Merge branch 'for-rmk/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into devel-stable

  * Support for Qualcomm Krait processors (run perf on your phone!)
  * Support for Cortex-A12 (run perf stat on your FPGA!)
  * Support for perf_sample_event_took, allowing us to automatically decrease
    the sample rate if we can't handle the PMU interrupts quickly enough
    (run perf record on your FPGA!).

As part of the Krait support, we also gain support for PPI generation by
the PMU.

38 files changed, 1107 insertions, 60 deletions

diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index b9d6a8b485e0..6d1e43d46187 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -38,6 +38,7 @@ dtb-$(CONFIG_ARCH_AT91) += at91sam9g35ek.dtb
 dtb-$(CONFIG_ARCH_AT91) += at91sam9x25ek.dtb
 dtb-$(CONFIG_ARCH_AT91) += at91sam9x35ek.dtb
 # sama5d3
+dtb-$(CONFIG_ARCH_AT91)	+= at91-sama5d3_xplained.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d31ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d33ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d34ek.dtb
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
new file mode 100644
index 000000000000..ce1375595e5f
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -0,0 +1,229 @@
+/*
+ * at91-sama5d3_xplained.dts - Device Tree file for the SAMA5D3 Xplained board
+ *
+ *  Copyright (C) 2014 Atmel,
+ *		  2014 Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+/dts-v1/;
+#include "sama5d36.dtsi"
+
+/ {
+	model = "SAMA5D3 Xplained";
+	compatible = "atmel,sama5d3-xplained", "atmel,sama5d3", "atmel,sama5";
+
+	chosen {
+		bootargs = "console=ttyS0,115200";
+	};
+
+	memory {
+		reg = <0x20000000 0x10000000>;
+	};
+
+	ahb {
+		apb {
+			mmc0: mmc@f0000000 {
+				pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_dat4_7 &pinctrl_mmc0_cd>;
+				status = "okay";
+				slot@0 {
+					reg = <0>;
+					bus-width = <8>;
+					cd-gpios = <&pioE 0 GPIO_ACTIVE_LOW>;
+				};
+			};
+
+			spi0: spi@f0004000 {
+				cs-gpios = <&pioD 13 0>;
+				status = "okay";
+			};
+
+			can0: can@f000c000 {
+				status = "okay";
+			};
+
+			i2c0: i2c@f0014000 {
+				status = "okay";
+			};
+
+			i2c1: i2c@f0018000 {
+				status = "okay";
+			};
+
+			macb0: ethernet@f0028000 {
+				phy-mode = "rgmii";
+				status = "okay";
+			};
+
+			usart0: serial@f001c000 {
+				status = "okay";
+			};
+
+			usart1: serial@f0020000 {
+				pinctrl-0 = <&pinctrl_usart1 &pinctrl_usart1_rts_cts>;
+				status = "okay";
+			};
+
+			uart0: serial@f0024000 {
+				status = "okay";
+			};
+
+			mmc1: mmc@f8000000 {
+				pinctrl-0 = <&pinctrl_mmc1_clk_cmd_dat0 &pinctrl_mmc1_dat1_3 &pinctrl_mmc1_cd>;
+				status = "okay";
+				slot@0 {
+					reg = <0>;
+					bus-width = <4>;
+					cd-gpios = <&pioE 1 GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			spi1: spi@f8008000 {
+				cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>;
+				status = "okay";
+			};
+
+			adc0: adc@f8018000 {
+				pinctrl-0 = <
+					&pinctrl_adc0_adtrg
+					&pinctrl_adc0_ad0
+					&pinctrl_adc0_ad1
+					&pinctrl_adc0_ad2
+					&pinctrl_adc0_ad3
+					&pinctrl_adc0_ad4
+					&pinctrl_adc0_ad5
+					&pinctrl_adc0_ad6
+					&pinctrl_adc0_ad7
+					&pinctrl_adc0_ad8
+					&pinctrl_adc0_ad9
+					>;
+				status = "okay";
+			};
+
+			i2c2: i2c@f801c000 {
+				dmas = <0>, <0>;	/* Do not use DMA for i2c2 */
+				status = "okay";
+			};
+
+			macb1: ethernet@f802c000 {
+				phy-mode = "rmii";
+				status = "okay";
+			};
+
+			dbgu: serial@ffffee00 {
+				status = "okay";
+			};
+
+			pinctrl@fffff200 {
+				board {
+					pinctrl_mmc0_cd: mmc0_cd {
+						atmel,pins =
+							<AT91_PIOE 0 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_mmc1_cd: mmc1_cd {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_usba_vbus: usba_vbus {
+						atmel,pins =
+							<AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>;	/* PE9, conflicts with A9 */
+					};
+				};
+			};
+
+			pmc: pmc@fffffc00 {
+				main: mainck {
+					clock-frequency = <12000000>;
+				};
+			};
+		};
+
+		nand0: nand@60000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "hw";
+			atmel,has-pmecc;
+			atmel,pmecc-cap = <4>;
+			atmel,pmecc-sector-size = <512>;
+			nand-on-flash-bbt;
+			status = "okay";
+
+			at91bootstrap@0 {
+				label = "at91bootstrap";
+				reg = <0x0 0x40000>;
+			};
+
+			bootloader@40000 {
+				label = "bootloader";
+				reg = <0x40000 0x80000>;
+			};
+
+			bootloaderenv@c0000 {
+				label = "bootloader env";
+				reg = <0xc0000 0xc0000>;
+			};
+
+			dtb@180000 {
+				label = "device tree";
+				reg = <0x180000 0x80000>;
+			};
+
+			kernel@200000 {
+				label = "kernel";
+				reg = <0x200000 0x600000>;
+			};
+
+			rootfs@800000 {
+				label = "rootfs";
+				reg = <0x800000 0x0f800000>;
+			};
+		};
+
+		usb0: gadget@00500000 {
+			atmel,vbus-gpio = <&pioE 9 GPIO_ACTIVE_HIGH>;	/* PE9, conflicts with A9 */
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usba_vbus>;
+			status = "okay";
+		};
+
+		usb1: ohci@00600000 {
+			num-ports = <3>;
+			atmel,vbus-gpio = <0
+					   &pioE 3 GPIO_ACTIVE_LOW
+					   &pioE 4 GPIO_ACTIVE_LOW
+					  >;
+			status = "okay";
+		};
+
+		usb2: ehci@00700000 {
+			status = "okay";
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		bp3 {
+			label = "PB_USER";
+			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
+			linux,code = <0x104>;
+			gpio-key,wakeup;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		d2 {
+			label = "d2";
+			gpios = <&pioE 23 GPIO_ACTIVE_LOW>;	/* PE23, conflicts with A23, CTS2 */
+			linux,default-trigger = "heartbeat";
+		};
+
+		d3 {
+			label = "d3";
+			gpios = <&pioE 24 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 0042f73068b0..fece8665fb63 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -523,7 +523,7 @@
 			};
 
 			i2c0: i2c@fff88000 {
-				compatible = "atmel,at91sam9263-i2c";
+				compatible = "atmel,at91sam9260-i2c";
 				reg = <0xfff88000 0x100>;
 				interrupts = <13 IRQ_TYPE_LEVEL_HIGH 6>;
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index e9487f6f0166..924a6a6ffd0f 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -124,6 +124,10 @@
 			nand-on-flash-bbt;
 			status = "okay";
 		};
+
+		usb0: ohci@00500000 {
+			status = "okay";
+		};
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 52447c17537a..3d5faf85f51b 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1228,7 +1228,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>,
 				 <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 0c1e8d871ed1..6cb9b68e2188 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -188,7 +188,6 @@
 		msp2: msp@80117000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&msp2_default_mode>;
-			status = "okay";
 		};
 
 		msp3: msp@80125000 {
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 040bb0eba152..10666ca8aee1 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -315,7 +315,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <55>;
 			clocks = <&ahb_gates 17>;
@@ -323,7 +323,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index ea16054857a4..64961595e8d6 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -278,7 +278,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <55>;
 			clocks = <&ahb_gates 17>;
@@ -286,7 +286,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 119f066f0d98..9ff09484847b 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -340,7 +340,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <0 55 4>;
 			clocks = <&ahb_gates 17>;
@@ -348,7 +348,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 845bc745706b..ee6982976d66 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -29,6 +29,7 @@ CONFIG_ARCH_OMAP3=y
 CONFIG_ARCH_OMAP4=y
 CONFIG_SOC_OMAP5=y
 CONFIG_SOC_AM33XX=y
+CONFIG_SOC_DRA7XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SOCFPGA=y
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad26c70..ae1919be8f98 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -71,6 +71,8 @@ struct arm_pmu {
 	void		(*disable)(struct perf_event *event);
 	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
 					 struct perf_event *event);
+	void		(*clear_event_idx)(struct pmu_hw_events *hw_events,
+					 struct perf_event *event);
 	int		(*set_event_filter)(struct hw_perf_event *evt,
 					    struct perf_event_attr *attr);
 	u32		(*read_counter)(struct perf_event *event);
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 789d846a9184..a6bc431cde70 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -16,6 +16,8 @@
 #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>
@@ -205,6 +207,8 @@ armpmu_del(struct perf_event *event, int flags)
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
+	if (armpmu->clear_event_idx)
+		armpmu->clear_event_idx(hw_events, event);
 
 	perf_event_update_userpage(event);
 }
@@ -295,14 +299,27 @@ validate_group(struct perf_event *event)
 
 static irqreturn_t armpmu_dispatch_irq(int irq, void *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);
+	struct arm_pmu *armpmu;
+	struct platform_device *plat_device;
+	struct arm_pmu_platdata *plat;
+	int ret;
+	u64 start_clock, finish_clock;
 
+	if (irq_is_percpu(irq))
+		dev = *(void **)dev;
+	armpmu = dev;
+	plat_device = armpmu->plat_device;
+	plat = dev_get_platdata(&plat_device->dev);
+
+	start_clock = sched_clock();
 	if (plat && plat->handle_irq)
-		return plat->handle_irq(irq, dev, armpmu->handle_irq);
+		ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
 	else
-		return armpmu->handle_irq(irq, dev);
+		ret = armpmu->handle_irq(irq, dev);
+	finish_clock = sched_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+	return ret;
 }
 
 static void
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 20d553c9f5e2..51798d7854ac 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -25,6 +25,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
 
 #include <asm/cputype.h>
 #include <asm/irq_regs.h>
@@ -33,6 +35,7 @@
 /* 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);
@@ -71,6 +74,26 @@ 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)
+{
+	struct arm_pmu *cpu_pmu = data;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int irq = platform_get_irq(pmu_device, 0);
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+	cpumask_set_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
+}
+
+static void cpu_pmu_disable_percpu_irq(void *data)
+{
+	struct arm_pmu *cpu_pmu = data;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int irq = platform_get_irq(pmu_device, 0);
+
+	cpumask_clear_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
+	disable_percpu_irq(irq);
+}
+
 static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 {
 	int i, irq, irqs;
@@ -78,12 +101,18 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
-	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);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		on_each_cpu(cpu_pmu_disable_percpu_irq, cpu_pmu, 1);
+		free_percpu_irq(irq, &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);
+		}
 	}
 }
 
@@ -101,33 +130,44 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 		return -ENODEV;
 	}
 
-	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, handler,
-				  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
-				  cpu_pmu);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, handler, "arm-pmu", &percpu_pmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",
 				irq);
 			return err;
 		}
-
-		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		on_each_cpu(cpu_pmu_enable_percpu_irq, cpu_pmu, 1);
+	} else {
+		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, handler,
+					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+					  cpu_pmu);
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+					irq);
+				return err;
+			}
+
+			cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		}
 	}
 
 	return 0;
@@ -141,6 +181,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
 		raw_spin_lock_init(&events->pmu_lock);
+		per_cpu(percpu_pmu, cpu) = cpu_pmu;
 	}
 
 	cpu_pmu->get_hw_events	= cpu_pmu_get_cpu_events;
@@ -181,6 +222,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = {
  */
 static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
+	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
 	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
 	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
 	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
@@ -188,6 +230,7 @@ static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
 	{.compatible = "arm,arm1176-pmu",	.data = armv6pmu_init},
 	{.compatible = "arm,arm1136-pmu",	.data = armv6pmu_init},
+	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
 	{},
 };
 
@@ -225,15 +268,6 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 		case ARM_CPU_PART_CORTEX_A9:
 			ret = armv7_a9_pmu_init(pmu);
 			break;
-		case ARM_CPU_PART_CORTEX_A5:
-			ret = armv7_a5_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A15:
-			ret = armv7_a15_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A7:
-			ret = armv7_a7_pmu_init(pmu);
-			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (implementor == ARM_CPU_IMP_INTEL) {
@@ -270,6 +304,9 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	cpu_pmu = pmu;
+	cpu_pmu->plat_device = pdev;
+
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
 		init_fn = of_id->data;
 		ret = init_fn(pmu);
@@ -282,8 +319,6 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	cpu_pmu = pmu;
-	cpu_pmu->plat_device = pdev;
 	cpu_pmu_init(cpu_pmu);
 	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 039cffb053a7..f4ef3981ed02 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -18,6 +18,10 @@
 
 #ifdef CONFIG_CPU_V7
 
+#include <asm/cp15.h>
+#include <asm/vfp.h>
+#include "../vfp/vfpinstr.h"
+
 /*
  * Common ARMv7 event types
  *
@@ -109,6 +113,33 @@ enum armv7_a15_perf_types {
 	ARMV7_A15_PERFCTR_PC_WRITE_SPEC			= 0x76,
 };
 
+/* ARMv7 Cortex-A12 specific event types */
+enum armv7_a12_perf_types {
+	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ		= 0x40,
+	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE	= 0x41,
+
+	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ		= 0x50,
+	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE		= 0x51,
+
+	ARMV7_A12_PERFCTR_PC_WRITE_SPEC			= 0x76,
+
+	ARMV7_A12_PERFCTR_PF_TLB_REFILL			= 0xe7,
+};
+
+/* ARMv7 Krait specific event types */
+enum krait_perf_types {
+	KRAIT_PMRESR0_GROUP0				= 0xcc,
+	KRAIT_PMRESR1_GROUP0				= 0xd0,
+	KRAIT_PMRESR2_GROUP0				= 0xd4,
+	KRAIT_VPMRESR0_GROUP0				= 0xd8,
+
+	KRAIT_PERFCTR_L1_ICACHE_ACCESS			= 0x10011,
+	KRAIT_PERFCTR_L1_ICACHE_MISS			= 0x10010,
+
+	KRAIT_PERFCTR_L1_ITLB_ACCESS			= 0x12222,
+	KRAIT_PERFCTR_L1_DTLB_ACCESS			= 0x12210,
+};
+
 /*
  * Cortex-A8 HW events mapping
  *
@@ -732,6 +763,262 @@ static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
+ * Cortex-A12 HW events mapping
+ */
+static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A12_PERFCTR_PC_WRITE_SPEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a12_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		/*
+		 * Not all performance counters differentiate between read
+		 * and write accesses/misses so we're not always strictly
+		 * correct, but it's the best we can do. Writes and reads get
+		 * combined in these cases.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
+ * Krait HW events mapping
+ */
+static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					  [PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= KRAIT_PERFCTR_L1_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
  * Perf Events' indices
  */
 #define	ARMV7_IDX_CYCLE_COUNTER	0
@@ -1212,6 +1499,24 @@ static int armv7_a7_map_event(struct perf_event *event)
 				&armv7_a7_perf_cache_map, 0xFF);
 }
 
+static int armv7_a12_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &armv7_a12_perf_map,
+				&armv7_a12_perf_cache_map, 0xFF);
+}
+
+static int krait_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &krait_perf_map,
+				&krait_perf_cache_map, 0xFFFFF);
+}
+
+static int krait_map_event_no_branch(struct perf_event *event)
+{
+	return armpmu_map_event(event, &krait_perf_map_no_branch,
+				&krait_perf_cache_map, 0xFFFFF);
+}
+
 static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->handle_irq	= armv7pmu_handle_irq;
@@ -1283,6 +1588,408 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
 	return 0;
 }
+
+static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "ARMv7 Cortex-A12";
+	cpu_pmu->map_event	= armv7_a12_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	return 0;
+}
+
+/*
+ * Krait Performance Monitor Region Event Selection Register (PMRESRn)
+ *
+ *            31   30     24     16     8      0
+ *            +--------------------------------+
+ *  PMRESR0   | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 0
+ *            +--------------------------------+
+ *  PMRESR1   | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 1
+ *            +--------------------------------+
+ *  PMRESR2   | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 2
+ *            +--------------------------------+
+ *  VPMRESR0  | EN |  CC  |  CC  |  CC  |  CC  |   N = 2, R = ?
+ *            +--------------------------------+
+ *              EN | G=3  | G=2  | G=1  | G=0
+ *
+ *  Event Encoding:
+ *
+ *      hwc->config_base = 0xNRCCG
+ *
+ *      N  = prefix, 1 for Krait CPU (PMRESRn), 2 for Venum VFP (VPMRESR)
+ *      R  = region register
+ *      CC = class of events the group G is choosing from
+ *      G  = group or particular event
+ *
+ *  Example: 0x12021 is a Krait CPU event in PMRESR2's group 1 with code 2
+ *
+ *  A region (R) corresponds to a piece of the CPU (execution unit, instruction
+ *  unit, etc.) while the event code (CC) corresponds to a particular class of
+ *  events (interrupts for example). An event code is broken down into
+ *  groups (G) that can be mapped into the PMU (irq, fiqs, and irq+fiqs for
+ *  example).
+ */
+
+#define KRAIT_EVENT		(1 << 16)
+#define VENUM_EVENT		(2 << 16)
+#define KRAIT_EVENT_MASK	(KRAIT_EVENT | VENUM_EVENT)
+#define PMRESRn_EN		BIT(31)
+
+static u32 krait_read_pmresrn(int n)
+{
+	u32 val;
+
+	switch (n) {
+	case 0:
+		asm volatile("mrc p15, 1, %0, c9, c15, 0" : "=r" (val));
+		break;
+	case 1:
+		asm volatile("mrc p15, 1, %0, c9, c15, 1" : "=r" (val));
+		break;
+	case 2:
+		asm volatile("mrc p15, 1, %0, c9, c15, 2" : "=r" (val));
+		break;
+	default:
+		BUG(); /* Should be validated in krait_pmu_get_event_idx() */
+	}
+
+	return val;
+}
+
+static void krait_write_pmresrn(int n, u32 val)
+{
+	switch (n) {
+	case 0:
+		asm volatile("mcr p15, 1, %0, c9, c15, 0" : : "r" (val));
+		break;
+	case 1:
+		asm volatile("mcr p15, 1, %0, c9, c15, 1" : : "r" (val));
+		break;
+	case 2:
+		asm volatile("mcr p15, 1, %0, c9, c15, 2" : : "r" (val));
+		break;
+	default:
+		BUG(); /* Should be validated in krait_pmu_get_event_idx() */
+	}
+}
+
+static u32 krait_read_vpmresr0(void)
+{
+	u32 val;
+	asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void krait_write_vpmresr0(u32 val)
+{
+	asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
+}
+
+static void krait_pre_vpmresr0(u32 *venum_orig_val, u32 *fp_orig_val)
+{
+	u32 venum_new_val;
+	u32 fp_new_val;
+
+	BUG_ON(preemptible());
+	/* CPACR Enable CP10 and CP11 access */
+	*venum_orig_val = get_copro_access();
+	venum_new_val = *venum_orig_val | CPACC_SVC(10) | CPACC_SVC(11);
+	set_copro_access(venum_new_val);
+
+	/* Enable FPEXC */
+	*fp_orig_val = fmrx(FPEXC);
+	fp_new_val = *fp_orig_val | FPEXC_EN;
+	fmxr(FPEXC, fp_new_val);
+}
+
+static void krait_post_vpmresr0(u32 venum_orig_val, u32 fp_orig_val)
+{
+	BUG_ON(preemptible());
+	/* Restore FPEXC */
+	fmxr(FPEXC, fp_orig_val);
+	isb();
+	/* Restore CPACR */
+	set_copro_access(venum_orig_val);
+}
+
+static u32 krait_get_pmresrn_event(unsigned int region)
+{
+	static const u32 pmresrn_table[] = { KRAIT_PMRESR0_GROUP0,
+					     KRAIT_PMRESR1_GROUP0,
+					     KRAIT_PMRESR2_GROUP0 };
+	return pmresrn_table[region];
+}
+
+static void krait_evt_setup(int idx, u32 config_base)
+{
+	u32 val;
+	u32 mask;
+	u32 vval, fval;
+	unsigned int region;
+	unsigned int group;
+	unsigned int code;
+	unsigned int group_shift;
+	bool venum_event;
+
+	venum_event = !!(config_base & VENUM_EVENT);
+	region = (config_base >> 12) & 0xf;
+	code   = (config_base >> 4) & 0xff;
+	group  = (config_base >> 0)  & 0xf;
+
+	group_shift = group * 8;
+	mask = 0xff << group_shift;
+
+	/* Configure evtsel for the region and group */
+	if (venum_event)
+		val = KRAIT_VPMRESR0_GROUP0;
+	else
+		val = krait_get_pmresrn_event(region);
+	val += group;
+	/* Mix in mode-exclusion bits */
+	val |= config_base & (ARMV7_EXCLUDE_USER | ARMV7_EXCLUDE_PL1);
+	armv7_pmnc_write_evtsel(idx, val);
+
+	asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
+
+	if (venum_event) {
+		krait_pre_vpmresr0(&vval, &fval);
+		val = krait_read_vpmresr0();
+		val &= ~mask;
+		val |= code << group_shift;
+		val |= PMRESRn_EN;
+		krait_write_vpmresr0(val);
+		krait_post_vpmresr0(vval, fval);
+	} else {
+		val = krait_read_pmresrn(region);
+		val &= ~mask;
+		val |= code << group_shift;
+		val |= PMRESRn_EN;
+		krait_write_pmresrn(region, val);
+	}
+}
+
+static u32 krait_clear_pmresrn_group(u32 val, int group)
+{
+	u32 mask;
+	int group_shift;
+
+	group_shift = group * 8;
+	mask = 0xff << group_shift;
+	val &= ~mask;
+
+	/* Don't clear enable bit if entire region isn't disabled */
+	if (val & ~PMRESRn_EN)
+		return val |= PMRESRn_EN;
+
+	return 0;
+}
+
+static void krait_clearpmu(u32 config_base)
+{
+	u32 val;
+	u32 vval, fval;
+	unsigned int region;
+	unsigned int group;
+	bool venum_event;
+
+	venum_event = !!(config_base & VENUM_EVENT);
+	region = (config_base >> 12) & 0xf;
+	group  = (config_base >> 0)  & 0xf;
+
+	if (venum_event) {
+		krait_pre_vpmresr0(&vval, &fval);
+		val = krait_read_vpmresr0();
+		val = krait_clear_pmresrn_group(val, group);
+		krait_write_vpmresr0(val);
+		krait_post_vpmresr0(vval, fval);
+	} else {
+		val = krait_read_pmresrn(region);
+		val = krait_clear_pmresrn_group(val, group);
+		krait_write_pmresrn(region, val);
+	}
+}
+
+static void krait_pmu_disable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+
+	/* Disable counter and interrupt */
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Disable counter */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Clear pmresr code (if destined for PMNx counters)
+	 */
+	if (hwc->config_base & KRAIT_EVENT_MASK)
+		krait_clearpmu(hwc->config_base);
+
+	/* Disable interrupt for this counter */
+	armv7_pmnc_disable_intens(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void krait_pmu_enable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	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(&events->pmu_lock, flags);
+
+	/* Disable counter */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Set event (if destined for PMNx counters)
+	 * We set the event for the cycle counter because we
+	 * have the ability to perform event filtering.
+	 */
+	if (hwc->config_base & KRAIT_EVENT_MASK)
+		krait_evt_setup(idx, hwc->config_base);
+	else
+		armv7_pmnc_write_evtsel(idx, hwc->config_base);
+
+	/* Enable interrupt for this counter */
+	armv7_pmnc_enable_intens(idx);
+
+	/* Enable counter */
+	armv7_pmnc_enable_counter(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void krait_pmu_reset(void *info)
+{
+	u32 vval, fval;
+
+	armv7pmu_reset(info);
+
+	/* Clear all pmresrs */
+	krait_write_pmresrn(0, 0);
+	krait_write_pmresrn(1, 0);
+	krait_write_pmresrn(2, 0);
+
+	krait_pre_vpmresr0(&vval, &fval);
+	krait_write_vpmresr0(0);
+	krait_post_vpmresr0(vval, fval);
+}
+
+static int krait_event_to_bit(struct perf_event *event, unsigned int region,
+			      unsigned int group)
+{
+	int bit;
+	struct hw_perf_event *hwc = &event->hw;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+
+	if (hwc->config_base & VENUM_EVENT)
+		bit = KRAIT_VPMRESR0_GROUP0;
+	else
+		bit = krait_get_pmresrn_event(region);
+	bit -= krait_get_pmresrn_event(0);
+	bit += group;
+	/*
+	 * Lower bits are reserved for use by the counters (see
+	 * armv7pmu_get_event_idx() for more info)
+	 */
+	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+
+	return bit;
+}
+
+/*
+ * We check for column exclusion constraints here.
+ * Two events cant use the same group within a pmresr register.
+ */
+static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc,
+				   struct perf_event *event)
+{
+	int idx;
+	int bit;
+	unsigned int prefix;
+	unsigned int region;
+	unsigned int code;
+	unsigned int group;
+	bool krait_event;
+	struct hw_perf_event *hwc = &event->hw;
+
+	region = (hwc->config_base >> 12) & 0xf;
+	code   = (hwc->config_base >> 4) & 0xff;
+	group  = (hwc->config_base >> 0) & 0xf;
+	krait_event = !!(hwc->config_base & KRAIT_EVENT_MASK);
+
+	if (krait_event) {
+		/* Ignore invalid events */
+		if (group > 3 || region > 2)
+			return -EINVAL;
+		prefix = hwc->config_base & KRAIT_EVENT_MASK;
+		if (prefix != KRAIT_EVENT && prefix != VENUM_EVENT)
+			return -EINVAL;
+		if (prefix == VENUM_EVENT && (code & 0xe0))
+			return -EINVAL;
+
+		bit = krait_event_to_bit(event, region, group);
+		if (test_and_set_bit(bit, cpuc->used_mask))
+			return -EAGAIN;
+	}
+
+	idx = armv7pmu_get_event_idx(cpuc, event);
+	if (idx < 0 && krait_event)
+		clear_bit(bit, cpuc->used_mask);
+
+	return idx;
+}
+
+static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				      struct perf_event *event)
+{
+	int bit;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int region;
+	unsigned int group;
+	bool krait_event;
+
+	region = (hwc->config_base >> 12) & 0xf;
+	group  = (hwc->config_base >> 0) & 0xf;
+	krait_event = !!(hwc->config_base & KRAIT_EVENT_MASK);
+
+	if (krait_event) {
+		bit = krait_event_to_bit(event, region, group);
+		clear_bit(bit, cpuc->used_mask);
+	}
+}
+
+static int krait_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "ARMv7 Krait";
+	/* Some early versions of Krait don't support PC write events */
+	if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node,
+				  "qcom,no-pc-write"))
+		cpu_pmu->map_event = krait_map_event_no_branch;
+	else
+		cpu_pmu->map_event = krait_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	cpu_pmu->reset		= krait_pmu_reset;
+	cpu_pmu->enable		= krait_pmu_enable_event;
+	cpu_pmu->disable	= krait_pmu_disable_event;
+	cpu_pmu->get_event_idx	= krait_pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = krait_pmu_clear_event_idx;
+	return 0;
+}
 #else
 static inline int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
@@ -1308,4 +2015,14 @@ static inline int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
 }
+
+static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
 #endif	/* CONFIG_CPU_V7 */
diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig
index 8f4649b301b2..1abae5f6a418 100644
--- a/arch/arm/mach-hisi/Kconfig
+++ b/arch/arm/mach-hisi/Kconfig
@@ -8,7 +8,7 @@ config ARCH_HI3xxx
 	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
-	select HAVE_ARM_TWD
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select PINCTRL
 	select PINCTRL_SINGLE
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index af2e582d2b74..4d677f442539 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -482,6 +482,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	if (IS_ENABLED(CONFIG_PCI_IMX6))
 		clk_set_parent(clk[lvds1_sel], clk[sata_ref]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index 3781a1853998..4c86f3035205 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -266,6 +266,9 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	/* Audio-related clocks configuration */
 	clk_set_parent(clks[IMX6SL_CLK_SPDIF0_SEL], clks[IMX6SL_CLK_PLL3_PFD3]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index 9d47adc078aa..7a9b98589db7 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -236,8 +236,6 @@ void __init imx6q_pm_init(void)
 		regmap_update_bits(gpr, IOMUXC_GPR1, IMX6Q_GPR1_GINT,
 				   IMX6Q_GPR1_GINT);
 
-	/* Set initial power mode */
-	imx6q_set_lpm(WAIT_CLOCKED);
 
 	suspend_set_ops(&imx6q_pm_ops);
 }
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index ba470d64493b..3795ae28a613 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -2,7 +2,6 @@ config ARCH_MOXART
 	bool "MOXA ART SoC" if ARCH_MULTI_V4T
 	select CPU_FA526
 	select ARM_DMA_MEM_BUFFERABLE
-	select DMA_OF
 	select USE_OF
 	select CLKSRC_OF
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 653b489479e0..e2ce4f8366a7 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -54,7 +54,7 @@ config SOC_OMAP5
 	select ARM_GIC
 	select CPU_V7
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c
index c9f309ae88c5..8b90c4f2d430 100644
--- a/arch/arm/mach-pxa/am300epd.c
+++ b/arch/arm/mach-pxa/am300epd.c
@@ -30,6 +30,7 @@
 
 #include <mach/gumstix.h>
 #include <mach/mfp-pxa25x.h>
+#include <mach/irqs.h>
 #include <linux/platform_data/video-pxafb.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h
index 954641e6c8b1..1b0825911e62 100644
--- a/arch/arm/mach-pxa/include/mach/balloon3.h
+++ b/arch/arm/mach-pxa/include/mach/balloon3.h
@@ -14,6 +14,8 @@
 #ifndef ASM_ARCH_BALLOON3_H
 #define ASM_ARCH_BALLOON3_H
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
 enum balloon3_features {
 	BALLOON3_FEATURE_OHCI,
 	BALLOON3_FEATURE_MMC,
diff --git a/arch/arm/mach-pxa/include/mach/corgi.h b/arch/arm/mach-pxa/include/mach/corgi.h
index f3c3493b468d..c030d955bbd7 100644
--- a/arch/arm/mach-pxa/include/mach/corgi.h
+++ b/arch/arm/mach-pxa/include/mach/corgi.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_ARCH_CORGI_H
 #define __ASM_ARCH_CORGI_H  1
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
 
 /*
  * Corgi (Non Standard) GPIO Definitions
diff --git a/arch/arm/mach-pxa/include/mach/csb726.h b/arch/arm/mach-pxa/include/mach/csb726.h
index 2628e7b72116..00cfbbbf73f7 100644
--- a/arch/arm/mach-pxa/include/mach/csb726.h
+++ b/arch/arm/mach-pxa/include/mach/csb726.h
@@ -11,6 +11,8 @@
 #ifndef CSB726_H
 #define CSB726_H
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 #define CSB726_GPIO_IRQ_LAN	52
 #define CSB726_GPIO_IRQ_SM501	53
 #define CSB726_GPIO_MMC_DETECT	100
diff --git a/arch/arm/mach-pxa/include/mach/gumstix.h b/arch/arm/mach-pxa/include/mach/gumstix.h
index dba14b6503ad..f7df27bbb42e 100644
--- a/arch/arm/mach-pxa/include/mach/gumstix.h
+++ b/arch/arm/mach-pxa/include/mach/gumstix.h
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /* BTRESET - Reset line to Bluetooth module, active low signal. */
 #define GPIO_GUMSTIX_BTRESET          7
diff --git a/arch/arm/mach-pxa/include/mach/idp.h b/arch/arm/mach-pxa/include/mach/idp.h
index 22a96f87232b..7e63f4680271 100644
--- a/arch/arm/mach-pxa/include/mach/idp.h
+++ b/arch/arm/mach-pxa/include/mach/idp.h
@@ -23,6 +23,7 @@
  * IDP hardware.
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 #define IDP_FLASH_PHYS		(PXA_CS0_PHYS)
 #define IDP_ALT_FLASH_PHYS	(PXA_CS1_PHYS)
diff --git a/arch/arm/mach-pxa/include/mach/palmld.h b/arch/arm/mach-pxa/include/mach/palmld.h
index 2c4471336570..b184f296023b 100644
--- a/arch/arm/mach-pxa/include/mach/palmld.h
+++ b/arch/arm/mach-pxa/include/mach/palmld.h
@@ -13,6 +13,8 @@
 #ifndef _INCLUDE_PALMLD_H_
 #define _INCLUDE_PALMLD_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmt5.h b/arch/arm/mach-pxa/include/mach/palmt5.h
index 0bd4f036c72f..e342c5921405 100644
--- a/arch/arm/mach-pxa/include/mach/palmt5.h
+++ b/arch/arm/mach-pxa/include/mach/palmt5.h
@@ -15,6 +15,8 @@
 #ifndef _INCLUDE_PALMT5_H_
 #define _INCLUDE_PALMT5_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h
index c383a21680b6..81c727b3cfd2 100644
--- a/arch/arm/mach-pxa/include/mach/palmtc.h
+++ b/arch/arm/mach-pxa/include/mach/palmtc.h
@@ -16,6 +16,8 @@
 #ifndef _INCLUDE_PALMTC_H_
 #define _INCLUDE_PALMTC_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h
index f2e530380253..92bc1f05300d 100644
--- a/arch/arm/mach-pxa/include/mach/palmtx.h
+++ b/arch/arm/mach-pxa/include/mach/palmtx.h
@@ -16,6 +16,8 @@
 #ifndef _INCLUDE_PALMTX_H_
 #define _INCLUDE_PALMTX_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h
index 6bf28de228bd..86ebd7b6c960 100644
--- a/arch/arm/mach-pxa/include/mach/pcm027.h
+++ b/arch/arm/mach-pxa/include/mach/pcm027.h
@@ -23,6 +23,8 @@
  * Definitions of CPU card resources only
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /* phyCORE-PXA270 (PCM027) Interrupts */
 #define PCM027_IRQ(x)          (IRQ_BOARD_START + (x))
 #define PCM027_BTDET_IRQ       PCM027_IRQ(0)
diff --git a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
index 0260aaa2fc17..7e544c14967e 100644
--- a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
+++ b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
@@ -20,6 +20,7 @@
  */
 
 #include <mach/pcm027.h>
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /*
  * definitions relevant only when the PCM-990
diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h
index f32ff75dcca8..b56b19351a03 100644
--- a/arch/arm/mach-pxa/include/mach/poodle.h
+++ b/arch/arm/mach-pxa/include/mach/poodle.h
@@ -15,6 +15,8 @@
 #ifndef __ASM_ARCH_POODLE_H
 #define __ASM_ARCH_POODLE_H  1
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /*
  * GPIOs
  */
diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/include/mach/spitz.h
index 0bfe6507c95d..25c9f62e46aa 100644
--- a/arch/arm/mach-pxa/include/mach/spitz.h
+++ b/arch/arm/mach-pxa/include/mach/spitz.h
@@ -15,8 +15,8 @@
 #define __ASM_ARCH_SPITZ_H  1
 #endif
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */
 #include <linux/fb.h>
-#include <linux/gpio.h>
 
 /* Spitz/Akita GPIOs */
 
diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index 2bb0e862598c..0497d95cef25 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_ARCH_TOSA_H_
 #define _ASM_ARCH_TOSA_H_ 1
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
 /*  TOSA Chip selects  */
 #define TOSA_LCDC_PHYS		PXA_CS4_PHYS
 /* Internel Scoop */
diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h
index d2ca01053f69..ae3ca013afab 100644
--- a/arch/arm/mach-pxa/include/mach/trizeps4.h
+++ b/arch/arm/mach-pxa/include/mach/trizeps4.h
@@ -10,6 +10,8 @@
 #ifndef _TRIPEPS4_H_
 #define _TRIPEPS4_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /* physical memory regions */
 #define TRIZEPS4_FLASH_PHYS	(PXA_CS0_PHYS)  /* Flash region */
 #define TRIZEPS4_DISK_PHYS	(PXA_CS1_PHYS)  /* Disk On Chip region */
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 338640631e08..05fa505df585 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -8,7 +8,7 @@ config ARCH_SHMOBILE_MULTI
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select ARM_GIC
 	select MIGHT_HAVE_CACHE_L2X0
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 1db2a5ca9ab8..8c09a8393fb6 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -25,6 +25,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/of.h>
+#include <linux/memblock.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
 
@@ -41,6 +42,18 @@
 
 void __iomem *zynq_scu_base;
 
+/**
+ * zynq_memory_init - Initialize special memory
+ *
+ * We need to stop things allocating the low memory as DMA can't work in
+ * the 1st 512K of memory.
+ */
+static void __init zynq_memory_init(void)
+{
+	if (!__pa(PAGE_OFFSET))
+		memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+}
+
 static struct platform_device zynq_cpuidle_device = {
 	.name = "cpuidle-zynq",
 };
@@ -117,5 +130,6 @@ DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform")
 	.init_machine	= zynq_init_machine,
 	.init_time	= zynq_timer_init,
 	.dt_compat	= zynq_dt_match,
+	.reserve	= zynq_memory_init,
 	.restart	= zynq_system_reset,
 MACHINE_END