}
+
+static int armv7_a5_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a5_perf_map,
+				&armv7_a5_perf_cache_map, 0xFF);
+}
+
+static int armv7_a15_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a15_perf_map,
+				&armv7_a15_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
@@ -1173,7 +1174,6 @@ static struct arm_pmu armv7pmu = {
 	.start			= armv7pmu_start,
 	.stop			= armv7pmu_stop,
 	.reset			= armv7pmu_reset,
-	.raw_event_mask		= 0xFF,
 	.max_period		= (1LLU << 32) - 1,
 };
 
@@ -1188,62 +1188,59 @@ static u32 __init armv7_read_num_pmnc_events(void)
 	return nb_cnt + 1;
 }
 
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA8;
 	armv7pmu.name		= "ARMv7 Cortex-A8";
-	armv7pmu.cache_map	= &armv7_a8_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a8_perf_map;
+	armv7pmu.map_event	= armv7_a8_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA9;
 	armv7pmu.name		= "ARMv7 Cortex-A9";
-	armv7pmu.cache_map	= &armv7_a9_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a9_perf_map;
+	armv7pmu.map_event	= armv7_a9_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA5;
 	armv7pmu.name		= "ARMv7 Cortex-A5";
-	armv7pmu.cache_map	= &armv7_a5_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a5_perf_map;
+	armv7pmu.map_event	= armv7_a5_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA15;
 	armv7pmu.name		= "ARMv7 Cortex-A15";
-	armv7pmu.cache_map	= &armv7_a15_perf_cache_map;
-	armv7pmu.event_map	= &armv7_a15_perf_map;
+	armv7pmu.map_event	= armv7_a15_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
 #else
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 3c4397491d08..e0cca10a8411 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -40,7 +40,7 @@ enum xscale_perf_types {
 };
 
 enum xscale_counters {
-	XSCALE_CYCLE_COUNTER	= 1,
+	XSCALE_CYCLE_COUNTER	= 0,
 	XSCALE_COUNTER0,
 	XSCALE_COUNTER1,
 	XSCALE_COUNTER2,
@@ -222,7 +222,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 {
 	unsigned long pmnc;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -249,13 +249,10 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
@@ -266,7 +263,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	irq_work_run();
@@ -284,6 +281,7 @@ static void
 xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
@@ -305,18 +303,19 @@ xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
@@ -336,16 +335,16 @@ xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
+xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc,
 			struct hw_perf_event *event)
 {
 	if (XSCALE_PERFCTR_CCNT == event->config_base) {
@@ -368,24 +367,26 @@ static void
 xscale1pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val |= XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale1pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u32
@@ -424,7 +425,13 @@ xscale1pmu_write_counter(int counter, u32 val)
 	}
 }
 
-static const struct arm_pmu xscale1pmu = {
+static int xscale_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &xscale_perf_map,
+				&xscale_perf_cache_map, 0xFF);
+}
+
+static struct arm_pmu xscale1pmu = {
 	.id		= ARM_PERF_PMU_ID_XSCALE1,
 	.name		= "xscale1",
 	.handle_irq	= xscale1pmu_handle_irq,
@@ -435,14 +442,12 @@ static const struct arm_pmu xscale1pmu = {
 	.get_event_idx	= xscale1pmu_get_event_idx,
 	.start		= xscale1pmu_start,
 	.stop		= xscale1pmu_stop,
-	.cache_map	= &xscale_perf_cache_map,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
+	.map_event	= xscale_map_event,
 	.num_events	= 3,
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__init xscale1pmu_init(void)
 {
 	return &xscale1pmu;
 }
@@ -560,7 +565,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 {
 	unsigned long pmnc, of_flags;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -581,13 +586,10 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
@@ -598,7 +600,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	irq_work_run();
@@ -616,6 +618,7 @@ static void
 xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags, ien, evtsel;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
 	evtsel = xscale2pmu_read_event_select();
@@ -649,16 +652,17 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags, ien, evtsel;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
 	evtsel = xscale2pmu_read_event_select();
@@ -692,14 +696,14 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
+xscale2pmu_get_event_idx(struct pmu_hw_events *cpuc,
 			struct hw_perf_event *event)
 {
 	int idx = xscale1pmu_get_event_idx(cpuc, event);
@@ -718,24 +722,26 @@ static void
 xscale2pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
 	val |= XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale2pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u32
@@ -786,7 +792,7 @@ xscale2pmu_write_counter(int counter, u32 val)
 	}
 }
 
-static const struct arm_pmu xscale2pmu = {
+static struct arm_pmu xscale2pmu = {
 	.id		= ARM_PERF_PMU_ID_XSCALE2,
 	.name		= "xscale2",
 	.handle_irq	= xscale2pmu_handle_irq,
@@ -797,24 +803,22 @@ static const struct arm_pmu xscale2pmu = {
 	.get_event_idx	= xscale2pmu_get_event_idx,
 	.start		= xscale2pmu_start,
 	.stop		= xscale2pmu_stop,
-	.cache_map	= &xscale_perf_cache_map,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
+	.map_event	= xscale_map_event,
 	.num_events	= 5,
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__init xscale2pmu_init(void)
 {
 	return &xscale2pmu;
 }
 #else
-static const struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__init xscale1pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__init xscale2pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
index 2b70709376c3..2c3407ee8576 100644
--- a/arch/arm/kernel/pmu.c
+++ b/arch/arm/kernel/pmu.c
@@ -10,192 +10,26 @@
  *
  */
 
-#define pr_fmt(fmt) "PMU: " fmt
-
-#include <linux/cpumask.h>
 #include <linux/err.h>
-#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 #include <asm/pmu.h>
 
-static volatile long pmu_lock;
-
-static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES];
-
-static int __devinit pmu_register(struct platform_device *pdev,
-					enum arm_pmu_type type)
-{
-	if (type < 0 || type >= ARM_NUM_PMU_DEVICES) {
-		pr_warning("received registration request for unknown "
-				"device %d\n", type);
-		return -EINVAL;
-	}
-
-	if (pmu_devices[type]) {
-		pr_warning("rejecting duplicate registration of PMU device "
-			"type %d.", type);
-		return -ENOSPC;
-	}
-
-	pr_info("registered new PMU device of type %d\n", type);
-	pmu_devices[type] = pdev;
-	return 0;
-}
-
-#define OF_MATCH_PMU(_name, _type) {	\
-	.compatible = _name,		\
-	.data = (void *)_type,		\
-}
-
-#define OF_MATCH_CPU(name)	OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU)
-
-static struct of_device_id armpmu_of_device_ids[] = {
-	OF_MATCH_CPU("arm,cortex-a9-pmu"),
-	OF_MATCH_CPU("arm,cortex-a8-pmu"),
-	OF_MATCH_CPU("arm,arm1136-pmu"),
-	OF_MATCH_CPU("arm,arm1176-pmu"),
-	{},
-};
-
-#define PLAT_MATCH_PMU(_name, _type) {	\
-	.name		= _name,	\
-	.driver_data	= _type,	\
-}
-
-#define PLAT_MATCH_CPU(_name)	PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU)
-
-static struct platform_device_id armpmu_plat_device_ids[] = {
-	PLAT_MATCH_CPU("arm-pmu"),
-	{},
-};
-
-enum arm_pmu_type armpmu_device_type(struct platform_device *pdev)
-{
-	const struct of_device_id	*of_id;
-	const struct platform_device_id *pdev_id;
-
-	/* provided by of_device_id table */
-	if (pdev->dev.of_node) {
-		of_id = of_match_device(armpmu_of_device_ids, &pdev->dev);
-		BUG_ON(!of_id);
-		return (enum arm_pmu_type)of_id->data;
-	}
-
-	/* Provided by platform_device_id table */
-	pdev_id = platform_get_device_id(pdev);
-	BUG_ON(!pdev_id);
-	return pdev_id->driver_data;
-}
-
-static int __devinit armpmu_device_probe(struct platform_device *pdev)
-{
-	return pmu_register(pdev, armpmu_device_type(pdev));
-}
-
-static struct platform_driver armpmu_driver = {
-	.driver		= {
-		.name	= "arm-pmu",
-		.of_match_table = armpmu_of_device_ids,
-	},
-	.probe		= armpmu_device_probe,
-	.id_table	= armpmu_plat_device_ids,
-};
-
-static int __init register_pmu_driver(void)
-{
-	return platform_driver_register(&armpmu_driver);
-}
-device_initcall(register_pmu_driver);
-
-struct platform_device *
-reserve_pmu(enum arm_pmu_type device)
-{
-	struct platform_device *pdev;
-
-	if (test_and_set_bit_lock(device, &pmu_lock)) {
-		pdev = ERR_PTR(-EBUSY);
-	} else if (pmu_devices[device] == NULL) {
-		clear_bit_unlock(device, &pmu_lock);
-		pdev = ERR_PTR(-ENODEV);
-	} else {
-		pdev = pmu_devices[device];
-	}
-
-	return pdev;
-}
-EXPORT_SYMBOL_GPL(reserve_pmu);
+/*
+ * PMU locking to ensure mutual exclusion between different subsystems.
+ */
+static unsigned long pmu_lock[BITS_TO_LONGS(ARM_NUM_PMU_DEVICES)];
 
 int
-release_pmu(enum arm_pmu_type device)
-{
-	if (WARN_ON(!pmu_devices[device]))
-		return -EINVAL;
-	clear_bit_unlock(device, &pmu_lock);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(release_pmu);
-
-static int
-set_irq_affinity(int irq,
-		 unsigned int cpu)
+reserve_pmu(enum arm_pmu_type type)
 {
-#ifdef CONFIG_SMP
-	int err = irq_set_affinity(irq, cpumask_of(cpu));
-	if (err)
-		pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-			   irq, cpu);
-	return err;
-#else
-	return -EINVAL;
-#endif
-}
-
-static int
-init_cpu_pmu(void)
-{
-	int i, irqs, err = 0;
-	struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU];
-
-	if (!pdev)
-		return -ENODEV;
-
-	irqs = pdev->num_resources;
-
-	/*
-	 * If we have a single PMU interrupt that we can't shift, assume that
-	 * we're running on a uniprocessor machine and continue.
-	 */
-	if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0)))
-		return 0;
-
-	for (i = 0; i < irqs; ++i) {
-		err = set_irq_affinity(platform_get_irq(pdev, i), i);
-		if (err)
-			break;
-	}
-
-	return err;
+	return test_and_set_bit_lock(type, pmu_lock) ? -EBUSY : 0;
 }
+EXPORT_SYMBOL_GPL(reserve_pmu);
 
-int
-init_pmu(enum arm_pmu_type device)
+void
+release_pmu(enum arm_pmu_type type)
 {
-	int err = 0;
-
-	switch (device) {
-	case ARM_PMU_DEVICE_CPU:
-		err = init_cpu_pmu();
-		break;
-	default:
-		pr_warning("attempt to initialise unknown device %d\n",
-				device);
-		err = -EINVAL;
-	}
-
-	return err;
+	clear_bit_unlock(type, pmu_lock);
 }
-EXPORT_SYMBOL_GPL(init_pmu);
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 9cf4cbf8f95b..d0cdedf4864d 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -57,7 +57,8 @@ relocate_new_kernel:
 	mov r0,#0
 	ldr r1,kexec_mach_type
 	ldr r2,kexec_boot_atags
-	mov pc,lr
+ ARM(	mov pc, lr	)
+ THUMB(	bx lr		)
 
 	.align
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 78d197d6ec34..6136144f8f8d 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -280,18 +280,19 @@ static void __init cacheid_init(void)
 	if (arch >= CPU_ARCH_ARMv6) {
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
+			arch = CPU_ARCH_ARMv7;
 			cacheid = CACHEID_VIPT_NONALIASING;
 			if ((cachetype & (3 << 14)) == 1 << 14)
 				cacheid |= CACHEID_ASID_TAGGED;
-			else if (cpu_has_aliasing_icache(CPU_ARCH_ARMv7))
-				cacheid |= CACHEID_VIPT_I_ALIASING;
-		} else if (cachetype & (1 << 23)) {
-			cacheid = CACHEID_VIPT_ALIASING;
 		} else {
-			cacheid = CACHEID_VIPT_NONALIASING;
-			if (cpu_has_aliasing_icache(CPU_ARCH_ARMv6))
-				cacheid |= CACHEID_VIPT_I_ALIASING;
+			arch = CPU_ARCH_ARMv6;
+			if (cachetype & (1 << 23))
+				cacheid = CACHEID_VIPT_ALIASING;
+			else
+				cacheid = CACHEID_VIPT_NONALIASING;
 		}
+		if (cpu_has_aliasing_icache(arch))
+			cacheid |= CACHEID_VIPT_I_ALIASING;
 	} else {
 		cacheid = CACHEID_VIVT;
 	}
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 2c277d40cee6..01c186222f3b 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -137,8 +137,8 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk);
 	clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
 
+	clockevents_register_device(clk);
+
 	/* Make sure our local interrupt controller has this enabled */
 	gic_enable_ppi(clk->irq);
-
-	clockevents_register_device(clk);
 }
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index d522b47e30b5..6c8e3b5f669f 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -157,7 +157,7 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
-	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
diff --git a/arch/arm/mach-ep93xx/include/mach/ts72xx.h b/arch/arm/mach-ep93xx/include/mach/ts72xx.h
index 0eabec62cd9d..f1397a13e76b 100644
--- a/arch/arm/mach-ep93xx/include/mach/ts72xx.h
+++ b/arch/arm/mach-ep93xx/include/mach/ts72xx.h
@@ -6,7 +6,7 @@
  * TS72xx memory map:
  *
  * virt		phys		size
- * febff000	22000000	4K	model number register
+ * febff000	22000000	4K	model number register (bits 0-2)
  * febfe000	22400000	4K	options register
  * febfd000	22800000	4K	options register #2
  * febf9000	10800000	4K	TS-5620 RTC index register
@@ -20,6 +20,9 @@
 #define TS72XX_MODEL_TS7200		0x00
 #define TS72XX_MODEL_TS7250		0x01
 #define TS72XX_MODEL_TS7260		0x02
+#define TS72XX_MODEL_TS7300		0x03
+#define TS72XX_MODEL_TS7400		0x04
+#define TS72XX_MODEL_MASK		0x07
 
 
 #define TS72XX_OPTIONS_PHYS_BASE	0x22400000
@@ -51,19 +54,34 @@
 
 #ifndef __ASSEMBLY__
 
+static inline int ts72xx_model(void)
+{
+	return __raw_readb(TS72XX_MODEL_VIRT_BASE) & TS72XX_MODEL_MASK;
+}
+
 static inline int board_is_ts7200(void)
 {
-	return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7200;
+	return ts72xx_model() == TS72XX_MODEL_TS7200;
 }
 
 static inline int board_is_ts7250(void)
 {
-	return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7250;
+	return ts72xx_model() == TS72XX_MODEL_TS7250;
 }
 
 static inline int board_is_ts7260(void)
 {
-	return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7260;
+	return ts72xx_model() == TS72XX_MODEL_TS7260;
+}
+
+static inline int board_is_ts7300(void)
+{
+	return ts72xx_model()  == TS72XX_MODEL_TS7300;
+}
+
+static inline int board_is_ts7400(void)
+{
+	return ts72xx_model() == TS72XX_MODEL_TS7400;
 }
 
 static inline int is_max197_installed(void)
diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c
index 851dea018578..1561b036a9bf 100644
--- a/arch/arm/mach-exynos4/clock.c
+++ b/arch/arm/mach-exynos4/clock.c
@@ -520,7 +520,7 @@ static struct clk init_clocks_off[] = {
 		.ctrlbit	= (1 << 21),
 	}, {
 		.name		= "ac97",
-		.id		= -1,
+		.devname	= "samsung-ac97",
 		.enable		= exynos4_clk_ip_peril_ctrl,
 		.ctrlbit	= (1 << 27),
 	}, {
diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c
index 2d8a40c9e6e5..746d6fc6d397 100644
--- a/arch/arm/mach-exynos4/cpu.c
+++ b/arch/arm/mach-exynos4/cpu.c
@@ -24,12 +24,13 @@
 #include <plat/exynos4.h>
 #include <plat/adc-core.h>
 #include <plat/sdhci.h>
-#include <plat/devs.h>
 #include <plat/fb-core.h>
 #include <plat/fimc-core.h>
 #include <plat/iic-core.h>
+#include <plat/reset.h>
 
 #include <mach/regs-irq.h>
+#include <mach/regs-pmu.h>
 
 extern int combiner_init(unsigned int combiner_nr, void __iomem *base,
 			 unsigned int irq_start);
@@ -128,6 +129,11 @@ static void exynos4_idle(void)
 	local_irq_enable();
 }
 
+static void exynos4_sw_reset(void)
+{
+	__raw_writel(0x1, S5P_SWRESET);
+}
+
 /*
  * exynos4_map_io
  *
@@ -241,5 +247,8 @@ int __init exynos4_init(void)
 	/* set idle function */
 	pm_idle = exynos4_idle;
 
+	/* set sw_reset function */
+	s5p_reset_hook = exynos4_sw_reset;
+
 	return sysdev_register(&exynos4_sysdev);
 }
diff --git a/arch/arm/mach-exynos4/include/mach/irqs.h b/arch/arm/mach-exynos4/include/mach/irqs.h
index 934d2a493982..f8952f8f3757 100644
--- a/arch/arm/mach-exynos4/include/mach/irqs.h
+++ b/arch/arm/mach-exynos4/include/mach/irqs.h
@@ -80,9 +80,8 @@
 #define IRQ_HSMMC3		IRQ_SPI(76)
 #define IRQ_DWMCI		IRQ_SPI(77)
 
-#define IRQ_MIPICSI0		IRQ_SPI(78)
-
-#define IRQ_MIPICSI1		IRQ_SPI(80)
+#define IRQ_MIPI_CSIS0		IRQ_SPI(78)
+#define IRQ_MIPI_CSIS1		IRQ_SPI(80)
 
 #define IRQ_ONENAND_AUDI	IRQ_SPI(82)
 #define IRQ_ROTATOR		IRQ_SPI(83)
diff --git a/arch/arm/mach-exynos4/include/mach/regs-pmu.h b/arch/arm/mach-exynos4/include/mach/regs-pmu.h
index fa49bbb8e7b0..cdf9b47c303c 100644
--- a/arch/arm/mach-exynos4/include/mach/regs-pmu.h
+++ b/arch/arm/mach-exynos4/include/mach/regs-pmu.h
@@ -29,6 +29,8 @@
 #define S5P_USE_STANDBY_WFE1			(1 << 25)
 #define S5P_USE_MASK				((0x3 << 16) | (0x3 << 24))
 
+#define S5P_SWRESET				S5P_PMUREG(0x0400)
+
 #define S5P_WAKEUP_STAT				S5P_PMUREG(0x0600)
 #define S5P_EINT_WAKEUP_MASK			S5P_PMUREG(0x0604)
 #define S5P_WAKEUP_MASK				S5P_PMUREG(0x0608)
diff --git a/arch/arm/mach-exynos4/irq-eint.c b/arch/arm/mach-exynos4/irq-eint.c
index 9d87d2ac7f68..badb8c66fc9b 100644
--- a/arch/arm/mach-exynos4/irq-eint.c
+++ b/arch/arm/mach-exynos4/irq-eint.c
@@ -23,6 +23,8 @@
 
 #include <mach/regs-gpio.h>
 
+#include <asm/mach/irq.h>
+
 static DEFINE_SPINLOCK(eint_lock);
 
 static unsigned int eint0_15_data[16];
@@ -184,8 +186,11 @@ static inline void exynos4_irq_demux_eint(unsigned int start)
 
 static void exynos4_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_get_chip(irq);
+	chained_irq_enter(chip, desc);
 	exynos4_irq_demux_eint(IRQ_EINT(16));
 	exynos4_irq_demux_eint(IRQ_EINT(24));
+	chained_irq_exit(chip, desc);
 }
 
 static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
@@ -193,6 +198,7 @@ static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
 	u32 *irq_data = irq_get_handler_data(irq);
 	struct irq_chip *chip = irq_get_chip(irq);
 
+	chained_irq_enter(chip, desc);
 	chip->irq_mask(&desc->irq_data);
 
 	if (chip->irq_ack)
@@ -201,6 +207,7 @@ static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
 	generic_handle_irq(*irq_data);
 
 	chip->irq_unmask(&desc->irq_data);
+	chained_irq_exit(chip, desc);
 }
 
 int __init exynos4_init_irq_eint(void)
diff --git a/arch/arm/mach-exynos4/mach-universal_c210.c b/arch/arm/mach-exynos4/mach-universal_c210.c
index d7ec84d586f2..2aac6f755c8e 100644
--- a/arch/arm/mach-exynos4/mach-universal_c210.c
+++ b/arch/arm/mach-exynos4/mach-universal_c210.c
@@ -79,7 +79,7 @@ static struct s3c2410_uartcfg universal_uartcfgs[] __initdata = {
 };
 
 static struct regulator_consumer_supply max8952_consumer =
-	REGULATOR_SUPPLY("vddarm", NULL);
+	REGULATOR_SUPPLY("vdd_arm", NULL);
 
 static struct max8952_platform_data universal_max8952_pdata __initdata = {
 	.gpio_vid0	= EXYNOS4_GPX0(3),
@@ -105,7 +105,7 @@ static struct max8952_platform_data universal_max8952_pdata __initdata = {
 };
 
 static struct regulator_consumer_supply lp3974_buck1_consumer =
-	REGULATOR_SUPPLY("vddint", NULL);
+	REGULATOR_SUPPLY("vdd_int", NULL);
 
 static struct regulator_consumer_supply lp3974_buck2_consumer =
 	REGULATOR_SUPPLY("vddg3d", NULL);
diff --git a/arch/arm/mach-exynos4/setup-usb-phy.c b/arch/arm/mach-exynos4/setup-usb-phy.c
index 0883c1b824b9..39aca045f660 100644
--- a/arch/arm/mach-exynos4/setup-usb-phy.c
+++ b/arch/arm/mach-exynos4/setup-usb-phy.c
@@ -82,7 +82,7 @@ static int exynos4_usb_phy1_init(struct platform_device *pdev)
 
 	rstcon &= ~(HOST_LINK_PORT_SWRST_MASK | PHY1_SWRST_MASK);
 	writel(rstcon, EXYNOS4_RSTCON);
-	udelay(50);
+	udelay(80);
 
 	clk_disable(otg_clk);
 	clk_put(otg_clk);
diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig
index dc26fff22cf0..c8e7afcf14ec 100644
--- a/arch/arm/mach-footbridge/Kconfig
+++ b/arch/arm/mach-footbridge/Kconfig
@@ -62,6 +62,7 @@ config ARCH_EBSA285_HOST
 config ARCH_NETWINDER
 	bool "NetWinder"
 	select CLKSRC_I8253
+	select CLKEVT_I8253
 	select FOOTBRIDGE_HOST
 	select ISA
 	select ISA_DMA
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index 1331fff51ae2..18c32a5541d9 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -18,6 +18,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <video/vga.h>
 
 #include <asm/irq.h>
 #include <asm/system.h>
diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c
index 881add0fbe5b..b1ec2cf53bb0 100644
--- a/arch/arm/mach-imx/mach-cpuimx27.c
+++ b/arch/arm/mach-imx/mach-cpuimx27.c
@@ -310,7 +310,7 @@ static struct sys_timer eukrea_cpuimx27_timer = {
 	.init = eukrea_cpuimx27_timer_init,
 };
 
-MACHINE_START(CPUIMX27, "EUKREA CPUIMX27")
+MACHINE_START(EUKREA_CPUIMX27, "EUKREA CPUIMX27")
 	.atag_offset = 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
diff --git a/arch/arm/mach-imx/mach-cpuimx35.c b/arch/arm/mach-imx/mach-cpuimx35.c
index 10b89139da48..470b654b0e6e 100644
--- a/arch/arm/mach-imx/mach-cpuimx35.c
+++ b/arch/arm/mach-imx/mach-cpuimx35.c
@@ -192,7 +192,7 @@ struct sys_timer eukrea_cpuimx35_timer = {
 	.init	= eukrea_cpuimx35_timer_init,
 };
 
-MACHINE_START(EUKREA_CPUIMX35, "Eukrea CPUIMX35")
+MACHINE_START(EUKREA_CPUIMX35SD, "Eukrea CPUIMX35")
 	/* Maintainer: Eukrea Electromatique */
 	.atag_offset = 0x100,
 	.map_io = mx35_map_io,
diff --git a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
index d8699b54268d..9163318e95a2 100644
--- a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
+++ b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
@@ -161,7 +161,7 @@ static struct sys_timer eukrea_cpuimx25_timer = {
 	.init   = eukrea_cpuimx25_timer_init,
 };
 
-MACHINE_START(EUKREA_CPUIMX25, "Eukrea CPUIMX25")
+MACHINE_START(EUKREA_CPUIMX25SD, "Eukrea CPUIMX25")
 	/* Maintainer: Eukrea Electromatique */
 	.atag_offset = 0x100,
 	.map_io = mx25_map_io,
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index e25f60f5db8f..9e5c1663fc4f 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -77,7 +77,7 @@ static int __init dns323_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	/*
 	 * Check for devices with hard-wired IRQs.
 	 */
-	irq = orion5x_pci_map_irq(const dev, slot, pin);
+	irq = orion5x_pci_map_irq(dev, slot, pin);
 	if (irq != -1)
 		return irq;
 
diff --git a/arch/arm/mach-orion5x/pci.c b/arch/arm/mach-orion5x/pci.c
index 28b8760ab9fa..bc4a920e26ee 100644
--- a/arch/arm/mach-orion5x/pci.c
+++ b/arch/arm/mach-orion5x/pci.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/mbus.h>
+#include <video/vga.h>
 #include <asm/irq.h>
 #include <asm/mach/pci.h>
 #include <plat/pcie.h>
diff --git a/arch/arm/mach-realview/include/mach/system.h b/arch/arm/mach-realview/include/mach/system.h
index a30f2e3ec178..6657ff231161 100644
--- a/arch/arm/mach-realview/include/mach/system.h
+++ b/arch/arm/mach-realview/include/mach/system.h
@@ -44,6 +44,7 @@ static inline void arch_reset(char mode, const char *cmd)
 	 */
 	if (realview_reset)
 		realview_reset(mode);
+	dsb();
 }
 
 #endif
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index 8bad64370689..055e2858b0dd 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -16,6 +16,7 @@
 #include <linux/suspend.h>
 #include <linux/serial_core.h>
 #include <linux/io.h>
+#include <linux/gpio.h>
 
 #include <mach/map.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-s5p64x0/irq-eint.c b/arch/arm/mach-s5p64x0/irq-eint.c
index 69ed4545112b..fe7380f5c3cd 100644
--- a/arch/arm/mach-s5p64x0/irq-eint.c
+++ b/arch/arm/mach-s5p64x0/irq-eint.c
@@ -129,7 +129,7 @@ static int s5p64x0_alloc_gc(void)
 	}
 
 	ct = gc->chip_types;
-	ct->chip.irq_ack = irq_gc_ack;
+	ct->chip.irq_ack = irq_gc_ack_set_bit;
 	ct->chip.irq_mask = irq_gc_mask_set_bit;
 	ct->chip.irq_unmask = irq_gc_mask_clr_bit;
 	ct->chip.irq_set_type = s5p64x0_irq_eint_set_type;
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index 309e388a8a83..f149d278377b 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -88,7 +88,7 @@ static struct sleep_save s5pv210_core_save[] = {
 	SAVE_ITEM(S3C2410_TCNTO(0)),
 };
 
-void s5pv210_cpu_suspend(unsigned long arg)
+static int s5pv210_cpu_suspend(unsigned long arg)
 {
 	unsigned long tmp;
 
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index 167a67c5ca54..5fde49da399a 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -342,6 +342,7 @@ static struct platform_device mipidsi0_device = {
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED,
 	.tmio_ocr_mask	= MMC_VDD_27_28 | MMC_VDD_28_29,
 };
@@ -383,7 +384,7 @@ void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
 }
 
 static struct sh_mobile_sdhi_info sh_sdhi1_info = {
-	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT,
 	.tmio_caps	= MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ,
 	.tmio_ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
 	.set_pwr	= ag5evm_sdhi1_set_pwr,
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index e7c5379069ef..de2253d7f157 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -642,6 +642,8 @@ static struct usbhs_private usbhs0_private = {
 		},
 		.driver_param = {
 			.buswait_bwait	= 4,
+			.d0_tx_id	= SHDMA_SLAVE_USB0_TX,
+			.d1_rx_id	= SHDMA_SLAVE_USB0_RX,
 		},
 	},
 };
@@ -811,6 +813,8 @@ static struct usbhs_private usbhs1_private = {
 			.buswait_bwait	= 4,
 			.pipe_type	= usbhs1_pipe_cfg,
 			.pipe_size	= ARRAY_SIZE(usbhs1_pipe_cfg),
+			.d0_tx_id	= SHDMA_SLAVE_USB1_TX,
+			.d1_rx_id	= SHDMA_SLAVE_USB1_RX,
 		},
 	},
 };
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index e6e11e4e2d43..66975921e646 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -503,16 +503,17 @@ static struct clk *late_main_clks[] = {
 	&sh7372_fsidivb_clk,
 };
 
-enum { MSTP001,
+enum { MSTP001, MSTP000,
        MSTP131, MSTP130,
        MSTP129, MSTP128, MSTP127, MSTP126, MSTP125,
        MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
-       MSTP218, MSTP217, MSTP216,
-       MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-       MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
-       MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403,
+       MSTP218, MSTP217, MSTP216, MSTP214, MSTP208, MSTP207,
+       MSTP206, MSTP205, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
+       MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
+       MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP407, MSTP406,
+       MSTP405, MSTP404, MSTP403, MSTP400,
        MSTP_NR };
 
 #define MSTP(_parent, _reg, _bit, _flags) \
@@ -520,6 +521,7 @@ enum { MSTP001,
 
 static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP001] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR0, 1, 0), /* IIC2 */
+	[MSTP000] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR0, 0, 0), /* MSIOF0 */
 	[MSTP131] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 31, 0), /* VEU3 */
 	[MSTP130] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 30, 0), /* VEU2 */
 	[MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* VEU1 */
@@ -538,14 +540,16 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */
 	[MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */
 	[MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */
+	[MSTP214] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 14, 0), /* USBDMAC */
+	[MSTP208] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 8, 0), /* MSIOF1 */
 	[MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
 	[MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
+	[MSTP205] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 5, 0), /* MSIOF2 */
 	[MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
 	[MSTP203] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 3, 0), /* SCIFA1 */
 	[MSTP202] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 2, 0), /* SCIFA2 */
 	[MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */
 	[MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */
-	[MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
 	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSI2 */
 	[MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */
 	[MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */
@@ -557,8 +561,12 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP413] = MSTP(&pllc1_div2_clk, SMSTPCR4, 13, 0), /* HDMI */
 	[MSTP411] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 11, 0), /* IIC3 */
 	[MSTP410] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 10, 0), /* IIC4 */
+	[MSTP407] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 7, 0), /* USB-DMAC1 */
 	[MSTP406] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 6, 0), /* USB1 */
+	[MSTP405] = MSTP(&r_clk, SMSTPCR4, 5, 0), /* CMT4 */
+	[MSTP404] = MSTP(&r_clk, SMSTPCR4, 4, 0), /* CMT3 */
 	[MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */
+	[MSTP400] = MSTP(&r_clk, SMSTPCR4, 0, 0), /* CMT2 */
 };
 
 static struct clk_lookup lookups[] = {
@@ -609,6 +617,7 @@ static struct clk_lookup lookups[] = {
 
 	/* MSTP32 clocks */
 	CLKDEV_DEV_ID("i2c-sh_mobile.2", &mstp_clks[MSTP001]), /* IIC2 */
+	CLKDEV_DEV_ID("spi_sh_msiof.0", &mstp_clks[MSTP000]), /* MSIOF0 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.4", &mstp_clks[MSTP131]), /* VEU3 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.3", &mstp_clks[MSTP130]), /* VEU2 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.2", &mstp_clks[MSTP129]), /* VEU1 */
@@ -629,14 +638,16 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */
 	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */
 	CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */
+	CLKDEV_DEV_ID("sh-dma-engine.3", &mstp_clks[MSTP214]), /* USB-DMAC0 */
+	CLKDEV_DEV_ID("spi_sh_msiof.1", &mstp_clks[MSTP208]), /* MSIOF1 */
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
 	CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */
+	CLKDEV_DEV_ID("spi_sh_msiof.2", &mstp_clks[MSTP205]), /* MSIOF2 */
 	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
 	CLKDEV_DEV_ID("sh-sci.1", &mstp_clks[MSTP203]), /* SCIFA1 */
 	CLKDEV_DEV_ID("sh-sci.2", &mstp_clks[MSTP202]), /* SCIFA2 */
 	CLKDEV_DEV_ID("sh-sci.3", &mstp_clks[MSTP201]), /* SCIFA3 */
 	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP200]), /* SCIFA4 */
-	CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */
 	CLKDEV_DEV_ID("sh_fsi2", &mstp_clks[MSTP328]), /* FSI2 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* IIC1 */
 	CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP322]), /* USB0 */
@@ -650,10 +661,14 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-mobile-hdmi", &mstp_clks[MSTP413]), /* HDMI */
 	CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* IIC3 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* IIC4 */
+	CLKDEV_DEV_ID("sh-dma-engine.4", &mstp_clks[MSTP407]), /* USB-DMAC1 */
 	CLKDEV_DEV_ID("r8a66597_hcd.1", &mstp_clks[MSTP406]), /* USB1 */
 	CLKDEV_DEV_ID("r8a66597_udc.1", &mstp_clks[MSTP406]), /* USB1 */
 	CLKDEV_DEV_ID("renesas_usbhs.1", &mstp_clks[MSTP406]), /* USB1 */
+	CLKDEV_DEV_ID("sh_cmt.4", &mstp_clks[MSTP405]), /* CMT4 */
+	CLKDEV_DEV_ID("sh_cmt.3", &mstp_clks[MSTP404]), /* CMT3 */
 	CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
+	CLKDEV_DEV_ID("sh_cmt.2", &mstp_clks[MSTP400]), /* CMT2 */
 
 	CLKDEV_ICK_ID("hdmi", "sh_mobile_lcdc_fb.1",
 		      &div6_reparent_clks[DIV6_HDMI]),
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index 6db2ccabc2bf..61a846bb30f2 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -365,7 +365,7 @@ void __init sh73a0_clock_init(void)
 	__raw_writel(0x108, SD2CKCR);
 
 	/* detect main clock parent */
-	switch ((__raw_readl(CKSCR) >> 24) & 0x03) {
+	switch ((__raw_readl(CKSCR) >> 28) & 0x03) {
 	case 0:
 		main_clk.parent = &sh73a0_extal1_clk;
 		break;
diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h
index ce595cee86cd..24e63a85e669 100644
--- a/arch/arm/mach-shmobile/include/mach/sh7372.h
+++ b/arch/arm/mach-shmobile/include/mach/sh7372.h
@@ -459,6 +459,10 @@ enum {
 	SHDMA_SLAVE_SDHI2_TX,
 	SHDMA_SLAVE_MMCIF_RX,
 	SHDMA_SLAVE_MMCIF_TX,
+	SHDMA_SLAVE_USB0_TX,
+	SHDMA_SLAVE_USB0_RX,
+	SHDMA_SLAVE_USB1_TX,
+	SHDMA_SLAVE_USB1_RX,
 };
 
 extern struct clk sh7372_extal1_clk;
diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c
index 3b28743c77eb..739315e30eb9 100644
--- a/arch/arm/mach-shmobile/intc-sh7372.c
+++ b/arch/arm/mach-shmobile/intc-sh7372.c
@@ -379,7 +379,7 @@ enum {
 	/* BBIF2 */
 	VPU,
 	TSIF1,
-	_3DG_SGX530,
+	/* 3DG */
 	_2DDMAC,
 	IIC2_ALI2, IIC2_TACKI2, IIC2_WAITI2, IIC2_DTEI2,
 	IPMMU_IPMMUR, IPMMU_IPMMUR2,
@@ -436,7 +436,7 @@ static struct intc_vect intcs_vectors[] = {
 	/* BBIF2 */
 	INTCS_VECT(VPU, 0x980),
 	INTCS_VECT(TSIF1, 0x9a0),
-	INTCS_VECT(_3DG_SGX530, 0x9e0),
+	/* 3DG */
 	INTCS_VECT(_2DDMAC, 0xa00),
 	INTCS_VECT(IIC2_ALI2, 0xa80), INTCS_VECT(IIC2_TACKI2, 0xaa0),
 	INTCS_VECT(IIC2_WAITI2, 0xac0), INTCS_VECT(IIC2_DTEI2, 0xae0),
@@ -521,7 +521,7 @@ static struct intc_mask_reg intcs_mask_registers[] = {
 	    RTDMAC_1_DEI3, RTDMAC_1_DEI2, RTDMAC_1_DEI1, RTDMAC_1_DEI0 } },
 	{ 0xffd20198, 0xffd201d8, 8, /* IMR6SA / IMCR6SA */
 	  { 0, 0, MSIOF, 0,
-	    _3DG_SGX530, 0, 0, 0 } },
+	    0, 0, 0, 0 } },
 	{ 0xffd2019c, 0xffd201dc, 8, /* IMR7SA / IMCR7SA */
 	  { 0, TMU_TUNI2, TMU_TUNI1, TMU_TUNI0,
 	    0, 0, 0, 0 } },
@@ -561,7 +561,6 @@ static struct intc_prio_reg intcs_prio_registers[] = {
 					      TMU_TUNI2, TSIF1 } },
 	{ 0xffd2001c, 0, 16, 4, /* IPRHS */ { 0, 0, VEU, BEU } },
 	{ 0xffd20020, 0, 16, 4, /* IPRIS */ { 0, MSIOF, TSIF0, IIC0 } },
-	{ 0xffd20024, 0, 16, 4, /* IPRJS */ { 0, _3DG_SGX530, 0, 0 } },
 	{ 0xffd20028, 0, 16, 4, /* IPRKS */ { 0, 0, LMB, 0 } },
 	{ 0xffd2002c, 0, 16, 4, /* IPRLS */ { IPMMU, 0, 0, 0 } },
 	{ 0xffd20030, 0, 16, 4, /* IPRMS */ { IIC2, 0, 0, 0 } },
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index 79f0413d8725..2d9b1b1a2538 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -169,35 +169,35 @@ static struct platform_device scif6_device = {
 };
 
 /* CMT */
-static struct sh_timer_config cmt10_platform_data = {
-	.name = "CMT10",
-	.channel_offset = 0x10,
-	.timer_bit = 0,
+static struct sh_timer_config cmt2_platform_data = {
+	.name = "CMT2",
+	.channel_offset = 0x40,
+	.timer_bit = 5,
 	.clockevent_rating = 125,
 	.clocksource_rating = 125,
 };
 
-static struct resource cmt10_resources[] = {
+static struct resource cmt2_resources[] = {
 	[0] = {
-		.name	= "CMT10",
-		.start	= 0xe6138010,
-		.end	= 0xe613801b,
+		.name	= "CMT2",
+		.start	= 0xe6130040,
+		.end	= 0xe613004b,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= evt2irq(0x0b00), /* CMT1_CMT10 */
+		.start	= evt2irq(0x0b80), /* CMT2 */
 		.flags	= IORESOURCE_IRQ,
 	},
 };
 
-static struct platform_device cmt10_device = {
+static struct platform_device cmt2_device = {
 	.name		= "sh_cmt",
-	.id		= 10,
+	.id		= 2,
 	.dev = {
-		.platform_data	= &cmt10_platform_data,
+		.platform_data	= &cmt2_platform_data,
 	},
-	.resource	= cmt10_resources,
-	.num_resources	= ARRAY_SIZE(cmt10_resources),
+	.resource	= cmt2_resources,
+	.num_resources	= ARRAY_SIZE(cmt2_resources),
 };
 
 /* TMU */
@@ -602,6 +602,150 @@ static struct platform_device dma2_device = {
 	},
 };
 
+/*
+ * USB-DMAC
+ */
+
+unsigned int usbts_shift[] = {3, 4, 5};
+
+enum {
+	XMIT_SZ_8BYTE		= 0,
+	XMIT_SZ_16BYTE		= 1,
+	XMIT_SZ_32BYTE		= 2,
+};
+
+#define USBTS_INDEX2VAL(i) (((i) & 3) << 6)
+
+static const struct sh_dmae_channel sh7372_usb_dmae_channels[] = {
+	{
+		.offset = 0,
+	}, {
+		.offset = 0x20,
+	},
+};
+
+/* USB DMAC0 */
+static const struct sh_dmae_slave_config sh7372_usb_dmae0_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_USB0_TX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB0_RX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	},
+};
+
+static struct sh_dmae_pdata usb_dma0_platform_data = {
+	.slave		= sh7372_usb_dmae0_slaves,
+	.slave_num	= ARRAY_SIZE(sh7372_usb_dmae0_slaves),
+	.channel	= sh7372_usb_dmae_channels,
+	.channel_num	= ARRAY_SIZE(sh7372_usb_dmae_channels),
+	.ts_low_shift	= 6,
+	.ts_low_mask	= 0xc0,
+	.ts_high_shift	= 0,
+	.ts_high_mask	= 0,
+	.ts_shift	= usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(usbts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chcr_offset	= 0x14,
+	.chcr_ie_bit	= 1 << 5,
+	.dmaor_is_32bit	= 1,
+	.needs_tend_set	= 1,
+	.no_dmars	= 1,
+};
+
+static struct resource sh7372_usb_dmae0_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xe68a0020,
+		.end	= 0xe68a0064 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* VCR/SWR/DMICR */
+		.start	= 0xe68a0000,
+		.end	= 0xe68a0014 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* IRQ for channels */
+		.start	= evt2irq(0x0a00),
+		.end	= evt2irq(0x0a00),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usb_dma0_device = {
+	.name		= "sh-dma-engine",
+	.id		= 3,
+	.resource	= sh7372_usb_dmae0_resources,
+	.num_resources	= ARRAY_SIZE(sh7372_usb_dmae0_resources),
+	.dev		= {
+		.platform_data	= &usb_dma0_platform_data,
+	},
+};
+
+/* USB DMAC1 */
+static const struct sh_dmae_slave_config sh7372_usb_dmae1_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_USB1_TX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB1_RX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	},
+};
+
+static struct sh_dmae_pdata usb_dma1_platform_data = {
+	.slave		= sh7372_usb_dmae1_slaves,
+	.slave_num	= ARRAY_SIZE(sh7372_usb_dmae1_slaves),
+	.channel	= sh7372_usb_dmae_channels,
+	.channel_num	= ARRAY_SIZE(sh7372_usb_dmae_channels),
+	.ts_low_shift	= 6,
+	.ts_low_mask	= 0xc0,
+	.ts_high_shift	= 0,
+	.ts_high_mask	= 0,
+	.ts_shift	= usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(usbts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chcr_offset	= 0x14,
+	.chcr_ie_bit	= 1 << 5,
+	.dmaor_is_32bit	= 1,
+	.needs_tend_set	= 1,
+	.no_dmars	= 1,
+};
+
+static struct resource sh7372_usb_dmae1_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xe68c0020,
+		.end	= 0xe68c0064 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* VCR/SWR/DMICR */
+		.start	= 0xe68c0000,
+		.end	= 0xe68c0014 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* IRQ for channels */
+		.start	= evt2irq(0x1d00),
+		.end	= evt2irq(0x1d00),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usb_dma1_device = {
+	.name		= "sh-dma-engine",
+	.id		= 4,
+	.resource	= sh7372_usb_dmae1_resources,
+	.num_resources	= ARRAY_SIZE(sh7372_usb_dmae1_resources),
+	.dev		= {
+		.platform_data	= &usb_dma1_platform_data,
+	},
+};
+
 /* VPU */
 static struct uio_info vpu_platform_data = {
 	.name = "VPU5HG",
@@ -818,7 +962,7 @@ static struct platform_device *sh7372_early_devices[] __initdata = {
 	&scif4_device,
 	&scif5_device,
 	&scif6_device,
-	&cmt10_device,
+	&cmt2_device,
 	&tmu00_device,
 	&tmu01_device,
 };
@@ -829,6 +973,8 @@ static struct platform_device *sh7372_late_devices[] __initdata = {
 	&dma0_device,
 	&dma1_device,
 	&dma2_device,
+	&usb_dma0_device,
+	&usb_dma1_device,
 	&vpu_device,
 	&veu0_device,
 	&veu1_device,
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index de72058180a6..1fafc3244607 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -318,6 +318,10 @@ static struct clk v2m_sp804_clk = {
 	.rate	= 1000000,
 };
 
+static struct clk v2m_ref_clk = {
+	.rate   = 32768,
+};
+
 static struct clk dummy_apb_pclk;
 
 static struct clk_lookup v2m_lookups[] = {
@@ -348,6 +352,9 @@ static struct clk_lookup v2m_lookups[] = {
 	}, {	/* CLCD */
 		.dev_id		= "mb:clcd",
 		.clk		= &osc1_clk,
+	}, {	/* SP805 WDT */
+		.dev_id		= "mb:wdt",
+		.clk		= &v2m_ref_clk,
 	}, {	/* SP804 timers */
 		.dev_id		= "sp804",
 		.con_id		= "v2m-timer0",
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 92bd102e3982..2e6849b41f66 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -379,7 +379,7 @@ 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
+.equ	cpu_arm920_suspend_size, 4 * 4
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 2bbcf053dffd..cd8f79c3a282 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -394,7 +394,7 @@ 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
+.equ	cpu_arm926_suspend_size, 4 * 4
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 07219c2ae114..69e7f2ef7384 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -182,11 +182,11 @@ ENDPROC(cpu_sa1100_do_suspend)
 
 ENTRY(cpu_sa1100_do_resume)
 	ldmia	r0, {r4 - r7}			@ load cp regs
-	mov	r1, #0
-	mcr	p15, 0, r1, c8, c7, 0		@ flush I+D TLBs
-	mcr	p15, 0, r1, c7, c7, 0		@ flush I&D cache
-	mcr	p15, 0, r1, c9, c0, 0		@ invalidate RB
-	mcr	p15, 0, r1, c9, c0, 5		@ allow user space to use RB
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0		@ flush I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0		@ flush I&D cache
+	mcr	p15, 0, ip, c9, c0, 0		@ invalidate RB
+	mcr	p15, 0, ip, c9, c0, 5		@ allow user space to use RB
 
 	mcr	p15, 0, r4, c3, c0, 0		@ domain ID
 	mcr	p15, 0, r5, c2, c0, 0		@ translation table base addr
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 219138d2f158..a923aa0fd00d 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -223,6 +223,22 @@ __v6_setup:
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
+#ifdef CONFIG_ARM_ERRATA_364296
+	/*
+	 * Workaround for the 364296 ARM1136 r0p2 erratum (possible cache data
+	 * corruption with hit-under-miss enabled). The conditional code below
+	 * (setting the undocumented bit 31 in the auxiliary control register
+	 * and the FI bit in the control register) disables hit-under-miss
+	 * without putting the processor into full low interrupt latency mode.
+	 */
+	ldr	r6, =0x4107b362			@ id for ARM1136 r0p2
+	mrc	p15, 0, r5, c0, c0, 0		@ get processor id
+	teq	r5, r6				@ check for the faulty core
+	mrceq	p15, 0, r5, c1, c0, 1		@ load aux control reg
+	orreq	r5, r5, #(1 << 31)		@ set the undocumented bit 31
+	mcreq	p15, 0, r5, c1, c0, 1		@ write aux control reg
+	orreq	r0, r0, #(1 << 21)		@ low interrupt latency configuration
+#endif
 	mov	pc, lr				@ return to head.S:__ret
 
 	/*
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index a30e78542ccf..9049c0764db2 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -66,6 +66,7 @@ ENDPROC(cpu_v7_proc_fin)
 ENTRY(cpu_v7_reset)
 	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
 	bic	r1, r1, #0x1			@ ...............m
+ THUMB(	bic	r1, r1, #1 << 30 )		@ SCTLR.TE (Thumb exceptions)
 	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
 	isb
 	mov	pc, r0
@@ -247,13 +248,16 @@ ENTRY(cpu_v7_do_resume)
 	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
 	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
-	mcr	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
+	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
+	teq	r4, r10			@ Is it already set?
+	mcrne	p15, 0, r10, c1, c0, 1	@ No, so write it
 	mcr	p15, 0, r11, c1, c0, 2	@ Co-processor access control
 	ldr	r4, =PRRR		@ PRRR
 	ldr	r5, =NMRR		@ NMRR
 	mcr	p15, 0, r4, c10, c2, 0	@ write PRRR
 	mcr	p15, 0, r5, c10, c2, 1	@ write NMRR
 	isb
+	dsb
 	mov	r0, r9			@ control register
 	mov	r2, r7, lsr #14		@ get TTB0 base
 	mov	r2, r2, lsl #14
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 28c72a2006a1..755e1bf22681 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -406,7 +406,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 	.align
 
 .globl	cpu_xsc3_suspend_size
-.equ	cpu_xsc3_suspend_size, 4 * 8
+.equ	cpu_xsc3_suspend_size, 4 * 7
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r10, lr}
@@ -418,12 +418,12 @@ ENTRY(cpu_xsc3_do_suspend)
 	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
 	mrc 	p15, 0, r10, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
-	stmia	r0, {r1, r4 - r10}	@ store v:p offset + cp regs
+	stmia	r0, {r4 - r10}		@ store cp regs
 	ldmia	sp!, {r4 - r10, pc}
 ENDPROC(cpu_xsc3_do_suspend)
 
 ENTRY(cpu_xsc3_do_resume)
-	ldmia	r0, {r1, r4 - r10}	@ load v:p offset + cp regs
+	ldmia	r0, {r4 - r10}		@ load cp regs
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
 	mcr	p15, 0, ip, c7, c10, 4	@ drain write (&fill) buffer
diff --git a/arch/arm/plat-s5p/clock.c b/arch/arm/plat-s5p/clock.c
index 02af235298e2..5f84a3f13ef9 100644
--- a/arch/arm/plat-s5p/clock.c
+++ b/arch/arm/plat-s5p/clock.c
@@ -192,7 +192,7 @@ unsigned long s5p_spdif_get_rate(struct clk *clk)
 	if (IS_ERR(pclk))
 		return -EINVAL;
 
-	rate = pclk->ops->get_rate(clk);
+	rate = pclk->ops->get_rate(pclk);
 	clk_put(pclk);
 
 	return rate;
diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c
index 327ab9f662e8..f71078ef6bb5 100644
--- a/arch/arm/plat-s5p/irq-gpioint.c
+++ b/arch/arm/plat-s5p/irq-gpioint.c
@@ -23,6 +23,8 @@
 #include <plat/gpio-core.h>
 #include <plat/gpio-cfg.h>
 
+#include <asm/mach/irq.h>
+
 #define GPIO_BASE(chip)		(((unsigned long)(chip)->base) & 0xFFFFF000u)
 
 #define CON_OFFSET		0x700
@@ -81,6 +83,9 @@ static void s5p_gpioint_handler(unsigned int irq, struct irq_desc *desc)
 	int group, pend_offset, mask_offset;
 	unsigned int pend, mask;
 
+	struct irq_chip *chip = irq_get_chip(irq);
+	chained_irq_enter(chip, desc);
+
 	for (group = 0; group < bank->nr_groups; group++) {
 		struct s3c_gpio_chip *chip = bank->chips[group];
 		if (!chip)
@@ -102,6 +107,7 @@ static void s5p_gpioint_handler(unsigned int irq, struct irq_desc *desc)
 			pend &= ~BIT(offset);
 		}
 	}
+	chained_irq_exit(chip, desc);
 }
 
 static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip)
diff --git a/arch/arm/plat-samsung/include/plat/backlight.h b/arch/arm/plat-samsung/include/plat/backlight.h
index 51d8da846a62..ad530c78fe8c 100644
--- a/arch/arm/plat-samsung/include/plat/backlight.h
+++ b/arch/arm/plat-samsung/include/plat/backlight.h
@@ -20,7 +20,7 @@ struct samsung_bl_gpio_info {
 	int func;
 };
 
-extern void samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
+extern void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 	struct platform_pwm_backlight_data *bl_data);
 
 #endif /* __ASM_PLAT_BACKLIGHT_H */
diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c
index f714d060370d..51583cd30164 100644
--- a/arch/arm/plat-samsung/irq-vic-timer.c
+++ b/arch/arm/plat-samsung/irq-vic-timer.c
@@ -22,9 +22,14 @@
 #include <plat/irq-vic-timer.h>
 #include <plat/regs-timer.h>
 
+#include <asm/mach/irq.h>
+
 static void s3c_irq_demux_vic_timer(unsigned int irq, struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_get_chip(irq);
+	chained_irq_enter(chip, desc);
 	generic_handle_irq((int)desc->irq_data.handler_data);
+	chained_irq_exit(chip, desc);
 }
 
 /* We assume the IRQ_TIMER0..IRQ_TIMER4 range is continuous. */
diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index fff68d0d521b..62cc8f981171 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -351,7 +351,7 @@ centro			MACH_CENTRO		CENTRO			1944
 nokia_rx51		MACH_NOKIA_RX51		NOKIA_RX51		1955
 omap_zoom2		MACH_OMAP_ZOOM2		OMAP_ZOOM2		1967
 cpuat9260		MACH_CPUAT9260		CPUAT9260		1973
-eukrea_cpuimx27		MACH_CPUIMX27		CPUIMX27		1975
+eukrea_cpuimx27		MACH_EUKREA_CPUIMX27	EUKREA_CPUIMX27		1975
 acs5k			MACH_ACS5K		ACS5K			1982
 snapper_9260		MACH_SNAPPER_9260	SNAPPER_9260		1987
 dsm320			MACH_DSM320		DSM320			1988
@@ -476,8 +476,8 @@ cns3420vb		MACH_CNS3420VB		CNS3420VB		2776
 omap4_panda		MACH_OMAP4_PANDA	OMAP4_PANDA		2791
 ti8168evm		MACH_TI8168EVM		TI8168EVM		2800
 teton_bga		MACH_TETON_BGA		TETON_BGA		2816
-eukrea_cpuimx25sd	MACH_EUKREA_CPUIMX25	EUKREA_CPUIMX25		2820
-eukrea_cpuimx35sd	MACH_EUKREA_CPUIMX35	EUKREA_CPUIMX35		2821
+eukrea_cpuimx25sd	MACH_EUKREA_CPUIMX25SD	EUKREA_CPUIMX25SD	2820
+eukrea_cpuimx35sd	MACH_EUKREA_CPUIMX35SD	EUKREA_CPUIMX35SD	2821
 eukrea_cpuimx51sd	MACH_EUKREA_CPUIMX51SD	EUKREA_CPUIMX51SD	2822
 eukrea_cpuimx51		MACH_EUKREA_CPUIMX51	EUKREA_CPUIMX51		2823
 smdkc210		MACH_SMDKC210		SMDKC210		2838
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index e66366fd2abc..3735abd7f8f6 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -259,7 +259,7 @@
 	ENTRY_SAME(ni_syscall)		/* query_module */
 	ENTRY_SAME(poll)
 	/* structs contain pointers and an in_addr... */
-	ENTRY_COMP(nfsservctl)
+	ENTRY_SAME(ni_syscall)		/* was nfsservctl */
 	ENTRY_SAME(setresgid)		/* 170 */
 	ENTRY_SAME(getresgid)
 	ENTRY_SAME(prctl)
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index f6736b7da463..fa0d27a400de 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -171,7 +171,7 @@ SYSCALL_SPU(setresuid)
 SYSCALL_SPU(getresuid)
 SYSCALL(ni_syscall)
 SYSCALL_SPU(poll)
-COMPAT_SYS(nfsservctl)
+SYSCALL(ni_syscall)
 SYSCALL_SPU(setresgid)
 SYSCALL_SPU(getresgid)
 COMPAT_SYS_SPU(prctl)
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index b97baf81a87b..2d3679b2447f 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -123,7 +123,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 struct perf_event;
 struct perf_sample_data;
 
-extern void ptrace_triggered(struct perf_event *bp, int nmi,
+extern void ptrace_triggered(struct perf_event *bp,
 		      struct perf_sample_data *data, struct pt_regs *regs);
 
 #define task_pt_regs(task) \
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
index e915deafac89..05559295d2ca 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
@@ -15,6 +15,7 @@
 #include <linux/serial_sci.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/dma-mapping.h>
 #include <linux/sh_timer.h>
 #include <linux/sh_dma.h>
 
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 32114e0941ae..db4ecd731a00 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -22,7 +22,7 @@
 #include <linux/atomic.h>
 #include <asm/smp.h>
 
-static void (*pm_idle)(void);
+void (*pm_idle)(void);
 
 static int hlt_counter;
 
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index d9006f8ffc14..7bbef95c9d1b 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -316,6 +316,35 @@ static int handle_unaligned_ins(insn_size_t instruction, struct pt_regs *regs,
 			break;
 		}
 		break;
+
+	case 9: /* mov.w @(disp,PC),Rn */
+		srcu = (unsigned char __user *)regs->pc;
+		srcu += 4;
+		srcu += (instruction & 0x00FF) << 1;
+		dst = (unsigned char *)rn;
+		*(unsigned long *)dst = 0;
+
+#if !defined(__LITTLE_ENDIAN__)
+		dst += 2;
+#endif
+
+		if (ma->from(dst, srcu, 2))
+			goto fetch_fault;
+		sign_extend(2, dst);
+		ret = 0;
+		break;
+
+	case 0xd: /* mov.l @(disp,PC),Rn */
+		srcu = (unsigned char __user *)(regs->pc & ~0x3);
+		srcu += 4;
+		srcu += (instruction & 0x00FF) << 2;
+		dst = (unsigned char *)rn;
+		*(unsigned long *)dst = 0;
+
+		if (ma->from(dst, srcu, 4))
+			goto fetch_fault;
+		ret = 0;
+		break;
 	}
 	return ret;
 
@@ -466,6 +495,7 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 		case 0x0500: /* mov.w @(disp,Rm),R0 */
 			goto simple;
 		case 0x0B00: /* bf   lab - no delayslot*/
+			ret = 0;
 			break;
 		case 0x0F00: /* bf/s lab */
 			ret = handle_delayslot(regs, instruction, ma);
@@ -479,6 +509,7 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 			}
 			break;
 		case 0x0900: /* bt   lab - no delayslot */
+			ret = 0;
 			break;
 		case 0x0D00: /* bt/s lab */
 			ret = handle_delayslot(regs, instruction, ma);
@@ -494,6 +525,9 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 		}
 		break;
 
+	case 0x9000: /* mov.w @(disp,Rm),Rn */
+		goto simple;
+
 	case 0xA000: /* bra label */
 		ret = handle_delayslot(regs, instruction, ma);
 		if (ret==0)
@@ -507,6 +541,9 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 			regs->pc += SH_PC_12BIT_OFFSET(instruction);
 		}
 		break;
+
+	case 0xD000: /* mov.l @(disp,Rm),Rn */
+		goto simple;
 	}
 	return ret;
 
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
index 100b9c204e78..42851122bbd9 100644
--- a/arch/sparc/kernel/irq.h
+++ b/arch/sparc/kernel/irq.h
@@ -88,7 +88,7 @@ BTFIXUPDEF_CALL(void, set_irq_udt, int)
 #define set_irq_udt(cpu) BTFIXUP_CALL(set_irq_udt)(cpu)
 
 /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */
-#define SUN4D_IPI_IRQ 14
+#define SUN4D_IPI_IRQ 13
 
 extern void sun4d_ipi_interrupt(void);
 
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index c9296ab0b1f4..edbec45d4688 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -68,7 +68,7 @@ sys_call_table32:
 	.word compat_sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys32_mlockall
 /*240*/	.word sys_munlockall, sys32_sched_setparam, sys32_sched_getparam, sys32_sched_setscheduler, sys32_sched_getscheduler
 	.word sys_sched_yield, sys32_sched_get_priority_max, sys32_sched_get_priority_min, sys32_sched_rr_get_interval, compat_sys_nanosleep
-/*250*/	.word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys32_nfsservctl
+/*250*/	.word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys_nis_syscall
 	.word sys32_sync_file_range, compat_sys_clock_settime, compat_sys_clock_gettime, compat_sys_clock_getres, sys32_clock_nanosleep
 /*260*/	.word compat_sys_sched_getaffinity, compat_sys_sched_setaffinity, sys32_timer_settime, compat_sys_timer_gettime, sys_timer_getoverrun
 	.word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy