Merge tag 'v3.18-rc1' into x86/urgent

Reason:
Need to apply audit patch on top of v3.18-rc1.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

404 files changed, 4260 insertions, 2216 deletions

diff --git a/arch/alpha/include/asm/syscall.h b/arch/alpha/include/asm/syscall.h
new file mode 100644
index 000000000000..88d28eb2a566
--- /dev/null
+++ b/arch/alpha/include/asm/syscall.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_ALPHA_SYSCALL_H
+#define _ASM_ALPHA_SYSCALL_H
+
+#include <uapi/linux/audit.h>
+
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_ALPHA;
+}
+
+#endif	/* _ASM_ALPHA_SYSCALL_H */
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index c52e7f0ee5f6..5c218aa3f3df 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -431,7 +431,7 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  */
 static int alpha_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
@@ -483,7 +483,7 @@ static int alpha_pmu_add(struct perf_event *event, int flags)
  */
 static void alpha_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long irq_flags;
 	int j;
@@ -531,7 +531,7 @@ static void alpha_pmu_read(struct perf_event *event)
 static void alpha_pmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		cpuc->idx_mask &= ~(1UL<<hwc->idx);
@@ -551,7 +551,7 @@ static void alpha_pmu_stop(struct perf_event *event, int flags)
 static void alpha_pmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
 		return;
@@ -724,7 +724,7 @@ static int alpha_pmu_event_init(struct perf_event *event)
  */
 static void alpha_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->enabled)
 		return;
@@ -750,7 +750,7 @@ static void alpha_pmu_enable(struct pmu *pmu)
 
 static void alpha_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuc->enabled)
 		return;
@@ -814,8 +814,8 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	struct hw_perf_event *hwc;
 	int idx, j;
 
-	__get_cpu_var(irq_pmi_count)++;
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	__this_cpu_inc(irq_pmi_count);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* Completely counting through the PMC's period to trigger a new PMC
 	 * overflow interrupt while in this interrupt routine is utterly
diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index 86d835157b54..d9ee81769899 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -321,7 +321,7 @@ asmlinkage unsigned long syscall_trace_enter(void)
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
 	    tracehook_report_syscall_entry(current_pt_regs()))
 		ret = -1UL;
-	audit_syscall_entry(AUDIT_ARCH_ALPHA, regs->r0, regs->r16, regs->r17, regs->r18, regs->r19);
+	audit_syscall_entry(regs->r0, regs->r16, regs->r17, regs->r18, regs->r19);
 	return ret ?: current_pt_regs()->r0;
 }
 
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index ee39cee8064c..643a9dcdf093 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -56,9 +56,9 @@ unsigned long est_cycle_freq;
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()  __get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()  __this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()      __this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()     __this_cpu_write(irq_work_pending, 0)
 
 void arch_irq_work_raise(void)
 {
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index dceb0441b1a6..034a94904d69 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -50,8 +50,6 @@ AS		+= -EL
 LD		+= -EL
 endif
 
-comma = ,
-
 # This selects which instruction set is used.
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 7c80af906897..38c89cafa1ab 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -354,13 +354,15 @@ dtb-$(CONFIG_ARCH_ORION5X) += orion5x-lacie-d2-network.dtb \
 	orion5x-rd88f5182-nas.dtb
 dtb-$(CONFIG_ARCH_PRIMA2) += prima2-evb.dtb
 dtb-$(CONFIG_ARCH_QCOM) += \
+	qcom-apq8064-cm-qs600.dtb \
 	qcom-apq8064-ifc6410.dtb \
 	qcom-apq8074-dragonboard.dtb \
 	qcom-apq8084-ifc6540.dtb \
 	qcom-apq8084-mtp.dtb \
 	qcom-ipq8064-ap148.dtb \
 	qcom-msm8660-surf.dtb \
-	qcom-msm8960-cdp.dtb
+	qcom-msm8960-cdp.dtb \
+	qcom-msm8974-sony-xperia-honami.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += \
 	rk3066a-bqcurie2.dtb \
 	rk3188-radxarock.dtb \
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 1d52de6370d5..693a3275606f 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -132,6 +132,12 @@
 			reg = <0x10020000 0x4000>;
 		};
 
+		mipi_phy: video-phy@10020710 {
+			compatible = "samsung,s5pv210-mipi-video-phy";
+			reg = <0x10020710 8>;
+			#phy-cells = <1>;
+		};
+
 		pd_cam: cam-power-domain@10023C00 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023C00 0x20>;
@@ -163,8 +169,14 @@
 			#clock-cells = <1>;
 		};
 
+		cmu_dmc: clock-controller@105C0000 {
+			compatible = "samsung,exynos3250-cmu-dmc";
+			reg = <0x105C0000 0x2000>;
+			#clock-cells = <1>;
+		};
+
 		rtc: rtc@10070000 {
-			compatible = "samsung,s3c6410-rtc";
+			compatible = "samsung,exynos3250-rtc";
 			reg = <0x10070000 0x100>;
 			interrupts = <0 73 0>, <0 74 0>;
 			status = "disabled";
@@ -216,6 +228,33 @@
 			interrupts = <0 240 0>;
 		};
 
+		fimd: fimd@11c00000 {
+			compatible = "samsung,exynos3250-fimd";
+			reg = <0x11c00000 0x30000>;
+			interrupt-names = "fifo", "vsync", "lcd_sys";
+			interrupts = <0 84 0>, <0 85 0>, <0 86 0>;
+			clocks = <&cmu CLK_SCLK_FIMD0>, <&cmu CLK_FIMD0>;
+			clock-names = "sclk_fimd", "fimd";
+			samsung,power-domain = <&pd_lcd0>;
+			samsung,sysreg = <&sys_reg>;
+			status = "disabled";
+		};
+
+		dsi_0: dsi@11C80000 {
+			compatible = "samsung,exynos3250-mipi-dsi";
+			reg = <0x11C80000 0x10000>;
+			interrupts = <0 83 0>;
+			samsung,phy-type = <0>;
+			samsung,power-domain = <&pd_lcd0>;
+			phys = <&mipi_phy 1>;
+			phy-names = "dsim";
+			clocks = <&cmu CLK_DSIM0>, <&cmu CLK_SCLK_MIPI0>;
+			clock-names = "bus_clk", "pll_clk";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		mshc_0: mshc@12510000 {
 			compatible = "samsung,exynos5250-dw-mshc";
 			reg = <0x12510000 0x1000>;
diff --git a/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi b/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi
index 99b26df8dbc7..0865a2e33f97 100644
--- a/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi
@@ -675,7 +675,7 @@
 		sd4_bus8: sd4-bus-width8 {
 			samsung,pins = "gpk1-3", "gpk1-4", "gpk1-5", "gpk1-6";
 			samsung,pin-function = <4>;
-			samsung,pin-pud = <4>;
+			samsung,pin-pud = <3>;
 			samsung,pin-drv = <3>;
 		};
 
diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
index 4f2df61c1cfc..aa7a7d727a7e 100644
--- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts
+++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
@@ -368,3 +368,7 @@
 		};
 	};
 };
+
+&usbdrd_dwc3_1 {
+	dr_mode = "host";
+};
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index 9a233828539c..82cdb74484cc 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -838,6 +838,14 @@
 	status = "okay";
 };
 
+&usbdrd_dwc3_0 {
+	dr_mode = "host";
+};
+
+&usbdrd_dwc3_1 {
+	dr_mode = "host";
+};
+
 &usbdrd_phy0 {
 	vbus-supply = <&usb300_vbus_reg>;
 };
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index bfe056d9148c..8617a031cbc0 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -815,7 +815,7 @@
 		#size-cells = <1>;
 		ranges;
 
-		dwc3 {
+		usbdrd_dwc3_0: dwc3 {
 			compatible = "snps,dwc3";
 			reg = <0x12000000 0x10000>;
 			interrupts = <0 72 0>;
@@ -841,7 +841,7 @@
 		#size-cells = <1>;
 		ranges;
 
-		dwc3 {
+		usbdrd_dwc3_1: dwc3 {
 			compatible = "snps,dwc3";
 			reg = <0x12400000 0x10000>;
 			interrupts = <0 73 0>;
diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts
index 1d31c8132558..7bb1c8dd42dd 100644
--- a/arch/arm/boot/dts/exynos5800-peach-pi.dts
+++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts
@@ -826,6 +826,14 @@
 	status = "okay";
 };
 
+&usbdrd_dwc3_0 {
+	dr_mode = "host";
+};
+
+&usbdrd_dwc3_1 {
+	dr_mode = "host";
+};
+
 &usbdrd_phy0 {
 	vbus-supply = <&usb300_vbus_reg>;
 };
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 9b0494a8ab45..739fcf29c643 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -659,6 +659,9 @@
 
 	ethernet@gpmc {
 		compatible = "smsc,lan91c94";
+
+		status = "disabled";
+
 		interrupt-parent = <&gpio2>;
 		interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;	/* gpio54 */
 		reg = <1 0x300 0xf>;		/* 16 byte IO range at offset 0x300 */
diff --git a/arch/arm/boot/dts/pxa27x.dtsi b/arch/arm/boot/dts/pxa27x.dtsi
index a70546945985..80fc5d7e9ef9 100644
--- a/arch/arm/boot/dts/pxa27x.dtsi
+++ b/arch/arm/boot/dts/pxa27x.dtsi
@@ -1,5 +1,6 @@
 /* The pxa3xx skeleton simply augments the 2xx version */
-/include/ "pxa2xx.dtsi"
+#include "pxa2xx.dtsi"
+#include "dt-bindings/clock/pxa2xx-clock.h"
 
 / {
 	model = "Marvell PXA27x familiy SoC";
@@ -35,4 +36,21 @@
 			#pwm-cells = <1>;
 		};
 	};
+
+	clocks {
+	       /*
+		* The muxing of external clocks/internal dividers for osc* clock
+		* sources has been hidden under the carpet by now.
+		*/
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		pxa2xx_clks: pxa2xx_clks@41300004 {
+			compatible = "marvell,pxa-clocks";
+			#clock-cells = <1>;
+			status = "okay";
+		};
+	};
+
 };
diff --git a/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts b/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts
new file mode 100644
index 000000000000..5d75666f7f6c
--- /dev/null
+++ b/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts
@@ -0,0 +1,59 @@
+#include "qcom-apq8064-v2.0.dtsi"
+
+/ {
+	model = "CompuLab CM-QS600";
+	compatible = "qcom,apq8064-cm-qs600", "qcom,apq8064";
+
+	soc {
+		pinctrl@800000 {
+			i2c1_pins: i2c1 {
+				mux {
+					pins = "gpio20", "gpio21";
+					function = "gsbi1";
+				};
+			};
+		};
+
+		gsbi@12440000 {
+			status = "okay";
+			qcom,mode = <GSBI_PROT_I2C>;
+
+			i2c@12460000 {
+				status = "okay";
+				clock-frequency = <200000>;
+				pinctrl-0 = <&i2c1_pins>;
+				pinctrl-names = "default";
+
+				eeprom: eeprom@50 {
+					compatible = "24c02";
+					reg = <0x50>;
+					pagesize = <32>;
+				};
+			};
+		};
+
+		gsbi@16600000 {
+			status = "ok";
+			qcom,mode = <GSBI_PROT_I2C_UART>;
+			serial@16640000 {
+				status = "ok";
+			};
+		};
+
+		amba {
+			/* eMMC */
+			sdcc1: sdcc@12400000 {
+				status = "okay";
+			};
+
+			/* External micro SD card */
+			sdcc3: sdcc@12180000 {
+				status = "okay";
+			};
+			/* WLAN */
+			sdcc4: sdcc@121c0000 {
+				status = "okay";
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom-ipq8064-ap148.dts b/arch/arm/boot/dts/qcom-ipq8064-ap148.dts
index 95e64955fb8e..55b2910efd87 100644
--- a/arch/arm/boot/dts/qcom-ipq8064-ap148.dts
+++ b/arch/arm/boot/dts/qcom-ipq8064-ap148.dts
@@ -81,5 +81,13 @@
 				};
 			};
 		};
+
+		sata-phy@1b400000 {
+			status = "ok";
+		};
+
+		sata@29000000 {
+			status = "ok";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi
index 244f857f0e6f..63b2146f563b 100644
--- a/arch/arm/boot/dts/qcom-ipq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi
@@ -234,6 +234,39 @@
 			};
 		};
 
+		sata_phy: sata-phy@1b400000 {
+			compatible = "qcom,ipq806x-sata-phy";
+			reg = <0x1b400000 0x200>;
+
+			clocks = <&gcc SATA_PHY_CFG_CLK>;
+			clock-names = "cfg";
+
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
+		sata@29000000 {
+			compatible = "qcom,ipq806x-ahci", "generic-ahci";
+			reg = <0x29000000 0x180>;
+
+			interrupts = <0 209 0x0>;
+
+			clocks = <&gcc SFAB_SATA_S_H_CLK>,
+				 <&gcc SATA_H_CLK>,
+				 <&gcc SATA_A_CLK>,
+				 <&gcc SATA_RXOOB_CLK>,
+				 <&gcc SATA_PMALIVE_CLK>;
+			clock-names = "slave_face", "iface", "core",
+					"rxoob", "pmalive";
+
+			assigned-clocks = <&gcc SATA_RXOOB_CLK>, <&gcc SATA_PMALIVE_CLK>;
+			assigned-clock-rates = <100000000>, <100000000>;
+
+			phys = <&sata_phy>;
+			phy-names = "sata-phy";
+			status = "disabled";
+		};
+
 		qcom,ssbi@500000 {
 			compatible = "qcom,ssbi";
 			reg = <0x00500000 0x1000>;
diff --git a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
new file mode 100644
index 000000000000..cccc21b7c8fd
--- /dev/null
+++ b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
@@ -0,0 +1,17 @@
+#include "qcom-msm8974.dtsi"
+
+/ {
+	model = "Sony Xperia Z1";
+	compatible = "sony,xperia-honami", "qcom,msm8974";
+
+	memory@0 {
+		reg = <0 0x40000000>, <0x40000000 0x40000000>;
+		device_type = "memory";
+	};
+};
+
+&soc {
+	serial@f991e000 {
+		status = "ok";
+	};
+};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index d73a2287b37a..531272c0e526 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -287,7 +287,7 @@
 
 		mbus_clk: clk@01c2015c {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-mod0-clk";
+			compatible = "allwinner,sun5i-a13-mbus-clk";
 			reg = <0x01c2015c 0x4>;
 			clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
 			clock-output-names = "mbus";
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index c4b5d7825b9f..b131068f4f35 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -285,7 +285,7 @@
 
 		mbus_clk: clk@01c2015c {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-mod0-clk";
+			compatible = "allwinner,sun5i-a13-mbus-clk";
 			reg = <0x01c2015c 0x4>;
 			clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
 			clock-output-names = "mbus";
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index a96b99465069..82097c905c48 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -382,7 +382,7 @@
 
 		mbus_clk: clk@01c2015c {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-mod0-clk";
+			compatible = "allwinner,sun5i-a13-mbus-clk";
 			reg = <0x01c2015c 0x4>;
 			clocks = <&osc24M>, <&pll6 2>, <&pll5 1>;
 			clock-output-names = "mbus";
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index fc7d1683bf67..72058b8a6f4d 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -1,6 +1,7 @@
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_MODULES=y
@@ -54,12 +55,14 @@ CONFIG_SMSC911X=y
 CONFIG_USB_USBNET=y
 CONFIG_USB_NET_SMSC75XX=y
 CONFIG_USB_NET_SMSC95XX=y
+CONFIG_USB_GADGET=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 CONFIG_KEYBOARD_CROS_EC=y
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_CYAPA=y
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ATMEL_MXT=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_SAMSUNG=y
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
@@ -68,15 +71,18 @@ CONFIG_HW_RANDOM=y
 CONFIG_TCG_TPM=y
 CONFIG_TCG_TIS_I2C_INFINEON=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MUX=y
 CONFIG_I2C_ARB_GPIO_CHALLENGE=y
 CONFIG_I2C_EXYNOS5=y
+CONFIG_I2C_GPIO=y
 CONFIG_I2C_CROS_EC_TUNNEL=y
 CONFIG_SPI=y
 CONFIG_SPI_S3C64XX=y
 CONFIG_I2C_S3C2410=y
 CONFIG_DEBUG_GPIO=y
 CONFIG_POWER_SUPPLY=y
+CONFIG_BATTERY_SBS=y
 CONFIG_CHARGER_TPS65090=y
 # CONFIG_HWMON is not set
 CONFIG_THERMAL=y
@@ -88,6 +94,7 @@ CONFIG_MFD_CROS_EC=y
 CONFIG_MFD_CROS_EC_I2C=y
 CONFIG_MFD_CROS_EC_SPI=y
 CONFIG_MFD_MAX77686=y
+CONFIG_MFD_MAX77693=y
 CONFIG_MFD_MAX8997=y
 CONFIG_MFD_SEC_CORE=y
 CONFIG_MFD_TPS65090=y
@@ -96,6 +103,8 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_REGULATOR_MAX8997=y
 CONFIG_REGULATOR_MAX77686=y
+CONFIG_REGULATOR_MAX77802=y
+CONFIG_REGULATOR_MAX77693=y
 CONFIG_REGULATOR_S2MPA01=y
 CONFIG_REGULATOR_S2MPS11=y
 CONFIG_REGULATOR_S5M8767=y
@@ -115,6 +124,7 @@ CONFIG_SND_SOC=y
 CONFIG_SND_SOC_SAMSUNG=y
 CONFIG_SND_SOC_SNOW=y
 CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_EXYNOS=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 69c7bed3c634..16e719c268dd 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -51,6 +51,7 @@ CONFIG_SOC_AM43XX=y
 CONFIG_SOC_DRA7XX=y
 CONFIG_ARM_THUMBEE=y
 CONFIG_ARM_ERRATA_411920=y
+CONFIG_ARM_ERRATA_430973=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_CMA=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index c1a4ca4f6e6d..847045313101 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -75,6 +75,7 @@ CONFIG_POWER_RESET_SUN6I=y
 CONFIG_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
 CONFIG_MFD_AXP20X=y
+CONFIG_REGULATOR=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 3f688b458143..acb0d5712716 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -37,6 +37,11 @@
  */
 #define TRAMPOLINE_VA		UL(CONFIG_VECTORS_BASE)
 
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES	2
+
 #ifndef __ASSEMBLY__
 
 #include <asm/cacheflush.h>
@@ -50,7 +55,7 @@ void free_hyp_pgds(void);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size);
+			  phys_addr_t pa, unsigned long size, bool writable);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
@@ -83,6 +88,11 @@ static inline void kvm_clean_pgd(pgd_t *pgd)
 	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
 }
 
+static inline void kvm_clean_pmd(pmd_t *pmd)
+{
+	clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t));
+}
+
 static inline void kvm_clean_pmd_entry(pmd_t *pmd)
 {
 	clean_pmd_entry(pmd);
@@ -123,10 +133,23 @@ static inline bool kvm_page_empty(void *ptr)
 }
 
 
-#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
-#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
-#define kvm_pud_table_empty(pudp) (0)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(kvm, pudp) (0)
+
+#define KVM_PREALLOC_LEVEL	0
 
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+	return 0;
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm) { }
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+	return kvm->arch.pgd;
+}
 
 struct kvm;
 
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 90aa4583b308..3b30062975b2 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -100,7 +100,7 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR)
+#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
 
 #define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 5e772a21ab97..ef9119f7462e 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -949,8 +949,8 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, scno);
 
-	audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1,
-			    regs->ARM_r2, regs->ARM_r3);
+	audit_syscall_entry(scno, regs->ARM_r0, regs->ARM_r1, regs->ARM_r2,
+			    regs->ARM_r3);
 
 	return scno;
 }
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index dfc32130bc44..93090213c71c 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -92,7 +92,7 @@ static int twd_timer_ack(void)
 
 static void twd_timer_stop(void)
 {
-	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 
 	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
 	disable_percpu_irq(clk->irq);
@@ -108,7 +108,7 @@ static void twd_update_frequency(void *new_rate)
 {
 	twd_timer_rate = *((unsigned long *) new_rate);
 
-	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_rate_change(struct notifier_block *nb,
@@ -134,7 +134,7 @@ static struct notifier_block twd_clk_nb = {
 
 static int twd_clk_init(void)
 {
-	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return clk_notifier_register(twd_clk, &twd_clk_nb);
 
 	return 0;
@@ -153,7 +153,7 @@ static void twd_update_frequency(void *data)
 {
 	twd_timer_rate = clk_get_rate(twd_clk);
 
-	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_cpufreq_transition(struct notifier_block *nb,
@@ -179,7 +179,7 @@ static struct notifier_block twd_cpufreq_nb = {
 
 static int twd_cpufreq_init(void)
 {
-	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return cpufreq_register_notifier(&twd_cpufreq_nb,
 			CPUFREQ_TRANSITION_NOTIFIER);
 
@@ -269,7 +269,7 @@ static void twd_get_clock(struct device_node *np)
  */
 static void twd_timer_setup(void)
 {
-	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 	int cpu = smp_processor_id();
 
 	/*
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 779605122f32..9e193c8a959e 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -409,7 +409,7 @@ static void update_vttbr(struct kvm *kvm)
 	kvm_next_vmid++;
 
 	/* update vttbr to be used with the new vmid */
-	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
 	kvm->arch.vttbr = pgd_phys | vmid;
@@ -808,7 +808,8 @@ static int hyp_init_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_STARTING:
 	case CPU_STARTING_FROZEN:
-		cpu_init_hyp_mode(NULL);
+		if (__hyp_get_vectors() == hyp_default_vectors)
+			cpu_init_hyp_mode(NULL);
 		break;
 	}
 
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 98c8c5b9a87f..14d488388480 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -433,10 +433,17 @@ ARM_BE8(rev	r10, r10	)
 	str	r3, [r11, #VGIC_V2_CPU_HCR]
 	str	r4, [r11, #VGIC_V2_CPU_VMCR]
 	str	r5, [r11, #VGIC_V2_CPU_MISR]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	str	r6, [r11, #(VGIC_V2_CPU_EISR + 4)]
+	str	r7, [r11, #VGIC_V2_CPU_EISR]
+	str	r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	r9, [r11, #VGIC_V2_CPU_ELRSR]
+#else
 	str	r6, [r11, #VGIC_V2_CPU_EISR]
 	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
 	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
 	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+#endif
 	str	r10, [r11, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index eea03069161b..57a403a5c22b 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,7 +42,7 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
-#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
 
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
 
@@ -134,7 +134,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (kvm_pte_table_empty(start_pte))
+	if (kvm_pte_table_empty(kvm, start_pte))
 		clear_pmd_entry(kvm, pmd, start_addr);
 }
 
@@ -158,7 +158,7 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
 		}
 	} while (pmd++, addr = next, addr != end);
 
-	if (kvm_pmd_table_empty(start_pmd))
+	if (kvm_pmd_table_empty(kvm, start_pmd))
 		clear_pud_entry(kvm, pud, start_addr);
 }
 
@@ -182,7 +182,7 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
 		}
 	} while (pud++, addr = next, addr != end);
 
-	if (kvm_pud_table_empty(start_pud))
+	if (kvm_pud_table_empty(kvm, start_pud))
 		clear_pgd_entry(kvm, pgd, start_addr);
 }
 
@@ -306,7 +306,7 @@ void free_boot_hyp_pgd(void)
 	if (boot_hyp_pgd) {
 		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		free_pages((unsigned long)boot_hyp_pgd, pgd_order);
+		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
@@ -343,7 +343,7 @@ void free_hyp_pgds(void)
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
 			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
-		free_pages((unsigned long)hyp_pgd, pgd_order);
+		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
 	}
 
@@ -401,13 +401,46 @@ static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
 	return 0;
 }
 
+static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
+				   unsigned long end, unsigned long pfn,
+				   pgprot_t prot)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned long addr, next;
+	int ret;
+
+	addr = start;
+	do {
+		pud = pud_offset(pgd, addr);
+
+		if (pud_none_or_clear_bad(pud)) {
+			pmd = pmd_alloc_one(NULL, addr);
+			if (!pmd) {
+				kvm_err("Cannot allocate Hyp pmd\n");
+				return -ENOMEM;
+			}
+			pud_populate(NULL, pud, pmd);
+			get_page(virt_to_page(pud));
+			kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+		}
+
+		next = pud_addr_end(addr, end);
+		ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+		if (ret)
+			return ret;
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+
+	return 0;
+}
+
 static int __create_hyp_mappings(pgd_t *pgdp,
 				 unsigned long start, unsigned long end,
 				 unsigned long pfn, pgprot_t prot)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd;
 	unsigned long addr, next;
 	int err = 0;
 
@@ -416,22 +449,21 @@ static int __create_hyp_mappings(pgd_t *pgdp,
 	end = PAGE_ALIGN(end);
 	do {
 		pgd = pgdp + pgd_index(addr);
-		pud = pud_offset(pgd, addr);
 
-		if (pud_none_or_clear_bad(pud)) {
-			pmd = pmd_alloc_one(NULL, addr);
-			if (!pmd) {
-				kvm_err("Cannot allocate Hyp pmd\n");
+		if (pgd_none(*pgd)) {
+			pud = pud_alloc_one(NULL, addr);
+			if (!pud) {
+				kvm_err("Cannot allocate Hyp pud\n");
 				err = -ENOMEM;
 				goto out;
 			}
-			pud_populate(NULL, pud, pmd);
-			get_page(virt_to_page(pud));
-			kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+			pgd_populate(NULL, pgd, pud);
+			get_page(virt_to_page(pgd));
+			kvm_flush_dcache_to_poc(pgd, sizeof(*pgd));
 		}
 
 		next = pgd_addr_end(addr, end);
-		err = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+		err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot);
 		if (err)
 			goto out;
 		pfn += (next - addr) >> PAGE_SHIFT;
@@ -521,6 +553,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
  */
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
+	int ret;
 	pgd_t *pgd;
 
 	if (kvm->arch.pgd != NULL) {
@@ -528,15 +561,38 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		return -EINVAL;
 	}
 
-	pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, S2_PGD_ORDER);
+	if (KVM_PREALLOC_LEVEL > 0) {
+		/*
+		 * Allocate fake pgd for the page table manipulation macros to
+		 * work.  This is not used by the hardware and we have no
+		 * alignment requirement for this allocation.
+		 */
+		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+				       GFP_KERNEL | __GFP_ZERO);
+	} else {
+		/*
+		 * Allocate actual first-level Stage-2 page table used by the
+		 * hardware for Stage-2 page table walks.
+		 */
+		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+	}
+
 	if (!pgd)
 		return -ENOMEM;
 
-	memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t));
+	ret = kvm_prealloc_hwpgd(kvm, pgd);
+	if (ret)
+		goto out_err;
+
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
-
 	return 0;
+out_err:
+	if (KVM_PREALLOC_LEVEL > 0)
+		kfree(pgd);
+	else
+		free_pages((unsigned long)pgd, S2_PGD_ORDER);
+	return ret;
 }
 
 /**
@@ -572,19 +628,39 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+	kvm_free_hwpgd(kvm);
+	if (KVM_PREALLOC_LEVEL > 0)
+		kfree(kvm->arch.pgd);
+	else
+		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
 	kvm->arch.pgd = NULL;
 }
 
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd;
 
 	pgd = kvm->arch.pgd + pgd_index(addr);
-	pud = pud_offset(pgd, addr);
+	if (WARN_ON(pgd_none(*pgd))) {
+		if (!cache)
+			return NULL;
+		pud = mmu_memory_cache_alloc(cache);
+		pgd_populate(NULL, pgd, pud);
+		get_page(virt_to_page(pgd));
+	}
+
+	return pud_offset(pgd, addr);
+}
+
+static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			     phys_addr_t addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = stage2_get_pud(kvm, cache, addr);
 	if (pud_none(*pud)) {
 		if (!cache)
 			return NULL;
@@ -630,7 +706,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
 
-	/* Create stage-2 page table mapping - Level 1 */
+	/* Create stage-2 page table mapping - Levels 0 and 1 */
 	pmd = stage2_get_pmd(kvm, cache, addr);
 	if (!pmd) {
 		/*
@@ -675,7 +751,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
  * @size:	The size of the mapping
  */
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size)
+			  phys_addr_t pa, unsigned long size, bool writable)
 {
 	phys_addr_t addr, end;
 	int ret = 0;
@@ -688,7 +764,11 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
 		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
 
-		ret = mmu_topup_memory_cache(&cache, 2, 2);
+		if (writable)
+			kvm_set_s2pte_writable(&pte);
+
+		ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
+						KVM_NR_MEM_OBJS);
 		if (ret)
 			goto out;
 		spin_lock(&kvm->mmu_lock);
@@ -777,6 +857,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	/* Let's check if we will get back a huge page backed by hugetlbfs */
 	down_read(&current->mm->mmap_sem);
 	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (unlikely(!vma)) {
+		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+		up_read(&current->mm->mmap_sem);
+		return -EFAULT;
+	}
+
 	if (is_vm_hugetlb_page(vma)) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
@@ -797,7 +883,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	up_read(&current->mm->mmap_sem);
 
 	/* We need minimum second+third level pages */
-	ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
+	ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES,
+				     KVM_NR_MEM_OBJS);
 	if (ret)
 		return ret;
 
@@ -843,7 +930,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
-				     mem_type == PAGE_S2_DEVICE);
+			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 	}
 
 
@@ -916,6 +1003,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		goto out_unlock;
 	}
 
+	/* Userspace should not be able to register out-of-bounds IPAs */
+	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
+
 	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
@@ -1072,8 +1162,8 @@ int kvm_mmu_init(void)
 			 (unsigned long)phys_base);
 	}
 
-	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
-	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
 
 	if (!hyp_pgd || !boot_hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
@@ -1126,13 +1216,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *old,
 				   enum kvm_mr_change change)
 {
-	gpa_t gpa = old->base_gfn << PAGE_SHIFT;
-	phys_addr_t size = old->npages << PAGE_SHIFT;
-	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
-		spin_lock(&kvm->mmu_lock);
-		unmap_stage2_range(kvm, gpa, size);
-		spin_unlock(&kvm->mmu_lock);
-	}
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -1140,7 +1223,77 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
-	return 0;
+	hva_t hva = mem->userspace_addr;
+	hva_t reg_end = hva + mem->memory_size;
+	bool writable = !(mem->flags & KVM_MEM_READONLY);
+	int ret = 0;
+
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE)
+		return 0;
+
+	/*
+	 * Prevent userspace from creating a memory region outside of the IPA
+	 * space addressable by the KVM guest IPA space.
+	 */
+	if (memslot->base_gfn + memslot->npages >=
+	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
+		return -EFAULT;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we can map
+	 * any of them right now.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Mapping a read-only VMA is only allowed if the
+		 * memory region is configured as read-only.
+		 */
+		if (writable && !(vma->vm_flags & VM_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (vma->vm_flags & VM_PFNMAP) {
+			gpa_t gpa = mem->guest_phys_addr +
+				    (vm_start - mem->userspace_addr);
+			phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) +
+					 vm_start - vma->vm_start;
+
+			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
+						    vm_end - vm_start,
+						    writable);
+			if (ret)
+				break;
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+
+	if (ret) {
+		spin_lock(&kvm->mmu_lock);
+		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+		spin_unlock(&kvm->mmu_lock);
+	}
+	return ret;
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -1165,4 +1318,10 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	unmap_stage2_range(kvm, gpa, size);
+	spin_unlock(&kvm->mmu_lock);
 }
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index ac99d87ffefe..1b9ae0257a6e 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y		:= gpio.o setup.o sysirq_mask.o
-obj-m		:=
-obj-n		:=
-obj-		:=
 
 obj-$(CONFIG_OLD_IRQ_AT91)	+= irq.o
 obj-$(CONFIG_OLD_CLK_AT91)	+= clock.o
diff --git a/arch/arm/mach-ebsa110/Makefile b/arch/arm/mach-ebsa110/Makefile
index 935e4af01a27..a7d68c13c1d1 100644
--- a/arch/arm/mach-ebsa110/Makefile
+++ b/arch/arm/mach-ebsa110/Makefile
@@ -5,6 +5,3 @@
 # Object file lists.
 
 obj-y			:= core.o io.o leds.o
-obj-m			:=
-obj-n			:=
-obj-			:=
diff --git a/arch/arm/mach-ep93xx/Makefile b/arch/arm/mach-ep93xx/Makefile
index 0dc51f9462de..78d427b34b1f 100644
--- a/arch/arm/mach-ep93xx/Makefile
+++ b/arch/arm/mach-ep93xx/Makefile
@@ -2,9 +2,6 @@
 # Makefile for the linux kernel.
 #
 obj-y			:= core.o clock.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 obj-$(CONFIG_EP93XX_DMA)	+= dma.o
 
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index 788f26d21141..27ae6144679c 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -7,11 +7,6 @@
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # Core
 
 obj-$(CONFIG_ARCH_EXYNOS)	+= exynos.o pmu.o exynos-smc.o firmware.o
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index b89e5f35db84..6b283eb3202e 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -161,7 +161,9 @@ static void exynos_restart(enum reboot_mode mode, const char *cmd)
 
 static struct platform_device exynos_cpuidle = {
 	.name              = "exynos_cpuidle",
+#ifdef CONFIG_ARM_EXYNOS_CPUIDLE
 	.dev.platform_data = exynos_enter_aftr,
+#endif
 	.id                = -1,
 };
 
diff --git a/arch/arm/mach-footbridge/Makefile b/arch/arm/mach-footbridge/Makefile
index c3faa3bc84dd..e83d5c8396ff 100644
--- a/arch/arm/mach-footbridge/Makefile
+++ b/arch/arm/mach-footbridge/Makefile
@@ -5,9 +5,6 @@
 # Object file lists.
 
 obj-y			:= common.o dma.o isa-irq.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 pci-y			+= dc21285.o
 pci-$(CONFIG_ARCH_CATS) += cats-pci.o
diff --git a/arch/arm/mach-iop13xx/Makefile b/arch/arm/mach-iop13xx/Makefile
index cad015fee12f..a3d9260e335f 100644
--- a/arch/arm/mach-iop13xx/Makefile
+++ b/arch/arm/mach-iop13xx/Makefile
@@ -1,8 +1,3 @@
-obj-y			:=
-obj-m			:=
-obj-n			:=
-obj-			:=
-
 obj-$(CONFIG_ARCH_IOP13XX) += setup.o
 obj-$(CONFIG_ARCH_IOP13XX) += irq.o
 obj-$(CONFIG_ARCH_IOP13XX) += pci.o
diff --git a/arch/arm/mach-iop32x/Makefile b/arch/arm/mach-iop32x/Makefile
index cfdf8a137c2b..2d4010abb82f 100644
--- a/arch/arm/mach-iop32x/Makefile
+++ b/arch/arm/mach-iop32x/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y			:= irq.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 obj-$(CONFIG_MACH_GLANTANK) += glantank.o
 obj-$(CONFIG_ARCH_IQ80321) += iq80321.o
diff --git a/arch/arm/mach-iop33x/Makefile b/arch/arm/mach-iop33x/Makefile
index 90081d8c9d16..e95db30d81d5 100644
--- a/arch/arm/mach-iop33x/Makefile
+++ b/arch/arm/mach-iop33x/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y			:= irq.o uart.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 obj-$(CONFIG_ARCH_IQ80331) += iq80331.o
 obj-$(CONFIG_MACH_IQ80332) += iq80332.o
diff --git a/arch/arm/mach-ks8695/Makefile b/arch/arm/mach-ks8695/Makefile
index e370caf0c91b..8ecb7973ae54 100644
--- a/arch/arm/mach-ks8695/Makefile
+++ b/arch/arm/mach-ks8695/Makefile
@@ -4,9 +4,6 @@
 #
 
 obj-y				:= cpu.o irq.o time.o devices.o
-obj-m				:=
-obj-n				:=
-obj-				:=
 
 # PCI support is optional
 obj-$(CONFIG_PCI)		+= pci.o
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index a4d52c42a438..5fa3755261ce 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1440,6 +1440,8 @@ static int gpmc_probe_nand_child(struct platform_device *pdev,
 				break;
 			}
 
+	gpmc_nand_data->flash_bbt = of_get_nand_on_flash_bbt(child);
+
 	val = of_get_nand_bus_width(child);
 	if (val == 16)
 		gpmc_nand_data->devsize = NAND_BUSWIDTH_16;
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index b8ad045bcb8d..03cbb16898a3 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -723,8 +723,16 @@ int __init omap_clk_init(void)
 	ti_clk_init_features();
 
 	ret = of_prcm_init();
-	if (!ret)
-		ret = omap_clk_soc_init();
+	if (ret)
+		return ret;
+
+	of_clk_init(NULL);
+
+	ti_dt_clk_init_retry_clks();
+
+	ti_dt_clockdomains_setup();
+
+	ret = omap_clk_soc_init();
 
 	return ret;
 }
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 74054b813600..ee2b5222eac0 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -525,8 +525,6 @@ int __init of_prcm_init(void)
 		memmap_index++;
 	}
 
-	ti_dt_clockdomains_setup();
-
 	return 0;
 }
 
diff --git a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
index ee6ced1cea7f..f1dd62946b36 100644
--- a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
@@ -143,6 +143,16 @@
 #define CCCR_M_MASK	0x0060	/* Memory Frequency to Run Mode Frequency Multiplier */
 #define CCCR_L_MASK	0x001f	/* Crystal Frequency to Memory Frequency Multiplier */
 
+#define CCCR_CPDIS_BIT	(31)
+#define CCCR_PPDIS_BIT	(30)
+#define CCCR_LCD_26_BIT	(27)
+#define CCCR_A_BIT	(25)
+
+#define CCSR_N2_MASK	CCCR_N_MASK
+#define CCSR_M_MASK	CCCR_M_MASK
+#define CCSR_L_MASK	CCCR_L_MASK
+#define CCSR_N2_SHIFT	7
+
 #define CKEN_AC97CONF   (31)    /* AC97 Controller Configuration */
 #define CKEN_CAMERA	(24)	/* Camera Interface Clock Enable */
 #define CKEN_SSP1	(23)	/* SSP1 Unit Clock Enable */
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index 9f6ec167902a..ad777b353bd5 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -416,17 +416,17 @@ static struct pxafb_mach_info *lpd270_lcd_to_use;
 
 static int __init lpd270_set_lcd(char *str)
 {
-	if (!strnicmp(str, "lq057q3dc02", 11)) {
+	if (!strncasecmp(str, "lq057q3dc02", 11)) {
 		lpd270_lcd_to_use = &sharp_lq057q3dc02;
-	} else if (!strnicmp(str, "lq121s1dg31", 11)) {
+	} else if (!strncasecmp(str, "lq121s1dg31", 11)) {
 		lpd270_lcd_to_use = &sharp_lq121s1dg31;
-	} else if (!strnicmp(str, "lq036q1da01", 11)) {
+	} else if (!strncasecmp(str, "lq036q1da01", 11)) {
 		lpd270_lcd_to_use = &sharp_lq036q1da01;
-	} else if (!strnicmp(str, "lq64d343", 8)) {
+	} else if (!strncasecmp(str, "lq64d343", 8)) {
 		lpd270_lcd_to_use = &sharp_lq64d343;
-	} else if (!strnicmp(str, "lq10d368", 8)) {
+	} else if (!strncasecmp(str, "lq10d368", 8)) {
 		lpd270_lcd_to_use = &sharp_lq10d368;
-	} else if (!strnicmp(str, "lq035q7db02-20", 14)) {
+	} else if (!strncasecmp(str, "lq035q7db02-20", 14)) {
 		lpd270_lcd_to_use = &sharp_lq035q7db02_20;
 	} else {
 		printk(KERN_INFO "lpd270: unknown lcd panel [%s]\n", str);
diff --git a/arch/arm/mach-rpc/Makefile b/arch/arm/mach-rpc/Makefile
index 992e28b4ae9a..2ebc6875aeb8 100644
--- a/arch/arm/mach-rpc/Makefile
+++ b/arch/arm/mach-rpc/Makefile
@@ -5,7 +5,3 @@
 # Object file lists.
 
 obj-y			:= dma.o ecard.o fiq.o irq.o riscpc.o time.o
-obj-m			:=
-obj-n			:=
-obj-			:=
-
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index 2235d0d3b38d..b92071638733 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -7,11 +7,6 @@
 #
 # Licensed under GPLv2
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # core
 
 obj-y				+= common.o
diff --git a/arch/arm/mach-s3c64xx/Makefile b/arch/arm/mach-s3c64xx/Makefile
index 58069a702a43..12f67b61ca5f 100644
--- a/arch/arm/mach-s3c64xx/Makefile
+++ b/arch/arm/mach-s3c64xx/Makefile
@@ -5,11 +5,6 @@
 #
 # Licensed under GPLv2
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # Core
 
 obj-y				+= common.o
diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile
index 7dc2d0e25a83..72b9e9671507 100644
--- a/arch/arm/mach-s5pv210/Makefile
+++ b/arch/arm/mach-s5pv210/Makefile
@@ -7,11 +7,6 @@
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # Core
 
 obj-$(CONFIG_PM_SLEEP)		+= pm.o sleep.o
diff --git a/arch/arm/mach-sa1100/Makefile b/arch/arm/mach-sa1100/Makefile
index 2732eef48966..f1114d11fe13 100644
--- a/arch/arm/mach-sa1100/Makefile
+++ b/arch/arm/mach-sa1100/Makefile
@@ -4,9 +4,6 @@
 
 # Common support
 obj-y := clock.o generic.o irq.o time.o #nmi-oopser.o
-obj-m :=
-obj-n :=
-obj-  :=
 
 # Specific board support
 obj-$(CONFIG_SA1100_ASSABET)		+= assabet.o
diff --git a/arch/arm/mach-shmobile/board-koelsch-reference.c b/arch/arm/mach-shmobile/board-koelsch-reference.c
index 9db5e6774fb7..46aa540133d6 100644
--- a/arch/arm/mach-shmobile/board-koelsch-reference.c
+++ b/arch/arm/mach-shmobile/board-koelsch-reference.c
@@ -41,16 +41,15 @@ static struct rcar_du_encoder_data koelsch_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-koelsch.c b/arch/arm/mach-shmobile/board-koelsch.c
index 126a8b4ec491..7111b5c1d67b 100644
--- a/arch/arm/mach-shmobile/board-koelsch.c
+++ b/arch/arm/mach-shmobile/board-koelsch.c
@@ -63,16 +63,15 @@ static struct rcar_du_encoder_data koelsch_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-lager-reference.c b/arch/arm/mach-shmobile/board-lager-reference.c
index 2a05c02bec39..bc4b48357dde 100644
--- a/arch/arm/mach-shmobile/board-lager-reference.c
+++ b/arch/arm/mach-shmobile/board-lager-reference.c
@@ -43,16 +43,15 @@ static struct rcar_du_encoder_data lager_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index f5a98e2942b3..571327b1c942 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -99,16 +99,15 @@ static struct rcar_du_encoder_data lager_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index e5cf4201e769..ce33d7825c49 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -192,16 +192,15 @@ static struct rcar_du_encoder_data du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-u300/Makefile b/arch/arm/mach-u300/Makefile
index 3ec74ac95bc1..87d37de054b6 100644
--- a/arch/arm/mach-u300/Makefile
+++ b/arch/arm/mach-u300/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y		:= core.o
-obj-m		:=
-obj-n		:=
-obj-		:=
 
 obj-$(CONFIG_MACH_U300_SPIDUMMY)  += dummyspichip.o
 obj-$(CONFIG_REGULATOR_AB3100)    += regulator.o
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index ee1d80593958..ba1196c968d8 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -279,7 +279,7 @@ ENTRY(\name\()_processor_functions)
 
 	.if \suspend
 	.word	cpu_\name\()_suspend_size
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 	.word	cpu_\name\()_do_suspend
 	.word	cpu_\name\()_do_resume
 #else
diff --git a/arch/arm/plat-iop/Makefile b/arch/arm/plat-iop/Makefile
index 224e56c6049b..f2af203d601f 100644
--- a/arch/arm/plat-iop/Makefile
+++ b/arch/arm/plat-iop/Makefile
@@ -2,8 +2,6 @@
 # Makefile for the linux kernel.
 #
 
-obj-y :=
-
 # IOP32X
 obj-$(CONFIG_ARCH_IOP32X) += i2c.o
 obj-$(CONFIG_ARCH_IOP32X) += pci.o
@@ -27,7 +25,3 @@ obj-$(CONFIG_ARCH_IOP33X) += restart.o
 # IOP13XX
 obj-$(CONFIG_ARCH_IOP13XX) += cp6.o
 obj-$(CONFIG_ARCH_IOP13XX) += time.o
-
-obj-m                  :=
-obj-n                  :=
-obj-                   :=
diff --git a/arch/arm/plat-omap/Makefile b/arch/arm/plat-omap/Makefile
index 0b01b68fd033..97a50e8883f9 100644
--- a/arch/arm/plat-omap/Makefile
+++ b/arch/arm/plat-omap/Makefile
@@ -6,9 +6,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-omap/include
 
 # Common support
 obj-y := sram.o dma.o counter_32k.o
-obj-m :=
-obj-n :=
-obj-  :=
 
 # omap_device support (OMAP2+ only at the moment)
 
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index c87aefbf3a13..9bd2776e7d05 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -268,8 +268,9 @@ config S5P_DEV_MFC
 comment "Power management"
 
 config SAMSUNG_PM_DEBUG
-	bool "S3C2410 PM Suspend debug"
-	depends on PM && DEBUG_KERNEL && DEBUG_S3C_UART
+	bool "Samsung PM Suspend debug"
+	depends on PM && DEBUG_KERNEL
+	depends on DEBUG_EXYNOS_UART || DEBUG_S3C24XX_UART || DEBUG_S3C2410_UART
 	help
 	  Say Y here if you want verbose debugging from the PM Suspend and
 	  Resume code. See <file:Documentation/arm/Samsung-S3C24XX/Suspend.txt>
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index 5fe175017f07..f0a008496993 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -6,11 +6,6 @@
 
 ccflags-$(CONFIG_ARCH_MULTI_V7) += -I$(srctree)/$(src)/include
 
-obj-y				:=
-obj-m				:=
-obj-n				:= dummy.o
-obj-				:=
-
 # Objects we always build independent of SoC choice
 
 obj-y				+= init.o cpu.o
diff --git a/arch/arm/plat-samsung/pm-debug.c b/arch/arm/plat-samsung/pm-debug.c
index 8f19f66388dd..39609601f407 100644
--- a/arch/arm/plat-samsung/pm-debug.c
+++ b/arch/arm/plat-samsung/pm-debug.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/serial_core.h>
+#include <linux/serial_s3c.h>
 #include <linux/io.h>
 
 #include <asm/mach/map.h>
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 59c86b6b3052..20901ffed182 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -30,8 +30,6 @@ AS		+= -EL
 LD		+= -EL
 endif
 
-comma = ,
-
 CHECKFLAGS	+= -D__aarch64__
 
 # Default value
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
index 8eb6d94c7851..2e25de0800b9 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -41,6 +41,10 @@
 	status = "ok";
 };
 
+&sgenet0 {
+	status = "ok";
+};
+
 &xgenet {
 	status = "ok";
 };
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index 87d3205e98d5..295c72d52a1f 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -176,6 +176,16 @@
 				clock-output-names = "menetclk";
 			};
 
+			sge0clk: sge0clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				csr-mask = <0x3>;
+				clock-output-names = "sge0clk";
+			};
+
 			xge0clk: xge0clk@1f61c000 {
 				compatible = "apm,xgene-device-clock";
 				#clock-cells = <1>;
@@ -611,6 +621,20 @@
 			};
 		};
 
+		sgenet0: ethernet@1f210000 {
+			compatible = "apm,xgene-enet";
+			status = "disabled";
+			reg = <0x0 0x1f210000 0x0 0x10000>,
+			      <0x0 0x1f200000 0x0 0X10000>,
+			      <0x0 0x1B000000 0x0 0X20000>;
+			reg-names = "enet_csr", "ring_csr", "ring_cmd";
+			interrupts = <0x0 0xA0 0x4>;
+			dma-coherent;
+			clocks = <&sge0clk 0>;
+			local-mac-address = [00 00 00 00 00 00];
+			phy-connection-type = "sgmii";
+		};
+
 		xgenet: ethernet@1f610000 {
 			compatible = "apm,xgene-enet";
 			status = "disabled";
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 774a7c85e70f..dc770bd4f5a5 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
diff --git a/arch/arm64/include/asm/dma-contiguous.h b/arch/arm64/include/asm/dma-contiguous.h
deleted file mode 100644
index 14c4c0ca7f2a..000000000000
--- a/arch/arm64/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef _ASM_DMA_CONTIGUOUS_H
-#define _ASM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index a030d163840b..0caf7a59f6a1 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -41,6 +41,18 @@
  */
 #define TRAMPOLINE_VA		(HYP_PAGE_OFFSET_MASK & PAGE_MASK)
 
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
+ * levels in addition to the PGD and potentially the PUD which are
+ * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2
+ * tables use one level of tables less than the kernel.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define KVM_MMU_CACHE_MIN_PAGES	1
+#else
+#define KVM_MMU_CACHE_MIN_PAGES	2
+#endif
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -53,6 +65,7 @@
 
 #else
 
+#include <asm/pgalloc.h>
 #include <asm/cachetype.h>
 #include <asm/cacheflush.h>
 
@@ -65,10 +78,6 @@
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
-/* Make sure we get the right size, and thus the right alignment */
-#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT))
-#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
-
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
@@ -77,7 +86,7 @@ void free_hyp_pgds(void);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size);
+			  phys_addr_t pa, unsigned long size, bool writable);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
@@ -93,6 +102,7 @@ void kvm_clear_hyp_idmap(void);
 #define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)
 
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
+static inline void kvm_clean_pmd(pmd_t *pmd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
 static inline void kvm_clean_pte_entry(pte_t *pte) {}
@@ -111,19 +121,116 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 #define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
 #define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)
 
+/*
+ * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
+ * the entire IPA input range with a single pgd entry, and we would only need
+ * one pgd entry.  Note that in this case, the pgd is actually not used by
+ * the MMU for Stage-2 translations, but is merely a fake pgd used as a data
+ * structure for the kernel pgtable macros to work.
+ */
+#if PGDIR_SHIFT > KVM_PHYS_SHIFT
+#define PTRS_PER_S2_PGD_SHIFT	0
+#else
+#define PTRS_PER_S2_PGD_SHIFT	(KVM_PHYS_SHIFT - PGDIR_SHIFT)
+#endif
+#define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
+#define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
+/*
+ * If we are concatenating first level stage-2 page tables, we would have less
+ * than or equal to 16 pointers in the fake PGD, because that's what the
+ * architecture allows.  In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS)
+ * represents the first level for the host, and we add 1 to go to the next
+ * level (which uses contatenation) for the stage-2 tables.
+ */
+#if PTRS_PER_S2_PGD <= 16
+#define KVM_PREALLOC_LEVEL	(4 - CONFIG_ARM64_PGTABLE_LEVELS + 1)
+#else
+#define KVM_PREALLOC_LEVEL	(0)
+#endif
+
+/**
+ * kvm_prealloc_hwpgd - allocate inital table for VTTBR
+ * @kvm:	The KVM struct pointer for the VM.
+ * @pgd:	The kernel pseudo pgd
+ *
+ * When the kernel uses more levels of page tables than the guest, we allocate
+ * a fake PGD and pre-populate it to point to the next-level page table, which
+ * will be the real initial page table pointed to by the VTTBR.
+ *
+ * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
+ * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
+ * allocate 2 consecutive PUD pages.
+ */
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+	unsigned int i;
+	unsigned long hwpgd;
+
+	if (KVM_PREALLOC_LEVEL == 0)
+		return 0;
+
+	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
+	if (!hwpgd)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+		if (KVM_PREALLOC_LEVEL == 1)
+			pgd_populate(NULL, pgd + i,
+				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+		else if (KVM_PREALLOC_LEVEL == 2)
+			pud_populate(NULL, pud_offset(pgd, 0) + i,
+				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+	}
+
+	return 0;
+}
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+	pgd_t *pgd = kvm->arch.pgd;
+	pud_t *pud;
+
+	if (KVM_PREALLOC_LEVEL == 0)
+		return pgd;
+
+	pud = pud_offset(pgd, 0);
+	if (KVM_PREALLOC_LEVEL == 1)
+		return pud;
+
+	BUG_ON(KVM_PREALLOC_LEVEL != 2);
+	return pmd_offset(pud, 0);
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm)
+{
+	if (KVM_PREALLOC_LEVEL > 0) {
+		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
+		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
+	}
+}
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
 	return page_count(ptr_page) == 1;
 }
 
-#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
-#ifndef CONFIG_ARM64_64K_PAGES
-#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+
+#ifdef __PAGETABLE_PMD_FOLDED
+#define kvm_pmd_table_empty(kvm, pmdp) (0)
+#else
+#define kvm_pmd_table_empty(kvm, pmdp) \
+	(kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2))
+#endif
+
+#ifdef __PAGETABLE_PUD_FOLDED
+#define kvm_pud_table_empty(kvm, pudp) (0)
 #else
-#define kvm_pmd_table_empty(pmdp) (0)
+#define kvm_pud_table_empty(kvm, pudp) \
+	(kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1))
 #endif
-#define kvm_pud_table_empty(pudp) (0)
 
 
 struct kvm;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index cefd3e825612..41a43bf26492 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
+#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index fe63ac5e9bf5..8a4ae8e73213 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1120,8 +1120,8 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
 
-	audit_syscall_entry(syscall_get_arch(), regs->syscallno,
-		regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]);
+	audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1],
+			    regs->regs[2], regs->regs[3]);
 
 	return regs->syscallno;
 }
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
index ae211772f991..f002fe1c3700 100644
--- a/arch/arm64/kvm/vgic-v2-switch.S
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -67,10 +67,14 @@ CPU_BE(	rev	w11, w11 )
 	str	w4, [x3, #VGIC_V2_CPU_HCR]
 	str	w5, [x3, #VGIC_V2_CPU_VMCR]
 	str	w6, [x3, #VGIC_V2_CPU_MISR]
-	str	w7, [x3, #VGIC_V2_CPU_EISR]
-	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)]
-	str	w9, [x3, #VGIC_V2_CPU_ELRSR]
-	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)]
+CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )
+CPU_LE(	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_LE(	str	w9, [x3, #VGIC_V2_CPU_ELRSR] )
+CPU_LE(	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w7, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_BE(	str	w8, [x3, #VGIC_V2_CPU_EISR] )
+CPU_BE(	str	w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w10, [x3, #VGIC_V2_CPU_ELRSR] )
 	str	w11, [x3, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
diff --git a/arch/avr32/kernel/kprobes.c b/arch/avr32/kernel/kprobes.c
index f820e9f25520..a94ece4a72c8 100644
--- a/arch/avr32/kernel/kprobes.c
+++ b/arch/avr32/kernel/kprobes.c
@@ -104,7 +104,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 
 static void __kprobes set_current_kprobe(struct kprobe *p)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static int __kprobes kprobe_handler(struct pt_regs *regs)
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index db85b5ec3351..37b75602adf6 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -7,7 +7,7 @@
  */
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
@@ -1356,10 +1356,10 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 		goto fail;
 
 	slave->sdata.dma_dev = &dw_dmac0_device.dev;
-	slave->sdata.cfg_hi = (DWC_CFGH_SRC_PER(0)
-				| DWC_CFGH_DST_PER(1));
-	slave->sdata.cfg_lo &= ~(DWC_CFGL_HS_DST_POL
-				| DWC_CFGL_HS_SRC_POL);
+	slave->sdata.src_id = 0;
+	slave->sdata.dst_id = 1;
+	slave->sdata.src_master = 1;
+	slave->sdata.dst_master = 0;
 
 	data->dma_slave = slave;
 
@@ -2052,8 +2052,7 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for capture should be configured. */
 	if (flags & AC97C_CAPTURE) {
 		rx_dws->dma_dev = &dw_dmac0_device.dev;
-		rx_dws->cfg_hi = DWC_CFGH_SRC_PER(3);
-		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		rx_dws->src_id = 3;
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
 	}
@@ -2061,8 +2060,7 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for playback should be configured. */
 	if (flags & AC97C_PLAYBACK) {
 		tx_dws->dma_dev = &dw_dmac0_device.dev;
-		tx_dws->cfg_hi = DWC_CFGH_DST_PER(4);
-		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		tx_dws->dst_id = 4;
 		tx_dws->src_master = 0;
 		tx_dws->dst_master = 1;
 	}
@@ -2134,8 +2132,7 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	dws = &data->dws;
 
 	dws->dma_dev = &dw_dmac0_device.dev;
-	dws->cfg_hi = DWC_CFGH_DST_PER(2);
-	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+	dws->dst_id = 2;
 	dws->src_master = 0;
 	dws->dst_master = 1;
 
diff --git a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
index 4bba58561d5c..11d7f4b28dc8 100644
--- a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
+++ b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
@@ -1,7 +1,7 @@
 #ifndef __MACH_ATMEL_MCI_H
 #define __MACH_ATMEL_MCI_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 /**
  * struct mci_dma_data - DMA data for MCI interface
diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h
index 17b5e92e3bc6..fe1160fbff91 100644
--- a/arch/blackfin/include/asm/ipipe.h
+++ b/arch/blackfin/include/asm/ipipe.h
@@ -157,7 +157,7 @@ static inline unsigned long __ipipe_ffnz(unsigned long ul)
 }
 
 #define __ipipe_do_root_xirq(ipd, irq)					\
-	((ipd)->irqs[irq].handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)))
+	((ipd)->irqs[irq].handler(irq, raw_cpu_ptr(&__ipipe_tick_regs)))
 
 #define __ipipe_run_irqtail(irq)  /* Must be a macro */			\
 	do {								\
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index ea2032013cc2..1e9c8b0bf486 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -300,7 +300,7 @@ again:
 
 static void bfin_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -318,7 +318,7 @@ static void bfin_pmu_stop(struct perf_event *event, int flags)
 
 static void bfin_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -335,7 +335,7 @@ static void bfin_pmu_start(struct perf_event *event, int flags)
 
 static void bfin_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	bfin_pmu_stop(event, PERF_EF_UPDATE);
 	__clear_bit(event->hw.idx, cpuc->used_mask);
@@ -345,7 +345,7 @@ static void bfin_pmu_del(struct perf_event *event, int flags)
 
 static int bfin_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	int ret = -EAGAIN;
@@ -421,7 +421,7 @@ static int bfin_pmu_event_init(struct perf_event *event)
 
 static void bfin_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	int i;
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 694619365265..dd2af74aff80 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -1309,12 +1309,12 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs)
 		bfin_write_TIMER_STATUS(1); /* Latch TIMIL0 */
 #endif
 		/* This is basically what we need from the register frame. */
-		__raw_get_cpu_var(__ipipe_tick_regs).ipend = regs->ipend;
-		__raw_get_cpu_var(__ipipe_tick_regs).pc = regs->pc;
+		__this_cpu_write(__ipipe_tick_regs.ipend, regs->ipend);
+		__this_cpu_write(__ipipe_tick_regs.pc, regs->pc);
 		if (this_domain != ipipe_root_domain)
-			__raw_get_cpu_var(__ipipe_tick_regs).ipend &= ~0x10;
+			__this_cpu_and(__ipipe_tick_regs.ipend, ~0x10);
 		else
-			__raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10;
+			__this_cpu_or(__ipipe_tick_regs.ipend, 0x10);
 	}
 
 	/*
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index ba6c30d8534d..8ad3e90cc8fc 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -146,7 +146,7 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 	platform_clear_ipi(cpu, IRQ_SUPPLE_1);
 
 	smp_rmb();
-	bfin_ipi_data = &__get_cpu_var(bfin_ipi);
+	bfin_ipi_data = this_cpu_ptr(&bfin_ipi);
 	while ((pending = atomic_xchg(&bfin_ipi_data->bits, 0)) != 0) {
 		msg = 0;
 		do {
diff --git a/arch/frv/mm/extable.c b/arch/frv/mm/extable.c
index 6aea124f574d..2fb9b3ab57b9 100644
--- a/arch/frv/mm/extable.c
+++ b/arch/frv/mm/extable.c
@@ -6,8 +6,6 @@
 #include <linux/spinlock.h>
 #include <asm/uaccess.h>
 
-extern const struct exception_table_entry __attribute__((aligned(8))) __start___ex_table[];
-extern const struct exception_table_entry __attribute__((aligned(8))) __stop___ex_table[];
 extern const void __memset_end, __memset_user_error_lr, __memset_user_error_handler;
 extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
 extern spinlock_t modlist_lock;
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 029bab36cd91..668786e84af8 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -159,7 +159,7 @@ static inline ia64_vector __ia64_irq_to_vector(int irq)
 static inline unsigned int
 __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index 1a873b36a4a1..2ab2003698ef 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -10,7 +10,7 @@
 #include <linux/uaccess.h>
 #include <asm-generic/sections.h>
 
-extern char __per_cpu_start[], __per_cpu_end[], __phys_per_cpu_start[];
+extern char __phys_per_cpu_start[];
 #ifdef	CONFIG_SMP
 extern char __cpu0_per_cpu[];
 #endif
diff --git a/arch/ia64/include/asm/sn/arch.h b/arch/ia64/include/asm/sn/arch.h
index 7caa1f44cd95..31eb784866f8 100644
--- a/arch/ia64/include/asm/sn/arch.h
+++ b/arch/ia64/include/asm/sn/arch.h
@@ -57,7 +57,7 @@ struct sn_hub_info_s {
 	u16 nasid_bitmask;
 };
 DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
-#define sn_hub_info 	(&__get_cpu_var(__sn_hub_info))
+#define sn_hub_info 	this_cpu_ptr(&__sn_hub_info)
 #define is_shub2()	(sn_hub_info->shub2)
 #define is_shub1()	(sn_hub_info->shub2 == 0)
 
@@ -72,7 +72,7 @@ DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
  * cpu.
  */
 DECLARE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
-#define sn_cnodeid_to_nasid	(&__get_cpu_var(__sn_cnodeid_to_nasid[0]))
+#define sn_cnodeid_to_nasid	this_cpu_ptr(&__sn_cnodeid_to_nasid[0])
 
 
 extern u8 sn_partition_id;
diff --git a/arch/ia64/include/asm/sn/nodepda.h b/arch/ia64/include/asm/sn/nodepda.h
index ee118b901de4..7c8b4710f071 100644
--- a/arch/ia64/include/asm/sn/nodepda.h
+++ b/arch/ia64/include/asm/sn/nodepda.h
@@ -70,7 +70,7 @@ typedef struct nodepda_s nodepda_t;
  */
 
 DECLARE_PER_CPU(struct nodepda_s *, __sn_nodepda);
-#define sn_nodepda		(__get_cpu_var(__sn_nodepda))
+#define sn_nodepda		__this_cpu_read(__sn_nodepda)
 #define	NODEPDA(cnodeid)	(sn_nodepda->pernode_pdaindr[cnodeid])
 
 /*
diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h
index d38c7ea5eea5..e8f3585e7e7a 100644
--- a/arch/ia64/include/asm/switch_to.h
+++ b/arch/ia64/include/asm/switch_to.h
@@ -32,7 +32,7 @@ extern void ia64_load_extra (struct task_struct *task);
 
 #ifdef CONFIG_PERFMON
   DECLARE_PER_CPU(unsigned long, pfm_syst_info);
-# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
+# define PERFMON_IS_SYSWIDE() (__this_cpu_read(pfm_syst_info) & 0x1)
 #else
 # define PERFMON_IS_SYSWIDE() (0)
 #endif
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index a7ff1c6ab068..1d0b875fec44 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -13,6 +13,7 @@
 #ifndef _ASM_SYSCALL_H
 #define _ASM_SYSCALL_H	1
 
+#include <uapi/linux/audit.h>
 #include <linux/sched.h>
 #include <linux/err.h>
 
@@ -79,4 +80,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 	ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
 }
+
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_IA64;
+}
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 10a14ead70b9..f3b51b57740a 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			317 /* length of syscall table */
+#define NR_syscalls			318 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/asm/uv/uv_hub.h b/arch/ia64/include/asm/uv/uv_hub.h
index 53e9dfacd073..2a88c7204e52 100644
--- a/arch/ia64/include/asm/uv/uv_hub.h
+++ b/arch/ia64/include/asm/uv/uv_hub.h
@@ -108,7 +108,7 @@ struct uv_hub_info_s {
 	unsigned char	n_val;
 };
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info 		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 18026b2eb582..4c2240c1b0cb 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -330,5 +330,6 @@
 #define __NR_renameat2			1338
 #define __NR_getrandom			1339
 #define __NR_memfd_create		1340
+#define __NR_bpf			1341
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 01edf242eb29..f5e96dffc63c 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1778,6 +1778,7 @@ sys_call_table:
 	data8 sys_renameat2
 	data8 sys_getrandom
 	data8 sys_memfd_create			// 1340
+	data8 sys_bpf
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index f2c418281130..812a1e6b3179 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -42,7 +42,7 @@ ia64_vector __ia64_irq_to_vector(int irq)
 
 unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 03ea78ed64a9..698d8fefde6c 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -330,7 +330,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 		int irq;
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
-		irq = __get_cpu_var(vector_irq)[vector];
+		irq = __this_cpu_read(vector_irq[vector]);
 		if (irq < 0)
 			continue;
 
@@ -344,7 +344,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 			goto unlock;
 
 		spin_lock_irqsave(&vector_lock, flags);
-		__get_cpu_var(vector_irq)[vector] = -1;
+		__this_cpu_write(vector_irq[vector], -1);
 		cpu_clear(me, vector_table[vector]);
 		spin_unlock_irqrestore(&vector_lock, flags);
 		cfg->move_cleanup_count--;
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 074fde49c9e6..c7c51445c3be 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -396,7 +396,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	unsigned int i;
 	i = atomic_read(&kcb->prev_kprobe_index);
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe[i-1].kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe[i-1].kp);
 	kcb->kprobe_status = kcb->prev_kprobe[i-1].status;
 	atomic_sub(1, &kcb->prev_kprobe_index);
 }
@@ -404,7 +404,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p,
 			struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static void kretprobe_trampoline(void)
@@ -823,7 +823,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			/*
 			 * jprobe instrumented function just completed
 			 */
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs)) {
 				goto ss_probe;
 			}
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index db7b36bb068b..8bfd36af46f8 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1341,7 +1341,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		ia64_mlogbuf_finish(1);
 	}
 
-	if (__get_cpu_var(ia64_mca_tr_reload)) {
+	if (__this_cpu_read(ia64_mca_tr_reload)) {
 		mca_insert_tr(0x1); /*Reload dynamic itrs*/
 		mca_insert_tr(0x2); /*Reload dynamic itrs*/
 	}
@@ -1868,14 +1868,14 @@ ia64_mca_cpu_init(void *cpu_data)
 		"MCA", cpu);
 	format_mca_init_stack(data, offsetof(struct ia64_mca_cpu, init_stack),
 		"INIT", cpu);
-	__get_cpu_var(ia64_mca_data) = __per_cpu_mca[cpu] = __pa(data);
+	__this_cpu_write(ia64_mca_data, (__per_cpu_mca[cpu] = __pa(data)));
 
 	/*
 	 * Stash away a copy of the PTE needed to map the per-CPU page.
 	 * We may need it during MCA recovery.
 	 */
-	__get_cpu_var(ia64_mca_per_cpu_pte) =
-		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_per_cpu_pte,
+		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL)));
 
 	/*
 	 * Also, stash away a copy of the PAL address and the PTE
@@ -1884,10 +1884,10 @@ ia64_mca_cpu_init(void *cpu_data)
 	pal_vaddr = efi_get_pal_addr();
 	if (!pal_vaddr)
 		return;
-	__get_cpu_var(ia64_mca_pal_base) =
-		GRANULEROUNDDOWN((unsigned long) pal_vaddr);
-	__get_cpu_var(ia64_mca_pal_pte) = pte_val(mk_pte_phys(__pa(pal_vaddr),
-							      PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_pal_base,
+		GRANULEROUNDDOWN((unsigned long) pal_vaddr));
+	__this_cpu_write(ia64_mca_pal_pte, pte_val(mk_pte_phys(__pa(pal_vaddr),
+							      PAGE_KERNEL)));
 }
 
 static void ia64_mca_cmc_vector_adjust(void *dummy)
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index deed6fa96bb0..b51514957620 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -215,7 +215,7 @@ static inline void play_dead(void)
 	unsigned int this_cpu = smp_processor_id();
 
 	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 
 	max_xtp();
 	local_irq_disable();
@@ -273,7 +273,7 @@ ia64_save_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_save_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE)
 		pfm_syst_wide_update_task(task, info, 0);
 #endif
@@ -293,7 +293,7 @@ ia64_load_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_load_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE) 
 		pfm_syst_wide_update_task(task, info, 1);
 #endif
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index b7a5fffe0924..6f54d511cc50 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -1219,7 +1219,7 @@ syscall_trace_enter (long arg0, long arg1, long arg2, long arg3,
 		ia64_sync_krbs();
 
 
-	audit_syscall_entry(AUDIT_ARCH_IA64, regs.r15, arg0, arg1, arg2, arg3);
+	audit_syscall_entry(regs.r15, arg0, arg1, arg2, arg3);
 
 	return 0;
 }
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index d3636e67a98e..6f7d4a4dcf24 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -299,7 +299,7 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 
 	if (!(current->thread.flags & IA64_THREAD_FPEMU_NOPRINT))  {
 		unsigned long count, current_jiffies = jiffies;
-		struct fpu_swa_msg *cp = &__get_cpu_var(cpulast);
+		struct fpu_swa_msg *cp = this_cpu_ptr(&cpulast);
 
 		if (unlikely(current_jiffies > cp->time))
 			cp->count = 0;
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 36182c84363c..5f6b6b48c1d5 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -629,7 +629,7 @@ void sn_cpu_init(void)
 
 	cnode = nasid_to_cnodeid(nasid);
 
-	sn_nodepda = nodepdaindr[cnode];
+	__this_cpu_write(__sn_nodepda, nodepdaindr[cnode]);
 
 	pda->led_address =
 	    (typeof(pda->led_address)) (LED0 + (slice << LED_CPU_SHIFT));
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 68c845411624..f9c8d9fc5939 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -134,8 +134,8 @@ sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 	itc = ia64_get_itc();
 	smp_flush_tlb_cpumask(*mm_cpumask(mm));
 	itc = ia64_get_itc() - itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes_itc_clocks += itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes++;
+	__this_cpu_add(ptcstats.shub_ipi_flushes_itc_clocks, itc);
+	__this_cpu_inc(ptcstats.shub_ipi_flushes);
 }
 
 /**
@@ -199,14 +199,14 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 			start += (1UL << nbits);
 		} while (start < end);
 		ia64_srlz_i();
-		__get_cpu_var(ptcstats).ptc_l++;
+		__this_cpu_inc(ptcstats.ptc_l);
 		preempt_enable();
 		return;
 	}
 
 	if (atomic_read(&mm->mm_users) == 1 && mymm) {
 		flush_tlb_mm(mm);
-		__get_cpu_var(ptcstats).change_rid++;
+		__this_cpu_inc(ptcstats.change_rid);
 		preempt_enable();
 		return;
 	}
@@ -250,11 +250,11 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	spin_lock_irqsave(PTC_LOCK(shub1), flags);
 	itc2 = ia64_get_itc();
 
-	__get_cpu_var(ptcstats).lock_itc_clocks += itc2 - itc;
-	__get_cpu_var(ptcstats).shub_ptc_flushes++;
-	__get_cpu_var(ptcstats).nodes_flushed += nix;
+	__this_cpu_add(ptcstats.lock_itc_clocks, itc2 - itc);
+	__this_cpu_inc(ptcstats.shub_ptc_flushes);
+	__this_cpu_add(ptcstats.nodes_flushed, nix);
 	if (!mymm)
-		 __get_cpu_var(ptcstats).shub_ptc_flushes_not_my_mm++;
+		 __this_cpu_inc(ptcstats.shub_ptc_flushes_not_my_mm);
 
 	if (use_cpu_ptcga && !mymm) {
 		old_rr = ia64_get_rr(start);
@@ -299,9 +299,9 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 
 done:
 	itc2 = ia64_get_itc() - itc2;
-	__get_cpu_var(ptcstats).shub_itc_clocks += itc2;
-	if (itc2 > __get_cpu_var(ptcstats).shub_itc_clocks_max)
-		__get_cpu_var(ptcstats).shub_itc_clocks_max = itc2;
+	__this_cpu_add(ptcstats.shub_itc_clocks, itc2);
+	if (itc2 > __this_cpu_read(ptcstats.shub_itc_clocks_max))
+		__this_cpu_write(ptcstats.shub_itc_clocks_max, itc2);
 
 	if (old_rr) {
 		ia64_set_rr(start, old_rr);
@@ -311,7 +311,7 @@ done:
 	spin_unlock_irqrestore(PTC_LOCK(shub1), flags);
 
 	if (flush_opt == 1 && deadlock) {
-		__get_cpu_var(ptcstats).deadlocks++;
+		__this_cpu_inc(ptcstats.deadlocks);
 		sn2_ipi_flush_all_tlb(mm);
 	}
 
@@ -334,7 +334,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 	short nasid, i;
 	unsigned long *piows, zeroval, n;
 
-	__get_cpu_var(ptcstats).deadlocks++;
+	__this_cpu_inc(ptcstats.deadlocks);
 
 	piows = (unsigned long *) pda->pio_write_status_addr;
 	zeroval = pda->pio_write_status_val;
@@ -349,7 +349,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 			ptc1 = CHANGE_NASID(nasid, ptc1);
 
 		n = sn2_ptc_deadlock_recovery_core(ptc0, data0, ptc1, data1, piows, zeroval);
-		__get_cpu_var(ptcstats).deadlocks2 += n;
+		__this_cpu_add(ptcstats.deadlocks2, n);
 	}
 
 }
diff --git a/arch/m68k/platform/68000/Makefile b/arch/m68k/68000/Makefile
index 1eab70c7194b..1eab70c7194b 100644
--- a/arch/m68k/platform/68000/Makefile
+++ b/arch/m68k/68000/Makefile
diff --git a/arch/m68k/platform/68000/bootlogo-vz.h b/arch/m68k/68000/bootlogo-vz.h
index b38e2b255142..b38e2b255142 100644
--- a/arch/m68k/platform/68000/bootlogo-vz.h
+++ b/arch/m68k/68000/bootlogo-vz.h
diff --git a/arch/m68k/platform/68000/bootlogo.h b/arch/m68k/68000/bootlogo.h
index b896c933fafc..b896c933fafc 100644
--- a/arch/m68k/platform/68000/bootlogo.h
+++ b/arch/m68k/68000/bootlogo.h
diff --git a/arch/m68k/platform/68000/entry.S b/arch/m68k/68000/entry.S
index 23ac054c6e1a..259b3661b614 100644
--- a/arch/m68k/platform/68000/entry.S
+++ b/arch/m68k/68000/entry.S
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/68328/entry.S
+ *  entry.S -- non-mmu 68000 interrupt and exception entry points
  *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *
diff --git a/arch/m68k/platform/68000/head.S b/arch/m68k/68000/head.S
index 536ef9616dad..536ef9616dad 100644
--- a/arch/m68k/platform/68000/head.S
+++ b/arch/m68k/68000/head.S
diff --git a/arch/m68k/platform/68000/ints.c b/arch/m68k/68000/ints.c
index cda49b12d7be..cda49b12d7be 100644
--- a/arch/m68k/platform/68000/ints.c
+++ b/arch/m68k/68000/ints.c
diff --git a/arch/m68k/platform/68000/m68328.c b/arch/m68k/68000/m68328.c
index e53caf4c3bfb..e53caf4c3bfb 100644
--- a/arch/m68k/platform/68000/m68328.c
+++ b/arch/m68k/68000/m68328.c
diff --git a/arch/m68k/platform/68000/m68EZ328.c b/arch/m68k/68000/m68EZ328.c
index 21952906e9e2..21952906e9e2 100644
--- a/arch/m68k/platform/68000/m68EZ328.c
+++ b/arch/m68k/68000/m68EZ328.c
diff --git a/arch/m68k/platform/68000/m68VZ328.c b/arch/m68k/68000/m68VZ328.c
index 0e5e5a10a021..0e5e5a10a021 100644
--- a/arch/m68k/platform/68000/m68VZ328.c
+++ b/arch/m68k/68000/m68VZ328.c
diff --git a/arch/m68k/platform/68000/romvec.S b/arch/m68k/68000/romvec.S
index 15c70cd6453f..15c70cd6453f 100644
--- a/arch/m68k/platform/68000/romvec.S
+++ b/arch/m68k/68000/romvec.S
diff --git a/arch/m68k/platform/68000/timers.c b/arch/m68k/68000/timers.c
index 99a98698bc95..99a98698bc95 100644
--- a/arch/m68k/platform/68000/timers.c
+++ b/arch/m68k/68000/timers.c
diff --git a/arch/m68k/platform/68360/Makefile b/arch/m68k/68360/Makefile
index f6f434383049..591ce42df3de 100644
--- a/arch/m68k/platform/68360/Makefile
+++ b/arch/m68k/68360/Makefile
@@ -1,5 +1,5 @@
 #
-# Makefile for arch/m68knommu/platform/68360.
+# Makefile for 68360 machines.
 #
 model-y			  := ram
 model-$(CONFIG_ROMKERNEL) := rom
diff --git a/arch/m68k/platform/68360/commproc.c b/arch/m68k/68360/commproc.c
index 315727b7ff40..315727b7ff40 100644
--- a/arch/m68k/platform/68360/commproc.c
+++ b/arch/m68k/68360/commproc.c
diff --git a/arch/m68k/platform/68360/config.c b/arch/m68k/68360/config.c
index d493ac43fe3f..17ec416fed9d 100644
--- a/arch/m68k/platform/68360/config.c
+++ b/arch/m68k/68360/config.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/68360/config.c
+ *  config.c - non-mmu 68360 platform initialization code
  *
  *  Copyright (c) 2000 Michael Leslie <mleslie@lineo.com>
  *  Copyright (C) 1993 Hamish Macdonald
diff --git a/arch/m68k/platform/68360/entry.S b/arch/m68k/68360/entry.S
index 447c33ef37fd..22eb3022f9ee 100644
--- a/arch/m68k/platform/68360/entry.S
+++ b/arch/m68k/68360/entry.S
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/68360/entry.S
+ *  entry.S - non-mmu 68360 interrupt and exceptions entry points
  *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2001 SED Systems, a Division of Calian Ltd.
diff --git a/arch/m68k/platform/68360/head-ram.S b/arch/m68k/68360/head-ram.S
index acd213170d80..62bc56f41d57 100644
--- a/arch/m68k/platform/68360/head-ram.S
+++ b/arch/m68k/68360/head-ram.S
@@ -1,6 +1,5 @@
-/* arch/m68knommu/platform/68360/head-ram.S
- *
- * Startup code for Motorola 68360
+/*
+ * head-ram.S - startup code for Motorola 68360
  *
  * Copyright 2001 (C) SED Systems, a Division of Calian Ltd.
  * Based on: arch/m68knommu/platform/68328/pilot/crt0_rom.S
diff --git a/arch/m68k/platform/68360/head-rom.S b/arch/m68k/68360/head-rom.S
index dfc756d99886..b3a7e40f35e1 100644
--- a/arch/m68k/platform/68360/head-rom.S
+++ b/arch/m68k/68360/head-rom.S
@@ -1,6 +1,5 @@
-/* arch/m68knommu/platform/68360/head-rom.S
- *
- * Startup code for Motorola 68360
+/*
+ * head-rom.S - startup code for Motorola 68360
  *
  * Copyright (C) SED Systems, a Division of Calian Ltd.
  * Based on: arch/m68knommu/platform/68328/pilot/crt0_rom.S
diff --git a/arch/m68k/platform/68360/ints.c b/arch/m68k/68360/ints.c
index 8cd42692331b..2360fc046681 100644
--- a/arch/m68k/platform/68360/ints.c
+++ b/arch/m68k/68360/ints.c
@@ -1,5 +1,5 @@
 /*
- * linux/arch/$(ARCH)/platform/$(PLATFORM)/ints.c
+ * ints.c - first level interrupt handlers
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file COPYING in the main directory of this archive
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 7f7830f2c5bc..0b29dcfef69f 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -92,9 +92,9 @@ endif
 #
 head-y				:= arch/m68k/kernel/head.o
 head-$(CONFIG_SUN3)		:= arch/m68k/kernel/sun3-head.o
-head-$(CONFIG_M68360)		:= arch/m68k/platform/68360/head.o
-head-$(CONFIG_M68000)		:= arch/m68k/platform/68000/head.o
-head-$(CONFIG_COLDFIRE)		:= arch/m68k/platform/coldfire/head.o
+head-$(CONFIG_M68360)		:= arch/m68k/68360/head.o
+head-$(CONFIG_M68000)		:= arch/m68k/68000/head.o
+head-$(CONFIG_COLDFIRE)		:= arch/m68k/coldfire/head.o
 
 core-y				+= arch/m68k/kernel/	arch/m68k/mm/
 libs-y				+= arch/m68k/lib/
@@ -114,9 +114,9 @@ core-$(CONFIG_NATFEAT)		+= arch/m68k/emu/
 core-$(CONFIG_M68040)		+= arch/m68k/fpsp040/
 core-$(CONFIG_M68060)		+= arch/m68k/ifpsp060/
 core-$(CONFIG_M68KFPU_EMU)	+= arch/m68k/math-emu/
-core-$(CONFIG_M68360)		+= arch/m68k/platform/68360/
-core-$(CONFIG_M68000)		+= arch/m68k/platform/68000/
-core-$(CONFIG_COLDFIRE)		+= arch/m68k/platform/coldfire/
+core-$(CONFIG_M68360)		+= arch/m68k/68360/
+core-$(CONFIG_M68000)		+= arch/m68k/68000/
+core-$(CONFIG_COLDFIRE)		+= arch/m68k/coldfire/
 
 
 all:	zImage
diff --git a/arch/m68k/platform/coldfire/Makefile b/arch/m68k/coldfire/Makefile
index 68f0fac60099..68f0fac60099 100644
--- a/arch/m68k/platform/coldfire/Makefile
+++ b/arch/m68k/coldfire/Makefile
diff --git a/arch/m68k/platform/coldfire/cache.c b/arch/m68k/coldfire/cache.c
index 71beeaf0c5c4..71beeaf0c5c4 100644
--- a/arch/m68k/platform/coldfire/cache.c
+++ b/arch/m68k/coldfire/cache.c
diff --git a/arch/m68k/platform/coldfire/clk.c b/arch/m68k/coldfire/clk.c
index fddfdccae63b..fddfdccae63b 100644
--- a/arch/m68k/platform/coldfire/clk.c
+++ b/arch/m68k/coldfire/clk.c
diff --git a/arch/m68k/platform/coldfire/device.c b/arch/m68k/coldfire/device.c
index 71ea4c02795d..71ea4c02795d 100644
--- a/arch/m68k/platform/coldfire/device.c
+++ b/arch/m68k/coldfire/device.c
diff --git a/arch/m68k/platform/coldfire/dma.c b/arch/m68k/coldfire/dma.c
index df5ce20d181c..df5ce20d181c 100644
--- a/arch/m68k/platform/coldfire/dma.c
+++ b/arch/m68k/coldfire/dma.c
diff --git a/arch/m68k/platform/coldfire/dma_timer.c b/arch/m68k/coldfire/dma_timer.c
index 235ad57c4707..235ad57c4707 100644
--- a/arch/m68k/platform/coldfire/dma_timer.c
+++ b/arch/m68k/coldfire/dma_timer.c
diff --git a/arch/m68k/platform/coldfire/entry.S b/arch/m68k/coldfire/entry.S
index 881ab8e379d4..52d312d5b4d4 100644
--- a/arch/m68k/platform/coldfire/entry.S
+++ b/arch/m68k/coldfire/entry.S
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/5307/entry.S
+ *  entry.S  -- interrupt and exception processing for ColdFire
  *
  *  Copyright (C) 1999-2007, Greg Ungerer (gerg@snapgear.com)
  *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
diff --git a/arch/m68k/platform/coldfire/firebee.c b/arch/m68k/coldfire/firebee.c
index 46d50534f981..46d50534f981 100644
--- a/arch/m68k/platform/coldfire/firebee.c
+++ b/arch/m68k/coldfire/firebee.c
diff --git a/arch/m68k/platform/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c
index e7e428681ec5..e7e428681ec5 100644
--- a/arch/m68k/platform/coldfire/gpio.c
+++ b/arch/m68k/coldfire/gpio.c
diff --git a/arch/m68k/platform/coldfire/head.S b/arch/m68k/coldfire/head.S
index fa31be297b85..fa31be297b85 100644
--- a/arch/m68k/platform/coldfire/head.S
+++ b/arch/m68k/coldfire/head.S
diff --git a/arch/m68k/platform/coldfire/intc-2.c b/arch/m68k/coldfire/intc-2.c
index 995093357c59..995093357c59 100644
--- a/arch/m68k/platform/coldfire/intc-2.c
+++ b/arch/m68k/coldfire/intc-2.c
diff --git a/arch/m68k/platform/coldfire/intc-5249.c b/arch/m68k/coldfire/intc-5249.c
index b0d1641053e4..b0d1641053e4 100644
--- a/arch/m68k/platform/coldfire/intc-5249.c
+++ b/arch/m68k/coldfire/intc-5249.c
diff --git a/arch/m68k/platform/coldfire/intc-525x.c b/arch/m68k/coldfire/intc-525x.c
index b23204d059ac..b23204d059ac 100644
--- a/arch/m68k/platform/coldfire/intc-525x.c
+++ b/arch/m68k/coldfire/intc-525x.c
diff --git a/arch/m68k/platform/coldfire/intc-5272.c b/arch/m68k/coldfire/intc-5272.c
index d7b695629a7e..d1e2fbad327c 100644
--- a/arch/m68k/platform/coldfire/intc-5272.c
+++ b/arch/m68k/coldfire/intc-5272.c
@@ -36,7 +36,7 @@
  * they also need acknowledging via acknowledge bits.
  */
 struct irqmap {
-	unsigned char	icr;
+	unsigned int	icr;
 	unsigned char	index;
 	unsigned char	ack;
 };
diff --git a/arch/m68k/platform/coldfire/intc-simr.c b/arch/m68k/coldfire/intc-simr.c
index 7cf2c156f72d..7cf2c156f72d 100644
--- a/arch/m68k/platform/coldfire/intc-simr.c
+++ b/arch/m68k/coldfire/intc-simr.c
diff --git a/arch/m68k/platform/coldfire/intc.c b/arch/m68k/coldfire/intc.c
index cce257420388..cce257420388 100644
--- a/arch/m68k/platform/coldfire/intc.c
+++ b/arch/m68k/coldfire/intc.c
diff --git a/arch/m68k/platform/coldfire/m5206.c b/arch/m68k/coldfire/m5206.c
index 0e55f449a88c..8945f5e7b39c 100644
--- a/arch/m68k/platform/coldfire/m5206.c
+++ b/arch/m68k/coldfire/m5206.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5206/config.c
+ *	m5206.c  -- platform support for ColdFire 5206 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  * 	Copyright (C) 2000-2001, Lineo Inc. (www.lineo.com) 
diff --git a/arch/m68k/platform/coldfire/m520x.c b/arch/m68k/coldfire/m520x.c
index 4040a3c93733..173834f251eb 100644
--- a/arch/m68k/platform/coldfire/m520x.c
+++ b/arch/m68k/coldfire/m520x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *  linux/arch/m68knommu/platform/520x/config.c
+ *  m520x.c  -- platform support for ColdFire 520x based boards
  *
  *  Copyright (C) 2005,      Freescale (www.freescale.com)
  *  Copyright (C) 2005,      Intec Automation (mike@steroidmicros.com)
diff --git a/arch/m68k/platform/coldfire/m523x.c b/arch/m68k/coldfire/m523x.c
index 6b7135e6d5b4..a191a467eff2 100644
--- a/arch/m68k/platform/coldfire/m523x.c
+++ b/arch/m68k/coldfire/m523x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/523x/config.c
+ *	m523x.c  -- platform support for ColdFire 523x based boards
  *
  *	Sub-architcture dependent initialization code for the Freescale
  *	523x CPUs.
diff --git a/arch/m68k/platform/coldfire/m5249.c b/arch/m68k/coldfire/m5249.c
index f6253a3313b3..e48f55adc447 100644
--- a/arch/m68k/platform/coldfire/m5249.c
+++ b/arch/m68k/coldfire/m5249.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5249/config.c
+ *	m5249.c  -- platform support for ColdFire 5249 based boards
  *
  *	Copyright (C) 2002, Greg Ungerer (gerg@snapgear.com)
  */
diff --git a/arch/m68k/platform/coldfire/m525x.c b/arch/m68k/coldfire/m525x.c
index 1adba3909035..3d8583e2187c 100644
--- a/arch/m68k/platform/coldfire/m525x.c
+++ b/arch/m68k/coldfire/m525x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	525x.c
+ *	525x.c  -- platform support for ColdFire 525x based boards
  *
  *	Copyright (C) 2012, Steven King <sfking@fdwdc.com>
  */
diff --git a/arch/m68k/platform/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c
index 8a4d3cc322c6..b15219ed22bf 100644
--- a/arch/m68k/platform/coldfire/m5272.c
+++ b/arch/m68k/coldfire/m5272.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5272/config.c
+ *	m5272.c  -- platform support for ColdFire 5272 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2001-2002, SnapGear Inc. (www.snapgear.com)
diff --git a/arch/m68k/platform/coldfire/m527x.c b/arch/m68k/coldfire/m527x.c
index 62d81ef016f1..2ba470735bed 100644
--- a/arch/m68k/platform/coldfire/m527x.c
+++ b/arch/m68k/coldfire/m527x.c
@@ -1,10 +1,10 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/527x/config.c
+ *	m527x.c  -- platform support for ColdFire 527x based boards
  *
  *	Sub-architcture dependent initialization code for the Freescale
- *	5270/5271 CPUs.
+ *	5270/5271 and 5274/5275 CPUs.
  *
  *	Copyright (C) 1999-2004, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2001-2004, SnapGear Inc. (www.snapgear.com)
diff --git a/arch/m68k/platform/coldfire/m528x.c b/arch/m68k/coldfire/m528x.c
index 21cd161d36f1..45e947aeade4 100644
--- a/arch/m68k/platform/coldfire/m528x.c
+++ b/arch/m68k/coldfire/m528x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/528x/config.c
+ *	m528x.c  -- platform support for ColdFire 528x based boards
  *
  *	Sub-architcture dependent initialization code for the Freescale
  *	5280, 5281 and 5282 CPUs.
diff --git a/arch/m68k/platform/coldfire/m5307.c b/arch/m68k/coldfire/m5307.c
index 887435361386..2da1d146e344 100644
--- a/arch/m68k/platform/coldfire/m5307.c
+++ b/arch/m68k/coldfire/m5307.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5307/config.c
+ *	m5307.c  -- platform support for ColdFire 5307 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2000, Lineo (www.lineo.com)
diff --git a/arch/m68k/platform/coldfire/m53xx.c b/arch/m68k/coldfire/m53xx.c
index 80879a7fe3d5..80879a7fe3d5 100644
--- a/arch/m68k/platform/coldfire/m53xx.c
+++ b/arch/m68k/coldfire/m53xx.c
diff --git a/arch/m68k/platform/coldfire/m5407.c b/arch/m68k/coldfire/m5407.c
index 2fb3cdbfde30..738eba6be40e 100644
--- a/arch/m68k/platform/coldfire/m5407.c
+++ b/arch/m68k/coldfire/m5407.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5407/config.c
+ *	m5407.c  -- platform support for ColdFire 5407 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2000, Lineo (www.lineo.com)
diff --git a/arch/m68k/platform/coldfire/m5441x.c b/arch/m68k/coldfire/m5441x.c
index 98a13cce93d8..98a13cce93d8 100644
--- a/arch/m68k/platform/coldfire/m5441x.c
+++ b/arch/m68k/coldfire/m5441x.c
diff --git a/arch/m68k/platform/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c
index 952da53aa0bc..075aaabd1360 100644
--- a/arch/m68k/platform/coldfire/m54xx.c
+++ b/arch/m68k/coldfire/m54xx.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/54xx/config.c
+ *	m54xx.c  -- platform support for ColdFire 54xx based boards
  *
  *	Copyright (C) 2010, Philippe De Muyter <phdm@macqel.be>
  */
@@ -23,7 +23,6 @@
 #include <asm/mcfuart.h>
 #include <asm/mcfclk.h>
 #include <asm/m54xxgpt.h>
-#include <asm/mcfclk.h>
 #ifdef CONFIG_MMU
 #include <asm/mmu_context.h>
 #endif
diff --git a/arch/m68k/platform/coldfire/mcf8390.c b/arch/m68k/coldfire/mcf8390.c
index 23a6874a3248..23a6874a3248 100644
--- a/arch/m68k/platform/coldfire/mcf8390.c
+++ b/arch/m68k/coldfire/mcf8390.c
diff --git a/arch/m68k/platform/coldfire/nettel.c b/arch/m68k/coldfire/nettel.c
index ddc48ec1b800..ddc48ec1b800 100644
--- a/arch/m68k/platform/coldfire/nettel.c
+++ b/arch/m68k/coldfire/nettel.c
diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index df9679238b6d..df9679238b6d 100644
--- a/arch/m68k/platform/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
diff --git a/arch/m68k/platform/coldfire/pit.c b/arch/m68k/coldfire/pit.c
index 493b3111d4c1..493b3111d4c1 100644
--- a/arch/m68k/platform/coldfire/pit.c
+++ b/arch/m68k/coldfire/pit.c
diff --git a/arch/m68k/platform/coldfire/reset.c b/arch/m68k/coldfire/reset.c
index f30952f0cbe6..f30952f0cbe6 100644
--- a/arch/m68k/platform/coldfire/reset.c
+++ b/arch/m68k/coldfire/reset.c
diff --git a/arch/m68k/platform/coldfire/sltimers.c b/arch/m68k/coldfire/sltimers.c
index 831a08cf6f40..831a08cf6f40 100644
--- a/arch/m68k/platform/coldfire/sltimers.c
+++ b/arch/m68k/coldfire/sltimers.c
diff --git a/arch/m68k/platform/coldfire/timers.c b/arch/m68k/coldfire/timers.c
index cd496a20fcc7..cd496a20fcc7 100644
--- a/arch/m68k/platform/coldfire/timers.c
+++ b/arch/m68k/coldfire/timers.c
diff --git a/arch/m68k/platform/coldfire/vectors.c b/arch/m68k/coldfire/vectors.c
index a4dbdecbec7a..08923fe600e0 100644
--- a/arch/m68k/platform/coldfire/vectors.c
+++ b/arch/m68k/coldfire/vectors.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/coldfire/vectors.c
+ *	vectors.c  -- high level trap setup for ColdFire
  *
  *	Copyright (C) 1999-2007, Greg Ungerer <gerg@snapgear.com>
  */
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 52f7e8499172..be4b5a813ad4 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -179,6 +179,15 @@ static inline void *ioremap_fullcache(unsigned long physaddr, unsigned long size
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return (void __iomem *) port;
+}
+
+static inline void ioport_unmap(void __iomem *p)
+{
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _M68KNOMMU_IO_H */
diff --git a/arch/m68k/include/asm/m54xxpci.h b/arch/m68k/include/asm/m54xxpci.h
index 6fbf54f72f2e..4687f5aa3741 100644
--- a/arch/m68k/include/asm/m54xxpci.h
+++ b/arch/m68k/include/asm/m54xxpci.h
@@ -72,7 +72,7 @@
 #define	PCIRFWPR	(CONFIG_MBAR + 0x84d4)	/* RX FIFO write pointer */
 
 #define	PACR		(CONFIG_MBAR + 0xc00)	/* PCI arbiter control */
-#define	PASR		(COFNIG_MBAR + 0xc04)	/* PCI arbiter status */
+#define	PASR		(CONFIG_MBAR + 0xc04)	/* PCI arbiter status */
 
 /*
  *	Definitions for the Global status and control register.
diff --git a/arch/m68k/platform/Makefile b/arch/m68k/platform/Makefile
deleted file mode 100644
index fc932bf65d34..000000000000
--- a/arch/m68k/platform/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-#
-# Makefile for the arch/m68knommu/platform.
-#
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 02c08737f6aa..2478ec6d23c9 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -258,7 +258,7 @@ int metag_pmu_event_set_period(struct perf_event *event,
 
 static void metag_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -306,7 +306,7 @@ static void metag_pmu_stop(struct perf_event *event, int flags)
 
 static int metag_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = 0, ret = 0;
 
@@ -348,7 +348,7 @@ out:
 
 static void metag_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -597,7 +597,7 @@ static int _hw_perf_event_init(struct perf_event *event)
 
 static void metag_pmu_enable_counter(struct hw_perf_event *event, int idx)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	unsigned int config = event->config;
 	unsigned int tmp = config & 0xf0;
 	unsigned long flags;
@@ -670,7 +670,7 @@ unlock:
 
 static void metag_pmu_disable_counter(struct hw_perf_event *event, int idx)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	unsigned int tmp = 0;
 	unsigned long flags;
 
@@ -718,7 +718,7 @@ out:
 
 static void metag_pmu_write_counter(int idx, u32 val)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	u32 tmp = 0;
 	unsigned long flags;
 
@@ -751,7 +751,7 @@ static int metag_pmu_event_map(int idx)
 static irqreturn_t metag_pmu_counter_overflow(int irq, void *dev)
 {
 	int idx = (int)dev;
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event = cpuhw->events[idx];
 	struct hw_perf_event *hwc = &event->hw;
 	struct pt_regs *regs = get_irq_regs();
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 9bc431783105..53cfaf34c343 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_MICROBLAZE_SYSCALL_H
 #define __ASM_MICROBLAZE_SYSCALL_H
 
+#include <uapi/linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <asm/ptrace.h>
@@ -99,4 +100,8 @@ static inline void syscall_set_arguments(struct task_struct *task,
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
 
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_MICROBLAZE;
+}
 #endif /* __ASM_MICROBLAZE_SYSCALL_H */
diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c
index 39cf50841f6d..bb10637ce688 100644
--- a/arch/microblaze/kernel/ptrace.c
+++ b/arch/microblaze/kernel/ptrace.c
@@ -147,8 +147,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
-	audit_syscall_entry(EM_MICROBLAZE, regs->r12, regs->r5, regs->r6,
-			    regs->r7, regs->r8);
+	audit_syscall_entry(regs->r12, regs->r5, regs->r6, regs->r7, regs->r8);
 
 	return ret ?: regs->r12;
 }
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 574c43000699..ad6badb6be71 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -29,6 +29,7 @@ config MIPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DMA_API_DEBUG
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -353,6 +354,7 @@ config MIPS_SEAD3
 	bool "MIPS SEAD3 board"
 	select BOOT_ELF32
 	select BOOT_RAW
+	select BUILTIN_DTB
 	select CEVT_R4K
 	select CSRC_R4K
 	select CSRC_GIC
@@ -742,6 +744,7 @@ config CAVIUM_OCTEON_SOC
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_SMP
 	select NR_CPUS_DEFAULT_16
+	select BUILTIN_DTB
 	help
 	  This option supports all of the Octeon reference boards from Cavium
 	  Networks. It builds a kernel that dynamically determines the Octeon
@@ -2482,6 +2485,9 @@ config USE_OF
 	select OF_EARLY_FLATTREE
 	select IRQ_DOMAIN
 
+config BUILTIN_DTB
+	bool
+
 endmenu
 
 config LOCKDEP_SUPPORT
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index bbac51e11179..23cb94806fbc 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -333,6 +333,16 @@ endif
 
 CLEAN_FILES += vmlinux.32 vmlinux.64
 
+# device-trees
+core-$(CONFIG_BUILTIN_DTB) += arch/mips/boot/dts/
+
+%.dtb %.dtb.S %.dtb.o: | scripts
+	$(Q)$(MAKE) $(build)=arch/mips/boot/dts arch/mips/boot/dts/$@
+
+PHONY += dtbs
+dtbs: scripts
+	$(Q)$(MAKE) $(build)=arch/mips/boot/dts dtbs
+
 archprepare:
 ifdef CONFIG_MIPS32_N32
 	@echo '  Checking missing-syscalls for N32'
@@ -367,6 +377,7 @@ define archhelp
 	echo '  vmlinuz.srec         - SREC zboot image'
 	echo '  uImage               - U-Boot image'
 	echo '  uImage.gz            - U-Boot image (gzip)'
+	echo '  dtbs                 - Device-tree blobs for enabled boards'
 	echo
 	echo '  These will be default as appropriate for a configured platform.'
 endef
diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index ef93ee3f6a2c..1c64fdbe4c81 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -21,6 +21,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/platform_device.h>
 #include <linux/smsc911x.h>
+#include <linux/wm97xx.h>
 
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/au1100_mmc.h>
@@ -711,6 +712,46 @@ static struct platform_device db1300_lcd_dev = {
 
 /**********************************************************************/
 
+static void db1300_wm97xx_irqen(struct wm97xx *wm, int enable)
+{
+	if (enable)
+		enable_irq(DB1300_AC97_PEN_INT);
+	else
+		disable_irq_nosync(DB1300_AC97_PEN_INT);
+}
+
+static struct wm97xx_mach_ops db1300_wm97xx_ops = {
+	.irq_enable	= db1300_wm97xx_irqen,
+	.irq_gpio	= WM97XX_GPIO_3,
+};
+
+static int db1300_wm97xx_probe(struct platform_device *pdev)
+{
+	struct wm97xx *wm = platform_get_drvdata(pdev);
+
+	/* external pendown indicator */
+	wm97xx_config_gpio(wm, WM97XX_GPIO_13, WM97XX_GPIO_IN,
+			   WM97XX_GPIO_POL_LOW, WM97XX_GPIO_STICKY,
+			   WM97XX_GPIO_WAKE);
+
+	/* internal "virtual" pendown gpio */
+	wm97xx_config_gpio(wm, WM97XX_GPIO_3, WM97XX_GPIO_OUT,
+			   WM97XX_GPIO_POL_LOW, WM97XX_GPIO_NOTSTICKY,
+			   WM97XX_GPIO_NOWAKE);
+
+	wm->pen_irq = DB1300_AC97_PEN_INT;
+
+	return wm97xx_register_mach_ops(wm, &db1300_wm97xx_ops);
+}
+
+static struct platform_driver db1300_wm97xx_driver = {
+	.driver.name	= "wm97xx-touch",
+	.driver.owner	= THIS_MODULE,
+	.probe		= db1300_wm97xx_probe,
+};
+
+/**********************************************************************/
+
 static struct platform_device *db1300_dev[] __initdata = {
 	&db1300_eth_dev,
 	&db1300_i2c_dev,
@@ -755,6 +796,9 @@ int __init db1300_dev_setup(void)
 	i2c_register_board_info(0, db1300_i2c_devs,
 				ARRAY_SIZE(db1300_i2c_devs));
 
+	if (platform_driver_register(&db1300_wm97xx_driver))
+		pr_warn("DB1300: failed to init touch pen irq support!\n");
+
 	/* Audio PSC clock is supplied by codecs (PSC1, 2) */
 	__raw_writel(PSC_SEL_CLK_SERCLK,
 	    (void __iomem *)KSEG1ADDR(AU1300_PSC1_PHYS_ADDR) + PSC_SEL_OFFSET);
@@ -762,9 +806,10 @@ int __init db1300_dev_setup(void)
 	__raw_writel(PSC_SEL_CLK_SERCLK,
 	    (void __iomem *)KSEG1ADDR(AU1300_PSC2_PHYS_ADDR) + PSC_SEL_OFFSET);
 	wmb();
-	/* I2C uses internal 48MHz EXTCLK1 */
+	/* I2C driver wants 50MHz, get as close as possible */
 	c = clk_get(NULL, "psc3_intclk");
 	if (!IS_ERR(c)) {
+		clk_set_rate(c, 50000000);
 		clk_prepare_enable(c);
 		clk_put(c);
 	}
diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index 7e89936f763e..0fd5177e35ab 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -34,12 +34,9 @@ static void __init db1550_hw_setup(void)
 	void __iomem *base;
 	unsigned long v;
 
-	/* complete SPI setup: link psc0_intclk to a 48MHz source,
-	 * and assign GPIO16 to PSC0_SYNC1 (SPI cs# line) as well as PSC1_SYNC
-	 * for AC97 on PB1550.
+	/* complete pin setup: assign GPIO16 to PSC0_SYNC1 (SPI cs# line)
+	 * as well as PSC1_SYNC for AC97 on PB1550.
 	 */
-	v = alchemy_rdsys(AU1000_SYS_CLKSRC);
-	alchemy_wrsys(v | 0x000001e0, AU1000_SYS_CLKSRC);
 	v = alchemy_rdsys(AU1000_SYS_PINFUNC);
 	alchemy_wrsys(v | 1 | SYS_PF_PSC1_S1, AU1000_SYS_PINFUNC);
 
@@ -586,11 +583,13 @@ int __init db1550_dev_setup(void)
 
 	c = clk_get(NULL, "psc0_intclk");
 	if (!IS_ERR(c)) {
+		clk_set_rate(c, 50000000);
 		clk_prepare_enable(c);
 		clk_put(c);
 	}
 	c = clk_get(NULL, "psc2_intclk");
 	if (!IS_ERR(c)) {
+		clk_set_rate(c, db1550_spi_platdata.mainclk_hz);
 		clk_prepare_enable(c);
 		clk_put(c);
 	}
diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c
index 8df86eb94972..be139a0198b0 100644
--- a/arch/mips/alchemy/devboards/platform.c
+++ b/arch/mips/alchemy/devboards/platform.c
@@ -11,6 +11,7 @@
 #include <linux/pm.h>
 
 #include <asm/bootinfo.h>
+#include <asm/idle.h>
 #include <asm/reboot.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
@@ -53,6 +54,8 @@ static void db1x_power_off(void)
 {
 	bcsr_write(BCSR_RESETS, 0);
 	bcsr_write(BCSR_SYSTEM, BCSR_SYSTEM_PWROFF | BCSR_SYSTEM_RESET);
+	while (1)		/* sit and spin */
+		cpu_wait();
 }
 
 static void db1x_reset(char *c)
diff --git a/arch/mips/boot/.gitignore b/arch/mips/boot/.gitignore
index a73d6e2c4f64..d3962cd5ce0c 100644
--- a/arch/mips/boot/.gitignore
+++ b/arch/mips/boot/.gitignore
@@ -5,3 +5,4 @@ zImage
 zImage.tmp
 calc_vmlinuz_load_addr
 uImage
+*.dtb
diff --git a/arch/mips/boot/dts/Makefile b/arch/mips/boot/dts/Makefile
new file mode 100644
index 000000000000..ca9c90e2cabf
--- /dev/null
+++ b/arch/mips/boot/dts/Makefile
@@ -0,0 +1,20 @@
+dtb-$(CONFIG_CAVIUM_OCTEON_SOC)		+= octeon_3xxx.dtb octeon_68xx.dtb
+dtb-$(CONFIG_DT_EASY50712)		+= easy50712.dtb
+dtb-$(CONFIG_DT_XLP_EVP)		+= xlp_evp.dtb
+dtb-$(CONFIG_DT_XLP_SVP)		+= xlp_svp.dtb
+dtb-$(CONFIG_DT_XLP_FVP)		+= xlp_fvp.dtb
+dtb-$(CONFIG_DT_XLP_GVP)		+= xlp_gvp.dtb
+dtb-$(CONFIG_DTB_RT2880_EVAL)		+= rt2880_eval.dtb
+dtb-$(CONFIG_DTB_RT305X_EVAL)		+= rt3052_eval.dtb
+dtb-$(CONFIG_DTB_RT3883_EVAL)		+= rt3883_eval.dtb
+dtb-$(CONFIG_DTB_MT7620A_EVAL)		+= mt7620a_eval.dtb
+dtb-$(CONFIG_MIPS_SEAD3)		+= sead3.dtb
+
+obj-y		+= $(patsubst %.dtb, %.dtb.o, $(dtb-y))
+
+targets		+= dtbs
+targets		+= $(dtb-y)
+
+dtbs: $(addprefix $(obj)/, $(dtb-y))
+
+clean-files	+= *.dtb *.dtb.S
diff --git a/arch/mips/lantiq/dts/danube.dtsi b/arch/mips/boot/dts/danube.dtsi
index d4c59e003708..d4c59e003708 100644
--- a/arch/mips/lantiq/dts/danube.dtsi
+++ b/arch/mips/boot/dts/danube.dtsi
diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/boot/dts/easy50712.dts
index 143b8a37b5e4..143b8a37b5e4 100644
--- a/arch/mips/lantiq/dts/easy50712.dts
+++ b/arch/mips/boot/dts/easy50712.dts
diff --git a/arch/mips/ralink/dts/mt7620a.dtsi b/arch/mips/boot/dts/mt7620a.dtsi
index 08bf24fefe9f..08bf24fefe9f 100644
--- a/arch/mips/ralink/dts/mt7620a.dtsi
+++ b/arch/mips/boot/dts/mt7620a.dtsi
diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/boot/dts/mt7620a_eval.dts
index 709f58132f5c..709f58132f5c 100644
--- a/arch/mips/ralink/dts/mt7620a_eval.dts
+++ b/arch/mips/boot/dts/mt7620a_eval.dts
diff --git a/arch/mips/cavium-octeon/octeon_3xxx.dts b/arch/mips/boot/dts/octeon_3xxx.dts
index fa33115bde33..fa33115bde33 100644
--- a/arch/mips/cavium-octeon/octeon_3xxx.dts
+++ b/arch/mips/boot/dts/octeon_3xxx.dts
diff --git a/arch/mips/cavium-octeon/octeon_68xx.dts b/arch/mips/boot/dts/octeon_68xx.dts
index 79b46fcb0a11..79b46fcb0a11 100644
--- a/arch/mips/cavium-octeon/octeon_68xx.dts
+++ b/arch/mips/boot/dts/octeon_68xx.dts
diff --git a/arch/mips/ralink/dts/rt2880.dtsi b/arch/mips/boot/dts/rt2880.dtsi
index 182afde2f2e1..182afde2f2e1 100644
--- a/arch/mips/ralink/dts/rt2880.dtsi
+++ b/arch/mips/boot/dts/rt2880.dtsi
diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/boot/dts/rt2880_eval.dts
index 0a685db093d4..0a685db093d4 100644
--- a/arch/mips/ralink/dts/rt2880_eval.dts
+++ b/arch/mips/boot/dts/rt2880_eval.dts
diff --git a/arch/mips/ralink/dts/rt3050.dtsi b/arch/mips/boot/dts/rt3050.dtsi
index e3203d414fee..e3203d414fee 100644
--- a/arch/mips/ralink/dts/rt3050.dtsi
+++ b/arch/mips/boot/dts/rt3050.dtsi
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/boot/dts/rt3052_eval.dts
index ec9e9a035541..ec9e9a035541 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/boot/dts/rt3052_eval.dts
diff --git a/arch/mips/ralink/dts/rt3883.dtsi b/arch/mips/boot/dts/rt3883.dtsi
index 3b131dd0d5ac..3b131dd0d5ac 100644
--- a/arch/mips/ralink/dts/rt3883.dtsi
+++ b/arch/mips/boot/dts/rt3883.dtsi
diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/boot/dts/rt3883_eval.dts
index e8df21a5d10d..e8df21a5d10d 100644
--- a/arch/mips/ralink/dts/rt3883_eval.dts
+++ b/arch/mips/boot/dts/rt3883_eval.dts
diff --git a/arch/mips/mti-sead3/sead3.dts b/arch/mips/boot/dts/sead3.dts
index e4b317d414f1..e4b317d414f1 100644
--- a/arch/mips/mti-sead3/sead3.dts
+++ b/arch/mips/boot/dts/sead3.dts
diff --git a/arch/mips/netlogic/dts/xlp_evp.dts b/arch/mips/boot/dts/xlp_evp.dts
index 89ad04808c02..89ad04808c02 100644
--- a/arch/mips/netlogic/dts/xlp_evp.dts
+++ b/arch/mips/boot/dts/xlp_evp.dts
diff --git a/arch/mips/netlogic/dts/xlp_fvp.dts b/arch/mips/boot/dts/xlp_fvp.dts
index 63e62b7bd758..63e62b7bd758 100644
--- a/arch/mips/netlogic/dts/xlp_fvp.dts
+++ b/arch/mips/boot/dts/xlp_fvp.dts
diff --git a/arch/mips/netlogic/dts/xlp_gvp.dts b/arch/mips/boot/dts/xlp_gvp.dts
index bb4ecd1d47fc..bb4ecd1d47fc 100644
--- a/arch/mips/netlogic/dts/xlp_gvp.dts
+++ b/arch/mips/boot/dts/xlp_gvp.dts
diff --git a/arch/mips/netlogic/dts/xlp_svp.dts b/arch/mips/boot/dts/xlp_svp.dts
index 1ebd00edaacc..1ebd00edaacc 100644
--- a/arch/mips/netlogic/dts/xlp_svp.dts
+++ b/arch/mips/boot/dts/xlp_svp.dts
diff --git a/arch/mips/cavium-octeon/.gitignore b/arch/mips/cavium-octeon/.gitignore
deleted file mode 100644
index 39c968605ff6..000000000000
--- a/arch/mips/cavium-octeon/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-*.dtb.S
-*.dtb
diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
index 4e952043c922..42f5f1a4b40a 100644
--- a/arch/mips/cavium-octeon/Makefile
+++ b/arch/mips/cavium-octeon/Makefile
@@ -20,13 +20,3 @@ obj-y += executive/
 obj-$(CONFIG_MTD)		      += flash_setup.o
 obj-$(CONFIG_SMP)		      += smp.o
 obj-$(CONFIG_OCTEON_ILM)	      += oct_ilm.o
-
-DTS_FILES = octeon_3xxx.dts octeon_68xx.dts
-DTB_FILES = $(patsubst %.dts, %.dtb, $(DTS_FILES))
-
-obj-y += $(patsubst %.dts, %.dtb.o, $(DTS_FILES))
-
-# Let's keep the .dtb files around in case we want to look at them.
-.SECONDARY:  $(addprefix $(obj)/, $(DTB_FILES))
-
-clean-files += $(DTB_FILES) $(patsubst %.dtb, %.dtb.S, $(DTB_FILES))
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 1b82ac6921e0..741734049675 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -264,13 +264,13 @@ static void octeon_irq_ciu_enable_local(struct irq_data *data)
 	unsigned long *pen;
 	unsigned long flags;
 	union octeon_ciu_chip_data cd;
-	raw_spinlock_t *lock = &__get_cpu_var(octeon_irq_ciu_spinlock);
+	raw_spinlock_t *lock = this_cpu_ptr(&octeon_irq_ciu_spinlock);
 
 	cd.p = irq_data_get_irq_chip_data(data);
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (cd.s.line == 0) {
-		pen = &__get_cpu_var(octeon_irq_ciu0_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu0_en_mirror);
 		__set_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -279,7 +279,7 @@ static void octeon_irq_ciu_enable_local(struct irq_data *data)
 		wmb();
 		cvmx_write_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2), *pen);
 	} else {
-		pen = &__get_cpu_var(octeon_irq_ciu1_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu1_en_mirror);
 		__set_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -296,13 +296,13 @@ static void octeon_irq_ciu_disable_local(struct irq_data *data)
 	unsigned long *pen;
 	unsigned long flags;
 	union octeon_ciu_chip_data cd;
-	raw_spinlock_t *lock = &__get_cpu_var(octeon_irq_ciu_spinlock);
+	raw_spinlock_t *lock = this_cpu_ptr(&octeon_irq_ciu_spinlock);
 
 	cd.p = irq_data_get_irq_chip_data(data);
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (cd.s.line == 0) {
-		pen = &__get_cpu_var(octeon_irq_ciu0_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu0_en_mirror);
 		__clear_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -311,7 +311,7 @@ static void octeon_irq_ciu_disable_local(struct irq_data *data)
 		wmb();
 		cvmx_write_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2), *pen);
 	} else {
-		pen = &__get_cpu_var(octeon_irq_ciu1_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu1_en_mirror);
 		__clear_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -431,11 +431,11 @@ static void octeon_irq_ciu_enable_local_v2(struct irq_data *data)
 
 	if (cd.s.line == 0) {
 		int index = cvmx_get_core_num() * 2;
-		set_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu0_en_mirror));
+		set_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu0_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1S(index), mask);
 	} else {
 		int index = cvmx_get_core_num() * 2 + 1;
-		set_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu1_en_mirror));
+		set_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu1_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1S(index), mask);
 	}
 }
@@ -450,11 +450,11 @@ static void octeon_irq_ciu_disable_local_v2(struct irq_data *data)
 
 	if (cd.s.line == 0) {
 		int index = cvmx_get_core_num() * 2;
-		clear_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu0_en_mirror));
+		clear_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu0_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1C(index), mask);
 	} else {
 		int index = cvmx_get_core_num() * 2 + 1;
-		clear_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu1_en_mirror));
+		clear_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu1_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1C(index), mask);
 	}
 }
@@ -1063,7 +1063,7 @@ static void octeon_irq_ip2_ciu(void)
 	const unsigned long core_id = cvmx_get_core_num();
 	u64 ciu_sum = cvmx_read_csr(CVMX_CIU_INTX_SUM0(core_id * 2));
 
-	ciu_sum &= __get_cpu_var(octeon_irq_ciu0_en_mirror);
+	ciu_sum &= __this_cpu_read(octeon_irq_ciu0_en_mirror);
 	if (likely(ciu_sum)) {
 		int bit = fls64(ciu_sum) - 1;
 		int irq = octeon_irq_ciu_to_irq[0][bit];
@@ -1080,7 +1080,7 @@ static void octeon_irq_ip3_ciu(void)
 {
 	u64 ciu_sum = cvmx_read_csr(CVMX_CIU_INT_SUM1);
 
-	ciu_sum &= __get_cpu_var(octeon_irq_ciu1_en_mirror);
+	ciu_sum &= __this_cpu_read(octeon_irq_ciu1_en_mirror);
 	if (likely(ciu_sum)) {
 		int bit = fls64(ciu_sum) - 1;
 		int irq = octeon_irq_ciu_to_irq[1][bit];
@@ -1129,10 +1129,10 @@ static void octeon_irq_init_ciu_percpu(void)
 	int coreid = cvmx_get_core_num();
 
 
-	__get_cpu_var(octeon_irq_ciu0_en_mirror) = 0;
-	__get_cpu_var(octeon_irq_ciu1_en_mirror) = 0;
+	__this_cpu_write(octeon_irq_ciu0_en_mirror, 0);
+	__this_cpu_write(octeon_irq_ciu1_en_mirror, 0);
 	wmb();
-	raw_spin_lock_init(&__get_cpu_var(octeon_irq_ciu_spinlock));
+	raw_spin_lock_init(this_cpu_ptr(&octeon_irq_ciu_spinlock));
 	/*
 	 * Disable All CIU Interrupts. The ones we need will be
 	 * enabled later.  Read the SUM register so we know the write
diff --git a/arch/mips/configs/sead3_defconfig b/arch/mips/configs/sead3_defconfig
index 0abe681c11a0..dae9354b6256 100644
--- a/arch/mips/configs/sead3_defconfig
+++ b/arch/mips/configs/sead3_defconfig
@@ -31,8 +31,8 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
diff --git a/arch/mips/configs/sead3micro_defconfig b/arch/mips/configs/sead3micro_defconfig
index 2a0da5bf4b64..cd91a775c74e 100644
--- a/arch/mips/configs/sead3micro_defconfig
+++ b/arch/mips/configs/sead3micro_defconfig
@@ -32,8 +32,8 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 57012ef1f51e..72e1cf1cab00 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,6 +1,7 @@
 # MIPS headers
 generic-y += cputime.h
 generic-y += current.h
+generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
 generic-y += hash.h
 generic-y += irq_work.h
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index e079598ae051..3325f3eb248c 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -231,6 +231,16 @@
 #define cpu_has_clo_clz	cpu_has_mips_r
 #endif
 
+/*
+ * MIPS32 R2, MIPS64 R2, Loongson 3A and Octeon have WSBH.
+ * MIPS64 R2, Loongson 3A and Octeon have WSBH, DSBH and DSHD.
+ * This indicates the availability of WSBH and in case of 64 bit CPUs also
+ * DSBH and DSHD.
+ */
+#ifndef cpu_has_wsbh
+#define cpu_has_wsbh		cpu_has_mips_r2
+#endif
+
 #ifndef cpu_has_dsp
 #define cpu_has_dsp		(cpu_data[0].ases & MIPS_ASE_DSP)
 #endif
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index d5f42c168001..a6c9ccb33c5c 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -79,6 +79,11 @@ struct cpuinfo_mips {
 #define NUM_WATCH_REGS 4
 	u16			watch_reg_masks[NUM_WATCH_REGS];
 	unsigned int		kscratch_mask; /* Usable KScratch mask. */
+	/*
+	 * Cache Coherency attribute for write-combine memory writes.
+	 * (shifted by _CACHE_SHIFT)
+	 */
+	unsigned int		writecombine;
 } __attribute__((aligned(SMP_CACHE_BYTES)));
 
 extern struct cpuinfo_mips cpu_data[];
diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h
index 0195745b4b1b..3ee347713307 100644
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@@ -33,17 +33,17 @@
 #ifdef CONFIG_DEBUG_FS
 
 struct mips_fpu_emulator_stats {
-	local_t emulated;
-	local_t loads;
-	local_t stores;
-	local_t cp1ops;
-	local_t cp1xops;
-	local_t errors;
-	local_t ieee754_inexact;
-	local_t ieee754_underflow;
-	local_t ieee754_overflow;
-	local_t ieee754_zerodiv;
-	local_t ieee754_invalidop;
+	unsigned long emulated;
+	unsigned long loads;
+	unsigned long stores;
+	unsigned long cp1ops;
+	unsigned long cp1xops;
+	unsigned long errors;
+	unsigned long ieee754_inexact;
+	unsigned long ieee754_underflow;
+	unsigned long ieee754_overflow;
+	unsigned long ieee754_zerodiv;
+	unsigned long ieee754_invalidop;
 };
 
 DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
@@ -51,7 +51,7 @@ DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
 #define MIPS_FPU_EMU_INC_STATS(M)					\
 do {									\
 	preempt_disable();						\
-	__local_inc(&__get_cpu_var(fpuemustats).M);			\
+	__this_cpu_inc(fpuemustats.M);					\
 	preempt_enable();						\
 } while (0)
 
diff --git a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h
index 09f45e6afade..c5b6eef0efa7 100644
--- a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h
@@ -8,6 +8,12 @@
 #define __ASM_MACH_AU1X00_CPU_FEATURE_OVERRIDES_H
 
 #define cpu_has_tlb			1
+#define cpu_has_tlbinv			0
+#define cpu_has_segments		0
+#define cpu_has_eva			0
+#define cpu_has_htw			0
+#define cpu_has_rixiex			0
+#define cpu_has_maar			0
 #define cpu_has_4kex			1
 #define cpu_has_3k_cache		0
 #define cpu_has_4k_cache		1
@@ -28,6 +34,8 @@
 #define cpu_has_mdmx			0
 #define cpu_has_mips3d			0
 #define cpu_has_smartmips		0
+#define cpu_has_rixi			0
+#define cpu_has_mmips			0
 #define cpu_has_vtag_icache		0
 #define cpu_has_dc_aliases		0
 #define cpu_has_ic_fills_f_dc		1
@@ -50,4 +58,8 @@
 #define cpu_dcache_line_size()		32
 #define cpu_icache_line_size()		32
 
+#define cpu_has_perf_cntr_intr_bit	0
+#define cpu_has_vz			0
+#define cpu_has_msa			0
+
 #endif /* __ASM_MACH_AU1X00_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
index cf8022872892..fa1f3cfbae8d 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
@@ -57,6 +57,7 @@
 #define cpu_has_vint		0
 #define cpu_has_veic		0
 #define cpu_hwrena_impl_bits	0xc0000000
+#define cpu_has_wsbh            1
 
 #define cpu_has_rixi		(cpu_data[0].cputype != CPU_CAVIUM_OCTEON)
 
diff --git a/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
index c0f3ef45c2c1..7d28f95b0512 100644
--- a/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
@@ -59,4 +59,6 @@
 #define cpu_has_watch		1
 #define cpu_has_local_ebase	0
 
+#define cpu_has_wsbh		IS_ENABLED(CONFIG_CPU_LOONGSON3)
+
 #endif /* __ASM_MACH_LOONGSON_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index e592f3687d6f..e747bfa0be7e 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -224,38 +224,52 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val)
 #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 
 #define _CACHE_CACHABLE_NONCOHERENT 0
+#define _CACHE_UNCACHED_ACCELERATED _CACHE_UNCACHED
 
 #elif defined(CONFIG_CPU_SB1)
 
 /* No penalty for being coherent on the SB1, so just
    use it for "noncoherent" spaces, too.  Shouldn't hurt. */
 
-#define _CACHE_UNCACHED		    (2<<_CACHE_SHIFT)
-#define _CACHE_CACHABLE_COW	    (5<<_CACHE_SHIFT)
 #define _CACHE_CACHABLE_NONCOHERENT (5<<_CACHE_SHIFT)
-#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)
 
 #elif defined(CONFIG_CPU_LOONGSON3)
 
 /* Using COHERENT flag for NONCOHERENT doesn't hurt. */
 
-#define _CACHE_UNCACHED             (2<<_CACHE_SHIFT)  /* LOONGSON       */
 #define _CACHE_CACHABLE_NONCOHERENT (3<<_CACHE_SHIFT)  /* LOONGSON       */
 #define _CACHE_CACHABLE_COHERENT    (3<<_CACHE_SHIFT)  /* LOONGSON-3     */
-#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)  /* LOONGSON       */
 
-#else
+#elif defined(CONFIG_MACH_JZ4740)
+
+/* Ingenic uses the WA bit to achieve write-combine memory writes */
+#define _CACHE_UNCACHED_ACCELERATED (1<<_CACHE_SHIFT)
 
-#define _CACHE_CACHABLE_NO_WA	    (0<<_CACHE_SHIFT)  /* R4600 only	  */
-#define _CACHE_CACHABLE_WA	    (1<<_CACHE_SHIFT)  /* R4600 only	  */
-#define _CACHE_UNCACHED		    (2<<_CACHE_SHIFT)  /* R4[0246]00	  */
-#define _CACHE_CACHABLE_NONCOHERENT (3<<_CACHE_SHIFT)  /* R4[0246]00	  */
-#define _CACHE_CACHABLE_CE	    (4<<_CACHE_SHIFT)  /* R4[04]00MC only */
-#define _CACHE_CACHABLE_COW	    (5<<_CACHE_SHIFT)  /* R4[04]00MC only */
-#define _CACHE_CACHABLE_COHERENT    (5<<_CACHE_SHIFT)  /* MIPS32R2 CMP	  */
-#define _CACHE_CACHABLE_CUW	    (6<<_CACHE_SHIFT)  /* R4[04]00MC only */
-#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)  /* R10000 only	  */
+#endif
 
+#ifndef _CACHE_CACHABLE_NO_WA
+#define _CACHE_CACHABLE_NO_WA		(0<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_WA
+#define _CACHE_CACHABLE_WA		(1<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_UNCACHED
+#define _CACHE_UNCACHED			(2<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_NONCOHERENT
+#define _CACHE_CACHABLE_NONCOHERENT	(3<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_CE
+#define _CACHE_CACHABLE_CE		(4<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_COW
+#define _CACHE_CACHABLE_COW		(5<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_CUW
+#define _CACHE_CACHABLE_CUW		(6<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_UNCACHED_ACCELERATED
+#define _CACHE_UNCACHED_ACCELERATED	(7<<_CACHE_SHIFT)
 #endif
 
 #define __READABLE	(_PAGE_SILENT_READ | _PAGE_ACCESSED | (cpu_has_rixi ? 0 : _PAGE_READ))
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index df49a308085c..d6d1928539b1 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -366,6 +366,16 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	/* cpu_data[0].writecombine is already shifted by _CACHE_SHIFT */
+	prot = (prot & ~_CACHE_MASK) | cpu_data[0].writecombine;
+
+	return __pgprot(prot);
+}
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index cdf68b33bd65..bb7963753730 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -129,7 +129,7 @@ extern const unsigned long sysn32_call_table[];
 
 static inline int syscall_get_arch(void)
 {
-	int arch = EM_MIPS;
+	int arch = AUDIT_ARCH_MIPS;
 #ifdef CONFIG_64BIT
 	if (!test_thread_flag(TIF_32BIT_REGS)) {
 		arch |= __AUDIT_ARCH_64BIT;
diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h
index ac9a8f9cd1fb..8f2d184dbe9f 100644
--- a/arch/mips/include/uapi/asm/swab.h
+++ b/arch/mips/include/uapi/asm/swab.h
@@ -13,12 +13,16 @@
 
 #define __SWAB_64_THRU_32__
 
-#if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
+#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||		\
+    defined(_MIPS_ARCH_LOONGSON3A)
 
 static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__(
+	"	.set	push			\n"
+	"	.set	arch=mips32r2		\n"
 	"	wsbh	%0, %1			\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -29,8 +33,11 @@ static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__(
+	"	.set	push			\n"
+	"	.set	arch=mips32r2		\n"
 	"	wsbh	%0, %1			\n"
 	"	rotr	%0, %0, 16		\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -46,8 +53,11 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 {
 	__asm__(
-	"	dsbh	%0, %1\n"
-	"	dshd	%0, %0"
+	"	.set	push			\n"
+	"	.set	arch=mips64r2		\n"
+	"	dsbh	%0, %1			\n"
+	"	dshd	%0, %0			\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -55,5 +65,5 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 }
 #define __arch_swab64 __arch_swab64
 #endif /* __mips64 */
-#endif /* MIPS R2 or newer  */
+#endif /* MIPS R2 or newer or Loongson 3A */
 #endif /* _ASM_SWAB_H */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index e34b10be782e..94c4a0c0a577 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -27,6 +27,7 @@
 #include <asm/msa.h>
 #include <asm/watch.h>
 #include <asm/elf.h>
+#include <asm/pgtable-bits.h>
 #include <asm/spram.h>
 #include <asm/uaccess.h>
 
@@ -764,6 +765,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			break;
 		case PRID_REV_LOONGSON3A:
 			c->cputype = CPU_LOONGSON3;
+			c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			break;
@@ -798,67 +800,83 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 
 static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 {
+	c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_4KC:
 		c->cputype = CPU_4KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 4Kc";
 		break;
 	case PRID_IMP_4KEC:
 	case PRID_IMP_4KECR2:
 		c->cputype = CPU_4KEC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 4KEc";
 		break;
 	case PRID_IMP_4KSC:
 	case PRID_IMP_4KSD:
 		c->cputype = CPU_4KSC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 4KSc";
 		break;
 	case PRID_IMP_5KC:
 		c->cputype = CPU_5KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 5Kc";
 		break;
 	case PRID_IMP_5KE:
 		c->cputype = CPU_5KE;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 5KE";
 		break;
 	case PRID_IMP_20KC:
 		c->cputype = CPU_20KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 20Kc";
 		break;
 	case PRID_IMP_24K:
 		c->cputype = CPU_24K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 24Kc";
 		break;
 	case PRID_IMP_24KE:
 		c->cputype = CPU_24K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 24KEc";
 		break;
 	case PRID_IMP_25KF:
 		c->cputype = CPU_25KF;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 25Kc";
 		break;
 	case PRID_IMP_34K:
 		c->cputype = CPU_34K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 34Kc";
 		break;
 	case PRID_IMP_74K:
 		c->cputype = CPU_74K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 74Kc";
 		break;
 	case PRID_IMP_M14KC:
 		c->cputype = CPU_M14KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS M14Kc";
 		break;
 	case PRID_IMP_M14KEC:
 		c->cputype = CPU_M14KEC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS M14KEc";
 		break;
 	case PRID_IMP_1004K:
 		c->cputype = CPU_1004K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 1004Kc";
 		break;
 	case PRID_IMP_1074K:
 		c->cputype = CPU_1074K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 1074Kc";
 		break;
 	case PRID_IMP_INTERAPTIV_UP:
@@ -932,6 +950,7 @@ static inline void cpu_probe_sibyte(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
 
+	c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_SB1:
 		c->cputype = CPU_SB1;
@@ -1063,6 +1082,7 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_JZRISC:
 		c->cputype = CPU_JZRISC;
+		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		__cpu_name[cpu] = "Ingenic JZRISC";
 		break;
 	default:
@@ -1169,6 +1189,7 @@ void cpu_probe(void)
 	c->processor_id = PRID_IMP_UNKNOWN;
 	c->fpu_id	= FPIR_IMP_NONE;
 	c->cputype	= CPU_UNKNOWN;
+	c->writecombine = _CACHE_UNCACHED;
 
 	c->processor_id = read_c0_prid();
 	switch (c->processor_id & PRID_COMP_MASK) {
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 1f8187ab0997..212f46f2014e 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -224,7 +224,7 @@ static void save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_old_SR = kcb->prev_kprobe.old_SR;
 	kcb->kprobe_saved_SR = kcb->prev_kprobe.saved_SR;
@@ -234,7 +234,7 @@ static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 			       struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_SR = kcb->kprobe_old_SR = (regs->cp0_status & ST0_IE);
 	kcb->kprobe_saved_epc = regs->cp0_epc;
 }
@@ -385,7 +385,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index b63f2482f288..a8f9cdc6f8b0 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -340,7 +340,7 @@ static int mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc,
 
 static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
 
@@ -360,7 +360,7 @@ static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 
 static void mipsxx_pmu_disable_event(int idx)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
@@ -460,7 +460,7 @@ static void mipspmu_stop(struct perf_event *event, int flags)
 
 static int mipspmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -496,7 +496,7 @@ out:
 
 static void mipspmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -1275,7 +1275,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static void pause_local_counters(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int ctr = mipspmu.num_counters;
 	unsigned long flags;
 
@@ -1291,7 +1291,7 @@ static void pause_local_counters(void)
 
 static void resume_local_counters(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int ctr = mipspmu.num_counters;
 
 	do {
@@ -1302,7 +1302,7 @@ static void resume_local_counters(void)
 
 static int mipsxx_pmu_handle_shared_irq(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_sample_data data;
 	unsigned int counters = mipspmu.num_counters;
 	u64 counter;
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index f7aac5b57b4b..9d1487d83293 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -780,9 +780,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[2]);
 
-	audit_syscall_entry(syscall_get_arch(),
-			    syscall,
-			    regs->regs[4], regs->regs[5],
+	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 	return syscall;
 }
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 7c1fe2b42d40..b3b8f0d9d4a7 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -24,6 +24,8 @@
 #include <linux/debugfs.h>
 #include <linux/kexec.h>
 #include <linux/sizes.h>
+#include <linux/device.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
@@ -476,6 +478,7 @@ static void __init bootmem_init(void)
  *  o bootmem_init()
  *  o sparse_init()
  *  o paging_init()
+ *  o dma_continguous_reserve()
  *
  * At this stage the bootmem allocator is ready to use.
  *
@@ -609,6 +612,7 @@ static void __init request_crashkernel(struct resource *res)
 
 static void __init arch_mem_init(char **cmdline_p)
 {
+	struct memblock_region *reg;
 	extern void plat_mem_setup(void);
 
 	/* call board setup routine */
@@ -675,6 +679,11 @@ static void __init arch_mem_init(char **cmdline_p)
 	sparse_init();
 	plat_swiotlb_setup();
 	paging_init();
+
+	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
+	/* Tell bootmem about cma reserved memblock section */
+	for_each_memblock(reserved, reg)
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 }
 
 static void __init resource_init(void)
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index df9e2bd9b2c2..06bb5ed6d80a 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -346,7 +346,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id)
 	int action, cpu = irq - IPI0_IRQ;
 
 	spin_lock_irqsave(&ipi_lock, flags);
-	action = __get_cpu_var(ipi_action_mask);
+	action = __this_cpu_read(ipi_action_mask);
 	per_cpu(ipi_action_mask, cpu) = 0;
 	clear_c0_cause(cpu ? C_SW1 : C_SW0);
 	spin_unlock_irqrestore(&ipi_lock, flags);
diff --git a/arch/mips/lantiq/Kconfig b/arch/mips/lantiq/Kconfig
index c0021912131e..e10d33342b30 100644
--- a/arch/mips/lantiq/Kconfig
+++ b/arch/mips/lantiq/Kconfig
@@ -30,6 +30,7 @@ choice
 config DT_EASY50712
 	bool "Easy50712"
 	depends on SOC_XWAY
+	select BUILTIN_DTB
 endchoice
 
 config PCI_LANTIQ
diff --git a/arch/mips/lantiq/Makefile b/arch/mips/lantiq/Makefile
index d6bdc579419f..690257ab86d6 100644
--- a/arch/mips/lantiq/Makefile
+++ b/arch/mips/lantiq/Makefile
@@ -6,8 +6,6 @@
 
 obj-y := irq.o clk.o prom.o
 
-obj-y += dts/
-
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 
 obj-$(CONFIG_SOC_TYPE_XWAY) += xway/
diff --git a/arch/mips/lantiq/dts/Makefile b/arch/mips/lantiq/dts/Makefile
deleted file mode 100644
index 6fa72dd641b2..000000000000
--- a/arch/mips/lantiq/dts/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-$(CONFIG_DT_EASY50712) := easy50712.dtb.o
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 9901237563c5..4c721e247ac9 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -277,9 +277,12 @@ LEAF(csum_partial)
 #endif
 
 	/* odd buffer alignment? */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+	.set	push
+	.set	arch=mips32r2
 	wsbh	v1, sum
 	movn	sum, v1, t7
+	.set	pop
 #else
 	beqz	t7, 1f			/* odd buffer alignment? */
 	 lui	v1, 0x00ff
@@ -726,9 +729,12 @@ LEAF(csum_partial)
 	addu	sum, v1
 #endif
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+	.set	push
+	.set	arch=mips32r2
 	wsbh	v1, sum
 	movn	sum, v1, odd
+	.set	pop
 #else
 	beqz	odd, 1f			/* odd buffer alignment? */
 	 lui	v1, 0x00ff
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index 74e827b4ec8f..d8c63af6c7cc 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -299,16 +299,16 @@ static void loongson3_init_secondary(void)
 	per_cpu(cpu_state, cpu) = CPU_ONLINE;
 
 	i = 0;
-	__get_cpu_var(core0_c0count) = 0;
+	__this_cpu_write(core0_c0count, 0);
 	loongson3_send_ipi_single(0, SMP_ASK_C0COUNT);
-	while (!__get_cpu_var(core0_c0count)) {
+	while (!__this_cpu_read(core0_c0count)) {
 		i++;
 		cpu_relax();
 	}
 
 	if (i > MAX_LOOPS)
 		i = MAX_LOOPS;
-	initcount = __get_cpu_var(core0_c0count) + i;
+	initcount = __this_cpu_read(core0_c0count) + i;
 	write_c0_count(initcount);
 }
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 44b6dff5aba2..33ba3c558fe4 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/cache.h>
 #include <asm/cpu-type.h>
@@ -128,23 +129,30 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 	dma_addr_t * dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
+	struct page *page = NULL;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
 		return ret;
 
 	gfp = massage_gfp_flags(dev, gfp);
 
-	ret = (void *) __get_free_pages(gfp, get_order(size));
-
-	if (ret) {
-		memset(ret, 0, size);
-		*dma_handle = plat_map_dma_mem(dev, ret, size);
-
-		if (!plat_device_is_coherent(dev)) {
-			dma_cache_wback_inv((unsigned long) ret, size);
-			if (!hw_coherentio)
-				ret = UNCAC_ADDR(ret);
-		}
+	if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+		page = dma_alloc_from_contiguous(dev,
+					count, get_order(size));
+	if (!page)
+		page = alloc_pages(gfp, get_order(size));
+
+	if (!page)
+		return NULL;
+
+	ret = page_address(page);
+	memset(ret, 0, size);
+	*dma_handle = plat_map_dma_mem(dev, ret, size);
+	if (!plat_device_is_coherent(dev)) {
+		dma_cache_wback_inv((unsigned long) ret, size);
+		if (!hw_coherentio)
+			ret = UNCAC_ADDR(ret);
 	}
 
 	return ret;
@@ -164,6 +172,8 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 {
 	unsigned long addr = (unsigned long) vaddr;
 	int order = get_order(size);
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = NULL;
 
 	if (dma_release_from_coherent(dev, order, vaddr))
 		return;
@@ -173,7 +183,10 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 	if (!plat_device_is_coherent(dev) && !hw_coherentio)
 		addr = CAC_ADDR(addr);
 
-	free_pages(addr, get_order(size));
+	page = virt_to_page((void *) addr);
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(size));
 }
 
 static inline void __dma_sync_virtual(void *addr, size_t size,
diff --git a/arch/mips/mti-sead3/Makefile b/arch/mips/mti-sead3/Makefile
index 071786fa234b..febf4334545e 100644
--- a/arch/mips/mti-sead3/Makefile
+++ b/arch/mips/mti-sead3/Makefile
@@ -19,9 +19,5 @@ obj-y				+= sead3-i2c-dev.o sead3-i2c.o \
 
 obj-$(CONFIG_EARLY_PRINTK)	+= sead3-console.o
 obj-$(CONFIG_USB_EHCI_HCD)	+= sead3-ehci.o
-obj-$(CONFIG_OF)		+= sead3.dtb.o
 
 CFLAGS_sead3-setup.o = -I$(src)/../../../scripts/dtc/libfdt
-
-$(obj)/%.dtb: $(obj)/%.dts
-	$(call if_changed,dtc)
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 7edc08398c4a..9b55143d19db 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -163,6 +163,19 @@ do {							\
 	(ctx)->idx++;					\
 } while (0)
 
+/*
+ * Similar to emit_instr but it must be used when we need to emit
+ * 32-bit or 64-bit instructions
+ */
+#define emit_long_instr(ctx, func, ...)			\
+do {							\
+	if ((ctx)->target != NULL) {			\
+		u32 *p = &(ctx)->target[ctx->idx];	\
+		UASM_i_##func(&p, ##__VA_ARGS__);	\
+	}						\
+	(ctx)->idx++;					\
+} while (0)
+
 /* Determine if immediate is within the 16-bit signed range */
 static inline bool is_range16(s32 imm)
 {
@@ -218,13 +231,6 @@ static inline void emit_ori(unsigned int dst, unsigned src, u32 imm,
 	}
 }
 
-
-static inline void emit_daddu(unsigned int dst, unsigned int src1,
-			      unsigned int src2, struct jit_ctx *ctx)
-{
-	emit_instr(ctx, daddu, dst, src1, src2);
-}
-
 static inline void emit_daddiu(unsigned int dst, unsigned int src,
 			       int imm, struct jit_ctx *ctx)
 {
@@ -283,11 +289,7 @@ static inline void emit_xori(ptr dst, ptr src, u32 imm, struct jit_ctx *ctx)
 
 static inline void emit_stack_offset(int offset, struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, daddiu, r_sp, r_sp, offset);
-	else
-		emit_instr(ctx, addiu, r_sp, r_sp, offset);
-
+	emit_long_instr(ctx, ADDIU, r_sp, r_sp, offset);
 }
 
 static inline void emit_subu(unsigned int dst, unsigned int src1,
@@ -365,10 +367,7 @@ static inline void emit_store_stack_reg(ptr reg, ptr base,
 					unsigned int offset,
 					struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, sd, reg, offset, base);
-	else
-		emit_instr(ctx, sw, reg, offset, base);
+	emit_long_instr(ctx, SW, reg, offset, base);
 }
 
 static inline void emit_store(ptr reg, ptr base, unsigned int offset,
@@ -381,10 +380,7 @@ static inline void emit_load_stack_reg(ptr reg, ptr base,
 				       unsigned int offset,
 				       struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, ld, reg, offset, base);
-	else
-		emit_instr(ctx, lw, reg, offset, base);
+	emit_long_instr(ctx, LW, reg, offset, base);
 }
 
 static inline void emit_load(unsigned int reg, unsigned int base,
@@ -458,10 +454,7 @@ static inline void emit_load_ptr(unsigned int dst, unsigned int src,
 				     int imm, struct jit_ctx *ctx)
 {
 	/* src contains the base addr of the 32/64-pointer */
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, ld, dst, imm, src);
-	else
-		emit_instr(ctx, lw, dst, imm, src);
+	emit_long_instr(ctx, LW, dst, imm, src);
 }
 
 /* load a function pointer to register */
@@ -483,10 +476,7 @@ static inline void emit_load_func(unsigned int reg, ptr imm,
 /* Move to real MIPS register */
 static inline void emit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_daddu(dst, src, r_zero, ctx);
-	else
-		emit_addu(dst, src, r_zero, ctx);
+	emit_long_instr(ctx, ADDU, dst, src, r_zero);
 }
 
 /* Move to JIT (32-bit) register */
@@ -623,10 +613,7 @@ static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
 	if (ctx->flags & SEEN_MEM) {
 		if (real_off % (RSIZE * 2))
 			real_off += RSIZE;
-		if (config_enabled(CONFIG_64BIT))
-			emit_daddiu(r_M, r_sp, real_off, ctx);
-		else
-			emit_addiu(r_M, r_sp, real_off, ctx);
+		emit_long_instr(ctx, ADDIU, r_M, r_sp, real_off);
 	}
 }
 
@@ -1241,7 +1228,7 @@ jmp_cmp:
 			emit_half_load(r_A, r_skb, off, ctx);
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 			/* This needs little endian fixup */
-			if (cpu_has_mips_r2) {
+			if (cpu_has_wsbh) {
 				/* R2 and later have the wsbh instruction */
 				emit_wsbh(r_A, r_A, ctx);
 			} else {
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 4eb683aef7d7..0823321c10e0 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -4,6 +4,7 @@ if NLM_XLP_BOARD
 config DT_XLP_EVP
 	bool "Built-in device tree for XLP EVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP EVP boards into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
@@ -13,6 +14,7 @@ config DT_XLP_EVP
 config DT_XLP_SVP
 	bool "Built-in device tree for XLP SVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP VP boards into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
@@ -22,6 +24,7 @@ config DT_XLP_SVP
 config DT_XLP_FVP
 	bool "Built-in device tree for XLP FVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP FVP board into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
@@ -31,6 +34,7 @@ config DT_XLP_FVP
 config DT_XLP_GVP
 	bool "Built-in device tree for XLP GVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP GVP board into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
diff --git a/arch/mips/netlogic/Makefile b/arch/mips/netlogic/Makefile
index 7602d1386614..36d169b2ca6d 100644
--- a/arch/mips/netlogic/Makefile
+++ b/arch/mips/netlogic/Makefile
@@ -1,4 +1,3 @@
 obj-$(CONFIG_NLM_COMMON)	+=	common/
 obj-$(CONFIG_CPU_XLR)		+=	xlr/
 obj-$(CONFIG_CPU_XLP)		+=	xlp/
-obj-$(CONFIG_CPU_XLP)		+=	dts/
diff --git a/arch/mips/netlogic/dts/Makefile b/arch/mips/netlogic/dts/Makefile
deleted file mode 100644
index 25c8e873ee25..000000000000
--- a/arch/mips/netlogic/dts/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-obj-$(CONFIG_DT_XLP_EVP) := xlp_evp.dtb.o
-obj-$(CONFIG_DT_XLP_SVP) += xlp_svp.dtb.o
-obj-$(CONFIG_DT_XLP_FVP) += xlp_fvp.dtb.o
-obj-$(CONFIG_DT_XLP_GVP) += xlp_gvp.dtb.o
diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig
index 4a296655f446..77e8a9620e18 100644
--- a/arch/mips/ralink/Kconfig
+++ b/arch/mips/ralink/Kconfig
@@ -42,18 +42,22 @@ choice
 	config DTB_RT2880_EVAL
 		bool "RT2880 eval kit"
 		depends on SOC_RT288X
+		select BUILTIN_DTB
 
 	config DTB_RT305X_EVAL
 		bool "RT305x eval kit"
 		depends on SOC_RT305X
+		select BUILTIN_DTB
 
 	config DTB_RT3883_EVAL
 		bool "RT3883 eval kit"
 		depends on SOC_RT3883
+		select BUILTIN_DTB
 
 	config DTB_MT7620A_EVAL
 		bool "MT7620A eval kit"
 		depends on SOC_MT7620
+		select BUILTIN_DTB
 
 endchoice
 
diff --git a/arch/mips/ralink/Makefile b/arch/mips/ralink/Makefile
index 98ae349827be..2c09c8aa0ae2 100644
--- a/arch/mips/ralink/Makefile
+++ b/arch/mips/ralink/Makefile
@@ -16,5 +16,3 @@ obj-$(CONFIG_SOC_RT3883) += rt3883.o
 obj-$(CONFIG_SOC_MT7620) += mt7620.o
 
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-
-obj-y += dts/
diff --git a/arch/mips/ralink/dts/Makefile b/arch/mips/ralink/dts/Makefile
deleted file mode 100644
index 18194fa93e80..000000000000
--- a/arch/mips/ralink/dts/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-obj-$(CONFIG_DTB_RT2880_EVAL) := rt2880_eval.dtb.o
-obj-$(CONFIG_DTB_RT305X_EVAL) := rt3052_eval.dtb.o
-obj-$(CONFIG_DTB_RT3883_EVAL) := rt3883_eval.dtb.o
-obj-$(CONFIG_DTB_MT7620A_EVAL) := mt7620a_eval.dtb.o
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index e38692a44e69..5bb29b3790ff 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -58,7 +58,7 @@ static irqreturn_t rt_timer_irq(int irq, void *_rt)
 
 static int rt_timer_request(struct rt_timer *rt)
 {
-	int err = request_irq(rt->irq, rt_timer_irq, IRQF_DISABLED,
+	int err = request_irq(rt->irq, rt_timer_irq, 0,
 						dev_name(rt->dev), rt);
 	if (err) {
 		dev_err(rt->dev, "failed to request irq\n");
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index b752bb67891d..2db9f1cf0694 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -19,6 +19,7 @@
 #ifndef __ASM_OPENRISC_SYSCALL_H__
 #define __ASM_OPENRISC_SYSCALL_H__
 
+#include <uapi/linux/audit.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 
@@ -71,4 +72,8 @@ syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
 	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
 }
 
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_OPENRISC;
+}
 #endif
diff --git a/arch/openrisc/include/uapi/asm/elf.h b/arch/openrisc/include/uapi/asm/elf.h
index f02ea5830420..88842760e66f 100644
--- a/arch/openrisc/include/uapi/asm/elf.h
+++ b/arch/openrisc/include/uapi/asm/elf.h
@@ -55,9 +55,8 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 /* A placeholder; OR32 does not have fp support yes, so no fp regs for now.  */
 typedef unsigned long elf_fpregset_t;
 
-/* This should be moved to include/linux/elf.h */
+/* EM_OPENRISC is defined in linux/elf-em.h */
 #define EM_OR32         0x8472
-#define EM_OPENRISC     92     /* OpenRISC 32-bit embedded processor */
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c
index 71a2a0c34c65..4f59fa4e34e5 100644
--- a/arch/openrisc/kernel/ptrace.c
+++ b/arch/openrisc/kernel/ptrace.c
@@ -187,8 +187,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
-	audit_syscall_entry(AUDIT_ARCH_OPENRISC, regs->gpr[11],
-			    regs->gpr[3], regs->gpr[4],
+	audit_syscall_entry(regs->gpr[11], regs->gpr[3], regs->gpr[4],
 			    regs->gpr[5], regs->gpr[6]);
 
 	return ret ? : regs->gpr[11];
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 8bdfd2c8c39f..a5eba95d87fe 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -3,6 +3,8 @@
 #ifndef _ASM_PARISC_SYSCALL_H_
 #define _ASM_PARISC_SYSCALL_H_
 
+#include <uapi/linux/audit.h>
+#include <linux/compat.h>
 #include <linux/err.h>
 #include <asm/ptrace.h>
 
@@ -37,4 +39,13 @@ static inline void syscall_get_arguments(struct task_struct *tsk,
 	}
 }
 
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_PARISC;
+#ifdef CONFIG_64BIT
+	if (!is_compat_task())
+		arch = AUDIT_ARCH_PARISC64;
+#endif
+	return arch;
+}
 #endif /*_ASM_PARISC_SYSCALL_H_*/
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 92438c21d453..9585c81f755f 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -280,14 +280,11 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 
 #ifdef CONFIG_64BIT
 	if (!is_compat_task())
-		audit_syscall_entry(AUDIT_ARCH_PARISC64,
-			regs->gr[20],
-			regs->gr[26], regs->gr[25],
-			regs->gr[24], regs->gr[23]);
+		audit_syscall_entry(regs->gr[20], regs->gr[26], regs->gr[25],
+				    regs->gr[24], regs->gr[23]);
 	else
 #endif
-		audit_syscall_entry(AUDIT_ARCH_PARISC,
-			regs->gr[20] & 0xffffffff,
+		audit_syscall_entry(regs->gr[20] & 0xffffffff,
 			regs->gr[26] & 0xffffffff,
 			regs->gr[25] & 0xffffffff,
 			regs->gr[24] & 0xffffffff,
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 6c840ceab820..e2452550bcb1 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -58,10 +58,10 @@ static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 static inline cputime_t cputime_to_scaled(const cputime_t ct)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR) &&
-	    __get_cpu_var(cputime_last_delta))
+	    __this_cpu_read(cputime_last_delta))
 		return (__force u64) ct *
-			__get_cpu_var(cputime_scaled_last_delta) /
-			__get_cpu_var(cputime_last_delta);
+			__this_cpu_read(cputime_scaled_last_delta) /
+			__this_cpu_read(cputime_last_delta);
 	return ct;
 }
 
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index b54b2add07be..6fa2708da153 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -13,7 +13,9 @@
 #ifndef _ASM_SYSCALL_H
 #define _ASM_SYSCALL_H	1
 
+#include <uapi/linux/audit.h>
 #include <linux/sched.h>
+#include <linux/thread_info.h>
 
 /* ftrace syscalls requires exporting the sys_call_table */
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -86,4 +88,8 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
 }
 
+static inline int syscall_get_arch(void)
+{
+	return is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+}
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index bd70a51d5747..e5dad9a9edc0 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -747,7 +747,11 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			break;
 		}
 		if (res != NULL) {
-			of_pci_range_to_resource(&range, dev, res);
+			res->name = dev->full_name;
+			res->flags = range.flags;
+			res->start = range.cpu_addr;
+			res->end = range.cpu_addr + range.size - 1;
+			res->parent = res->child = res->sibling = NULL;
 		}
 	}
 }
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index cdb404ea3468..f21897b42057 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1788,14 +1788,11 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 
 #ifdef CONFIG_PPC64
 	if (!is_32bit_task())
-		audit_syscall_entry(AUDIT_ARCH_PPC64,
-				    regs->gpr[0],
-				    regs->gpr[3], regs->gpr[4],
+		audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
 				    regs->gpr[5], regs->gpr[6]);
 	else
 #endif
-		audit_syscall_entry(AUDIT_ARCH_PPC,
-				    regs->gpr[0],
+		audit_syscall_entry(regs->gpr[0],
 				    regs->gpr[3] & 0xffffffff,
 				    regs->gpr[4] & 0xffffffff,
 				    regs->gpr[5] & 0xffffffff,
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 296391395b95..f2cf1f90295b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -58,6 +58,9 @@ config NO_IOPORT_MAP
 config PCI_QUIRKS
 	def_bool n
 
+config ARCH_SUPPORTS_UPROBES
+	def_bool 64BIT
+
 config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -97,6 +100,7 @@ config S390
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
+	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES if !SMP
 	select GENERIC_FIND_FIRST_BIT
@@ -113,10 +117,11 @@ config S390
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE if 64BIT
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS if 64BIT
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER if 64BIT
+	select HAVE_FUNCTION_TRACER if 64BIT
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 874e6d6e9c5f..878e67973151 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -35,13 +35,16 @@ endif
 
 export LD_BFD
 
-cflags-$(CONFIG_MARCH_G5)     += -march=g5
-cflags-$(CONFIG_MARCH_Z900)   += -march=z900
-cflags-$(CONFIG_MARCH_Z990)   += -march=z990
-cflags-$(CONFIG_MARCH_Z9_109) += -march=z9-109
-cflags-$(CONFIG_MARCH_Z10)    += -march=z10
-cflags-$(CONFIG_MARCH_Z196)   += -march=z196
-cflags-$(CONFIG_MARCH_ZEC12)  += -march=zEC12
+mflags-$(CONFIG_MARCH_G5)     := -march=g5
+mflags-$(CONFIG_MARCH_Z900)   := -march=z900
+mflags-$(CONFIG_MARCH_Z990)   := -march=z990
+mflags-$(CONFIG_MARCH_Z9_109) := -march=z9-109
+mflags-$(CONFIG_MARCH_Z10)    := -march=z10
+mflags-$(CONFIG_MARCH_Z196)   := -march=z196
+mflags-$(CONFIG_MARCH_ZEC12)  := -march=zEC12
+
+aflags-y += $(mflags-y)
+cflags-y += $(mflags-y)
 
 cflags-$(CONFIG_MARCH_G5_TUNE)		+= -mtune=g5
 cflags-$(CONFIG_MARCH_Z900_TUNE)	+= -mtune=z900
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 19ff956b752b..b5dce6544d76 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -15,11 +15,13 @@
 
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 /* Fast-BCR without checkpoint synchronization */
-#define mb() do {  asm volatile("bcr 14,0" : : : "memory"); } while (0)
+#define __ASM_BARRIER "bcr 14,0\n"
 #else
-#define mb() do {  asm volatile("bcr 15,0" : : : "memory"); } while (0)
+#define __ASM_BARRIER "bcr 15,0\n"
 #endif
 
+#define mb() do {  asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
+
 #define rmb()				mb()
 #define wmb()				mb()
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 3001887f94b7..f8c196984853 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -8,8 +8,6 @@
 #define _S390_CPUTIME_H
 
 #include <linux/types.h>
-#include <linux/percpu.h>
-#include <linux/spinlock.h>
 #include <asm/div64.h>
 
 
@@ -167,28 +165,8 @@ static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
 	return clock;
 }
 
-struct s390_idle_data {
-	int nohz_delay;
-	unsigned int sequence;
-	unsigned long long idle_count;
-	unsigned long long idle_time;
-	unsigned long long clock_idle_enter;
-	unsigned long long clock_idle_exit;
-	unsigned long long timer_idle_enter;
-	unsigned long long timer_idle_exit;
-};
+cputime64_t arch_cpu_idle_time(int cpu);
 
-DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
-
-cputime64_t s390_get_idle_time(int cpu);
-
-#define arch_idle_time(cpu) s390_get_idle_time(cpu)
-
-static inline int s390_nohz_delay(int cpu)
-{
-	return __get_cpu_var(s390_idle).nohz_delay != 0;
-}
-
-#define arch_needs_cpu(cpu) s390_nohz_delay(cpu)
+#define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
 
 #endif /* _S390_CPUTIME_H */
diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h
index 04a83f5773cd..60323c21938b 100644
--- a/arch/s390/include/asm/dis.h
+++ b/arch/s390/include/asm/dis.h
@@ -13,12 +13,13 @@
 #define OPERAND_FPR	0x2	/* Operand printed as %fx */
 #define OPERAND_AR	0x4	/* Operand printed as %ax */
 #define OPERAND_CR	0x8	/* Operand printed as %cx */
-#define OPERAND_DISP	0x10	/* Operand printed as displacement */
-#define OPERAND_BASE	0x20	/* Operand printed as base register */
-#define OPERAND_INDEX	0x40	/* Operand printed as index register */
-#define OPERAND_PCREL	0x80	/* Operand printed as pc-relative symbol */
-#define OPERAND_SIGNED	0x100	/* Operand printed as signed value */
-#define OPERAND_LENGTH	0x200	/* Operand printed as length (+1) */
+#define OPERAND_VR	0x10	/* Operand printed as %vx */
+#define OPERAND_DISP	0x20	/* Operand printed as displacement */
+#define OPERAND_BASE	0x40	/* Operand printed as base register */
+#define OPERAND_INDEX	0x80	/* Operand printed as index register */
+#define OPERAND_PCREL	0x100	/* Operand printed as pc-relative symbol */
+#define OPERAND_SIGNED	0x200	/* Operand printed as signed value */
+#define OPERAND_LENGTH	0x400	/* Operand printed as length (+1) */
 
 
 struct s390_operand {
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 78f4f8711d58..f6e43d39e3d8 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -102,6 +102,7 @@
 #define HWCAP_S390_ETF3EH	256
 #define HWCAP_S390_HIGH_GPRS	512
 #define HWCAP_S390_TE		1024
+#define HWCAP_S390_VXRS		2048
 
 /*
  * These are used to set parameters in the core dumps.
@@ -225,6 +226,6 @@ int arch_setup_additional_pages(struct linux_binprm *, int);
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-void *fill_cpu_elf_notes(void *ptr, struct save_area *sa);
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vxrs);
 
 #endif
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index bf246dae1367..3aef8afec336 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -4,6 +4,7 @@
 #ifndef __ASSEMBLY__
 
 extern void _mcount(void);
+extern char ftrace_graph_caller_end;
 
 struct dyn_arch_ftrace { };
 
@@ -17,10 +18,8 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 #endif /* __ASSEMBLY__ */
 
-#ifdef CONFIG_64BIT
-#define MCOUNT_INSN_SIZE  12
-#else
-#define MCOUNT_INSN_SIZE  22
-#endif
+#define MCOUNT_INSN_SIZE  18
+
+#define ARCH_SUPPORTS_FTRACE_OPS 1
 
 #endif /* _ASM_S390_FTRACE_H */
diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
new file mode 100644
index 000000000000..6af037f574b8
--- /dev/null
+++ b/arch/s390/include/asm/idle.h
@@ -0,0 +1,26 @@
+/*
+ *  Copyright IBM Corp. 2014
+ *
+ *  Author: Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _S390_IDLE_H
+#define _S390_IDLE_H
+
+#include <linux/types.h>
+#include <linux/device.h>
+
+struct s390_idle_data {
+	unsigned int sequence;
+	unsigned long long idle_count;
+	unsigned long long idle_time;
+	unsigned long long clock_idle_enter;
+	unsigned long long clock_idle_exit;
+	unsigned long long timer_idle_enter;
+	unsigned long long timer_idle_exit;
+};
+
+extern struct device_attribute dev_attr_idle_count;
+extern struct device_attribute dev_attr_idle_time_us;
+
+#endif /* _S390_IDLE_H */
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index c81661e756a0..ece606c2ee86 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -89,12 +89,12 @@ extern u32 ipl_flags;
 extern u32 dump_prefix_page;
 
 struct dump_save_areas {
-	struct save_area **areas;
+	struct save_area_ext **areas;
 	int count;
 };
 
 extern struct dump_save_areas dump_save_areas;
-struct save_area *dump_save_area_create(int cpu);
+struct save_area_ext *dump_save_area_create(int cpu);
 
 extern void do_reipl(void);
 extern void do_halt(void);
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index c4dd400a2791..b0d5f0a97a01 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -51,6 +51,7 @@ enum interruption_class {
 	IRQEXT_CMS,
 	IRQEXT_CMC,
 	IRQEXT_CMR,
+	IRQEXT_FTP,
 	IRQIO_CIO,
 	IRQIO_QAI,
 	IRQIO_DAS,
@@ -81,7 +82,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
 
 static __always_inline void inc_irq_stat(enum interruption_class irq)
 {
-	__get_cpu_var(irq_stat).irqs[irq]++;
+	__this_cpu_inc(irq_stat.irqs[irq]);
 }
 
 struct ext_code {
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 4176dfe0fba1..98629173ce3b 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -84,6 +84,10 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 	unsigned long val, void *data);
 
+int probe_is_prohibited_opcode(u16 *insn);
+int probe_get_fixup_type(u16 *insn);
+int probe_is_insn_relative_long(u16 *insn);
+
 #define flush_insn_slot(p)	do { } while (0)
 
 #endif	/* _ASM_S390_KPROBES_H */
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 4349197ab9df..6cc51fe84410 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <asm/ptrace.h>
 #include <asm/cpu.h>
+#include <asm/types.h>
 
 #ifdef CONFIG_32BIT
 
@@ -31,6 +32,11 @@ struct save_area {
 	u32	ctrl_regs[16];
 } __packed;
 
+struct save_area_ext {
+	struct save_area	sa;
+	__vector128		vx_regs[32];
+};
+
 struct _lowcore {
 	psw_t	restart_psw;			/* 0x0000 */
 	psw_t	restart_old_psw;		/* 0x0008 */
@@ -183,6 +189,11 @@ struct save_area {
 	u64	ctrl_regs[16];
 } __packed;
 
+struct save_area_ext {
+	struct save_area	sa;
+	__vector128		vx_regs[32];
+};
+
 struct _lowcore {
 	__u8	pad_0x0000[0x0014-0x0000];	/* 0x0000 */
 	__u32	ipl_parmblock_ptr;		/* 0x0014 */
@@ -310,7 +321,10 @@ struct _lowcore {
 
 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
-	__u8	pad_0x1000[0x11b8-0x1000];	/* 0x1000 */
+	__u8	pad_0x1000[0x11b0-0x1000];	/* 0x1000 */
+
+	/* Pointer to vector register save area */
+	__u64	vector_save_area_addr;		/* 0x11b0 */
 
 	/* 64 bit extparam used for pfault/diag 250: defined by architecture */
 	__u64	ext_params2;			/* 0x11B8 */
@@ -334,9 +348,10 @@ struct _lowcore {
 
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
+	__u8	pad_0x1900[0x1c00-0x1900];	/* 0x1900 */
 
-	/* align to the top of the prefix area */
-	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
+	/* Software defined save area for vector registers */
+	__u8	vector_save_area[1024];		/* 0x1c00 */
 } __packed;
 
 #endif /* CONFIG_32BIT */
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
index 35f8ec185616..3027a5a72b74 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -38,7 +38,7 @@ struct mci {
 	__u32 pm :  1; /* 22 psw program mask and cc validity */
 	__u32 ia :  1; /* 23 psw instruction address validity */
 	__u32 fa :  1; /* 24 failing storage address validity */
-	__u32	 :  1; /* 25 */
+	__u32 vr :  1; /* 25 vector register validity */
 	__u32 ec :  1; /* 26 external damage code validity */
 	__u32 fp :  1; /* 27 floating point register validity */
 	__u32 gr :  1; /* 28 general register validity */
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index fa91e0097458..933355e0d091 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -31,7 +31,7 @@
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
 		old__ = prev__;						\
@@ -70,7 +70,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
 		asm volatile(						\
@@ -97,7 +97,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
@@ -116,7 +116,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
@@ -138,7 +138,7 @@
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
 	preempt_enable();						\
 	ret__;								\
@@ -154,7 +154,7 @@
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
 	preempt_enable();						\
 	ret__;								\
@@ -173,8 +173,8 @@
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
 	preempt_disable();						\
-	p1__ = __this_cpu_ptr(&(pcp1));					\
-	p2__ = __this_cpu_ptr(&(pcp2));					\
+	p1__ = raw_cpu_ptr(&(pcp1));					\
+	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
 	preempt_enable();						\
 	ret__;								\
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index b7054356cc98..57c882761dea 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -217,7 +217,6 @@ extern unsigned long MODULES_END;
  */
 
 /* Hardware bits in the page table entry */
-#define _PAGE_CO	0x100		/* HW Change-bit override */
 #define _PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define _PAGE_INVALID	0x400		/* HW invalid bit    */
 #define _PAGE_LARGE	0x800		/* Bit to mark a large pte */
@@ -234,8 +233,8 @@ extern unsigned long MODULES_END;
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK		(PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \
-				 _PAGE_DIRTY | _PAGE_YOUNG)
+#define _PAGE_CHG_MASK		(PAGE_MASK | _PAGE_SPECIAL | _PAGE_DIRTY | \
+				 _PAGE_YOUNG)
 
 /*
  * handle_pte_fault uses pte_present, pte_none and pte_file to find out the
@@ -354,7 +353,6 @@ extern unsigned long MODULES_END;
 
 #define _REGION3_ENTRY_LARGE	0x400	/* RTTE-format control, large page  */
 #define _REGION3_ENTRY_RO	0x200	/* page protection bit		    */
-#define _REGION3_ENTRY_CO	0x100	/* change-recording override	    */
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
@@ -371,7 +369,6 @@ extern unsigned long MODULES_END;
 #define _SEGMENT_ENTRY_YOUNG	0x1000	/* SW segment young bit */
 #define _SEGMENT_ENTRY_SPLIT	0x0800	/* THP splitting bit */
 #define _SEGMENT_ENTRY_LARGE	0x0400	/* STE-format control, large page */
-#define _SEGMENT_ENTRY_CO	0x0100	/* change-recording override   */
 #define _SEGMENT_ENTRY_READ	0x0002	/* SW segment read bit */
 #define _SEGMENT_ENTRY_WRITE	0x0001	/* SW segment write bit */
 
@@ -873,8 +870,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else {
-		if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1)
-			pte_val(entry) |= _PAGE_CO;
 		*ptep = entry;
 	}
 }
@@ -1044,6 +1039,22 @@ static inline void __ptep_ipte_local(unsigned long address, pte_t *ptep)
 		: "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
 }
 
+static inline void __ptep_ipte_range(unsigned long address, int nr, pte_t *ptep)
+{
+	unsigned long pto = (unsigned long) ptep;
+
+#ifndef CONFIG_64BIT
+	/* pto in ESA mode must point to the start of the segment table */
+	pto &= 0x7ffffc00;
+#endif
+	/* Invalidate a range of ptes + global TLB flush of the ptes */
+	do {
+		asm volatile(
+			"	.insn rrf,0xb2210000,%2,%0,%1,0"
+			: "+a" (address), "+a" (nr) : "a" (pto) : "memory");
+	} while (nr != 255);
+}
+
 static inline void ptep_flush_direct(struct mm_struct *mm,
 				     unsigned long address, pte_t *ptep)
 {
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index e568fc8a7250..d559bdb03d18 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -13,9 +13,11 @@
 
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
 #define CIF_ASCE		1	/* user asce needs fixup / uaccess */
+#define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
 
 #define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
 #define _CIF_ASCE		(1<<CIF_ASCE)
+#define _CIF_NOHZ_DELAY		(1<<CIF_NOHZ_DELAY)
 
 
 #ifndef __ASSEMBLY__
@@ -43,6 +45,8 @@ static inline int test_cpu_flag(int flag)
 	return !!(S390_lowcore.cpu_flags & (1U << flag));
 }
 
+#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -113,6 +117,7 @@ struct thread_struct {
 	int ri_signum;
 #ifdef CONFIG_64BIT
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
+	__vector128 *vxrs;		/* Vector register save area */
 #endif
 };
 
@@ -285,7 +290,12 @@ static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc)
 	return (psw.addr - ilc) & mask;
 #endif
 }
- 
+
+/*
+ * Function to stop a processor until the next interrupt occurs
+ */
+void enabled_wait(void);
+
 /*
  * Function to drop a processor into disabled wait state
  */
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 55d69dd7473c..be317feff7ac 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -161,6 +161,12 @@ static inline long regs_return_value(struct pt_regs *regs)
 	return regs->gprs[2];
 }
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	regs->psw.addr = val | PSW_ADDR_AMODE;
+}
+
 int regs_query_register_offset(const char *name);
 const char *regs_query_register_name(unsigned int offset);
 unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 089a49814c50..7736fdd72595 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -55,8 +55,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_FLAG_LPP	(1UL << 13)
 #define MACHINE_FLAG_TOPOLOGY	(1UL << 14)
 #define MACHINE_FLAG_TE		(1UL << 15)
-#define MACHINE_FLAG_RRBM	(1UL << 16)
 #define MACHINE_FLAG_TLB_LC	(1UL << 17)
+#define MACHINE_FLAG_VX		(1UL << 18)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -78,8 +78,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_LPP		(0)
 #define MACHINE_HAS_TOPOLOGY	(0)
 #define MACHINE_HAS_TE		(0)
-#define MACHINE_HAS_RRBM	(0)
 #define MACHINE_HAS_TLB_LC	(0)
+#define MACHINE_HAS_VX		(0)
 #else /* CONFIG_64BIT */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -91,8 +91,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_LPP		(S390_lowcore.machine_flags & MACHINE_FLAG_LPP)
 #define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
-#define MACHINE_HAS_RRBM	(S390_lowcore.machine_flags & MACHINE_FLAG_RRBM)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
+#define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
 #endif /* CONFIG_64BIT */
 
 /*
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index bf9c823d4020..49576115dbb7 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -15,6 +15,7 @@
 #define SIGP_SET_ARCHITECTURE	     18
 #define SIGP_COND_EMERGENCY_SIGNAL   19
 #define SIGP_SENSE_RUNNING	     21
+#define SIGP_STORE_ADDITIONAL_STATUS 23
 
 /* SIGP condition codes */
 #define SIGP_CC_ORDER_CODE_ACCEPTED 0
@@ -33,9 +34,10 @@
 
 #ifndef __ASSEMBLY__
 
-static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status)
+static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm,
+			      u32 *status)
 {
-	register unsigned int reg1 asm ("1") = parm;
+	register unsigned long reg1 asm ("1") = parm;
 	int cc;
 
 	asm volatile(
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 4f1307962a95..762d4f88af5a 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -29,7 +29,6 @@ extern int smp_find_processor_id(u16 address);
 extern int smp_store_status(int cpu);
 extern int smp_vcpu_scheduled(int cpu);
 extern void smp_yield_cpu(int cpu);
-extern void smp_yield(void);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);
 extern void smp_fill_possible_mask(void);
@@ -50,7 +49,6 @@ static inline int smp_find_processor_id(u16 address) { return 0; }
 static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
-static inline void smp_yield(void) { }
 static inline void smp_fill_possible_mask(void) { }
 
 #endif /* CONFIG_SMP */
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 96879f7ad6da..d6bdf906caa5 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -37,11 +37,17 @@ _raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new)
  * (the type definitions are in asm/spinlock_types.h)
  */
 
+void arch_lock_relax(unsigned int cpu);
+
 void arch_spin_lock_wait(arch_spinlock_t *);
 int arch_spin_trylock_retry(arch_spinlock_t *);
-void arch_spin_relax(arch_spinlock_t *);
 void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 
+static inline void arch_spin_relax(arch_spinlock_t *lock)
+{
+	arch_lock_relax(lock->lock);
+}
+
 static inline u32 arch_spin_lockval(int cpu)
 {
 	return ~cpu;
@@ -64,11 +70,6 @@ static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
 		      _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
-static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
-{
-	return _raw_compare_and_swap(&lp->lock, SPINLOCK_LOCKVAL, 0);
-}
-
 static inline void arch_spin_lock(arch_spinlock_t *lp)
 {
 	if (!arch_spin_trylock_once(lp))
@@ -91,7 +92,13 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
-	arch_spin_tryrelease_once(lp);
+	typecheck(unsigned int, lp->lock);
+	asm volatile(
+		__ASM_BARRIER
+		"st	%1,%0\n"
+		: "+Q" (lp->lock)
+		: "d" (0)
+		: "cc", "memory");
 }
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
@@ -123,13 +130,12 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
  */
 #define arch_write_can_lock(x) ((x)->lock == 0)
 
-extern void _raw_read_lock_wait(arch_rwlock_t *lp);
-extern void _raw_read_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_read_trylock_retry(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
 static inline int arch_read_trylock_once(arch_rwlock_t *rw)
 {
 	unsigned int old = ACCESS_ONCE(rw->lock);
@@ -144,16 +150,82 @@ static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 		      _raw_compare_and_swap(&rw->lock, 0, 0x80000000));
 }
 
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+
+#define __RAW_OP_OR	"lao"
+#define __RAW_OP_AND	"lan"
+#define __RAW_OP_ADD	"laa"
+
+#define __RAW_LOCK(ptr, op_val, op_string)		\
+({							\
+	unsigned int old_val;				\
+							\
+	typecheck(unsigned int *, ptr);			\
+	asm volatile(					\
+		op_string "	%0,%2,%1\n"		\
+		"bcr	14,0\n"				\
+		: "=d" (old_val), "+Q" (*ptr)		\
+		: "d" (op_val)				\
+		: "cc", "memory");			\
+	old_val;					\
+})
+
+#define __RAW_UNLOCK(ptr, op_val, op_string)		\
+({							\
+	unsigned int old_val;				\
+							\
+	typecheck(unsigned int *, ptr);			\
+	asm volatile(					\
+		"bcr	14,0\n"				\
+		op_string "	%0,%2,%1\n"		\
+		: "=d" (old_val), "+Q" (*ptr)		\
+		: "d" (op_val)				\
+		: "cc", "memory");			\
+	old_val;					\
+})
+
+extern void _raw_read_lock_wait(arch_rwlock_t *lp);
+extern void _raw_write_lock_wait(arch_rwlock_t *lp, unsigned int prev);
+
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
-	if (!arch_read_trylock_once(rw))
+	unsigned int old;
+
+	old = __RAW_LOCK(&rw->lock, 1, __RAW_OP_ADD);
+	if ((int) old < 0)
 		_raw_read_lock_wait(rw);
 }
 
-static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	__RAW_UNLOCK(&rw->lock, -1, __RAW_OP_ADD);
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int old;
+
+	old = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
+	if (old != 0)
+		_raw_write_lock_wait(rw, old);
+	rw->owner = SPINLOCK_LOCKVAL;
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	rw->owner = 0;
+	__RAW_UNLOCK(&rw->lock, 0x7fffffff, __RAW_OP_AND);
+}
+
+#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+extern void _raw_read_lock_wait(arch_rwlock_t *lp);
+extern void _raw_write_lock_wait(arch_rwlock_t *lp);
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	if (!arch_read_trylock_once(rw))
-		_raw_read_lock_wait_flags(rw, flags);
+		_raw_read_lock_wait(rw);
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -169,19 +241,24 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait(rw);
-}
-
-static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags)
-{
-	if (!arch_write_trylock_once(rw))
-		_raw_write_lock_wait_flags(rw, flags);
+	rw->owner = SPINLOCK_LOCKVAL;
 }
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
-	_raw_compare_and_swap(&rw->lock, 0x80000000, 0);
+	typecheck(unsigned int, rw->lock);
+
+	rw->owner = 0;
+	asm volatile(
+		__ASM_BARRIER
+		"st	%1,%0\n"
+		: "+Q" (rw->lock)
+		: "d" (0)
+		: "cc", "memory");
 }
 
+#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	if (!arch_read_trylock_once(rw))
@@ -191,12 +268,20 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	if (!arch_write_trylock_once(rw))
-		return _raw_write_trylock_retry(rw);
+	if (!arch_write_trylock_once(rw) && !_raw_write_trylock_retry(rw))
+		return 0;
+	rw->owner = SPINLOCK_LOCKVAL;
 	return 1;
 }
 
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
+static inline void arch_read_relax(arch_rwlock_t *rw)
+{
+	arch_lock_relax(rw->owner);
+}
+
+static inline void arch_write_relax(arch_rwlock_t *rw)
+{
+	arch_lock_relax(rw->owner);
+}
 
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index b2cd6ff7c2c5..d84b6939237c 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -13,6 +13,7 @@ typedef struct {
 
 typedef struct {
 	unsigned int lock;
+	unsigned int owner;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 18ea9e3f8142..2542a7e4c8b4 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -103,6 +103,61 @@ static inline void restore_fp_regs(freg_t *fprs)
 	asm volatile("ld 15,%0" : : "Q" (fprs[15]));
 }
 
+static inline void save_vx_regs(__vector128 *vxrs)
+{
+	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
+
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
+		: "=Q" (*(addrtype *) vxrs) : : "1");
+}
+
+static inline void save_vx_regs_safe(__vector128 *vxrs)
+{
+	unsigned long cr0, flags;
+
+	flags = arch_local_irq_save();
+	__ctl_store(cr0, 0, 0);
+	__ctl_set_bit(0, 17);
+	__ctl_set_bit(0, 18);
+	save_vx_regs(vxrs);
+	__ctl_load(cr0, 0, 0);
+	arch_local_irq_restore(flags);
+}
+
+static inline void restore_vx_regs(__vector128 *vxrs)
+{
+	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
+
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
+		: : "Q" (*(addrtype *) vxrs) : "1");
+}
+
+static inline void save_fp_vx_regs(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	if (task->thread.vxrs)
+		save_vx_regs(task->thread.vxrs);
+	else
+#endif
+	save_fp_regs(task->thread.fp_regs.fprs);
+}
+
+static inline void restore_fp_vx_regs(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	if (task->thread.vxrs)
+		restore_vx_regs(task->thread.vxrs);
+	else
+#endif
+	restore_fp_regs(task->thread.fp_regs.fprs);
+}
+
 static inline void save_access_regs(unsigned int *acrs)
 {
 	typedef struct { int _[NUM_ACRS]; } acrstype;
@@ -120,16 +175,16 @@ static inline void restore_access_regs(unsigned int *acrs)
 #define switch_to(prev,next,last) do {					\
 	if (prev->mm) {							\
 		save_fp_ctl(&prev->thread.fp_regs.fpc);			\
-		save_fp_regs(prev->thread.fp_regs.fprs);		\
+		save_fp_vx_regs(prev);					\
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
 	}								\
 	if (next->mm) {							\
+		update_cr_regs(next);					\
 		restore_fp_ctl(&next->thread.fp_regs.fpc);		\
-		restore_fp_regs(next->thread.fp_regs.fprs);		\
+		restore_fp_vx_regs(next);				\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
-		update_cr_regs(next);					\
 	}								\
 	prev = __switch_to(prev,next);					\
 } while (0)
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index b833e9c0bfbf..4d62fd5b56e5 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -84,11 +84,13 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
 #define TIF_SECCOMP		5	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_UPROBE		7	/* breakpointed or single-stepping */
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP		19	/* This task is single stepped */
 #define TIF_BLOCK_STEP		20	/* This task is block stepped */
+#define TIF_UPROBE_SINGLESTEP	21	/* This task is uprobe single stepped */
 
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
@@ -97,6 +99,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+#define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_31BIT		(1<<TIF_31BIT)
 #define _TIF_SINGLE_STEP	(1<<TIF_SINGLE_STEP)
 
diff --git a/arch/s390/include/asm/uprobes.h b/arch/s390/include/asm/uprobes.h
new file mode 100644
index 000000000000..1411dff7fea7
--- /dev/null
+++ b/arch/s390/include/asm/uprobes.h
@@ -0,0 +1,42 @@
+/*
+ *    User-space Probes (UProbes) for s390
+ *
+ *    Copyright IBM Corp. 2014
+ *    Author(s): Jan Willeke,
+ */
+
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <linux/notifier.h>
+
+typedef u16 uprobe_opcode_t;
+
+#define UPROBE_XOL_SLOT_BYTES	256 /* cache aligned */
+
+#define UPROBE_SWBP_INSN	0x0002
+#define UPROBE_SWBP_INSN_SIZE	2
+
+struct arch_uprobe {
+	union{
+		uprobe_opcode_t insn[3];
+		uprobe_opcode_t ixol[3];
+	};
+	unsigned int saved_per : 1;
+	unsigned int saved_int_code;
+};
+
+struct arch_uprobe_task {
+};
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm,
+			     unsigned long addr);
+int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
+int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
+				 void *data);
+void arch_uprobe_abort_xol(struct arch_uprobe *ap, struct pt_regs *regs);
+unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
+						struct pt_regs *regs);
+#endif	/* _ASM_UPROBES_H */
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index bc9746a7d47c..a62526d09201 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -22,13 +22,17 @@ struct vdso_data {
 	__u64 xtime_tod_stamp;		/* TOD clock for xtime		0x08 */
 	__u64 xtime_clock_sec;		/* Kernel time			0x10 */
 	__u64 xtime_clock_nsec;		/*				0x18 */
-	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x20 */
-	__u64 wtom_clock_nsec;		/*				0x28 */
-	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x30 */
-	__u32 tz_dsttime;		/* Type of dst correction	0x34 */
-	__u32 ectg_available;		/* ECTG instruction present	0x38 */
-	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x3c */
-	__u32 tk_shift;			/* Shift used for xtime_nsec	0x40 */
+	__u64 xtime_coarse_sec;		/* Coarse kernel time		0x20 */
+	__u64 xtime_coarse_nsec;	/*				0x28 */
+	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x30 */
+	__u64 wtom_clock_nsec;		/*				0x38 */
+	__u64 wtom_coarse_sec;		/* Coarse wall to monotonic	0x40 */
+	__u64 wtom_coarse_nsec;		/*				0x48 */
+	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x50 */
+	__u32 tz_dsttime;		/* Type of dst correction	0x54 */
+	__u32 ectg_available;		/* ECTG instruction present	0x58 */
+	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x5c */
+	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
 };
 
 struct vdso_per_cpu_data {
diff --git a/arch/s390/include/asm/vtimer.h b/arch/s390/include/asm/vtimer.h
index bfe25d513ad2..10a179af62d8 100644
--- a/arch/s390/include/asm/vtimer.h
+++ b/arch/s390/include/asm/vtimer.h
@@ -28,6 +28,4 @@ extern int del_virt_timer(struct vtimer_list *timer);
 extern void init_cpu_vtimer(void);
 extern void vtime_init(void);
 
-extern void vtime_stop_cpu(void);
-
 #endif /* _ASM_S390_TIMER_H */
diff --git a/arch/s390/include/uapi/asm/sigcontext.h b/arch/s390/include/uapi/asm/sigcontext.h
index b30de9c01bbe..5f0b8d7ddb0b 100644
--- a/arch/s390/include/uapi/asm/sigcontext.h
+++ b/arch/s390/include/uapi/asm/sigcontext.h
@@ -7,10 +7,14 @@
 #define _ASM_S390_SIGCONTEXT_H
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 
-#define __NUM_GPRS 16
-#define __NUM_FPRS 16
-#define __NUM_ACRS 16
+#define __NUM_GPRS		16
+#define __NUM_FPRS		16
+#define __NUM_ACRS		16
+#define __NUM_VXRS		32
+#define __NUM_VXRS_LOW		16
+#define __NUM_VXRS_HIGH		16
 
 #ifndef __s390x__
 
@@ -59,6 +63,16 @@ typedef struct
 	_s390_fp_regs     fpregs;
 } _sigregs;
 
+typedef struct
+{
+#ifndef __s390x__
+	unsigned long gprs_high[__NUM_GPRS];
+#endif
+	unsigned long long vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	unsigned char __reserved[128];
+} _sigregs_ext;
+
 struct sigcontext
 {
 	unsigned long	oldmask[_SIGCONTEXT_NSIG_WORDS];
diff --git a/arch/s390/include/uapi/asm/types.h b/arch/s390/include/uapi/asm/types.h
index 038f2b9178a4..3c3951e3415b 100644
--- a/arch/s390/include/uapi/asm/types.h
+++ b/arch/s390/include/uapi/asm/types.h
@@ -17,6 +17,10 @@
 typedef unsigned long addr_t; 
 typedef __signed__ long saddr_t;
 
+typedef struct {
+	__u32 u[4];
+} __vector128;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI_S390_TYPES_H */
diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h
index 3e077b2a4705..64a69aa5dde0 100644
--- a/arch/s390/include/uapi/asm/ucontext.h
+++ b/arch/s390/include/uapi/asm/ucontext.h
@@ -7,10 +7,15 @@
 #ifndef _ASM_S390_UCONTEXT_H
 #define _ASM_S390_UCONTEXT_H
 
-#define UC_EXTENDED	0x00000001
-
-#ifndef __s390x__
+#define UC_GPRS_HIGH	1	/* uc_mcontext_ext has valid high gprs */
+#define UC_VXRS		2	/* uc_mcontext_ext has valid vector regs */
 
+/*
+ * The struct ucontext_extended describes how the registers are stored
+ * on a rt signal frame. Please note that the structure is not fixed,
+ * if new CPU registers are added to the user state the size of the
+ * struct ucontext_extended will increase.
+ */
 struct ucontext_extended {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
@@ -19,11 +24,9 @@ struct ucontext_extended {
 	sigset_t	  uc_sigmask;
 	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
 	unsigned char	  __unused[128 - sizeof(sigset_t)];
-	unsigned long	  uc_gprs_high[16];
+	_sigregs_ext	  uc_mcontext_ext;
 };
 
-#endif
-
 struct ucontext {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index a95c4ca99617..204c43a4c245 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 
-obj-y	:= traps.o time.o process.o base.o early.o setup.o vtime.o
+obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
@@ -52,11 +52,9 @@ obj-$(CONFIG_COMPAT)		+= compat_wrapper.o $(compat-obj-y)
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_FUNCTION_TRACER)	+= $(if $(CONFIG_64BIT),mcount64.o,mcount.o)
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
-obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o
 
 ifdef CONFIG_64BIT
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o \
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index afe1715a4eb7..ef279a136801 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -9,7 +9,7 @@
 #include <linux/kbuild.h>
 #include <linux/kvm_host.h>
 #include <linux/sched.h>
-#include <asm/cputime.h>
+#include <asm/idle.h>
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
 
@@ -62,8 +62,12 @@ int main(void)
 	DEFINE(__VDSO_XTIME_STAMP, offsetof(struct vdso_data, xtime_tod_stamp));
 	DEFINE(__VDSO_XTIME_SEC, offsetof(struct vdso_data, xtime_clock_sec));
 	DEFINE(__VDSO_XTIME_NSEC, offsetof(struct vdso_data, xtime_clock_nsec));
+	DEFINE(__VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec));
+	DEFINE(__VDSO_XTIME_CRS_NSEC, offsetof(struct vdso_data, xtime_coarse_nsec));
 	DEFINE(__VDSO_WTOM_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(__VDSO_WTOM_CRS_SEC, offsetof(struct vdso_data, wtom_coarse_sec));
+	DEFINE(__VDSO_WTOM_CRS_NSEC, offsetof(struct vdso_data, wtom_coarse_nsec));
 	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
 	DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available));
 	DEFINE(__VDSO_TK_MULT, offsetof(struct vdso_data, tk_mult));
@@ -73,8 +77,11 @@ int main(void)
 	/* constants used by the vdso */
 	DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
 	DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
+	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
 	DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
+	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
 	BLANK();
 	/* idle data offsets */
 	DEFINE(__CLOCK_IDLE_ENTER, offsetof(struct s390_idle_data, clock_idle_enter));
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 70d4b7c4beaa..a0a886c04977 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -50,6 +50,14 @@ typedef struct
 	_s390_fp_regs32     fpregs;
 } _sigregs32;
 
+typedef struct
+{
+	__u32 gprs_high[__NUM_GPRS];
+	__u64 vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	__u8 __reserved[128];
+} _sigregs_ext32;
+
 #define _SIGCONTEXT_NSIG32	64
 #define _SIGCONTEXT_NSIG_BPW32	32
 #define __SIGNAL_FRAMESIZE32	96
@@ -72,6 +80,7 @@ struct ucontext32 {
 	compat_sigset_t		uc_sigmask;
 	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
 	unsigned char		__unused[128 - sizeof(compat_sigset_t)];
+	_sigregs_ext32		uc_mcontext_ext;
 };
 
 struct stat64_emu31;
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 598b0b42668b..009f5eb11125 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -36,17 +36,16 @@ typedef struct
 	struct sigcontext32 sc;
 	_sigregs32 sregs;
 	int signo;
-	__u32 gprs_high[NUM_GPRS];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	_sigregs_ext32 sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
 } sigframe32;
 
 typedef struct 
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE32];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	__u16 svc_insn;
 	compat_siginfo_t info;
 	struct ucontext32 uc;
-	__u32 gprs_high[NUM_GPRS];
 } rt_sigframe32;
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
@@ -151,6 +150,38 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return err ? -EFAULT : 0;
 }
 
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	int i;
+
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+	if (current->thread.vxrs) {
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	int i;
+
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
+
 static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 {
 	_sigregs32 user_sregs;
@@ -163,11 +194,8 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 		(__u32)(regs->psw.mask & PSW_MASK_BA);
 	for (i = 0; i < NUM_GPRS; i++)
 		user_sregs.regs.gprs[i] = (__u32) regs->gprs[i];
-	save_access_regs(current->thread.acrs);
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	save_fp_regs(current->thread.fp_regs.fprs);
 	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(user_sregs.fpregs));
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32)))
@@ -207,37 +235,67 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 		regs->gprs[i] = (__u64) user_sregs.regs.gprs[i];
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	restore_access_regs(current->thread.acrs);
 
 	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(current->thread.fp_regs));
 
-	restore_fp_regs(current->thread.fp_regs.fprs);
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
-static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
+static int save_sigregs_ext32(struct pt_regs *regs,
+			      _sigregs_ext32 __user *sregs_ext)
 {
 	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
+	/* Save high gprs to signal stack */
 	for (i = 0; i < NUM_GPRS; i++)
 		gprs_high[i] = regs->gprs[i] >> 32;
-	if (__copy_to_user(uregs, &gprs_high, sizeof(gprs_high)))
+	if (__copy_to_user(&sregs_ext->gprs_high, &gprs_high,
+			   sizeof(sregs_ext->gprs_high)))
 		return -EFAULT;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
-static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
+static int restore_sigregs_ext32(struct pt_regs *regs,
+				 _sigregs_ext32 __user *sregs_ext)
 {
 	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
-	if (__copy_from_user(&gprs_high, uregs, sizeof(gprs_high)))
+	/* Restore high gprs from signal stack */
+	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
+			     sizeof(&sregs_ext->gprs_high)))
 		return -EFAULT;
 	for (i = 0; i < NUM_GPRS; i++)
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
 	return 0;
 }
 
@@ -252,8 +310,9 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 	set_current_blocked(&set);
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
-	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
+	if (restore_sigregs_ext32(regs, &frame->sregs_ext))
 		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -269,12 +328,13 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+	if (compat_restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
 	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
+	if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		goto badframe;
-	if (compat_restore_altstack(&frame->uc.uc_stack))
-		goto badframe; 
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -324,37 +384,64 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 			 struct pt_regs *regs)
 {
 	int sig = ksig->sig;
-	sigframe32 __user *frame = get_sigframe(&ksig->ka, regs, sizeof(sigframe32));
-
+	sigframe32 __user *frame;
+	struct sigcontext32 sc;
+	unsigned long restorer;
+	size_t frame_size;
+
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext.__reserved);
+	if (!MACHINE_HAS_VX)
+		frame_size -= sizeof(frame->sregs_ext.vxrs_low) +
+			      sizeof(frame->sregs_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32))
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
+		return -EFAULT;
+
+	/* Create struct sigcontext32 on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32);
+	sc.sregs = (__u32)(unsigned long __force) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
 		return -EFAULT;
 
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs32 on the signal stack */
 	if (save_sigregs32(regs, &frame->sregs))
 		return -EFAULT;
-	if (save_sigregs_gprs_high(regs, frame->gprs_high))
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
 		return -EFAULT;
-	if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs))
+
+	/* Create _sigregs_ext32 on the signal stack */
+	if (save_sigregs_ext32(regs, &frame->sregs_ext))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64 __force) ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
-			       (u16 __force __user *)(frame->retcode)))
+		/* Signal frames without vectors registers are short ! */
+		__u16 __user *svc = (void *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
         }
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
-		return -EFAULT;
-
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (__force __u64) frame;
 	/* Force 31 bit amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_BA |
@@ -375,50 +462,69 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 		regs->gprs[6] = task_thread_info(current)->last_break;
 	}
 
-	/* Place signal number on stack to allow backtrace from handler.  */
-	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
-		return -EFAULT;
 	return 0;
 }
 
 static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 			    struct pt_regs *regs)
 {
-	int err = 0;
-	rt_sigframe32 __user *frame = get_sigframe(&ksig->ka, regs, sizeof(rt_sigframe32));
-
+	rt_sigframe32 __user *frame;
+	unsigned long restorer;
+	size_t frame_size;
+	u32 uc_flags;
+
+	frame_size = sizeof(*frame) -
+		     sizeof(frame->uc.uc_mcontext_ext.__reserved);
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	uc_flags = UC_GPRS_HIGH;
+	if (MACHINE_HAS_VX) {
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	} else
+		frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) +
+			      sizeof(frame->uc.uc_mcontext_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
-		return -EFAULT;
-
-	/* Create the ucontext.  */
-	err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags);
-	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]);
-	err |= save_sigregs32(regs, &frame->uc.uc_mcontext);
-	err |= save_sigregs_gprs_high(regs, frame->gprs_high);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64 __force) ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-			       (u16 __force __user *)(frame->retcode)))
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(0, &frame->uc.uc_link) ||
+	    __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs32(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (__force __u64) frame;
 	/* Force 31 bit amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_BA |
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index a3b9150e6802..9f73c8059022 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -46,9 +46,9 @@ struct dump_save_areas dump_save_areas;
 /*
  * Allocate and add a save area for a CPU
  */
-struct save_area *dump_save_area_create(int cpu)
+struct save_area_ext *dump_save_area_create(int cpu)
 {
-	struct save_area **save_areas, *save_area;
+	struct save_area_ext **save_areas, *save_area;
 
 	save_area = kmalloc(sizeof(*save_area), GFP_KERNEL);
 	if (!save_area)
@@ -386,9 +386,45 @@ static void *nt_s390_prefix(void *ptr, struct save_area *sa)
 }
 
 /*
+ * Initialize vxrs high note (full 128 bit VX registers 16-31)
+ */
+static void *nt_s390_vx_high(void *ptr, __vector128 *vx_regs)
+{
+	return nt_init(ptr, NT_S390_VXRS_HIGH, &vx_regs[16],
+		       16 * sizeof(__vector128), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize vxrs low note (lower halves of VX registers 0-15)
+ */
+static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
+{
+	Elf64_Nhdr *note;
+	u64 len;
+	int i;
+
+	note = (Elf64_Nhdr *)ptr;
+	note->n_namesz = strlen(KEXEC_CORE_NOTE_NAME) + 1;
+	note->n_descsz = 16 * 8;
+	note->n_type = NT_S390_VXRS_LOW;
+	len = sizeof(Elf64_Nhdr);
+
+	memcpy(ptr + len, KEXEC_CORE_NOTE_NAME, note->n_namesz);
+	len = roundup(len + note->n_namesz, 4);
+
+	ptr += len;
+	/* Copy lower halves of SIMD registers 0-15 */
+	for (i = 0; i < 16; i++) {
+		memcpy(ptr, &vx_regs[i], 8);
+		ptr += 8;
+	}
+	return ptr;
+}
+
+/*
  * Fill ELF notes for one CPU with save area registers
  */
-void *fill_cpu_elf_notes(void *ptr, struct save_area *sa)
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vx_regs)
 {
 	ptr = nt_prstatus(ptr, sa);
 	ptr = nt_fpregset(ptr, sa);
@@ -397,6 +433,10 @@ void *fill_cpu_elf_notes(void *ptr, struct save_area *sa)
 	ptr = nt_s390_tod_preg(ptr, sa);
 	ptr = nt_s390_ctrs(ptr, sa);
 	ptr = nt_s390_prefix(ptr, sa);
+	if (MACHINE_HAS_VX && vx_regs) {
+		ptr = nt_s390_vx_low(ptr, vx_regs);
+		ptr = nt_s390_vx_high(ptr, vx_regs);
+	}
 	return ptr;
 }
 
@@ -484,7 +524,7 @@ static int get_cpu_cnt(void)
 	int i, cpus = 0;
 
 	for (i = 0; i < dump_save_areas.count; i++) {
-		if (dump_save_areas.areas[i]->pref_reg == 0)
+		if (dump_save_areas.areas[i]->sa.pref_reg == 0)
 			continue;
 		cpus++;
 	}
@@ -530,17 +570,17 @@ static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
  */
 static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 {
-	struct save_area *sa;
+	struct save_area_ext *sa_ext;
 	void *ptr_start = ptr;
 	int i;
 
 	ptr = nt_prpsinfo(ptr);
 
 	for (i = 0; i < dump_save_areas.count; i++) {
-		sa = dump_save_areas.areas[i];
-		if (sa->pref_reg == 0)
+		sa_ext = dump_save_areas.areas[i];
+		if (sa_ext->sa.pref_reg == 0)
 			continue;
-		ptr = fill_cpu_elf_notes(ptr, sa);
+		ptr = fill_cpu_elf_notes(ptr, &sa_ext->sa, sa_ext->vx_regs);
 	}
 	ptr = nt_vmcoreinfo(ptr);
 	memset(phdr, 0, sizeof(*phdr));
@@ -581,7 +621,7 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
-	alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
+	alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
 		mem_chunk_cnt * sizeof(Elf64_Phdr);
 	hdr = kzalloc_panic(alloc_size);
 	/* Init elf header */
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 993efe6a887c..f3762937dd82 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -60,6 +60,11 @@ enum {
 	A_28,	/* Access reg. starting at position 28 */
 	C_8,	/* Control reg. starting at position 8 */
 	C_12,	/* Control reg. starting at position 12 */
+	V_8,	/* Vector reg. starting at position 8, extension bit at 36 */
+	V_12,	/* Vector reg. starting at position 12, extension bit at 37 */
+	V_16,	/* Vector reg. starting at position 16, extension bit at 38 */
+	V_32,	/* Vector reg. starting at position 32, extension bit at 39 */
+	W_12,	/* Vector reg. at bit 12, extension at bit 37, used as index */
 	B_16,	/* Base register starting at position 16 */
 	B_32,	/* Base register starting at position 32 */
 	X_12,	/* Index register starting at position 12 */
@@ -82,6 +87,8 @@ enum {
 	U8_24,	/* 8 bit unsigned value starting at 24 */
 	U8_32,	/* 8 bit unsigned value starting at 32 */
 	I8_8,	/* 8 bit signed value starting at 8 */
+	I8_16,	/* 8 bit signed value starting at 16 */
+	I8_24,	/* 8 bit signed value starting at 24 */
 	I8_32,	/* 8 bit signed value starting at 32 */
 	J12_12, /* PC relative offset at 12 */
 	I16_16,	/* 16 bit signed value starting at 16 */
@@ -96,6 +103,9 @@ enum {
 	U32_16,	/* 32 bit unsigned value starting at 16 */
 	M_16,	/* 4 bit optional mask starting at 16 */
 	M_20,	/* 4 bit optional mask starting at 20 */
+	M_24,	/* 4 bit optional mask starting at 24 */
+	M_28,	/* 4 bit optional mask starting at 28 */
+	M_32,	/* 4 bit optional mask starting at 32 */
 	RO_28,	/* optional GPR starting at position 28 */
 };
 
@@ -130,7 +140,7 @@ enum {
 	INSTR_RSY_RDRM,
 	INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD, INSTR_RS_RRRD,
 	INSTR_RS_RURD,
-	INSTR_RXE_FRRD, INSTR_RXE_RRRD,
+	INSTR_RXE_FRRD, INSTR_RXE_RRRD, INSTR_RXE_RRRDM,
 	INSTR_RXF_FRRDF,
 	INSTR_RXY_FRRD, INSTR_RXY_RRRD, INSTR_RXY_URRD,
 	INSTR_RX_FRRD, INSTR_RX_RRRD, INSTR_RX_URRD,
@@ -143,6 +153,17 @@ enum {
 	INSTR_SS_L0RDRD, INSTR_SS_LIRDRD, INSTR_SS_LLRDRD, INSTR_SS_RRRDRD,
 	INSTR_SS_RRRDRD2, INSTR_SS_RRRDRD3,
 	INSTR_S_00, INSTR_S_RD,
+	INSTR_VRI_V0IM, INSTR_VRI_V0I0, INSTR_VRI_V0IIM, INSTR_VRI_VVIM,
+	INSTR_VRI_VVV0IM, INSTR_VRI_VVV0I0, INSTR_VRI_VVIMM,
+	INSTR_VRR_VV00MMM, INSTR_VRR_VV000MM, INSTR_VRR_VV0000M,
+	INSTR_VRR_VV00000, INSTR_VRR_VVV0M0M, INSTR_VRR_VV00M0M,
+	INSTR_VRR_VVV000M, INSTR_VRR_VVV000V, INSTR_VRR_VVV0000,
+	INSTR_VRR_VVV0MMM, INSTR_VRR_VVV00MM, INSTR_VRR_VVVMM0V,
+	INSTR_VRR_VVVM0MV, INSTR_VRR_VVVM00V, INSTR_VRR_VRR0000,
+	INSTR_VRS_VVRDM, INSTR_VRS_VVRD0, INSTR_VRS_VRRDM, INSTR_VRS_VRRD0,
+	INSTR_VRS_RVRDM,
+	INSTR_VRV_VVRDM, INSTR_VRV_VWRDM,
+	INSTR_VRX_VRRDM, INSTR_VRX_VRRD0,
 };
 
 static const struct s390_operand operands[] =
@@ -168,6 +189,11 @@ static const struct s390_operand operands[] =
 	[A_28]	 = {  4, 28, OPERAND_AR },
 	[C_8]	 = {  4,  8, OPERAND_CR },
 	[C_12]	 = {  4, 12, OPERAND_CR },
+	[V_8]	 = {  4,  8, OPERAND_VR },
+	[V_12]	 = {  4, 12, OPERAND_VR },
+	[V_16]	 = {  4, 16, OPERAND_VR },
+	[V_32]	 = {  4, 32, OPERAND_VR },
+	[W_12]	 = {  4, 12, OPERAND_INDEX | OPERAND_VR },
 	[B_16]	 = {  4, 16, OPERAND_BASE | OPERAND_GPR },
 	[B_32]	 = {  4, 32, OPERAND_BASE | OPERAND_GPR },
 	[X_12]	 = {  4, 12, OPERAND_INDEX | OPERAND_GPR },
@@ -190,6 +216,11 @@ static const struct s390_operand operands[] =
 	[U8_24]  = {  8, 24, 0 },
 	[U8_32]  = {  8, 32, 0 },
 	[J12_12] = { 12, 12, OPERAND_PCREL },
+	[I8_8]	 = {  8,  8, OPERAND_SIGNED },
+	[I8_16]  = {  8, 16, OPERAND_SIGNED },
+	[I8_24]  = {  8, 24, OPERAND_SIGNED },
+	[I8_32]  = {  8, 32, OPERAND_SIGNED },
+	[I16_32] = { 16, 32, OPERAND_SIGNED },
 	[I16_16] = { 16, 16, OPERAND_SIGNED },
 	[U16_16] = { 16, 16, 0 },
 	[U16_32] = { 16, 32, 0 },
@@ -202,6 +233,9 @@ static const struct s390_operand operands[] =
 	[U32_16] = { 32, 16, 0 },
 	[M_16]	 = {  4, 16, 0 },
 	[M_20]	 = {  4, 20, 0 },
+	[M_24]	 = {  4, 24, 0 },
+	[M_28]	 = {  4, 28, 0 },
+	[M_32]	 = {  4, 32, 0 },
 	[RO_28]  = {  4, 28, OPERAND_GPR }
 };
 
@@ -283,6 +317,7 @@ static const unsigned char formats[][7] = {
 	[INSTR_RS_RURD]	  = { 0xff, R_8,U4_12,D_20,B_16,0,0 },
 	[INSTR_RXE_FRRD]  = { 0xff, F_8,D_20,X_12,B_16,0,0 },
 	[INSTR_RXE_RRRD]  = { 0xff, R_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RXE_RRRDM] = { 0xff, R_8,D_20,X_12,B_16,M_32,0 },
 	[INSTR_RXF_FRRDF] = { 0xff, F_32,F_8,D_20,X_12,B_16,0 },
 	[INSTR_RXY_FRRD]  = { 0xff, F_8,D20_20,X_12,B_16,0,0 },
 	[INSTR_RXY_RRRD]  = { 0xff, R_8,D20_20,X_12,B_16,0,0 },
@@ -307,6 +342,37 @@ static const unsigned char formats[][7] = {
 	[INSTR_SS_RRRDRD] = { 0xff, D_20,R_8,B_16,D_36,B_32,R_12 },
 	[INSTR_S_00]	  = { 0xff, 0,0,0,0,0,0 },
 	[INSTR_S_RD]	  = { 0xff, D_20,B_16,0,0,0,0 },
+	[INSTR_VRI_V0IM]  = { 0xff, V_8,I16_16,M_32,0,0,0 },
+	[INSTR_VRI_V0I0]  = { 0xff, V_8,I16_16,0,0,0,0 },
+	[INSTR_VRI_V0IIM] = { 0xff, V_8,I8_16,I8_24,M_32,0,0 },
+	[INSTR_VRI_VVIM]  = { 0xff, V_8,I16_16,V_12,M_32,0,0 },
+	[INSTR_VRI_VVV0IM]= { 0xff, V_8,V_12,V_16,I8_24,M_32,0 },
+	[INSTR_VRI_VVV0I0]= { 0xff, V_8,V_12,V_16,I8_24,0,0 },
+	[INSTR_VRI_VVIMM] = { 0xff, V_8,V_12,I16_16,M_32,M_28,0 },
+	[INSTR_VRR_VV00MMM]={ 0xff, V_8,V_12,M_32,M_28,M_24,0 },
+	[INSTR_VRR_VV000MM]={ 0xff, V_8,V_12,M_32,M_28,0,0 },
+	[INSTR_VRR_VV0000M]={ 0xff, V_8,V_12,M_32,0,0,0 },
+	[INSTR_VRR_VV00000]={ 0xff, V_8,V_12,0,0,0,0 },
+	[INSTR_VRR_VVV0M0M]={ 0xff, V_8,V_12,V_16,M_32,M_24,0 },
+	[INSTR_VRR_VV00M0M]={ 0xff, V_8,V_12,M_32,M_24,0,0 },
+	[INSTR_VRR_VVV000M]={ 0xff, V_8,V_12,V_16,M_32,0,0 },
+	[INSTR_VRR_VVV000V]={ 0xff, V_8,V_12,V_16,V_32,0,0 },
+	[INSTR_VRR_VVV0000]={ 0xff, V_8,V_12,V_16,0,0,0 },
+	[INSTR_VRR_VVV0MMM]={ 0xff, V_8,V_12,V_16,M_32,M_28,M_24 },
+	[INSTR_VRR_VVV00MM]={ 0xff, V_8,V_12,V_16,M_32,M_28,0 },
+	[INSTR_VRR_VVVMM0V]={ 0xff, V_8,V_12,V_16,V_32,M_20,M_24 },
+	[INSTR_VRR_VVVM0MV]={ 0xff, V_8,V_12,V_16,V_32,M_28,M_20 },
+	[INSTR_VRR_VVVM00V]={ 0xff, V_8,V_12,V_16,V_32,M_20,0 },
+	[INSTR_VRR_VRR0000]={ 0xff, V_8,R_12,R_16,0,0,0 },
+	[INSTR_VRS_VVRDM] = { 0xff, V_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRS_VVRD0] = { 0xff, V_8,V_12,D_20,B_16,0,0 },
+	[INSTR_VRS_VRRDM] = { 0xff, V_8,R_12,D_20,B_16,M_32,0 },
+	[INSTR_VRS_VRRD0] = { 0xff, V_8,R_12,D_20,B_16,0,0 },
+	[INSTR_VRS_RVRDM] = { 0xff, R_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRV_VVRDM] = { 0xff, V_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRV_VWRDM] = { 0xff, V_8,D_20,W_12,B_16,M_32,0 },
+	[INSTR_VRX_VRRDM] = { 0xff, V_8,D_20,X_12,B_16,M_32,0 },
+	[INSTR_VRX_VRRD0] = { 0xff, V_8,D_20,X_12,B_16,0,0 },
 };
 
 enum {
@@ -381,6 +447,11 @@ enum {
 	LONG_INSN_MPCIFC,
 	LONG_INSN_STPCIFC,
 	LONG_INSN_PCISTB,
+	LONG_INSN_VPOPCT,
+	LONG_INSN_VERLLV,
+	LONG_INSN_VESRAV,
+	LONG_INSN_VESRLV,
+	LONG_INSN_VSBCBI
 };
 
 static char *long_insn_name[] = {
@@ -455,6 +526,11 @@ static char *long_insn_name[] = {
 	[LONG_INSN_MPCIFC] = "mpcifc",
 	[LONG_INSN_STPCIFC] = "stpcifc",
 	[LONG_INSN_PCISTB] = "pcistb",
+	[LONG_INSN_VPOPCT] = "vpopct",
+	[LONG_INSN_VERLLV] = "verllv",
+	[LONG_INSN_VESRAV] = "vesrav",
+	[LONG_INSN_VESRLV] = "vesrlv",
+	[LONG_INSN_VSBCBI] = "vsbcbi",
 };
 
 static struct s390_insn opcode[] = {
@@ -1369,6 +1445,150 @@ static struct s390_insn opcode_e5[] = {
 	{ "", 0, INSTR_INVALID }
 };
 
+static struct s390_insn opcode_e7[] = {
+#ifdef CONFIG_64BIT
+	{ "lcbb", 0x27, INSTR_RXE_RRRDM },
+	{ "vgef", 0x13, INSTR_VRV_VVRDM },
+	{ "vgeg", 0x12, INSTR_VRV_VVRDM },
+	{ "vgbm", 0x44, INSTR_VRI_V0I0 },
+	{ "vgm", 0x46, INSTR_VRI_V0IIM },
+	{ "vl", 0x06, INSTR_VRX_VRRD0 },
+	{ "vlr", 0x56, INSTR_VRR_VV00000 },
+	{ "vlrp", 0x05, INSTR_VRX_VRRDM },
+	{ "vleb", 0x00, INSTR_VRX_VRRDM },
+	{ "vleh", 0x01, INSTR_VRX_VRRDM },
+	{ "vlef", 0x03, INSTR_VRX_VRRDM },
+	{ "vleg", 0x02, INSTR_VRX_VRRDM },
+	{ "vleib", 0x40, INSTR_VRI_V0IM },
+	{ "vleih", 0x41, INSTR_VRI_V0IM },
+	{ "vleif", 0x43, INSTR_VRI_V0IM },
+	{ "vleig", 0x42, INSTR_VRI_V0IM },
+	{ "vlgv", 0x21, INSTR_VRS_RVRDM },
+	{ "vllez", 0x04, INSTR_VRX_VRRDM },
+	{ "vlm", 0x36, INSTR_VRS_VVRD0 },
+	{ "vlbb", 0x07, INSTR_VRX_VRRDM },
+	{ "vlvg", 0x22, INSTR_VRS_VRRDM },
+	{ "vlvgp", 0x62, INSTR_VRR_VRR0000 },
+	{ "vll", 0x37, INSTR_VRS_VRRD0 },
+	{ "vmrh", 0x61, INSTR_VRR_VVV000M },
+	{ "vmrl", 0x60, INSTR_VRR_VVV000M },
+	{ "vpk", 0x94, INSTR_VRR_VVV000M },
+	{ "vpks", 0x97, INSTR_VRR_VVV0M0M },
+	{ "vpkls", 0x95, INSTR_VRR_VVV0M0M },
+	{ "vperm", 0x8c, INSTR_VRR_VVV000V },
+	{ "vpdi", 0x84, INSTR_VRR_VVV000M },
+	{ "vrep", 0x4d, INSTR_VRI_VVIM },
+	{ "vrepi", 0x45, INSTR_VRI_V0IM },
+	{ "vscef", 0x1b, INSTR_VRV_VWRDM },
+	{ "vsceg", 0x1a, INSTR_VRV_VWRDM },
+	{ "vsel", 0x8d, INSTR_VRR_VVV000V },
+	{ "vseg", 0x5f, INSTR_VRR_VV0000M },
+	{ "vst", 0x0e, INSTR_VRX_VRRD0 },
+	{ "vsteb", 0x08, INSTR_VRX_VRRDM },
+	{ "vsteh", 0x09, INSTR_VRX_VRRDM },
+	{ "vstef", 0x0b, INSTR_VRX_VRRDM },
+	{ "vsteg", 0x0a, INSTR_VRX_VRRDM },
+	{ "vstm", 0x3e, INSTR_VRS_VVRD0 },
+	{ "vstl", 0x3f, INSTR_VRS_VRRD0 },
+	{ "vuph", 0xd7, INSTR_VRR_VV0000M },
+	{ "vuplh", 0xd5, INSTR_VRR_VV0000M },
+	{ "vupl", 0xd6, INSTR_VRR_VV0000M },
+	{ "vupll", 0xd4, INSTR_VRR_VV0000M },
+	{ "va", 0xf3, INSTR_VRR_VVV000M },
+	{ "vacc", 0xf1, INSTR_VRR_VVV000M },
+	{ "vac", 0xbb, INSTR_VRR_VVVM00V },
+	{ "vaccc", 0xb9, INSTR_VRR_VVVM00V },
+	{ "vn", 0x68, INSTR_VRR_VVV0000 },
+	{ "vnc", 0x69, INSTR_VRR_VVV0000 },
+	{ "vavg", 0xf2, INSTR_VRR_VVV000M },
+	{ "vavgl", 0xf0, INSTR_VRR_VVV000M },
+	{ "vcksm", 0x66, INSTR_VRR_VVV0000 },
+	{ "vec", 0xdb, INSTR_VRR_VV0000M },
+	{ "vecl", 0xd9, INSTR_VRR_VV0000M },
+	{ "vceq", 0xf8, INSTR_VRR_VVV0M0M },
+	{ "vch", 0xfb, INSTR_VRR_VVV0M0M },
+	{ "vchl", 0xf9, INSTR_VRR_VVV0M0M },
+	{ "vclz", 0x53, INSTR_VRR_VV0000M },
+	{ "vctz", 0x52, INSTR_VRR_VV0000M },
+	{ "vx", 0x6d, INSTR_VRR_VVV0000 },
+	{ "vgfm", 0xb4, INSTR_VRR_VVV000M },
+	{ "vgfma", 0xbc, INSTR_VRR_VVVM00V },
+	{ "vlc", 0xde, INSTR_VRR_VV0000M },
+	{ "vlp", 0xdf, INSTR_VRR_VV0000M },
+	{ "vmx", 0xff, INSTR_VRR_VVV000M },
+	{ "vmxl", 0xfd, INSTR_VRR_VVV000M },
+	{ "vmn", 0xfe, INSTR_VRR_VVV000M },
+	{ "vmnl", 0xfc, INSTR_VRR_VVV000M },
+	{ "vmal", 0xaa, INSTR_VRR_VVVM00V },
+	{ "vmae", 0xae, INSTR_VRR_VVVM00V },
+	{ "vmale", 0xac, INSTR_VRR_VVVM00V },
+	{ "vmah", 0xab, INSTR_VRR_VVVM00V },
+	{ "vmalh", 0xa9, INSTR_VRR_VVVM00V },
+	{ "vmao", 0xaf, INSTR_VRR_VVVM00V },
+	{ "vmalo", 0xad, INSTR_VRR_VVVM00V },
+	{ "vmh", 0xa3, INSTR_VRR_VVV000M },
+	{ "vmlh", 0xa1, INSTR_VRR_VVV000M },
+	{ "vml", 0xa2, INSTR_VRR_VVV000M },
+	{ "vme", 0xa6, INSTR_VRR_VVV000M },
+	{ "vmle", 0xa4, INSTR_VRR_VVV000M },
+	{ "vmo", 0xa7, INSTR_VRR_VVV000M },
+	{ "vmlo", 0xa5, INSTR_VRR_VVV000M },
+	{ "vno", 0x6b, INSTR_VRR_VVV0000 },
+	{ "vo", 0x6a, INSTR_VRR_VVV0000 },
+	{ { 0, LONG_INSN_VPOPCT }, 0x50, INSTR_VRR_VV0000M },
+	{ { 0, LONG_INSN_VERLLV }, 0x73, INSTR_VRR_VVV000M },
+	{ "verll", 0x33, INSTR_VRS_VVRDM },
+	{ "verim", 0x72, INSTR_VRI_VVV0IM },
+	{ "veslv", 0x70, INSTR_VRR_VVV000M },
+	{ "vesl", 0x30, INSTR_VRS_VVRDM },
+	{ { 0, LONG_INSN_VESRAV }, 0x7a, INSTR_VRR_VVV000M },
+	{ "vesra", 0x3a, INSTR_VRS_VVRDM },
+	{ { 0, LONG_INSN_VESRLV }, 0x78, INSTR_VRR_VVV000M },
+	{ "vesrl", 0x38, INSTR_VRS_VVRDM },
+	{ "vsl", 0x74, INSTR_VRR_VVV0000 },
+	{ "vslb", 0x75, INSTR_VRR_VVV0000 },
+	{ "vsldb", 0x77, INSTR_VRI_VVV0I0 },
+	{ "vsra", 0x7e, INSTR_VRR_VVV0000 },
+	{ "vsrab", 0x7f, INSTR_VRR_VVV0000 },
+	{ "vsrl", 0x7c, INSTR_VRR_VVV0000 },
+	{ "vsrlb", 0x7d, INSTR_VRR_VVV0000 },
+	{ "vs", 0xf7, INSTR_VRR_VVV000M },
+	{ "vscb", 0xf5, INSTR_VRR_VVV000M },
+	{ "vsb", 0xbf, INSTR_VRR_VVVM00V },
+	{ { 0, LONG_INSN_VSBCBI }, 0xbd, INSTR_VRR_VVVM00V },
+	{ "vsumg", 0x65, INSTR_VRR_VVV000M },
+	{ "vsumq", 0x67, INSTR_VRR_VVV000M },
+	{ "vsum", 0x64, INSTR_VRR_VVV000M },
+	{ "vtm", 0xd8, INSTR_VRR_VV00000 },
+	{ "vfae", 0x82, INSTR_VRR_VVV0M0M },
+	{ "vfee", 0x80, INSTR_VRR_VVV0M0M },
+	{ "vfene", 0x81, INSTR_VRR_VVV0M0M },
+	{ "vistr", 0x5c, INSTR_VRR_VV00M0M },
+	{ "vstrc", 0x8a, INSTR_VRR_VVVMM0V },
+	{ "vfa", 0xe3, INSTR_VRR_VVV00MM },
+	{ "wfc", 0xcb, INSTR_VRR_VV000MM },
+	{ "wfk", 0xca, INSTR_VRR_VV000MM },
+	{ "vfce", 0xe8, INSTR_VRR_VVV0MMM },
+	{ "vfch", 0xeb, INSTR_VRR_VVV0MMM },
+	{ "vfche", 0xea, INSTR_VRR_VVV0MMM },
+	{ "vcdg", 0xc3, INSTR_VRR_VV00MMM },
+	{ "vcdlg", 0xc1, INSTR_VRR_VV00MMM },
+	{ "vcgd", 0xc2, INSTR_VRR_VV00MMM },
+	{ "vclgd", 0xc0, INSTR_VRR_VV00MMM },
+	{ "vfd", 0xe5, INSTR_VRR_VVV00MM },
+	{ "vfi", 0xc7, INSTR_VRR_VV00MMM },
+	{ "vlde", 0xc4, INSTR_VRR_VV000MM },
+	{ "vled", 0xc5, INSTR_VRR_VV00MMM },
+	{ "vfm", 0xe7, INSTR_VRR_VVV00MM },
+	{ "vfma", 0x8f, INSTR_VRR_VVVM0MV },
+	{ "vfms", 0x8e, INSTR_VRR_VVVM0MV },
+	{ "vfpso", 0xcc, INSTR_VRR_VV00MMM },
+	{ "vfsq", 0xce, INSTR_VRR_VV000MM },
+	{ "vfs", 0xe2, INSTR_VRR_VVV00MM },
+	{ "vftci", 0x4a, INSTR_VRI_VVIMM },
+#endif
+};
+
 static struct s390_insn opcode_eb[] = {
 #ifdef CONFIG_64BIT
 	{ "lmg", 0x04, INSTR_RSY_RRRD },
@@ -1552,16 +1772,17 @@ static struct s390_insn opcode_ed[] = {
 static unsigned int extract_operand(unsigned char *code,
 				    const struct s390_operand *operand)
 {
+	unsigned char *cp;
 	unsigned int val;
 	int bits;
 
 	/* Extract fragments of the operand byte for byte.  */
-	code += operand->shift / 8;
+	cp = code + operand->shift / 8;
 	bits = (operand->shift & 7) + operand->bits;
 	val = 0;
 	do {
 		val <<= 8;
-		val |= (unsigned int) *code++;
+		val |= (unsigned int) *cp++;
 		bits -= 8;
 	} while (bits > 0);
 	val >>= -bits;
@@ -1571,6 +1792,18 @@ static unsigned int extract_operand(unsigned char *code,
 	if (operand->bits == 20 && operand->shift == 20)
 		val = (val & 0xff) << 12 | (val & 0xfff00) >> 8;
 
+	/* Check for register extensions bits for vector registers. */
+	if (operand->flags & OPERAND_VR) {
+		if (operand->shift == 8)
+			val |= (code[4] & 8) << 1;
+		else if (operand->shift == 12)
+			val |= (code[4] & 4) << 2;
+		else if (operand->shift == 16)
+			val |= (code[4] & 2) << 3;
+		else if (operand->shift == 32)
+			val |= (code[4] & 1) << 4;
+	}
+
 	/* Sign extend value if the operand is signed or pc relative.  */
 	if ((operand->flags & (OPERAND_SIGNED | OPERAND_PCREL)) &&
 	    (val & (1U << (operand->bits - 1))))
@@ -1639,6 +1872,10 @@ struct s390_insn *find_insn(unsigned char *code)
 	case 0xe5:
 		table = opcode_e5;
 		break;
+	case 0xe7:
+		table = opcode_e7;
+		opfrag = code[5];
+		break;
 	case 0xeb:
 		table = opcode_eb;
 		opfrag = code[5];
@@ -1734,6 +1971,8 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
 				ptr += sprintf(ptr, "%%c%i", value);
+			else if (operand->flags & OPERAND_VR)
+				ptr += sprintf(ptr, "%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 0dff972a169c..cef2879edff3 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -390,10 +390,10 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
 	if (test_facility(50) && test_facility(73))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
-	if (test_facility(66))
-		S390_lowcore.machine_flags |= MACHINE_FLAG_RRBM;
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
+	if (test_facility(129))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 #endif
 }
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 1aad48398d06..0554b9771c9f 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <linux/signal.h>
 #include <asm/ptrace.h>
-#include <asm/cputime.h>
+#include <asm/idle.h>
 
 extern void *restart_stack;
 extern unsigned long suspend_zero_pages;
@@ -21,6 +21,8 @@ void psw_idle(struct s390_idle_data *, unsigned long);
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
 
+int alloc_vector_registers(struct task_struct *tsk);
+
 void do_protection_exception(struct pt_regs *regs);
 void do_dat_exception(struct pt_regs *regs);
 
@@ -43,8 +45,10 @@ void special_op_exception(struct pt_regs *regs);
 void specification_exception(struct pt_regs *regs);
 void transaction_exception(struct pt_regs *regs);
 void translation_exception(struct pt_regs *regs);
+void vector_exception(struct pt_regs *regs);
 
 void do_per_trap(struct pt_regs *regs);
+void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
 void syscall_trace(struct pt_regs *regs, int entryexit);
 void kernel_stack_overflow(struct pt_regs * regs);
 void do_signal(struct pt_regs *regs);
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index f2e674c702e1..7b2e03afd017 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -42,7 +42,8 @@ STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
-_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
+		   _TIF_UPROBE)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
 _CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE)
@@ -265,6 +266,10 @@ sysc_work:
 	jo	sysc_mcck_pending
 	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
+#ifdef CONFIG_UPROBES
+	tm	__TI_flags+7(%r12),_TIF_UPROBE
+	jo	sysc_uprobe_notify
+#endif
 	tm	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	jo	sysc_singlestep
 	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
@@ -323,6 +328,16 @@ sysc_notify_resume:
 	jg	do_notify_resume
 
 #
+# _TIF_UPROBE is set, call uprobe_notify_resume
+#
+#ifdef CONFIG_UPROBES
+sysc_uprobe_notify:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,sysc_return
+	jg	uprobe_notify_resume
+#endif
+
+#
 # _PIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 54d6493c4a56..51d14fe5eb9a 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -1,7 +1,7 @@
 /*
  * Dynamic function tracer architecture backend.
  *
- * Copyright IBM Corp. 2009
+ * Copyright IBM Corp. 2009,2014
  *
  *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
  *		Martin Schwidefsky <schwidefsky@de.ibm.com>
@@ -17,100 +17,76 @@
 #include <asm/asm-offsets.h>
 #include "entry.h"
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-
+void mcount_replace_code(void);
 void ftrace_disable_code(void);
 void ftrace_enable_insn(void);
 
-#ifdef CONFIG_64BIT
 /*
- * The 64-bit mcount code looks like this:
+ * The mcount code looks like this:
  *	stg	%r14,8(%r15)		# offset 0
- * >	larl	%r1,<&counter>		# offset 6
- * >	brasl	%r14,_mcount		# offset 12
+ *	larl	%r1,<&counter>		# offset 6
+ *	brasl	%r14,_mcount		# offset 12
  *	lg	%r14,8(%r15)		# offset 18
- * Total length is 24 bytes. The middle two instructions of the mcount
- * block get overwritten by ftrace_make_nop / ftrace_make_call.
- * The 64-bit enabled ftrace code block looks like this:
- *	stg	%r14,8(%r15)		# offset 0
+ * Total length is 24 bytes. The complete mcount block initially gets replaced
+ * by ftrace_make_nop. Subsequent calls to ftrace_make_call / ftrace_make_nop
+ * only patch the jg/lg instruction within the block.
+ * Note: we do not patch the first instruction to an unconditional branch,
+ * since that would break kprobes/jprobes. It is easier to leave the larl
+ * instruction in and only modify the second instruction.
+ * The enabled ftrace code block looks like this:
+ *	larl	%r0,.+24		# offset 0
  * >	lg	%r1,__LC_FTRACE_FUNC	# offset 6
- * >	lgr	%r0,%r0			# offset 12
- * >	basr	%r14,%r1		# offset 16
- *	lg	%r14,8(%15)		# offset 18
- * The return points of the mcount/ftrace function have the same offset 18.
- * The 64-bit disable ftrace code block looks like this:
- *	stg	%r14,8(%r15)		# offset 0
+ *	br	%r1			# offset 12
+ *	brcl	0,0			# offset 14
+ *	brc	0,0			# offset 20
+ * The ftrace function gets called with a non-standard C function call ABI
+ * where r0 contains the return address. It is also expected that the called
+ * function only clobbers r0 and r1, but restores r2-r15.
+ * The return point of the ftrace function has offset 24, so execution
+ * continues behind the mcount block.
+ *	larl	%r0,.+24		# offset 0
  * >	jg	.+18			# offset 6
- * >	lgr	%r0,%r0			# offset 12
- * >	basr	%r14,%r1		# offset 16
- *	lg	%r14,8(%15)		# offset 18
+ *	br	%r1			# offset 12
+ *	brcl	0,0			# offset 14
+ *	brc	0,0			# offset 20
  * The jg instruction branches to offset 24 to skip as many instructions
  * as possible.
  */
 asm(
 	"	.align	4\n"
+	"mcount_replace_code:\n"
+	"	larl	%r0,0f\n"
 	"ftrace_disable_code:\n"
 	"	jg	0f\n"
-	"	lgr	%r0,%r0\n"
-	"	basr	%r14,%r1\n"
+	"	br	%r1\n"
+	"	brcl	0,0\n"
+	"	brc	0,0\n"
 	"0:\n"
 	"	.align	4\n"
 	"ftrace_enable_insn:\n"
 	"	lg	%r1,"__stringify(__LC_FTRACE_FUNC)"\n");
 
+#define MCOUNT_BLOCK_SIZE	24
+#define MCOUNT_INSN_OFFSET	6
 #define FTRACE_INSN_SIZE	6
 
-#else /* CONFIG_64BIT */
-/*
- * The 31-bit mcount code looks like this:
- *	st	%r14,4(%r15)		# offset 0
- * >	bras	%r1,0f			# offset 4
- * >	.long	_mcount			# offset 8
- * >	.long	<&counter>		# offset 12
- * > 0:	l	%r14,0(%r1)		# offset 16
- * >	l	%r1,4(%r1)		# offset 20
- *	basr	%r14,%r14		# offset 24
- *	l	%r14,4(%r15)		# offset 26
- * Total length is 30 bytes. The twenty bytes starting from offset 4
- * to offset 24 get overwritten by ftrace_make_nop / ftrace_make_call.
- * The 31-bit enabled ftrace code block looks like this:
- *	st	%r14,4(%r15)		# offset 0
- * >	l	%r14,__LC_FTRACE_FUNC	# offset 4
- * >	j	0f			# offset 8
- * >	.fill	12,1,0x07		# offset 12
- *   0:	basr	%r14,%r14		# offset 24
- *	l	%r14,4(%r14)		# offset 26
- * The return points of the mcount/ftrace function have the same offset 26.
- * The 31-bit disabled ftrace code block looks like this:
- *	st	%r14,4(%r15)		# offset 0
- * >	j	.+26			# offset 4
- * >	j	0f			# offset 8
- * >	.fill	12,1,0x07		# offset 12
- *   0:	basr	%r14,%r14		# offset 24
- *	l	%r14,4(%r14)		# offset 26
- * The j instruction branches to offset 30 to skip as many instructions
- * as possible.
- */
-asm(
-	"	.align	4\n"
-	"ftrace_disable_code:\n"
-	"	j	1f\n"
-	"	j	0f\n"
-	"	.fill	12,1,0x07\n"
-	"0:	basr	%r14,%r14\n"
-	"1:\n"
-	"	.align	4\n"
-	"ftrace_enable_insn:\n"
-	"	l	%r14,"__stringify(__LC_FTRACE_FUNC)"\n");
-
-#define FTRACE_INSN_SIZE	4
-
-#endif /* CONFIG_64BIT */
-
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	return 0;
+}
 
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
+	/* Initial replacement of the whole mcount block */
+	if (addr == MCOUNT_ADDR) {
+		if (probe_kernel_write((void *) rec->ip - MCOUNT_INSN_OFFSET,
+				       mcount_replace_code,
+				       MCOUNT_BLOCK_SIZE))
+			return -EPERM;
+		return 0;
+	}
 	if (probe_kernel_write((void *) rec->ip, ftrace_disable_code,
 			       MCOUNT_INSN_SIZE))
 		return -EPERM;
@@ -135,8 +111,6 @@ int __init ftrace_dyn_arch_init(void)
 	return 0;
 }
 
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * Hook the return address and push it in the stack of return addresses
@@ -162,31 +136,26 @@ out:
 	return parent;
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE
 /*
  * Patch the kernel code at ftrace_graph_caller location. The instruction
- * there is branch relative and save to prepare_ftrace_return. To disable
- * the call to prepare_ftrace_return we patch the bras offset to point
- * directly after the instructions. To enable the call we calculate
- * the original offset to prepare_ftrace_return and put it back.
+ * there is branch relative on condition. To enable the ftrace graph code
+ * block, we simply patch the mask field of the instruction to zero and
+ * turn the instruction into a nop.
+ * To disable the ftrace graph code the mask field will be patched to
+ * all ones, which turns the instruction into an unconditional branch.
  */
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	unsigned short offset;
+	u8 op = 0x04; /* set mask field to zero */
 
-	offset = ((void *) prepare_ftrace_return -
-		  (void *) ftrace_graph_caller) / 2;
-	return probe_kernel_write((void *) ftrace_graph_caller + 2,
-				  &offset, sizeof(offset));
+	return probe_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	static unsigned short offset = 0x0002;
+	u8 op = 0xf4; /* set mask field to all ones */
 
-	return probe_kernel_write((void *) ftrace_graph_caller + 2,
-				  &offset, sizeof(offset));
+	return probe_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
 }
 
-#endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index e88d35d74950..d62eee11f0b5 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -398,7 +398,7 @@ ENTRY(startup_kdump)
 	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 #ifndef CONFIG_MARCH_G5
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
-	.insn	s,0xb2b10000,__LC_STFL_FAC_LIST	# store facility list
+	.insn	s,0xb2b10000,0		# store facilities @ __LC_STFL_FAC_LIST
 	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
 	jz	0f
 	la	%r0,1
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
new file mode 100644
index 000000000000..7559f1beab29
--- /dev/null
+++ b/arch/s390/kernel/idle.c
@@ -0,0 +1,124 @@
+/*
+ * Idle functions for s390.
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/kprobes.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <asm/cputime.h>
+#include <asm/nmi.h>
+#include <asm/smp.h>
+#include "entry.h"
+
+static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
+
+void __kprobes enabled_wait(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	unsigned long long idle_time;
+	unsigned long psw_mask;
+
+	trace_hardirqs_on();
+
+	/* Wait for external, I/O or machine check interrupt. */
+	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT |
+		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+	clear_cpu_flag(CIF_NOHZ_DELAY);
+
+	/* Call the assembler magic in entry.S */
+	psw_idle(idle, psw_mask);
+
+	/* Account time spent with enabled wait psw loaded as idle time. */
+	idle->sequence++;
+	smp_wmb();
+	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
+	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
+	idle->idle_time += idle_time;
+	idle->idle_count++;
+	account_idle_time(idle_time);
+	smp_wmb();
+	idle->sequence++;
+}
+
+static ssize_t show_idle_count(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
+	unsigned long long idle_count;
+	unsigned int sequence;
+
+	do {
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_count = ACCESS_ONCE(idle->idle_count);
+		if (ACCESS_ONCE(idle->clock_idle_enter))
+			idle_count++;
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
+	return sprintf(buf, "%llu\n", idle_count);
+}
+DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
+
+static ssize_t show_idle_time(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
+	unsigned long long now, idle_time, idle_enter, idle_exit;
+	unsigned int sequence;
+
+	do {
+		now = get_tod_clock();
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_time = ACCESS_ONCE(idle->idle_time);
+		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
+		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
+	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+	return sprintf(buf, "%llu\n", idle_time >> 12);
+}
+DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
+
+cputime64_t arch_cpu_idle_time(int cpu)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
+	unsigned long long now, idle_enter, idle_exit;
+	unsigned int sequence;
+
+	do {
+		now = get_tod_clock();
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
+		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
+	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+}
+
+void arch_cpu_idle_enter(void)
+{
+	local_mcck_disable();
+}
+
+void arch_cpu_idle(void)
+{
+	if (!test_cpu_flag(CIF_MCCK_PENDING))
+		/* Halt the cpu and keep track of cpu time accounting. */
+		enabled_wait();
+	local_irq_enable();
+}
+
+void arch_cpu_idle_exit(void)
+{
+	local_mcck_enable();
+	if (test_cpu_flag(CIF_MCCK_PENDING))
+		s390_handle_mcck();
+}
+
+void arch_cpu_idle_dead(void)
+{
+	cpu_die();
+}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 8eb82443cfbd..1b8a38ab7861 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -70,6 +70,7 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 	{.irq = IRQEXT_CMS, .name = "CMS", .desc = "[EXT] CPU-Measurement: Sampling"},
 	{.irq = IRQEXT_CMC, .name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"},
 	{.irq = IRQEXT_CMR, .name = "CMR", .desc = "[EXT] CPU-Measurement: RI"},
+	{.irq = IRQEXT_FTP, .name = "FTP", .desc = "[EXT] HMC FTP Service"},
 	{.irq = IRQIO_CIO,  .name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"},
 	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"},
 	{.irq = IRQIO_DAS,  .name = "DAS", .desc = "[I/O] DASD"},
@@ -258,7 +259,7 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy)
 
 	ext_code = *(struct ext_code *) &regs->int_code;
 	if (ext_code.code != EXT_IRQ_CLK_COMP)
-		__get_cpu_var(s390_idle).nohz_delay = 1;
+		set_cpu_flag(CIF_NOHZ_DELAY);
 
 	index = ext_hash(ext_code.code);
 	rcu_read_lock();
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index bc71a7b95af5..014d4729b134 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -58,161 +58,13 @@ struct kprobe_insn_cache kprobe_dmainsn_slots = {
 	.insn_size = MAX_INSN_SIZE,
 };
 
-static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
-{
-	if (!is_known_insn((unsigned char *)insn))
-		return -EINVAL;
-	switch (insn[0] >> 8) {
-	case 0x0c:	/* bassm */
-	case 0x0b:	/* bsm	 */
-	case 0x83:	/* diag  */
-	case 0x44:	/* ex	 */
-	case 0xac:	/* stnsm */
-	case 0xad:	/* stosm */
-		return -EINVAL;
-	case 0xc6:
-		switch (insn[0] & 0x0f) {
-		case 0x00: /* exrl   */
-			return -EINVAL;
-		}
-	}
-	switch (insn[0]) {
-	case 0x0101:	/* pr	 */
-	case 0xb25a:	/* bsa	 */
-	case 0xb240:	/* bakr  */
-	case 0xb258:	/* bsg	 */
-	case 0xb218:	/* pc	 */
-	case 0xb228:	/* pt	 */
-	case 0xb98d:	/* epsw	 */
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int __kprobes get_fixup_type(kprobe_opcode_t *insn)
-{
-	/* default fixup method */
-	int fixup = FIXUP_PSW_NORMAL;
-
-	switch (insn[0] >> 8) {
-	case 0x05:	/* balr	*/
-	case 0x0d:	/* basr */
-		fixup = FIXUP_RETURN_REGISTER;
-		/* if r2 = 0, no branch will be taken */
-		if ((insn[0] & 0x0f) == 0)
-			fixup |= FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0x06:	/* bctr	*/
-	case 0x07:	/* bcr	*/
-		fixup = FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0x45:	/* bal	*/
-	case 0x4d:	/* bas	*/
-		fixup = FIXUP_RETURN_REGISTER;
-		break;
-	case 0x47:	/* bc	*/
-	case 0x46:	/* bct	*/
-	case 0x86:	/* bxh	*/
-	case 0x87:	/* bxle	*/
-		fixup = FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0x82:	/* lpsw	*/
-		fixup = FIXUP_NOT_REQUIRED;
-		break;
-	case 0xb2:	/* lpswe */
-		if ((insn[0] & 0xff) == 0xb2)
-			fixup = FIXUP_NOT_REQUIRED;
-		break;
-	case 0xa7:	/* bras	*/
-		if ((insn[0] & 0x0f) == 0x05)
-			fixup |= FIXUP_RETURN_REGISTER;
-		break;
-	case 0xc0:
-		if ((insn[0] & 0x0f) == 0x05)	/* brasl */
-			fixup |= FIXUP_RETURN_REGISTER;
-		break;
-	case 0xeb:
-		switch (insn[2] & 0xff) {
-		case 0x44: /* bxhg  */
-		case 0x45: /* bxleg */
-			fixup = FIXUP_BRANCH_NOT_TAKEN;
-			break;
-		}
-		break;
-	case 0xe3:	/* bctg	*/
-		if ((insn[2] & 0xff) == 0x46)
-			fixup = FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0xec:
-		switch (insn[2] & 0xff) {
-		case 0xe5: /* clgrb */
-		case 0xe6: /* cgrb  */
-		case 0xf6: /* crb   */
-		case 0xf7: /* clrb  */
-		case 0xfc: /* cgib  */
-		case 0xfd: /* cglib */
-		case 0xfe: /* cib   */
-		case 0xff: /* clib  */
-			fixup = FIXUP_BRANCH_NOT_TAKEN;
-			break;
-		}
-		break;
-	}
-	return fixup;
-}
-
-static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn)
-{
-	/* Check if we have a RIL-b or RIL-c format instruction which
-	 * we need to modify in order to avoid instruction emulation. */
-	switch (insn[0] >> 8) {
-	case 0xc0:
-		if ((insn[0] & 0x0f) == 0x00) /* larl */
-			return true;
-		break;
-	case 0xc4:
-		switch (insn[0] & 0x0f) {
-		case 0x02: /* llhrl  */
-		case 0x04: /* lghrl  */
-		case 0x05: /* lhrl   */
-		case 0x06: /* llghrl */
-		case 0x07: /* sthrl  */
-		case 0x08: /* lgrl   */
-		case 0x0b: /* stgrl  */
-		case 0x0c: /* lgfrl  */
-		case 0x0d: /* lrl    */
-		case 0x0e: /* llgfrl */
-		case 0x0f: /* strl   */
-			return true;
-		}
-		break;
-	case 0xc6:
-		switch (insn[0] & 0x0f) {
-		case 0x02: /* pfdrl  */
-		case 0x04: /* cghrl  */
-		case 0x05: /* chrl   */
-		case 0x06: /* clghrl */
-		case 0x07: /* clhrl  */
-		case 0x08: /* cgrl   */
-		case 0x0a: /* clgrl  */
-		case 0x0c: /* cgfrl  */
-		case 0x0d: /* crl    */
-		case 0x0e: /* clgfrl */
-		case 0x0f: /* clrl   */
-			return true;
-		}
-		break;
-	}
-	return false;
-}
-
 static void __kprobes copy_instruction(struct kprobe *p)
 {
 	s64 disp, new_disp;
 	u64 addr, new_addr;
 
 	memcpy(p->ainsn.insn, p->addr, insn_length(p->opcode >> 8));
-	if (!is_insn_relative_long(p->ainsn.insn))
+	if (!probe_is_insn_relative_long(p->ainsn.insn))
 		return;
 	/*
 	 * For pc-relative instructions in RIL-b or RIL-c format patch the
@@ -276,7 +128,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	if ((unsigned long) p->addr & 0x01)
 		return -EINVAL;
 	/* Make sure the probe isn't going on a difficult instruction */
-	if (is_prohibited_opcode(p->addr))
+	if (probe_is_prohibited_opcode(p->addr))
 		return -EINVAL;
 	if (s390_get_insn_slot(p))
 		return -ENOMEM;
@@ -366,9 +218,9 @@ static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb,
  */
 static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
 {
-	kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe);
+	kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe);
 	kcb->prev_kprobe.status = kcb->kprobe_status;
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 /*
@@ -378,7 +230,7 @@ static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
  */
 static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
@@ -459,7 +311,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
 	} else if (kprobe_running()) {
-		p = __get_cpu_var(current_kprobe);
+		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
 			/*
 			 * Continuation after the jprobe completed and
@@ -605,7 +457,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	unsigned long ip = regs->psw.addr & PSW_ADDR_INSN;
-	int fixup = get_fixup_type(p->ainsn.insn);
+	int fixup = probe_get_fixup_type(p->ainsn.insn);
 
 	if (fixup & FIXUP_PSW_NORMAL)
 		ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn;
@@ -789,11 +641,6 @@ void __kprobes jprobe_return(void)
 	asm volatile(".word 0x0002");
 }
 
-static void __used __kprobes jprobe_return_end(void)
-{
-	asm volatile("bcr 0,0");
-}
-
 int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 719e27b2cf22..4685337fa7c6 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -25,6 +25,7 @@
 #include <asm/elf.h>
 #include <asm/asm-offsets.h>
 #include <asm/os_info.h>
+#include <asm/switch_to.h>
 
 typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long);
 
@@ -43,7 +44,7 @@ static void add_elf_notes(int cpu)
 
 	memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa));
 	ptr = (u64 *) per_cpu_ptr(crash_notes, cpu);
-	ptr = fill_cpu_elf_notes(ptr, sa);
+	ptr = fill_cpu_elf_notes(ptr, sa, NULL);
 	memset(ptr, 0, sizeof(struct elf_note));
 }
 
@@ -53,8 +54,11 @@ static void add_elf_notes(int cpu)
 static void setup_regs(void)
 {
 	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
+	struct _lowcore *lc;
 	int cpu, this_cpu;
 
+	/* Get lowcore pointer from store status of this CPU (absolute zero) */
+	lc = (struct _lowcore *)(unsigned long)S390_lowcore.prefixreg_save_area;
 	this_cpu = smp_find_processor_id(stap());
 	add_elf_notes(this_cpu);
 	for_each_online_cpu(cpu) {
@@ -64,6 +68,8 @@ static void setup_regs(void)
 			continue;
 		add_elf_notes(cpu);
 	}
+	if (MACHINE_HAS_VX)
+		save_vx_regs_safe((void *) lc->vector_save_area_addr);
 	/* Copy dump CPU store status info to absolute zero */
 	memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
 }
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 433c6dbfa442..4300ea374826 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -8,62 +8,72 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
+#include <asm/ptrace.h>
 
 	.section .kprobes.text, "ax"
 
 ENTRY(ftrace_stub)
 	br	%r14
 
+#define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
+#define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
+#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
+#define STACK_PTREGS_PSW  (STACK_PTREGS + __PT_PSW)
+
 ENTRY(_mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
 	br	%r14
 
 ENTRY(ftrace_caller)
+	.globl	ftrace_regs_caller
+	.set	ftrace_regs_caller,ftrace_caller
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_SIZE
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	stg	%r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+	stg	%r0,(STACK_PTREGS_PSW+8)(%r15)
+	stmg	%r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+	aghik	%r2,%r0,-MCOUNT_INSN_SIZE
+	lgrl	%r4,function_trace_op
+	lgrl	%r1,ftrace_trace_function
+#else
+	lgr	%r2,%r0
+	aghi	%r2,-MCOUNT_INSN_SIZE
+	larl	%r4,function_trace_op
+	lg	%r4,0(%r4)
+	larl	%r1,ftrace_trace_function
+	lg	%r1,0(%r1)
 #endif
-	stm	%r2,%r5,16(%r15)
-	bras	%r1,1f
-0:	.long	ftrace_trace_function
-1:	st	%r14,56(%r15)
-	lr	%r0,%r15
-	ahi	%r15,-96
-	l	%r3,100(%r15)
-	la	%r2,0(%r14)
-	st	%r0,__SF_BACKCHAIN(%r15)
-	la	%r3,0(%r3)
-	ahi	%r2,-MCOUNT_INSN_SIZE
-	l	%r14,0b-0b(%r1)
-	l	%r14,0(%r14)
-	basr	%r14,%r14
+	lgr	%r3,%r14
+	la	%r5,STACK_PTREGS(%r15)
+	basr	%r14,%r1
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	l	%r2,100(%r15)
-	l	%r3,152(%r15)
+# The j instruction gets runtime patched to a nop instruction.
+# See ftrace_enable_ftrace_graph_caller.
 ENTRY(ftrace_graph_caller)
-# The bras instruction gets runtime patched to call prepare_ftrace_return.
-# See ftrace_enable_ftrace_graph_caller. The patched instruction is:
-#	bras	%r14,prepare_ftrace_return
-	bras	%r14,0f
-0:	st	%r2,100(%r15)
+	j	ftrace_graph_caller_end
+	lg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+	lg	%r3,(STACK_PTREGS_PSW+8)(%r15)
+	brasl	%r14,prepare_ftrace_return
+	stg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+ftrace_graph_caller_end:
+	.globl	ftrace_graph_caller_end
 #endif
-	ahi	%r15,96
-	l	%r14,56(%r15)
-	lm	%r2,%r5,16(%r15)
-	br	%r14
+	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
+	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
+	br	%r1
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 ENTRY(return_to_handler)
-	stm	%r2,%r5,16(%r15)
-	st	%r14,56(%r15)
-	lr	%r0,%r15
-	ahi	%r15,-96
-	st	%r0,__SF_BACKCHAIN(%r15)
-	bras	%r1,0f
-	.long	ftrace_return_to_handler
-0:	l	%r2,0b-0b(%r1)
-	basr	%r14,%r2
-	lr	%r14,%r2
-	ahi	%r15,96
-	lm	%r2,%r5,16(%r15)
+	stmg	%r2,%r5,32(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	brasl	%r14,ftrace_return_to_handler
+	aghi	%r15,STACK_FRAME_OVERHEAD
+	lgr	%r14,%r2
+	lmg	%r2,%r5,32(%r15)
 	br	%r14
 
 #endif
diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S
deleted file mode 100644
index c67a8bf0fd9a..000000000000
--- a/arch/s390/kernel/mcount64.S
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Copyright IBM Corp. 2008, 2009
- *
- *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-
-	.section .kprobes.text, "ax"
-
-ENTRY(ftrace_stub)
-	br	%r14
-
-ENTRY(_mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
-	br	%r14
-
-ENTRY(ftrace_caller)
-#endif
-	stmg	%r2,%r5,32(%r15)
-	stg	%r14,112(%r15)
-	lgr	%r1,%r15
-	aghi	%r15,-160
-	stg	%r1,__SF_BACKCHAIN(%r15)
-	lgr	%r2,%r14
-	lg	%r3,168(%r15)
-	aghi	%r2,-MCOUNT_INSN_SIZE
-	larl	%r14,ftrace_trace_function
-	lg	%r14,0(%r14)
-	basr	%r14,%r14
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	lg	%r2,168(%r15)
-	lg	%r3,272(%r15)
-ENTRY(ftrace_graph_caller)
-# The bras instruction gets runtime patched to call prepare_ftrace_return.
-# See ftrace_enable_ftrace_graph_caller. The patched instruction is:
-#	bras	%r14,prepare_ftrace_return
-	bras	%r14,0f
-0:	stg	%r2,168(%r15)
-#endif
-	aghi	%r15,160
-	lmg	%r2,%r5,32(%r15)
-	lg	%r14,112(%r15)
-	br	%r14
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-ENTRY(return_to_handler)
-	stmg	%r2,%r5,32(%r15)
-	lgr	%r1,%r15
-	aghi	%r15,-160
-	stg	%r1,__SF_BACKCHAIN(%r15)
-	brasl	%r14,ftrace_return_to_handler
-	aghi	%r15,160
-	lgr	%r14,%r2
-	lmg	%r2,%r5,32(%r15)
-	br	%r14
-
-#endif
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 210e1285f75a..dd1c24ceda50 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -20,6 +20,7 @@
 #include <asm/cputime.h>
 #include <asm/nmi.h>
 #include <asm/crw.h>
+#include <asm/switch_to.h>
 
 struct mcck_struct {
 	int kill_task;
@@ -53,8 +54,12 @@ void s390_handle_mcck(void)
 	 */
 	local_irq_save(flags);
 	local_mcck_disable();
-	mcck = __get_cpu_var(cpu_mcck);
-	memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct));
+	/*
+	 * Ummm... Does this make sense at all? Copying the percpu struct
+	 * and then zapping it one statement later?
+	 */
+	memcpy(&mcck, this_cpu_ptr(&cpu_mcck), sizeof(mcck));
+	memset(&mcck, 0, sizeof(struct mcck_struct));
 	clear_cpu_flag(CIF_MCCK_PENDING);
 	local_mcck_enable();
 	local_irq_restore(flags);
@@ -163,6 +168,21 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			"	ld	15,120(%0)\n"
 			: : "a" (fpt_save_area));
 	}
+
+#ifdef CONFIG_64BIT
+	/* Revalidate vector registers */
+	if (MACHINE_HAS_VX && current->thread.vxrs) {
+		if (!mci->vr) {
+			/*
+			 * Vector registers can't be restored and therefore
+			 * the process needs to be terminated.
+			 */
+			kill_task = 1;
+		}
+		restore_vx_regs((__vector128 *)
+				S390_lowcore.vector_save_area_addr);
+	}
+#endif
 	/* Revalidate access registers */
 	asm volatile(
 		"	lam	0,15,0(%0)"
@@ -253,7 +273,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	nmi_enter();
 	inc_irq_stat(NMI_NMI);
 	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
-	mcck = &__get_cpu_var(cpu_mcck);
+	mcck = this_cpu_ptr(&cpu_mcck);
 	umode = user_mode(regs);
 
 	if (mci->sd) {
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index d3194de7ae1e..56fdad479115 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -173,7 +173,7 @@ static int validate_ctr_auth(const struct hw_perf_event *hwc)
  */
 static void cpumf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 
 	if (cpuhw->flags & PMU_F_ENABLED)
@@ -196,7 +196,7 @@ static void cpumf_pmu_enable(struct pmu *pmu)
  */
 static void cpumf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 	u64 inactive;
 
@@ -230,7 +230,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 		return;
 
 	inc_irq_stat(IRQEXT_CMC);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
@@ -250,7 +250,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 #define PMC_RELEASE   1
 static void setup_pmc_cpu(void *flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	switch (*((int *) flags)) {
 	case PMC_INIT:
@@ -475,7 +475,7 @@ static void cpumf_pmu_read(struct perf_event *event)
 
 static void cpumf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
@@ -506,7 +506,7 @@ static void cpumf_pmu_start(struct perf_event *event, int flags)
 
 static void cpumf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -527,7 +527,7 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags)
 
 static int cpumf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Check authorization for the counter set to which this
 	 * counter belongs.
@@ -551,7 +551,7 @@ static int cpumf_pmu_add(struct perf_event *event, int flags)
 
 static void cpumf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpumf_pmu_stop(event, PERF_EF_UPDATE);
 
@@ -575,7 +575,7 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
  */
 static void cpumf_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->flags |= PERF_EVENT_TXN;
@@ -589,7 +589,7 @@ static void cpumf_pmu_start_txn(struct pmu *pmu)
  */
 static void cpumf_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(cpuhw->tx_state != cpuhw->state);
 
@@ -604,7 +604,7 @@ static void cpumf_pmu_cancel_txn(struct pmu *pmu)
  */
 static int cpumf_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	u64 state;
 
 	/* check if the updated state can be scheduled */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ea0c7b2ef030..08e761318c17 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -562,7 +562,7 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 static void setup_pmc_cpu(void *flags)
 {
 	int err;
-	struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpusf = this_cpu_ptr(&cpu_hw_sf);
 
 	err = 0;
 	switch (*((int *) flags)) {
@@ -849,7 +849,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 
 static void cpumsf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hw_perf_event *hwc;
 	int err;
 
@@ -898,7 +898,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 
 static void cpumsf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hws_lsctl_request_block inactive;
 	struct hws_qsi_info_block si;
 	int err;
@@ -1306,7 +1306,7 @@ static void cpumsf_pmu_read(struct perf_event *event)
  */
 static void cpumsf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
 		return;
@@ -1327,7 +1327,7 @@ static void cpumsf_pmu_start(struct perf_event *event, int flags)
  */
 static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	if (event->hw.state & PERF_HES_STOPPED)
 		return;
@@ -1346,7 +1346,7 @@ static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 
 static int cpumsf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	int err;
 
 	if (cpuhw->flags & PMU_F_IN_USE)
@@ -1397,7 +1397,7 @@ out:
 
 static void cpumsf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	perf_pmu_disable(event->pmu);
 	cpumsf_pmu_stop(event, PERF_EF_UPDATE);
@@ -1470,7 +1470,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 	if (!(alert & CPU_MF_INT_SF_MASK))
 		return;
 	inc_irq_stat(IRQEXT_CMS);
-	cpuhw = &__get_cpu_var(cpu_hw_sf);
+	cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 813ec7260878..f6f8886399f6 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -49,7 +49,7 @@ PGM_CHECK_DEFAULT			/* 17 */
 PGM_CHECK_64BIT(transaction_exception)	/* 18 */
 PGM_CHECK_DEFAULT			/* 19 */
 PGM_CHECK_DEFAULT			/* 1a */
-PGM_CHECK_DEFAULT			/* 1b */
+PGM_CHECK_64BIT(vector_exception)	/* 1b */
 PGM_CHECK(space_switch_exception)	/* 1c */
 PGM_CHECK(hfp_sqrt_exception)		/* 1d */
 PGM_CHECK_DEFAULT			/* 1e */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 93b9ca42e5c0..ed84cc224899 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -61,30 +61,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return sf->gprs[8];
 }
 
-void arch_cpu_idle(void)
-{
-	local_mcck_disable();
-	if (test_cpu_flag(CIF_MCCK_PENDING)) {
-		local_mcck_enable();
-		local_irq_enable();
-		return;
-	}
-	/* Halt the cpu and keep track of cpu time accounting. */
-	vtime_stop_cpu();
-	local_irq_enable();
-}
-
-void arch_cpu_idle_exit(void)
-{
-	if (test_cpu_flag(CIF_MCCK_PENDING))
-		s390_handle_mcck();
-}
-
-void arch_cpu_idle_dead(void)
-{
-	cpu_die();
-}
-
 extern void __kprobes kernel_thread_starter(void);
 
 /*
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 24612029f450..dbdd33ee0102 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -23,15 +23,13 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id);
  */
 void cpu_init(void)
 {
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
-	struct cpuid *id = &__get_cpu_var(cpu_id);
+	struct cpuid *id = this_cpu_ptr(&cpu_id);
 
 	get_cpu_id(id);
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
-	memset(idle, 0, sizeof(*idle));
 }
 
 /*
@@ -41,7 +39,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te"
+		"edat", "etf3eh", "highgprs", "te", "vx"
 	};
 	unsigned long n = (unsigned long) v - 1;
 	int i;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index bebacad48305..99a567b70d16 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -38,15 +38,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-enum s390_regset {
-	REGSET_GENERAL,
-	REGSET_FP,
-	REGSET_LAST_BREAK,
-	REGSET_TDB,
-	REGSET_SYSTEM_CALL,
-	REGSET_GENERAL_EXTENDED,
-};
-
 void update_cr_regs(struct task_struct *task)
 {
 	struct pt_regs *regs = task_pt_regs(task);
@@ -55,27 +46,39 @@ void update_cr_regs(struct task_struct *task)
 
 #ifdef CONFIG_64BIT
 	/* Take care of the enable/disable of transactional execution. */
-	if (MACHINE_HAS_TE) {
+	if (MACHINE_HAS_TE || MACHINE_HAS_VX) {
 		unsigned long cr, cr_new;
 
 		__ctl_store(cr, 0, 0);
-		/* Set or clear transaction execution TXC bit 8. */
-		cr_new = cr | (1UL << 55);
-		if (task->thread.per_flags & PER_FLAG_NO_TE)
-			cr_new &= ~(1UL << 55);
+		cr_new = cr;
+		if (MACHINE_HAS_TE) {
+			/* Set or clear transaction execution TXC bit 8. */
+			cr_new |= (1UL << 55);
+			if (task->thread.per_flags & PER_FLAG_NO_TE)
+				cr_new &= ~(1UL << 55);
+		}
+		if (MACHINE_HAS_VX) {
+			/* Enable/disable of vector extension */
+			cr_new &= ~(1UL << 17);
+			if (task->thread.vxrs)
+				cr_new |= (1UL << 17);
+		}
 		if (cr_new != cr)
 			__ctl_load(cr_new, 0, 0);
-		/* Set or clear transaction execution TDC bits 62 and 63. */
-		__ctl_store(cr, 2, 2);
-		cr_new = cr & ~3UL;
-		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
-			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
-				cr_new |= 1UL;
-			else
-				cr_new |= 2UL;
+		if (MACHINE_HAS_TE) {
+			/* Set/clear transaction execution TDC bits 62/63. */
+			__ctl_store(cr, 2, 2);
+			cr_new = cr & ~3UL;
+			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
+				if (task->thread.per_flags &
+				    PER_FLAG_TE_ABORT_RAND_TEND)
+					cr_new |= 1UL;
+				else
+					cr_new |= 2UL;
+			}
+			if (cr_new != cr)
+				__ctl_load(cr_new, 2, 2);
 		}
-		if (cr_new != cr)
-			__ctl_load(cr_new, 2, 2);
 	}
 #endif
 	/* Copy user specified PER registers */
@@ -84,7 +87,8 @@ void update_cr_regs(struct task_struct *task)
 	new.end = thread->per_user.end;
 
 	/* merge TIF_SINGLE_STEP into user specified PER registers. */
-	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) {
+	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP) ||
+	    test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) {
 		if (test_tsk_thread_flag(task, TIF_BLOCK_STEP))
 			new.control |= PER_EVENT_BRANCH;
 		else
@@ -93,6 +97,8 @@ void update_cr_regs(struct task_struct *task)
 		new.control |= PER_CONTROL_SUSPENSION;
 		new.control |= PER_EVENT_TRANSACTION_END;
 #endif
+		if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP))
+			new.control |= PER_EVENT_IFETCH;
 		new.start = 0;
 		new.end = PSW_ADDR_INSN;
 	}
@@ -828,9 +834,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->gprs[2]);
 
-	audit_syscall_entry(is_compat_task() ?
-				AUDIT_ARCH_S390 : AUDIT_ARCH_S390X,
-			    regs->gprs[2], regs->orig_gpr2,
+	audit_syscall_entry(regs->gprs[2], regs->orig_gpr2,
 			    regs->gprs[3], regs->gprs[4],
 			    regs->gprs[5]);
 out:
@@ -923,7 +927,15 @@ static int s390_fpregs_get(struct task_struct *target,
 		save_fp_ctl(&target->thread.fp_regs.fpc);
 		save_fp_regs(target->thread.fp_regs.fprs);
 	}
+#ifdef CONFIG_64BIT
+	else if (target->thread.vxrs) {
+		int i;
 
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			target->thread.fp_regs.fprs[i] =
+				*(freg_t *)(target->thread.vxrs + i);
+	}
+#endif
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   &target->thread.fp_regs, 0, -1);
 }
@@ -957,9 +969,20 @@ static int s390_fpregs_set(struct task_struct *target,
 					target->thread.fp_regs.fprs,
 					offsetof(s390_fp_regs, fprs), -1);
 
-	if (rc == 0 && target == current) {
-		restore_fp_ctl(&target->thread.fp_regs.fpc);
-		restore_fp_regs(target->thread.fp_regs.fprs);
+	if (rc == 0) {
+		if (target == current) {
+			restore_fp_ctl(&target->thread.fp_regs.fpc);
+			restore_fp_regs(target->thread.fp_regs.fprs);
+		}
+#ifdef CONFIG_64BIT
+		else if (target->thread.vxrs) {
+			int i;
+
+			for (i = 0; i < __NUM_VXRS_LOW; i++)
+				*(freg_t *)(target->thread.vxrs + i) =
+					target->thread.fp_regs.fprs[i];
+		}
+#endif
 	}
 
 	return rc;
@@ -1015,6 +1038,95 @@ static int s390_tdb_set(struct task_struct *target,
 	return 0;
 }
 
+static int s390_vxrs_active(struct task_struct *target,
+			      const struct user_regset *regset)
+{
+	return !!target->thread.vxrs;
+}
+
+static int s390_vxrs_low_get(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     void *kbuf, void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(target->thread.vxrs + i) + 1);
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_low_set(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     const void *kbuf, const void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i, rc;
+
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+	if (rc == 0) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(target->thread.vxrs + i) + 1) = vxrs[i];
+		if (target == current)
+			restore_vx_regs(target->thread.vxrs);
+	}
+
+	return rc;
+}
+
+static int s390_vxrs_high_get(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      void *kbuf, void __user *ubuf)
+{
+	__vector128 vxrs[__NUM_VXRS_HIGH];
+
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		memcpy(vxrs, target->thread.vxrs + __NUM_VXRS_LOW,
+		       sizeof(vxrs));
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_high_set(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      const void *kbuf, const void __user *ubuf)
+{
+	int rc;
+
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				target->thread.vxrs + __NUM_VXRS_LOW, 0, -1);
+	if (rc == 0 && target == current)
+		restore_vx_regs(target->thread.vxrs);
+
+	return rc;
+}
+
 #endif
 
 static int s390_system_call_get(struct task_struct *target,
@@ -1038,7 +1150,7 @@ static int s390_system_call_set(struct task_struct *target,
 }
 
 static const struct user_regset s390_regsets[] = {
-	[REGSET_GENERAL] = {
+	{
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(s390_regs) / sizeof(long),
 		.size = sizeof(long),
@@ -1046,7 +1158,7 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_regs_get,
 		.set = s390_regs_set,
 	},
-	[REGSET_FP] = {
+	{
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(s390_fp_regs) / sizeof(long),
 		.size = sizeof(long),
@@ -1054,8 +1166,16 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(unsigned int),
+		.align = sizeof(unsigned int),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
 #ifdef CONFIG_64BIT
-	[REGSET_LAST_BREAK] = {
+	{
 		.core_note_type = NT_S390_LAST_BREAK,
 		.n = 1,
 		.size = sizeof(long),
@@ -1063,7 +1183,7 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_last_break_get,
 		.set = s390_last_break_set,
 	},
-	[REGSET_TDB] = {
+	{
 		.core_note_type = NT_S390_TDB,
 		.n = 1,
 		.size = 256,
@@ -1071,15 +1191,25 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_tdb_get,
 		.set = s390_tdb_set,
 	},
-#endif
-	[REGSET_SYSTEM_CALL] = {
-		.core_note_type = NT_S390_SYSTEM_CALL,
-		.n = 1,
-		.size = sizeof(unsigned int),
-		.align = sizeof(unsigned int),
-		.get = s390_system_call_get,
-		.set = s390_system_call_set,
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
 	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
+	},
+#endif
 };
 
 static const struct user_regset_view user_s390_view = {
@@ -1244,7 +1374,7 @@ static int s390_compat_last_break_set(struct task_struct *target,
 }
 
 static const struct user_regset s390_compat_regsets[] = {
-	[REGSET_GENERAL] = {
+	{
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(s390_compat_regs) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
@@ -1252,7 +1382,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_regs_get,
 		.set = s390_compat_regs_set,
 	},
-	[REGSET_FP] = {
+	{
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(s390_fp_regs) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
@@ -1260,7 +1390,15 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
-	[REGSET_LAST_BREAK] = {
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(compat_uint_t),
+		.align = sizeof(compat_uint_t),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
+	{
 		.core_note_type = NT_S390_LAST_BREAK,
 		.n = 1,
 		.size = sizeof(long),
@@ -1268,7 +1406,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_last_break_get,
 		.set = s390_compat_last_break_set,
 	},
-	[REGSET_TDB] = {
+	{
 		.core_note_type = NT_S390_TDB,
 		.n = 1,
 		.size = 256,
@@ -1276,15 +1414,25 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_tdb_get,
 		.set = s390_tdb_set,
 	},
-	[REGSET_SYSTEM_CALL] = {
-		.core_note_type = NT_S390_SYSTEM_CALL,
-		.n = 1,
-		.size = sizeof(compat_uint_t),
-		.align = sizeof(compat_uint_t),
-		.get = s390_system_call_get,
-		.set = s390_system_call_set,
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
 	},
-	[REGSET_GENERAL_EXTENDED] = {
+	{
 		.core_note_type = NT_S390_HIGH_GPRS,
 		.n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 82bc113e8c1d..e80d9ff9a56d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -343,6 +343,9 @@ static void __init setup_lowcore(void)
 		__ctl_set_bit(14, 29);
 	}
 #else
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
 	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
 #endif
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
@@ -452,8 +455,8 @@ static void __init setup_memory_end(void)
 #ifdef CONFIG_64BIT
 	vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN;
 	tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE;
-	tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size;
-	if (tmp <= (1UL << 42))
+	tmp = tmp * (sizeof(struct page) + PAGE_SIZE);
+	if (tmp + vmalloc_size + MODULES_LEN <= (1UL << 42))
 		vmax = 1UL << 42;	/* 3-level kernel page table */
 	else
 		vmax = 1UL << 53;	/* 4-level kernel page table */
@@ -765,6 +768,12 @@ static void __init setup_hwcaps(void)
 	 */
 	if (test_facility(50) && test_facility(73))
 		elf_hwcap |= HWCAP_S390_TE;
+
+	/*
+	 * Vector extension HWCAP_S390_VXRS is bit 11.
+	 */
+	if (test_facility(129))
+		elf_hwcap |= HWCAP_S390_VXRS;
 #endif
 
 	get_cpu_id(&cpu_id);
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 469c4c6d9182..0c1a0ff0a558 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -31,30 +31,117 @@
 #include <asm/switch_to.h>
 #include "entry.h"
 
-typedef struct 
+/*
+ * Layout of an old-style signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| struct sigcontext			|
+ *	|	oldmask				|
+ *	|	_sigregs *			|
+ *	-----------------------------------------
+ *	| _sigregs with				|
+ *	|	_s390_regs_common		|
+ *	|	_s390_fp_regs			|
+ *	-----------------------------------------
+ *	| int signo				|
+ *	-----------------------------------------
+ *	| _sigregs_ext with			|
+ *	|	gprs_high 64 byte (opt)		|
+ *	|	vxrs_low 128 byte (opt)		|
+ *	|	vxrs_high 256 byte (opt)	|
+ *	|	reserved 128 byte (opt)		|
+ *	-----------------------------------------
+ *	| __u16 svc_insn			|
+ *	-----------------------------------------
+ * The svc_insn entry with the sigreturn system call opcode does not
+ * have a fixed position and moves if gprs_high or vxrs exist.
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct sigframe
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
 	struct sigcontext sc;
 	_sigregs sregs;
 	int signo;
-	__u8 retcode[S390_SYSCALL_SIZE];
-} sigframe;
+	_sigregs_ext sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
+};
 
-typedef struct 
+/*
+ * Layout of an rt signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| svc __NR_rt_sigreturn 2 byte		|
+ *	-----------------------------------------
+ *	| struct siginfo			|
+ *	-----------------------------------------
+ *	| struct ucontext_extended with		|
+ *	|	unsigned long uc_flags		|
+ *	|	struct ucontext *uc_link	|
+ *	|	stack_t uc_stack		|
+ *	|	_sigregs uc_mcontext with	|
+ *	|		_s390_regs_common	|
+ *	|		_s390_fp_regs		|
+ *	|	sigset_t uc_sigmask		|
+ *	|	_sigregs_ext uc_mcontext_ext	|
+ *	|		gprs_high 64 byte (opt)	|
+ *	|		vxrs_low 128 byte (opt)	|
+ *	|		vxrs_high 256 byte (opt)|
+ *	|		reserved 128 byte (opt)	|
+ *	-----------------------------------------
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct rt_sigframe
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	__u16 svc_insn;
 	struct siginfo info;
-	struct ucontext uc;
-} rt_sigframe;
+	struct ucontext_extended uc;
+};
+
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+#ifdef CONFIG_64BIT
+	if (current->thread.vxrs) {
+		int i;
+
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+#endif
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+#ifdef CONFIG_64BIT
+	if (current->thread.vxrs) {
+		int i;
+
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+#endif
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
 
 /* Returns non-zero on fault. */
 static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 {
 	_sigregs user_sregs;
 
-	save_access_regs(current->thread.acrs);
-
 	/* Copy a 'clean' PSW mask to the user to avoid leaking
 	   information about whether PER is currently on.  */
 	user_sregs.regs.psw.mask = PSW_USER_BITS |
@@ -63,12 +150,6 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&user_sregs.regs.gprs, &regs->gprs, sizeof(sregs->regs.gprs));
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	/* 
-	 * We have to store the fp registers to current->thread.fp_regs
-	 * to merge them with the emulated registers.
-	 */
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	save_fp_regs(current->thread.fp_regs.fprs);
 	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(user_sregs.fpregs));
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs)))
@@ -107,20 +188,64 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&regs->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs));
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	restore_access_regs(current->thread.acrs);
 
 	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(current->thread.fp_regs));
 
-	restore_fp_regs(current->thread.fp_regs.fprs);
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
+/* Returns non-zero on fault. */
+static int save_sigregs_ext(struct pt_regs *regs,
+			    _sigregs_ext __user *sregs_ext)
+{
+#ifdef CONFIG_64BIT
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
+#endif
+	return 0;
+}
+
+static int restore_sigregs_ext(struct pt_regs *regs,
+			       _sigregs_ext __user *sregs_ext)
+{
+#ifdef CONFIG_64BIT
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
+#endif
+	return 0;
+}
+
 SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	sigframe __user *frame = (sigframe __user *)regs->gprs[15];
+	struct sigframe __user *frame =
+		(struct sigframe __user *) regs->gprs[15];
 	sigset_t set;
 
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
@@ -128,6 +253,9 @@ SYSCALL_DEFINE0(sigreturn)
 	set_current_blocked(&set);
 	if (restore_sigregs(regs, &frame->sregs))
 		goto badframe;
+	if (restore_sigregs_ext(regs, &frame->sregs_ext))
+		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -137,16 +265,20 @@ badframe:
 SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	rt_sigframe __user *frame = (rt_sigframe __user *)regs->gprs[15];
+	struct rt_sigframe __user *frame =
+		(struct rt_sigframe __user *)regs->gprs[15];
 	sigset_t set;
 
 	if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
 	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-	if (restore_altstack(&frame->uc.uc_stack))
+	if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
 		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -154,11 +286,6 @@ badframe:
 }
 
 /*
- * Set up a signal frame.
- */
-
-
-/*
  * Determine which stack to use..
  */
 static inline void __user *
@@ -195,39 +322,63 @@ static inline int map_signal(int sig)
 static int setup_frame(int sig, struct k_sigaction *ka,
 		       sigset_t *set, struct pt_regs * regs)
 {
-	sigframe __user *frame;
-
-	frame = get_sigframe(ka, regs, sizeof(sigframe));
+	struct sigframe __user *frame;
+	struct sigcontext sc;
+	unsigned long restorer;
+	size_t frame_size;
 
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext);
+	if (MACHINE_HAS_VX)
+		frame_size += sizeof(frame->sregs_ext);
+	frame = get_sigframe(ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE))
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
 		return -EFAULT;
 
+	/* Create struct sigcontext on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE);
+	sc.sregs = (_sigregs __user __force *) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs on the signal stack */
 	if (save_sigregs(regs, &frame->sregs))
 		return -EFAULT;
-	if (__put_user(&frame->sregs, &frame->sc.sregs))
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
+		return -EFAULT;
+
+	/* Create _sigregs_ext on the signal stack */
+	if (save_sigregs_ext(regs, &frame->sregs_ext))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-                regs->gprs[14] = (unsigned long)
-			ka->sa.sa_restorer | PSW_ADDR_AMODE;
+		restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
-                regs->gprs[14] = (unsigned long)
-			frame->retcode | PSW_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
-	                       (u16 __user *)(frame->retcode)))
+		/* Signal frame without vector registers are short ! */
+		__u16 __user *svc = (void *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
-		return -EFAULT;
-
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (unsigned long) frame;
 	/* Force default amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
@@ -247,54 +398,69 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 		regs->gprs[5] = regs->int_parm_long;
 		regs->gprs[6] = task_thread_info(current)->last_break;
 	}
-
-	/* Place signal number on stack to allow backtrace from handler.  */
-	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
-		return -EFAULT;
 	return 0;
 }
 
 static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
-	int err = 0;
-	rt_sigframe __user *frame;
-
-	frame = get_sigframe(&ksig->ka, regs, sizeof(rt_sigframe));
+	struct rt_sigframe __user *frame;
+	unsigned long uc_flags, restorer;
+	size_t frame_size;
 
+	frame_size = sizeof(struct rt_sigframe) - sizeof(_sigregs_ext);
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	uc_flags = 0;
+#ifdef CONFIG_64BIT
+	if (MACHINE_HAS_VX) {
+		frame_size += sizeof(_sigregs_ext);
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	}
+#endif
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (copy_siginfo_to_user(&frame->info, &ksig->info))
-		return -EFAULT;
-
-	/* Create the ucontext.  */
-	err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(NULL, &frame->uc.uc_link);
-	err |= __save_altstack(&frame->uc.uc_stack, regs->gprs[15]);
-	err |= save_sigregs(regs, &frame->uc.uc_mcontext);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-                regs->gprs[14] = (unsigned long)
+		restorer = (unsigned long)
 			ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
-                regs->gprs[14] = (unsigned long)
-			frame->retcode | PSW_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-			       (u16 __user *)(frame->retcode)))
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(NULL, &frame->uc.uc_link) ||
+	    __save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (unsigned long) frame;
 	/* Force default amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 243c7e512600..6fd9e60101f1 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -45,6 +45,7 @@
 #include <asm/debug.h>
 #include <asm/os_info.h>
 #include <asm/sigp.h>
+#include <asm/idle.h>
 #include "entry.h"
 
 enum {
@@ -82,7 +83,8 @@ DEFINE_MUTEX(smp_cpu_state_mutex);
 /*
  * Signal processor helper functions.
  */
-static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status)
+static inline int __pcpu_sigp_relax(u16 addr, u8 order, unsigned long parm,
+				    u32 *status)
 {
 	int cc;
 
@@ -178,6 +180,9 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 			goto out;
 	}
 #else
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
 	if (vdso_alloc_per_cpu(lc))
 		goto out;
 #endif
@@ -333,12 +338,6 @@ int smp_vcpu_scheduled(int cpu)
 	return pcpu_running(pcpu_devices + cpu);
 }
 
-void smp_yield(void)
-{
-	if (MACHINE_HAS_DIAG44)
-		asm volatile("diag 0,0,0x44");
-}
-
 void smp_yield_cpu(int cpu)
 {
 	if (MACHINE_HAS_DIAG9C)
@@ -517,35 +516,53 @@ EXPORT_SYMBOL(smp_ctl_clear_bit);
 static void __init smp_get_save_area(int cpu, u16 address)
 {
 	void *lc = pcpu_devices[0].lowcore;
-	struct save_area *save_area;
+	struct save_area_ext *sa_ext;
+	unsigned long vx_sa;
 
 	if (is_kdump_kernel())
 		return;
 	if (!OLDMEM_BASE && (address == boot_cpu_address ||
 			     ipl_info.type != IPL_TYPE_FCP_DUMP))
 		return;
-	save_area = dump_save_area_create(cpu);
-	if (!save_area)
+	sa_ext = dump_save_area_create(cpu);
+	if (!sa_ext)
 		panic("could not allocate memory for save area\n");
 	if (address == boot_cpu_address) {
 		/* Copy the registers of the boot cpu. */
-		copy_oldmem_page(1, (void *) save_area, sizeof(*save_area),
+		copy_oldmem_page(1, (void *) &sa_ext->sa, sizeof(sa_ext->sa),
 				 SAVE_AREA_BASE - PAGE_SIZE, 0);
+		if (MACHINE_HAS_VX)
+			save_vx_regs_safe(sa_ext->vx_regs);
 		return;
 	}
 	/* Get the registers of a non-boot cpu. */
 	__pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL);
-	memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area));
+	memcpy_real(&sa_ext->sa, lc + SAVE_AREA_BASE, sizeof(sa_ext->sa));
+	if (!MACHINE_HAS_VX)
+		return;
+	/* Get the VX registers */
+	vx_sa = __get_free_page(GFP_KERNEL);
+	if (!vx_sa)
+		panic("could not allocate memory for VX save area\n");
+	__pcpu_sigp_relax(address, SIGP_STORE_ADDITIONAL_STATUS, vx_sa, NULL);
+	memcpy(sa_ext->vx_regs, (void *) vx_sa, sizeof(sa_ext->vx_regs));
+	free_page(vx_sa);
 }
 
 int smp_store_status(int cpu)
 {
+	unsigned long vx_sa;
 	struct pcpu *pcpu;
 
 	pcpu = pcpu_devices + cpu;
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STOP_AND_STORE_STATUS,
 			      0, NULL) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
+	if (!MACHINE_HAS_VX)
+		return 0;
+	vx_sa = __pa(pcpu->lowcore->vector_save_area_addr);
+	__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
+			  vx_sa, NULL);
 	return 0;
 }
 
@@ -667,7 +684,7 @@ static void smp_start_secondary(void *cpuvoid)
 	cpu_init();
 	preempt_disable();
 	init_cpu_timer();
-	init_cpu_vtimer();
+	vtime_init();
 	pfault_init();
 	notify_cpu_starting(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
@@ -726,6 +743,7 @@ int __cpu_disable(void)
 	cregs[6]  &= ~0xff000000UL;	/* disable all I/O interrupts */
 	cregs[14] &= ~0x1f000000UL;	/* disable most machine checks */
 	__ctl_load(cregs, 0, 15);
+	clear_cpu_flag(CIF_NOHZ_DELAY);
 	return 0;
 }
 
@@ -898,42 +916,6 @@ static struct attribute_group cpu_common_attr_group = {
 	.attrs = cpu_common_attrs,
 };
 
-static ssize_t show_idle_count(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long idle_count;
-	unsigned int sequence;
-
-	do {
-		sequence = ACCESS_ONCE(idle->sequence);
-		idle_count = ACCESS_ONCE(idle->idle_count);
-		if (ACCESS_ONCE(idle->clock_idle_enter))
-			idle_count++;
-	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
-	return sprintf(buf, "%llu\n", idle_count);
-}
-static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
-
-static ssize_t show_idle_time(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long now, idle_time, idle_enter, idle_exit;
-	unsigned int sequence;
-
-	do {
-		now = get_tod_clock();
-		sequence = ACCESS_ONCE(idle->sequence);
-		idle_time = ACCESS_ONCE(idle->idle_time);
-		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
-		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
-	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
-	return sprintf(buf, "%llu\n", idle_time >> 12);
-}
-static DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
-
 static struct attribute *cpu_online_attrs[] = {
 	&dev_attr_idle_count.attr,
 	&dev_attr_idle_time_us.attr,
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 4cef607f3711..005d665fe4a5 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -92,7 +92,7 @@ void clock_comparator_work(void)
 	struct clock_event_device *cd;
 
 	S390_lowcore.clock_comparator = -1ULL;
-	cd = &__get_cpu_var(comparators);
+	cd = this_cpu_ptr(&comparators);
 	cd->event_handler(cd);
 }
 
@@ -232,6 +232,19 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->wtom_clock_nsec -= nsecps;
 		vdso_data->wtom_clock_sec++;
 	}
+
+	vdso_data->xtime_coarse_sec = tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec =
+		(long)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	vdso_data->wtom_coarse_sec =
+		vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtom_coarse_nsec =
+		vdso_data->xtime_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+	while (vdso_data->wtom_coarse_nsec >= NSEC_PER_SEC) {
+		vdso_data->wtom_coarse_nsec -= NSEC_PER_SEC;
+		vdso_data->wtom_coarse_sec++;
+	}
+
 	vdso_data->tk_mult = tk->tkr.mult;
 	vdso_data->tk_shift = tk->tkr.shift;
 	smp_wmb();
@@ -360,7 +373,7 @@ EXPORT_SYMBOL(get_sync_clock);
  */
 static void disable_sync_clock(void *dummy)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	/*
 	 * Clear the in-sync bit 2^31. All get_sync_clock calls will
 	 * fail until the sync bit is turned back on. In addition
@@ -377,7 +390,7 @@ static void disable_sync_clock(void *dummy)
  */
 static void enable_sync_clock(void)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	atomic_set_mask(0x80000000, sw_ptr);
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 355a16c55702..b93bed76ea94 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -464,15 +464,17 @@ static struct sched_domain_topology_level s390_topology[] = {
 
 static int __init topology_init(void)
 {
-	if (!MACHINE_HAS_TOPOLOGY) {
+	if (MACHINE_HAS_TOPOLOGY)
+		set_topology_timer();
+	else
 		topology_update_polarization_simple();
-		goto out;
-	}
-	set_topology_timer();
-out:
-
-	set_sched_topology(s390_topology);
-
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);
+
+static int __init early_topology_init(void)
+{
+	set_sched_topology(s390_topology);
+	return 0;
+}
+early_initcall(early_topology_init);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index c5762324d9ee..9ff5ecba26ab 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -18,6 +18,8 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 int show_unhandled_signals = 1;
@@ -58,15 +60,10 @@ int is_valid_bugaddr(unsigned long addr)
 	return 1;
 }
 
-static void __kprobes do_trap(struct pt_regs *regs,
-			      int si_signo, int si_code, char *str)
+void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 {
 	siginfo_t info;
 
-	if (notify_die(DIE_TRAP, str, regs, 0,
-		       regs->int_code, si_signo) == NOTIFY_STOP)
-		return;
-
 	if (user_mode(regs)) {
 		info.si_signo = si_signo;
 		info.si_errno = 0;
@@ -90,6 +87,15 @@ static void __kprobes do_trap(struct pt_regs *regs,
         }
 }
 
+static void __kprobes do_trap(struct pt_regs *regs, int si_signo, int si_code,
+			      char *str)
+{
+	if (notify_die(DIE_TRAP, str, regs, 0,
+		       regs->int_code, si_signo) == NOTIFY_STOP)
+		return;
+	do_report_trap(regs, si_signo, si_code, str);
+}
+
 void __kprobes do_per_trap(struct pt_regs *regs)
 {
 	siginfo_t info;
@@ -178,6 +184,7 @@ void __kprobes illegal_op(struct pt_regs *regs)
 	siginfo_t info;
         __u8 opcode[6];
 	__u16 __user *location;
+	int is_uprobe_insn = 0;
 	int signal = 0;
 
 	location = get_trap_ip(regs);
@@ -194,6 +201,10 @@ void __kprobes illegal_op(struct pt_regs *regs)
 				force_sig_info(SIGTRAP, &info, current);
 			} else
 				signal = SIGILL;
+#ifdef CONFIG_UPROBES
+		} else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
+			is_uprobe_insn = 1;
+#endif
 #ifdef CONFIG_MATHEMU
 		} else if (opcode[0] == 0xb3) {
 			if (get_user(*((__u16 *) (opcode+2)), location+1))
@@ -219,11 +230,13 @@ void __kprobes illegal_op(struct pt_regs *regs)
 #endif
 		} else
 			signal = SIGILL;
-	} else {
-		/*
-		 * If we get an illegal op in kernel mode, send it through the
-		 * kprobes notifier. If kprobes doesn't pick it up, SIGILL
-		 */
+	}
+	/*
+	 * We got either an illegal op in kernel mode, or user space trapped
+	 * on a uprobes illegal instruction. See if kprobes or uprobes picks
+	 * it up. If not, SIGILL.
+	 */
+	if (is_uprobe_insn || !user_mode(regs)) {
 		if (notify_die(DIE_BPT, "bpt", regs, 0,
 			       3, SIGTRAP) != NOTIFY_STOP)
 			signal = SIGILL;
@@ -292,6 +305,74 @@ DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
 	      "specification exception");
 #endif
 
+#ifdef CONFIG_64BIT
+int alloc_vector_registers(struct task_struct *tsk)
+{
+	__vector128 *vxrs;
+	int i;
+
+	/* Allocate vector register save area. */
+	vxrs = kzalloc(sizeof(__vector128) * __NUM_VXRS,
+		       GFP_KERNEL|__GFP_REPEAT);
+	if (!vxrs)
+		return -ENOMEM;
+	preempt_disable();
+	if (tsk == current)
+		save_fp_regs(tsk->thread.fp_regs.fprs);
+	/* Copy the 16 floating point registers */
+	for (i = 0; i < 16; i++)
+		*(freg_t *) &vxrs[i] = tsk->thread.fp_regs.fprs[i];
+	tsk->thread.vxrs = vxrs;
+	if (tsk == current) {
+		__ctl_set_bit(0, 17);
+		restore_vx_regs(vxrs);
+	}
+	preempt_enable();
+	return 0;
+}
+
+void vector_exception(struct pt_regs *regs)
+{
+	int si_code, vic;
+
+	if (!MACHINE_HAS_VX) {
+		do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
+		return;
+	}
+
+	/* get vector interrupt code from fpc */
+	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
+	switch (vic) {
+	case 1: /* invalid vector operation */
+		si_code = FPE_FLTINV;
+		break;
+	case 2: /* division by zero */
+		si_code = FPE_FLTDIV;
+		break;
+	case 3: /* overflow */
+		si_code = FPE_FLTOVF;
+		break;
+	case 4: /* underflow */
+		si_code = FPE_FLTUND;
+		break;
+	case 5:	/* inexact */
+		si_code = FPE_FLTRES;
+		break;
+	default: /* unknown cause */
+		si_code = 0;
+	}
+	do_trap(regs, SIGFPE, si_code, "vector exception");
+}
+
+static int __init disable_vector_extension(char *str)
+{
+	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
+	return 1;
+}
+__setup("novx", disable_vector_extension);
+#endif
+
 void data_exception(struct pt_regs *regs)
 {
 	__u16 __user *location;
@@ -357,6 +438,18 @@ void data_exception(struct pt_regs *regs)
                 }
         }
 #endif 
+#ifdef CONFIG_64BIT
+	/* Check for vector register enablement */
+	if (MACHINE_HAS_VX && !current->thread.vxrs &&
+	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
+		alloc_vector_registers(current);
+		/* Vector data exception is suppressing, rewind psw. */
+		regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
+		clear_pt_regs_flag(regs, PIF_PER_TRAP);
+		return;
+	}
+#endif
+
 	if (current->thread.fp_regs.fpc & FPC_DXC_MASK)
 		signal = SIGFPE;
 	else
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
new file mode 100644
index 000000000000..956f4f7a591c
--- /dev/null
+++ b/arch/s390/kernel/uprobes.c
@@ -0,0 +1,332 @@
+/*
+ *  User-space Probes (UProbes) for s390
+ *
+ *    Copyright IBM Corp. 2014
+ *    Author(s): Jan Willeke,
+ */
+
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/uprobes.h>
+#include <linux/compat.h>
+#include <linux/kdebug.h>
+#include <asm/switch_to.h>
+#include <asm/facility.h>
+#include <asm/dis.h>
+#include "entry.h"
+
+#define	UPROBE_TRAP_NR	UINT_MAX
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+			     unsigned long addr)
+{
+	return probe_is_prohibited_opcode(auprobe->insn);
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if (psw_bits(regs->psw).eaba == PSW_AMODE_24BIT)
+		return -EINVAL;
+	if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_AMODE_31BIT)
+		return -EINVAL;
+	clear_pt_regs_flag(regs, PIF_PER_TRAP);
+	auprobe->saved_per = psw_bits(regs->psw).r;
+	auprobe->saved_int_code = regs->int_code;
+	regs->int_code = UPROBE_TRAP_NR;
+	regs->psw.addr = current->utask->xol_vaddr;
+	set_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
+	update_cr_regs(current);
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *tsk)
+{
+	struct pt_regs *regs = task_pt_regs(tsk);
+
+	if (regs->int_code != UPROBE_TRAP_NR)
+		return true;
+	return false;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	int fixup = probe_get_fixup_type(auprobe->insn);
+	struct uprobe_task *utask = current->utask;
+
+	clear_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
+	update_cr_regs(current);
+	psw_bits(regs->psw).r = auprobe->saved_per;
+	regs->int_code = auprobe->saved_int_code;
+
+	if (fixup & FIXUP_PSW_NORMAL)
+		regs->psw.addr += utask->vaddr - utask->xol_vaddr;
+	if (fixup & FIXUP_RETURN_REGISTER) {
+		int reg = (auprobe->insn[0] & 0xf0) >> 4;
+
+		regs->gprs[reg] += utask->vaddr - utask->xol_vaddr;
+	}
+	if (fixup & FIXUP_BRANCH_NOT_TAKEN) {
+		int ilen = insn_length(auprobe->insn[0] >> 8);
+
+		if (regs->psw.addr - utask->xol_vaddr == ilen)
+			regs->psw.addr = utask->vaddr + ilen;
+	}
+	/* If per tracing was active generate trap */
+	if (regs->psw.mask & PSW_MASK_PER)
+		do_per_trap(regs);
+	return 0;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
+				 void *data)
+{
+	struct die_args *args = data;
+	struct pt_regs *regs = args->regs;
+
+	if (!user_mode(regs))
+		return NOTIFY_DONE;
+	if (regs->int_code & 0x200) /* Trap during transaction */
+		return NOTIFY_DONE;
+	switch (val) {
+	case DIE_BPT:
+		if (uprobe_pre_sstep_notifier(regs))
+			return NOTIFY_STOP;
+		break;
+	case DIE_SSTEP:
+		if (uprobe_post_sstep_notifier(regs))
+			return NOTIFY_STOP;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	clear_thread_flag(TIF_UPROBE_SINGLESTEP);
+	regs->int_code = auprobe->saved_int_code;
+	regs->psw.addr = current->utask->vaddr;
+}
+
+unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
+						struct pt_regs *regs)
+{
+	unsigned long orig;
+
+	orig = regs->gprs[14];
+	regs->gprs[14] = trampoline;
+	return orig;
+}
+
+/* Instruction Emulation */
+
+static void adjust_psw_addr(psw_t *psw, unsigned long len)
+{
+	psw->addr = __rewind_psw(*psw, -len);
+}
+
+#define EMU_ILLEGAL_OP		1
+#define EMU_SPECIFICATION	2
+#define EMU_ADDRESSING		3
+
+#define emu_load_ril(ptr, output)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(*(ptr)) input;			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (get_user(input, ptr))			\
+		__rc = EMU_ADDRESSING;			\
+	else						\
+		*(output) = input;			\
+	__rc;						\
+})
+
+#define emu_store_ril(ptr, input)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (put_user(*(input), ptr))		\
+		__rc = EMU_ADDRESSING;			\
+	__rc;						\
+})
+
+#define emu_cmp_ril(regs, ptr, cmp)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(*(ptr)) input;			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (get_user(input, ptr))			\
+		__rc = EMU_ADDRESSING;			\
+	else if (input > *(cmp))			\
+		psw_bits((regs)->psw).cc = 1;		\
+	else if (input < *(cmp))			\
+		psw_bits((regs)->psw).cc = 2;		\
+	else						\
+		psw_bits((regs)->psw).cc = 0;		\
+	__rc;						\
+})
+
+struct insn_ril {
+	u8 opc0;
+	u8 reg	: 4;
+	u8 opc1 : 4;
+	s32 disp;
+} __packed;
+
+union split_register {
+	u64 u64;
+	u32 u32[2];
+	u16 u16[4];
+	s64 s64;
+	s32 s32[2];
+	s16 s16[4];
+};
+
+/*
+ * pc relative instructions are emulated, since parameters may not be
+ * accessible from the xol area due to range limitations.
+ */
+static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	union split_register *rx;
+	struct insn_ril *insn;
+	unsigned int ilen;
+	void *uptr;
+	int rc = 0;
+
+	insn = (struct insn_ril *) &auprobe->insn;
+	rx = (union split_register *) &regs->gprs[insn->reg];
+	uptr = (void *)(regs->psw.addr + (insn->disp * 2));
+	ilen = insn_length(insn->opc0);
+
+	switch (insn->opc0) {
+	case 0xc0:
+		switch (insn->opc1) {
+		case 0x00: /* larl */
+			rx->u64 = (unsigned long)uptr;
+			break;
+		}
+		break;
+	case 0xc4:
+		switch (insn->opc1) {
+		case 0x02: /* llhrl */
+			rc = emu_load_ril((u16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x04: /* lghrl */
+			rc = emu_load_ril((s16 __user *)uptr, &rx->u64);
+			break;
+		case 0x05: /* lhrl */
+			rc = emu_load_ril((s16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x06: /* llghrl */
+			rc = emu_load_ril((u16 __user *)uptr, &rx->u64);
+			break;
+		case 0x08: /* lgrl */
+			rc = emu_load_ril((u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0c: /* lgfrl */
+			rc = emu_load_ril((s32 __user *)uptr, &rx->u64);
+			break;
+		case 0x0d: /* lrl */
+			rc = emu_load_ril((u32 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x0e: /* llgfrl */
+			rc = emu_load_ril((u32 __user *)uptr, &rx->u64);
+			break;
+		case 0x07: /* sthrl */
+			rc = emu_store_ril((u16 __user *)uptr, &rx->u16[3]);
+			break;
+		case 0x0b: /* stgrl */
+			rc = emu_store_ril((u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0f: /* strl */
+			rc = emu_store_ril((u32 __user *)uptr, &rx->u32[1]);
+			break;
+		}
+		break;
+	case 0xc6:
+		switch (insn->opc1) {
+		case 0x02: /* pfdrl */
+			if (!test_facility(34))
+				rc = EMU_ILLEGAL_OP;
+			break;
+		case 0x04: /* cghrl */
+			rc = emu_cmp_ril(regs, (s16 __user *)uptr, &rx->s64);
+			break;
+		case 0x05: /* chrl */
+			rc = emu_cmp_ril(regs, (s16 __user *)uptr, &rx->s32[1]);
+			break;
+		case 0x06: /* clghrl */
+			rc = emu_cmp_ril(regs, (u16 __user *)uptr, &rx->u64);
+			break;
+		case 0x07: /* clhrl */
+			rc = emu_cmp_ril(regs, (u16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x08: /* cgrl */
+			rc = emu_cmp_ril(regs, (s64 __user *)uptr, &rx->s64);
+			break;
+		case 0x0a: /* clgrl */
+			rc = emu_cmp_ril(regs, (u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0c: /* cgfrl */
+			rc = emu_cmp_ril(regs, (s32 __user *)uptr, &rx->s64);
+			break;
+		case 0x0d: /* crl */
+			rc = emu_cmp_ril(regs, (s32 __user *)uptr, &rx->s32[1]);
+			break;
+		case 0x0e: /* clgfrl */
+			rc = emu_cmp_ril(regs, (u32 __user *)uptr, &rx->u64);
+			break;
+		case 0x0f: /* clrl */
+			rc = emu_cmp_ril(regs, (u32 __user *)uptr, &rx->u32[1]);
+			break;
+		}
+		break;
+	}
+	adjust_psw_addr(&regs->psw, ilen);
+	switch (rc) {
+	case EMU_ILLEGAL_OP:
+		regs->int_code = ilen << 16 | 0x0001;
+		do_report_trap(regs, SIGILL, ILL_ILLOPC, NULL);
+		break;
+	case EMU_SPECIFICATION:
+		regs->int_code = ilen << 16 | 0x0006;
+		do_report_trap(regs, SIGILL, ILL_ILLOPC , NULL);
+		break;
+	case EMU_ADDRESSING:
+		regs->int_code = ilen << 16 | 0x0005;
+		do_report_trap(regs, SIGSEGV, SEGV_MAPERR, NULL);
+		break;
+	}
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if ((psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) ||
+	    ((psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) &&
+	     !is_compat_task())) {
+		regs->psw.addr = __rewind_psw(regs->psw, UPROBE_SWBP_INSN_SIZE);
+		do_report_trap(regs, SIGILL, ILL_ILLADR, NULL);
+		return true;
+	}
+	if (probe_is_insn_relative_long(auprobe->insn)) {
+		handle_insn_ril(auprobe, regs);
+		return true;
+	}
+	return false;
+}
diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S
index 36aaa25d05da..eca3f001f081 100644
--- a/arch/s390/kernel/vdso32/clock_getres.S
+++ b/arch/s390/kernel/vdso32/clock_getres.S
@@ -19,14 +19,20 @@
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
 	.cfi_startproc
+	basr	%r1,0
+	la	%r1,4f-.(%r1)
 	chi	%r2,__CLOCK_REALTIME
 	je	0f
 	chi	%r2,__CLOCK_MONOTONIC
+	je	0f
+	la	%r1,5f-4f(%r1)
+	chi	%r2,__CLOCK_REALTIME_COARSE
+	je	0f
+	chi	%r2,__CLOCK_MONOTONIC_COARSE
 	jne	3f
 0:	ltr	%r3,%r3
 	jz	2f				/* res == NULL */
-	basr	%r1,0
-1:	l	%r0,4f-1b(%r1)
+1:	l	%r0,0(%r1)
 	xc	0(4,%r3),0(%r3)			/* set tp->tv_sec to zero */
 	st	%r0,4(%r3)			/* store tp->tv_usec */
 2:	lhi	%r2,0
@@ -35,5 +41,6 @@ __kernel_clock_getres:
 	svc	0
 	br	%r14
 4:	.long	__CLOCK_REALTIME_RES
+5:	.long	__CLOCK_COARSE_RES
 	.cfi_endproc
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index 7cf18f8d4cb4..48c2206a3956 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -21,8 +21,12 @@ __kernel_clock_gettime:
 	.cfi_startproc
 	basr	%r5,0
 0:	al	%r5,21f-0b(%r5)			/* get &_vdso_data */
+	chi	%r2,__CLOCK_REALTIME_COARSE
+	je	10f
 	chi	%r2,__CLOCK_REALTIME
 	je	11f
+	chi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	9f
 	chi	%r2,__CLOCK_MONOTONIC
 	jne	19f
 
@@ -30,8 +34,8 @@ __kernel_clock_gettime:
 1:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	1b
-	stck	24(%r15)			/* Store TOD clock */
-	lm	%r0,%r1,24(%r15)
+	stcke	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,25(%r15)
 	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,2f
@@ -68,12 +72,32 @@ __kernel_clock_gettime:
 	lhi	%r2,0
 	br	%r14
 
+	/* CLOCK_MONOTONIC_COARSE */
+9:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	9b
+	l	%r2,__VDSO_WTOM_CRS_SEC+4(%r5)
+	l	%r1,__VDSO_WTOM_CRS_NSEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	9b
+	j	8b
+
+	/* CLOCK_REALTIME_COARSE */
+10:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	10b
+	l	%r2,__VDSO_XTIME_CRS_SEC+4(%r5)
+	l	%r1,__VDSO_XTIME_CRS_NSEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	10b
+	j	17f
+
 	/* CLOCK_REALTIME */
 11:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	11b
-	stck	24(%r15)			/* Store TOD clock */
-	lm	%r0,%r1,24(%r15)
+	stcke	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,25(%r15)
 	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,12f
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index fd621a950f7c..60def5f562db 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -29,8 +29,8 @@ __kernel_gettimeofday:
 	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	1b
-	stck	24(%r15)			/* Store TOD clock */
-	lm	%r0,%r1,24(%r15)
+	stcke	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,25(%r15)
 	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,3f
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index 34deba7c7ed1..c8513deb8c66 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -19,6 +19,12 @@
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
 	.cfi_startproc
+	larl	%r1,4f
+	cghi	%r2,__CLOCK_REALTIME_COARSE
+	je	0f
+	cghi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	0f
+	larl	%r1,3f
 	cghi	%r2,__CLOCK_REALTIME
 	je	0f
 	cghi	%r2,__CLOCK_MONOTONIC
@@ -32,7 +38,6 @@ __kernel_clock_getres:
 	jz	2f
 0:	ltgr	%r3,%r3
 	jz	1f				/* res == NULL */
-	larl	%r1,3f
 	lg	%r0,0(%r1)
 	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
 	stg	%r0,8(%r3)			/* store tp->tv_usec */
@@ -42,5 +47,6 @@ __kernel_clock_getres:
 	svc	0
 	br	%r14
 3:	.quad	__CLOCK_REALTIME_RES
+4:	.quad	__CLOCK_COARSE_RES
 	.cfi_endproc
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index 3f34e09db5f4..9d9761f8e110 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -20,12 +20,16 @@
 __kernel_clock_gettime:
 	.cfi_startproc
 	larl	%r5,_vdso_data
+	cghi	%r2,__CLOCK_REALTIME_COARSE
+	je	4f
 	cghi	%r2,__CLOCK_REALTIME
 	je	5f
 	cghi	%r2,__CLOCK_THREAD_CPUTIME_ID
 	je	9f
 	cghi	%r2,-2		/* Per-thread CPUCLOCK with PID=0, VIRT=1 */
 	je	9f
+	cghi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	3f
 	cghi	%r2,__CLOCK_MONOTONIC
 	jne	12f
 
@@ -33,10 +37,10 @@ __kernel_clock_gettime:
 0:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	0b
-	stck	48(%r15)			/* Store TOD clock */
+	stcke	48(%r15)			/* Store TOD clock */
 	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
 	lg	%r0,__VDSO_WTOM_SEC(%r5)
-	lg	%r1,48(%r15)
+	lg	%r1,49(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_WTOM_NSEC(%r5)
@@ -54,13 +58,33 @@ __kernel_clock_gettime:
 	lghi	%r2,0
 	br	%r14
 
+	/* CLOCK_MONOTONIC_COARSE */
+3:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	3b
+	lg	%r0,__VDSO_WTOM_CRS_SEC(%r5)
+	lg	%r1,__VDSO_WTOM_CRS_NSEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	3b
+	j	2b
+
+	/* CLOCK_REALTIME_COARSE */
+4:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	4b
+	lg	%r0,__VDSO_XTIME_CRS_SEC(%r5)
+	lg	%r1,__VDSO_XTIME_CRS_NSEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	4b
+	j	7f
+
 	/* CLOCK_REALTIME */
 5:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	5b
-	stck	48(%r15)			/* Store TOD clock */
+	stcke	48(%r15)			/* Store TOD clock */
 	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
-	lg	%r1,48(%r15)
+	lg	%r1,49(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index d0860d1d0ccc..7a344995a97f 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -28,8 +28,8 @@ __kernel_gettimeofday:
 	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	0b
-	stck	48(%r15)			/* Store TOD clock */
-	lg	%r1,48(%r15)
+	stcke	48(%r15)			/* Store TOD clock */
+	lg	%r1,49(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 8c34363d6f1e..416f2a323ba5 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -6,27 +6,18 @@
  */
 
 #include <linux/kernel_stat.h>
-#include <linux/notifier.h>
-#include <linux/kprobes.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
 
-#include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/vtimer.h>
 #include <asm/vtime.h>
-#include <asm/irq.h>
-#include "entry.h"
 
 static void virt_timer_expire(void);
 
-DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
-
 static LIST_HEAD(virt_timer_list);
 static DEFINE_SPINLOCK(virt_timer_lock);
 static atomic64_t virt_timer_current;
@@ -152,49 +143,6 @@ void vtime_account_system(struct task_struct *tsk)
 __attribute__((alias("vtime_account_irq_enter")));
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
-void __kprobes vtime_stop_cpu(void)
-{
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
-	unsigned long long idle_time;
-	unsigned long psw_mask;
-
-	trace_hardirqs_on();
-
-	/* Wait for external, I/O or machine check interrupt. */
-	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT |
-		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	idle->nohz_delay = 0;
-
-	/* Call the assembler magic in entry.S */
-	psw_idle(idle, psw_mask);
-
-	/* Account time spent with enabled wait psw loaded as idle time. */
-	idle->sequence++;
-	smp_wmb();
-	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
-	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
-	idle->idle_time += idle_time;
-	idle->idle_count++;
-	account_idle_time(idle_time);
-	smp_wmb();
-	idle->sequence++;
-}
-
-cputime64_t s390_get_idle_time(int cpu)
-{
-	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit;
-	unsigned int sequence;
-
-	do {
-		now = get_tod_clock();
-		sequence = ACCESS_ONCE(idle->sequence);
-		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
-		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
-	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
-}
-
 /*
  * Sorted add to a list. List is linear searched until first bigger
  * element is found.
@@ -372,31 +320,8 @@ EXPORT_SYMBOL(del_virt_timer);
 /*
  * Start the virtual CPU timer on the current CPU.
  */
-void init_cpu_vtimer(void)
+void vtime_init(void)
 {
 	/* set initial cpu timer */
 	set_vtimer(VTIMER_MAX_SLICE);
 }
-
-static int s390_nohz_notify(struct notifier_block *self, unsigned long action,
-			    void *hcpu)
-{
-	struct s390_idle_data *idle;
-	long cpu = (long) hcpu;
-
-	idle = &per_cpu(s390_idle, cpu);
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DYING:
-		idle->nohz_delay = 0;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-void __init vtime_init(void)
-{
-	/* Enable cpu timer interrupts on the boot cpu. */
-	init_cpu_vtimer();
-	cpu_notifier(s390_nohz_notify, 0);
-}
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index c6d752e8bf28..a01df233856f 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -6,3 +6,5 @@ lib-y += delay.o string.o uaccess.o find.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o
 obj-$(CONFIG_64BIT) += mem64.o
 lib-$(CONFIG_SMP) += spinlock.o
+lib-$(CONFIG_KPROBES) += probes.o
+lib-$(CONFIG_UPROBES) += probes.o
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index a9f3d0042d58..16dc42d83f93 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -43,7 +43,7 @@ static void __udelay_disabled(unsigned long long usecs)
 	lockdep_off();
 	do {
 		set_clock_comparator(end);
-		vtime_stop_cpu();
+		enabled_wait();
 	} while (get_tod_clock_fast() < end);
 	lockdep_on();
 	__ctl_load(cr0, 0, 0);
@@ -62,7 +62,7 @@ static void __udelay_enabled(unsigned long long usecs)
 			clock_saved = local_tick_disable();
 			set_clock_comparator(end);
 		}
-		vtime_stop_cpu();
+		enabled_wait();
 		if (clock_saved)
 			local_tick_enable(clock_saved);
 	} while (get_tod_clock_fast() < end);
diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c
new file mode 100644
index 000000000000..c5d64a099719
--- /dev/null
+++ b/arch/s390/lib/probes.c
@@ -0,0 +1,159 @@
+/*
+ *    Common helper functions for kprobes and uprobes
+ *
+ *    Copyright IBM Corp. 2014
+ */
+
+#include <linux/kprobes.h>
+#include <asm/dis.h>
+
+int probe_is_prohibited_opcode(u16 *insn)
+{
+	if (!is_known_insn((unsigned char *)insn))
+		return -EINVAL;
+	switch (insn[0] >> 8) {
+	case 0x0c:	/* bassm */
+	case 0x0b:	/* bsm	 */
+	case 0x83:	/* diag  */
+	case 0x44:	/* ex	 */
+	case 0xac:	/* stnsm */
+	case 0xad:	/* stosm */
+		return -EINVAL;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x00: /* exrl   */
+			return -EINVAL;
+		}
+	}
+	switch (insn[0]) {
+	case 0x0101:	/* pr	 */
+	case 0xb25a:	/* bsa	 */
+	case 0xb240:	/* bakr  */
+	case 0xb258:	/* bsg	 */
+	case 0xb218:	/* pc	 */
+	case 0xb228:	/* pt	 */
+	case 0xb98d:	/* epsw	 */
+	case 0xe560:	/* tbegin */
+	case 0xe561:	/* tbeginc */
+	case 0xb2f8:	/* tend	 */
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int probe_get_fixup_type(u16 *insn)
+{
+	/* default fixup method */
+	int fixup = FIXUP_PSW_NORMAL;
+
+	switch (insn[0] >> 8) {
+	case 0x05:	/* balr	*/
+	case 0x0d:	/* basr */
+		fixup = FIXUP_RETURN_REGISTER;
+		/* if r2 = 0, no branch will be taken */
+		if ((insn[0] & 0x0f) == 0)
+			fixup |= FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0x06:	/* bctr	*/
+	case 0x07:	/* bcr	*/
+		fixup = FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0x45:	/* bal	*/
+	case 0x4d:	/* bas	*/
+		fixup = FIXUP_RETURN_REGISTER;
+		break;
+	case 0x47:	/* bc	*/
+	case 0x46:	/* bct	*/
+	case 0x86:	/* bxh	*/
+	case 0x87:	/* bxle	*/
+		fixup = FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0x82:	/* lpsw	*/
+		fixup = FIXUP_NOT_REQUIRED;
+		break;
+	case 0xb2:	/* lpswe */
+		if ((insn[0] & 0xff) == 0xb2)
+			fixup = FIXUP_NOT_REQUIRED;
+		break;
+	case 0xa7:	/* bras	*/
+		if ((insn[0] & 0x0f) == 0x05)
+			fixup |= FIXUP_RETURN_REGISTER;
+		break;
+	case 0xc0:
+		if ((insn[0] & 0x0f) == 0x05)	/* brasl */
+			fixup |= FIXUP_RETURN_REGISTER;
+		break;
+	case 0xeb:
+		switch (insn[2] & 0xff) {
+		case 0x44: /* bxhg  */
+		case 0x45: /* bxleg */
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+			break;
+		}
+		break;
+	case 0xe3:	/* bctg	*/
+		if ((insn[2] & 0xff) == 0x46)
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0xec:
+		switch (insn[2] & 0xff) {
+		case 0xe5: /* clgrb */
+		case 0xe6: /* cgrb  */
+		case 0xf6: /* crb   */
+		case 0xf7: /* clrb  */
+		case 0xfc: /* cgib  */
+		case 0xfd: /* cglib */
+		case 0xfe: /* cib   */
+		case 0xff: /* clib  */
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+			break;
+		}
+		break;
+	}
+	return fixup;
+}
+
+int probe_is_insn_relative_long(u16 *insn)
+{
+	/* Check if we have a RIL-b or RIL-c format instruction which
+	 * we need to modify in order to avoid instruction emulation. */
+	switch (insn[0] >> 8) {
+	case 0xc0:
+		if ((insn[0] & 0x0f) == 0x00) /* larl */
+			return true;
+		break;
+	case 0xc4:
+		switch (insn[0] & 0x0f) {
+		case 0x02: /* llhrl  */
+		case 0x04: /* lghrl  */
+		case 0x05: /* lhrl   */
+		case 0x06: /* llghrl */
+		case 0x07: /* sthrl  */
+		case 0x08: /* lgrl   */
+		case 0x0b: /* stgrl  */
+		case 0x0c: /* lgfrl  */
+		case 0x0d: /* lrl    */
+		case 0x0e: /* llgfrl */
+		case 0x0f: /* strl   */
+			return true;
+		}
+		break;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x02: /* pfdrl  */
+		case 0x04: /* cghrl  */
+		case 0x05: /* chrl   */
+		case 0x06: /* clghrl */
+		case 0x07: /* clhrl  */
+		case 0x08: /* cgrl   */
+		case 0x0a: /* clgrl  */
+		case 0x0c: /* cgfrl  */
+		case 0x0d: /* crl    */
+		case 0x0e: /* clgfrl */
+		case 0x0f: /* clrl   */
+			return true;
+		}
+		break;
+	}
+	return false;
+}
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 5b0e445bc3f3..034a35a3e9c1 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -98,17 +98,6 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 }
 EXPORT_SYMBOL(arch_spin_lock_wait_flags);
 
-void arch_spin_relax(arch_spinlock_t *lp)
-{
-	unsigned int cpu = lp->lock;
-	if (cpu != 0) {
-		if (MACHINE_IS_VM || MACHINE_IS_KVM ||
-		    !smp_vcpu_scheduled(~cpu))
-			smp_yield_cpu(~cpu);
-	}
-}
-EXPORT_SYMBOL(arch_spin_relax);
-
 int arch_spin_trylock_retry(arch_spinlock_t *lp)
 {
 	int count;
@@ -122,15 +111,21 @@ EXPORT_SYMBOL(arch_spin_trylock_retry);
 
 void _raw_read_lock_wait(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	unsigned int owner, old;
 	int count = spin_retry;
 
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+	__RAW_LOCK(&rw->lock, -1, __RAW_OP_ADD);
+#endif
+	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			smp_yield();
+			if (owner && !smp_vcpu_scheduled(~owner))
+				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
 		old = ACCESS_ONCE(rw->lock);
+		owner = ACCESS_ONCE(rw->owner);
 		if ((int) old < 0)
 			continue;
 		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
@@ -139,28 +134,6 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 }
 EXPORT_SYMBOL(_raw_read_lock_wait);
 
-void _raw_read_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
-{
-	unsigned int old;
-	int count = spin_retry;
-
-	local_irq_restore(flags);
-	while (1) {
-		if (count-- <= 0) {
-			smp_yield();
-			count = spin_retry;
-		}
-		old = ACCESS_ONCE(rw->lock);
-		if ((int) old < 0)
-			continue;
-		local_irq_disable();
-		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
-			return;
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL(_raw_read_lock_wait_flags);
-
 int _raw_read_trylock_retry(arch_rwlock_t *rw)
 {
 	unsigned int old;
@@ -177,46 +150,62 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw)
 }
 EXPORT_SYMBOL(_raw_read_trylock_retry);
 
-void _raw_write_lock_wait(arch_rwlock_t *rw)
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+
+void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev)
 {
-	unsigned int old;
+	unsigned int owner, old;
 	int count = spin_retry;
 
+	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			smp_yield();
+			if (owner && !smp_vcpu_scheduled(~owner))
+				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
 		old = ACCESS_ONCE(rw->lock);
-		if (old)
-			continue;
-		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
-			return;
+		owner = ACCESS_ONCE(rw->owner);
+		smp_rmb();
+		if ((int) old >= 0) {
+			prev = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
+			old = prev;
+		}
+		if ((old & 0x7fffffff) == 0 && (int) prev >= 0)
+			break;
 	}
 }
 EXPORT_SYMBOL(_raw_write_lock_wait);
 
-void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
+#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+void _raw_write_lock_wait(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	unsigned int owner, old, prev;
 	int count = spin_retry;
 
-	local_irq_restore(flags);
+	prev = 0x80000000;
+	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			smp_yield();
+			if (owner && !smp_vcpu_scheduled(~owner))
+				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
 		old = ACCESS_ONCE(rw->lock);
-		if (old)
-			continue;
-		local_irq_disable();
-		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
-			return;
-		local_irq_restore(flags);
+		owner = ACCESS_ONCE(rw->owner);
+		if ((int) old >= 0 &&
+		    _raw_compare_and_swap(&rw->lock, old, old | 0x80000000))
+			prev = old;
+		else
+			smp_rmb();
+		if ((old & 0x7fffffff) == 0 && (int) prev >= 0)
+			break;
 	}
 }
-EXPORT_SYMBOL(_raw_write_lock_wait_flags);
+EXPORT_SYMBOL(_raw_write_lock_wait);
+
+#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
 int _raw_write_trylock_retry(arch_rwlock_t *rw)
 {
@@ -233,3 +222,13 @@ int _raw_write_trylock_retry(arch_rwlock_t *rw)
 	return 0;
 }
 EXPORT_SYMBOL(_raw_write_trylock_retry);
+
+void arch_lock_relax(unsigned int cpu)
+{
+	if (!cpu)
+		return;
+	if (MACHINE_IS_LPAR && smp_vcpu_scheduled(~cpu))
+		return;
+	smp_yield_cpu(~cpu);
+}
+EXPORT_SYMBOL(arch_lock_relax);
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 46d517c3c763..d46cadeda204 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -54,7 +54,6 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level)
 		return;
 	}
 	seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW ");
-	seq_printf(m, "%s", pr & _PAGE_CO ? "CO " : "   ");
 	seq_putc(m, '\n');
 }
 
@@ -129,7 +128,7 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st,
 }
 
 #ifdef CONFIG_64BIT
-#define _PMD_PROT_MASK (_SEGMENT_ENTRY_PROTECT | _SEGMENT_ENTRY_CO)
+#define _PMD_PROT_MASK _SEGMENT_ENTRY_PROTECT
 #else
 #define _PMD_PROT_MASK 0
 #endif
@@ -157,7 +156,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st,
 }
 
 #ifdef CONFIG_64BIT
-#define _PUD_PROT_MASK (_REGION3_ENTRY_RO | _REGION3_ENTRY_CO)
+#define _PUD_PROT_MASK _REGION3_ENTRY_RO
 #else
 #define _PUD_PROT_MASK 0
 #endif
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 389bc17934b7..3c80d2e38f03 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -88,7 +88,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
 		pmd_val(pmd) |= pte_page(pte)[1].index;
 	} else
-		pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO;
+		pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
 	*(pmd_t *) ptep = pmd;
 }
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 8400f494623f..3fef3b299665 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <asm/cacheflush.h>
+#include <asm/facility.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 
@@ -103,27 +104,50 @@ int set_memory_x(unsigned long addr, int numpages)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
+
+static void ipte_range(pte_t *pte, unsigned long address, int nr)
+{
+	int i;
+
+	if (test_facility(13) && IS_ENABLED(CONFIG_64BIT)) {
+		__ptep_ipte_range(address, nr - 1, pte);
+		return;
+	}
+	for (i = 0; i < nr; i++) {
+		__ptep_ipte(address, pte);
+		address += PAGE_SIZE;
+		pte++;
+	}
+}
+
 void kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long address;
+	int nr, i, j;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
-	int i;
 
-	for (i = 0; i < numpages; i++) {
+	for (i = 0; i < numpages;) {
 		address = page_to_phys(page + i);
 		pgd = pgd_offset_k(address);
 		pud = pud_offset(pgd, address);
 		pmd = pmd_offset(pud, address);
 		pte = pte_offset_kernel(pmd, address);
-		if (!enable) {
-			__ptep_ipte(address, pte);
-			pte_val(*pte) = _PAGE_INVALID;
-			continue;
+		nr = (unsigned long)pte >> ilog2(sizeof(long));
+		nr = PTRS_PER_PTE - (nr & (PTRS_PER_PTE - 1));
+		nr = min(numpages - i, nr);
+		if (enable) {
+			for (j = 0; j < nr; j++) {
+				pte_val(*pte) = __pa(address);
+				address += PAGE_SIZE;
+				pte++;
+			}
+		} else {
+			ipte_range(pte, address, nr);
 		}
-		pte_val(*pte) = __pa(address);
+		i += nr;
 	}
 }
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index fdbd7888cb07..b1593c2f751a 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -236,8 +236,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 				if (!new_page)
 					goto out;
 				pmd_val(*pm_dir) = __pa(new_page) |
-					_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
-					_SEGMENT_ENTRY_CO;
+					_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE;
 				address = (address + PMD_SIZE) & PMD_MASK;
 				continue;
 			}
@@ -253,9 +252,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
 		if (pte_none(*pt_dir)) {
-			unsigned long new_page;
+			void *new_page;
 
-			new_page =__pa(vmem_alloc_pages(0));
+			new_page = vmemmap_alloc_block(PAGE_SIZE, node);
 			if (!new_page)
 				goto out;
 			pte_val(*pt_dir) =
@@ -263,7 +262,6 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 		}
 		address += PAGE_SIZE;
 	}
-	memset((void *)start, 0, end - start);
 	ret = 0;
 out:
 	return ret;
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index e53c6f268807..ff9b4eb34589 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -178,7 +178,7 @@ static int smp_ctl_qsi(int cpu)
 static void hws_ext_handler(struct ext_code ext_code,
 			    unsigned int param32, unsigned long param64)
 {
-	struct hws_cpu_buffer *cb = &__get_cpu_var(sampler_cpu_buffer);
+	struct hws_cpu_buffer *cb = this_cpu_ptr(&sampler_cpu_buffer);
 
 	if (!(param32 & CPU_MF_INT_SF_MASK))
 		return;
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 7d80df4f09cb..95be3b0ce0ac 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SH_SYSCALL_32_H
 #define __ASM_SH_SYSCALL_32_H
 
+#include <uapi/linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/err.h>
@@ -93,4 +94,13 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	}
 }
 
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_SH;
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	arch |= __AUDIT_ARCH_LE;
+#endif
+	return arch;
+}
 #endif /* __ASM_SH_SYSCALL_32_H */
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index c3561ca72bee..c6a797b90b80 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SH_SYSCALL_64_H
 #define __ASM_SH_SYSCALL_64_H
 
+#include <uapi/linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <asm/ptrace.h>
@@ -61,4 +62,17 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->regs[2 + i], args, n * sizeof(args[0]));
 }
 
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_SH;
+
+#ifdef CONFIG_64BIT
+	arch |= __AUDIT_ARCH_64BIT;
+#endif
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	arch |= __AUDIT_ARCH_LE;
+#endif
+
+	return arch;
+}
 #endif /* __ASM_SH_SYSCALL_64_H */
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 668c81631c08..c1a6b89bfe70 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -484,17 +484,6 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-static inline int audit_arch(void)
-{
-	int arch = EM_SH;
-
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-	arch |= __AUDIT_ARCH_LE;
-#endif
-
-	return arch;
-}
-
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
@@ -513,8 +502,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[0]);
 
-	audit_syscall_entry(audit_arch(), regs->regs[3],
-			    regs->regs[4], regs->regs[5],
+	audit_syscall_entry(regs->regs[3], regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
 	return ret ?: regs->regs[0];
diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c
index af90339dadcd..5cea973a65b2 100644
--- a/arch/sh/kernel/ptrace_64.c
+++ b/arch/sh/kernel/ptrace_64.c
@@ -504,20 +504,6 @@ asmlinkage int sh64_ptrace(long request, long pid,
 	return sys_ptrace(request, pid, addr, data);
 }
 
-static inline int audit_arch(void)
-{
-	int arch = EM_SH;
-
-#ifdef CONFIG_64BIT
-	arch |= __AUDIT_ARCH_64BIT;
-#endif
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-	arch |= __AUDIT_ARCH_LE;
-#endif
-
-	return arch;
-}
-
 asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long long ret = 0;
@@ -536,8 +522,7 @@ asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[9]);
 
-	audit_syscall_entry(audit_arch(), regs->regs[1],
-			    regs->regs[2], regs->regs[3],
+	audit_syscall_entry(regs->regs[1], regs->regs[2], regs->regs[3],
 			    regs->regs[4], regs->regs[5]);
 
 	return ret ?: regs->regs[9];
diff --git a/arch/sparc/include/asm/cpudata_32.h b/arch/sparc/include/asm/cpudata_32.h
index 0300d94c25b3..05f366379f53 100644
--- a/arch/sparc/include/asm/cpudata_32.h
+++ b/arch/sparc/include/asm/cpudata_32.h
@@ -26,6 +26,6 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu) per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data() __get_cpu_var(__cpu_data)
+#define local_cpu_data() (*this_cpu_ptr(&__cpu_data))
 
 #endif /* _SPARC_CPUDATA_H */
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 0e594076912c..a6e424d185d0 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -30,7 +30,7 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data()	__get_cpu_var(__cpu_data)
+#define local_cpu_data()	(*this_cpu_ptr(&__cpu_data))
 
 #endif /* !(__ASSEMBLY__) */
 
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 025a02ad2e31..49f71fd5b56e 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -1,9 +1,11 @@
 #ifndef __ASM_SPARC_SYSCALL_H
 #define __ASM_SPARC_SYSCALL_H
 
+#include <uapi/linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <asm/ptrace.h>
+#include <asm/thread_info.h>
 
 /*
  * The syscall table always contains 32 bit pointers since we know that the
@@ -124,4 +126,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 		regs->u_regs[UREG_I0 + i + j] = args[j];
 }
 
+static inline int syscall_get_arch(void)
+{
+	return is_32bit_task() ? AUDIT_ARCH_SPARC : AUDIT_ARCH_SPARC64;
+}
+
 #endif /* __ASM_SPARC_SYSCALL_H */
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index 96efa7adc223..025c98446b1e 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -130,6 +130,8 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define _TIF_DO_NOTIFY_RESUME_MASK	(_TIF_NOTIFY_RESUME | \
 					 _TIF_SIGPENDING)
 
+#define is_32bit_task()	(1)
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index f85dc8512ab3..798f0279a4b5 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -63,7 +63,8 @@ struct thread_info {
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
-	unsigned long		fpregs[0] __attribute__ ((aligned(64)));
+	unsigned long		fpregs[(7 * 256) / sizeof(unsigned long)]
+		__attribute__ ((aligned(64)));
 };
 
 #endif /* !(__ASSEMBLY__) */
@@ -220,6 +221,8 @@ register struct thread_info *current_thread_info_reg asm("g6");
 				 _TIF_NEED_RESCHED)
 #define _TIF_DO_NOTIFY_RESUME_MASK	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING)
 
+#define is_32bit_task()	(test_thread_flag(TIF_32BIT))
+
 /*
  * Thread-synchronous status.
  *
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index b26673759283..1f0aa2024e94 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -39,6 +39,14 @@
 297:	wr		%o5, FPRS_FEF, %fprs;		\
 298:
 
+#define VISEntryHalfFast(fail_label)			\
+	rd		%fprs, %o5;			\
+	andcc		%o5, FPRS_FEF, %g0;		\
+	be,pt		%icc, 297f;			\
+	 nop;						\
+	ba,a,pt		%xcc, fail_label;		\
+297:	wr		%o5, FPRS_FEF, %fprs;
+
 #define VISExitHalf					\
 	wr		%o5, 0, %fprs;
 
diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index b2c2c5be281c..d668ca149e64 100644
--- a/arch/sparc/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
@@ -24,11 +24,11 @@
 	mov		TLB_TAG_ACCESS, %g4		! For reload of vaddr
 
 /* PROT ** ICACHE line 2: More real fault processing */
+	ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
 	bgu,pn		%xcc, winfix_trampoline		! Yes, perform winfixup
-	 ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
-	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
 	 mov		FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
-	nop
+	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
+	 nop
 	nop
 	nop
 	nop
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 98d712843413..cd83be527586 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -83,7 +83,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_orig_tnpc = kcb->prev_kprobe.orig_tnpc;
 	kcb->kprobe_orig_tstate_pil = kcb->prev_kprobe.orig_tstate_pil;
@@ -92,7 +92,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 				struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_orig_tnpc = regs->tnpc;
 	kcb->kprobe_orig_tstate_pil = (regs->tstate & TSTATE_PIL);
 }
@@ -155,7 +155,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 018ef11f57df..ea2bad306f93 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -343,7 +343,7 @@ static void leon_ipi_resched(int cpu)
 
 void leonsmp_ipi_interrupt(void)
 {
-	struct leon_ipi_work *work = &__get_cpu_var(leon_ipi_work);
+	struct leon_ipi_work *work = this_cpu_ptr(&leon_ipi_work);
 
 	if (work->single) {
 		work->single = 0;
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 5b1151dcba13..a9973bb4a1b2 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -100,20 +100,20 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
 
 	sum = local_cpu_data().irq0_irqs;
-	if (__get_cpu_var(nmi_touch)) {
-		__get_cpu_var(nmi_touch) = 0;
+	if (__this_cpu_read(nmi_touch)) {
+		__this_cpu_write(nmi_touch, 0);
 		touched = 1;
 	}
-	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+	if (!touched && __this_cpu_read(last_irq_sum) == sum) {
 		__this_cpu_inc(alert_counter);
 		if (__this_cpu_read(alert_counter) == 30 * nmi_hz)
 			die_nmi("BUG: NMI Watchdog detected LOCKUP",
 				regs, panic_on_timeout);
 	} else {
-		__get_cpu_var(last_irq_sum) = sum;
+		__this_cpu_write(last_irq_sum, sum);
 		__this_cpu_write(alert_counter, 0);
 	}
-	if (__get_cpu_var(wd_enabled)) {
+	if (__this_cpu_read(wd_enabled)) {
 		pcr_ops->write_pic(0, pcr_ops->nmi_picl_value(nmi_hz));
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_enable);
 	}
@@ -154,7 +154,7 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 void stop_nmi_watchdog(void *unused)
 {
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
-	__get_cpu_var(wd_enabled) = 0;
+	__this_cpu_write(wd_enabled, 0);
 	atomic_dec(&nmi_active);
 }
 
@@ -207,7 +207,7 @@ error:
 
 void start_nmi_watchdog(void *unused)
 {
-	__get_cpu_var(wd_enabled) = 1;
+	__this_cpu_write(wd_enabled, 1);
 	atomic_inc(&nmi_active);
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
@@ -218,7 +218,7 @@ void start_nmi_watchdog(void *unused)
 
 static void nmi_adjust_hz_one(void *unused)
 {
-	if (!__get_cpu_var(wd_enabled))
+	if (!__this_cpu_read(wd_enabled))
 		return;
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index d07f6b29aed8..49d33b178793 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -48,7 +48,7 @@ static int iommu_batch_initialized;
 /* Interrupts must be disabled.  */
 static inline void iommu_batch_start(struct device *dev, unsigned long prot, unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	p->dev		= dev;
 	p->prot		= prot;
@@ -94,7 +94,7 @@ static long iommu_batch_flush(struct iommu_batch *p)
 
 static inline void iommu_batch_new_entry(unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	if (p->entry + p->npages == entry)
 		return;
@@ -106,7 +106,7 @@ static inline void iommu_batch_new_entry(unsigned long entry)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_add(u64 phys_page)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
@@ -120,7 +120,7 @@ static inline long iommu_batch_add(u64 phys_page)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_end(void)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index c9759ad3f34a..46a5e4508752 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1013,7 +1013,7 @@ static void update_pcrs_for_enable(struct cpu_hw_events *cpuc)
 
 static void sparc_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (cpuc->enabled)
@@ -1031,7 +1031,7 @@ static void sparc_pmu_enable(struct pmu *pmu)
 
 static void sparc_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (!cpuc->enabled)
@@ -1065,7 +1065,7 @@ static int active_event_index(struct cpu_hw_events *cpuc,
 
 static void sparc_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (flags & PERF_EF_RELOAD) {
@@ -1080,7 +1080,7 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
 
 static void sparc_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -1096,7 +1096,7 @@ static void sparc_pmu_stop(struct perf_event *event, int flags)
 
 static void sparc_pmu_del(struct perf_event *event, int _flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 	int i;
 
@@ -1133,7 +1133,7 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 
 static void sparc_pmu_read(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -1145,7 +1145,7 @@ static DEFINE_MUTEX(pmc_grab_mutex);
 
 static void perf_stop_nmi_watchdog(void *unused)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	stop_nmi_watchdog(NULL);
@@ -1356,7 +1356,7 @@ static int collect_events(struct perf_event *group, int max_count,
 
 static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
@@ -1498,7 +1498,7 @@ static int sparc_pmu_event_init(struct perf_event *event)
  */
 static void sparc_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
@@ -1511,7 +1511,7 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
  */
 static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
@@ -1524,13 +1524,13 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu)
  */
 static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n;
 
 	if (!sparc_pmu)
 		return -EINVAL;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 	n = cpuc->n_events;
 	if (check_excludes(cpuc->event, 0, n))
 		return -EINVAL;
@@ -1601,7 +1601,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* If the PMU has the TOE IRQ enable bits, we need to do a
 	 * dummy write to the %pcr to clear the overflow bits and thus
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index c13c9f25d83a..9ddc4928a089 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -1076,13 +1076,8 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->u_regs[UREG_G1]);
 
-	audit_syscall_entry((test_thread_flag(TIF_32BIT) ?
-			     AUDIT_ARCH_SPARC :
-			     AUDIT_ARCH_SPARC64),
-			    regs->u_regs[UREG_G1],
-			    regs->u_regs[UREG_I0],
-			    regs->u_regs[UREG_I1],
-			    regs->u_regs[UREG_I2],
+	audit_syscall_entry(regs->u_regs[UREG_G1], regs->u_regs[UREG_I0],
+			    regs->u_regs[UREG_I1], regs->u_regs[UREG_I2],
 			    regs->u_regs[UREG_I3]);
 
 	return ret;
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index d5c319553fd0..9d98e5002a09 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -204,7 +204,7 @@ static void __init smp4d_ipi_init(void)
 
 void sun4d_ipi_interrupt(void)
 {
-	struct sun4d_ipi_work *work = &__get_cpu_var(sun4d_ipi_work);
+	struct sun4d_ipi_work *work = this_cpu_ptr(&sun4d_ipi_work);
 
 	if (work->single) {
 		work->single = 0;
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 3fddf64c7fc6..59da0c3ea788 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -765,7 +765,7 @@ void setup_sparc64_timer(void)
 			     : /* no outputs */
 			     : "r" (pstate));
 
-	sevt = &__get_cpu_var(sparc64_events);
+	sevt = this_cpu_ptr(&sparc64_events);
 
 	memcpy(sevt, &sparc64_clockevent, sizeof(*sevt));
 	sevt->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 14158d40ba76..be98685c14c6 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	nop
 	.previous
 
-	rdpr	%tl, %g3
-	cmp	%g3, 1
+	rdpr	%tl, %g7
+	cmp	%g7, 1
 	bne,pn	%xcc, winfix_trampoline
-	 nop
+	 mov	%g3, %g4
 	ba,pt	%xcc, etrap
 	 rd	%pc, %g7
 	call	hugetlb_setup
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 9cf2ee01cee3..140527a20e7d 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -41,6 +41,10 @@
 #endif
 #endif
 
+#if !defined(EX_LD) && !defined(EX_ST)
+#define NON_USER_COPY
+#endif
+
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
@@ -197,9 +201,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 mov		EX_RETVAL(%o3), %o0
 
 .Llarge_src_unaligned:
+#ifdef NON_USER_COPY
+	VISEntryHalfFast(.Lmedium_vis_entry_fail)
+#else
+	VISEntryHalf
+#endif
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
-	VISEntryHalf
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
 	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
@@ -240,6 +248,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 	ba,a,pt		%icc, .Lmedium_unaligned
 
+#ifdef NON_USER_COPY
+.Lmedium_vis_entry_fail:
+	 or		%o0, %o1, %g2
+#endif
 .Lmedium:
 	LOAD(prefetch, %o1 + 0x40, #n_reads_strong)
 	andcc		%g2, 0x7, %g0
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b89aba217e3b..9df2190c097e 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -52,14 +52,14 @@ out:
 
 void arch_enter_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	tb->active = 1;
 }
 
 void arch_leave_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	if (tb->tlb_nr)
 		flush_tlb_pending();
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index 71af5747874d..60d62a292fce 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -140,12 +140,12 @@ extern unsigned int debug_smp_processor_id(void);
 
 /*
  * Read the set of maskable interrupts.
- * We avoid the preemption warning here via __this_cpu_ptr since even
+ * We avoid the preemption warning here via raw_cpu_ptr since even
  * if irqs are already enabled, it's harmless to read the wrong cpu's
  * enabled mask.
  */
 #define arch_local_irqs_enabled() \
-	(*__this_cpu_ptr(&interrupts_enabled_mask))
+	(*raw_cpu_ptr(&interrupts_enabled_mask))
 
 /* Re-enable all maskable interrupts. */
 #define arch_local_irq_enable() \
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index 4734215e2ad4..f67753db1f78 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -84,7 +84,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *t)
 	 * clear any pending DMA interrupts.
 	 */
 	if (current->thread.tile_dma_state.enabled)
-		install_page_table(mm->pgd, __get_cpu_var(current_asid));
+		install_page_table(mm->pgd, __this_cpu_read(current_asid));
 #endif
 }
 
@@ -96,12 +96,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		int cpu = smp_processor_id();
 
 		/* Pick new ASID. */
-		int asid = __get_cpu_var(current_asid) + 1;
+		int asid = __this_cpu_read(current_asid) + 1;
 		if (asid > max_asid) {
 			asid = min_asid;
 			local_flush_tlb();
 		}
-		__get_cpu_var(current_asid) = asid;
+		__this_cpu_write(current_asid, asid);
 
 		/* Clear cpu from the old mm, and set it in the new one. */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 637f2ffaa5f5..ba85765e1436 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -73,7 +73,7 @@ static DEFINE_PER_CPU(int, irq_depth);
  */
 void tile_dev_intr(struct pt_regs *regs, int intnum)
 {
-	int depth = __get_cpu_var(irq_depth)++;
+	int depth = __this_cpu_inc_return(irq_depth);
 	unsigned long original_irqs;
 	unsigned long remaining_irqs;
 	struct pt_regs *old_regs;
@@ -120,7 +120,7 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 
 		/* Count device irqs; Linux IPIs are counted elsewhere. */
 		if (irq != IRQ_RESCHEDULE)
-			__get_cpu_var(irq_stat).irq_dev_intr_count++;
+			__this_cpu_inc(irq_stat.irq_dev_intr_count);
 
 		generic_handle_irq(irq);
 	}
@@ -130,10 +130,10 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 	 * including any that were reenabled during interrupt
 	 * handling.
 	 */
-	if (depth == 0)
-		unmask_irqs(~__get_cpu_var(irq_disable_mask));
+	if (depth == 1)
+		unmask_irqs(~__this_cpu_read(irq_disable_mask));
 
-	__get_cpu_var(irq_depth)--;
+	__this_cpu_dec(irq_depth);
 
 	/*
 	 * Track time spent against the current process again and
@@ -151,7 +151,7 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 static void tile_irq_chip_enable(struct irq_data *d)
 {
 	get_cpu_var(irq_disable_mask) &= ~(1UL << d->irq);
-	if (__get_cpu_var(irq_depth) == 0)
+	if (__this_cpu_read(irq_depth) == 0)
 		unmask_irqs(1UL << d->irq);
 	put_cpu_var(irq_disable_mask);
 }
@@ -197,7 +197,7 @@ static void tile_irq_chip_ack(struct irq_data *d)
  */
 static void tile_irq_chip_eoi(struct irq_data *d)
 {
-	if (!(__get_cpu_var(irq_disable_mask) & (1UL << d->irq)))
+	if (!(__this_cpu_read(irq_disable_mask) & (1UL << d->irq)))
 		unmask_irqs(1UL << d->irq);
 }
 
diff --git a/arch/tile/kernel/messaging.c b/arch/tile/kernel/messaging.c
index 7867266f9716..ac950be1318e 100644
--- a/arch/tile/kernel/messaging.c
+++ b/arch/tile/kernel/messaging.c
@@ -28,7 +28,7 @@ static DEFINE_PER_CPU(HV_MsgState, msg_state);
 void init_messaging(void)
 {
 	/* Allocate storage for messages in kernel space */
-	HV_MsgState *state = &__get_cpu_var(msg_state);
+	HV_MsgState *state = this_cpu_ptr(&msg_state);
 	int rc = hv_register_message_state(state);
 	if (rc != HV_OK)
 		panic("hv_register_message_state: error %d", rc);
@@ -96,7 +96,7 @@ void hv_message_intr(struct pt_regs *regs, int intnum)
 			struct hv_driver_cb *cb =
 				(struct hv_driver_cb *)him->intarg;
 			cb->callback(cb, him->intdata);
-			__get_cpu_var(irq_stat).irq_hv_msg_count++;
+			__this_cpu_inc(irq_stat.irq_hv_msg_count);
 		}
 	}
 
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index 2bf6c9c135c1..bb509cee3b59 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -590,7 +590,7 @@ static int tile_event_set_period(struct perf_event *event)
  */
 static void tile_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -616,7 +616,7 @@ static void tile_pmu_stop(struct perf_event *event, int flags)
  */
 static void tile_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = event->hw.idx;
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -650,7 +650,7 @@ static void tile_pmu_start(struct perf_event *event, int flags)
  */
 static int tile_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc;
 	unsigned long mask;
 	int b, max_cnt;
@@ -706,7 +706,7 @@ static int tile_pmu_add(struct perf_event *event, int flags)
  */
 static void tile_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	/*
@@ -880,14 +880,14 @@ static struct pmu tilera_pmu = {
 int tile_pmu_handle_irq(struct pt_regs *regs, int fault)
 {
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	u64 val;
 	unsigned long status;
 	int bit;
 
-	__get_cpu_var(perf_irqs)++;
+	__this_cpu_inc(perf_irqs);
 
 	if (!atomic_read(&tile_active_events))
 		return 0;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 16ed58948757..0050cbc1d9de 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -64,7 +64,7 @@ early_param("idle", idle_setup);
 
 void arch_cpu_idle(void)
 {
-	__get_cpu_var(irq_stat).idle_timestamp = jiffies;
+	__this_cpu_write(irq_stat.idle_timestamp, jiffies);
 	_cpu_idle();
 }
 
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 112ababa9e55..b9736ded06f2 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1218,7 +1218,8 @@ static void __init validate_hv(void)
 	 * various asid variables to their appropriate initial states.
 	 */
 	asid_range = hv_inquire_asid(0);
-	__get_cpu_var(current_asid) = min_asid = asid_range.start;
+	min_asid = asid_range.start;
+	__this_cpu_write(current_asid, min_asid);
 	max_asid = asid_range.start + asid_range.size - 1;
 
 	if (hv_confstr(HV_CONFSTR_CHIP_MODEL, (HV_VirtAddr)chip_model,
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index de07fa7d1315..6cb2ce31b5a2 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -740,7 +740,7 @@ static DEFINE_PER_CPU(unsigned long, ss_saved_pc);
 
 void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 {
-	unsigned long *ss_pc = &__get_cpu_var(ss_saved_pc);
+	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	struct thread_info *info = (void *)current_thread_info();
 	int is_single_step = test_ti_thread_flag(info, TIF_SINGLESTEP);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
@@ -766,7 +766,7 @@ void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 
 void single_step_once(struct pt_regs *regs)
 {
-	unsigned long *ss_pc = &__get_cpu_var(ss_saved_pc);
+	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
 
 	*ss_pc = regs->pc;
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index 19eaa62d456a..d3c4ed780ce2 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(flush_icache_range);
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	__get_cpu_var(irq_stat).irq_resched_count++;
+	__this_cpu_inc(irq_stat.irq_resched_count);
 	scheduler_ipi();
 
 	return IRQ_HANDLED;
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index 732e9d138661..0d59a1b60c74 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -41,7 +41,7 @@ void __init smp_prepare_boot_cpu(void)
 	int cpu = smp_processor_id();
 	set_cpu_online(cpu, 1);
 	set_cpu_present(cpu, 1);
-	__get_cpu_var(cpu_state) = CPU_ONLINE;
+	__this_cpu_write(cpu_state, CPU_ONLINE);
 
 	init_messaging();
 }
@@ -158,7 +158,7 @@ static void start_secondary(void)
 	/* printk(KERN_DEBUG "Initializing CPU#%d\n", cpuid); */
 
 	/* Initialize the current asid for our first page table. */
-	__get_cpu_var(current_asid) = min_asid;
+	__this_cpu_write(current_asid, min_asid);
 
 	/* Set up this thread as another owner of the init_mm */
 	atomic_inc(&init_mm.mm_count);
@@ -201,7 +201,7 @@ void online_secondary(void)
 	notify_cpu_starting(smp_processor_id());
 
 	set_cpu_online(smp_processor_id(), 1);
-	__get_cpu_var(cpu_state) = CPU_ONLINE;
+	__this_cpu_write(cpu_state, CPU_ONLINE);
 
 	/* Set up tile-specific state for this cpu. */
 	setup_cpu(0);
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index c1b362277fb7..b854a1cd0079 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -162,7 +162,7 @@ static DEFINE_PER_CPU(struct clock_event_device, tile_timer) = {
 
 void setup_tile_timer(void)
 {
-	struct clock_event_device *evt = &__get_cpu_var(tile_timer);
+	struct clock_event_device *evt = this_cpu_ptr(&tile_timer);
 
 	/* Fill in fields that are speed-specific. */
 	clockevents_calc_mult_shift(evt, cycles_per_sec, TILE_MINSEC);
@@ -182,7 +182,7 @@ void setup_tile_timer(void)
 void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct clock_event_device *evt = &__get_cpu_var(tile_timer);
+	struct clock_event_device *evt = this_cpu_ptr(&tile_timer);
 
 	/*
 	 * Mask the timer interrupt here, since we are a oneshot timer
@@ -194,7 +194,7 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 	irq_enter();
 
 	/* Track interrupt count. */
-	__get_cpu_var(irq_stat).irq_timer_count++;
+	__this_cpu_inc(irq_stat.irq_timer_count);
 
 	/* Call the generic timer handler */
 	evt->event_handler(evt);
@@ -235,7 +235,7 @@ cycles_t ns2cycles(unsigned long nsecs)
 	 * We do not have to disable preemption here as each core has the same
 	 * clock frequency.
 	 */
-	struct clock_event_device *dev = &__raw_get_cpu_var(tile_timer);
+	struct clock_event_device *dev = raw_cpu_ptr(&tile_timer);
 
 	/*
 	 * as in clocksource.h and x86's timer.h, we split the calculation
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 0dc218294770..6aa2f2625447 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -103,7 +103,7 @@ static void kmap_atomic_register(struct page *page, int type,
 	spin_lock(&amp_lock);
 
 	/* With interrupts disabled, now fill in the per-cpu info. */
-	amp = &__get_cpu_var(amps).per_type[type];
+	amp = this_cpu_ptr(&amps.per_type[type]);
 	amp->page = page;
 	amp->cpu = smp_processor_id();
 	amp->va = va;
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index a092e393bd20..caa270165f86 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -593,14 +593,14 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 	interrupt_mask_set_mask(-1ULL);
 	rc = flush_and_install_context(__pa(pgtables),
 				       init_pgprot((unsigned long)pgtables),
-				       __get_cpu_var(current_asid),
+				       __this_cpu_read(current_asid),
 				       cpumask_bits(my_cpu_mask));
 	interrupt_mask_restore_mask(irqmask);
 	BUG_ON(rc != 0);
 
 	/* Copy the page table back to the normal swapper_pg_dir. */
 	memcpy(pgd_base, pgtables, sizeof(pgtables));
-	__install_page_table(pgd_base, __get_cpu_var(current_asid),
+	__install_page_table(pgd_base, __this_cpu_read(current_asid),
 			     swapper_pgprot);
 
 	/*
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index 6915d28cf118..87bc86821bc9 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -39,7 +39,8 @@ config LOCKDEP_SUPPORT
 
 config STACKTRACE_SUPPORT
 	bool
-	default n
+	default y
+	select STACKTRACE
 
 config GENERIC_CALIBRATE_DELAY
 	bool
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 7d26d9c0b2fb..f70dd540655d 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -659,10 +659,6 @@ static int __init eth_setup(char *str)
 	}
 
 	new = alloc_bootmem(sizeof(*new));
-	if (new == NULL) {
-		printk(KERN_ERR "eth_init : alloc_bootmem failed\n");
-		return 1;
-	}
 
 	INIT_LIST_HEAD(&new->list);
 	new->index = n;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 3716e6952554..e8ab93c3e638 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q)
 
 	while(1){
 		struct ubd *dev = q->queuedata;
-		if(dev->end_sg == 0){
+		if(dev->request == NULL){
 			struct request *req = blk_fetch_request(q);
 			if(req == NULL)
 				return;
@@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 			prepare_flush_request(req, io_req);
-			submit_request(io_req, dev);
+			if (submit_request(io_req, dev) == false)
+				return;
 		}
 
 		while(dev->start_sg < dev->end_sg){
diff --git a/arch/um/include/asm/stacktrace.h b/arch/um/include/asm/stacktrace.h
new file mode 100644
index 000000000000..9a864328c67f
--- /dev/null
+++ b/arch/um/include/asm/stacktrace.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_UML_STACKTRACE_H
+#define _ASM_UML_STACKTRACE_H
+
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+
+struct stack_frame {
+	struct stack_frame *next_frame;
+	unsigned long return_address;
+};
+
+struct stacktrace_ops {
+	void (*address)(void *data, unsigned long address, int reliable);
+};
+
+#ifdef CONFIG_FRAME_POINTER
+static inline unsigned long
+get_frame_pointer(struct task_struct *task, struct pt_regs *segv_regs)
+{
+	if (!task || task == current)
+		return segv_regs ? PT_REGS_BP(segv_regs) : current_bp();
+	return KSTK_EBP(task);
+}
+#else
+static inline unsigned long
+get_frame_pointer(struct task_struct *task, struct pt_regs *segv_regs)
+{
+	return 0;
+}
+#endif
+
+static inline unsigned long
+*get_stack_pointer(struct task_struct *task, struct pt_regs *segv_regs)
+{
+	if (!task || task == current)
+		return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp();
+	return (unsigned long *)KSTK_ESP(task);
+}
+
+void dump_trace(struct task_struct *tsk, const struct stacktrace_ops *ops, void *data);
+
+#endif /* _ASM_UML_STACKTRACE_H */
diff --git a/arch/um/include/shared/mem_user.h b/arch/um/include/shared/mem_user.h
index 46384acd547b..cb84414e3e66 100644
--- a/arch/um/include/shared/mem_user.h
+++ b/arch/um/include/shared/mem_user.h
@@ -49,7 +49,7 @@ extern int iomem_size;
 extern int init_mem_user(void);
 extern void setup_memory(void *entry);
 extern unsigned long find_iomem(char *driver, unsigned long *len_out);
-extern int init_maps(unsigned long physmem, unsigned long iomem,
+extern void mem_total_pages(unsigned long physmem, unsigned long iomem,
 		     unsigned long highmem);
 extern unsigned long get_vm(unsigned long len);
 extern void setup_physmem(unsigned long start, unsigned long usable,
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index d8b78a03855c..2d840a070c8b 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
 obj-$(CONFIG_GCOV)	+= gmon_syms.o
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+obj-$(CONFIG_STACKTRACE) += stacktrace.o
 
 USER_OBJS := config.o
 
diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index 30fdd5d0067b..549ecf3f5857 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -22,39 +22,19 @@ EXPORT_SYMBOL(high_physmem);
 
 extern unsigned long long physmem_size;
 
-int __init init_maps(unsigned long physmem, unsigned long iomem,
+void __init mem_total_pages(unsigned long physmem, unsigned long iomem,
 		     unsigned long highmem)
 {
-	struct page *p, *map;
-	unsigned long phys_len, phys_pages, highmem_len, highmem_pages;
-	unsigned long iomem_len, iomem_pages, total_len, total_pages;
-	int i;
-
-	phys_pages = physmem >> PAGE_SHIFT;
-	phys_len = phys_pages * sizeof(struct page);
-
-	iomem_pages = iomem >> PAGE_SHIFT;
-	iomem_len = iomem_pages * sizeof(struct page);
+	unsigned long phys_pages, highmem_pages;
+	unsigned long iomem_pages, total_pages;
 
+	phys_pages    = physmem >> PAGE_SHIFT;
+	iomem_pages   = iomem   >> PAGE_SHIFT;
 	highmem_pages = highmem >> PAGE_SHIFT;
-	highmem_len = highmem_pages * sizeof(struct page);
-
-	total_pages = phys_pages + iomem_pages + highmem_pages;
-	total_len = phys_len + iomem_len + highmem_len;
 
-	map = alloc_bootmem_low_pages(total_len);
-	if (map == NULL)
-		return -ENOMEM;
-
-	for (i = 0; i < total_pages; i++) {
-		p = &map[i];
-		memset(p, 0, sizeof(struct page));
-		SetPageReserved(p);
-		INIT_LIST_HEAD(&p->lru);
-	}
+	total_pages   = phys_pages + iomem_pages + highmem_pages;
 
 	max_mapnr = total_pages;
-	return 0;
 }
 
 void map_memory(unsigned long virt, unsigned long phys, unsigned long len,
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 694d551c8899..62435ef003d9 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -165,8 +165,7 @@ static void send_sigtrap(struct task_struct *tsk, struct uml_pt_regs *regs,
  */
 void syscall_trace_enter(struct pt_regs *regs)
 {
-	audit_syscall_entry(HOST_AUDIT_ARCH,
-			    UPT_SYSCALL_NR(&regs->regs),
+	audit_syscall_entry(UPT_SYSCALL_NR(&regs->regs),
 			    UPT_SYSCALL_ARG1(&regs->regs),
 			    UPT_SYSCALL_ARG2(&regs->regs),
 			    UPT_SYSCALL_ARG3(&regs->regs),
diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c
new file mode 100644
index 000000000000..ebe7bcf62684
--- /dev/null
+++ b/arch/um/kernel/stacktrace.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2013 Richard Weinberger <richard@nod.at>
+ * Copyright (C) 2014 Google Inc., Author: Daniel Walter <dwalter@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/stacktrace.h>
+
+void dump_trace(struct task_struct *tsk,
+		const struct stacktrace_ops *ops,
+		void *data)
+{
+	int reliable = 0;
+	unsigned long *sp, bp, addr;
+	struct pt_regs *segv_regs = tsk->thread.segv_regs;
+	struct stack_frame *frame;
+
+	bp = get_frame_pointer(tsk, segv_regs);
+	sp = get_stack_pointer(tsk, segv_regs);
+
+	frame = (struct stack_frame *)bp;
+	while (((long) sp & (THREAD_SIZE-1)) != 0) {
+		addr = *sp;
+		if (__kernel_text_address(addr)) {
+			reliable = 0;
+			if ((unsigned long) sp == bp + sizeof(long)) {
+				frame = frame ? frame->next_frame : NULL;
+				bp = (unsigned long)frame;
+				reliable = 1;
+			}
+			ops->address(data, addr, reliable);
+		}
+		sp++;
+	}
+}
+
+static void save_addr(void *data, unsigned long address, int reliable)
+{
+	struct stack_trace *trace = data;
+
+	if (!reliable)
+		return;
+	if (trace->nr_entries >= trace->max_entries)
+		return;
+
+	trace->entries[trace->nr_entries++] = address;
+}
+
+static const struct stacktrace_ops dump_ops = {
+	.address = save_addr
+};
+
+static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace)
+{
+	dump_trace(tsk, &dump_ops, trace);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	__save_stack_trace(current, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c
index 799d7e413bf5..894c8d303cda 100644
--- a/arch/um/kernel/sysrq.c
+++ b/arch/um/kernel/sysrq.c
@@ -12,57 +12,20 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <asm/sysrq.h>
+#include <asm/stacktrace.h>
 #include <os.h>
 
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-static void do_stack_trace(unsigned long *sp, unsigned long bp)
+static void _print_addr(void *data, unsigned long address, int reliable)
 {
-	int reliable;
-	unsigned long addr;
-	struct stack_frame *frame = (struct stack_frame *)bp;
-
-	printk(KERN_INFO "Call Trace:\n");
-	while (((long) sp & (THREAD_SIZE-1)) != 0) {
-		addr = *sp;
-		if (__kernel_text_address(addr)) {
-			reliable = 0;
-			if ((unsigned long) sp == bp + sizeof(long)) {
-				frame = frame ? frame->next_frame : NULL;
-				bp = (unsigned long)frame;
-				reliable = 1;
-			}
-
-			printk(KERN_INFO " [<%08lx>]", addr);
-			printk(KERN_CONT " %s", reliable ? "" : "? ");
-			print_symbol(KERN_CONT "%s", addr);
-			printk(KERN_CONT "\n");
-		}
-		sp++;
-	}
-	printk(KERN_INFO "\n");
+	pr_info(" [<%08lx>]", address);
+	pr_cont(" %s", reliable ? "" : "? ");
+	print_symbol("%s", address);
+	pr_cont("\n");
 }
 
-static unsigned long get_frame_pointer(struct task_struct *task,
-				       struct pt_regs *segv_regs)
-{
-	if (!task || task == current)
-		return segv_regs ? PT_REGS_BP(segv_regs) : current_bp();
-	else
-		return KSTK_EBP(task);
-}
-
-static unsigned long *get_stack_pointer(struct task_struct *task,
-					struct pt_regs *segv_regs)
-{
-	if (!task || task == current)
-		return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp();
-	else
-		return (unsigned long *)KSTK_ESP(task);
-}
+static const struct stacktrace_ops stackops = {
+	.address = _print_addr
+};
 
 void show_stack(struct task_struct *task, unsigned long *stack)
 {
@@ -71,7 +34,7 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 	int i;
 
 	if (!segv_regs && os_is_signal_stack()) {
-		printk(KERN_ERR "Received SIGSEGV in SIGSEGV handler,"
+		pr_err("Received SIGSEGV in SIGSEGV handler,"
 				" aborting stack trace!\n");
 		return;
 	}
@@ -83,16 +46,18 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 	if (!stack)
 		sp = get_stack_pointer(task, segv_regs);
 
-	printk(KERN_INFO "Stack:\n");
+	pr_info("Stack:\n");
 	stack = sp;
 	for (i = 0; i < 3 * STACKSLOTS_PER_LINE; i++) {
 		if (kstack_end(stack))
 			break;
 		if (i && ((i % STACKSLOTS_PER_LINE) == 0))
-			printk(KERN_CONT "\n");
-		printk(KERN_CONT " %08lx", *stack++);
+			pr_cont("\n");
+		pr_cont(" %08lx", *stack++);
 	}
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 
-	do_stack_trace(sp, bp);
+	pr_info("Call Trace:\n");
+	dump_trace(current, &stackops, NULL);
+	pr_info("\n");
 }
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 016adf0985d5..9274eae6ae7b 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -348,12 +348,7 @@ int __init linux_main(int argc, char **argv)
 	start_vm = VMALLOC_START;
 
 	setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
-	if (init_maps(physmem_size, iomem_size, highmem)) {
-		printf("Failed to allocate mem_map for %Lu bytes of physical "
-		       "memory and %Lu bytes of highmem\n", physmem_size,
-		       highmem);
-		exit(1);
-	}
+	mem_total_pages(physmem_size, iomem_size, highmem);
 
 	virtmem_size = physmem_size;
 	stack = (unsigned long) argv;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 711de084ab57..8ffba18395c8 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -198,12 +198,12 @@ sysexit_from_sys_call:
 
 #ifdef CONFIG_AUDITSYSCALL
 	.macro auditsys_entry_common
-	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
-	movl %edx,%r8d			/* 5th arg: 3rd syscall arg */
-	/* (already in %ecx)		   4th arg: 2nd syscall arg */
-	movl %ebx,%edx			/* 3rd arg: 1st syscall arg */
-	movl %eax,%esi			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_I386,%edi	/* 1st arg: audit arch */
+	movl %esi,%r8d			/* 5th arg: 4th syscall arg */
+	movl %ecx,%r9d			/*swap with edx*/
+	movl %edx,%ecx			/* 4th arg: 3rd syscall arg */
+	movl %r9d,%edx			/* 3rd arg: 2nd syscall arg */
+	movl %ebx,%esi			/* 2nd arg: 1st syscall arg */
+	movl %eax,%edi			/* 1st arg: syscall number */
 	call __audit_syscall_entry
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall number */
 	cmpq $(IA32_NR_syscalls-1),%rax
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 3bf000fab0ae..d55a210a49bf 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -6,6 +6,7 @@ genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
 generic-y += cputime.h
+generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
 generic-y += scatterlist.h
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 4b528a970bd4..61fd18b83b6c 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -97,11 +97,11 @@ extern void hw_breakpoint_restore(void);
 DECLARE_PER_CPU(int, debug_stack_usage);
 static inline void debug_stack_usage_inc(void)
 {
-	__get_cpu_var(debug_stack_usage)++;
+	__this_cpu_inc(debug_stack_usage);
 }
 static inline void debug_stack_usage_dec(void)
 {
-	__get_cpu_var(debug_stack_usage)--;
+	__this_cpu_dec(debug_stack_usage);
 }
 int is_debug_stack(unsigned long addr);
 void debug_stack_set_zero(void);
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
deleted file mode 100644
index b4b38bacb404..000000000000
--- a/arch/x86/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASMX86_DMA_CONTIGUOUS_H
-#define ASMX86_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
-#endif
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 53cdfb2857ab..4421b5da409d 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -27,7 +27,6 @@
 #include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
-#define  ARCH_SUPPORTS_KPROBES_ON_FTRACE
 
 struct pt_regs;
 struct kprobe;
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 85e13ccf15c4..d725382c2ae0 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu)
 {
 #ifdef CONFIG_SMP
 	if (smp_num_siblings == 2)
-		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+		return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index c63e925fd6b7..a00ad8f2a657 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -164,7 +164,7 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
@@ -601,16 +601,16 @@ struct uv_hub_nmi_s {
 
 struct uv_cpu_nmi_s {
 	struct uv_hub_nmi_s	*hub;
-	atomic_t		state;
-	atomic_t		pinging;
+	int			state;
+	int			pinging;
 	int			queries;
 	int			pings;
 };
 
-DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-#define uv_cpu_nmi			(__get_cpu_var(__uv_cpu_nmi))
+DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+
 #define uv_hub_nmi			(uv_cpu_nmi.hub)
-#define uv_cpu_nmi_per(cpu)		(per_cpu(__uv_cpu_nmi, cpu))
+#define uv_cpu_nmi_per(cpu)		(per_cpu(uv_cpu_nmi, cpu))
 #define uv_hub_nmi_per(cpu)		(uv_cpu_nmi_per(cpu).hub)
 
 /* uv_cpu_nmi_states */
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index af5b08ab3b71..5972b108f15a 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -146,7 +146,7 @@ static inline int is_apbt_capable(void)
 static int __init apbt_clockevent_register(void)
 {
 	struct sfi_timer_table_entry *mtmr;
-	struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev);
+	struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev);
 
 	mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
 	if (mtmr == NULL) {
@@ -200,7 +200,7 @@ void apbt_setup_secondary_clock(void)
 	if (!cpu)
 		return;
 
-	adev = &__get_cpu_var(cpu_apbt_dev);
+	adev = this_cpu_ptr(&cpu_apbt_dev);
 	if (!adev->timer) {
 		adev->timer = dw_apb_clockevent_init(cpu, adev->name,
 			APBT_CLOCKEVENT_RATING, adev_virt_addr(adev),
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 24b5894396a0..ba6cc041edb1 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -561,7 +561,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
  */
 static void setup_APIC_timer(void)
 {
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
 
 	if (this_cpu_has(X86_FEATURE_ARAT)) {
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
@@ -696,7 +696,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 static int __init calibrate_APIC_clock(void)
 {
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
 	void (*real_handler)(struct clock_event_device *dev);
 	unsigned long deltaj;
 	long delta, deltatsc;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 6ce600f9bc78..e658f21681c8 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -42,7 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	 * We are to modify mask, so we need an own copy
 	 * and be sure it's manipulated with irq off.
 	 */
-	ipi_mask_ptr = __raw_get_cpu_var(ipi_mask);
+	ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
 	cpumask_copy(ipi_mask_ptr, mask);
 
 	/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 700f958652f8..4b4f78c9ba19 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -964,6 +964,7 @@ static void vgetcpu_set_mode(void)
 		vgetcpu_mode = VGETCPU_LSL;
 }
 
+#ifdef CONFIG_IA32_EMULATION
 /* May not be __init: called during resume */
 static void syscall32_cpu_init(void)
 {
@@ -975,7 +976,8 @@ static void syscall32_cpu_init(void)
 
 	wrmsrl(MSR_CSTAR, ia32_cstar_target);
 }
-#endif
+#endif		/* CONFIG_IA32_EMULATION */
+#endif		/* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_32
 void enable_sep_cpu(void)
@@ -1198,9 +1200,9 @@ DEFINE_PER_CPU(int, debug_stack_usage);
 
 int is_debug_stack(unsigned long addr)
 {
-	return __get_cpu_var(debug_stack_usage) ||
-		(addr <= __get_cpu_var(debug_stack_addr) &&
-		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
+	return __this_cpu_read(debug_stack_usage) ||
+		(addr <= __this_cpu_read(debug_stack_addr) &&
+		 addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
 }
 NOKPROBE_SYMBOL(is_debug_stack);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 5ac2d1fb28bc..4cfba4371a71 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -83,7 +83,7 @@ static DEFINE_MUTEX(mce_inject_mutex);
 static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 {
 	int cpu = smp_processor_id();
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 	if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
 		return NMI_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
@@ -97,7 +97,7 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 static void mce_irq_ipi(void *info)
 {
 	int cpu = smp_processor_id();
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 
 	if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
 			m->inject_flags & MCJ_EXCEPTION) {
@@ -109,7 +109,7 @@ static void mce_irq_ipi(void *info)
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 	int context = MCJ_CTX(m->inject_flags);
 	int ret = 0;
 	int cpu = m->extcpu;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bd9ccda8087f..61a9668cebfd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -400,7 +400,7 @@ static u64 mce_rdmsrl(u32 msr)
 
 		if (offset < 0)
 			return 0;
-		return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
+		return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
 	}
 
 	if (rdmsrl_safe(msr, &v)) {
@@ -422,7 +422,7 @@ static void mce_wrmsrl(u32 msr, u64 v)
 		int offset = msr_to_offset(msr);
 
 		if (offset >= 0)
-			*(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
+			*(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
 		return;
 	}
 	wrmsrl(msr, v);
@@ -478,7 +478,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring);
 /* Runs with CPU affinity in workqueue */
 static int mce_ring_empty(void)
 {
-	struct mce_ring *r = &__get_cpu_var(mce_ring);
+	struct mce_ring *r = this_cpu_ptr(&mce_ring);
 
 	return r->start == r->end;
 }
@@ -490,7 +490,7 @@ static int mce_ring_get(unsigned long *pfn)
 
 	*pfn = 0;
 	get_cpu();
-	r = &__get_cpu_var(mce_ring);
+	r = this_cpu_ptr(&mce_ring);
 	if (r->start == r->end)
 		goto out;
 	*pfn = r->ring[r->start];
@@ -504,7 +504,7 @@ out:
 /* Always runs in MCE context with preempt off */
 static int mce_ring_add(unsigned long pfn)
 {
-	struct mce_ring *r = &__get_cpu_var(mce_ring);
+	struct mce_ring *r = this_cpu_ptr(&mce_ring);
 	unsigned next;
 
 	next = (r->end + 1) % MCE_RING_SIZE;
@@ -526,7 +526,7 @@ int mce_available(struct cpuinfo_x86 *c)
 static void mce_schedule_work(void)
 {
 	if (!mce_ring_empty())
-		schedule_work(&__get_cpu_var(mce_work));
+		schedule_work(this_cpu_ptr(&mce_work));
 }
 
 DEFINE_PER_CPU(struct irq_work, mce_irq_work);
@@ -551,7 +551,7 @@ static void mce_report_event(struct pt_regs *regs)
 		return;
 	}
 
-	irq_work_queue(&__get_cpu_var(mce_irq_work));
+	irq_work_queue(this_cpu_ptr(&mce_irq_work));
 }
 
 /*
@@ -1045,7 +1045,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	mce_gather_info(&m, regs);
 
-	final = &__get_cpu_var(mces_seen);
+	final = this_cpu_ptr(&mces_seen);
 	*final = m;
 
 	memset(valid_banks, 0, sizeof(valid_banks));
@@ -1278,22 +1278,22 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) =
 
 static int cmc_error_seen(void)
 {
-	unsigned long *v = &__get_cpu_var(mce_polled_error);
+	unsigned long *v = this_cpu_ptr(&mce_polled_error);
 
 	return test_and_clear_bit(0, v);
 }
 
 static void mce_timer_fn(unsigned long data)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv;
 	int notify;
 
 	WARN_ON(smp_processor_id() != data);
 
-	if (mce_available(__this_cpu_ptr(&cpu_info))) {
+	if (mce_available(this_cpu_ptr(&cpu_info))) {
 		machine_check_poll(MCP_TIMESTAMP,
-				&__get_cpu_var(mce_poll_banks));
+				this_cpu_ptr(&mce_poll_banks));
 		mce_intel_cmci_poll();
 	}
 
@@ -1323,7 +1323,7 @@ static void mce_timer_fn(unsigned long data)
  */
 void mce_timer_kick(unsigned long interval)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long when = jiffies + interval;
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
@@ -1659,7 +1659,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 
 static void __mcheck_cpu_init_timer(void)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned int cpu = smp_processor_id();
 
 	setup_timer(t, mce_timer_fn, cpu);
@@ -1702,8 +1702,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_timer();
-	INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
-	init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb);
+	INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
+	init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
 }
 
 /*
@@ -1955,7 +1955,7 @@ static struct miscdevice mce_chrdev_device = {
 static void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
-	__clear_bit(bank, __get_cpu_var(mce_poll_banks));
+	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
 	cmci_disable_bank(bank);
 }
 
@@ -2065,7 +2065,7 @@ static void mce_syscore_shutdown(void)
 static void mce_syscore_resume(void)
 {
 	__mcheck_cpu_init_generic();
-	__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
+	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
 }
 
 static struct syscore_ops mce_syscore_ops = {
@@ -2080,7 +2080,7 @@ static struct syscore_ops mce_syscore_ops = {
 
 static void mce_cpu_restart(void *data)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_timer();
@@ -2096,14 +2096,14 @@ static void mce_restart(void)
 /* Toggle features for corrected errors */
 static void mce_disable_cmci(void *data)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	cmci_clear();
 }
 
 static void mce_enable_ce(void *all)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	cmci_reenable();
 	cmci_recheck();
@@ -2336,7 +2336,7 @@ static void mce_disable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
@@ -2354,7 +2354,7 @@ static void mce_reenable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1e49f8f41276..5d4999f95aec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -310,7 +310,7 @@ static void amd_threshold_interrupt(void)
 			 * event.
 			 */
 			machine_check_poll(MCP_TIMESTAMP,
-					&__get_cpu_var(mce_poll_banks));
+					this_cpu_ptr(&mce_poll_banks));
 
 			if (high & MASK_OVERFLOW_HI) {
 				rdmsrl(address, m.misc);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 3bdb95ae8c43..b3c97bafc123 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -86,7 +86,7 @@ void mce_intel_cmci_poll(void)
 {
 	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
 		return;
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 }
 
 void mce_intel_hcpu_update(unsigned long cpu)
@@ -145,7 +145,7 @@ static void cmci_storm_disable_banks(void)
 	u64 val;
 
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = __get_cpu_var(mce_banks_owned);
+	owned = this_cpu_ptr(mce_banks_owned);
 	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
 		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 		val &= ~MCI_CTL2_CMCI_EN;
@@ -195,7 +195,7 @@ static void intel_threshold_interrupt(void)
 {
 	if (cmci_storm_detect())
 		return;
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 	mce_notify_irq();
 }
 
@@ -206,7 +206,7 @@ static void intel_threshold_interrupt(void)
  */
 static void cmci_discover(int banks)
 {
-	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+	unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
 	unsigned long flags;
 	int i;
 	int bios_wrong_thresh = 0;
@@ -228,7 +228,7 @@ static void cmci_discover(int banks)
 		/* Already owned by someone else? */
 		if (val & MCI_CTL2_CMCI_EN) {
 			clear_bit(i, owned);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
 			continue;
 		}
 
@@ -252,7 +252,7 @@ static void cmci_discover(int banks)
 		/* Did the enable bit stick? -- the bank supports CMCI */
 		if (val & MCI_CTL2_CMCI_EN) {
 			set_bit(i, owned);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
 			/*
 			 * We are able to set thresholds for some banks that
 			 * had a threshold of 0. This means the BIOS has not
@@ -263,7 +263,7 @@ static void cmci_discover(int banks)
 					(val & MCI_CTL2_CMCI_THRESHOLD_MASK))
 				bios_wrong_thresh = 1;
 		} else {
-			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
+			WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
 		}
 	}
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
@@ -284,10 +284,10 @@ void cmci_recheck(void)
 	unsigned long flags;
 	int banks;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
 		return;
 	local_irq_save(flags);
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 	local_irq_restore(flags);
 }
 
@@ -296,12 +296,12 @@ static void __cmci_disable_bank(int bank)
 {
 	u64 val;
 
-	if (!test_bit(bank, __get_cpu_var(mce_banks_owned)))
+	if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
 		return;
 	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_EN;
 	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	__clear_bit(bank, __get_cpu_var(mce_banks_owned));
+	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 16c73022306e..1b8299dd3d91 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -494,7 +494,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
 
 void x86_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -512,7 +512,7 @@ void x86_pmu_disable_all(void)
 
 static void x86_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu_initialized())
 		return;
@@ -529,7 +529,7 @@ static void x86_pmu_disable(struct pmu *pmu)
 
 void x86_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -876,7 +876,7 @@ static void x86_pmu_start(struct perf_event *event, int flags);
 
 static void x86_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	int i, added = cpuc->n_added;
@@ -1030,7 +1030,7 @@ void x86_pmu_enable_event(struct perf_event *event)
  */
 static int x86_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc;
 	int assign[X86_PMC_IDX_MAX];
 	int n, n0, ret;
@@ -1081,7 +1081,7 @@ out:
 
 static void x86_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = event->hw.idx;
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -1160,7 +1160,7 @@ void perf_event_print_debug(void)
 
 void x86_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
@@ -1182,7 +1182,7 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 
 static void x86_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	/*
@@ -1237,7 +1237,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * Some chipsets need to unmask the LVTPC in a particular spot
@@ -1646,7 +1646,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
  */
 static int x86_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];
 	int n, ret;
 
@@ -2005,7 +2005,7 @@ static unsigned long get_segment_base(unsigned int segment)
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+		desc = raw_cpu_ptr(gdt_page.gdt);
 	}
 
 	return get_desc_base(desc + idx);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index beeb7cc07044..28926311aac1 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -699,7 +699,7 @@ __init int amd_pmu_init(void)
 
 void amd_pmu_enable_virt(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	cpuc->perf_ctr_virt_mask = 0;
 
@@ -711,7 +711,7 @@ EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
 
 void amd_pmu_disable_virt(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * We only mask out the Host-only bit so that host-only counting works
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3851def5057c..a73947c53b65 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1174,7 +1174,7 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
 
 static void intel_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
@@ -1187,7 +1187,7 @@ static void intel_pmu_disable_all(void)
 
 static void intel_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	intel_pmu_pebs_enable_all();
 	intel_pmu_lbr_enable_all();
@@ -1221,7 +1221,7 @@ static void intel_pmu_enable_all(int added)
  */
 static void intel_pmu_nhm_workaround(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	static const unsigned long nhm_magic[4] = {
 		0x4300B5,
 		0x4300D2,
@@ -1320,7 +1320,7 @@ static inline bool event_is_checkpointed(struct perf_event *event)
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
@@ -1384,7 +1384,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
 		if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -1478,7 +1478,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	u64 status;
 	int handled;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * No known reason to not always do late ACK,
@@ -1910,7 +1910,7 @@ EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
 
 static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
@@ -1931,7 +1931,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 
 static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 	int idx;
 
@@ -1965,7 +1965,7 @@ static void core_pmu_enable_event(struct perf_event *event)
 
 static void core_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index b1553d05a5cb..46211bcc813e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -474,7 +474,7 @@ void intel_pmu_enable_bts(u64 config)
 
 void intel_pmu_disable_bts(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long debugctlmsr;
 
 	if (!cpuc->ds)
@@ -491,7 +491,7 @@ void intel_pmu_disable_bts(void)
 
 int intel_pmu_drain_bts_buffer(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct bts_record {
 		u64	from;
@@ -669,7 +669,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
@@ -684,7 +684,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -702,7 +702,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 void intel_pmu_pebs_enable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -710,7 +710,7 @@ void intel_pmu_pebs_enable_all(void)
 
 void intel_pmu_pebs_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
@@ -718,7 +718,7 @@ void intel_pmu_pebs_disable_all(void)
 
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
@@ -829,7 +829,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * We cast to the biggest pebs_record but are careful not to
 	 * unconditionally access the 'extra' entries.
 	 */
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
@@ -916,7 +916,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event = cpuc->events[0]; /* PMC0 only */
 	struct pebs_record_core *at, *top;
@@ -957,7 +957,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event = NULL;
 	void *at, *top;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 4af10617de33..45fa730a5283 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -133,7 +133,7 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
@@ -183,7 +183,7 @@ void intel_pmu_lbr_reset(void)
 
 void intel_pmu_lbr_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -203,7 +203,7 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 
 void intel_pmu_lbr_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -220,7 +220,7 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 
 void intel_pmu_lbr_enable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_users)
 		__intel_pmu_lbr_enable();
@@ -228,7 +228,7 @@ void intel_pmu_lbr_enable_all(void)
 
 void intel_pmu_lbr_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_users)
 		__intel_pmu_lbr_disable();
@@ -332,7 +332,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 void intel_pmu_lbr_read(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuc->lbr_users)
 		return;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 619f7699487a..d64f275fe274 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -187,7 +187,7 @@ static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
 
 static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct perf_event *event;
 	unsigned long flags;
 
@@ -234,7 +234,7 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	unsigned long flags;
 
 	spin_lock_irqsave(&pmu->lock, flags);
@@ -244,7 +244,7 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
@@ -278,7 +278,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
@@ -696,7 +696,7 @@ static int __init rapl_pmu_init(void)
 		return -1;
 	}
 
-	pmu = __get_cpu_var(rapl_pmu);
+	pmu = __this_cpu_read(rapl_pmu);
 
 	pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
 		" API unit is 2^-32 Joules,"
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 838fa8772c62..5b0c232d1ee6 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -217,7 +217,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs)
 	int bit, loops;
 	u64 status;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	knc_pmu_disable_all();
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 5d466b7d8609..f2e56783af3d 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -915,7 +915,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 
 static void p4_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -984,7 +984,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
 
 static void p4_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -1004,7 +1004,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		int overflow;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a618fcd2c07d..f5ab56d14287 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -237,7 +237,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 	ced->max_nr_ranges++;
 
 	/* If crashk_low_res is not 0, another range split possible */
-	if (crashk_low_res.end != 0)
+	if (crashk_low_res.end)
 		ced->max_nr_ranges++;
 }
 
@@ -335,9 +335,11 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
 	if (ret)
 		return ret;
 
-	ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
-	if (ret)
-		return ret;
+	if (crashk_low_res.end) {
+		ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+		if (ret)
+			return ret;
+	}
 
 	/* Exclude GART region */
 	if (ced->gart_end) {
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4b0e1dfa2226..b553ed89e5f5 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -449,12 +449,11 @@ sysenter_audit:
 	jnz syscall_trace_entry
 	addl $4,%esp
 	CFI_ADJUST_CFA_OFFSET -4
-	/* %esi already in 8(%esp)	   6th arg: 4th syscall arg */
-	/* %edx already in 4(%esp)	   5th arg: 3rd syscall arg */
-	/* %ecx already in 0(%esp)	   4th arg: 2nd syscall arg */
-	movl %ebx,%ecx			/* 3rd arg: 1st syscall arg */
-	movl %eax,%edx			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_I386,%eax	/* 1st arg: audit arch */
+	movl %esi,4(%esp)		/* 5th arg: 4th syscall arg */
+	movl %edx,(%esp)		/* 4th arg: 3rd syscall arg */
+	/* %ecx already in %ecx		   3rd arg: 2nd syscall arg */
+	movl %ebx,%edx			/* 2nd arg: 1st syscall arg */
+	/* %eax already in %eax		   1st arg: syscall number */
 	call __audit_syscall_entry
 	pushl_cfi %ebx
 	movl PT_EAX(%esp),%eax		/* reload syscall number */
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 5f9cf20cdb68..3d5fb509bdeb 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -108,7 +108,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	int i;
 
 	for (i = 0; i < HBP_NUM; i++) {
-		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
 		if (!*slot) {
 			*slot = bp;
@@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	set_debugreg(info->address, i);
 	__this_cpu_write(cpu_debugreg[i], info->address);
 
-	dr7 = &__get_cpu_var(cpu_dr7);
+	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 |= encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
@@ -146,7 +146,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	int i;
 
 	for (i = 0; i < HBP_NUM; i++) {
-		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
 		if (*slot == bp) {
 			*slot = NULL;
@@ -157,7 +157,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
 		return;
 
-	dr7 = &__get_cpu_var(cpu_dr7);
+	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 &= ~__encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 4d1c746892eb..e4b503d5558c 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -52,13 +52,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	    regs->sp <= curbase + THREAD_SIZE)
 		return;
 
-	irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+	irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
 			STACK_TOP_MARGIN;
-	irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+	irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
 	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
 		return;
 
-	oist = &__get_cpu_var(orig_ist);
+	oist = this_cpu_ptr(&orig_ist);
 	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
 	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
 	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 9642b9b33655..ca05f86481aa 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -26,6 +26,7 @@
 #include <asm/setup.h>
 #include <asm/crash.h>
 #include <asm/efi.h>
+#include <asm/kexec-bzimage64.h>
 
 #define MAX_ELFCOREHDR_STR_LEN	30	/* elfcorehdr=0x<64bit-value> */
 
@@ -267,7 +268,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	return ret;
 }
 
-int bzImage64_probe(const char *buf, unsigned long len)
+static int bzImage64_probe(const char *buf, unsigned long len)
 {
 	int ret = -ENOEXEC;
 	struct setup_header *header;
@@ -325,10 +326,10 @@ int bzImage64_probe(const char *buf, unsigned long len)
 	return ret;
 }
 
-void *bzImage64_load(struct kimage *image, char *kernel,
-		     unsigned long kernel_len, char *initrd,
-		     unsigned long initrd_len, char *cmdline,
-		     unsigned long cmdline_len)
+static void *bzImage64_load(struct kimage *image, char *kernel,
+			    unsigned long kernel_len, char *initrd,
+			    unsigned long initrd_len, char *cmdline,
+			    unsigned long cmdline_len)
 {
 
 	struct setup_header *header;
@@ -514,7 +515,7 @@ out_free_params:
 }
 
 /* This cleanup function is called after various segments have been loaded */
-int bzImage64_cleanup(void *loader_data)
+static int bzImage64_cleanup(void *loader_data)
 {
 	struct bzimage64_data *ldata = loader_data;
 
@@ -528,7 +529,7 @@ int bzImage64_cleanup(void *loader_data)
 }
 
 #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG
-int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
+static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 {
 	bool trusted;
 	int ret;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 3dd8e2c4d74a..f6945bef2cd1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/kprobes.h>
 #include <linux/debugfs.h>
+#include <linux/nmi.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -243,9 +244,9 @@ u32 kvm_read_and_reset_pf_reason(void)
 {
 	u32 reason = 0;
 
-	if (__get_cpu_var(apf_reason).enabled) {
-		reason = __get_cpu_var(apf_reason).reason;
-		__get_cpu_var(apf_reason).reason = 0;
+	if (__this_cpu_read(apf_reason.enabled)) {
+		reason = __this_cpu_read(apf_reason.reason);
+		__this_cpu_write(apf_reason.reason, 0);
 	}
 
 	return reason;
@@ -318,7 +319,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 	 * there's no need for lock or memory barriers.
 	 * An optimization barrier is implied in apic write.
 	 */
-	if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi)))
+	if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
 		return;
 	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
@@ -329,13 +330,13 @@ void kvm_guest_cpu_init(void)
 		return;
 
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
-		u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason));
+		u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
 
 #ifdef CONFIG_PREEMPT
 		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
 #endif
 		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
-		__get_cpu_var(apf_reason).enabled = 1;
+		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
 	}
@@ -344,8 +345,8 @@ void kvm_guest_cpu_init(void)
 		unsigned long pa;
 		/* Size alignment is implied but just to make it explicit. */
 		BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
-		__get_cpu_var(kvm_apic_eoi) = 0;
-		pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi))
+		__this_cpu_write(kvm_apic_eoi, 0);
+		pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
 			| KVM_MSR_ENABLED;
 		wrmsrl(MSR_KVM_PV_EOI_EN, pa);
 	}
@@ -356,11 +357,11 @@ void kvm_guest_cpu_init(void)
 
 static void kvm_pv_disable_apf(void)
 {
-	if (!__get_cpu_var(apf_reason).enabled)
+	if (!__this_cpu_read(apf_reason.enabled))
 		return;
 
 	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
-	__get_cpu_var(apf_reason).enabled = 0;
+	__this_cpu_write(apf_reason.enabled, 0);
 
 	printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
 	       smp_processor_id());
@@ -499,6 +500,13 @@ void __init kvm_guest_init(void)
 #else
 	kvm_guest_cpu_init();
 #endif
+
+	/*
+	 * Hard lockup detection is enabled by default. Disable it, as guests
+	 * can get false positives too easily, for example if the host is
+	 * overcommitted.
+	 */
+	watchdog_enable_hardlockup_detector(false);
 }
 
 static noinline uint32_t __kvm_cpuid_base(void)
@@ -716,7 +724,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	if (in_nmi())
 		return;
 
-	w = &__get_cpu_var(klock_waiting);
+	w = this_cpu_ptr(&klock_waiting);
 	cpu = smp_processor_id();
 	start = spin_time_start();
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 29576c244699..749b0e423419 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1445,12 +1445,12 @@ static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
 {
 #ifdef CONFIG_X86_64
 	if (arch == AUDIT_ARCH_X86_64) {
-		audit_syscall_entry(arch, regs->orig_ax, regs->di,
+		audit_syscall_entry(regs->orig_ax, regs->di,
 				    regs->si, regs->dx, regs->r10);
 	} else
 #endif
 	{
-		audit_syscall_entry(arch, regs->orig_ax, regs->bx,
+		audit_syscall_entry(regs->orig_ax, regs->bx,
 				    regs->cx, regs->dx, regs->si);
 	}
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f7f6a4a157a6..65510f624dfe 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -670,7 +670,7 @@ static int svm_hardware_enable(void)
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
-		__get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT;
+		__this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT);
 	}
 
 
@@ -1313,8 +1313,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR) &&
-	    svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) {
-		__get_cpu_var(current_tsc_ratio) = svm->tsc_ratio;
+	    svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
+		__this_cpu_write(current_tsc_ratio, svm->tsc_ratio);
 		wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio);
 	}
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 04fa1b8298c8..0acac81f198b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -472,6 +472,7 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
+		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -1626,7 +1627,7 @@ static void reload_tss(void)
 	/*
 	 * VT restores TR but not its size.  Useless.
 	 */
-	struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *descs;
 
 	descs = (void *)gdt->address;
@@ -1672,7 +1673,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 
 static unsigned long segment_base(u16 selector)
 {
-	struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *d;
 	unsigned long table_base;
 	unsigned long v;
@@ -1802,7 +1803,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	 */
 	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
 		stts();
-	load_gdt(&__get_cpu_var(host_gdt));
+	load_gdt(this_cpu_ptr(&host_gdt));
 }
 
 static void vmx_load_host_state(struct vcpu_vmx *vmx)
@@ -1832,7 +1833,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	if (vmx->loaded_vmcs->cpu != cpu) {
-		struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+		struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 		unsigned long sysenter_esp;
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
@@ -2771,7 +2772,7 @@ static int hardware_enable(void)
 		ept_sync_global();
 	}
 
-	native_store_gdt(&__get_cpu_var(host_gdt));
+	native_store_gdt(this_cpu_ptr(&host_gdt));
 
 	return 0;
 }
@@ -4267,11 +4268,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	u32 low32, high32;
 	unsigned long tmpl;
 	struct desc_ptr dt;
+	unsigned long cr4;
 
 	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
-	vmcs_writel(HOST_CR4, read_cr4());  /* 22.2.3, 22.2.5 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
+	/* Save the most likely value for this task's CR4 in the VMCS. */
+	cr4 = read_cr4();
+	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
+	vmx->host_state.vmcs_host_cr4 = cr4;
+
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
 	/*
@@ -7514,7 +7520,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long debugctlmsr;
+	unsigned long debugctlmsr, cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
@@ -7540,6 +7546,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
+	cr4 = read_cr4();
+	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+		vmcs_writel(HOST_CR4, cr4);
+		vmx->host_state.vmcs_host_cr4 = cr4;
+	}
+
 	/* When single-stepping over STI and MOV SS, we must clear the
 	 * corresponding interruptibility bits in the guest state. Otherwise
 	 * vmentry fails as it then expects bit 14 (BS) in pending debug
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5430e4b0af29..34c8f94331f8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1559,7 +1559,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
 	if (unlikely(this_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index baff1da354e0..af78e50ca6ce 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -86,6 +86,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
+	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -108,12 +109,23 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	pfn      = phys_addr >> PAGE_SHIFT;
-	last_pfn = last_addr >> PAGE_SHIFT;
-	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-				  __ioremap_check_ram) == 1)
+	/* First check if whole region can be identified as RAM or not */
+	ram_region = region_is_ram(phys_addr, size);
+	if (ram_region > 0) {
+		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
+				(unsigned long int)phys_addr,
+				(unsigned long int)last_addr);
 		return NULL;
+	}
 
+	/* If could not be identified(-1), check page by page */
+	if (ram_region < 0) {
+		pfn      = phys_addr >> PAGE_SHIFT;
+		last_pfn = last_addr >> PAGE_SHIFT;
+		if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+					  __ioremap_check_ram) == 1)
+			return NULL;
+	}
 	/*
 	 * Mappings have to be page-aligned
 	 */
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index dd89a13f1051..b4f2e7e9e907 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -140,7 +140,7 @@ static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context);
 
 bool kmemcheck_active(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	return data->balance > 0;
 }
@@ -148,7 +148,7 @@ bool kmemcheck_active(struct pt_regs *regs)
 /* Save an address that needs to be shown/hidden */
 static void kmemcheck_save_addr(unsigned long addr)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr));
 	data->addr[data->n_addrs++] = addr;
@@ -156,7 +156,7 @@ static void kmemcheck_save_addr(unsigned long addr)
 
 static unsigned int kmemcheck_show_all(void)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	unsigned int i;
 	unsigned int n;
 
@@ -169,7 +169,7 @@ static unsigned int kmemcheck_show_all(void)
 
 static unsigned int kmemcheck_hide_all(void)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	unsigned int i;
 	unsigned int n;
 
@@ -185,7 +185,7 @@ static unsigned int kmemcheck_hide_all(void)
  */
 void kmemcheck_show(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	BUG_ON(!irqs_disabled());
 
@@ -226,7 +226,7 @@ void kmemcheck_show(struct pt_regs *regs)
  */
 void kmemcheck_hide(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	int n;
 
 	BUG_ON(!irqs_disabled());
@@ -528,7 +528,7 @@ static void kmemcheck_access(struct pt_regs *regs,
 	const uint8_t *insn_primary;
 	unsigned int size;
 
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	/* Recursive fault -- ouch. */
 	if (data->busy) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index d221374d5ce8..1a883705a12a 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -463,6 +463,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+	unsigned long start, end;
+	struct memblock_region *r;
+
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
+	/* Mark all kernel nodes. */
+	for_each_memblock(reserved, r)
+		node_set(r->nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
 	unsigned long uninitialized_var(pfn_align);
@@ -481,6 +517,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	}
 
 	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, alloc node data won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
+	/*
 	 * If sections array is gonna be used for pfn -> nid mapping, check
 	 * whether its granularity is fine enough.
 	 */
@@ -548,41 +593,6 @@ static void __init numa_init_array(void)
 	}
 }
 
-static void __init numa_clear_kernel_node_hotplug(void)
-{
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
-	struct memblock_region *r;
-
-	/*
-	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
-	 */
-	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
-	}
-
-	/* Mark all kernel nodes. */
-	for_each_memblock(reserved, r)
-		node_set(r->nid, numa_kernel_nodes);
-
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
-	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
-
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
-
-		memblock_clear_hotplug(start, end - start);
-	}
-}
-
 static int __init numa_init(int (*init_func)(void))
 {
 	int i;
@@ -637,15 +647,6 @@ static int __init numa_init(int (*init_func)(void))
 	}
 	numa_init_array();
 
-	/*
-	 * At very early time, the kernel have to use some memory such as
-	 * loading the kernel image. We cannot prevent this anyway. So any
-	 * node the kernel resides in should be un-hotpluggable.
-	 *
-	 * And when we come here, numa_init() won't fail.
-	 */
-	numa_clear_kernel_node_hotplug();
-
 	return 0;
 }
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index d56cd1f515bd..3f627345d51c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -182,12 +182,17 @@ struct jit_context {
 	bool seen_ld_abs;
 };
 
+/* maximum number of bytes emitted while JITing one eBPF insn */
+#define BPF_MAX_INSN_SIZE	128
+#define BPF_INSN_SAFETY		64
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
 	struct bpf_insn *insn = bpf_prog->insnsi;
 	int insn_cnt = bpf_prog->len;
-	u8 temp[64];
+	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i;
 	int proglen = 0;
 	u8 *prog = temp;
@@ -225,7 +230,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	EMIT2(0x31, 0xc0); /* xor eax, eax */
 	EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
 
-	if (ctx->seen_ld_abs) {
+	if (seen_ld_abs) {
 		/* r9d : skb->len - skb->data_len (headlen)
 		 * r10 : skb->data
 		 */
@@ -685,7 +690,7 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
-			if (ctx->seen_ld_abs) {
+			if (seen_ld_abs) {
 				EMIT2(0x41, 0x52); /* push %r10 */
 				EMIT2(0x41, 0x51); /* push %r9 */
 				/* need to adjust jmp offset, since
@@ -699,7 +704,7 @@ xadd:			if (is_imm8(insn->off))
 				return -EINVAL;
 			}
 			EMIT1_off32(0xE8, jmp_offset);
-			if (ctx->seen_ld_abs) {
+			if (seen_ld_abs) {
 				EMIT2(0x41, 0x59); /* pop %r9 */
 				EMIT2(0x41, 0x5A); /* pop %r10 */
 			}
@@ -804,7 +809,8 @@ emit_jmp:
 			goto common_load;
 		case BPF_LD | BPF_ABS | BPF_W:
 			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load:		ctx->seen_ld_abs = true;
+common_load:
+			ctx->seen_ld_abs = seen_ld_abs = true;
 			jmp_offset = func - (image + addrs[i]);
 			if (!func || !is_simm32(jmp_offset)) {
 				pr_err("unsupported bpf func %d addr %p image %p\n",
@@ -878,6 +884,11 @@ common_load:		ctx->seen_ld_abs = true;
 		}
 
 		ilen = prog - temp;
+		if (ilen > BPF_MAX_INSN_SIZE) {
+			pr_err("bpf_jit_compile fatal insn size error\n");
+			return -EFAULT;
+		}
+
 		if (image) {
 			if (unlikely(proglen + ilen > oldproglen)) {
 				pr_err("bpf_jit_compile fatal error\n");
@@ -934,9 +945,11 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 			goto out;
 		}
 		if (image) {
-			if (proglen != oldproglen)
+			if (proglen != oldproglen) {
 				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
 				       proglen, oldproglen);
+				goto out;
+			}
 			break;
 		}
 		if (proglen == oldproglen) {
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 379e8bd0deea..1d2e6392f5fa 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -64,11 +64,11 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
 {
 	if (ctr_running)
-		model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+		model->check_ctrs(regs, this_cpu_ptr(&cpu_msrs));
 	else if (!nmi_enabled)
 		return NMI_DONE;
 	else
-		model->stop(&__get_cpu_var(cpu_msrs));
+		model->stop(this_cpu_ptr(&cpu_msrs));
 	return NMI_HANDLED;
 }
 
@@ -91,7 +91,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs)
 
 static void nmi_cpu_start(void *dummy)
 {
-	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+	struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
 	if (!msrs->controls)
 		WARN_ON_ONCE(1);
 	else
@@ -111,7 +111,7 @@ static int nmi_start(void)
 
 static void nmi_cpu_stop(void *dummy)
 {
-	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+	struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
 	if (!msrs->controls)
 		WARN_ON_ONCE(1);
 	else
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 98ab13058f89..ad1d91f475ab 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -372,7 +372,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+	return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c89c93320c12..c6b146e67116 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -63,8 +63,8 @@
 
 static struct uv_hub_nmi_s **uv_hub_nmi_list;
 
-DEFINE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_nmi);
+DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi);
 
 static unsigned long nmi_mmr;
 static unsigned long nmi_mmr_clear;
@@ -215,7 +215,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
 	int nmi = 0;
 
 	local64_inc(&uv_nmi_count);
-	uv_cpu_nmi.queries++;
+	this_cpu_inc(uv_cpu_nmi.queries);
 
 	do {
 		nmi = atomic_read(&hub_nmi->in_nmi);
@@ -293,7 +293,7 @@ static void uv_nmi_nr_cpus_ping(void)
 	int cpu;
 
 	for_each_cpu(cpu, uv_nmi_cpu_mask)
-		atomic_set(&uv_cpu_nmi_per(cpu).pinging, 1);
+		uv_cpu_nmi_per(cpu).pinging = 1;
 
 	apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI);
 }
@@ -304,8 +304,8 @@ static void uv_nmi_cleanup_mask(void)
 	int cpu;
 
 	for_each_cpu(cpu, uv_nmi_cpu_mask) {
-		atomic_set(&uv_cpu_nmi_per(cpu).pinging, 0);
-		atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_OUT);
+		uv_cpu_nmi_per(cpu).pinging =  0;
+		uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_OUT;
 		cpumask_clear_cpu(cpu, uv_nmi_cpu_mask);
 	}
 }
@@ -328,7 +328,7 @@ static int uv_nmi_wait_cpus(int first)
 		int loop_delay = uv_nmi_loop_delay;
 
 		for_each_cpu(j, uv_nmi_cpu_mask) {
-			if (atomic_read(&uv_cpu_nmi_per(j).state)) {
+			if (uv_cpu_nmi_per(j).state) {
 				cpumask_clear_cpu(j, uv_nmi_cpu_mask);
 				if (++k >= n)
 					break;
@@ -359,7 +359,7 @@ static int uv_nmi_wait_cpus(int first)
 static void uv_nmi_wait(int master)
 {
 	/* indicate this cpu is in */
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_IN);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN);
 
 	/* if not the first cpu in (the master), then we are a slave cpu */
 	if (!master)
@@ -419,7 +419,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
 			"UV:%sNMI process trace for CPU %d\n", dots, cpu);
 		show_regs(regs);
 	}
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
 }
 
 /* Trigger a slave cpu to dump it's state */
@@ -427,20 +427,20 @@ static void uv_nmi_trigger_dump(int cpu)
 {
 	int retry = uv_nmi_trigger_delay;
 
-	if (atomic_read(&uv_cpu_nmi_per(cpu).state) != UV_NMI_STATE_IN)
+	if (uv_cpu_nmi_per(cpu).state != UV_NMI_STATE_IN)
 		return;
 
-	atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP);
+	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP;
 	do {
 		cpu_relax();
 		udelay(10);
-		if (atomic_read(&uv_cpu_nmi_per(cpu).state)
+		if (uv_cpu_nmi_per(cpu).state
 				!= UV_NMI_STATE_DUMP)
 			return;
 	} while (--retry > 0);
 
 	pr_crit("UV: CPU %d stuck in process dump function\n", cpu);
-	atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP_DONE);
+	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE;
 }
 
 /* Wait until all cpus ready to exit */
@@ -488,7 +488,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
 	} else {
 		while (!atomic_read(&uv_nmi_slave_continue))
 			cpu_relax();
-		while (atomic_read(&uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
+		while (this_cpu_read(uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
 			cpu_relax();
 		uv_nmi_dump_state_cpu(cpu, regs);
 	}
@@ -615,7 +615,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 	local_irq_save(flags);
 
 	/* If not a UV System NMI, ignore */
-	if (!atomic_read(&uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
+	if (!this_cpu_read(uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
 		local_irq_restore(flags);
 		return NMI_DONE;
 	}
@@ -639,7 +639,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 		uv_call_kgdb_kdb(cpu, regs, master);
 
 	/* Clear per_cpu "in nmi" flag */
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_OUT);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT);
 
 	/* Clear MMR NMI flag on each hub */
 	uv_clear_nmi(cpu);
@@ -666,16 +666,16 @@ static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs)
 {
 	int ret;
 
-	uv_cpu_nmi.queries++;
-	if (!atomic_read(&uv_cpu_nmi.pinging)) {
+	this_cpu_inc(uv_cpu_nmi.queries);
+	if (!this_cpu_read(uv_cpu_nmi.pinging)) {
 		local64_inc(&uv_nmi_ping_misses);
 		return NMI_DONE;
 	}
 
-	uv_cpu_nmi.pings++;
+	this_cpu_inc(uv_cpu_nmi.pings);
 	local64_inc(&uv_nmi_ping_count);
 	ret = uv_handle_nmi(reason, regs);
-	atomic_set(&uv_cpu_nmi.pinging, 0);
+	this_cpu_write(uv_cpu_nmi.pinging, 0);
 	return ret;
 }
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 5c86786bbfd2..a244237f3cfa 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -365,7 +365,7 @@ __setup("uvrtcevt", uv_enable_evt_rtc);
 
 static __init void uv_rtc_register_clockevents(struct work_struct *dummy)
 {
-	struct clock_event_device *ced = &__get_cpu_var(cpu_ced);
+	struct clock_event_device *ced = this_cpu_ptr(&cpu_ced);
 
 	*ced = clock_event_device_uv;
 	ced->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 899dd2454256..f52e033557c9 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -18,8 +18,9 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 
 targets += kexec-purgatory.c
 
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
 quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = cat $(obj)/purgatory.ro | $(objtree)/scripts/basic/bin2c kexec_purgatory > $(obj)/kexec-purgatory.c
+      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
 
 $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
 	$(call if_changed,bin2c)
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index 54f8102ccde5..e59eef20647b 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -47,8 +47,6 @@ struct user_desc;
 
 #ifdef CONFIG_X86_32
 
-#define HOST_AUDIT_ARCH AUDIT_ARCH_I386
-
 extern int ptrace_get_thread_area(struct task_struct *child, int idx,
                                   struct user_desc __user *user_desc);
 
@@ -57,8 +55,6 @@ extern int ptrace_set_thread_area(struct task_struct *child, int idx,
 
 #else
 
-#define HOST_AUDIT_ARCH AUDIT_ARCH_X86_64
-
 #define PT_REGS_R8(r) UPT_R8(&(r)->regs)
 #define PT_REGS_R9(r) UPT_R9(&(r)->regs)
 #define PT_REGS_R10(r) UPT_R10(&(r)->regs)
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
new file mode 100644
index 000000000000..9fe77b7b5a0e
--- /dev/null
+++ b/arch/x86/um/asm/syscall.h
@@ -0,0 +1,15 @@
+#ifndef __UM_ASM_SYSCALL_H
+#define __UM_ASM_SYSCALL_H
+
+#include <uapi/linux/audit.h>
+
+static inline int syscall_get_arch(void)
+{
+#ifdef CONFIG_X86_32
+	return AUDIT_ARCH_I386;
+#else
+	return AUDIT_ARCH_X86_64;
+#endif
+}
+
+#endif /* __UM_ASM_SYSCALL_H */
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index 8d0c420465cc..fa4b8b9841ff 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -214,242 +214,3 @@ csum_partial:
 	ret
 				
 #endif
-
-/*
-unsigned int csum_partial_copy_generic (const char *src, char *dst,
-				  int len, int sum, int *src_err_ptr, int *dst_err_ptr)
- */ 
-
-/*
- * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- *	  DST definitions? It's damn hard to trigger all cases.  I hope I got
- *	  them all but there's no guarantee.
- */
-
-#define SRC(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE(9999b, 6001f)
-
-#define DST(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE(9999b, 6002f)
-
-.align 4
-
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
-#define ARGBASE 16		
-#define FP		12
-
-csum_partial_copy_generic_i386:
-	subl  $4,%esp	
-	pushl %edi
-	pushl %esi
-	pushl %ebx
-	movl ARGBASE+16(%esp),%eax	# sum
-	movl ARGBASE+12(%esp),%ecx	# len
-	movl ARGBASE+4(%esp),%esi	# src
-	movl ARGBASE+8(%esp),%edi	# dst
-
-	testl $2, %edi			# Check alignment. 
-	jz 2f				# Jump if alignment is ok.
-	subl $2, %ecx			# Alignment uses up two bytes.
-	jae 1f				# Jump if we had at least two bytes.
-	addl $2, %ecx			# ecx was < 2.  Deal with it.
-	jmp 4f
-SRC(1:	movw (%esi), %bx	)
-	addl $2, %esi
-DST(	movw %bx, (%edi)	)
-	addl $2, %edi
-	addw %bx, %ax	
-	adcl $0, %eax
-2:
-	movl %ecx, FP(%esp)
-	shrl $5, %ecx
-	jz 2f
-	testl %esi, %esi
-SRC(1:	movl (%esi), %ebx	)
-SRC(	movl 4(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 4(%edi)	)
-
-SRC(	movl 8(%esi), %ebx	)
-SRC(	movl 12(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 8(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 12(%edi)	)
-
-SRC(	movl 16(%esi), %ebx 	)
-SRC(	movl 20(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 16(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 20(%edi)	)
-
-SRC(	movl 24(%esi), %ebx	)
-SRC(	movl 28(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 24(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 28(%edi)	)
-
-	lea 32(%esi), %esi
-	lea 32(%edi), %edi
-	dec %ecx
-	jne 1b
-	adcl $0, %eax
-2:	movl FP(%esp), %edx
-	movl %edx, %ecx
-	andl $0x1c, %edx
-	je 4f
-	shrl $2, %edx			# This clears CF
-SRC(3:	movl (%esi), %ebx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
-	lea 4(%esi), %esi
-	lea 4(%edi), %edi
-	dec %edx
-	jne 3b
-	adcl $0, %eax
-4:	andl $3, %ecx
-	jz 7f
-	cmpl $2, %ecx
-	jb 5f
-SRC(	movw (%esi), %cx	)
-	leal 2(%esi), %esi
-DST(	movw %cx, (%edi)	)
-	leal 2(%edi), %edi
-	je 6f
-	shll $16,%ecx
-SRC(5:	movb (%esi), %cl	)
-DST(	movb %cl, (%edi)	)
-6:	addl %ecx, %eax
-	adcl $0, %eax
-7:
-5000:
-
-# Exception handler:
-.section .fixup, "ax"							
-
-6001:
-	movl ARGBASE+20(%esp), %ebx	# src_err_ptr
-	movl $-EFAULT, (%ebx)
-
-	# zero the complete destination - computing the rest
-	# is too much work 
-	movl ARGBASE+8(%esp), %edi	# dst
-	movl ARGBASE+12(%esp), %ecx	# len
-	xorl %eax,%eax
-	rep ; stosb
-
-	jmp 5000b
-
-6002:
-	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT,(%ebx)
-	jmp 5000b
-
-.previous
-
-	popl %ebx
-	popl %esi
-	popl %edi
-	popl %ecx			# equivalent to addl $4,%esp
-	ret	
-
-#else
-
-/* Version for PentiumII/PPro */
-
-#define ROUND1(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
-	addl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	; 
-
-#define ROUND(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
-	adcl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	;
-
-#define ARGBASE 12
-		
-csum_partial_copy_generic_i386:
-	pushl %ebx
-	pushl %edi
-	pushl %esi
-	movl ARGBASE+4(%esp),%esi	#src
-	movl ARGBASE+8(%esp),%edi	#dst	
-	movl ARGBASE+12(%esp),%ecx	#len
-	movl ARGBASE+16(%esp),%eax	#sum
-#	movl %ecx, %edx  
-	movl %ecx, %ebx  
-	movl %esi, %edx
-	shrl $6, %ecx     
-	andl $0x3c, %ebx  
-	negl %ebx
-	subl %ebx, %esi  
-	subl %ebx, %edi  
-	lea  -1(%esi),%edx
-	andl $-32,%edx
-	lea 3f(%ebx,%ebx), %ebx
-	testl %esi, %esi 
-	jmp *%ebx
-1:	addl $64,%esi
-	addl $64,%edi 
-	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
-	ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)	
-	ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)	
-	ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)	
-	ROUND (-16) ROUND(-12) ROUND(-8)  ROUND(-4)	
-3:	adcl $0,%eax
-	addl $64, %edx
-	dec %ecx
-	jge 1b
-4:	movl ARGBASE+12(%esp),%edx	#len
-	andl $3, %edx
-	jz 7f
-	cmpl $2, %edx
-	jb 5f
-SRC(	movw (%esi), %dx         )
-	leal 2(%esi), %esi
-DST(	movw %dx, (%edi)         )
-	leal 2(%edi), %edi
-	je 6f
-	shll $16,%edx
-5:
-SRC(	movb (%esi), %dl         )
-DST(	movb %dl, (%edi)         )
-6:	addl %edx, %eax
-	adcl $0, %eax
-7:
-.section .fixup, "ax"
-6001:	movl	ARGBASE+20(%esp), %ebx	# src_err_ptr	
-	movl $-EFAULT, (%ebx)
-	# zero the complete destination (computing the rest is too much work)
-	movl ARGBASE+8(%esp),%edi	# dst
-	movl ARGBASE+12(%esp),%ecx	# len
-	xorl %eax,%eax
-	rep; stosb
-	jmp 7b
-6002:	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT, (%ebx)
-	jmp  7b			
-.previous				
-
-	popl %esi
-	popl %edi
-	popl %ebx
-	ret
-				
-#undef ROUND
-#undef ROUND1		
-		
-#endif
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index acb0effd8077..1a3f0445432a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -821,7 +821,7 @@ static void xen_convert_trap_info(const struct desc_ptr *desc,
 
 void xen_copy_trap_info(struct trap_info *traps)
 {
-	const struct desc_ptr *desc = &__get_cpu_var(idt_desc);
+	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
 
 	xen_convert_trap_info(desc, traps);
 }
@@ -838,7 +838,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
 
 	spin_lock(&lock);
 
-	__get_cpu_var(idt_desc) = *desc;
+	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
 
 	xen_convert_trap_info(desc, traps);
 
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 0d82003e76ad..ea54a08d8301 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,7 +54,7 @@ DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 void xen_mc_flush(void)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_entry *mc;
 	int ret = 0;
 	unsigned long flags;
@@ -131,7 +131,7 @@ void xen_mc_flush(void)
 
 struct multicall_space __xen_mc_entry(size_t args)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_space ret;
 	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
@@ -162,7 +162,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 
 struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_space ret = { NULL, NULL };
 
 	BUG_ON(preemptible());
@@ -192,7 +192,7 @@ out:
 
 void xen_mc_callback(void (*fn)(void *), void *data)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct callback *cb;
 
 	if (b->cbidx == MC_BATCH) {
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 0ba5f3b967f0..23b45eb9a89c 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -109,7 +109,7 @@ static bool xen_pvspin = true;
 __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
 	int irq = __this_cpu_read(lock_kicker_irq);
-	struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+	struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
 	int cpu = smp_processor_id();
 	u64 start;
 	unsigned long flags;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5718b0b58b60..a1d430b112b3 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -80,7 +80,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
 	BUG_ON(preemptible());
 
-	state = &__get_cpu_var(xen_runstate);
+	state = this_cpu_ptr(&xen_runstate);
 
 	/*
 	 * The runstate info is always updated by the hypervisor on
@@ -123,7 +123,7 @@ static void do_stolen_accounting(void)
 
 	WARN_ON(state.state != RUNSTATE_running);
 
-	snap = &__get_cpu_var(xen_runstate_snapshot);
+	snap = this_cpu_ptr(&xen_runstate_snapshot);
 
 	/* work out how much time the VCPU has not been runn*ing*  */
 	runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
@@ -158,7 +158,7 @@ cycle_t xen_clocksource_read(void)
 	cycle_t ret;
 
 	preempt_disable_notrace();
-	src = &__get_cpu_var(xen_vcpu)->time;
+	src = this_cpu_ptr(&xen_vcpu->time);
 	ret = pvclock_clocksource_read(src);
 	preempt_enable_notrace();
 	return ret;
@@ -397,7 +397,7 @@ static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.
 
 static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = &__get_cpu_var(xen_clock_events).evt;
+	struct clock_event_device *evt = this_cpu_ptr(&xen_clock_events.evt);
 	irqreturn_t ret;
 
 	ret = IRQ_NONE;
@@ -460,7 +460,7 @@ void xen_setup_cpu_clockevents(void)
 {
 	BUG_ON(preemptible());
 
-	clockevents_register_device(&__get_cpu_var(xen_clock_events).evt);
+	clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt));
 }
 
 void xen_timer_resume(void)
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 562fac664751..4d54b481123b 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -342,7 +342,7 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 		do_syscall_trace();
 
 #if 0
-	audit_syscall_entry(current, AUDIT_ARCH_XTENSA..);
+	audit_syscall_entry(...);
 #endif
 }