Merge tag 'drivers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc

Pull ARM SoC driver updates from Arnd Bergmann:
 "These are changes for drivers that are intimately tied to some SoC and
  for some reason could not get merged through the respective subsystem
  maintainer tree.

  The largest single change here this time around is the Tegra
  iommu/memory controller driver, which gets updated to the new iommu DT
  binding.  More drivers like this are likely to follow for the
  following merge window, but we should be able to do those through the
  iommu maintainer.

  Other notable changes are:
   - reset controller drivers from the reset maintainer (socfpga, sti,
     berlin)
   - fixes for the keystone navigator driver merged last time
   - at91 rtc driver changes related to the at91 cleanups
   - ARM perf driver changes from Will Deacon
   - updates for the brcmstb_gisb driver"

* tag 'drivers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (53 commits)
  clocksource: arch_timer: Allow the device tree to specify uninitialized timer registers
  clocksource: arch_timer: Fix code to use physical timers when requested
  memory: Add NVIDIA Tegra memory controller support
  bus: brcmstb_gisb: Add register offset tables for older chips
  bus: brcmstb_gisb: Look up register offsets in a table
  bus: brcmstb_gisb: Introduce wrapper functions for MMIO accesses
  bus: brcmstb_gisb: Make the driver buildable on MIPS
  of: Add NVIDIA Tegra memory controller binding
  ARM: tegra: Move AHB Kconfig to drivers/amba
  amba: Add Kconfig file
  clk: tegra: Implement memory-controller clock
  serial: samsung: Fix serial config dependencies for exynos7
  bus: brcmstb_gisb: resolve section mismatch
  ARM: common: edma: edma_pm_resume may be unused
  ARM: common: edma: add suspend resume hook
  powerpc/iommu: Rename iommu_[un]map_sg functions
  rtc: at91sam9: add DT bindings documentation
  rtc: at91sam9: use clk API instead of relying on AT91_SLOW_CLOCK
  ARM: at91: add clk_lookup entry for RTT devices
  rtc: at91sam9: rework the Kconfig description
  ...

19 files changed, 426 insertions, 334 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8db9dc07f8ac..c8424a85bc04 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1246,9 +1246,6 @@ source "arch/arm/common/Kconfig"
 
 menu "Bus support"
 
-config ARM_AMBA
-	bool
-
 config ISA
 	bool
 	help
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 72041f002b7e..5662a872689b 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -245,6 +245,8 @@ struct edma {
 	/* list of channels with no even trigger; terminated by "-1" */
 	const s8	*noevent;
 
+	struct edma_soc_info *info;
+
 	/* The edma_inuse bit for each PaRAM slot is clear unless the
 	 * channel is in use ... by ARM or DSP, for QDMA, or whatever.
 	 */
@@ -296,7 +298,7 @@ static void map_dmach_queue(unsigned ctlr, unsigned ch_no,
 			~(0x7 << bit), queue_no << bit);
 }
 
-static void __init assign_priority_to_queue(unsigned ctlr, int queue_no,
+static void assign_priority_to_queue(unsigned ctlr, int queue_no,
 		int priority)
 {
 	int bit = queue_no * 4;
@@ -315,7 +317,7 @@ static void __init assign_priority_to_queue(unsigned ctlr, int queue_no,
  * included in that particular EDMA variant (Eg : dm646x)
  *
  */
-static void __init map_dmach_param(unsigned ctlr)
+static void map_dmach_param(unsigned ctlr)
 {
 	int i;
 	for (i = 0; i < EDMA_MAX_DMACH; i++)
@@ -1798,6 +1800,7 @@ static int edma_probe(struct platform_device *pdev)
 			edma_write_array2(j, EDMA_DRAE, i, 1, 0x0);
 			edma_write_array(j, EDMA_QRAE, i, 0x0);
 		}
+		edma_cc[j]->info = info[j];
 		arch_num_cc++;
 
 		edma_dev_info.id = j;
@@ -1807,9 +1810,56 @@ static int edma_probe(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int edma_pm_resume(struct device *dev)
+{
+	int i, j;
+
+	for (j = 0; j < arch_num_cc; j++) {
+		struct edma *cc = edma_cc[j];
+
+		s8 (*queue_priority_mapping)[2];
+
+		queue_priority_mapping = cc->info->queue_priority_mapping;
+
+		/* Event queue priority mapping */
+		for (i = 0; queue_priority_mapping[i][0] != -1; i++)
+			assign_priority_to_queue(j,
+						 queue_priority_mapping[i][0],
+						 queue_priority_mapping[i][1]);
+
+		/*
+		 * Map the channel to param entry if channel mapping logic
+		 * exist
+		 */
+		if (edma_read(j, EDMA_CCCFG) & CHMAP_EXIST)
+			map_dmach_param(j);
+
+		for (i = 0; i < cc->num_channels; i++) {
+			if (test_bit(i, cc->edma_inuse)) {
+				/* ensure access through shadow region 0 */
+				edma_or_array2(j, EDMA_DRAE, 0, i >> 5,
+					       BIT(i & 0x1f));
+
+				setup_dma_interrupt(i,
+						    cc->intr_data[i].callback,
+						    cc->intr_data[i].data);
+			}
+		}
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops edma_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(NULL, edma_pm_resume)
+};
+
 static struct platform_driver edma_driver = {
 	.driver = {
 		.name	= "edma",
+		.pm	= &edma_pm_ops,
 		.of_match_table = edma_of_ids,
 	},
 	.probe = edma_probe,
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 92793ba69c40..d4ebf5679f1f 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -78,6 +78,15 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }
 
+static inline u64 arch_counter_get_cntpct(void)
+{
+	u64 cval;
+
+	isb();
+	asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
+	return cval;
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index c3a83691af8e..d9cf138fd7d4 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,7 +12,7 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-#ifdef CONFIG_HW_PERF_EVENTS
+#ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 0b648c541293..b1596bd59129 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -15,6 +15,8 @@
 #include <linux/interrupt.h>
 #include <linux/perf_event.h>
 
+#include <asm/cputype.h>
+
 /*
  * struct arm_pmu_platdata - ARM PMU platform data
  *
@@ -66,19 +68,25 @@ struct pmu_hw_events {
 	/*
 	 * The events that are active on the PMU for the given index.
 	 */
-	struct perf_event	**events;
+	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;
+	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
 
 	/*
 	 * Hardware lock to serialize accesses to PMU registers. Needed for the
 	 * read/modify/write sequences.
 	 */
 	raw_spinlock_t		pmu_lock;
+
+	/*
+	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
+	 * already have to allocate this struct per cpu.
+	 */
+	struct arm_pmu		*percpu_pmu;
 };
 
 struct arm_pmu {
@@ -107,7 +115,8 @@ struct arm_pmu {
 	struct mutex	reserve_mutex;
 	u64		max_period;
 	struct platform_device	*plat_device;
-	struct pmu_hw_events	*(*get_hw_events)(void);
+	struct pmu_hw_events	__percpu *hw_events;
+	struct notifier_block	hotplug_nb;
 };
 
 #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
@@ -127,6 +136,27 @@ int armpmu_map_event(struct perf_event *event,
 						[PERF_COUNT_HW_CACHE_RESULT_MAX],
 		     u32 raw_event_mask);
 
+struct pmu_probe_info {
+	unsigned int cpuid;
+	unsigned int mask;
+	int (*init)(struct arm_pmu *);
+};
+
+#define PMU_PROBE(_cpuid, _mask, _fn)	\
+{					\
+	.cpuid = (_cpuid),		\
+	.mask = (_mask),		\
+	.init = (_fn),			\
+}
+
+#define ARM_PMU_PROBE(_cpuid, _fn) \
+	PMU_PROBE(_cpuid, ARM_CPU_PART_MASK, _fn)
+
+#define ARM_PMU_XSCALE_MASK	((0xff << 24) | ARM_CPU_XSCALE_ARCH_MASK)
+
+#define XSCALE_PMU_PROBE(_version, _fn) \
+	PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn)
+
 #endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 38ddd9f83d0e..8dcbed5016ac 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -82,7 +82,7 @@ obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_CPU_PJ4B)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
-obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
new file mode 100644
index 000000000000..4e02ae5950ff
--- /dev/null
+++ b/arch/arm/kernel/perf_callchain.c
@@ -0,0 +1,136 @@
+/*
+ * ARM callchain support
+ *
+ * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
+ * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
+ *
+ * This code is based on the ARM OProfile backtrace code.
+ */
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct frame_tail {
+	struct frame_tail __user *fp;
+	unsigned long sp;
+	unsigned long lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail __user *
+user_backtrace(struct frame_tail __user *tail,
+	       struct perf_callchain_entry *entry)
+{
+	struct frame_tail buftail;
+	unsigned long err;
+
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= buftail.fp)
+		return NULL;
+
+	return buftail.fp - 1;
+}
+
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+{
+	struct frame_tail __user *tail;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->ARM_pc);
+
+	if (!current->mm)
+		return;
+
+	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
+
+	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+	       tail && !((unsigned long)tail & 0x3))
+		tail = user_backtrace(tail, entry);
+}
+
+/*
+ * Gets called by walk_stackframe() for every stackframe. This will be called
+ * whist unwinding the stackframe and is like a subroutine return so we use
+ * the PC.
+ */
+static int
+callchain_trace(struct stackframe *fr,
+		void *data)
+{
+	struct perf_callchain_entry *entry = data;
+	perf_callchain_store(entry, fr->pc);
+	return 0;
+}
+
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+{
+	struct stackframe fr;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	arm_get_current_stackframe(regs, &fr);
+	walk_stackframe(&fr, callchain_trace, entry);
+}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+		return perf_guest_cbs->get_guest_ip();
+
+	return instruction_pointer(regs);
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	int misc = 0;
+
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		if (perf_guest_cbs->is_user_mode())
+			misc |= PERF_RECORD_MISC_GUEST_USER;
+		else
+			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (user_mode(regs))
+			misc |= PERF_RECORD_MISC_USER;
+		else
+			misc |= PERF_RECORD_MISC_KERNEL;
+	}
+
+	return misc;
+}
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 266cba46db3e..e34934f63a49 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -7,21 +7,18 @@
  * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
  *
  * This code is based on the sparc64 perf event code, which is in turn based
- * on the x86 code. Callchain code is based on the ARM OProfile backtrace
- * code.
+ * on the x86 code.
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
-#include <linux/uaccess.h>
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
 
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
-#include <asm/stacktrace.h>
 
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
@@ -80,8 +77,12 @@ armpmu_map_event(struct perf_event *event,
 		 u32 raw_event_mask)
 {
 	u64 config = event->attr.config;
+	int type = event->attr.type;
 
-	switch (event->attr.type) {
+	if (type == event->pmu->type)
+		return armpmu_map_raw_event(raw_event_mask, config);
+
+	switch (type) {
 	case PERF_TYPE_HARDWARE:
 		return armpmu_map_hw_event(event_map, config);
 	case PERF_TYPE_HW_CACHE:
@@ -200,7 +201,7 @@ static void
 armpmu_del(struct perf_event *event, int flags)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
+	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -217,7 +218,7 @@ static int
 armpmu_add(struct perf_event *event, int flags)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
+	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -274,14 +275,12 @@ validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
 	struct pmu_hw_events fake_pmu;
-	DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);
 
 	/*
 	 * Initialise the fake PMU. We only need to populate the
 	 * used_mask for the purposes of validation.
 	 */
-	memset(fake_used_mask, 0, sizeof(fake_used_mask));
-	fake_pmu.used_mask = fake_used_mask;
+	memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask));
 
 	if (!validate_event(&fake_pmu, leader))
 		return -EINVAL;
@@ -305,17 +304,21 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 	int ret;
 	u64 start_clock, finish_clock;
 
-	if (irq_is_percpu(irq))
-		dev = *(void **)dev;
-	armpmu = dev;
+	/*
+	 * we request the IRQ with a (possibly percpu) struct arm_pmu**, but
+	 * the handlers expect a struct arm_pmu*. The percpu_irq framework will
+	 * do any necessary shifting, we just need to perform the first
+	 * dereference.
+	 */
+	armpmu = *(void **)dev;
 	plat_device = armpmu->plat_device;
 	plat = dev_get_platdata(&plat_device->dev);
 
 	start_clock = sched_clock();
 	if (plat && plat->handle_irq)
-		ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
+		ret = plat->handle_irq(irq, armpmu, armpmu->handle_irq);
 	else
-		ret = armpmu->handle_irq(irq, dev);
+		ret = armpmu->handle_irq(irq, armpmu);
 	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);
@@ -468,7 +471,7 @@ static int armpmu_event_init(struct perf_event *event)
 static void armpmu_enable(struct pmu *pmu)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
+	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
 	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
 
 	if (enabled)
@@ -533,130 +536,3 @@ int armpmu_register(struct arm_pmu *armpmu, int type)
 	return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
 }
 
-/*
- * Callchain handling code.
- */
-
-/*
- * The registers we're interested in are at the end of the variable
- * length saved register structure. The fp points at the end of this
- * structure so the address of this struct is:
- * (struct frame_tail *)(xxx->fp)-1
- *
- * This code has been adapted from the ARM OProfile support.
- */
-struct frame_tail {
-	struct frame_tail __user *fp;
-	unsigned long sp;
-	unsigned long lr;
-} __attribute__((packed));
-
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry *entry)
-{
-	struct frame_tail buftail;
-	unsigned long err;
-
-	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail + 1 >= buftail.fp)
-		return NULL;
-
-	return buftail.fp - 1;
-}
-
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
-{
-	struct frame_tail __user *tail;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
-	perf_callchain_store(entry, regs->ARM_pc);
-
-	if (!current->mm)
-		return;
-
-	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
-
-	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
-	       tail && !((unsigned long)tail & 0x3))
-		tail = user_backtrace(tail, entry);
-}
-
-/*
- * Gets called by walk_stackframe() for every stackframe. This will be called
- * whist unwinding the stackframe and is like a subroutine return so we use
- * the PC.
- */
-static int
-callchain_trace(struct stackframe *fr,
-		void *data)
-{
-	struct perf_callchain_entry *entry = data;
-	perf_callchain_store(entry, fr->pc);
-	return 0;
-}
-
-void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
-{
-	struct stackframe fr;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
-	arm_get_current_stackframe(regs, &fr);
-	walk_stackframe(&fr, callchain_trace, entry);
-}
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
-
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
-	int misc = 0;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
-
-	return misc;
-}
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index eb2c4d55666b..dd9acc95ebc0 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -35,11 +35,6 @@
 /* Set at runtime when we know what CPU type we are. */
 static struct arm_pmu *cpu_pmu;
 
-static DEFINE_PER_CPU(struct arm_pmu *, percpu_pmu);
-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);
-
 /*
  * Despite the names, these two functions are CPU-specific and are used
  * by the OProfile/perf code.
@@ -69,11 +64,6 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 #include "perf_event_v6.c"
 #include "perf_event_v7.c"
 
-static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
-{
-	return this_cpu_ptr(&cpu_hw_events);
-}
-
 static void cpu_pmu_enable_percpu_irq(void *data)
 {
 	int irq = *(int *)data;
@@ -92,20 +82,21 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 {
 	int i, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
 	irq = platform_get_irq(pmu_device, 0);
 	if (irq >= 0 && irq_is_percpu(irq)) {
 		on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
-		free_percpu_irq(irq, &percpu_pmu);
+		free_percpu_irq(irq, &hw_events->percpu_pmu);
 	} else {
 		for (i = 0; i < irqs; ++i) {
 			if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
 				continue;
 			irq = platform_get_irq(pmu_device, i);
 			if (irq >= 0)
-				free_irq(irq, cpu_pmu);
+				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, i));
 		}
 	}
 }
@@ -114,19 +105,21 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 {
 	int i, err, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
 
 	if (!pmu_device)
 		return -ENODEV;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 	if (irqs < 1) {
-		printk_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		pr_warn_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
 		return 0;
 	}
 
 	irq = platform_get_irq(pmu_device, 0);
 	if (irq >= 0 && irq_is_percpu(irq)) {
-		err = request_percpu_irq(irq, handler, "arm-pmu", &percpu_pmu);
+		err = request_percpu_irq(irq, handler, "arm-pmu",
+					 &hw_events->percpu_pmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",
 				irq);
@@ -153,7 +146,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 
 			err = request_irq(irq, handler,
 					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
-					  cpu_pmu);
+					  per_cpu_ptr(&hw_events->percpu_pmu, i));
 			if (err) {
 				pr_err("unable to request IRQ%d for ARM PMU counters\n",
 					irq);
@@ -167,18 +160,50 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 	return 0;
 }
 
-static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
+/*
+ * PMU hardware loses all context when a CPU goes offline.
+ * When a CPU is hotplugged back in, since some hardware registers are
+ * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
+ * junk values out of them.
+ */
+static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
+			  void *hcpu)
+{
+	struct arm_pmu *pmu = container_of(b, struct arm_pmu, hotplug_nb);
+
+	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
+		return NOTIFY_DONE;
+
+	if (pmu->reset)
+		pmu->reset(pmu);
+	else
+		return NOTIFY_DONE;
+
+	return NOTIFY_OK;
+}
+
+static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
+	int err;
 	int cpu;
+	struct pmu_hw_events __percpu *cpu_hw_events;
+
+	cpu_hw_events = alloc_percpu(struct pmu_hw_events);
+	if (!cpu_hw_events)
+		return -ENOMEM;
+
+	cpu_pmu->hotplug_nb.notifier_call = cpu_pmu_notify;
+	err = register_cpu_notifier(&cpu_pmu->hotplug_nb);
+	if (err)
+		goto out_hw_events;
+
 	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);
+		struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
 		raw_spin_lock_init(&events->pmu_lock);
-		per_cpu(percpu_pmu, cpu) = cpu_pmu;
+		events->percpu_pmu = cpu_pmu;
 	}
 
-	cpu_pmu->get_hw_events	= cpu_pmu_get_cpu_events;
+	cpu_pmu->hw_events	= cpu_hw_events;
 	cpu_pmu->request_irq	= cpu_pmu_request_irq;
 	cpu_pmu->free_irq	= cpu_pmu_free_irq;
 
@@ -189,31 +214,19 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	/* If no interrupts available, set the corresponding capability flag */
 	if (!platform_get_irq(cpu_pmu->plat_device, 0))
 		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
-}
-
-/*
- * PMU hardware loses all context when a CPU goes offline.
- * When a CPU is hotplugged back in, since some hardware registers are
- * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
- * junk values out of them.
- */
-static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
-			  void *hcpu)
-{
-	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
-		return NOTIFY_DONE;
 
-	if (cpu_pmu && cpu_pmu->reset)
-		cpu_pmu->reset(cpu_pmu);
-	else
-		return NOTIFY_DONE;
+	return 0;
 
-	return NOTIFY_OK;
+out_hw_events:
+	free_percpu(cpu_hw_events);
+	return err;
 }
 
-static struct notifier_block cpu_pmu_hotplug_notifier = {
-	.notifier_call = cpu_pmu_notify,
-};
+static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
+{
+	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
+	free_percpu(cpu_pmu->hw_events);
+}
 
 /*
  * PMU platform driver and devicetree bindings.
@@ -241,48 +254,34 @@ static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 	{},
 };
 
+static const struct pmu_probe_info pmu_probe_table[] = {
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM1136, armv6_1136_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM1156, armv6_1156_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM1176, armv6_1176_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM11MPCORE, armv6mpcore_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A8, armv7_a8_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A9, armv7_a9_pmu_init),
+	XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V1, xscale1pmu_init),
+	XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V2, xscale2pmu_init),
+	{ /* sentinel value */ }
+};
+
 /*
  * CPU PMU identification and probing.
  */
 static int probe_current_pmu(struct arm_pmu *pmu)
 {
 	int cpu = get_cpu();
+	unsigned int cpuid = read_cpuid_id();
 	int ret = -ENODEV;
+	const struct pmu_probe_info *info;
 
 	pr_info("probing PMU on CPU %d\n", cpu);
 
-	switch (read_cpuid_part()) {
-	/* ARM Ltd CPUs. */
-	case ARM_CPU_PART_ARM1136:
-		ret = armv6_1136_pmu_init(pmu);
-		break;
-	case ARM_CPU_PART_ARM1156:
-		ret = armv6_1156_pmu_init(pmu);
-		break;
-	case ARM_CPU_PART_ARM1176:
-		ret = armv6_1176_pmu_init(pmu);
-		break;
-	case ARM_CPU_PART_ARM11MPCORE:
-		ret = armv6mpcore_pmu_init(pmu);
-		break;
-	case ARM_CPU_PART_CORTEX_A8:
-		ret = armv7_a8_pmu_init(pmu);
-		break;
-	case ARM_CPU_PART_CORTEX_A9:
-		ret = armv7_a9_pmu_init(pmu);
-		break;
-
-	default:
-		if (read_cpuid_implementor() == ARM_CPU_IMP_INTEL) {
-			switch (xscale_cpu_arch_version()) {
-			case ARM_CPU_XSCALE_ARCH_V1:
-				ret = xscale1pmu_init(pmu);
-				break;
-			case ARM_CPU_XSCALE_ARCH_V2:
-				ret = xscale2pmu_init(pmu);
-				break;
-			}
-		}
+	for (info = pmu_probe_table; info->init != NULL; info++) {
+		if ((cpuid & info->mask) != info->cpuid)
+			continue;
+		ret = info->init(pmu);
 		break;
 	}
 
@@ -299,13 +298,13 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	int ret = -ENODEV;
 
 	if (cpu_pmu) {
-		pr_info("attempt to register multiple PMU devices!");
+		pr_info("attempt to register multiple PMU devices!\n");
 		return -ENOSPC;
 	}
 
 	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
 	if (!pmu) {
-		pr_info("failed to allocate PMU device!");
+		pr_info("failed to allocate PMU device!\n");
 		return -ENOMEM;
 	}
 
@@ -320,18 +319,24 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	if (ret) {
-		pr_info("failed to probe PMU!");
+		pr_info("failed to probe PMU!\n");
 		goto out_free;
 	}
 
-	cpu_pmu_init(cpu_pmu);
-	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+	ret = cpu_pmu_init(cpu_pmu);
+	if (ret)
+		goto out_free;
 
-	if (!ret)
-		return 0;
+	ret = armpmu_register(cpu_pmu, -1);
+	if (ret)
+		goto out_destroy;
 
+	return 0;
+
+out_destroy:
+	cpu_pmu_destroy(cpu_pmu);
 out_free:
-	pr_info("failed to register PMU devices!");
+	pr_info("failed to register PMU devices!\n");
 	kfree(pmu);
 	return ret;
 }
@@ -348,16 +353,6 @@ static struct platform_driver cpu_pmu_driver = {
 
 static int __init register_pmu_driver(void)
 {
-	int err;
-
-	err = register_cpu_notifier(&cpu_pmu_hotplug_notifier);
-	if (err)
-		return err;
-
-	err = platform_driver_register(&cpu_pmu_driver);
-	if (err)
-		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
-
-	return err;
+	return platform_driver_register(&cpu_pmu_driver);
 }
 device_initcall(register_pmu_driver);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index abfeb04f3213..f2ffd5c542ed 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -262,7 +262,7 @@ static void armv6pmu_enable_event(struct perf_event *event)
 	unsigned long val, mask, evt, flags;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -300,7 +300,7 @@ armv6pmu_handle_irq(int irq_num,
 	unsigned long pmcr = armv6_pmcr_read();
 	struct perf_sample_data data;
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
-	struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;
 
@@ -356,7 +356,7 @@ armv6pmu_handle_irq(int irq_num,
 static void armv6pmu_start(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
@@ -368,7 +368,7 @@ static void armv6pmu_start(struct arm_pmu *cpu_pmu)
 static void armv6pmu_stop(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
@@ -409,7 +409,7 @@ static void armv6pmu_disable_event(struct perf_event *event)
 	unsigned long val, mask, evt, flags;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -444,7 +444,7 @@ static void armv6mpcore_pmu_disable_event(struct perf_event *event)
 	unsigned long val, mask, flags, evt = 0;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 116758b77f93..8993770c47de 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -564,13 +564,11 @@ static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx)
 	return pmnc & BIT(ARMV7_IDX_TO_COUNTER(idx));
 }
 
-static inline int armv7_pmnc_select_counter(int idx)
+static inline void armv7_pmnc_select_counter(int idx)
 {
 	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter));
 	isb();
-
-	return idx;
 }
 
 static inline u32 armv7pmu_read_counter(struct perf_event *event)
@@ -580,13 +578,15 @@ static inline u32 armv7pmu_read_counter(struct perf_event *event)
 	int idx = hwc->idx;
 	u32 value = 0;
 
-	if (!armv7_pmnc_counter_valid(cpu_pmu, idx))
+	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
 		pr_err("CPU%u reading wrong counter %d\n",
 			smp_processor_id(), idx);
-	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+	} 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)
+	} else {
+		armv7_pmnc_select_counter(idx);
 		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value));
+	}
 
 	return value;
 }
@@ -597,45 +597,43 @@ static inline void armv7pmu_write_counter(struct perf_event *event, u32 value)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	if (!armv7_pmnc_counter_valid(cpu_pmu, idx))
+	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
-	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+	} 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)
+	} else {
+		armv7_pmnc_select_counter(idx);
 		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
+	}
 }
 
 static inline void armv7_pmnc_write_evtsel(int idx, u32 val)
 {
-	if (armv7_pmnc_select_counter(idx) == idx) {
-		val &= ARMV7_EVTYPE_MASK;
-		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
-	}
+	armv7_pmnc_select_counter(idx);
+	val &= ARMV7_EVTYPE_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
 }
 
-static inline int armv7_pmnc_enable_counter(int idx)
+static inline void armv7_pmnc_enable_counter(int idx)
 {
 	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter)));
-	return idx;
 }
 
-static inline int armv7_pmnc_disable_counter(int idx)
+static inline void armv7_pmnc_disable_counter(int idx)
 {
 	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter)));
-	return idx;
 }
 
-static inline int armv7_pmnc_enable_intens(int idx)
+static inline void armv7_pmnc_enable_intens(int idx)
 {
 	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter)));
-	return idx;
 }
 
-static inline int armv7_pmnc_disable_intens(int idx)
+static inline void armv7_pmnc_disable_intens(int idx)
 {
 	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
@@ -643,8 +641,6 @@ static inline int armv7_pmnc_disable_intens(int idx)
 	/* Clear the overflow flag in case an interrupt is pending. */
 	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter)));
 	isb();
-
-	return idx;
 }
 
 static inline u32 armv7_pmnc_getreset_flags(void)
@@ -667,34 +663,34 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 	u32 val;
 	unsigned int cnt;
 
-	printk(KERN_INFO "PMNC registers dump:\n");
+	pr_info("PMNC registers dump:\n");
 
 	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
-	printk(KERN_INFO "PMNC  =0x%08x\n", val);
+	pr_info("PMNC  =0x%08x\n", val);
 
 	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
-	printk(KERN_INFO "CNTENS=0x%08x\n", val);
+	pr_info("CNTENS=0x%08x\n", val);
 
 	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
-	printk(KERN_INFO "INTENS=0x%08x\n", val);
+	pr_info("INTENS=0x%08x\n", val);
 
 	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
-	printk(KERN_INFO "FLAGS =0x%08x\n", val);
+	pr_info("FLAGS =0x%08x\n", val);
 
 	asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
-	printk(KERN_INFO "SELECT=0x%08x\n", val);
+	pr_info("SELECT=0x%08x\n", val);
 
 	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
-	printk(KERN_INFO "CCNT  =0x%08x\n", val);
+	pr_info("CCNT  =0x%08x\n", val);
 
 	for (cnt = ARMV7_IDX_COUNTER0;
 			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); 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",
+		pr_info("CNT[%d] count =0x%08x\n",
 			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",
+		pr_info("CNT[%d] evtsel=0x%08x\n",
 			ARMV7_IDX_TO_COUNTER(cnt), val);
 	}
 }
@@ -705,7 +701,7 @@ static void armv7pmu_enable_event(struct perf_event *event)
 	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
@@ -751,7 +747,7 @@ static void armv7pmu_disable_event(struct perf_event *event)
 	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
@@ -783,7 +779,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	u32 pmnc;
 	struct perf_sample_data data;
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
-	struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;
 
@@ -843,7 +839,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 static void armv7pmu_start(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Enable all counters */
@@ -854,7 +850,7 @@ static void armv7pmu_start(struct arm_pmu *cpu_pmu)
 static void armv7pmu_stop(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Disable all counters */
@@ -1287,7 +1283,7 @@ static void krait_pmu_disable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/* Disable counter and interrupt */
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
@@ -1313,7 +1309,7 @@ static void krait_pmu_enable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 08da0af550b7..8af9f1f82c68 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -138,7 +138,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 	unsigned long pmnc;
 	struct perf_sample_data data;
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
-	struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;
 
@@ -198,7 +198,7 @@ static void xscale1pmu_enable_event(struct perf_event *event)
 	unsigned long val, mask, evt, flags;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	switch (idx) {
@@ -234,7 +234,7 @@ static void xscale1pmu_disable_event(struct perf_event *event)
 	unsigned long val, mask, evt, flags;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	switch (idx) {
@@ -287,7 +287,7 @@ xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc,
 static void xscale1pmu_start(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
@@ -299,7 +299,7 @@ static void xscale1pmu_start(struct arm_pmu *cpu_pmu)
 static void xscale1pmu_stop(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
@@ -485,7 +485,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 	unsigned long pmnc, of_flags;
 	struct perf_sample_data data;
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
-	struct pmu_hw_events *cpuc = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 	struct pt_regs *regs;
 	int idx;
 
@@ -539,7 +539,7 @@ static void xscale2pmu_enable_event(struct perf_event *event)
 	unsigned long flags, ien, evtsel;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	ien = xscale2pmu_read_int_enable();
@@ -585,7 +585,7 @@ static void xscale2pmu_disable_event(struct perf_event *event)
 	unsigned long flags, ien, evtsel, of_flags;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	ien = xscale2pmu_read_int_enable();
@@ -651,7 +651,7 @@ out:
 static void xscale2pmu_start(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
@@ -663,7 +663,7 @@ static void xscale2pmu_start(struct arm_pmu *cpu_pmu)
 static void xscale2pmu_stop(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
-	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc();
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 095399618ca5..d0be9a1ef6b8 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -2,6 +2,7 @@ menuconfig ARCH_TEGRA
 	bool "NVIDIA Tegra" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_TRUSTED_FOUNDATIONS
+	select ARM_AMBA
 	select ARM_GIC
 	select CLKSRC_MMIO
 	select HAVE_ARM_SCU if SMP
@@ -59,12 +60,4 @@ config ARCH_TEGRA_124_SOC
 	  Support for NVIDIA Tegra T124 processor family, based on the
 	  ARM CortexA15MP CPU
 
-config TEGRA_AHB
-	bool "Enable AHB driver for NVIDIA Tegra SoCs"
-	default y
-	help
-	  Adds AHB configuration functionality for NVIDIA Tegra SoCs,
-	  which controls AHB bus master arbitration and some
-	  performance parameters(priority, prefech size).
-
 endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7c79c6494379..6caad5428178 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -169,9 +169,6 @@ endmenu
 
 menu "Bus support"
 
-config ARM_AMBA
-	bool
-
 config PCI
 	bool "PCI support"
 	help
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f19097134b02..b1fa4e614718 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -104,6 +104,15 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
+static inline u64 arch_counter_get_cntpct(void)
+{
+	/*
+	 * AArch64 kernel and user space mandate the use of CNTVCT.
+	 */
+	BUG();
+	return 0;
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 42632c7a2a4e..9cfa3706a1b8 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -137,13 +137,16 @@ static inline void set_iommu_table_base_and_group(struct device *dev,
 	iommu_add_device(dev);
 }
 
-extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
-			struct scatterlist *sglist, int nelems,
-			unsigned long mask, enum dma_data_direction direction,
-			struct dma_attrs *attrs);
-extern void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
-			   int nelems, enum dma_data_direction direction,
-			   struct dma_attrs *attrs);
+extern int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
+			    struct scatterlist *sglist, int nelems,
+			    unsigned long mask,
+			    enum dma_data_direction direction,
+			    struct dma_attrs *attrs);
+extern void ppc_iommu_unmap_sg(struct iommu_table *tbl,
+			       struct scatterlist *sglist,
+			       int nelems,
+			       enum dma_data_direction direction,
+			       struct dma_attrs *attrs);
 
 extern void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 				  size_t size, dma_addr_t *dma_handle,
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 54d0116256f7..4c68bfe4108a 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -60,16 +60,16 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction,
 			    struct dma_attrs *attrs)
 {
-	return iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
-			    device_to_mask(dev), direction, attrs);
+	return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
+				device_to_mask(dev), direction, attrs);
 }
 
 static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction,
 		struct dma_attrs *attrs)
 {
-	iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction,
-		       attrs);
+	ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+			   direction, attrs);
 }
 
 /* We support DMA to/from any memory page via the iommu */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index a10642a0d861..a83cf5ef6488 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -428,10 +428,10 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 		ppc_md.tce_flush(tbl);
 }
 
-int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
-		 struct scatterlist *sglist, int nelems,
-		 unsigned long mask, enum dma_data_direction direction,
-		 struct dma_attrs *attrs)
+int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
+		     struct scatterlist *sglist, int nelems,
+		     unsigned long mask, enum dma_data_direction direction,
+		     struct dma_attrs *attrs)
 {
 	dma_addr_t dma_next = 0, dma_addr;
 	struct scatterlist *s, *outs, *segstart;
@@ -539,7 +539,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
 	DBG("mapped %d elements:\n", outcount);
 
-	/* For the sake of iommu_unmap_sg, we clear out the length in the
+	/* For the sake of ppc_iommu_unmap_sg, we clear out the length in the
 	 * next entry of the sglist if we didn't fill the list completely
 	 */
 	if (outcount < incount) {
@@ -572,9 +572,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 }
 
 
-void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction,
-		struct dma_attrs *attrs)
+void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
+			int nelems, enum dma_data_direction direction,
+			struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 2b90ff8a93be..c7c8720aa39f 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -621,8 +621,9 @@ static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
 	if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))
 		return dma_direct_ops.map_sg(dev, sg, nents, direction, attrs);
 	else
-		return iommu_map_sg(dev, cell_get_iommu_table(dev), sg, nents,
-				    device_to_mask(dev), direction, attrs);
+		return ppc_iommu_map_sg(dev, cell_get_iommu_table(dev), sg,
+					nents, device_to_mask(dev),
+					direction, attrs);
 }
 
 static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
@@ -632,8 +633,8 @@ static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
 	if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))
 		dma_direct_ops.unmap_sg(dev, sg, nents, direction, attrs);
 	else
-		iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents, direction,
-			       attrs);
+		ppc_iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents,
+				   direction, attrs);
 }
 
 static int dma_fixed_dma_supported(struct device *dev, u64 mask)