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.

79 files changed, 1618 insertions, 160 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
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 495ab6f84a61..eaf54a30bedc 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -148,6 +148,15 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
 
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
 #define KVM_ARM_IRQ_TYPE_MASK		0xff
diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h
index 05b7d39e4391..66fc24c24238 100644
--- a/arch/microblaze/include/asm/delay.h
+++ b/arch/microblaze/include/asm/delay.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_MICROBLAZE_DELAY_H
 #define _ASM_MICROBLAZE_DELAY_H
 
+#include <linux/param.h>
+
 extern inline void __delay(unsigned long loops)
 {
 	asm volatile ("# __delay		\n\t"		\
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index a2cea7206077..3fbb7f1db3bc 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -89,6 +89,11 @@ static inline unsigned int readl(const volatile void __iomem *addr)
 {
 	return le32_to_cpu(*(volatile unsigned int __force *)addr);
 }
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return le64_to_cpu(__raw_readq(addr));
+}
 static inline void writeb(unsigned char v, volatile void __iomem *addr)
 {
 	*(volatile unsigned char __force *)addr = v;
@@ -101,6 +106,7 @@ static inline void writel(unsigned int v, volatile void __iomem *addr)
 {
 	*(volatile unsigned int __force *)addr = cpu_to_le32(v);
 }
+#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr)
 
 /* ioread and iowrite variants. thease are for now same as __raw_
  * variants of accessors. we might check for endianess in the feature
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index b7fb0438458c..17645b2e2f07 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -66,7 +66,7 @@ real_start:
 	mts	rmsr, r0
 /* Disable stack protection from bootloader */
 	mts	rslr, r0
-	addi	r8, r0, 0xFFFFFFF
+	addi	r8, r0, 0xFFFFFFFF
 	mts	rshr, r8
 /*
  * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc'
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index e27e9ad6818e..150866b2a3fe 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -134,6 +134,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 }
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
+extern int __dma_set_mask(struct device *dev, u64 dma_mask);
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index f7a8036579b5..42632c7a2a4e 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -77,6 +77,7 @@ struct iommu_table {
 #ifdef CONFIG_IOMMU_API
 	struct iommu_group *it_group;
 #endif
+	void (*set_bypass)(struct iommu_table *tbl, bool enable);
 };
 
 /* Pure 2^n version of get_order */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4ee06fe15de4..d0e784e0ff48 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,6 +8,7 @@
 
 #ifdef __powerpc64__
 
+extern char __start_interrupts[];
 extern char __end_interrupts[];
 
 extern char __prom_init_toc_start[];
@@ -21,6 +22,17 @@ static inline int in_kernel_text(unsigned long addr)
 	return 0;
 }
 
+static inline int overlaps_interrupt_vector_text(unsigned long start,
+							unsigned long end)
+{
+	unsigned long real_start, real_end;
+	real_start = __start_interrupts - _stext;
+	real_end = __end_interrupts - _stext;
+
+	return start < (unsigned long)__va(real_end) &&
+		(unsigned long)__va(real_start) < end;
+}
+
 static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 {
 	return start < (unsigned long)__init_end &&
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 8032b97ccdcb..ee78f6e49d64 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
-int dma_set_mask(struct device *dev, u64 dma_mask)
+int __dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	if (ppc_md.dma_set_mask)
-		return ppc_md.dma_set_mask(dev, dma_mask);
 	if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
 		return dma_ops->set_dma_mask(dev, dma_mask);
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
@@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 	*dev->dma_mask = dma_mask;
 	return 0;
 }
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (ppc_md.dma_set_mask)
+		return ppc_md.dma_set_mask(dev, dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
 EXPORT_SYMBOL(dma_set_mask);
 
 u64 dma_get_required_mask(struct device *dev)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7bb30dca4e19..fdc679d309ec 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -362,9 +362,13 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	 */
 	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
 		return NULL;
+
 	driver = eeh_pcid_get(dev);
-	if (driver && driver->err_handler)
-		return NULL;
+	if (driver) {
+		eeh_pcid_put(dev);
+		if (driver->err_handler)
+			return NULL;
+	}
 
 	/* Remove it from PCI subsystem */
 	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d773dd440a45..88e3ec6e1d96 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	memset(tbl->it_map, 0xff, sz);
 	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
 
+	/*
+	 * Disable iommu bypass, otherwise the user can DMA to all of
+	 * our physical memory via the bypass window instead of just
+	 * the pages that has been explicitly mapped into the iommu
+	 */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, false);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_take_ownership);
@@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl)
 	/* Restore bit#0 set by iommu_init_table() */
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
+
+	/* The kernel owns the device now, we can restore the iommu bypass */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, true);
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9729b23bfb0a..1d0848bba049 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -559,8 +559,13 @@ void exc_lvl_ctx_init(void)
 #ifdef CONFIG_PPC64
 		cpu_nr = i;
 #else
+#ifdef CONFIG_SMP
 		cpu_nr = get_hard_smp_processor_id(i);
+#else
+		cpu_nr = 0;
 #endif
+#endif
+
 		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
 		tp = critirq_ctx[cpu_nr];
 		tp->cpu = cpu_nr;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 75d4f7340da8..015ae55c1868 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
 
 /* Values we need to export to the second kernel via the device tree. */
 static phys_addr_t kernel_end;
+static phys_addr_t crashk_base;
 static phys_addr_t crashk_size;
+static unsigned long long mem_limit;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
@@ -207,7 +209,7 @@ static struct property kernel_end_prop = {
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
 	.length = sizeof(phys_addr_t),
-	.value = &crashk_res.start,
+	.value = &crashk_base
 };
 
 static struct property crashk_size_prop = {
@@ -219,9 +221,11 @@ static struct property crashk_size_prop = {
 static struct property memory_limit_prop = {
 	.name = "linux,memory-limit",
 	.length = sizeof(unsigned long long),
-	.value = &memory_limit,
+	.value = &mem_limit,
 };
 
+#define cpu_to_be_ulong	__PASTE(cpu_to_be, BITS_PER_LONG)
+
 static void __init export_crashk_values(struct device_node *node)
 {
 	struct property *prop;
@@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node)
 		of_remove_property(node, prop);
 
 	if (crashk_res.start != 0) {
+		crashk_base = cpu_to_be_ulong(crashk_res.start),
 		of_add_property(node, &crashk_base_prop);
-		crashk_size = resource_size(&crashk_res);
+		crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
 		of_add_property(node, &crashk_size_prop);
 	}
 
@@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node)
 	 * memory_limit is required by the kexec-tools to limit the
 	 * crash regions to the actual memory used.
 	 */
+	mem_limit = cpu_to_be_ulong(memory_limit);
 	of_update_property(node, &memory_limit_prop);
 }
 
@@ -264,7 +270,7 @@ static int __init kexec_setup(void)
 		of_remove_property(node, prop);
 
 	/* information needed by userspace when using default_machine_kexec */
-	kernel_end = __pa(_end);
+	kernel_end = cpu_to_be_ulong(__pa(_end));
 	of_add_property(node, &kernel_end_prop);
 
 	export_crashk_values(node);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index be4e6d648f60..59d229a2a3e0 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image)
 
 /* Values we need to export to the second kernel via the device tree. */
 static unsigned long htab_base;
+static unsigned long htab_size;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -379,7 +380,7 @@ static struct property htab_base_prop = {
 static struct property htab_size_prop = {
 	.name = "linux,htab-size",
 	.length = sizeof(unsigned long),
-	.value = &htab_size_bytes,
+	.value = &htab_size,
 };
 
 static int __init export_htab_values(void)
@@ -403,8 +404,9 @@ static int __init export_htab_values(void)
 	if (prop)
 		of_remove_property(node, prop);
 
-	htab_base = __pa(htab_address);
+	htab_base = cpu_to_be64(__pa(htab_address));
 	of_add_property(node, &htab_base_prop);
+	htab_size = cpu_to_be64(htab_size_bytes);
 	of_add_property(node, &htab_size_prop);
 
 	of_node_put(node);
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1ab001..1482327cfeba 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -69,8 +69,8 @@ _GLOBAL(relocate)
 	 * R_PPC64_RELATIVE ones.
 	 */
 	mtctr	r8
-5:	lwz	r0,12(9)	/* ELF64_R_TYPE(reloc->r_info) */
-	cmpwi	r0,R_PPC64_RELATIVE
+5:	ld	r0,8(9)		/* ELF64_R_TYPE(reloc->r_info) */
+	cmpdi	r0,R_PPC64_RELATIVE
 	bne	6f
 	ld	r6,0(r9)	/* reloc->r_offset */
 	ld	r0,16(r9)	/* reloc->r_addend */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 2b0da27eaee4..04cc4fcca78b 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -247,7 +247,12 @@ static void __init exc_lvl_early_init(void)
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
 	for_each_possible_cpu(i) {
+#ifdef CONFIG_SMP
 		hw_cpu = get_hard_smp_processor_id(i);
+#else
+		hw_cpu = 0;
+#endif
+
 		critirq_ctx[hw_cpu] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index de6881259aef..d766d6ee33fe 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,20 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/*
+		 * If relocatable, check if it overlaps interrupt vectors that
+		 * are copied down to real 0. For relocatable kernel
+		 * (e.g. kdump case) we copy interrupt vectors down to real
+		 * address 0. Mark that region as executable. This is
+		 * because on p8 system with relocation on exception feature
+		 * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
+		 * in order to execute the interrupt handlers in virtual
+		 * mode the vector region need to be marked as executable.
+		 */
+		if ((PHYSICAL_START > MEMORY_START) &&
+			overlaps_interrupt_vector_text(vaddr, vaddr + step))
+				tprot &= ~HPTE_R_N;
+
 		hash = hpt_hash(vpn, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29b89e863d7c..67cf22083f4c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1147,6 +1147,9 @@ static void power_pmu_enable(struct pmu *pmu)
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
+	if (cpuhw->bhrb_users)
+		ppmu->config_bhrb(cpuhw->bhrb_filter);
+
 	write_mmcr0(cpuhw, mmcr0);
 
 	/*
@@ -1158,8 +1161,6 @@ static void power_pmu_enable(struct pmu *pmu)
 	}
 
  out:
-	if (cpuhw->bhrb_users)
-		ppmu->config_bhrb(cpuhw->bhrb_filter);
 
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index a3f7abd2f13f..96cee20dcd34 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -25,6 +25,37 @@
 #define PM_BRU_FIN			0x10068
 #define PM_BR_MPRED_CMPL		0x400f6
 
+/* All L1 D cache load references counted at finish, gated by reject */
+#define PM_LD_REF_L1			0x100ee
+/* Load Missed L1 */
+#define PM_LD_MISS_L1			0x3e054
+/* Store Missed L1 */
+#define PM_ST_MISS_L1			0x300f0
+/* L1 cache data prefetches */
+#define PM_L1_PREF			0x0d8b8
+/* Instruction fetches from L1 */
+#define PM_INST_FROM_L1			0x04080
+/* Demand iCache Miss */
+#define PM_L1_ICACHE_MISS		0x200fd
+/* Instruction Demand sectors wriittent into IL1 */
+#define PM_L1_DEMAND_WRITE		0x0408c
+/* Instruction prefetch written into IL1 */
+#define PM_IC_PREF_WRITE		0x0408e
+/* The data cache was reloaded from local core's L3 due to a demand load */
+#define PM_DATA_FROM_L3			0x4c042
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+#define PM_DATA_FROM_L3MISS		0x300fe
+/* All successful D-side store dispatches for this thread */
+#define PM_L2_ST			0x17080
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+#define PM_L2_ST_MISS			0x17082
+/* Total HW L3 prefetches(Load+store) */
+#define PM_L3_PREF_ALL			0x4e052
+/* Data PTEG reload */
+#define PM_DTLB_MISS			0x300fc
+/* ITLB Reloaded */
+#define PM_ITLB_MISS			0x400fc
+
 
 /*
  * Raw event encoding for POWER8:
@@ -557,6 +588,8 @@ static int power8_generic_events[] = {
 	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BRU_FIN,
 	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1,
 };
 
 static u64 power8_bhrb_filter_map(u64 branch_sample_type)
@@ -596,6 +629,116 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter)
 	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
 }
 
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+			[ C(RESULT_MISS)   ] = PM_LD_MISS_L1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ST_MISS_L1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_PREF,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+			[ C(RESULT_MISS)   ] = PM_L1_ICACHE_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L2_ST,
+			[ C(RESULT_MISS)   ] = PM_L2_ST_MISS,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_DTLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ITLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_BRU_FIN,
+			[ C(RESULT_MISS)   ] = PM_BR_MPRED_CMPL,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
 static struct power_pmu power8_pmu = {
 	.name			= "POWER8",
 	.n_counter		= 6,
@@ -611,6 +754,7 @@ static struct power_pmu power8_pmu = {
 	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
+	.cache_events		= &power8_cache_events,
 	.attr_groups		= power8_pmu_attr_groups,
 	.bhrb_nr		= 32,
 };
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7d6dcc6d5fa9..3b2b4fb3585b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/memblock.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
+	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
 	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
+static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
+				     struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	uint64_t top;
+	bool bypass = false;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return -ENODEV;;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (pe->tce_bypass_enabled) {
+		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		bypass = (dma_mask >= top);
+	}
+
+	if (bypass) {
+		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
+		set_dma_ops(&pdev->dev, &dma_direct_ops);
+		set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	} else {
+		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
+		set_dma_ops(&pdev->dev, &dma_iommu_ops);
+		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	}
+	return 0;
+}
+
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
 	struct pci_dev *dev;
@@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
 }
 
+static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+{
+	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+					      tce32_table);
+	uint16_t window_id = (pe->pe_number << 1 ) + 1;
+	int64_t rc;
+
+	pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
+	if (enable) {
+		phys_addr_t top = memblock_end_of_DRAM();
+
+		top = roundup_pow_of_two(top);
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     top);
+	} else {
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     0);
+
+		/*
+		 * We might want to reset the DMA ops of all devices on
+		 * this PE. However in theory, that shouldn't be necessary
+		 * as this is used for VFIO/KVM pass-through and the device
+		 * hasn't yet been returned to its kernel driver
+		 */
+	}
+	if (rc)
+		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
+	else
+		pe->tce_bypass_enabled = enable;
+}
+
+static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
+					  struct pnv_ioda_pe *pe)
+{
+	/* TVE #1 is selected by PCI address bit 59 */
+	pe->tce_bypass_base = 1ull << 59;
+
+	/* Install set_bypass callback for VFIO */
+	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+
+	/* Enable bypass by default */
+	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+}
+
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe)
 {
@@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
+	/* Also create a bypass window */
+	pnv_pci_ioda2_setup_bypass_pe(phb, pe);
 	return;
 fail:
 	if (pe->tce32_seg >= 0)
@@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b555ebc57ef5..95633d79ef5d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -634,6 +634,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb && phb->dma_set_mask)
+		return phb->dma_set_mask(phb, pdev, dma_mask);
+	return __dma_set_mask(&pdev->dev, dma_mask);
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 13f1942a9a5f..cde169442775 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -54,7 +54,9 @@ struct pnv_ioda_pe {
 	struct iommu_table	tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
-	/* XXX TODO: Add support for additional 64-bit iommus */
+	/* 64-bit TCE bypass region */
+	bool			tce_bypass_enabled;
+	uint64_t		tce_bypass_base;
 
 	/* MSIs. MVE index is identical for for 32 and 64 bit MSI
 	 * and -1 if not supported. (It's actually identical to the
@@ -113,6 +115,8 @@ struct pnv_phb {
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
+			    u64 dma_mask);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index de6819be1f95..0051e108ef0f 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,12 +7,20 @@ extern void pnv_smp_init(void);
 static inline void pnv_smp_init(void) { }
 #endif
 
+struct pci_dev;
+
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
+extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
+
+static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	return -ENODEV;
+}
 #endif
 
 extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f65c97c..110f4fbd319f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/bug.h>
 #include <linux/cpuidle.h>
+#include <linux/pci.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -141,6 +142,13 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
+static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (dev_is_pci(dev))
+		return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
+
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -238,6 +246,7 @@ define_machine(powernv) {
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = powernv_idle,
 	.calibrate_decr		= generic_calibrate_decr,
+	.dma_set_mask		= pnv_dma_set_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 37300f6ee244..80b1d57c306a 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -20,6 +20,7 @@ config PPC_PSERIES
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
 	select HOTPLUG_CPU if SMP
+	select ARCH_RANDOM
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 8e639d7cbda7..972df0ffd4dc 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -430,8 +430,7 @@ static void pSeries_machine_kexec(struct kimage *image)
 {
 	long rc;
 
-	if (firmware_has_feature(FW_FEATURE_SET_MODE) &&
-	    (image->type != KEXEC_TYPE_CRASH)) {
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		rc = pSeries_disable_reloc_on_exc();
 		if (rc != H_SUCCESS)
 			pr_warning("Warning: Failed to disable relocation on "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0e166ed4cd16..8209744b2829 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -886,25 +886,25 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 
 	/* Default: read HW settings */
 	if (flow_type == IRQ_TYPE_DEFAULT) {
-		switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
-			       MPIC_INFO(VECPRI_SENSE_MASK))) {
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_EDGE_RISING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_EDGE_FALLING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_LEVEL_HIGH;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_LEVEL_LOW;
-				break;
-		}
+		int vold_ps;
+
+		vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
+				  MPIC_INFO(VECPRI_SENSE_MASK));
+
+		if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_EDGE_RISING;
+		else if	(vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_EDGE_FALLING;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_LEVEL_HIGH;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_LEVEL_LOW;
+		else
+			WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold);
 	}
 
 	/* Apply to irq desc */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a90731b3d44a..b07909850f77 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -309,16 +309,23 @@ static void get_output_lock(void)
 
 	if (xmon_speaker == me)
 		return;
+
 	for (;;) {
-		if (xmon_speaker == 0) {
-			last_speaker = cmpxchg(&xmon_speaker, 0, me);
-			if (last_speaker == 0)
-				return;
-		}
-		timeout = 10000000;
+		last_speaker = cmpxchg(&xmon_speaker, 0, me);
+		if (last_speaker == 0)
+			return;
+
+		/*
+		 * Wait a full second for the lock, we might be on a slow
+		 * console, but check every 100us.
+		 */
+		timeout = 10000;
 		while (xmon_speaker == last_speaker) {
-			if (--timeout > 0)
+			if (--timeout > 0) {
+				udelay(100);
 				continue;
+			}
+
 			/* hostile takeover */
 			prev = cmpxchg(&xmon_speaker, last_speaker, me);
 			if (prev == last_speaker)
@@ -397,7 +404,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 	}
 
 	xmon_fault_jmp[cpu] = recurse_jmp;
-	cpumask_set_cpu(cpu, &cpus_in_xmon);
 
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
@@ -419,6 +425,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		release_output_lock();
 	}
 
+	cpumask_set_cpu(cpu, &cpus_in_xmon);
+
  waiting:
 	secondary = 1;
 	while (secondary && !xmon_gate) {
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 4c4a1cef5208..47c8630c93cd 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -529,6 +529,7 @@ static int __init appldata_init(void)
 {
 	int rc;
 
+	init_virt_timer(&appldata_timer);
 	appldata_timer.function = appldata_timer_function;
 	appldata_timer.data = (unsigned long) &appldata_work;
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae2579c..d7c00507568a 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@ ENTRY(startup_continue)
 	.quad	0			# cr12: tracing off
 	.quad	0			# cr13: home space segment table
 	.quad	0xc0000000		# cr14: machine check handling off
-	.quad	0			# cr15: linkage stack operations
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
 .Lpcmsk:.quad	0x0000000180000000
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
@@ -67,12 +67,15 @@ ENTRY(startup_continue)
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
-.Lduct: .long	0,0,0,0,.Lduald,0,0,0
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
 	.long	0,0,0,0,0,0,0,0
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
 	.align	128
 .Lduald:.rept	8
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 
 ENTRY(_ehead)
 
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e9dfb0..27c50f4d90cb 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
 
 #define ESSA_SET_STABLE		1
 #define ESSA_SET_UNUSED		2
@@ -41,6 +43,14 @@ void __init cmma_init(void)
 
 	if (!cmma_flag)
 		return;
+	/*
+	 * Disable CMM for dump, otherwise  the tprot based memory
+	 * detection can fail because of unstable pages.
+	 */
+	if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+		cmma_flag = 0;
+		return;
+	}
 	asm volatile(
 		"       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
 		"0:     la      %0,0\n"
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3b978c472d08..3d6b9f81cc68 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -132,6 +132,8 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
 extern void efi_setup_page_tables(void);
 extern void __init old_map_region(efi_memory_desc_t *md);
+extern void __init runtime_code_page_mkexec(void);
+extern void __init efi_runtime_mkexec(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index bbc8b12fa443..5ad38ad07890 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -445,10 +445,20 @@ static inline int pte_same(pte_t a, pte_t b)
 	return a.pte == b.pte;
 }
 
+static inline int pteval_present(pteval_t pteval)
+{
+	/*
+	 * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this
+	 * way clearly states that the intent is that protnone and numa
+	 * hinting ptes are considered present for the purposes of
+	 * pagetable operations like zapping, protection changes, gup etc.
+	 */
+	return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA);
+}
+
 static inline int pte_present(pte_t a)
 {
-	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
-			       _PAGE_NUMA);
+	return pteval_present(pte_flags(a));
 }
 
 #define pte_accessible pte_accessible
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 24b6fd10625a..8e28bf2fc3ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
-	if (cpu_has(c, X86_FEATURE_SMAP))
+	if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
 		set_in_cr4(X86_CR4_SMAP);
+#else
+		clear_in_cr4(X86_CR4_SMAP);
+#endif
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d4bdd253fea7..e6253195a301 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa_symbol(ip));
 
-	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+	return ip;
 }
 
 static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
+	ip = text_ip_addr(ip);
+
 	/* replace the text with the new text */
-	if (do_ftrace_mod_code(ip, new_code))
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	sync_core();
@@ -221,37 +222,51 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 	return -EINVAL;
 }
 
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
 {
-	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	unsigned char old[MCOUNT_INSN_SIZE];
 	int ret;
 
-	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, (unsigned long)func);
+	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+	ftrace_update_func = ip;
+	/* Make sure the breakpoints see the ftrace_update_func update */
+	smp_wmb();
 
 	/* See comment above by declaration of modifying_ftrace_code */
 	atomic_inc(&modifying_ftrace_code);
 
 	ret = ftrace_modify_code(ip, old, new);
 
+	atomic_dec(&modifying_ftrace_code);
+
+	return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char *new;
+	int ret;
+
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
 	/* Also update the regs callback function */
 	if (!ret) {
 		ip = (unsigned long)(&ftrace_regs_call);
-		memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(ip, (unsigned long)func);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = update_ftrace_func(ip, new);
 	}
 
-	atomic_dec(&modifying_ftrace_code);
-
 	return ret;
 }
 
 static int is_ftrace_caller(unsigned long ip)
 {
-	if (ip == (unsigned long)(&ftrace_call) ||
-		ip == (unsigned long)(&ftrace_regs_call))
+	if (ip == ftrace_update_func)
 		return 1;
 
 	return 0;
@@ -677,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data)
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
 
-static int ftrace_mod_jmp(unsigned long ip,
-			  int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
-	unsigned char code[MCOUNT_INSN_SIZE];
+	static union ftrace_code_union calc;
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	/* Jmp not a call (ignore the .e8) */
+	calc.e8		= 0xe9;
+	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
 
-	if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
-		return -EINVAL;
+	/*
+	 * ftrace external locks synchronize the access to the static variable.
+	 */
+	return calc.code;
+}
 
-	*(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+	unsigned char *new;
 
-	if (do_ftrace_mod_code(ip, &code))
-		return -EPERM;
+	new = ftrace_jmp_replace(ip, (unsigned long)func);
 
-	return 0;
+	return update_ftrace_func(ip, new);
 }
 
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
 
-	old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_graph_caller);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
-
-	old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
 
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
 
 #endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19e5adb49a27..acb3b606613e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -209,7 +209,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	 * dance when its actually needed.
 	 */
 
-	preempt_disable();
+	preempt_disable_notrace();
 	data = this_cpu_read(cyc2ns.head);
 	tail = this_cpu_read(cyc2ns.tail);
 
@@ -229,7 +229,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 		if (!--data->__count)
 			this_cpu_write(cyc2ns.tail, data);
 	}
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return ns;
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d591c895803..6dea040cc3a1 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1001,6 +1001,12 @@ static int fault_in_kernel_space(unsigned long address)
 
 static inline bool smap_violation(int error_code, struct pt_regs *regs)
 {
+	if (!IS_ENABLED(CONFIG_X86_SMAP))
+		return false;
+
+	if (!static_cpu_has(X86_FEATURE_SMAP))
+		return false;
+
 	if (error_code & PF_USER)
 		return false;
 
@@ -1087,11 +1093,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
+	if (unlikely(smap_violation(error_code, regs))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
 	/*
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 4df9591eadad..f15103dff4b4 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -42,7 +42,7 @@ void __init efi_bgrt_init(void)
 
 	if (bgrt_tab->header.length < sizeof(*bgrt_tab))
 		return;
-	if (bgrt_tab->version != 1)
+	if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
 		return;
 	if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
 		return;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d62ec87a2b26..1a201ac7cef8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -792,7 +792,7 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
 		set_memory_nx(addr, npages);
 }
 
-static void __init runtime_code_page_mkexec(void)
+void __init runtime_code_page_mkexec(void)
 {
 	efi_memory_desc_t *md;
 	void *p;
@@ -1069,8 +1069,7 @@ void __init efi_enter_virtual_mode(void)
 	efi.update_capsule = virt_efi_update_capsule;
 	efi.query_capsule_caps = virt_efi_query_capsule_caps;
 
-	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
-		runtime_code_page_mkexec();
+	efi_runtime_mkexec();
 
 	kfree(new_memmap);
 
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 249b183cf417..0b74cdf7f816 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -77,3 +77,9 @@ void efi_call_phys_epilog(void)
 
 	local_irq_restore(efi_rt_eflags);
 }
+
+void __init efi_runtime_mkexec(void)
+{
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6284f158a47d..0c2a234fef1e 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -233,3 +233,12 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 {
 	efi_setup = phys_addr + sizeof(struct setup_data);
 }
+
+void __init efi_runtime_mkexec(void)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2423ef04ffea..256282e7888b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 /* Assume pteval_t is equivalent to all the other *val_t types. */
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
-	if (val & _PAGE_PRESENT) {
+	if (pteval_present(val)) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		unsigned long pfn = mfn_to_pfn(mfn);
 
@@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 
 static pteval_t pte_pfn_to_mfn(pteval_t val)
 {
-	if (val & _PAGE_PRESENT) {
+	if (pteval_present(val)) {
 		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & PTE_FLAGS_MASK;
 		unsigned long mfn;