Merge branch 'perf/urgent' into perf/core

Merge reason: We are going to queue up a dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

66 files changed, 314 insertions, 133 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a48aecc17ea..dfb0312f4e7 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1280,7 +1280,7 @@ config ARM_ERRATA_743622
 	depends on CPU_V7
 	help
 	  This option enables the workaround for the 743622 Cortex-A9
-	  (r2p0..r2p2) erratum. Under very rare conditions, a faulty
+	  (r2p*) erratum. Under very rare conditions, a faulty
 	  optimisation in the Cortex-A9 Store Buffer may lead to data
 	  corruption. This workaround sets a specific bit in the diagnostic
 	  register of the Cortex-A9 which disables the Store Buffer
diff --git a/arch/arm/boot/.gitignore b/arch/arm/boot/.gitignore
index ce1c5ff746e..3c79f85975a 100644
--- a/arch/arm/boot/.gitignore
+++ b/arch/arm/boot/.gitignore
@@ -3,3 +3,4 @@ zImage
 xipImage
 bootpImage
 uImage
+*.dtb
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index b5a5be2536c..90114faa9f3 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -134,7 +134,7 @@ 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 idx);
 
 int armpmu_event_set_period(struct perf_event *event,
 			    struct hw_perf_event *hwc,
diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c
index 4dd0edab6a6..1651d495074 100644
--- a/arch/arm/kernel/ecard.c
+++ b/arch/arm/kernel/ecard.c
@@ -242,6 +242,7 @@ static void ecard_init_pgtables(struct mm_struct *mm)
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
 
+	vma.vm_flags = VM_EXEC;
 	vma.vm_mm = mm;
 
 	flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 5bb91bf3d47..b2abfa18f13 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -180,7 +180,7 @@ armpmu_event_set_period(struct perf_event *event,
 u64
 armpmu_event_update(struct perf_event *event,
 		    struct hw_perf_event *hwc,
-		    int idx, int overflow)
+		    int idx)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	u64 delta, prev_raw_count, new_raw_count;
@@ -193,13 +193,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	new_raw_count &= armpmu->max_period;
-	prev_raw_count &= armpmu->max_period;
-
-	if (overflow)
-		delta = armpmu->max_period - prev_raw_count + new_raw_count + 1;
-	else
-		delta = new_raw_count - prev_raw_count;
+	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
 
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
@@ -216,7 +210,7 @@ armpmu_read(struct perf_event *event)
 	if (hwc->idx < 0)
 		return;
 
-	armpmu_event_update(event, hwc, hwc->idx, 0);
+	armpmu_event_update(event, hwc, hwc->idx);
 }
 
 static void
@@ -232,7 +226,7 @@ armpmu_stop(struct perf_event *event, int flags)
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		armpmu->disable(hwc, hwc->idx);
 		barrier(); /* why? */
-		armpmu_event_update(event, hwc, hwc->idx, 0);
+		armpmu_event_update(event, hwc, hwc->idx);
 		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
 	}
 }
@@ -518,7 +512,13 @@ __hw_perf_event_init(struct perf_event *event)
 	hwc->config_base	    |= (unsigned long)mapping;
 
 	if (!hwc->sample_period) {
-		hwc->sample_period  = armpmu->max_period;
+		/*
+		 * For non-sampling runs, limit the sample_period to half
+		 * of the counter width. That way, the new counter value
+		 * is far less likely to overtake the previous one unless
+		 * you have some serious IRQ latency issues.
+		 */
+		hwc->sample_period  = armpmu->max_period >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -680,6 +680,28 @@ static void __init cpu_pmu_init(struct arm_pmu *armpmu)
 }
 
 /*
+ * 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 __cpuinit pmu_cpu_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(NULL);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata pmu_cpu_notifier = {
+	.notifier_call = pmu_cpu_notify,
+};
+
+/*
  * CPU PMU identification and registration.
  */
 static int __init
@@ -730,6 +752,7 @@ init_hw_perf_events(void)
 		pr_info("enabled with %s PMU driver, %d counters available\n",
 			cpu_pmu->name, cpu_pmu->num_events);
 		cpu_pmu_init(cpu_pmu);
+		register_cpu_notifier(&pmu_cpu_notifier);
 		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
 	} else {
 		pr_info("no hardware support available\n");
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 533be9930ec..b78af0cc6ef 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -467,23 +467,6 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 	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
 armv6pmu_handle_irq(int irq_num,
 		    void *dev)
@@ -513,7 +496,8 @@ armv6pmu_handle_irq(int irq_num,
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!counter_is_active(pmcr, idx))
+		/* Ignore if we don't have an event. */
+		if (!event)
 			continue;
 
 		/*
@@ -524,7 +508,7 @@ armv6pmu_handle_irq(int irq_num,
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 6933244c68f..4d7095af2ab 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -809,6 +809,11 @@ static inline int armv7_pmnc_disable_intens(int idx)
 
 	counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
+	isb();
+	/* 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;
 }
 
@@ -955,6 +960,10 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
+		/* Ignore if we don't have an event. */
+		if (!event)
+			continue;
+
 		/*
 		 * We have a single interrupt for all counters. Check that
 		 * each counter has overflowed before we process it.
@@ -963,7 +972,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 3b99d826982..71a21e6712f 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -255,11 +255,14 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
+		if (!event)
+			continue;
+
 		if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
@@ -592,11 +595,14 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
+		if (!event)
+			continue;
+
+		if (!xscale2_pmnc_counter_has_overflowed(of_flags, idx))
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
@@ -663,7 +669,7 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 static void
 xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
-	unsigned long flags, ien, evtsel;
+	unsigned long flags, ien, evtsel, of_flags;
 	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
@@ -672,26 +678,31 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
 		ien &= ~XSCALE2_CCOUNT_INT_EN;
+		of_flags = XSCALE2_CCOUNT_OVERFLOW;
 		break;
 	case XSCALE_COUNTER0:
 		ien &= ~XSCALE2_COUNT0_INT_EN;
 		evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
+		of_flags = XSCALE2_COUNT0_OVERFLOW;
 		break;
 	case XSCALE_COUNTER1:
 		ien &= ~XSCALE2_COUNT1_INT_EN;
 		evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
+		of_flags = XSCALE2_COUNT1_OVERFLOW;
 		break;
 	case XSCALE_COUNTER2:
 		ien &= ~XSCALE2_COUNT2_INT_EN;
 		evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
+		of_flags = XSCALE2_COUNT2_OVERFLOW;
 		break;
 	case XSCALE_COUNTER3:
 		ien &= ~XSCALE2_COUNT3_INT_EN;
 		evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
+		of_flags = XSCALE2_COUNT3_OVERFLOW;
 		break;
 	default:
 		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
@@ -701,6 +712,7 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
+	xscale2pmu_write_overflow_flags(of_flags);
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index b7582dd10dc..96e2adcd5a8 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -38,10 +38,6 @@
 #if defined(CONFIG_AT_HDMAC) || defined(CONFIG_AT_HDMAC_MODULE)
 static u64 hdmac_dmamask = DMA_BIT_MASK(32);
 
-static struct at_dma_platform_data atdma_pdata = {
-	.nr_channels	= 8,
-};
-
 static struct resource hdmac_resources[] = {
 	[0] = {
 		.start	= AT91SAM9G45_BASE_DMA,
@@ -56,12 +52,11 @@ static struct resource hdmac_resources[] = {
 };
 
 static struct platform_device at_hdmac_device = {
-	.name		= "at_hdmac",
+	.name		= "at91sam9g45_dma",
 	.id		= -1,
 	.dev		= {
 				.dma_mask		= &hdmac_dmamask,
 				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &atdma_pdata,
 	},
 	.resource	= hdmac_resources,
 	.num_resources	= ARRAY_SIZE(hdmac_resources),
@@ -69,9 +64,15 @@ static struct platform_device at_hdmac_device = {
 
 void __init at91_add_device_hdmac(void)
 {
-	dma_cap_set(DMA_MEMCPY, atdma_pdata.cap_mask);
-	dma_cap_set(DMA_SLAVE, atdma_pdata.cap_mask);
-	platform_device_register(&at_hdmac_device);
+#if defined(CONFIG_OF)
+	struct device_node *of_node =
+		of_find_node_by_name(NULL, "dma-controller");
+
+	if (of_node)
+		of_node_put(of_node);
+	else
+#endif
+		platform_device_register(&at_hdmac_device);
 }
 #else
 void __init at91_add_device_hdmac(void) {}
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index 61908dce978..9be71c11d0f 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -33,10 +33,6 @@
 #if defined(CONFIG_AT_HDMAC) || defined(CONFIG_AT_HDMAC_MODULE)
 static u64 hdmac_dmamask = DMA_BIT_MASK(32);
 
-static struct at_dma_platform_data atdma_pdata = {
-	.nr_channels	= 2,
-};
-
 static struct resource hdmac_resources[] = {
 	[0] = {
 		.start	= AT91SAM9RL_BASE_DMA,
@@ -51,12 +47,11 @@ static struct resource hdmac_resources[] = {
 };
 
 static struct platform_device at_hdmac_device = {
-	.name		= "at_hdmac",
+	.name		= "at91sam9rl_dma",
 	.id		= -1,
 	.dev		= {
 				.dma_mask		= &hdmac_dmamask,
 				.coherent_dma_mask	= DMA_BIT_MASK(32),
-				.platform_data		= &atdma_pdata,
 	},
 	.resource	= hdmac_resources,
 	.num_resources	= ARRAY_SIZE(hdmac_resources),
@@ -64,7 +59,6 @@ static struct platform_device at_hdmac_device = {
 
 void __init at91_add_device_hdmac(void)
 {
-	dma_cap_set(DMA_MEMCPY, atdma_pdata.cap_mask);
 	platform_device_register(&at_hdmac_device);
 }
 #else
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index d5fb44f16d3..d67d0b4feb6 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -34,6 +34,7 @@
 #include <mach/ep93xx_spi.h>
 #include <mach/gpio-ep93xx.h>
 
+#include <asm/hardware/vic.h>
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
@@ -361,6 +362,7 @@ MACHINE_START(VISION_EP9307, "Vision Engraving Systems EP9307")
 	.atag_offset	= 0x100,
 	.map_io		= vision_map_io,
 	.init_irq	= ep93xx_init_irq,
+	.handle_irq	= vic_handle_irq,
 	.timer		= &ep93xx_timer,
 	.init_machine	= vision_init_machine,
 	.restart	= ep93xx_restart,
diff --git a/arch/arm/mach-exynos/mach-universal_c210.c b/arch/arm/mach-exynos/mach-universal_c210.c
index 0fc65ffde8f..38939956c34 100644
--- a/arch/arm/mach-exynos/mach-universal_c210.c
+++ b/arch/arm/mach-exynos/mach-universal_c210.c
@@ -13,6 +13,7 @@
 #include <linux/i2c.h>
 #include <linux/gpio_keys.h>
 #include <linux/gpio.h>
+#include <linux/interrupt.h>
 #include <linux/fb.h>
 #include <linux/mfd/max8998.h>
 #include <linux/regulator/machine.h>
@@ -595,6 +596,7 @@ static struct mxt_platform_data qt602240_platform_data = {
 	.threshold	= 0x28,
 	.voltage	= 2800000,		/* 2.8V */
 	.orient		= MXT_DIAGONAL,
+	.irqflags	= IRQF_TRIGGER_FALLING,
 };
 
 static struct i2c_board_info i2c3_devs[] __initdata = {
diff --git a/arch/arm/mach-lpc32xx/include/mach/irqs.h b/arch/arm/mach-lpc32xx/include/mach/irqs.h
index 2667f52e3b0..9e3b90df32e 100644
--- a/arch/arm/mach-lpc32xx/include/mach/irqs.h
+++ b/arch/arm/mach-lpc32xx/include/mach/irqs.h
@@ -61,7 +61,7 @@
  */
 #define IRQ_LPC32XX_JTAG_COMM_TX	LPC32XX_SIC1_IRQ(1)
 #define IRQ_LPC32XX_JTAG_COMM_RX	LPC32XX_SIC1_IRQ(2)
-#define IRQ_LPC32XX_GPI_11		LPC32XX_SIC1_IRQ(4)
+#define IRQ_LPC32XX_GPI_28		LPC32XX_SIC1_IRQ(4)
 #define IRQ_LPC32XX_TS_P		LPC32XX_SIC1_IRQ(6)
 #define IRQ_LPC32XX_TS_IRQ		LPC32XX_SIC1_IRQ(7)
 #define IRQ_LPC32XX_TS_AUX		LPC32XX_SIC1_IRQ(8)
diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c
index 4eae566dfdc..c74de01ab5b 100644
--- a/arch/arm/mach-lpc32xx/irq.c
+++ b/arch/arm/mach-lpc32xx/irq.c
@@ -118,6 +118,10 @@ static const struct lpc32xx_event_info lpc32xx_events[NR_IRQS] = {
 		.event_group = &lpc32xx_event_pin_regs,
 		.mask = LPC32XX_CLKPWR_EXTSRC_GPI_06_BIT,
 	},
+	[IRQ_LPC32XX_GPI_28] = {
+		.event_group = &lpc32xx_event_pin_regs,
+		.mask = LPC32XX_CLKPWR_EXTSRC_GPI_28_BIT,
+	},
 	[IRQ_LPC32XX_GPIO_00] = {
 		.event_group = &lpc32xx_event_int_regs,
 		.mask = LPC32XX_CLKPWR_INTSRC_GPIO_00_BIT,
@@ -305,9 +309,18 @@ static int lpc32xx_irq_wake(struct irq_data *d, unsigned int state)
 
 		if (state)
 			eventreg |= lpc32xx_events[d->irq].mask;
-		else
+		else {
 			eventreg &= ~lpc32xx_events[d->irq].mask;
 
+			/*
+			 * When disabling the wakeup, clear the latched
+			 * event
+			 */
+			__raw_writel(lpc32xx_events[d->irq].mask,
+				lpc32xx_events[d->irq].
+				event_group->rawstat_reg);
+		}
+
 		__raw_writel(eventreg,
 			lpc32xx_events[d->irq].event_group->enab_reg);
 
@@ -380,13 +393,15 @@ void __init lpc32xx_init_irq(void)
 
 	/* Setup SIC1 */
 	__raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_SIC1_BASE));
-	__raw_writel(MIC_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC1_BASE));
-	__raw_writel(MIC_ATR_DEFAULT, LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC1_BASE));
+	__raw_writel(SIC1_APR_DEFAULT, LPC32XX_INTC_POLAR(LPC32XX_SIC1_BASE));
+	__raw_writel(SIC1_ATR_DEFAULT,
+				LPC32XX_INTC_ACT_TYPE(LPC32XX_SIC1_BASE));
 
 	/* Setup SIC2 */
 	__raw_writel(0, LPC32XX_INTC_MASK(LPC32XX_SIC2_BASE));
-	__raw_writel(MIC_APR_DEFAULT,