254 files changed, 3758 insertions, 2741 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 8d2ae24b9f4a..1feb169274fe 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -407,6 +407,12 @@ config CLONE_BACKWARDS2
         help
           Architecture has the first two arguments of clone(2) swapped.
 
+config CLONE_BACKWARDS3
+        bool
+        help
+          Architecture has tls passed as the 3rd argument of clone(2),
+          not the 5th one.
+
 config ODD_RT_SIGACTION
         bool
         help
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
index 99c10475d477..9c548c7cf001 100644
--- a/arch/arc/lib/strchr-700.S
+++ b/arch/arc/lib/strchr-700.S
@@ -39,9 +39,18 @@ ARC_ENTRY strchr
         ld.a    r2,[r0,4]
         sub     r12,r6,r7
         bic     r12,r12,r6
+#ifdef __LITTLE_ENDIAN__
         and     r7,r12,r4
         breq    r7,0,.Loop ; For speed, we want this branch to be unaligned.
         b       .Lfound_char ; Likewise this one.
+#else
+        and     r12,r12,r4
+        breq    r12,0,.Loop ; For speed, we want this branch to be unaligned.
+        lsr_s   r12,r12,7
+        bic     r2,r7,r6
+        b.d     .Lfound_char_b
+        and_s   r2,r2,r12
+#endif
 ; /* We require this code address to be unaligned for speed...  */
 .Laligned:
         ld_s    r2,[r0]
@@ -95,6 +104,7 @@ ARC_ENTRY strchr
         lsr     r7,r7,7
 
         bic     r2,r7,r6
+.Lfound_char_b:
         norm    r2,r2
         sub_s   r0,r0,4
         asr_s   r2,r2,3
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 43594d5116ef..cd5c1c97b043 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2064,8 +2064,7 @@ config KEXEC
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
-          initially work for you.  It may help to enable device hotplugging
-          support.
+          initially work for you.
 
 config ATAGS_PROC
         bool "Export atags in procfs"
diff --git a/arch/arm/boot/dts/am335x-bone.dts b/arch/arm/boot/dts/am335x-bone.dts
index 444b4ede0d60..d318987d44a1 100644
--- a/arch/arm/boot/dts/am335x-bone.dts
+++ b/arch/arm/boot/dts/am335x-bone.dts
@@ -120,6 +120,35 @@
                         status = "okay";
                 };
 
+                musb: usb@47400000 {
+                        status = "okay";
+
+                        control@44e10000 {
+                                status = "okay";
+                        };
+
+                        usb-phy@47401300 {
+                                status = "okay";
+                        };
+
+                        usb-phy@47401b00 {
+                                status = "okay";
+                        };
+
+                        usb@47401000 {
+                                status = "okay";
+                        };
+
+                        usb@47401800 {
+                                status = "okay";
+                                dr_mode = "host";
+                        };
+
+                        dma-controller@07402000  {
+                                status = "okay";
+                        };
+                };
+
                 i2c0: i2c@44e0b000 {
                         pinctrl-names = "default";
                         pinctrl-0 = <&i2c0_pins>;
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 3aee1a43782d..e8ec8756e498 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -171,6 +171,35 @@
                         };
                 };
 
+                musb: usb@47400000 {
+                        status = "okay";
+
+                        control@44e10000 {
+                                status = "okay";
+                        };
+
+                        usb-phy@47401300 {
+                                status = "okay";
+                        };
+
+                        usb-phy@47401b00 {
+                                status = "okay";
+                        };
+
+                        usb@47401000 {
+                                status = "okay";
+                        };
+
+                        usb@47401800 {
+                                status = "okay";
+                                dr_mode = "host";
+                        };
+
+                        dma-controller@07402000  {
+                                status = "okay";
+                        };
+                };
+
                 i2c1: i2c@4802a000 {
                         pinctrl-names = "default";
                         pinctrl-0 = <&i2c1_pins>;
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 0c8ad173d2b0..4f339fa91c57 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -14,6 +14,7 @@
 /dts-v1/;
 
 #include "am33xx.dtsi"
+#include <dt-bindings/pwm/pwm.h>
 
 / {
         model = "TI AM335x EVM-SK";
@@ -207,6 +208,22 @@
                         };
                 };
 
+                musb: usb@47400000 {
+                        status = "okay";
+
+                        control@44e10000 {
+                                status = "okay";
+                        };
+
+                        usb-phy@47401300 {
+                                status = "okay";
+                        };
+
+                        usb@47401000 {
+                                status = "okay";
+                        };
+                };
+
                 epwmss2: epwmss@48304000 {
                         status = "okay";
 
@@ -298,7 +315,7 @@
 
         backlight {
                 compatible = "pwm-backlight";
-                pwms = <&ecap2 0 50000 1>;
+                pwms = <&ecap2 0 50000 PWM_POLARITY_INVERTED>;
                 brightness-levels = <0 58 61 66 75 90 125 170 255>;
                 default-brightness-level = <8>;
         };
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 38b446ba1ce1..f9c5da9c7fe1 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -26,6 +26,10 @@
                 serial5 = &uart5;
                 d_can0 = &dcan0;
                 d_can1 = &dcan1;
+                usb0 = &usb0;
+                usb1 = &usb1;
+                phy0 = &usb0_phy;
+                phy1 = &usb1_phy;
         };
 
         cpus {
@@ -333,21 +337,132 @@
                         status = "disabled";
                 };
 
-                usb@47400000 {
-                        compatible = "ti,musb-am33xx";
-                        reg = <0x47400000 0x1000        /* usbss */
-                               0x47401000 0x800         /* musb instance 0 */
-                               0x47401800 0x800>;       /* musb instance 1 */
-                        interrupts = <17                /* usbss */
-                                      18                /* musb instance 0 */
-                                      19>;              /* musb instance 1 */
-                        multipoint = <1>;
-                        num-eps = <16>;
-                        ram-bits = <12>;
-                        port0-mode = <3>;
-                        port1-mode = <3>;
-                        power = <250>;
+                usb: usb@47400000 {
+                        compatible = "ti,am33xx-usb";
+                        reg = <0x47400000 0x1000>;
+                        ranges;
+                        #address-cells = <1>;
+                        #size-cells = <1>;
                         ti,hwmods = "usb_otg_hs";
+                        status = "disabled";
+
+                        ctrl_mod: control@44e10000 {
+                                compatible = "ti,am335x-usb-ctrl-module";
+                                reg = <0x44e10620 0x10
+                                        0x44e10648 0x4>;
+                                reg-names = "phy_ctrl", "wakeup";
+                                status = "disabled";
+                        };
+
+                        usb0_phy: usb-phy@47401300 {
+                                compatible = "ti,am335x-usb-phy";
+                                reg = <0x47401300 0x100>;
+                                reg-names = "phy";
+                                status = "disabled";
+                                ti,ctrl_mod = <&ctrl_mod>;
+                        };
+
+                        usb0: usb@47401000 {
+                                compatible = "ti,musb-am33xx";
+                                status = "disabled";
+                                reg = <0x47401400 0x400
+                                        0x47401000 0x200>;
+                                reg-names = "mc", "control";
+
+                                interrupts = <18>;
+                                interrupt-names = "mc";
+                                dr_mode = "otg";
+                                mentor,multipoint = <1>;
+                                mentor,num-eps = <16>;
+                                mentor,ram-bits = <12>;
+                                mentor,power = <500>;
+                                phys = <&usb0_phy>;
+
+                                dmas = <&cppi41dma  0 0 &cppi41dma  1 0
+                                        &cppi41dma  2 0 &cppi41dma  3 0
+                                        &cppi41dma  4 0 &cppi41dma  5 0
+                                        &cppi41dma  6 0 &cppi41dma  7 0
+                                        &cppi41dma  8 0 &cppi41dma  9 0
+                                        &cppi41dma 10 0 &cppi41dma 11 0
+                                        &cppi41dma 12 0 &cppi41dma 13 0
+                                        &cppi41dma 14 0 &cppi41dma  0 1
+                                        &cppi41dma  1 1 &cppi41dma  2 1
+                                        &cppi41dma  3 1 &cppi41dma  4 1
+                                        &cppi41dma  5 1 &cppi41dma  6 1
+                                        &cppi41dma  7 1 &cppi41dma  8 1
+                                        &cppi41dma  9 1 &cppi41dma 10 1
+                                        &cppi41dma 11 1 &cppi41dma 12 1
+                                        &cppi41dma 13 1 &cppi41dma 14 1>;
+                                dma-names =
+                                        "rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7",
+                                        "rx8", "rx9", "rx10", "rx11", "rx12", "rx13",
+                                        "rx14", "rx15",
+                                        "tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7",
+                                        "tx8", "tx9", "tx10", "tx11", "tx12", "tx13",
+                                        "tx14", "tx15";
+                        };
+
+                        usb1_phy: usb-phy@47401b00 {
+                                compatible = "ti,am335x-usb-phy";
+                                reg = <0x47401b00 0x100>;
+                                reg-names = "phy";
+                                status = "disabled";
+                                ti,ctrl_mod = <&ctrl_mod>;
+                        };
+
+                        usb1: usb@47401800 {
+                                compatible = "ti,musb-am33xx";
+                                status = "disabled";
+                                reg = <0x47401c00 0x400
+                                        0x47401800 0x200>;
+                                reg-names = "mc", "control";
+                                interrupts = <19>;
+                                interrupt-names = "mc";
+                                dr_mode = "otg";
+                                mentor,multipoint = <1>;
+                                mentor,num-eps = <16>;
+                                mentor,ram-bits = <12>;
+                                mentor,power = <500>;
+                                phys = <&usb1_phy>;
+
+                                dmas = <&cppi41dma 15 0 &cppi41dma 16 0
+                                        &cppi41dma 17 0 &cppi41dma 18 0
+                                        &cppi41dma 19 0 &cppi41dma 20 0
+                                        &cppi41dma 21 0 &cppi41dma 22 0
+                                        &cppi41dma 23 0 &cppi41dma 24 0
+                                        &cppi41dma 25 0 &cppi41dma 26 0
+                                        &cppi41dma 27 0 &cppi41dma 28 0
+                                        &cppi41dma 29 0 &cppi41dma 15 1
+                                        &cppi41dma 16 1 &cppi41dma 17 1
+                                        &cppi41dma 18 1 &cppi41dma 19 1
+                                        &cppi41dma 20 1 &cppi41dma 21 1
+                                        &cppi41dma 22 1 &cppi41dma 23 1
+                                        &cppi41dma 24 1 &cppi41dma 25 1
+                                        &cppi41dma 26 1 &cppi41dma 27 1
+                                        &cppi41dma 28 1 &cppi41dma 29 1>;
+                                dma-names =
+                                        "rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7",
+                                        "rx8", "rx9", "rx10", "rx11", "rx12", "rx13",
+                                        "rx14", "rx15",
+                                        "tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7",
+                                        "tx8", "tx9", "tx10", "tx11", "tx12", "tx13",
+                                        "tx14", "tx15";
+                        };
+
+                        cppi41dma: dma-controller@07402000 {
+                                compatible = "ti,am3359-cppi41";
+                                reg =  <0x47400000 0x1000
+                                        0x47402000 0x1000
+                                        0x47403000 0x1000
+                                        0x47404000 0x4000>;
+                                reg-names = "glue", "controller", "scheduler", "queuemgr";
+                                interrupts = <17>;
+                                interrupt-names = "glue";
+                                #dma-cells = <2>;
+                                #dma-channels = <30>;
+                                #dma-requests = <256>;
+                                status = "disabled";
+                        };
                 };
 
                 epwmss0: epwmss@48300000 {
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index d59b70c6a6a0..3d77dbe406f4 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -14,11 +14,11 @@
         compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9";
 
         chosen {
-                bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
+                bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
         };
 
         memory {
-                reg = <0x20000000 0x10000000>;
+                reg = <0x20000000 0x8000000>;
         };
 
         clocks {
diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi
index b753855b2058..49e3c45818c2 100644
--- a/arch/arm/boot/dts/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi
@@ -94,8 +94,9 @@
 
                 usb0: ohci@00600000 {
                         status = "okay";
-                        num-ports = <2>;
-                        atmel,vbus-gpio = <&pioD 19 GPIO_ACTIVE_LOW
+                        num-ports = <3>;
+                        atmel,vbus-gpio = <0 /* &pioD 18 GPIO_ACTIVE_LOW *//* Activate to have access to port A */
+                                           &pioD 19 GPIO_ACTIVE_LOW
                                            &pioD 20 GPIO_ACTIVE_LOW
                                           >;
                 };
diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi
index ff7f5d855845..586134e2a382 100644
--- a/arch/arm/boot/dts/exynos5440.dtsi
+++ b/arch/arm/boot/dts/exynos5440.dtsi
@@ -248,6 +248,7 @@
                 #interrupt-cells = <1>;
                 interrupt-map-mask = <0 0 0 0>;
                 interrupt-map = <0x0 0 &gic 53>;
+                num-lanes = <4>;
         };
 
         pcie@2a0000 {
@@ -267,5 +268,6 @@
                 #interrupt-cells = <1>;
                 interrupt-map-mask = <0 0 0 0>;
                 interrupt-map = <0x0 0 &gic 56>;
+                num-lanes = <4>;
         };
 };
diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts
index e035f4664b97..15715d921d14 100644
--- a/arch/arm/boot/dts/imx28-evk.dts
+++ b/arch/arm/boot/dts/imx28-evk.dts
@@ -220,6 +220,7 @@
                         auart0: serial@8006a000 {
                                 pinctrl-names = "default";
                                 pinctrl-0 = <&auart0_pins_a>;
+                                fsl,uart-has-rtscts;
                                 status = "okay";
                         };
 
diff --git a/arch/arm/boot/dts/msm8660-surf.dts b/arch/arm/boot/dts/msm8660-surf.dts
index cdc010e0f93e..386d42870215 100644
--- a/arch/arm/boot/dts/msm8660-surf.dts
+++ b/arch/arm/boot/dts/msm8660-surf.dts
@@ -38,7 +38,7 @@
         };
 
         serial@19c40000 {
-                compatible = "qcom,msm-hsuart", "qcom,msm-uart";
+                compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
                 reg = <0x19c40000 0x1000>,
                       <0x19c00000 0x1000>;
                 interrupts = <0 195 0x0>;
diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts
index db2060c46540..93e9f7e0b7ad 100644
--- a/arch/arm/boot/dts/msm8960-cdp.dts
+++ b/arch/arm/boot/dts/msm8960-cdp.dts
@@ -26,7 +26,7 @@
                 cpu-offset = <0x80000>;
         };
 
-        msmgpio: gpio@fd510000 {
+        msmgpio: gpio@800000 {
                 compatible = "qcom,msm-gpio";
                 gpio-controller;
                 #gpio-cells = <2>;
@@ -34,11 +34,11 @@
                 interrupts = <0 32 0x4>;
                 interrupt-controller;
                 #interrupt-cells = <2>;
-                reg = <0xfd510000 0x4000>;
+                reg = <0x800000 0x4000>;
         };
 
         serial@16440000 {
-                compatible = "qcom,msm-hsuart", "qcom,msm-uart";
+                compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
                 reg = <0x16440000 0x1000>,
                       <0x16400000 0x1000>;
                 interrupts = <0 154 0x0>;
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 08b72678abff..65d7b601651c 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -235,7 +235,7 @@
 };
 
 &mmc1 {
-        vmmc-supply = <&vmmcsd_fixed>;
+        vmmc-supply = <&ldo9_reg>;
         bus-width = <4>;
 };
 
@@ -282,6 +282,7 @@
 
                         regulators {
                                 smps123_reg: smps123 {
+                                        /* VDD_OPP_MPU */
                                         regulator-name = "smps123";
                                         regulator-min-microvolt = < 600000>;
                                         regulator-max-microvolt = <1500000>;
@@ -290,6 +291,7 @@
                                 };
 
                                 smps45_reg: smps45 {
+                                        /* VDD_OPP_MM */
                                         regulator-name = "smps45";
                                         regulator-min-microvolt = < 600000>;
                                         regulator-max-microvolt = <1310000>;
@@ -298,6 +300,7 @@
                                 };
 
                                 smps6_reg: smps6 {
+                                        /* VDD_DDR3 - over VDD_SMPS6 */
                                         regulator-name = "smps6";
                                         regulator-min-microvolt = <1200000>;
                                         regulator-max-microvolt = <1200000>;
@@ -306,6 +309,7 @@
                                 };
 
                                 smps7_reg: smps7 {
+                                        /* VDDS_1v8_OMAP over VDDS_1v8_MAIN */
                                         regulator-name = "smps7";
                                         regulator-min-microvolt = <1800000>;
                                         regulator-max-microvolt = <1800000>;
@@ -314,6 +318,7 @@
                                 };
 
                                 smps8_reg: smps8 {
+                                        /* VDD_OPP_CORE */
                                         regulator-name = "smps8";
                                         regulator-min-microvolt = < 600000>;
                                         regulator-max-microvolt = <1310000>;
@@ -322,15 +327,15 @@
                                 };
 
                                 smps9_reg: smps9 {
+                                        /* VDDA_2v1_AUD over VDD_2v1 */
                                         regulator-name = "smps9";
                                         regulator-min-microvolt = <2100000>;
                                         regulator-max-microvolt = <2100000>;
-                                        regulator-always-on;
-                                        regulator-boot-on;
                                         ti,smps-range = <0x80>;
                                 };
 
                                 smps10_reg: smps10 {
+                                        /* VBUS_5V_OTG */
                                         regulator-name = "smps10";
                                         regulator-min-microvolt = <5000000>;
                                         regulator-max-microvolt = <5000000>;
@@ -339,38 +344,40 @@
                                 };
 
                                 ldo1_reg: ldo1 {
+                                        /* VDDAPHY_CAM: vdda_csiport */
                                         regulator-name = "ldo1";
-                                        regulator-min-microvolt = <2800000>;
-                                        regulator-max-microvolt = <2800000>;
-                                        regulator-always-on;
-                                        regulator-boot-on;
+                                        regulator-min-microvolt = <1500000>;
+                                        regulator-max-microvolt = <1800000>;
                                 };
 
                                 ldo2_reg: ldo2 {
+                                        /* VCC_2V8_DISP: Does not go anywhere */
                                         regulator-name = "ldo2";
-                                        regulator-min-microvolt = <2900000>;
-                                        regulator-max-microvolt = <2900000>;
-                                        regulator-always-on;
-                                        regulator-boot-on;
+                                        regulator-min-microvolt = <2800000>;
+                                        regulator-max-microvolt = <2800000>;
+                                        /* Unused */
+                                        status = "disabled";
                                 };
 
                                 ldo3_reg: ldo3 {
+                                        /* VDDAPHY_MDM: vdda_lli */
                                         regulator-name = "ldo3";
-                                        regulator-min-microvolt = <3000000>;
-                                        regulator-max-microvolt = <3000000>;
-                                        regulator-always-on;
+                                        regulator-min-microvolt = <1500000>;
+                                        regulator-max-microvolt = <1500000>;
                                         regulator-boot-on;
+                                        /* Only if Modem is used */
+                                        status = "disabled";
                                 };
 
                                 ldo4_reg: ldo4 {
+                                        /* VDDAPHY_DISP: vdda_dsiport/hdmi */
                                         regulator-name = "ldo4";
-                                        regulator-min-microvolt = <2200000>;
-                                        regulator-max-microvolt = <2200000>;
-                                        regulator-always-on;
-                                        regulator-boot-on;
+                                        regulator-min-microvolt = <1500000>;
+                                        regulator-max-microvolt = <1800000>;
                                 };
 
                                 ldo5_reg: ldo5 {
+                                        /* VDDA_1V8_PHY: usb/sata/hdmi.. */
                                         regulator-name = "ldo5";
                                         regulator-min-microvolt = <1800000>;
                                         regulator-max-microvolt = <1800000>;
@@ -379,38 +386,43 @@
                                 };
 
                                 ldo6_reg: ldo6 {
+                                        /* VDDS_1V2_WKUP: hsic/ldo_emu_wkup */
                                         regulator-name = "ldo6";
-                                        regulator-min-microvolt = <1500000>;
-                                        regulator-max-microvolt = <1500000>;
+                                        regulator-min-microvolt = <1200000>;
+                                        regulator-max-microvolt = <1200000>;
                                         regulator-always-on;
                                         regulator-boot-on;
                                 };
 
                                 ldo7_reg: ldo7 {
+                                        /* VDD_VPP: vpp1 */
                                         regulator-name = "ldo7";
-                                        regulator-min-microvolt = <1500000>;
-                                        regulator-max-microvolt = <1500000>;
-                                        regulator-always-on;
-                                        regulator-boot-on;
+                                        regulator-min-microvolt = <2000000>;
+                                        regulator-max-microvolt = <2000000>;
+                                        /* Only for efuse reprograming! */
+                                        status = "disabled";
                                 };
 
                                 ldo8_reg: ldo8 {
+                                        /* VDD_3v0: Does not go anywhere */
                                         regulator-name = "ldo8";
-                                        regulator-min-microvolt = <1500000>;
-                                        regulator-max-microvolt = <1500000>;
-                                        regulator-always-on;
+                                        regulator-min-microvolt = <3000000>;
+                                        regulator-max-microvolt = <3000000>;
                                         regulator-boot-on;
+                                        /* Unused */
+                                        status = "disabled";
                                 };
 
                                 ldo9_reg: ldo9 {
+                                        /* VCC_DV_SDIO: vdds_sdcard */
                                         regulator-name = "ldo9";
                                         regulator-min-microvolt = <1800000>;
-                                        regulator-max-microvolt = <3300000>;
-                                        regulator-always-on;
+                                        regulator-max-microvolt = <3000000>;
                                         regulator-boot-on;
                                 };
 
                                 ldoln_reg: ldoln {
+                                        /* VDDA_1v8_REF: vdds_osc/mm_l4per.. */
                                         regulator-name = "ldoln";
                                         regulator-min-microvolt = <1800000>;
                                         regulator-max-microvolt = <1800000>;
@@ -419,12 +431,20 @@
                                 };
 
                                 ldousb_reg: ldousb {
+                                        /* VDDA_3V_USB: VDDA_USBHS33 */
                                         regulator-name = "ldousb";
                                         regulator-min-microvolt = <3250000>;
                                         regulator-max-microvolt = <3250000>;
                                         regulator-always-on;
                                         regulator-boot-on;
                                 };
+
+                                regen3_reg: regen3 {
+                                        /* REGEN3 controls LDO9 supply to card */
+                                        regulator-name = "regen3";
+                                        regulator-always-on;
+                                        regulator-boot-on;
+                                };
                         };
                 };
         };
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index e643620417a9..07be2cd7b318 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -644,7 +644,7 @@
                         utmi-mode = <2>;
                         ranges;
                         dwc3@4a030000 {
-                                compatible = "synopsys,dwc3";
+                                compatible = "snps,dwc3";
                                 reg = <0x4a030000 0x1000>;
                                 interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
                                 usb-phy = <&usb2_phy>, <&usb3_phy>;
diff --git a/arch/arm/boot/dts/stih41x.dtsi b/arch/arm/boot/dts/stih41x.dtsi
index 7321403cab8a..f5b9898d9c6e 100644
--- a/arch/arm/boot/dts/stih41x.dtsi
+++ b/arch/arm/boot/dts/stih41x.dtsi
@@ -6,10 +6,12 @@
                 #address-cells = <1>;
                 #size-cells = <0>;
                 cpu@0 {
+                        device_type = "cpu";
                         compatible = "arm,cortex-a9";
                         reg = <0>;
                 };
                 cpu@1 {
+                        device_type = "cpu";
                         compatible = "arm,cortex-a9";
                         reg = <1>;
                 };
diff --git a/arch/arm/boot/dts/tegra20-colibri-512.dtsi b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
index 2fcb3f2ca160..5592be6f2f7a 100644
--- a/arch/arm/boot/dts/tegra20-colibri-512.dtsi
+++ b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
@@ -457,6 +457,7 @@
         };
 
         usb-phy@c5004000 {
+                status = "okay";
                 nvidia,phy-reset-gpio = <&gpio TEGRA_GPIO(V, 1)
                         GPIO_ACTIVE_LOW>;
         };
diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index 365760b33a26..c8242533268f 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -566,7 +566,6 @@
 
         usb@c5000000 {
                 status = "okay";
-                nvidia,vbus-gpio = <&gpio TEGRA_GPIO(D, 0) GPIO_ACTIVE_HIGH>;
                 dr_mode = "otg";
         };
 
@@ -830,6 +829,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&gpio 24 0>; /* PD0 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
         };
 
diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts
index ed4b901b0227..1e9d33adb925 100644
--- a/arch/arm/boot/dts/tegra20-trimslice.dts
+++ b/arch/arm/boot/dts/tegra20-trimslice.dts
@@ -312,7 +312,6 @@
 
         usb@c5000000 {
                 status = "okay";
-                nvidia,vbus-gpio = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_HIGH>;
         };
 
         usb-phy@c5000000 {
@@ -412,6 +411,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&gpio 170 0>; /* PV2 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
         };
 
diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts
index ab67c94db280..c703197dca6e 100644
--- a/arch/arm/boot/dts/tegra20-whistler.dts
+++ b/arch/arm/boot/dts/tegra20-whistler.dts
@@ -509,7 +509,6 @@
 
         usb@c5000000 {
                 status = "okay";
-                nvidia,vbus-gpio = <&tca6416 0 GPIO_ACTIVE_HIGH>;
         };
 
         usb-phy@c5000000 {
@@ -519,7 +518,6 @@
 
         usb@c5008000 {
                 status = "okay";
-                nvidia,vbus-gpio = <&tca6416 1 GPIO_ACTIVE_HIGH>;
         };
 
         usb-phy@c5008000 {
@@ -588,6 +586,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&tca6416 0 0>; /* GPIO_PMU0 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
 
                 vbus3_reg: regulator@3 {
@@ -598,6 +598,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&tca6416 1 0>; /* GPIO_PMU1 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
         };
 
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 9653fd8288d2..e4570834512e 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -477,13 +477,13 @@
                          <&tegra_car TEGRA20_CLK_USBD>;
                 clock-names = "reg", "pll_u", "timer", "utmi-pads";
                 nvidia,has-legacy-mode;
-                hssync_start_delay = <9>;
-                idle_wait_delay = <17>;
-                elastic_limit = <16>;
-                term_range_adj = <6>;
-                xcvr_setup = <9>;
-                xcvr_lsfslew = <1>;
-                xcvr_lsrslew = <1>;
+                nvidia,hssync-start-delay = <9>;
+                nvidia,idle-wait-delay = <17>;
+                nvidia,elastic-limit = <16>;
+                nvidia,term-range-adj = <6>;
+                nvidia,xcvr-setup = <9>;
+                nvidia,xcvr-lsfslew = <1>;
+                nvidia,xcvr-lsrslew = <1>;
                 status = "disabled";
         };
 
@@ -527,13 +527,13 @@
                          <&tegra_car TEGRA20_CLK_CLK_M>,
                          <&tegra_car TEGRA20_CLK_USBD>;
                 clock-names = "reg", "pll_u", "timer", "utmi-pads";
-                hssync_start_delay = <9>;
-                idle_wait_delay = <17>;
-                elastic_limit = <16>;
-                term_range_adj = <6>;
-                xcvr_setup = <9>;
-                xcvr_lsfslew = <2>;
-                xcvr_lsrslew = <2>;
+                nvidia,hssync-start-delay = <9>;
+                nvidia,idle-wait-delay = <17>;
+                nvidia,elastic-limit = <16>;
+                nvidia,term-range-adj = <6>;
+                nvidia,xcvr-setup = <9>;
+                nvidia,xcvr-lsfslew = <2>;
+                nvidia,xcvr-lsrslew = <2>;
                 status = "disabled";
         };
 
diff --git a/arch/arm/boot/dts/wm8850-w70v2.dts b/arch/arm/boot/dts/wm8850-w70v2.dts
index 90e913fb64be..7a563d2523b0 100644
--- a/arch/arm/boot/dts/wm8850-w70v2.dts
+++ b/arch/arm/boot/dts/wm8850-w70v2.dts
@@ -11,13 +11,14 @@
 
 /dts-v1/;
 /include/ "wm8850.dtsi"
+#include <dt-bindings/pwm/pwm.h>
 
 / {
         model = "Wondermedia WM8850-W70v2 Tablet";
 
         backlight {
                 compatible = "pwm-backlight";
-                pwms = <&pwm 0 50000 1>;        /* duty inverted */
+                pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
 
                 brightness-levels = <0 40 60 80 100 130 190 255>;
                 default-brightness-level = <5>;
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index e406d575c94f..5665134bfa3e 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -17,7 +17,8 @@ int arch_timer_arch_init(void);
  * nicely work out which register we want, and chuck away the rest of
  * the code. At least it does so with a recent GCC (4.6.3).
  */
-static inline void arch_timer_reg_write(const int access, const int reg, u32 val)
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 {
         if (access == ARCH_TIMER_PHYS_ACCESS) {
                 switch (reg) {
@@ -28,9 +29,7 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val
                         asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
                         break;
                 }
-        }
-
-        if (access == ARCH_TIMER_VIRT_ACCESS) {
+        } else if (access == ARCH_TIMER_VIRT_ACCESS) {
                 switch (reg) {
                 case ARCH_TIMER_REG_CTRL:
                         asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
@@ -44,7 +43,8 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val
         isb();
 }
 
-static inline u32 arch_timer_reg_read(const int access, const int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
         u32 val = 0;
 
@@ -57,9 +57,7 @@ static inline u32 arch_timer_reg_read(const int access, const int reg)
                         asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
                         break;
                 }
-        }
-
-        if (access == ARCH_TIMER_VIRT_ACCESS) {
+        } else if (access == ARCH_TIMER_VIRT_ACCESS) {
                 switch (reg) {
                 case ARCH_TIMER_REG_CTRL:
                         asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 6462a721ebd4..a252c0bfacf5 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -88,4 +88,7 @@ static inline u32 mpidr_hash_size(void)
 {
         return 1 << mpidr_hash.bits;
 }
+
+extern int platform_can_cpu_hotplug(void);
+
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index f8b8965666e9..b07c09e5a0ac 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -107,7 +107,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
                 "       subs    %1, %0, %0, ror #16\n"
                 "       addeq   %0, %0, %4\n"
                 "       strexeq %2, %0, [%3]"
-                : "=&r" (slock), "=&r" (contended), "=r" (res)
+                : "=&r" (slock), "=&r" (contended), "=&r" (res)
                 : "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
                 : "cc");
         } while (res);
@@ -168,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-        unsigned long tmp;
+        unsigned long contended, res;
 
-        __asm__ __volatile__(
-"       ldrex   %0, [%1]\n"
-"       teq     %0, #0\n"
-"       strexeq %0, %2, [%1]"
-        : "=&r" (tmp)
-        : "r" (&rw->lock), "r" (0x80000000)
-        : "cc");
+        do {
+                __asm__ __volatile__(
+                "       ldrex   %0, [%2]\n"
+                "       mov     %1, #0\n"
+                "       teq     %0, #0\n"
+                "       strexeq %1, %3, [%2]"
+                : "=&r" (contended), "=&r" (res)
+                : "r" (&rw->lock), "r" (0x80000000)
+                : "cc");
+        } while (res);
 
-        if (tmp == 0) {
+        if (!contended) {
                 smp_mb();
                 return 1;
         } else {
@@ -254,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-        unsigned long tmp, tmp2 = 1;
+        unsigned long contended, res;
 
-        __asm__ __volatile__(
-"       ldrex   %0, [%2]\n"
-"       adds    %0, %0, #1\n"
-"       strexpl %1, %0, [%2]\n"
-        : "=&r" (tmp), "+r" (tmp2)
-        : "r" (&rw->lock)
-        : "cc");
+        do {
+                __asm__ __volatile__(
+                "       ldrex   %0, [%2]\n"
+                "       mov     %1, #0\n"
+                "       adds    %0, %0, #1\n"
+                "       strexpl %1, %0, [%2]"
+                : "=&r" (contended), "=&r" (res)
+                : "r" (&rw->lock)
+                : "cc");
+        } while (res);
 
-        smp_mb();
-        return tmp2 == 0;
+        /* If the lock is negative, then it is already held for write. */
+        if (contended < 0x80000000) {
+                smp_mb();
+                return 1;
+        } else {
+                return 0;
+        }
 }
 
 /* read_can_lock - would read_trylock() succeed? */
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 46e7cfb3e721..0baf7f0d9394 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -43,6 +43,7 @@ struct mmu_gather {
         struct mm_struct        *mm;
         unsigned int            fullmm;
         struct vm_area_struct   *vma;
+        unsigned long           start, end;
         unsigned long           range_start;
         unsigned long           range_end;
         unsigned int            nr;
@@ -107,10 +108,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = fullmm;
+        tlb->fullmm = !(start | (end+1));
+        tlb->start = start;
+        tlb->end = end;
         tlb->vma = NULL;
         tlb->max = ARRAY_SIZE(tlb->local);
         tlb->pages = tlb->local;
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 261fcc826169..88e14d74b6de 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -525,11 +525,6 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw)
                          * Assign resources.
                          */
                         pci_bus_assign_resources(bus);
-
-                        /*
-                         * Enable bridges
-                         */
-                        pci_enable_bridges(bus);
                 }
 
                 /*
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 5859c8bc727c..2ee8a17d2b01 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -169,6 +169,11 @@ void __init arm_dt_init_cpu_maps(void)
         }
 }
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+        return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu);
+}
+
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt_phys: physical address of dt blob
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d40d0ef389db..9cbe70c8b0ef 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -357,7 +357,8 @@ ENDPROC(__pabt_svc)
         .endm
 
         .macro  kuser_cmpxchg_check
-#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) && \
+    !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 25442f451148..918875d96d5d 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -84,17 +84,14 @@ int show_fiq_list(struct seq_file *p, int prec)
 
 void set_fiq_handler(void *start, unsigned int length)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-        void *base = (void *)0xffff0000;
-#else
         void *base = vectors_page;
-#endif
         unsigned offset = FIQ_OFFSET;
 
         memcpy(base + offset, start, length);
+        if (!cache_is_vipt_nonaliasing())
+                flush_icache_range((unsigned long)base + offset, offset +
+                                   length);
         flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
-        if (!vectors_high())
-                flush_icache_range(offset, offset + length);
 }
 
 int claim_fiq(struct fiq_handler *f)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 4fb074c446bf..57221e349a7c 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -15,6 +15,7 @@
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
+#include <asm/smp_plat.h>
 #include <asm/system_misc.h>
 
 extern const unsigned char relocate_new_kernel[];
@@ -39,6 +40,14 @@ int machine_kexec_prepare(struct kimage *image)
         int i, err;
 
         /*
+         * Validate that if the current HW supports SMP, then the SW supports
+         * and implements CPU hotplug for the current HW. If not, we won't be
+         * able to kexec reliably, so fail the prepare operation.
+         */
+        if (num_possible_cpus() > 1 && !platform_can_cpu_hotplug())
+                return -EINVAL;
+
+        /*
          * No segment at default ATAGs address. try to locate
          * a dtb using magic.
          */
@@ -73,6 +82,7 @@ void machine_crash_nonpanic_core(void *unused)
         crash_save_cpu(&regs, smp_processor_id());
         flush_cache_all();
 
+        set_cpu_online(smp_processor_id(), false);
         atomic_dec(&waiting_for_crash_ipi);
         while (1)
                 cpu_relax();
@@ -134,10 +144,13 @@ void machine_kexec(struct kimage *image)
         unsigned long reboot_code_buffer_phys;
         void *reboot_code_buffer;
 
-        if (num_online_cpus() > 1) {
-                pr_err("kexec: error: multiple CPUs still online\n");
-                return;
-        }
+        /*
+         * This can only happen if machine_shutdown() failed to disable some
+         * CPU, and that can only happen if the checks in
+         * machine_kexec_prepare() were not correct. If this fails, we can't
+         * reliably kexec anyway, so BUG_ON is appropriate.
+         */
+        BUG_ON(num_online_cpus() > 1);
 
         page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index d9f5cd4e533f..e186ee1e63f6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -53,7 +53,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-        int mapping = (*event_map)[config];
+        int mapping;
+
+        if (config >= PERF_COUNT_HW_MAX)
+                return -EINVAL;
+
+        mapping = (*event_map)[config];
         return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -253,6 +258,9 @@ validate_event(struct pmu_hw_events *hw_events,
         struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
         struct pmu *leader_pmu = event->group_leader->pmu;
 
+        if (is_software_event(event))
+                return 1;
+
         if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
                 return 1;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 536c85fe72a8..94f6b05f9e24 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -462,7 +462,7 @@ int in_gate_area_no_mm(unsigned long addr)
 {
         return in_gate_area(NULL, addr);
 }
-#define is_gate_vma(vma)        ((vma) = &gate_vma)
+#define is_gate_vma(vma)        ((vma) == &gate_vma)
 #else
 #define is_gate_vma(vma)        0
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index c2b4f8f0be9a..2dc19349eb19 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -145,6 +145,16 @@ int boot_secondary(unsigned int cpu, struct task_struct *idle)
         return -ENOSYS;
 }
 
+int platform_can_cpu_hotplug(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+        if (smp_ops.cpu_kill)
+                return 1;
+#endif
+
+        return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void percpu_timer_stop(void);
 
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a59546a256..85a87370f144 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -74,12 +74,8 @@ struct cpu_efficiency table_efficiency[] = {
         {NULL, },
 };
 
-struct cpu_capacity {
-        unsigned long hwid;
-        unsigned long capacity;
-};
-
-struct cpu_capacity *cpu_capacity;
+unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)       __cpu_capacity[cpu]
 
 unsigned long middle_capacity = 1;
 
@@ -100,15 +96,19 @@ static void __init parse_dt_topology(void)
         unsigned long capacity = 0;
         int alloc_size, cpu = 0;
 
-        alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity);
-        cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+        alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
+        __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
 
-        while ((cn = of_find_node_by_type(cn, "cpu"))) {
-                const u32 *rate, *reg;
+        for_each_possible_cpu(cpu) {
+                const u32 *rate;
                 int len;
 
-                if (cpu >= num_possible_cpus())
-                        break;
+                /* too early to use cpu->of_node */
+                cn = of_get_cpu_node(cpu, NULL);
+                if (!cn) {
+                        pr_err("missing device node for CPU %d\n", cpu);
+                        continue;
+                }
 
                 for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
                         if (of_device_is_compatible(cn, cpu_eff->compatible))
@@ -124,12 +124,6 @@ static void __init parse_dt_topology(void)
                         continue;
                 }
 
-                reg = of_get_property(cn, "reg", &len);
-                if (!reg || len != 4) {
-                        pr_err("%s missing reg property\n", cn->full_name);
-                        continue;
-                }
-
                 capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
 
                 /* Save min capacity of the system */
@@ -140,13 +134,9 @@ static void __init parse_dt_topology(void)
                 if (capacity > max_capacity)
                         max_capacity = capacity;
 
-                cpu_capacity[cpu].capacity = capacity;
-                cpu_capacity[cpu++].hwid = be32_to_cpup(reg);
+                cpu_capacity(cpu) = capacity;
         }
 
-        if (cpu < num_possible_cpus())
-                cpu_capacity[cpu].hwid = (unsigned long)(-1);
-
         /* If min and max capacities are equals, we bypass the update of the
          * cpu_scale because all CPUs have the same capacity. Otherwise, we
          * compute a middle_capacity factor that will ensure that the capacity
@@ -154,9 +144,7 @@ static void __init parse_dt_topology(void)
          * SCHED_POWER_SCALE, which is the default value, but with the
          * constraint explained near table_efficiency[].
          */
-        if (min_capacity == max_capacity)
-                cpu_capacity[0].hwid = (unsigned long)(-1);
-        else if (4*max_capacity < (3*(max_capacity + min_capacity)))
+        if (4*max_capacity < (3*(max_capacity + min_capacity)))
                 middle_capacity = (min_capacity + max_capacity)
                                 >> (SCHED_POWER_SHIFT+1);
         else
@@ -170,23 +158,12 @@ static void __init parse_dt_topology(void)
  * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
  * function returns directly for SMP system.
  */
-void update_cpu_power(unsigned int cpu, unsigned long hwid)
+void update_cpu_power(unsigned int cpu)
 {
-        unsigned int idx = 0;
-
-        /* look for the cpu's hwid in the cpu capacity table */
-        for (idx = 0; idx < num_possible_cpus(); idx++) {
-                if (cpu_capacity[idx].hwid == hwid)
-                        break;
-
-                if (cpu_capacity[idx].hwid == -1)
-                        return;
-        }
-
-        if (idx == num_possible_cpus())
+        if (!cpu_capacity(cpu))
                 return;
 
-        set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity);
+        set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
 
         printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
                 cpu, arch_scale_freq_power(NULL, cpu));
@@ -194,7 +171,7 @@ void update_cpu_power(unsigned int cpu, unsigned long hwid)
 
 #else
 static inline void parse_dt_topology(void) {}
-static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
+static inline void update_cpu_power(unsigned int cpuid) {}
 #endif
 
  /*
@@ -281,7 +258,7 @@ void store_cpu_topology(unsigned int cpuid)
 
         update_siblings_masks(cpuid);
 
-        update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK);
+        update_cpu_power(cpuid);
 
         printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
                 cpuid, cpu_topology[cpuid].thread_id,
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 4a5199070430..db9cf692d4dd 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -146,7 +146,11 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 #define access_pmintenclr pm_fake
 
 /* Architected CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg cp15_regs[] = {
         /* CSSELR: swapped by interrupt.S. */
@@ -154,8 +158,8 @@ static const struct coproc_reg cp15_regs[] = {
                         NULL, reset_unknown, c0_CSSELR },
 
         /* TTBR0/TTBR1: swapped by interrupt.S. */
-        { CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
-        { CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
+        { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
+        { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
 
         /* TTBCR: swapped by interrupt.S. */
         { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
@@ -182,7 +186,7 @@ static const struct coproc_reg cp15_regs[] = {
                         NULL, reset_unknown, c6_IFAR },
 
         /* PAR swapped by interrupt.S */
-        { CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
+        { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
 
         /*
          * DC{C,I,CI}SW operations:
@@ -399,12 +403,13 @@ static bool index_to_params(u64 id, struct coproc_params *params)
                               | KVM_REG_ARM_OPC1_MASK))
                         return false;
                 params->is_64bit = true;
-                params->CRm = ((id & KVM_REG_ARM_CRM_MASK)
+                /* CRm to CRn: see cp15_to_index for details */
+                params->CRn = ((id & KVM_REG_ARM_CRM_MASK)
                                >> KVM_REG_ARM_CRM_SHIFT);
                 params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK)
                                >> KVM_REG_ARM_OPC1_SHIFT);
                 params->Op2 = 0;
-                params->CRn = 0;
+                params->CRm = 0;
                 return true;
         default:
                 return false;
@@ -898,7 +903,14 @@ static u64 cp15_to_index(const struct coproc_reg *reg)
         if (reg->is_64) {
                 val |= KVM_REG_SIZE_U64;
                 val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
-                val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT);
+                /*
+                 * CRn always denotes the primary coproc. reg. nr. for the
+                 * in-kernel representation, but the user space API uses the
+                 * CRm for the encoding, because it is modelled after the
+                 * MRRC/MCRR instructions: see the ARM ARM rev. c page
+                 * B3-1445
+                 */
+                val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT);
         } else {
                 val |= KVM_REG_SIZE_U32;
                 val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index b7301d3e4799..0461d5c8d3de 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -135,6 +135,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
                 return -1;
         if (i1->CRn != i2->CRn)
                 return i1->CRn - i2->CRn;
+        if (i1->is_64 != i2->is_64)
+                return i2->is_64 - i1->is_64;
         if (i1->CRm != i2->CRm)
                 return i1->CRm - i2->CRm;
         if (i1->Op1 != i2->Op1)
@@ -145,6 +147,7 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 
 #define CRn(_x)         .CRn = _x
 #define CRm(_x)         .CRm = _x
+#define CRm64(_x)       .CRn = _x, .CRm = 0
 #define Op1(_x)         .Op1 = _x
 #define Op2(_x)         .Op2 = _x
 #define is64            .is_64 = true
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index 685063a6d0cf..cf93472b9dd6 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -114,7 +114,11 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu,
 
 /*
  * A15-specific CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg a15_regs[] = {
         /* MPIDR: we use VMPIDR for guest access. */
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index b8e06b7a2833..0c25d9487d53 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -63,7 +63,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
                       struct kvm_exit_mmio *mmio)
 {
-        unsigned long rt, len;
+        unsigned long rt;
+        int len;
         bool is_write, sign_extend;
 
         if (kvm_vcpu_dabt_isextabt(vcpu)) {
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index ca6bea4859b4..0988d9e04dd4 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -85,6 +85,12 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
         return p;
 }
 
+static bool page_empty(void *ptr)
+{
+        struct page *ptr_page = virt_to_page(ptr);
+        return page_count(ptr_page) == 1;
+}
+
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
         pmd_t *pmd_table = pmd_offset(pud, 0);
@@ -103,12 +109,6 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
         put_page(virt_to_page(pmd));
 }
 
-static bool pmd_empty(pmd_t *pmd)
-{
-        struct page *pmd_page = virt_to_page(pmd);
-        return page_count(pmd_page) == 1;
-}
-
 static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
 {
         if (pte_present(*pte)) {
@@ -118,12 +118,6 @@ static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
         }
 }
 
-static bool pte_empty(pte_t *pte)
-{
-        struct page *pte_page = virt_to_page(pte);
-        return page_count(pte_page) == 1;
-}
-
 static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
                         unsigned long long start, u64 size)
 {
@@ -132,37 +126,37 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
         pmd_t *pmd;
         pte_t *pte;
         unsigned long long addr = start, end = start + size;
-        u64 range;
+        u64 next;
 
         while (addr < end) {
                 pgd = pgdp + pgd_index(addr);
                 pud = pud_offset(pgd, addr);
                 if (pud_none(*pud)) {
-                        addr += PUD_SIZE;
+                        addr = pud_addr_end(addr, end);
                         continue;
                 }
 
                 pmd = pmd_offset(pud, addr);
                 if (pmd_none(*pmd)) {
-                        addr += PMD_SIZE;
+                        addr = pmd_addr_end(addr, end);
                         continue;
                 }
 
                 pte = pte_offset_kernel(pmd, addr);
                 clear_pte_entry(kvm, pte, addr);
-                range = PAGE_SIZE;
+                next = addr + PAGE_SIZE;
 
                 /* If we emptied the pte, walk back up the ladder */
-                if (pte_empty(pte)) {
+                if (page_empty(pte)) {
                         clear_pmd_entry(kvm, pmd, addr);
-                        range = PMD_SIZE;
-                        if (pmd_empty(pmd)) {
+                        next = pmd_addr_end(addr, end);
+                        if (page_empty(pmd) && !page_empty(pud)) {
                                 clear_pud_entry(kvm, pud, addr);
-                                range = PUD_SIZE;
+                                next = pud_addr_end(addr, end);
                         }
                 }
 
-                addr += range;
+                addr = next;
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index 2abee6626aac..916e5a142917 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -227,6 +227,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID("usart", "f8020000.serial", &usart1_clk),
         CLKDEV_CON_DEV_ID("usart", "f8024000.serial", &usart2_clk),
         CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk),
+        CLKDEV_CON_DEV_ID("usart", "f8040000.serial", &uart0_clk),
+        CLKDEV_CON_DEV_ID("usart", "f8044000.serial", &uart1_clk),
         CLKDEV_CON_DEV_ID("t0_clk", "f8008000.timer", &tcb0_clk),
         CLKDEV_CON_DEV_ID("t0_clk", "f800c000.timer", &tcb0_clk),
         CLKDEV_CON_DEV_ID("mci_clk", "f0008000.mmc", &mmc0_clk),
diff --git a/arch/arm/mach-at91/include/mach/at91_adc.h b/arch/arm/mach-at91/include/mach/at91_adc.h
index 8e7ed5c90817..048a57f76bd3 100644
--- a/arch/arm/mach-at91/include/mach/at91_adc.h
+++ b/arch/arm/mach-at91/include/mach/at91_adc.h
@@ -28,9 +28,12 @@
 #define                 AT91_ADC_TRGSEL_EXTERNAL        (6 << 1)
 #define         AT91_ADC_LOWRES         (1 << 4)        /* Low Resolution */
 #define         AT91_ADC_SLEEP          (1 << 5)        /* Sleep Mode */
-#define         AT91_ADC_PRESCAL        (0x3f << 8)     /* Prescalar Rate Selection */
+#define         AT91_ADC_PRESCAL_9260   (0x3f << 8)     /* Prescalar Rate Selection */
+#define         AT91_ADC_PRESCAL_9G45   (0xff << 8)
 #define                 AT91_ADC_PRESCAL_(x)    ((x) << 8)
-#define         AT91_ADC_STARTUP        (0x1f << 16)    /* Startup Up Time */
+#define         AT91_ADC_STARTUP_9260   (0x1f << 16)    /* Startup Up Time */
+#define         AT91_ADC_STARTUP_9G45   (0x7f << 16)
+#define         AT91_ADC_STARTUP_9X5    (0xf << 16)
 #define                 AT91_ADC_STARTUP_(x)    ((x) << 16)
 #define         AT91_ADC_SHTIM          (0xf  << 24)    /* Sample & Hold Time */
 #define                 AT91_ADC_SHTIM_(x)      ((x) << 24)
@@ -48,6 +51,9 @@
 #define         AT91_ADC_ENDRX          (1 << 18)       /* End of RX Buffer */
 #define         AT91_ADC_RXFUFF         (1 << 19)       /* RX Buffer Full */
 
+#define AT91_ADC_SR_9X5         0x30            /* Status Register for 9x5 */
+#define         AT91_ADC_SR_DRDY_9X5    (1 << 24)       /* Data Ready */
+
 #define AT91_ADC_LCDR           0x20            /* Last Converted Data Register */
 #define         AT91_ADC_LDATA          (0x3ff)
 
@@ -58,4 +64,10 @@
 #define AT91_ADC_CHR(n)         (0x30 + ((n) * 4))      /* Channel Data Register N */
 #define         AT91_ADC_DATA           (0x3ff)
 
+#define AT91_ADC_CDR0_9X5       (0x50)                  /* Channel Data Register 0 for 9X5 */
+
+#define AT91_ADC_TRGR_9260      AT91_ADC_MR
+#define AT91_ADC_TRGR_9G45      0x08
+#define AT91_ADC_TRGR_9X5       0xC0
+
 #endif
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index dff4ddc5ef81..139e42da25f0 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -75,6 +75,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
         .parts                  = davinci_nand_partitions,
         .nr_parts               = ARRAY_SIZE(davinci_nand_partitions),
         .ecc_mode               = NAND_ECC_HW_SYNDROME,
+        .ecc_bits               = 4,
         .bbt_options            = NAND_BBT_USE_FLASH,
 };
 
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index a33686a6fbb2..fa4bfaf952d8 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -153,6 +153,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = {
         .parts          = davinci_evm_nandflash_partition,
         .nr_parts       = ARRAY_SIZE(davinci_evm_nandflash_partition),
         .ecc_mode       = NAND_ECC_HW,
+        .ecc_bits       = 1,
         .bbt_options    = NAND_BBT_USE_FLASH,
         .timing         = &davinci_evm_nandflash_timing,
 };
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index fbb8e5ab1dc1..0c005e876cac 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -90,6 +90,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
         .parts                  = davinci_nand_partitions,
         .nr_parts               = ARRAY_SIZE(davinci_nand_partitions),
         .ecc_mode               = NAND_ECC_HW,
+        .ecc_bits               = 1,
         .options                = 0,
 };
 
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 2bc112adf565..808233b60e3d 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -88,6 +88,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = {
         .parts          = davinci_ntosd2_nandflash_partition,
         .nr_parts       = ARRAY_SIZE(davinci_ntosd2_nandflash_partition),
         .ecc_mode       = NAND_ECC_HW,
+        .ecc_bits       = 1,
         .bbt_options    = NAND_BBT_USE_FLASH,
 };
 
diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c
index 36aef3a7dedb..f1ac1c94ac0f 100644
--- a/arch/arm/mach-davinci/cpuidle.c
+++ b/arch/arm/mach-davinci/cpuidle.c
@@ -65,7 +65,7 @@ static struct cpuidle_driver davinci_idle_driver = {
         .states[1]              = {
                 .enter                  = davinci_enter_idle,
                 .exit_latency           = 10,
-                .target_residency       = 100000,
+                .target_residency       = 10000,
                 .flags                  = CPUIDLE_FLAG_TIME_VALID,
                 .name                   = "DDR SR",
                 .desc                   = "WFI and DDR Self Refresh",
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 7be13f8e69a0..a02f275a198d 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -254,13 +254,12 @@ static void __init imx6q_opp_init(struct device *cpu_dev)
 {
         struct device_node *np;
 
-        np = of_find_node_by_path("/cpus/cpu@0");
+        np = of_node_get(cpu_dev->of_node);
         if (!np) {
                 pr_warn("failed to find cpu0 node\n");
                 return;
         }
 
-        cpu_dev->of_node = np;
         if (of_init_opp_table(cpu_dev)) {
                 pr_warn("failed to init OPP table\n");
                 goto put_node;
diff --git a/arch/arm/mach-msm/Kconfig b/arch/arm/mach-msm/Kconfig
index 614e41e7881b..905efc8cac79 100644
--- a/arch/arm/mach-msm/Kconfig
+++ b/arch/arm/mach-msm/Kconfig
@@ -121,8 +121,7 @@ config MSM_SMD
         bool
 
 config MSM_GPIOMUX
-        depends on !(ARCH_MSM8X60 || ARCH_MSM8960)
-        bool "MSM V1 TLMM GPIOMUX architecture"
+        bool
         help
           Support for MSM V1 TLMM GPIOMUX architecture.
 
diff --git a/arch/arm/mach-msm/devices-msm7x00.c b/arch/arm/mach-msm/devices-msm7x00.c
index 6d50fb964863..d83404d4b328 100644
--- a/arch/arm/mach-msm/devices-msm7x00.c
+++ b/arch/arm/mach-msm/devices-msm7x00.c
@@ -456,9 +456,9 @@ static struct clk_pcom_desc msm_clocks_7x01a[] = {
         CLK_PCOM("tsif_ref_clk",        TSIF_REF_CLK,   NULL, 0),
         CLK_PCOM("tv_dac_clk",  TV_DAC_CLK,     NULL, 0),
         CLK_PCOM("tv_enc_clk",  TV_ENC_CLK,     NULL, 0),
-        CLK_PCOM("uart_clk",    UART1_CLK,      "msm_serial.0", OFF),
-        CLK_PCOM("uart_clk",    UART2_CLK,      "msm_serial.1", 0),
-        CLK_PCOM("uart_clk",    UART3_CLK,      "msm_serial.2", OFF),
+        CLK_PCOM("core",        UART1_CLK,      "msm_serial.0", OFF),
+        CLK_PCOM("core",        UART2_CLK,      "msm_serial.1", 0),
+        CLK_PCOM("core",        UART3_CLK,      "msm_serial.2", OFF),
         CLK_PCOM("uart1dm_clk", UART1DM_CLK,    NULL, OFF),
         CLK_PCOM("uart2dm_clk", UART2DM_CLK,    NULL, 0),
         CLK_PCOM("usb_hs_clk",  USB_HS_CLK,     "msm_hsusb", OFF),
diff --git a/arch/arm/mach-msm/devices-msm7x30.c b/arch/arm/mach-msm/devices-msm7x30.c
index d4db75acff56..14e286948f69 100644
--- a/arch/arm/mach-msm/devices-msm7x30.c
+++ b/arch/arm/mach-msm/devices-msm7x30.c
@@ -211,7 +211,7 @@ static struct clk_pcom_desc msm_clocks_7x30[] = {
         CLK_PCOM("spi_pclk",    SPI_P_CLK,      NULL, 0),
         CLK_PCOM("tv_dac_clk",  TV_DAC_CLK,     NULL, 0),
         CLK_PCOM("tv_enc_clk",  TV_ENC_CLK,     NULL, 0),
-        CLK_PCOM("uart_clk",    UART2_CLK,      "msm_serial.1", 0),
+        CLK_PCOM("core",        UART2_CLK,      "msm_serial.1", 0),
         CLK_PCOM("usb_phy_clk", USB_PHY_CLK,    NULL, 0),
         CLK_PCOM("usb_hs_clk",          USB_HS_CLK,             NULL, OFF),
         CLK_PCOM("usb_hs_pclk",         USB_HS_P_CLK,           NULL, OFF),
diff --git a/arch/arm/mach-msm/devices-qsd8x50.c b/arch/arm/mach-msm/devices-qsd8x50.c
index f5518112284b..2ed89b25d304 100644
--- a/arch/arm/mach-msm/devices-qsd8x50.c
+++ b/arch/arm/mach-msm/devices-qsd8x50.c
@@ -358,9 +358,9 @@ static struct clk_pcom_desc msm_clocks_8x50[] = {
         CLK_PCOM("tsif_ref_clk",        TSIF_REF_CLK,   NULL, 0),
         CLK_PCOM("tv_dac_clk",  TV_DAC_CLK,     NULL, 0),
         CLK_PCOM("tv_enc_clk",  TV_ENC_CLK,     NULL, 0),
-        CLK_PCOM("uart_clk",    UART1_CLK,      NULL, OFF),
-        CLK_PCOM("uart_clk",    UART2_CLK,      NULL, 0),
-        CLK_PCOM("uart_clk",    UART3_CLK,      "msm_serial.2", OFF),
+        CLK_PCOM("core",        UART1_CLK,      NULL, OFF),
+        CLK_PCOM("core",        UART2_CLK,      NULL, 0),
+        CLK_PCOM("core",        UART3_CLK,      "msm_serial.2", OFF),
         CLK_PCOM("uartdm_clk",  UART1DM_CLK,    NULL, OFF),
         CLK_PCOM("uartdm_clk",  UART2DM_CLK,    NULL, 0),
         CLK_PCOM("usb_hs_clk",  USB_HS_CLK,     NULL, OFF),
diff --git a/arch/arm/mach-msm/gpiomux-v1.c b/arch/arm/mach-msm/gpiomux-v1.c
deleted file mode 100644
index 27de2abd7144..000000000000
--- a/arch/arm/mach-msm/gpiomux-v1.c
+++ /dev/null
@@ -1,33 +0,0 @@
-/* Copyright (c) 2010, Code Aurora Forum. 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- */
-#include <linux/kernel.h>
-#include "gpiomux.h"
-#include "proc_comm.h"
-
-void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val)
-{
-        unsigned tlmm_config  = (val & ~GPIOMUX_CTL_MASK) |
-                                ((gpio & 0x3ff) << 4);
-        unsigned tlmm_disable = 0;
-        int rc;
-
-        rc = msm_proc_comm(PCOM_RPC_GPIO_TLMM_CONFIG_EX,
-                           &tlmm_config, &tlmm_disable);
-        if (rc)
-                pr_err("%s: unexpected proc_comm failure %d: %08x %08x\n",
-                       __func__, rc, tlmm_config, tlmm_disable);
-}
diff --git a/arch/arm/mach-msm/gpiomux.h b/arch/arm/mach-msm/gpiomux.h
index 8e82f41a8923..4410d7766f93 100644
--- a/arch/arm/mach-msm/gpiomux.h
+++ b/arch/arm/mach-msm/gpiomux.h
@@ -73,16 +73,6 @@ extern struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS];
 int msm_gpiomux_write(unsigned gpio,
                       gpiomux_config_t active,
                       gpiomux_config_t suspended);
-
-/* Architecture-internal function for use by the framework only.
- * This function can assume the following:
- * - the gpio value has passed a bounds-check
- * - the gpiomux spinlock has been obtained
- *
- * This function is not for public consumption.  External users
- * should use msm_gpiomux_write.
- */
-void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val);
 #else
 static inline int msm_gpiomux_write(unsigned gpio,
                                     gpiomux_config_t active,
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
index ce81d3031405..594b63db4215 100644
--- a/arch/arm/mach-mvebu/platsmp.c
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -29,45 +29,40 @@
 #include "pmsu.h"
 #include "coherency.h"
 
+static struct clk *__init get_cpu_clk(int cpu)
+{
+        struct clk *cpu_clk;
+        struct device_node *np = of_get_cpu_node(cpu, NULL);
+
+        if (WARN(!np, "missing cpu node\n"))
+                return NULL;
+        cpu_clk = of_clk_get(np, 0);
+        if (WARN_ON(IS_ERR(cpu_clk)))
+                return NULL;
+        return cpu_clk;
+}
+
 void __init set_secondary_cpus_clock(void)
 {
-        int thiscpu;
+        int thiscpu, cpu;
         unsigned long rate;
-        struct clk *cpu_clk = NULL;
-        struct device_node *np = NULL;
+        struct clk *cpu_clk;
 
         thiscpu = smp_processor_id();
-        for_each_node_by_type(np, "cpu") {
-                int err;
-                int cpu;
-
-                err = of_property_read_u32(np, "reg", &cpu);
-                if (WARN_ON(err))
-                        return;
-
-                if (cpu == thiscpu) {
-                        cpu_clk = of_clk_get(np, 0);
-                        break;
-                }
-        }
-        if (WARN_ON(IS_ERR(cpu_clk)))
+        cpu_clk = get_cpu_clk(thiscpu);
+        if (!cpu_clk)
                 return;
         clk_prepare_enable(cpu_clk);
         rate = clk_get_rate(cpu_clk);
 
         /* set all the other CPU clk to the same rate than the boot CPU */
-        for_each_node_by_type(np, "cpu") {
-                int err;
-                int cpu;
-
-                err = of_property_read_u32(np, "reg", &cpu);
-                if (WARN_ON(err))
+        for_each_possible_cpu(cpu) {
+                if (cpu == thiscpu)
+                        continue;
+                cpu_clk = get_cpu_clk(cpu);
+                if (!cpu_clk)
                         return;
-
-                if (cpu != thiscpu) {
-                        cpu_clk = of_clk_get(np, 0);
-                        clk_set_rate(cpu_clk, rate);
-                }
+                clk_set_rate(cpu_clk, rate);
         }
 }
 
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index f6eeb87e4e95..827d15009a86 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -122,11 +122,7 @@ static struct musb_hdrc_config musb_config = {
 };
 
 static struct musb_hdrc_platform_data tusb_data = {
-#ifdef CONFIG_USB_GADGET_MUSB_HDRC
         .mode           = MUSB_OTG,
-#else
-        .mode           = MUSB_HOST,
-#endif
         .set_power      = tusb_set_power,
         .min_power      = 25,   /* x2 = 50 mA drawn from VBUS as peripheral */
         .power          = 100,  /* Max 100 mA VBUS for host mode */
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 04c116555412..1c6ae5f5bae7 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -33,7 +33,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mmc/host.h>
 #include <linux/usb/phy.h>
-#include <linux/usb/nop-usb-xceiv.h>
+#include <linux/usb/usb_phy_gen_xceiv.h>
 
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
@@ -279,7 +279,7 @@ static struct regulator_consumer_supply beagle_vsim_supply[] = {
 static struct gpio_led gpio_leds[];
 
 /* PHY's VCC regulator might be added later, so flag that we need it */
-static struct nop_usb_xceiv_platform_data hsusb2_phy_data = {
+static struct usb_phy_gen_xceiv_platform_data hsusb2_phy_data = {
         .needs_vcc = true,
 };
 
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index 8c026269baca..52bdddd41e0e 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -33,7 +33,7 @@
 #include <linux/i2c/twl.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/musb.h>
-#include <linux/usb/nop-usb-xceiv.h>
+#include <linux/usb/usb_phy_gen_xceiv.h>
 #include <linux/smsc911x.h>
 
 #include <linux/wl12xx.h>
@@ -468,7 +468,7 @@ struct wl12xx_platform_data omap3evm_wlan_data __initdata = {
 static struct regulator_consumer_supply omap3evm_vaux2_supplies[] = {
         REGULATOR_SUPPLY("VDD_CSIPHY1", "omap3isp"),    /* OMAP ISP */
         REGULATOR_SUPPLY("VDD_CSIPHY2", "omap3isp"),    /* OMAP ISP */
-        REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"),     /* hsusb port 2 */
+        REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"), /* hsusb port 2 */
         REGULATOR_SUPPLY("vaux2", NULL),
 };
 
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index b1547a0edfcd..d2b455e70486 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -352,7 +352,7 @@ static struct regulator_consumer_supply pandora_vcc_lcd_supply[] = {
 };
 
 static struct regulator_consumer_supply pandora_usb_phy_supply[] = {
-        REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"),     /* hsusb port 2 */
+        REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"), /* hsusb port 2 */
 };
 
 /* ads7846 on SPI and 2 nub controllers on I2C */
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index d2ea68ea678a..7735105561d8 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -85,7 +85,7 @@ static struct omap_board_mux board_mux[] __initdata = {
 
 static struct omap_musb_board_data musb_board_data = {
         .interface_type         = MUSB_INTERFACE_ULPI,
-        .mode                   = MUSB_PERIPHERAL,
+        .mode                   = MUSB_OTG,
         .power                  = 0,
 };
 
diff --git a/arch/arm/mach-omap2/dss-common.c b/arch/arm/mach-omap2/dss-common.c
index 393aeefaebb0..043e5705f2a6 100644
--- a/arch/arm/mach-omap2/dss-common.c
+++ b/arch/arm/mach-omap2/dss-common.c
@@ -42,7 +42,7 @@
 
 /* Using generic display panel */
 static struct tfp410_platform_data omap4_dvi_panel = {
-        .i2c_bus_num            = 3,
+        .i2c_bus_num            = 2,
         .power_down_gpio        = PANDA_DVI_TFP410_POWER_DOWN_GPIO,
 };
 
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 5cc92874be7e..f99f68e1e85b 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -129,6 +129,7 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
         struct device_node *node = pdev->dev.of_node;
         const char *oh_name;
         int oh_cnt, i, ret = 0;
+        bool device_active = false;
 
         oh_cnt = of_property_count_strings(node, "ti,hwmods");
         if (oh_cnt <= 0) {
@@ -152,6 +153,8 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
                         goto odbfd_exit1;
                 }
                 hwmods[i] = oh;
+                if (oh->flags & HWMOD_INIT_NO_IDLE)
+                        device_active = true;
         }
 
         od = omap_device_alloc(pdev, hwmods, oh_cnt);
@@ -172,6 +175,11 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
 
         pdev->dev.pm_domain = &omap_device_pm_domain;
 
+        if (device_active) {
+                omap_device_enable(pdev);
+                pm_runtime_set_active(&pdev->dev);
+        }
+
 odbfd_exit1:
         kfree(hwmods);
 odbfd_exit:
@@ -842,6 +850,7 @@ static int __init omap_device_late_idle(struct device *dev, void *data)
 {
         struct platform_device *pdev = to_platform_device(dev);
         struct omap_device *od = to_omap_device(pdev);
+        int i;
 
         if (!od)
                 return 0;
@@ -850,6 +859,15 @@ static int __init omap_device_late_idle(struct device *dev, void *data)
          * If omap_device state is enabled, but has no driver bound,
          * idle it.
          */
+
+        /*
+         * Some devices (like memory controllers) are always kept
+         * enabled, and should not be idled even with no drivers.
+         */
+        for (i = 0; i < od->hwmods_cnt; i++)
+                if (od->hwmods[i]->flags & HWMOD_INIT_NO_IDLE)
+                        return 0;
+
         if (od->_driver_status != BUS_NOTIFY_BOUND_DRIVER) {
                 if (od->_state == OMAP_DEVICE_STATE_ENABLED) {
                         dev_warn(dev, "%s: enabled but no driver.  Idling\n",
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 7341eff63f56..7f4db12b1459 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2386,7 +2386,7 @@ static void __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data)
 
                 np = of_dev_hwmod_lookup(of_find_node_by_name(NULL, "ocp"), oh);
                 if (np)
-                        va_start = of_iomap(np, 0);
+                        va_start = of_iomap(np, oh->mpu_rt_idx);
         } else {
                 va_start = ioremap(mem->pa_start, mem->pa_end - mem->pa_start);
         }
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index aab33fd814c0..e1482a9b3bc2 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -95,6 +95,54 @@ extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type3;
 #define MODULEMODE_HWCTRL               1
 #define MODULEMODE_SWCTRL               2
 
+#define DEBUG_OMAP2UART1_FLAGS  0
+#define DEBUG_OMAP2UART2_FLAGS  0
+#define DEBUG_OMAP2UART3_FLAGS  0
+#define DEBUG_OMAP3UART3_FLAGS  0
+#define DEBUG_OMAP3UART4_FLAGS  0
+#define DEBUG_OMAP4UART3_FLAGS  0
+#define DEBUG_OMAP4UART4_FLAGS  0
+#define DEBUG_TI81XXUART1_FLAGS 0
+#define DEBUG_TI81XXUART2_FLAGS 0
+#define DEBUG_TI81XXUART3_FLAGS 0
+#define DEBUG_AM33XXUART1_FLAGS 0
+
+#define DEBUG_OMAPUART_FLAGS    (HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET)
+
+#if defined(CONFIG_DEBUG_OMAP2UART1)
+#undef DEBUG_OMAP2UART1_FLAGS
+#define DEBUG_OMAP2UART1_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP2UART2)
+#undef DEBUG_OMAP2UART2_FLAGS
+#define DEBUG_OMAP2UART2_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP2UART3)
+#undef DEBUG_OMAP2UART3_FLAGS
+#define DEBUG_OMAP2UART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP3UART3)
+#undef DEBUG_OMAP3UART3_FLAGS
+#define DEBUG_OMAP3UART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP3UART4)
+#undef DEBUG_OMAP3UART4_FLAGS
+#define DEBUG_OMAP3UART4_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP4UART3)
+#undef DEBUG_OMAP4UART3_FLAGS
+#define DEBUG_OMAP4UART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_OMAP4UART4)
+#undef DEBUG_OMAP4UART4_FLAGS
+#define DEBUG_OMAP4UART4_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_TI81XXUART1)
+#undef DEBUG_TI81XXUART1_FLAGS
+#define DEBUG_TI81XXUART1_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_TI81XXUART2)
+#undef DEBUG_TI81XXUART2_FLAGS
+#define DEBUG_TI81XXUART2_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_TI81XXUART3)
+#undef DEBUG_TI81XXUART3_FLAGS
+#define DEBUG_TI81XXUART3_FLAGS DEBUG_OMAPUART_FLAGS
+#elif defined(CONFIG_DEBUG_AM33XXUART1)
+#undef DEBUG_AM33XXUART1_FLAGS
+#define DEBUG_AM33XXUART1_FLAGS DEBUG_OMAPUART_FLAGS
+#endif
 
 /**
  * struct omap_hwmod_mux_info - hwmod specific mux configuration
@@ -568,6 +616,7 @@ struct omap_hwmod_link {
  * @voltdm: pointer to voltage domain (filled in at runtime)
  * @dev_attr: arbitrary device attributes that can be passed to the driver
  * @_sysc_cache: internal-use hwmod flags
+ * @mpu_rt_idx: index of device address space for register target (for DT boot)
  * @_mpu_rt_va: cached register target start address (internal use)
  * @_mpu_port: cached MPU register target slave (internal use)
  * @opt_clks_cnt: number of @opt_clks
@@ -617,6 +666,7 @@ struct omap_hwmod {
         struct list_head                node;
         struct omap_hwmod_ocp_if        *_mpu_port;
         u16                             flags;
+        u8                              mpu_rt_idx;
         u8                              response_lat;
         u8                              rst_lines_cnt;
         u8                              opt_clks_cnt;
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index d05fc7b54567..56cebb05509e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -512,7 +512,7 @@ struct omap_hwmod omap2xxx_uart1_hwmod = {
         .mpu_irqs       = omap2_uart1_mpu_irqs,
         .sdma_reqs      = omap2_uart1_sdma_reqs,
         .main_clk       = "uart1_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP2UART1_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = CORE_MOD,
@@ -532,7 +532,7 @@ struct omap_hwmod omap2xxx_uart2_hwmod = {
         .mpu_irqs       = omap2_uart2_mpu_irqs,
         .sdma_reqs      = omap2_uart2_sdma_reqs,
         .main_clk       = "uart2_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP2UART2_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = CORE_MOD,
@@ -552,7 +552,7 @@ struct omap_hwmod omap2xxx_uart3_hwmod = {
         .mpu_irqs       = omap2_uart3_mpu_irqs,
         .sdma_reqs      = omap2_uart3_sdma_reqs,
         .main_clk       = "uart3_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP2UART3_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = CORE_MOD,
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index 28bbd56346a9..eb2f3b93b51c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -562,6 +562,7 @@ static struct omap_hwmod am33xx_cpgmac0_hwmod = {
         .clkdm_name     = "cpsw_125mhz_clkdm",
         .flags          = (HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY),
         .main_clk       = "cpsw_125mhz_gclk",
+        .mpu_rt_idx     = 1,
         .prcm           = {
                 .omap4  = {
                         .clkctrl_offs   = AM33XX_CM_PER_CPGMAC0_CLKCTRL_OFFSET,
@@ -1512,7 +1513,7 @@ static struct omap_hwmod am33xx_uart1_hwmod = {
         .name           = "uart1",
         .class          = &uart_class,
         .clkdm_name     = "l4_wkup_clkdm",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_AM33XXUART1_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .main_clk       = "dpll_per_m2_div4_wkupdm_ck",
         .prcm           = {
                 .omap4  = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index f7a3df2fb579..0c3a427da544 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -490,7 +490,7 @@ static struct omap_hwmod omap3xxx_uart1_hwmod = {
         .mpu_irqs       = omap2_uart1_mpu_irqs,
         .sdma_reqs      = omap2_uart1_sdma_reqs,
         .main_clk       = "uart1_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_TI81XXUART1_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = CORE_MOD,
@@ -509,7 +509,7 @@ static struct omap_hwmod omap3xxx_uart2_hwmod = {
         .mpu_irqs       = omap2_uart2_mpu_irqs,
         .sdma_reqs      = omap2_uart2_sdma_reqs,
         .main_clk       = "uart2_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_TI81XXUART2_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = CORE_MOD,
@@ -528,7 +528,8 @@ static struct omap_hwmod omap3xxx_uart3_hwmod = {
         .mpu_irqs       = omap2_uart3_mpu_irqs,
         .sdma_reqs      = omap2_uart3_sdma_reqs,
         .main_clk       = "uart3_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP3UART3_FLAGS | DEBUG_TI81XXUART3_FLAGS |
+                                HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = OMAP3430_PER_MOD,
@@ -558,7 +559,7 @@ static struct omap_hwmod omap36xx_uart4_hwmod = {
         .mpu_irqs       = uart4_mpu_irqs,
         .sdma_reqs      = uart4_sdma_reqs,
         .main_clk       = "uart4_fck",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP3UART4_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .prcm           = {
                 .omap2 = {
                         .module_offs = OMAP3430_PER_MOD,
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index d04b5e60fdbe..9c3b504477d7 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2858,8 +2858,7 @@ static struct omap_hwmod omap44xx_uart3_hwmod = {
         .name           = "uart3",
         .class          = &omap44xx_uart_hwmod_class,
         .clkdm_name     = "l4_per_clkdm",
-        .flags          = HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET |
-                                HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP4UART3_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .main_clk       = "func_48m_fclk",
         .prcm = {
                 .omap4 = {
@@ -2875,7 +2874,7 @@ static struct omap_hwmod omap44xx_uart4_hwmod = {
         .name           = "uart4",
         .class          = &omap44xx_uart_hwmod_class,
         .clkdm_name     = "l4_per_clkdm",
-        .flags          = HWMOD_SWSUP_SIDLE_ACT,
+        .flags          = DEBUG_OMAP4UART4_FLAGS | HWMOD_SWSUP_SIDLE_ACT,
         .main_clk       = "func_48m_fclk",
         .prcm = {
                 .omap4 = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index f37ae96b70a1..3c70f5c1860f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -1375,7 +1375,7 @@ static struct omap_hwmod omap54xx_uart3_hwmod = {
         .name           = "uart3",
         .class          = &omap54xx_uart_hwmod_class,
         .clkdm_name     = "l4per_clkdm",
-        .flags          = HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET,
+        .flags          = DEBUG_OMAP4UART3_FLAGS,
         .main_clk       = "func_48m_fclk",
         .prcm = {
                 .omap4 = {
@@ -1391,6 +1391,7 @@ static struct omap_hwmod omap54xx_uart4_hwmod = {
         .name           = "uart4",
         .class          = &omap54xx_uart_hwmod_class,
         .clkdm_name     = "l4per_clkdm",
+        .flags          = DEBUG_OMAP4UART4_FLAGS,
         .main_clk       = "func_48m_fclk",
         .prcm = {
                 .omap4 = {
diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index 3a674de6cb63..a388f8c1bcb3 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -208,17 +208,6 @@ static int __init omap_serial_early_init(void)
                                 pr_info("%s used as console in debug mode: uart%d clocks will not be gated",
                                         uart_name, uart->num);
                         }
-
-                        /*
-                         * omap-uart can be used for earlyprintk logs
-                         * So if omap-uart is used as console then prevent
-                         * uart reset and idle to get logs from omap-uart
-                         * until uart console driver is available to take
-                         * care for console messages.
-                         * Idling or resetting omap-uart while printing logs
-                         * early boot logs can stall the boot-up.
-                         */
-                        oh->flags |= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET;
                 }
         } while (1);
 
diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c
index 2eb19d4d0aa1..e83a6a4b184a 100644
--- a/arch/arm/mach-omap2/usb-host.c
+++ b/arch/arm/mach-omap2/usb-host.c
@@ -28,7 +28,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/usb/phy.h>
-#include <linux/usb/nop-usb-xceiv.h>
+#include <linux/usb/usb_phy_gen_xceiv.h>
 
 #include "soc.h"
 #include "omap_device.h"
@@ -349,7 +349,7 @@ static struct fixed_voltage_config hsusb_reg_config = {
         /* .init_data filled later */
 };
 
-static const char *nop_name = "nop_usb_xceiv"; /* NOP PHY driver */
+static const char *nop_name = "usb_phy_gen_xceiv"; /* NOP PHY driver */
 static const char *reg_name = "reg-fixed-voltage"; /* Regulator driver */
 
 /**
@@ -460,9 +460,9 @@ int usbhs_init_phys(struct usbhs_phy_data *phy, int num_phys)
                 pdevinfo.name = nop_name;
                 pdevinfo.id = phy->port;
                 pdevinfo.data = phy->platform_data;
-                pdevinfo.size_data = sizeof(struct nop_usb_xceiv_platform_data);
-
-                scnprintf(phy_id, MAX_STR, "nop_usb_xceiv.%d",
+                pdevinfo.size_data =
+                        sizeof(struct usb_phy_gen_xceiv_platform_data);
+                scnprintf(phy_id, MAX_STR, "usb_phy_gen_xceiv.%d",
                                         phy->port);
                 pdev = platform_device_register_full(&pdevinfo);
                 if (IS_ERR(pdev)) {
diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c
index 8c4de2708cf2..bc897231bd10 100644
--- a/arch/arm/mach-omap2/usb-musb.c
+++ b/arch/arm/mach-omap2/usb-musb.c
@@ -38,11 +38,8 @@ static struct musb_hdrc_config musb_config = {
 };
 
 static struct musb_hdrc_platform_data musb_plat = {
-#ifdef CONFIG_USB_GADGET_MUSB_HDRC
         .mode           = MUSB_OTG,
-#else
-        .mode           = MUSB_HOST,
-#endif
+
         /* .clock is set dynamically */
         .config         = &musb_config,
 
diff --git a/arch/arm/mach-prima2/common.c b/arch/arm/mach-prima2/common.c
index 2c70f74fed5d..e110b6d4ae8c 100644
--- a/arch/arm/mach-prima2/common.c
+++ b/arch/arm/mach-prima2/common.c
@@ -42,7 +42,6 @@ static const char *atlas6_dt_match[] __initdata = {
 
 DT_MACHINE_START(ATLAS6_DT, "Generic ATLAS6 (Flattened Device Tree)")
         /* Maintainer: Barry Song <baohua.song@csr.com> */
-        .nr_irqs        = 128,
         .map_io         = sirfsoc_map_io,
         .init_time      = sirfsoc_init_time,
         .init_late      = sirfsoc_init_late,
@@ -59,7 +58,6 @@ static const char *prima2_dt_match[] __initdata = {
 
 DT_MACHINE_START(PRIMA2_DT, "Generic PRIMA2 (Flattened Device Tree)")
         /* Maintainer: Barry Song <baohua.song@csr.com> */
-        .nr_irqs        = 128,
         .map_io         = sirfsoc_map_io,
         .init_time      = sirfsoc_init_time,
         .dma_zone_size  = SZ_256M,
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index e115f6742107..c5be60d85e4b 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -1162,9 +1162,6 @@ static void __init eva_init(void)
         gpio_request_one(61, GPIOF_OUT_INIT_HIGH, NULL); /* LCDDON */
         gpio_request_one(202, GPIOF_OUT_INIT_LOW, NULL); /* LCD0_LED_CONT */
 
-        /* Touchscreen */
-        gpio_request_one(166, GPIOF_OUT_INIT_HIGH, NULL); /* TP_RST_B */
-
         /* GETHER */
         gpio_request_one(18, GPIOF_OUT_INIT_HIGH, NULL); /* PHY_RST */
 
diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c
index d5554646916c..3354a85c90f7 100644
--- a/arch/arm/mach-shmobile/board-bockw.c
+++ b/arch/arm/mach-shmobile/board-bockw.c
@@ -167,7 +167,13 @@ static const struct pinctrl_map bockw_pinctrl_map[] = {
                                   "usb1", "usb1"),
         /* SDHI0 */
         PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
-                                  "sdhi0", "sdhi0"),
+                                  "sdhi0_data4", "sdhi0"),
+        PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
+                                  "sdhi0_ctrl", "sdhi0"),
+        PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
+                                  "sdhi0_cd", "sdhi0"),
+        PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
+                                  "sdhi0_wp", "sdhi0"),
 };
 
 #define FPGA    0x18200000
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index d73e21d3ea8a..8d6bd5c5efb9 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -59,7 +59,7 @@ static __initdata struct gpio_led_platform_data lager_leds_pdata = {
 #define GPIO_KEY(c, g, d, ...) \
         { .code = c, .gpio = g, .desc = d, .active_low = 1 }
 
-static __initdata struct gpio_keys_button gpio_buttons[] = {
+static struct gpio_keys_button gpio_buttons[] = {
         GPIO_KEY(KEY_4,         RCAR_GP_PIN(1, 28),     "SW2-pin4"),
         GPIO_KEY(KEY_3,         RCAR_GP_PIN(1, 26),     "SW2-pin3"),
         GPIO_KEY(KEY_2,         RCAR_GP_PIN(1, 24),     "SW2-pin2"),
diff --git a/arch/arm/mach-sti/headsmp.S b/arch/arm/mach-sti/headsmp.S
index 78ebc7559f53..4c09bae86edf 100644
--- a/arch/arm/mach-sti/headsmp.S
+++ b/arch/arm/mach-sti/headsmp.S
@@ -16,8 +16,6 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-        __INIT
-
 /*
  * ST specific entry point for secondary CPUs.  This provides
  * a "holding pen" into which all secondary cores are held until we're
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 0d1e4128d460..fc97cfd52769 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -29,7 +29,6 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/pda_power.h>
-#include <linux/platform_data/tegra_usb.h>
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/sys_soc.h>
@@ -46,40 +45,6 @@
 #include "fuse.h"
 #include "iomap.h"
 
-static struct tegra_ehci_platform_data tegra_ehci1_pdata = {
-        .operating_mode = TEGRA_USB_OTG,
-        .power_down_on_bus_suspend = 1,
-        .vbus_gpio = -1,
-};
-
-static struct tegra_ulpi_config tegra_ehci2_ulpi_phy_config = {
-        .reset_gpio = -1,
-        .clk = "cdev2",
-};
-
-static struct tegra_ehci_platform_data tegra_ehci2_pdata = {
-        .phy_config = &tegra_ehci2_ulpi_phy_config,
-        .operating_mode = TEGRA_USB_HOST,
-        .power_down_on_bus_suspend = 1,
-        .vbus_gpio = -1,
-};
-
-static struct tegra_ehci_platform_data tegra_ehci3_pdata = {
-        .operating_mode = TEGRA_USB_HOST,
-        .power_down_on_bus_suspend = 1,
-        .vbus_gpio = -1,
-};
-
-static struct of_dev_auxdata tegra20_auxdata_lookup[] __initdata = {
-        OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5000000, "tegra-ehci.0",
-                       &tegra_ehci1_pdata),
-        OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5004000, "tegra-ehci.1",
-                       &tegra_ehci2_pdata),
-        OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5008000, "tegra-ehci.2",
-                       &tegra_ehci3_pdata),
-        {}
-};
-
 static void __init tegra_dt_init(void)
 {
         struct soc_device_attribute *soc_dev_attr;
@@ -112,8 +77,7 @@ static void __init tegra_dt_init(void)
          * devices
          */
 out:
-        of_platform_populate(NULL, of_default_bus_match_table,
-                                tegra20_auxdata_lookup, parent);
+        of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
 }
 
 static void __init trimslice_init(void)
diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index bf9b6be5b180..fe1f3e26b88b 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -4,7 +4,6 @@
 
 obj-y                           := cpu.o devices.o devices-common.o \
                                    id.o usb.o timer.o pm.o
-obj-$(CONFIG_CPU_IDLE)          += cpuidle.o
 obj-$(CONFIG_CACHE_L2X0)        += cache-l2x0.o
 obj-$(CONFIG_UX500_SOC_DB8500)  += cpu-db8500.o devices-db8500.o
 obj-$(CONFIG_MACH_MOP500)       += board-mop500.o board-mop500-sdi.o \
diff --git a/arch/arm/mach-ux500/cpuidle.c b/arch/arm/mach-ux500/cpuidle.c
deleted file mode 100644
index a45dd09daed9..000000000000
--- a/arch/arm/mach-ux500/cpuidle.c
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- * Copyright (c) 2012 Linaro : Daniel Lezcano <daniel.lezcano@linaro.org> (IBM)
- *
- * Based on the work of Rickard Andersson <rickard.andersson@stericsson.com>
- * and Jonas Aaberg <jonas.aberg@stericsson.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/module.h>
-#include <linux/cpuidle.h>
-#include <linux/spinlock.h>
-#include <linux/atomic.h>
-#include <linux/smp.h>
-#include <linux/mfd/dbx500-prcmu.h>
-#include <linux/platform_data/arm-ux500-pm.h>
-
-#include <asm/cpuidle.h>
-#include <asm/proc-fns.h>
-
-#include "db8500-regs.h"
-#include "id.h"
-
-static atomic_t master = ATOMIC_INIT(0);
-static DEFINE_SPINLOCK(master_lock);
-
-static inline int ux500_enter_idle(struct cpuidle_device *dev,
-                                   struct cpuidle_driver *drv, int index)
-{
-        int this_cpu = smp_processor_id();
-        bool recouple = false;
-
-        if (atomic_inc_return(&master) == num_online_cpus()) {
-
-                /* With this lock, we prevent the other cpu to exit and enter
-                 * this function again and become the master */
-                if (!spin_trylock(&master_lock))
-                        goto wfi;
-
-                /* decouple the gic from the A9 cores */
-                if (prcmu_gic_decouple()) {
-                        spin_unlock(&master_lock);
-                        goto out;
-                }
-
-                /* If an error occur, we will have to recouple the gic
-                 * manually */
-                recouple = true;
-
-                /* At this state, as the gic is decoupled, if the other
-                 * cpu is in WFI, we have the guarantee it won't be wake
-                 * up, so we can safely go to retention */
-                if (!prcmu_is_cpu_in_wfi(this_cpu ? 0 : 1))
-                        goto out;
-
-                /* The prcmu will be in charge of watching the interrupts
-                 * and wake up the cpus */
-                if (prcmu_copy_gic_settings())
-                        goto out;
-
-                /* Check in the meantime an interrupt did
-                 * not occur on the gic ... */
-                if (prcmu_gic_pending_irq())
-                        goto out;
-
-                /* ... and the prcmu */
-                if (prcmu_pending_irq())
-                        goto out;
-
-                /* Go to the retention state, the prcmu will wait for the
-                 * cpu to go WFI and this is what happens after exiting this
-                 * 'master' critical section */
-                if (prcmu_set_power_state(PRCMU_AP_IDLE, true, true))
-                        goto out;
-
-                /* When we switch to retention, the prcmu is in charge
-                 * of recoupling the gic automatically */
-                recouple = false;
-
-                spin_unlock(&master_lock);
-        }
-wfi:
-        cpu_do_idle();
-out:
-        atomic_dec(&master);
-
-        if (recouple) {
-                prcmu_gic_recouple();
-                spin_unlock(&master_lock);
-        }
-
-        return index;
-}
-
-static struct cpuidle_driver ux500_idle_driver = {
-        .name = "ux500_idle",
-        .owner = THIS_MODULE,
-        .states = {
-                ARM_CPUIDLE_WFI_STATE,
-                {
-                        .enter            = ux500_enter_idle,
-                        .exit_latency     = 70,
-                        .target_residency = 260,
-                        .flags            = CPUIDLE_FLAG_TIME_VALID |
-                                            CPUIDLE_FLAG_TIMER_STOP,
-                        .name             = "ApIdle",
-                        .desc             = "ARM Retention",
-                },
-        },
-        .safe_state_index = 0,
-        .state_count = 2,
-};
-
-int __init ux500_idle_init(void)
-{
-        if (!(cpu_is_u8500_family() || cpu_is_ux540_family()))
-                return -ENODEV;
-
-        /* Configure wake up reasons */
-        prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) |
-                             PRCMU_WAKEUP(ABB));
-
-        return cpuidle_register(&ux500_idle_driver, NULL);
-}
-
-device_initcall(ux500_idle_init);
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index db5c2cab8fda..cd2c88e7a8f7 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -809,15 +809,18 @@ config KUSER_HELPERS
           the CPU type fitted to the system.  This permits binaries to be
           run on ARMv4 through to ARMv7 without modification.
 
+          See Documentation/arm/kernel_user_helpers.txt for details.
+
           However, the fixed address nature of these helpers can be used
           by ROP (return orientated programming) authors when creating
           exploits.
 
           If all of the binaries and libraries which run on your platform
           are built specifically for your platform, and make no use of
-          these helpers, then you can turn this option off.  However,
-          when such an binary or library is run, it will receive a SIGILL
-          signal, which will terminate the program.
+          these helpers, then you can turn this option off to hinder
+          such exploits. However, in that case, if a binary or library
+          relying on those helpers is run, it will receive a SIGILL signal,
+          which will terminate the program.
 
           Say N here only if you are absolutely certain that you do not
           need these helpers; otherwise, the safe option is to say Y.
diff --git a/arch/arm/plat-samsung/init.c b/arch/arm/plat-samsung/init.c
index 3e5c4619caa5..50a3ea0037db 100644
--- a/arch/arm/plat-samsung/init.c
+++ b/arch/arm/plat-samsung/init.c
@@ -55,12 +55,13 @@ void __init s3c_init_cpu(unsigned long idcode,
 
         printk("CPU %s (id 0x%08lx)\n", cpu->name, idcode);
 
-        if (cpu->map_io == NULL || cpu->init == NULL) {
+        if (cpu->init == NULL) {
                 printk(KERN_ERR "CPU %s support not enabled\n", cpu->name);
                 panic("Unsupported Samsung CPU");
         }
 
-        cpu->map_io();
+        if (cpu->map_io)
+                cpu->map_io();
 }
 
 /* s3c24xx_init_clocks
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index c9770ba5c7df..8a6295c86209 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,6 +170,7 @@ static void __init xen_percpu_init(void *unused)
         per_cpu(xen_vcpu, cpu) = vcpup;
 
         enable_percpu_irq(xen_events_irq, 0);
+        put_cpu();
 }
 
 static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 98abd476992d..c9f1d2816c2b 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -26,7 +26,13 @@
 
 #include <clocksource/arm_arch_timer.h>
 
-static inline void arch_timer_reg_write(int access, int reg, u32 val)
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code.
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 {
         if (access == ARCH_TIMER_PHYS_ACCESS) {
                 switch (reg) {
@@ -36,8 +42,6 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val)
                 case ARCH_TIMER_REG_TVAL:
                         asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
                         break;
-                default:
-                        BUILD_BUG();
                 }
         } else if (access == ARCH_TIMER_VIRT_ACCESS) {
                 switch (reg) {
@@ -47,17 +51,14 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val)
                 case ARCH_TIMER_REG_TVAL:
                         asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
                         break;
-                default:
-                        BUILD_BUG();
                 }
-        } else {
-                BUILD_BUG();
         }
 
         isb();
 }
 
-static inline u32 arch_timer_reg_read(int access, int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
         u32 val;
 
@@ -69,8 +70,6 @@ static inline u32 arch_timer_reg_read(int access, int reg)
                 case ARCH_TIMER_REG_TVAL:
                         asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
                         break;
-                default:
-                        BUILD_BUG();
                 }
         } else if (access == ARCH_TIMER_VIRT_ACCESS) {
                 switch (reg) {
@@ -80,11 +79,7 @@ static inline u32 arch_timer_reg_read(int access, int reg)
                 case ARCH_TIMER_REG_TVAL:
                         asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
                         break;
-                default:
-                        BUILD_BUG();
                 }
-        } else {
-                BUILD_BUG();
         }
 
         return val;
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index c92de4163eba..b25763bc0ec4 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -42,14 +42,15 @@
 #define TPIDR_EL1       18      /* Thread ID, Privileged */
 #define AMAIR_EL1       19      /* Aux Memory Attribute Indirection Register */
 #define CNTKCTL_EL1     20      /* Timer Control Register (EL1) */
+#define PAR_EL1         21      /* Physical Address Register */
 /* 32bit specific registers. Keep them at the end of the range */
-#define DACR32_EL2      21      /* Domain Access Control Register */
-#define IFSR32_EL2      22      /* Instruction Fault Status Register */
-#define FPEXC32_EL2     23      /* Floating-Point Exception Control Register */
-#define DBGVCR32_EL2    24      /* Debug Vector Catch Register */
-#define TEECR32_EL1     25      /* ThumbEE Configuration Register */
-#define TEEHBR32_EL1    26      /* ThumbEE Handler Base Register */
-#define NR_SYS_REGS     27
+#define DACR32_EL2      22      /* Domain Access Control Register */
+#define IFSR32_EL2      23      /* Instruction Fault Status Register */
+#define FPEXC32_EL2     24      /* Floating-Point Exception Control Register */
+#define DBGVCR32_EL2    25      /* Debug Vector Catch Register */
+#define TEECR32_EL1     26      /* ThumbEE Configuration Register */
+#define TEEHBR32_EL1    27      /* ThumbEE Handler Base Register */
+#define NR_SYS_REGS     28
 
 /* 32bit mapping */
 #define c0_MPIDR        (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
@@ -69,6 +70,8 @@
 #define c5_AIFSR        (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */
 #define c6_DFAR         (FAR_EL1 * 2)   /* Data Fault Address Register */
 #define c6_IFAR         (c6_DFAR + 1)   /* Instruction Fault Address Register */
+#define c7_PAR          (PAR_EL1 * 2)   /* Physical Address Register */
+#define c7_PAR_high     (c7_PAR + 1)    /* PAR top 32 bits */
 #define c10_PRRR        (MAIR_EL1 * 2)  /* Primary Region Remap Register */
 #define c10_NMRR        (c10_PRRR + 1)  /* Normal Memory Remap Register */
 #define c12_VBAR        (VBAR_EL1 * 2)  /* Vector Base Address Register */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 644d73956864..0859a4ddd1e7 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -129,7 +129,7 @@ struct kvm_vcpu_arch {
         struct kvm_mmu_memory_cache mmu_page_cache;
 
         /* Target CPU and feature flags */
-        u32 target;
+        int target;
         DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
         /* Detect first run of a vcpu */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 46b3beb4b773..717031a762c2 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -35,6 +35,7 @@ struct mmu_gather {
         struct mm_struct        *mm;
         unsigned int            fullmm;
         struct vm_area_struct   *vma;
+        unsigned long           start, end;
         unsigned long           range_start;
         unsigned long           range_end;
         unsigned int            nr;
@@ -97,10 +98,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = fullmm;
+        tlb->fullmm = !(start | (end+1));
+        tlb->start = start;
+        tlb->end = end;
         tlb->vma = NULL;
         tlb->max = ARRAY_SIZE(tlb->local);
         tlb->pages = tlb->local;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9ba33c40cdf8..12e6ccb88691 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-        int mapping = (*event_map)[config];
+        int mapping;
+
+        if (config >= PERF_COUNT_HW_MAX)
+                return -EINVAL;
+
+        mapping = (*event_map)[config];
         return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -317,6 +322,9 @@ validate_event(struct pmu_hw_events *hw_events,
         struct hw_perf_event fake_event = event->hw;
         struct pmu *leader_pmu = event->group_leader->pmu;
 
+        if (is_software_event(event))
+                return 1;
+
         if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
                 return 1;
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index ff985e3d8b72..1ac0bbbdddb2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -214,6 +214,7 @@ __kvm_hyp_code_start:
         mrs     x21,    tpidr_el1
         mrs     x22,    amair_el1
         mrs     x23,    cntkctl_el1
+        mrs     x24,    par_el1
 
         stp     x4, x5, [x3]
         stp     x6, x7, [x3, #16]
@@ -225,6 +226,7 @@ __kvm_hyp_code_start:
         stp     x18, x19, [x3, #112]
         stp     x20, x21, [x3, #128]
         stp     x22, x23, [x3, #144]
+        str     x24, [x3, #160]
 .endm
 
 .macro restore_sysregs
@@ -243,6 +245,7 @@ __kvm_hyp_code_start:
         ldp     x18, x19, [x3, #112]
         ldp     x20, x21, [x3, #128]
         ldp     x22, x23, [x3, #144]
+        ldr     x24, [x3, #160]
 
         msr     vmpidr_el2,     x4
         msr     csselr_el1,     x5
@@ -264,6 +267,7 @@ __kvm_hyp_code_start:
         msr     tpidr_el1,      x21
         msr     amair_el1,      x22
         msr     cntkctl_el1,    x23
+        msr     par_el1,        x24
 .endm
 
 .macro skip_32bit_state tmp, target
@@ -600,6 +604,8 @@ END(__kvm_vcpu_run)
 
 // void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 ENTRY(__kvm_tlb_flush_vmid_ipa)
+        dsb     ishst
+
         kern_hyp_va     x0
         ldr     x2, [x0, #KVM_VTTBR]
         msr     vttbr_el2, x2
@@ -621,6 +627,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
 ENTRY(__kvm_flush_vm_context)
+        dsb     ishst
         tlbi    alle1is
         ic      ialluis
         dsb     sy
@@ -753,6 +760,10 @@ el1_trap:
          */
         tbnz    x1, #7, 1f      // S1PTW is set
 
+        /* Preserve PAR_EL1 */
+        mrs     x3, par_el1
+        push    x3, xzr
+
         /*
          * Permission fault, HPFAR_EL2 is invalid.
          * Resolve the IPA the hard way using the guest VA.
@@ -766,6 +777,8 @@ el1_trap:
 
         /* Read result */
         mrs     x3, par_el1
+        pop     x0, xzr                 // Restore PAR_EL1 from the stack
+        msr     par_el1, x0
         tbnz    x3, #0, 3f              // Bail out if we failed the translation
         ubfx    x3, x3, #12, #36        // Extract IPA
         lsl     x3, x3, #4              // and present it like HPFAR
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 94923609753b..02e9d09e1d80 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -211,6 +211,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
         /* FAR_EL1 */
         { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
           NULL, reset_unknown, FAR_EL1 },
+        /* PAR_EL1 */
+        { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
+          NULL, reset_unknown, PAR_EL1 },
 
         /* PMINTENSET_EL1 */
         { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
diff --git a/arch/avr32/boards/atngw100/mrmt.c b/arch/avr32/boards/atngw100/mrmt.c
index f91431963452..7de083d19b7e 100644
--- a/arch/avr32/boards/atngw100/mrmt.c
+++ b/arch/avr32/boards/atngw100/mrmt.c
@@ -150,7 +150,6 @@ static struct ac97c_platform_data __initdata ac97c0_data = {
 static struct platform_device rmt_ts_device = {
         .name   = "ucb1400_ts",
         .id     = -1,
-        }
 };
 #endif
 
diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c
index 0aa35f0eb0db..deb67843693c 100644
--- a/arch/frv/mb93090-mb00/pci-vdk.c
+++ b/arch/frv/mb93090-mb00/pci-vdk.c
@@ -320,7 +320,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases);
  *  are examined.
  */
 
-void __init pcibios_fixup_bus(struct pci_bus *bus)
+void pcibios_fixup_bus(struct pci_bus *bus)
 {
 #if 0
         printk("### PCIBIOS_FIXUP_BUS(%d)\n",bus->number);
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 33a97929d055..77d442ab28c8 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -158,6 +158,7 @@ source "kernel/Kconfig.hz"
 endmenu
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 source "drivers/Kconfig"
 source "fs/Kconfig"
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5a768ad8e893..b36370d3eab9 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -565,9 +565,9 @@ config KEXEC
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
-          initially work for you.  It may help to enable device hotplugging
-          support.  As of this writing the exact hardware interface is
-          strongly in flux, so no good recommendation can be made.
+          initially work for you.  As of this writing the exact hardware
+          interface is strongly in flux, so no good recommendation can be
+          made.
 
 config CRASH_DUMP
           bool "kernel crash dumps"
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index ef3a9de01954..bc5efc7c3f3f 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -22,7 +22,7 @@
  * unmapping a portion of the virtual address space, these hooks are called according to
  * the following template:
  *
- *      tlb <- tlb_gather_mmu(mm, full_mm_flush);       // start unmap for address space MM
+ *      tlb <- tlb_gather_mmu(mm, start, end);          // start unmap for address space MM
  *      {
  *        for each vma that needs a shootdown do {
  *          tlb_start_vma(tlb, vma);
@@ -58,6 +58,7 @@ struct mmu_gather {
         unsigned int            max;
         unsigned char           fullmm;         /* non-zero means full mm flush */
         unsigned char           need_flush;     /* really unmapped some PTEs? */
+        unsigned long           start, end;
         unsigned long           start_addr;
         unsigned long           end_addr;
         struct page             **pages;
@@ -155,13 +156,15 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
         tlb->max = ARRAY_SIZE(tlb->local);
         tlb->pages = tlb->local;
         tlb->nr = 0;
-        tlb->fullmm = full_mm_flush;
+        tlb->fullmm = !(start | (end+1));
+        tlb->start = start;
+        tlb->end = end;
         tlb->start_addr = ~0UL;
 }
 
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index 2291a7d69d49..121a6660ad4e 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -18,9 +18,11 @@
 #include <asm/machdep.h>
 #include <asm/natfeat.h>
 
+extern long nf_get_id_phys(unsigned long feature_name);
+
 asm("\n"
-"       .global nf_get_id,nf_call\n"
-"nf_get_id:\n"
+"       .global nf_get_id_phys,nf_call\n"
+"nf_get_id_phys:\n"
 "       .short  0x7300\n"
 "       rts\n"
 "nf_call:\n"
@@ -29,12 +31,25 @@ asm("\n"
 "1:     moveq.l #0,%d0\n"
 "       rts\n"
 "       .section __ex_table,\"a\"\n"
-"       .long   nf_get_id,1b\n"
+"       .long   nf_get_id_phys,1b\n"
 "       .long   nf_call,1b\n"
 "       .previous");
-EXPORT_SYMBOL_GPL(nf_get_id);
 EXPORT_SYMBOL_GPL(nf_call);
 
+long nf_get_id(const char *feature_name)
+{
+        /* feature_name may be in vmalloc()ed memory, so make a copy */
+        char name_copy[32];
+        size_t n;
+
+        n = strlcpy(name_copy, feature_name, sizeof(name_copy));
+        if (n >= sizeof(name_copy))
+                return 0;
+
+        return nf_get_id_phys(virt_to_phys(name_copy));
+}
+EXPORT_SYMBOL_GPL(nf_get_id);
+
 void nfprint(const char *fmt, ...)
 {
         static char buf[256];
@@ -43,7 +58,7 @@ void nfprint(const char *fmt, ...)
 
         va_start(ap, fmt);
         n = vsnprintf(buf, 256, fmt, ap);
-        nf_call(nf_get_id("NF_STDERR"), buf);
+        nf_call(nf_get_id("NF_STDERR"), virt_to_phys(buf));
         va_end(ap);
 }
 
@@ -68,7 +83,7 @@ void nf_init(void)
         id = nf_get_id("NF_NAME");
         if (!id)
                 return;
-        nf_call(id, buf, 256);
+        nf_call(id, virt_to_phys(buf), 256);
         buf[255] = 0;
 
         pr_info("NatFeats found (%s, %lu.%lu)\n", buf, version >> 16,
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index e3011338ab40..0721858fbd1e 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -41,8 +41,8 @@ static inline s32 nfhd_read_write(u32 major, u32 minor, u32 rwflag, u32 recno,
 static inline s32 nfhd_get_capacity(u32 major, u32 minor, u32 *blocks,
                                     u32 *blocksize)
 {
-        return nf_call(nfhd_id + NFHD_GET_CAPACITY, major, minor, blocks,
-                       blocksize);
+        return nf_call(nfhd_id + NFHD_GET_CAPACITY, major, minor,
+                       virt_to_phys(blocks), virt_to_phys(blocksize));
 }
 
 static LIST_HEAD(nfhd_list);
diff --git a/arch/m68k/emu/nfcon.c b/arch/m68k/emu/nfcon.c
index 6685bf45c2c3..57e8c8fb5eba 100644
--- a/arch/m68k/emu/nfcon.c
+++ b/arch/m68k/emu/nfcon.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/uaccess.h>
+#include <linux/io.h>
 
 #include <asm/natfeat.h>
 
@@ -25,17 +26,18 @@ static struct tty_driver *nfcon_tty_driver;
 static void nfputs(const char *str, unsigned int count)
 {
         char buf[68];
+        unsigned long phys = virt_to_phys(buf);
 
         buf[64] = 0;
         while (count > 64) {
                 memcpy(buf, str, 64);
-                nf_call(stderr_id, buf);
+                nf_call(stderr_id, phys);
                 str += 64;
                 count -= 64;
         }
         memcpy(buf, str, count);
         buf[count] = 0;
-        nf_call(stderr_id, buf);
+        nf_call(stderr_id, phys);
 }
 
 static void nfcon_write(struct console *con, const char *str,
@@ -79,7 +81,7 @@ static int nfcon_tty_put_char(struct tty_struct *tty, unsigned char ch)
 {
         char temp[2] = { ch, 0 };
 
-        nf_call(stderr_id, temp);
+        nf_call(stderr_id, virt_to_phys(temp));
         return 1;
 }
 
diff --git a/arch/m68k/emu/nfeth.c b/arch/m68k/emu/nfeth.c
index 695cd737a42e..a0985fd088d1 100644
--- a/arch/m68k/emu/nfeth.c
+++ b/arch/m68k/emu/nfeth.c
@@ -195,7 +195,8 @@ static struct net_device * __init nfeth_probe(int unit)
         char mac[ETH_ALEN], host_ip[32], local_ip[32];
         int err;
 
-        if (!nf_call(nfEtherID + XIF_GET_MAC, unit, mac, ETH_ALEN))
+        if (!nf_call(nfEtherID + XIF_GET_MAC, unit, virt_to_phys(mac),
+                     ETH_ALEN))
                 return NULL;
 
         dev = alloc_etherdev(sizeof(struct nfeth_private));
@@ -217,9 +218,9 @@ static struct net_device * __init nfeth_probe(int unit)
         }
 
         nf_call(nfEtherID + XIF_GET_IPHOST, unit,
-                host_ip, sizeof(host_ip));
+                virt_to_phys(host_ip), sizeof(host_ip));
         nf_call(nfEtherID + XIF_GET_IPATARI, unit,
-                local_ip, sizeof(local_ip));
+                virt_to_phys(local_ip), sizeof(local_ip));
 
         netdev_info(dev, KBUILD_MODNAME " addr:%s (%s) HWaddr:%pM\n", host_ip,
                     local_ip, mac);
diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h
index 444ea8a09e9f..ef881cfbbca9 100644
--- a/arch/m68k/include/asm/div64.h
+++ b/arch/m68k/include/asm/div64.h
@@ -15,16 +15,17 @@
                 unsigned long long n64;                         \
         } __n;                                                  \
         unsigned long __rem, __upper;                           \
+        unsigned long __base = (base);                          \
                                                                 \
         __n.n64 = (n);                                          \
         if ((__upper = __n.n32[0])) {                           \
                 asm ("divul.l %2,%1:%0"                         \
-                        : "=d" (__n.n32[0]), "=d" (__upper)     \
-                        : "d" (base), "0" (__n.n32[0]));        \
+                     : "=d" (__n.n32[0]), "=d" (__upper)        \
+                     : "d" (__base), "0" (__n.n32[0]));         \
         }                                                       \
         asm ("divu.l %2,%1:%0"                                  \
-                : "=d" (__n.n32[1]), "=d" (__rem)               \
-                : "d" (base), "1" (__upper), "0" (__n.n32[1])); \
+             : "=d" (__n.n32[1]), "=d" (__rem)                  \
+             : "d" (__base), "1" (__upper), "0" (__n.n32[1]));  \
         (n) = __n.n64;                                          \
         __rem;                                                  \
 })
diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h
index 7ef4115b8c4a..5053092b369f 100644
--- a/arch/m68k/include/asm/irqflags.h
+++ b/arch/m68k/include/asm/irqflags.h
@@ -67,6 +67,10 @@ static inline void arch_local_irq_restore(unsigned long flags)
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
+        if (MACH_IS_ATARI) {
+                /* Ignore HSYNC = ipl 2 on Atari */
+                return (flags & ~(ALLOWINT | 0x200)) != 0;
+        }
         return (flags & ~ALLOWINT) != 0;
 }
 
diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/platform/coldfire/pci.c
index b33f97a13e6d..df9679238b6d 100644
--- a/arch/m68k/platform/coldfire/pci.c
+++ b/arch/m68k/platform/coldfire/pci.c
@@ -319,7 +319,6 @@ static int __init mcf_pci_init(void)
         pci_fixup_irqs(pci_common_swizzle, mcf_pci_map_irq);
         pci_bus_size_bridges(rootbus);
         pci_bus_assign_resources(rootbus);
-        pci_enable_bridges(rootbus);
         return 0;
 }
 
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d22a4ecffff4..4fab52294d98 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -28,7 +28,7 @@ config MICROBLAZE
         select GENERIC_CLOCKEVENTS
         select GENERIC_IDLE_POLL_SETUP
         select MODULES_USE_ELF_RELA
-        select CLONE_BACKWARDS
+        select CLONE_BACKWARDS3
 
 config SWAP
         def_bool n
diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h
index 20c5e8e5121b..9977816c5ad3 100644
--- a/arch/microblaze/include/asm/prom.h
+++ b/arch/microblaze/include/asm/prom.h
@@ -50,9 +50,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index e12764c2a9d0..dccd7cec442d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2305,9 +2305,9 @@ config KEXEC
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
-          initially work for you.  It may help to enable device hotplugging
-          support.  As of this writing the exact hardware interface is
-          strongly in flux, so no good recommendation can be made.
+          initially work for you.  As of this writing the exact hardware
+          interface is strongly in flux, so no good recommendation can be
+          made.
 
 config CRASH_DUMP
           bool "Kernel crash dumps"
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 1dc086087a72..fa44f3ec5302 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -17,6 +17,8 @@
 #define current_cpu_type()      current_cpu_data.cputype
 #endif
 
+#define boot_cpu_type()         cpu_data[0].cputype
+
 /*
  * SMP assumption: Options of CPU 0 are a superset of all processors.
  * This is true for all known MIPS systems.
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 159abc8842d2..126da74d4c55 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -66,6 +66,8 @@ static void __init bmips_smp_setup(void)
         int i, cpu = 1, boot_cpu = 0;
 
 #if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
+        int cpu_hw_intr;
+
         /* arbitration priority */
         clear_c0_brcm_cmt_ctrl(0x30);
 
@@ -80,8 +82,12 @@ static void __init bmips_smp_setup(void)
          * MIPS interrupt 2 (HW INT 0) is the CPU0 L1 controller output
          * MIPS interrupt 3 (HW INT 1) is the CPU1 L1 controller output
          */
-        change_c0_brcm_cmt_intr(0xf8018000,
-                                        (0x02 << 27) | (0x03 << 15));
+        if (boot_cpu == 0)
+                cpu_hw_intr = 0x02;
+        else
+                cpu_hw_intr = 0x1d;
+
+        change_c0_brcm_cmt_intr(0xf8018000, (cpu_hw_intr << 27) | (0x03 << 15));
 
         /* single core, 2 threads (2 pipelines) */
         max_cpus = 2;
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 1765bab000a0..faf84c5f2629 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -1335,8 +1335,9 @@ static ssize_t store_kill(struct device *dev, struct device_attribute *attr,
 
         return len;
 }
+static DEVICE_ATTR(kill, S_IWUSR, NULL, store_kill);
 
-static ssize_t show_ntcs(struct device *cd, struct device_attribute *attr,
+static ssize_t ntcs_show(struct device *cd, struct device_attribute *attr,
                          char *buf)
 {
         struct vpe *vpe = get_vpe(tclimit);
@@ -1344,7 +1345,7 @@ static ssize_t show_ntcs(struct device *cd, struct device_attribute *attr,
         return sprintf(buf, "%d\n", vpe->ntcs);
 }
 
-static ssize_t store_ntcs(struct device *dev, struct device_attribute *attr,
+static ssize_t ntcs_store(struct device *dev, struct device_attribute *attr,
                           const char *buf, size_t len)
 {
         struct vpe *vpe = get_vpe(tclimit);
@@ -1365,12 +1366,14 @@ static ssize_t store_ntcs(struct device *dev, struct device_attribute *attr,
 out_einval:
         return -EINVAL;
 }
+static DEVICE_ATTR_RW(ntcs);
 
-static struct device_attribute vpe_class_attributes[] = {
-        __ATTR(kill, S_IWUSR, NULL, store_kill),
-        __ATTR(ntcs, S_IRUGO | S_IWUSR, show_ntcs, store_ntcs),
-        {}
+static struct attribute vpe_attrs[] = {
+        &dev_attr_kill.attr,
+        &dev_attr_ntcs.attr,
+        NULL,
 };
+ATTRIBUTE_GROUPS(vpe);
 
 static void vpe_device_release(struct device *cd)
 {
@@ -1381,7 +1384,7 @@ struct class vpe_class = {
         .name = "vpe",
         .owner = THIS_MODULE,
         .dev_release = vpe_device_release,
-        .dev_attrs = vpe_class_attributes,
+        .dev_groups = vpe_groups,
 };
 
 struct device vpe_device;
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index e773659ccf9f..46048d24328c 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -803,6 +803,32 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
                                 dec_insn.next_pc_inc;
                 return 1;
                 break;
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+        case lwc2_op: /* This is bbit0 on Octeon */
+                if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0)
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+        case ldc2_op: /* This is bbit032 on Octeon */
+                if ((regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) == 0)
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+        case swc2_op: /* This is bbit1 on Octeon */
+                if (regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt))
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+        case sdc2_op: /* This is bbit132 on Octeon */
+                if (regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32)))
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+#endif
         case cop0_op:
         case cop1_op:
         case cop2_op:
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index e4b1140cdae0..3a2b6e9f25cf 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -166,7 +166,7 @@ static void mipsxx_reg_setup(struct op_counter_config *ctr)
                         reg.control[i] |= M_PERFCTL_USER;
                 if (ctr[i].exl)
                         reg.control[i] |= M_PERFCTL_EXL;
-                if (current_cpu_type() == CPU_XLR)
+                if (boot_cpu_type() == CPU_XLR)
                         reg.control[i] |= M_PERFCTL_COUNT_ALL_THREADS;
                 reg.counter[i] = 0x80000000 - ctr[i].count;
         }
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index 594e60d6a43b..33e7aa52d9c4 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -113,7 +113,6 @@ static void pcibios_scanbus(struct pci_controller *hose)
                 if (!pci_has_flag(PCI_PROBE_ONLY)) {
                         pci_bus_size_bridges(bus);
                         pci_bus_assign_resources(bus);
-                        pci_enable_bridges(bus);
                 }
         }
 }
diff --git a/arch/mips/pnx833x/common/platform.c b/arch/mips/pnx833x/common/platform.c
index d22dc0d6f289..2b7e837dc2e2 100644
--- a/arch/mips/pnx833x/common/platform.c
+++ b/arch/mips/pnx833x/common/platform.c
@@ -206,11 +206,13 @@ static struct resource pnx833x_ethernet_resources[] = {
                 .end   = PNX8335_IP3902_PORTS_END,
                 .flags = IORESOURCE_MEM,
         },
+#ifdef CONFIG_SOC_PNX8335
         [1] = {
                 .start = PNX8335_PIC_ETHERNET_INT,
                 .end   = PNX8335_PIC_ETHERNET_INT,
                 .flags = IORESOURCE_IRQ,
         },
+#endif
 };
 
 static struct platform_device pnx833x_ethernet_device = {
diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c
index dd0ab982d77e..f9407e170476 100644
--- a/arch/mips/sni/a20r.c
+++ b/arch/mips/sni/a20r.c
@@ -122,7 +122,6 @@ static struct resource sc26xx_rsrc[] = {
 
 static struct sccnxp_pdata sccnxp_data = {
         .reg_shift      = 2,
-        .frequency      = 3686400,
         .mctrl_cfg[0]   = MCTRL_SIG(DTR_OP, LINE_OP7) |
                           MCTRL_SIG(RTS_OP, LINE_OP3) |
                           MCTRL_SIG(DSR_IP, LINE_IP5) |
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 99dbab1c59ac..d60bf98fa5cf 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -55,6 +55,7 @@ config GENERIC_CSUM
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h
index bbb34e5343a2..eb59bfe23e85 100644
--- a/arch/openrisc/include/asm/prom.h
+++ b/arch/openrisc/include/asm/prom.h
@@ -44,9 +44,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* Get the MAC address */
 extern const void *of_get_mac_address(struct device_node *np);
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3bf72cd2c8fc..5aecda05e0da 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -369,9 +369,9 @@ config KEXEC
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
-          initially work for you.  It may help to enable device hotplugging
-          support.  As of this writing the exact hardware interface is
-          strongly in flux, so no good recommendation can be made.
+          initially work for you.  As of this writing the exact hardware
+          interface is strongly in flux, so no good recommendation can be
+          made.
 
 config CRASH_DUMP
         bool "Build a kdump crash kernel"
@@ -566,7 +566,7 @@ config SCHED_SMT
 config PPC_DENORMALISATION
         bool "PowerPC denormalisation exception handling"
         depends on PPC_BOOK3S_64
-        default "n"
+        default "y" if PPC_POWERNV
         ---help---
           Add support for handling denormalisation of single precision
           values.  Useful for bare metal only.  If unsure say Y here.
@@ -979,6 +979,7 @@ config RELOCATABLE
           must live at a different physical address than the primary
           kernel.
 
+# This value must have zeroes in the bottom 60 bits otherwise lots will break
 config PAGE_OFFSET
         hex
         default "0xc000000000000000"
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 988c812aab5b..b9f426212d3a 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -211,9 +211,19 @@ extern long long virt_phys_offset;
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET))
 #define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET)
 #else
+#ifdef CONFIG_PPC64
+/*
+ * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET
+ * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit.
+ */
+#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET))
+#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL)
+
+#else /* 32-bit, non book E */
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START))
 #define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START)
 #endif
+#endif
 
 /*
  * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 8b2492644754..3fd2f1b6f906 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -138,11 +138,11 @@ extern ssize_t power_events_sysfs_show(struct device *dev,
 #define EVENT_PTR(_id, _suffix)         &EVENT_VAR(_id, _suffix).attr.attr
 
 #define EVENT_ATTR(_name, _id, _suffix)                                 \
-        PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id,    \
+        PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id,       \
                         power_events_sysfs_show)
 
 #define GENERIC_EVENT_ATTR(_name, _id)  EVENT_ATTR(_name, _id, _g)
 #define GENERIC_EVENT_PTR(_id)          EVENT_PTR(_id, _g)
 
-#define POWER_EVENT_ATTR(_name, _id)    EVENT_ATTR(PM_##_name, _id, _p)
+#define POWER_EVENT_ATTR(_name, _id)    EVENT_ATTR(_name, _id, _p)
 #define POWER_EVENT_PTR(_id)            EVENT_PTR(_id, _p)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 47a35b08b963..e378cccfca55 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -247,6 +247,10 @@ struct thread_struct {
         unsigned long   tm_orig_msr;    /* Thread's MSR on ctx switch */
         struct pt_regs  ckpt_regs;      /* Checkpointed registers */
 
+        unsigned long   tm_tar;
+        unsigned long   tm_ppr;
+        unsigned long   tm_dscr;
+
         /*
          * Transactional FP and VSX 0-31 register set.
          * NOTE: the sense of these is the opposite of the integer ckpt_regs!
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da154f68b..ac204e022922 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* cache lookup */
 struct device_node *of_find_next_cache_node(struct device_node *np);
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a6840e4e24f7..99222e27f173 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -254,19 +254,28 @@
 #define SPRN_HRMOR      0x139   /* Real mode offset register */
 #define SPRN_HSRR0      0x13A   /* Hypervisor Save/Restore 0 */
 #define SPRN_HSRR1      0x13B   /* Hypervisor Save/Restore 1 */
+/* HFSCR and FSCR bit numbers are the same */
+#define FSCR_TAR_LG     8       /* Enable Target Address Register */
+#define FSCR_EBB_LG     7       /* Enable Event Based Branching */
+#define FSCR_TM_LG      5       /* Enable Transactional Memory */
+#define FSCR_PM_LG      4       /* Enable prob/priv access to PMU SPRs */
+#define FSCR_BHRB_LG    3       /* Enable Branch History Rolling Buffer*/
+#define FSCR_DSCR_LG    2       /* Enable Data Stream Control Register */
+#define FSCR_VECVSX_LG  1       /* Enable VMX/VSX  */
+#define FSCR_FP_LG      0       /* Enable Floating Point */
 #define SPRN_FSCR       0x099   /* Facility Status & Control Register */
-#define   FSCR_TAR      (1 << (63-55)) /* Enable Target Address Register */
-#define   FSCR_EBB      (1 << (63-56)) /* Enable Event Based Branching */
-#define   FSCR_DSCR     (1 << (63-61)) /* Enable Data Stream Control Register */
+#define   FSCR_TAR      __MASK(FSCR_TAR_LG)
+#define   FSCR_EBB      __MASK(FSCR_EBB_LG)
+#define   FSCR_DSCR     __MASK(FSCR_DSCR_LG)
 #define SPRN_HFSCR      0xbe    /* HV=1 Facility Status & Control Register */
-#define   HFSCR_TAR     (1 << (63-55)) /* Enable Target Address Register */
-#define   HFSCR_EBB     (1 << (63-56)) /* Enable Event Based Branching */
-#define   HFSCR_TM      (1 << (63-58)) /* Enable Transactional Memory */
-#define   HFSCR_PM      (1 << (63-60)) /* Enable prob/priv access to PMU SPRs */
-#define   HFSCR_BHRB    (1 << (63-59)) /* Enable Branch History Rolling Buffer*/
-#define   HFSCR_DSCR    (1 << (63-61)) /* Enable Data Stream Control Register */
-#define   HFSCR_VECVSX  (1 << (63-62)) /* Enable VMX/VSX  */
-#define   HFSCR_FP      (1 << (63-63)) /* Enable Floating Point */
+#define   HFSCR_TAR     __MASK(FSCR_TAR_LG)
+#define   HFSCR_EBB     __MASK(FSCR_EBB_LG)
+#define   HFSCR_TM      __MASK(FSCR_TM_LG)
+#define   HFSCR_PM      __MASK(FSCR_PM_LG)
+#define   HFSCR_BHRB    __MASK(FSCR_BHRB_LG)
+#define   HFSCR_DSCR    __MASK(FSCR_DSCR_LG)
+#define   HFSCR_VECVSX  __MASK(FSCR_VECVSX_LG)
+#define   HFSCR_FP      __MASK(FSCR_FP_LG)
 #define SPRN_TAR        0x32f   /* Target Address Register */
 #define SPRN_LPCR       0x13E   /* LPAR Control Register */
 #define   LPCR_VPM0     (1ul << (63-0))
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 49a13e0ef234..294c2cedcf7a 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -15,6 +15,15 @@ extern struct task_struct *__switch_to(struct task_struct *,
 struct thread_struct;
 extern struct task_struct *_switch(struct thread_struct *prev,
                                    struct thread_struct *next);
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void save_tar(struct thread_struct *prev)
+{
+        if (cpu_has_feature(CPU_FTR_ARCH_207S))
+                prev->tar = mfspr(SPRN_TAR);
+}
+#else
+static inline void save_tar(struct thread_struct *prev) {}
+#endif
 
 extern void giveup_fpu(struct task_struct *);
 extern void load_up_fpu(void);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c7e8afc2ead0..8207459efe56 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -138,6 +138,9 @@ int main(void)
         DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
         DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
         DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+        DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
+        DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
+        DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
         DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
         DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
                                          transact_vr[0]));
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index ea9414c8088d..55593ee2d5aa 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1061,7 +1061,7 @@ static const struct file_operations proc_eeh_operations = {
 
 static int __init eeh_init_proc(void)
 {
-        if (machine_is(pseries))
+        if (machine_is(pseries) || machine_is(powernv))
                 proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
         return 0;
 }
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ab15b8d057ad..2bd0b885b0fe 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -449,15 +449,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 BEGIN_FTR_SECTION
-        /*
-         * Back up the TAR across context switches.  Note that the TAR is not
-         * available for use in the kernel.  (To provide this, the TAR should
-         * be backed up/restored on exception entry/exit instead, and be in
-         * pt_regs.  FIXME, this should be in pt_regs anyway (for debug).)
-         */
-        mfspr   r0,SPRN_TAR
-        std     r0,THREAD_TAR(r3)
-
         /* Event based branch registers */
         mfspr   r0, SPRN_BESCR
         std     r0, THREAD_BESCR(r3)
@@ -584,9 +575,34 @@ BEGIN_FTR_SECTION
         ld      r7,DSCR_DEFAULT@toc(2)
         ld      r0,THREAD_DSCR(r4)
         cmpwi   r6,0
+        li      r8, FSCR_DSCR
         bne     1f
         ld      r0,0(r7)
-1:      cmpd    r0,r25
+        b       3f
+1:
+  BEGIN_FTR_SECTION_NESTED(70)
+        mfspr   r6, SPRN_FSCR
+        or      r6, r6, r8
+        mtspr   SPRN_FSCR, r6
+    BEGIN_FTR_SECTION_NESTED(69)
+        mfspr   r6, SPRN_HFSCR
+        or      r6, r6, r8
+        mtspr   SPRN_HFSCR, r6
+    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+        b       4f
+  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+3:
+  BEGIN_FTR_SECTION_NESTED(70)
+        mfspr   r6, SPRN_FSCR
+        andc    r6, r6, r8
+        mtspr   SPRN_FSCR, r6
+    BEGIN_FTR_SECTION_NESTED(69)
+        mfspr   r6, SPRN_HFSCR
+        andc    r6, r6, r8
+        mtspr   SPRN_HFSCR, r6
+    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+4:      cmpd    r0,r25
         beq     2f
         mtspr   SPRN_DSCR,r0
 2:
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4e00d223b2e3..902ca3c6b4b6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -848,7 +848,7 @@ hv_facility_unavailable_relon_trampoline:
         . = 0x4f80
         SET_SCRATCH0(r13)
         EXCEPTION_PROLOG_0(PACA_EXGEN)
-        b       facility_unavailable_relon_hv
+        b       hv_facility_unavailable_relon_hv
 
         STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
 #ifdef CONFIG_PPC_DENORMALISATION
@@ -1175,6 +1175,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
         b       .ret_from_except
 
         STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
+        STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception)
 
         .align  7
         .globl  __end_handlers
@@ -1188,7 +1189,7 @@ __end_handlers:
         STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
         STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
         STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
-        STD_RELON_EXCEPTION_HV_OOL(0xf80, facility_unavailable)
+        STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index d92f3871e9cf..e2a0a162299b 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -35,7 +35,13 @@
 #include <asm/vdso_datapage.h>
 #include <asm/vio.h>
 #include <asm/mmu.h>
+#include <asm/machdep.h>
 
+
+/*
+ * This isn't a module but we expose that to userspace
+ * via /proc so leave the definitions here
+ */
 #define MODULE_VERS "1.9"
 #define MODULE_NAME "lparcfg"
 
@@ -418,7 +424,8 @@ static void parse_em_data(struct seq_file *m)
 {
         unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 
-        if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+        if (firmware_has_feature(FW_FEATURE_LPAR) &&
+            plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
                 seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
 }
 
@@ -677,7 +684,6 @@ static int lparcfg_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations lparcfg_fops = {
-        .owner          = THIS_MODULE,
         .read           = seq_read,
         .write          = lparcfg_write,
         .open           = lparcfg_open,
@@ -699,14 +705,4 @@ static int __init lparcfg_init(void)
         }
         return 0;
 }
-
-static void __exit lparcfg_cleanup(void)
-{
-        remove_proc_subtree("powerpc/lparcfg", NULL);
-}
-
-module_init(lparcfg_init);
-module_exit(lparcfg_cleanup);
-MODULE_DESCRIPTION("Interface for LPAR configuration data");
-MODULE_AUTHOR("Dave Engebretsen");
-MODULE_LICENSE("GPL");
+machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 7d22a675fe1a..2b4a9a4db7d9 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1674,12 +1674,8 @@ void pcibios_scan_phb(struct pci_controller *hose)
         /* Configure PCI Express settings */
         if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
                 struct pci_bus *child;
-                list_for_each_entry(child, &bus->children, node) {
-                        struct pci_dev *self = child->self;
-                        if (!self)
-                                continue;
-                        pcie_bus_configure_settings(child, self->pcie_mpss);
-                }
+                list_for_each_entry(child, &bus->children, node)
+                        pcie_bus_configure_settings(child);
         }
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c517dbe705fd..8083be20fe5e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -600,6 +600,16 @@ struct task_struct *__switch_to(struct task_struct *prev,
         struct ppc64_tlb_batch *batch;
 #endif
 
+        /* Back up the TAR across context switches.
+         * Note that the TAR is not available for use in the kernel.  (To
+         * provide this, the TAR should be backed up/restored on exception
+         * entry/exit instead, and be in pt_regs.  FIXME, this should be in
+         * pt_regs anyway (for debug).)
+         * Save the TAR here before we do treclaim/trecheckpoint as these
+         * will change the TAR.
+         */
+        save_tar(&prev->thread);
+
         __switch_to_tm(prev);
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index eb23ac92abb9..1c14cd4a5e05 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -865,49 +865,10 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-/* Find the device node for a given logical cpu number, also returns the cpu
- * local thread number (index in ibm,interrupt-server#s) if relevant and
- * asked for (non NULL)
- */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-        int hardid;
-        struct device_node *np;
-
-        hardid = get_hard_smp_processor_id(cpu);
-
-        for_each_node_by_type(np, "cpu") {
-                const u32 *intserv;
-                unsigned int plen, t;
-
-                /* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
-                 * fallback to "reg" property and assume no threads
-                 */
-                intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
-                                &plen);
-                if (intserv == NULL) {
-                        const u32 *reg = of_get_property(np, "reg", NULL);
-                        if (reg == NULL)
-                                continue;
-                        if (*reg == hardid) {
-                                if (thread)
-                                        *thread = 0;
-                                return np;
-                        }
-                } else {
-                        plen /= sizeof(u32);
-                        for (t = 0; t < plen; t++) {
-                                if (hardid == intserv[t]) {
-                                        if (thread)
-                                                *thread = t;
-                                        return np;
-                                }
-                        }
-                }
-        }
-        return NULL;
+        return (int)phys_id == get_hard_smp_processor_id(cpu);
 }
-EXPORT_SYMBOL(of_get_cpu_node);
 
 #if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
 static struct debugfs_blob_wrapper flat_dt_blob;
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 51be8fb24803..0554d1f6d70d 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -233,6 +233,16 @@ dont_backup_fp:
         std     r5, _CCR(r7)
         std     r6, _XER(r7)
 
+
+        /* ******************** TAR, PPR, DSCR ********** */
+        mfspr   r3, SPRN_TAR
+        mfspr   r4, SPRN_PPR
+        mfspr   r5, SPRN_DSCR
+
+        std     r3, THREAD_TM_TAR(r12)
+        std     r4, THREAD_TM_PPR(r12)
+        std     r5, THREAD_TM_DSCR(r12)
+
         /* MSR and flags:  We don't change CRs, and we don't need to alter
          * MSR.
          */
@@ -347,6 +357,16 @@ dont_restore_fp:
         mtmsr   r6                              /* FP/Vec off again! */
 
 restore_gprs:
+
+        /* ******************** TAR, PPR, DSCR ********** */
+        ld      r4, THREAD_TM_TAR(r3)
+        ld      r5, THREAD_TM_PPR(r3)
+        ld      r6, THREAD_TM_DSCR(r3)
+
+        mtspr   SPRN_TAR,       r4
+        mtspr   SPRN_PPR,       r5
+        mtspr   SPRN_DSCR,      r6
+
         /* ******************** CR,LR,CCR,MSR ********** */
         ld      r3, _CTR(r7)
         ld      r4, _LINK(r7)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index bf33c22e38a4..e435bc089ea3 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -44,9 +44,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/pmc.h>
-#ifdef CONFIG_PPC32
 #include <asm/reg.h>
-#endif
 #ifdef CONFIG_PMAC_BACKLIGHT
 #include <asm/backlight.h>
 #endif
@@ -1296,43 +1294,54 @@ void vsx_unavailable_exception(struct pt_regs *regs)
         die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
 }
 
+#ifdef CONFIG_PPC64
 void facility_unavailable_exception(struct pt_regs *regs)
 {
         static char *facility_strings[] = {
-                "FPU",
-                "VMX/VSX",
-                "DSCR",
-                "PMU SPRs",
-                "BHRB",
-                "TM",
-                "AT",
-                "EBB",
-                "TAR",
+                [FSCR_FP_LG] = "FPU",
+                [FSCR_VECVSX_LG] = "VMX/VSX",
+                [FSCR_DSCR_LG] = "DSCR",
+                [FSCR_PM_LG] = "PMU SPRs",
+                [FSCR_BHRB_LG] = "BHRB",
+                [FSCR_TM_LG] = "TM",
+                [FSCR_EBB_LG] = "EBB",
+                [FSCR_TAR_LG] = "TAR",
         };
-        char *facility, *prefix;
+        char *facility = "unknown";
         u64 value;
+        u8 status;
+        bool hv;
 
-        if (regs->trap == 0xf60) {
-                value = mfspr(SPRN_FSCR);
-                prefix = "";
-        } else {
+        hv = (regs->trap == 0xf80);
+        if (hv)
                 value = mfspr(SPRN_HFSCR);
-                prefix = "Hypervisor ";
+        else
+                value = mfspr(SPRN_FSCR);
+
+        status = value >> 56;
+        if (status == FSCR_DSCR_LG) {
+                /* User is acessing the DSCR.  Set the inherit bit and allow
+                 * the user to set it directly in future by setting via the
+                 * H/FSCR DSCR bit.
+                 */
+                current->thread.dscr_inherit = 1;
+                if (hv)
+                        mtspr(SPRN_HFSCR, value | HFSCR_DSCR);
+                else
+                        mtspr(SPRN_FSCR,  value | FSCR_DSCR);
+                return;
         }
 
-        value = value >> 56;
+        if ((status < ARRAY_SIZE(facility_strings)) &&
+            facility_strings[status])
+                facility = facility_strings[status];
 
         /* We restore the interrupt state now */
         if (!arch_irq_disabled_regs(regs))
                 local_irq_enable();
 
-        if (value < ARRAY_SIZE(facility_strings))
-                facility = facility_strings[value];
-        else
-                facility = "unknown";
-
         pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
-                prefix, facility, regs->nip, regs->msr);
+               hv ? "Hypervisor " : "", facility, regs->nip, regs->msr);
 
         if (user_mode(regs)) {
                 _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
@@ -1341,6 +1350,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 
         die("Unexpected facility unavailable exception", regs, SIGABRT);
 }
+#endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2efa9dde741a..7629cd3eb91a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1809,7 +1809,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
                 rma_size <<= PAGE_SHIFT;
                 rmls = lpcr_rmls(rma_size);
                 err = -EINVAL;
-                if (rmls < 0) {
+                if ((long)rmls < 0) {
                         pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
                         goto out_srcu;
                 }
@@ -1874,7 +1874,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
         /* Allocate the guest's logical partition ID */
 
         lpid = kvmppc_alloc_lpid();
-        if (lpid < 0)
+        if ((long)lpid < 0)
                 return -ENOMEM;
         kvm->arch.lpid = lpid;
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 19498a567a81..c6e13d9a9e15 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1047,11 +1047,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
         if (err)
                 goto free_shadow_vcpu;
 
+        err = -ENOMEM;
         p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
-        /* the real shared page fills the last 4k of our page */
-        vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
         if (!p)
                 goto uninit_vcpu;
+        /* the real shared page fills the last 4k of our page */
+        vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
 
 #ifdef CONFIG_PPC_BOOK3S_64
         /* default to book3s_64 (970fx) */
diff --git a/arch/powerpc/perf/power7-events-list.h b/arch/powerpc/perf/power7-events-list.h
new file mode 100644
index 000000000000..687790a2c0b8
--- /dev/null
+++ b/arch/powerpc/perf/power7-events-list.h
@@ -0,0 +1,548 @@
+/*
+ * Performance counter support for POWER7 processors.
+ *
+ * Copyright 2013 Runzhen Wang, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+EVENT(PM_IC_DEMAND_L2_BR_ALL,                 0x04898)
+EVENT(PM_GCT_UTIL_7_TO_10_SLOTS,              0x020a0)
+EVENT(PM_PMC2_SAVED,                          0x10022)
+EVENT(PM_CMPLU_STALL_DFU,                     0x2003c)
+EVENT(PM_VSU0_16FLOP,                         0x0a0a4)
+EVENT(PM_MRK_LSU_DERAT_MISS,                  0x3d05a)
+EVENT(PM_MRK_ST_CMPL,                         0x10034)
+EVENT(PM_NEST_PAIR3_ADD,                      0x40881)
+EVENT(PM_L2_ST_DISP,                          0x46180)
+EVENT(PM_L2_CASTOUT_MOD,                      0x16180)
+EVENT(PM_ISEG,                                0x020a4)
+EVENT(PM_MRK_INST_TIMEO,                      0x40034)
+EVENT(PM_L2_RCST_DISP_FAIL_ADDR,              0x36282)
+EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM,         0x0d0b6)
+EVENT(PM_IERAT_WR_64K,                        0x040be)
+EVENT(PM_MRK_DTLB_MISS_16M,                   0x4d05e)
+EVENT(PM_IERAT_MISS,                          0x100f6)
+EVENT(PM_MRK_PTEG_FROM_LMEM,                  0x4d052)
+EVENT(PM_FLOP,                                0x100f4)
+EVENT(PM_THRD_PRIO_4_5_CYC,                   0x040b4)
+EVENT(PM_BR_PRED_TA,                          0x040aa)
+EVENT(PM_CMPLU_STALL_FXU,                     0x20014)
+EVENT(PM_EXT_INT,                             0x200f8)
+EVENT(PM_VSU_FSQRT_FDIV,                      0x0a888)
+EVENT(PM_MRK_LD_MISS_EXPOSED_CYC,             0x1003e)
+EVENT(PM_LSU1_LDF,                            0x0c086)
+EVENT(PM_IC_WRITE_ALL,                        0x0488c)
+EVENT(PM_LSU0_SRQ_STFWD,                      0x0c0a0)
+EVENT(PM_PTEG_FROM_RL2L3_MOD,                 0x1c052)
+EVENT(PM_MRK_DATA_FROM_L31_SHR,               0x1d04e)
+EVENT(PM_DATA_FROM_L21_MOD,                   0x3c046)
+EVENT(PM_VSU1_SCAL_DOUBLE_ISSUED,             0x0b08a)
+EVENT(PM_VSU0_8FLOP,                          0x0a0a0)
+EVENT(PM_POWER_EVENT1,                        0x1006e)
+EVENT(PM_DISP_CLB_HELD_BAL,                   0x02092)
+EVENT(PM_VSU1_2FLOP,                          0x0a09a)
+EVENT(PM_LWSYNC_HELD,                         0x0209a)
+EVENT(PM_PTEG_FROM_DL2L3_SHR,                 0x3c054)
+EVENT(PM_INST_FROM_L21_MOD,                   0x34046)
+EVENT(PM_IERAT_XLATE_WR_16MPLUS,              0x040bc)
+EVENT(PM_IC_REQ_ALL,                          0x04888)
+EVENT(PM_DSLB_MISS,                           0x0d090)
+EVENT(PM_L3_MISS,                             0x1f082)
+EVENT(PM_LSU0_L1_PREF,                        0x0d0b8)
+EVENT(PM_VSU_SCALAR_SINGLE_ISSUED,            0x0b884)
+EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM_STRIDE,  0x0d0be)
+EVENT(PM_L2_INST,                             0x36080)
+EVENT(PM_VSU0_FRSP,                           0x0a0b4)
+EVENT(PM_FLUSH_DISP,                          0x02082)
+EVENT(PM_PTEG_FROM_L2MISS,                    0x4c058)
+EVENT(PM_VSU1_DQ_ISSUED,                      0x0b09a)
+EVENT(PM_CMPLU_STALL_LSU,                     0x20012)
+EVENT(PM_MRK_DATA_FROM_DMEM,                  0x1d04a)
+EVENT(PM_LSU_FLUSH_ULD,                       0x0c8b0)
+EVENT(PM_PTEG_FROM_LMEM,                      0x4c052)
+EVENT(PM_MRK_DERAT_MISS_16M,                  0x3d05c)
+EVENT(PM_THRD_ALL_RUN_CYC,                    0x2000c)
+EVENT(PM_MEM0_PREFETCH_DISP,                  0x20083)
+EVENT(PM_MRK_STALL_CMPLU_CYC_COUNT,           0x3003f)
+EVENT(PM_DATA_FROM_DL2L3_MOD,                 0x3c04c)
+EVENT(PM_VSU_FRSP,                            0x0a8b4)
+EVENT(PM_MRK_DATA_FROM_L21_MOD,               0x3d046)
+EVENT(PM_PMC1_OVERFLOW,                       0x20010)
+EVENT(PM_VSU0_SINGLE,                         0x0a0a8)
+EVENT(PM_MRK_PTEG_FROM_L3MISS,                0x2d058)
+EVENT(PM_MRK_PTEG_FROM_L31_SHR,               0x2d056)
+EVENT(PM_VSU0_VECTOR_SP_ISSUED,               0x0b090)
+EVENT(PM_VSU1_FEST,                           0x0a0ba)
+EVENT(PM_MRK_INST_DISP,                       0x20030)
+EVENT(PM_VSU0_COMPLEX_ISSUED,                 0x0b096)
+EVENT(PM_LSU1_FLUSH_UST,                      0x0c0b6)
+EVENT(PM_INST_CMPL,                           0x00002)
+EVENT(PM_FXU_IDLE,                            0x1000e)
+EVENT(PM_LSU0_FLUSH_ULD,                      0x0c0b0)
+EVENT(PM_MRK_DATA_FROM_DL2L3_MOD,             0x3d04c)
+EVENT(PM_LSU_LMQ_SRQ_EMPTY_ALL_CYC,           0x3001c)
+EVENT(PM_LSU1_REJECT_LMQ_FULL,                0x0c0a6)
+EVENT(PM_INST_PTEG_FROM_L21_MOD,              0x3e056)
+EVENT(PM_INST_FROM_RL2L3_MOD,                 0x14042)
+EVENT(PM_SHL_CREATED,                         0x05082)
+EVENT(PM_L2_ST_HIT,                           0x46182)
+EVENT(PM_DATA_FROM_DMEM,                      0x1c04a)
+EVENT(PM_L3_LD_MISS,                          0x2f082)
+EVENT(PM_FXU1_BUSY_FXU0_IDLE,                 0x4000e)
+EVENT(PM_DISP_CLB_HELD_RES,                   0x02094)
+EVENT(PM_L2_SN_SX_I_DONE,                     0x36382)
+EVENT(PM_GRP_CMPL,                            0x30004)
+EVENT(PM_STCX_CMPL,                           0x0c098)
+EVENT(PM_VSU0_2FLOP,                          0x0a098)
+EVENT(PM_L3_PREF_MISS,                        0x3f082)
+EVENT(PM_LSU_SRQ_SYNC_CYC,                    0x0d096)
+EVENT(PM_LSU_REJECT_ERAT_MISS,                0x20064)
+EVENT(PM_L1_ICACHE_MISS,                      0x200fc)
+EVENT(PM_LSU1_FLUSH_SRQ,                      0x0c0be)
+EVENT(PM_LD_REF_L1_LSU0,                      0x0c080)
+EVENT(PM_VSU0_FEST,                           0x0a0b8)
+EVENT(PM_VSU_VECTOR_SINGLE_ISSUED,            0x0b890)
+EVENT(PM_FREQ_UP,                             0x4000c)
+EVENT(PM_DATA_FROM_LMEM,                      0x3c04a)
+EVENT(PM_LSU1_LDX,                            0x0c08a)
+EVENT(PM_PMC3_OVERFLOW,                       0x40010)
+EVENT(PM_MRK_BR_MPRED,                        0x30036)
+EVENT(PM_SHL_MATCH,                           0x05086)
+EVENT(PM_MRK_BR_TAKEN,                        0x10036)
+EVENT(PM_CMPLU_STALL_BRU,                     0x4004e)
+EVENT(PM_ISLB_MISS,                           0x0d092)
+EVENT(PM_CYC,                                 0x0001e)
+EVENT(PM_DISP_HELD_THERMAL,                   0x30006)
+EVENT(PM_INST_PTEG_FROM_RL2L3_SHR,            0x2e054)
+EVENT(PM_LSU1_SRQ_STFWD,                      0x0c0a2)
+EVENT(PM_GCT_NOSLOT_BR_MPRED,                 0x4001a)
+EVENT(PM_1PLUS_PPC_CMPL,                      0x100f2)
+EVENT(PM_PTEG_FROM_DMEM,                      0x2c052)
+EVENT(PM_VSU_2FLOP,                           0x0a898)
+EVENT(PM_GCT_FULL_CYC,                        0x04086)
+EVENT(PM_MRK_DATA_FROM_L3_CYC,                0x40020)
+EVENT(PM_LSU_SRQ_S0_ALLOC,                    0x0d09d)
+EVENT(PM_MRK_DERAT_MISS_4K,                   0x1d05c)
+EVENT(PM_BR_MPRED_TA,                         0x040ae)
+EVENT(PM_INST_PTEG_FROM_L2MISS,               0x4e058)
+EVENT(PM_DPU_HELD_POWER,                      0x20006)
+EVENT(PM_RUN_INST_CMPL,                       0x400fa)
+EVENT(PM_MRK_VSU_FIN,                         0x30032)
+EVENT(PM_LSU_SRQ_S0_VALID,                    0x0d09c)
+EVENT(PM_GCT_EMPTY_CYC,                       0x20008)
+EVENT(PM_IOPS_DISP,                           0x30014)
+EVENT(PM_RUN_SPURR,                           0x10008)
+EVENT(PM_PTEG_FROM_L21_MOD,                   0x3c056)
+EVENT(PM_VSU0_1FLOP,                          0x0a080)
+EVENT(PM_SNOOP_TLBIE,                         0x0d0b2)
+EVENT(PM_DATA_FROM_L3MISS,                    0x2c048)
+EVENT(PM_VSU_SINGLE,                          0x0a8a8)
+EVENT(PM_DTLB_MISS_16G,                       0x1c05e)
+EVENT(PM_CMPLU_STALL_VECTOR,                  0x2001c)
+EVENT(PM_FLUSH,                               0x400f8)
+EVENT(PM_L2_LD_HIT,                           0x36182)
+EVENT(PM_NEST_PAIR2_AND,                      0x30883)
+EVENT(PM_VSU1_1FLOP,                          0x0a082)
+EVENT(PM_IC_PREF_REQ,                         0x0408a)
+EVENT(PM_L3_LD_HIT,                           0x2f080)
+EVENT(PM_GCT_NOSLOT_IC_MISS,                  0x2001a)
+EVENT(PM_DISP_HELD,                           0x10006)
+EVENT(PM_L2_LD,                               0x16080)
+EVENT(PM_LSU_FLUSH_SRQ,                       0x0c8bc)
+EVENT(PM_BC_PLUS_8_CONV,                      0x040b8)
+EVENT(PM_MRK_DATA_FROM_L31_MOD_CYC,           0x40026)
+EVENT(PM_CMPLU_STALL_VECTOR_LONG,             0x4004a)
+EVENT(PM_L2_RCST_BUSY_RC_FULL,                0x26282)
+EVENT(PM_TB_BIT_TRANS,                        0x300f8)
+EVENT(PM_THERMAL_MAX,                         0x40006)
+EVENT(PM_LSU1_FLUSH_ULD,                      0x0c0b2)
+EVENT(PM_LSU1_REJECT_LHS,                     0x0c0ae)
+EVENT(PM_LSU_LRQ_S0_ALLOC,                    0x0d09f)
+EVENT(PM_L3_CO_L31,                           0x4f080)
+EVENT(PM_POWER_EVENT4,                        0x4006e)
+EVENT(PM_DATA_FROM_L31_SHR,                   0x1c04e)
+EVENT(PM_BR_UNCOND,                           0x0409e)
+EVENT(PM_LSU1_DC_PREF_STREAM_ALLOC,           0x0d0aa)
+EVENT(PM_PMC4_REWIND,                         0x10020)
+EVENT(PM_L2_RCLD_DISP,                        0x16280)
+EVENT(PM_THRD_PRIO_2_3_CYC,                   0x040b2)
+EVENT(PM_MRK_PTEG_FROM_L2MISS,                0x4d058)
+EVENT(PM_IC_DEMAND_L2_BHT_REDIRECT,           0x04098)
+EVENT(PM_LSU_DERAT_MISS,                      0x200f6)
+EVENT(PM_IC_PREF_CANCEL_L2,                   0x04094)
+EVENT(PM_MRK_FIN_STALL_CYC_COUNT,             0x1003d)
+EVENT(PM_BR_PRED_CCACHE,                      0x040a0)
+EVENT(PM_GCT_UTIL_1_TO_2_SLOTS,               0x0209c)
+EVENT(PM_MRK_ST_CMPL_INT,                     0x30034)
+EVENT(PM_LSU_TWO_TABLEWALK_CYC,               0x0d0a6)
+EVENT(PM_MRK_DATA_FROM_L3MISS,                0x2d048)
+EVENT(PM_GCT_NOSLOT_CYC,                      0x100f8)
+EVENT(PM_LSU_SET_MPRED,                       0x0c0a8)
+EVENT(PM_FLUSH_DISP_TLBIE,                    0x0208a)
+EVENT(PM_VSU1_FCONV,                          0x0a0b2)
+EVENT(PM_DERAT_MISS_16G,                      0x4c05c)
+EVENT(PM_INST_FROM_LMEM,                      0x3404a)
+EVENT(PM_IC_DEMAND_L2_BR_REDIRECT,            0x0409a)
+EVENT(PM_CMPLU_STALL_SCALAR_LONG,             0x20018)
+EVENT(PM_INST_PTEG_FROM_L2,                   0x1e050)
+EVENT(PM_PTEG_FROM_L2,                        0x1c050)
+EVENT(PM_MRK_DATA_FROM_L21_SHR_CYC,           0x20024)
+EVENT(PM_MRK_DTLB_MISS_4K,                    0x2d05a)
+EVENT(PM_VSU0_FPSCR,                          0x0b09c)
+EVENT(PM_VSU1_VECT_DOUBLE_ISSUED,             0x0b082)
+EVENT(PM_MRK_PTEG_FROM_RL2L3_MOD,             0x1d052)
+EVENT(PM_MEM0_RQ_DISP,                        0x10083)
+EVENT(PM_L2_LD_MISS,                          0x26080)
+EVENT(PM_VMX_RESULT_SAT_1,                    0x0b0a0)
+EVENT(PM_L1_PREF,                             0x0d8b8)
+EVENT(PM_MRK_DATA_FROM_LMEM_CYC,              0x2002c)
+EVENT(PM_GRP_IC_MISS_NONSPEC,                 0x1000c)
+EVENT(PM_PB_NODE_PUMP,                        0x10081)
+EVENT(PM_SHL_MERGED,                          0x05084)
+EVENT(PM_NEST_PAIR1_ADD,                      0x20881)
+EVENT(PM_DATA_FROM_L3,                        0x1c048)
+EVENT(PM_LSU_FLUSH,                           0x0208e)
+EVENT(PM_LSU_SRQ_SYNC_COUNT,                  0x0d097)
+EVENT(PM_PMC2_OVERFLOW,                       0x30010)
+EVENT(PM_LSU_LDF,                             0x0c884)
+EVENT(PM_POWER_EVENT3,                        0x3006e)
+EVENT(PM_DISP_WT,                             0x30008)
+EVENT(PM_CMPLU_STALL_REJECT,                  0x40016)
+EVENT(PM_IC_BANK_CONFLICT,                    0x04082)
+EVENT(PM_BR_MPRED_CR_TA,                      0x048ae)
+EVENT(PM_L2_INST_MISS,                        0x36082)
+EVENT(PM_CMPLU_STALL_ERAT_MISS,               0x40018)
+EVENT(PM_NEST_PAIR2_ADD,                      0x30881)
+EVENT(PM_MRK_LSU_FLUSH,                       0x0d08c)
+EVENT(PM_L2_LDST,                             0x16880)
+EVENT(PM_INST_FROM_L31_SHR,                   0x1404e)
+EVENT(PM_VSU0_FIN,                            0x0a0bc)
+EVENT(PM_LARX_LSU,                            0x0c894)
+EVENT(PM_INST_FROM_RMEM,                      0x34042)
+EVENT(PM_DISP_CLB_HELD_TLBIE,                 0x02096)
+EVENT(PM_MRK_DATA_FROM_DMEM_CYC,              0x2002e)
+EVENT(PM_BR_PRED_CR,                          0x040a8)
+EVENT(PM_LSU_REJECT,                          0x10064)
+EVENT(PM_GCT_UTIL_3_TO_6_SLOTS,               0x0209e)
+EVENT(PM_CMPLU_STALL_END_GCT_NOSLOT,          0x10028)
+EVENT(PM_LSU0_REJECT_LMQ_FULL,                0x0c0a4)
+EVENT(PM_VSU_FEST,                            0x0a8b8)
+EVENT(PM_NEST_PAIR0_AND,                      0x10883)
+EVENT(PM_PTEG_FROM_L3,                        0x2c050)
+EVENT(PM_POWER_EVENT2,                        0x2006e)
+EVENT(PM_IC_PREF_CANCEL_PAGE,                 0x04090)
+EVENT(PM_VSU0_FSQRT_FDIV,                     0x0a088)
+EVENT(PM_MRK_GRP_CMPL,                        0x40030)
+EVENT(PM_VSU0_SCAL_DOUBLE_ISSUED,             0x0b088)
+EVENT(PM_GRP_DISP,                            0x3000a)
+EVENT(PM_LSU0_LDX,                            0x0c088)
+EVENT(PM_DATA_FROM_L2,                        0x1c040)
+EVENT(PM_MRK_DATA_FROM_RL2L3_MOD,             0x1d042)
+EVENT(PM_LD_REF_L1,                           0x0c880)
+EVENT(PM_VSU0_VECT_DOUBLE_ISSUED,             0x0b080)
+EVENT(PM_VSU1_2FLOP_DOUBLE,                   0x0a08e)
+EVENT(PM_THRD_PRIO_6_7_CYC,                   0x040b6)
+EVENT(PM_BC_PLUS_8_RSLV_TAKEN,                0x040ba)
+EVENT(PM_BR_MPRED_CR,                         0x040ac)
+EVENT(PM_L3_CO_MEM,                           0x4f082)
+EVENT(PM_LD_MISS_L1,                          0x400f0)
+EVENT(PM_DATA_FROM_RL2L3_MOD,                 0x1c042)
+EVENT(PM_LSU_SRQ_FULL_CYC,                    0x1001a)
+EVENT(PM_TABLEWALK_CYC,                       0x10026)
+EVENT(PM_MRK_PTEG_FROM_RMEM,                  0x3d052)
+EVENT(PM_LSU_SRQ_STFWD,                       0x0c8a0)
+EVENT(PM_INST_PTEG_FROM_RMEM,                 0x3e052)
+EVENT(PM_FXU0_FIN,                            0x10004)
+EVENT(PM_LSU1_L1_SW_PREF,                     0x0c09e)
+EVENT(PM_PTEG_FROM_L31_MOD,                   0x1c054)
+EVENT(PM_PMC5_OVERFLOW,                       0x10024)
+EVENT(PM_LD_REF_L1_LSU1,                      0x0c082)
+EVENT(PM_INST_PTEG_FROM_L21_SHR,              0x4e056)
+EVENT(PM_CMPLU_STALL_THRD,                    0x1001c)
+EVENT(PM_DATA_FROM_RMEM,                      0x3c042)
+EVENT(PM_VSU0_SCAL_SINGLE_ISSUED,             0x0b084)
+EVENT(PM_BR_MPRED_LSTACK,                     0x040a6)
+EVENT(PM_MRK_DATA_FROM_RL2L3_MOD_CYC,         0x40028)
+EVENT(PM_LSU0_FLUSH_UST,                      0x0c0b4)
+EVENT(PM_LSU_NCST,                            0x0c090)
+EVENT(PM_BR_TAKEN,                            0x20004)
+EVENT(PM_INST_PTEG_FROM_LMEM,                 0x4e052)
+EVENT(PM_GCT_NOSLOT_BR_MPRED_IC_MISS,         0x4001c)
+EVENT(PM_DTLB_MISS_4K,                        0x2c05a)
+EVENT(PM_PMC4_SAVED,                          0x30022)
+EVENT(PM_VSU1_PERMUTE_ISSUED,                 0x0b092)
+EVENT(PM_SLB_MISS,                            0x0d890)
+EVENT(PM_LSU1_FLUSH_LRQ,                      0x0c0ba)
+EVENT(PM_DTLB_MISS,                           0x300fc)
+EVENT(PM_VSU1_FRSP,                           0x0a0b6)
+EVENT(PM_VSU_VECTOR_DOUBLE_ISSUED,            0x0b880)
+EVENT(PM_L2_CASTOUT_SHR,                      0x16182)
+EVENT(PM_DATA_FROM_DL2L3_SHR,                 0x3c044)
+EVENT(PM_VSU1_STF,                            0x0b08e)
+EVENT(PM_ST_FIN,                              0x200f0)
+EVENT(PM_PTEG_FROM_L21_SHR,                   0x4c056)
+EVENT(PM_L2_LOC_GUESS_WRONG,                  0x26480)
+EVENT(PM_MRK_STCX_FAIL,                       0x0d08e)
+EVENT(PM_LSU0_REJECT_LHS,                     0x0c0ac)
+EVENT(PM_IC_PREF_CANCEL_HIT,                  0x04092)
+EVENT(PM_L3_PREF_BUSY,                        0x4f080)
+EVENT(PM_MRK_BRU_FIN,                         0x2003a)
+EVENT(PM_LSU1_NCLD,                           0x0c08e)
+EVENT(PM_INST_PTEG_FROM_L31_MOD,              0x1e054)
+EVENT(PM_LSU_NCLD,                            0x0c88c)
+EVENT(PM_LSU_LDX,                             0x0c888)
+EVENT(PM_L2_LOC_GUESS_CORRECT,                0x16480)
+EVENT(PM_THRESH_TIMEO,                        0x10038)
+EVENT(PM_L3_PREF_ST,                          0x0d0ae)
+EVENT(PM_DISP_CLB_HELD_SYNC,                  0x02098)
+EVENT(PM_VSU_SIMPLE_ISSUED,                   0x0b894)
+EVENT(PM_VSU1_SINGLE,                         0x0a0aa)
+EVENT(PM_DATA_TABLEWALK_CYC,                  0x3001a)
+EVENT(PM_L2_RC_ST_DONE,                       0x36380)
+EVENT(PM_MRK_PTEG_FROM_L21_MOD,               0x3d056)
+EVENT(PM_LARX_LSU1,                           0x0c096)
+EVENT(PM_MRK_DATA_FROM_RMEM,                  0x3d042)
+EVENT(PM_DISP_CLB_HELD,                       0x02090)
+EVENT(PM_DERAT_MISS_4K,                       0x1c05c)
+EVENT(PM_L2_RCLD_DISP_FAIL_ADDR,              0x16282)
+EVENT(PM_SEG_EXCEPTION,                       0x028a4)
+EVENT(PM_FLUSH_DISP_SB,                       0x0208c)
+EVENT(PM_L2_DC_INV,                           0x26182)
+EVENT(PM_PTEG_FROM_DL2L3_MOD,                 0x4c054)
+EVENT(PM_DSEG,                                0x020a6)
+EVENT(PM_BR_PRED_LSTACK,                      0x040a2)
+EVENT(PM_VSU0_STF,                            0x0b08c)
+EVENT(PM_LSU_FX_FIN,                          0x10066)
+EVENT(PM_DERAT_MISS_16M,                      0x3c05c)
+EVENT(PM_MRK_PTEG_FROM_DL2L3_MOD,             0x4d054)
+EVENT(PM_GCT_UTIL_11_PLUS_SLOTS,              0x020a2)
+EVENT(PM_INST_FROM_L3,                        0x14048)
+EVENT(PM_MRK_IFU_FIN,                         0x3003a)
+EVENT(PM_ITLB_MISS,                           0x400fc)
+EVENT(PM_VSU_STF,                             0x0b88c)
+EVENT(PM_LSU_FLUSH_UST,                       0x0c8b4)
+EVENT(PM_L2_LDST_MISS,                        0x26880)
+EVENT(PM_FXU1_FIN,                            0x40004)
+EVENT(PM_SHL_DEALLOCATED,                     0x05080)
+EVENT(PM_L2_SN_M_WR_DONE,                     0x46382)
+EVENT(PM_LSU_REJECT_SET_MPRED,                0x0c8a8)
+EVENT(PM_L3_PREF_LD,                          0x0d0ac)
+EVENT(PM_L2_SN_M_RD_DONE,                     0x46380)
+EVENT(PM_MRK_DERAT_MISS_16G,                  0x4d05c)
+EVENT(PM_VSU_FCONV,                           0x0a8b0)
+EVENT(PM_ANY_THRD_RUN_CYC,                    0x100fa)
+EVENT(PM_LSU_LMQ_FULL_CYC,                    0x0d0a4)
+EVENT(PM_MRK_LSU_REJECT_LHS,                  0x0d082)
+EVENT(PM_MRK_LD_MISS_L1_CYC,                  0x4003e)
+EVENT(PM_MRK_DATA_FROM_L2_CYC,                0x20020)
+EVENT(PM_INST_IMC_MATCH_DISP,                 0x30016)
+EVENT(PM_MRK_DATA_FROM_RMEM_CYC,              0x4002c)
+EVENT(PM_VSU0_SIMPLE_ISSUED,                  0x0b094)
+EVENT(PM_CMPLU_STALL_DIV,                     0x40014)
+EVENT(PM_MRK_PTEG_FROM_RL2L3_SHR,             0x2d054)
+EVENT(PM_VSU_FMA_DOUBLE,                      0x0a890)
+EVENT(PM_VSU_4FLOP,                           0x0a89c)
+EVENT(PM_VSU1_FIN,                            0x0a0be)
+EVENT(PM_NEST_PAIR1_AND,                      0x20883)
+EVENT(PM_INST_PTEG_FROM_RL2L3_MOD,            0x1e052)
+EVENT(PM_RUN_CYC,                             0x200f4)
+EVENT(PM_PTEG_FROM_RMEM,                      0x3c052)
+EVENT(PM_LSU_LRQ_S0_VALID,                    0x0d09e)
+EVENT(PM_LSU0_LDF,                            0x0c084)
+EVENT(PM_FLUSH_COMPLETION,                    0x30012)
+EVENT(PM_ST_MISS_L1,                          0x300f0)
+EVENT(PM_L2_NODE_PUMP,                        0x36480)
+EVENT(PM_INST_FROM_DL2L3_SHR,                 0x34044)
+EVENT(PM_MRK_STALL_CMPLU_CYC,                 0x3003e)
+EVENT(PM_VSU1_DENORM,                         0x0a0ae)
+EVENT(PM_MRK_DATA_FROM_L31_SHR_CYC,           0x20026)
+EVENT(PM_NEST_PAIR0_ADD,                      0x10881)
+EVENT(PM_INST_FROM_L3MISS,                    0x24048)
+EVENT(PM_EE_OFF_EXT_INT,                      0x02080)
+EVENT(PM_INST_PTEG_FROM_DMEM,                 0x2e052)
+EVENT(PM_INST_FROM_DL2L3_MOD,                 0x3404c)
+EVENT(PM_PMC6_OVERFLOW,                       0x30024)
+EVENT(PM_VSU_2FLOP_DOUBLE,                    0x0a88c)
+EVENT(PM_TLB_MISS,                            0x20066)
+EVENT(PM_FXU_BUSY,                            0x2000e)
+EVENT(PM_L2_RCLD_DISP_FAIL_OTHER,             0x26280)
+EVENT(PM_LSU_REJECT_LMQ_FULL,                 0x0c8a4)
+EVENT(PM_IC_RELOAD_SHR,                       0x04096)
+EVENT(PM_GRP_MRK,                             0x10031)
+EVENT(PM_MRK_ST_NEST,                         0x20034)
+EVENT(PM_VSU1_FSQRT_FDIV,                     0x0a08a)
+EVENT(PM_LSU0_FLUSH_LRQ,                      0x0c0b8)
+EVENT(PM_LARX_LSU0,                           0x0c094)
+EVENT(PM_IBUF_FULL_CYC,                       0x04084)
+EVENT(PM_MRK_DATA_FROM_DL2L3_SHR_CYC,         0x2002a)
+EVENT(PM_LSU_DC_PREF_STREAM_ALLOC,            0x0d8a8)
+EVENT(PM_GRP_MRK_CYC,                         0x10030)
+EVENT(PM_MRK_DATA_FROM_RL2L3_SHR_CYC,         0x20028)
+EVENT(PM_L2_GLOB_GUESS_CORRECT,               0x16482)
+EVENT(PM_LSU_REJECT_LHS,                      0x0c8ac)
+EVENT(PM_MRK_DATA_FROM_LMEM,                  0x3d04a)
+EVENT(PM_INST_PTEG_FROM_L3,                   0x2e050)
+EVENT(PM_FREQ_DOWN,                           0x3000c)
+EVENT(PM_PB_RETRY_NODE_PUMP,                  0x30081)
+EVENT(PM_INST_FROM_RL2L3_SHR,                 0x1404c)
+EVENT(PM_MRK_INST_ISSUED,                     0x10032)
+EVENT(PM_PTEG_FROM_L3MISS,                    0x2c058)
+EVENT(PM_RUN_PURR,                            0x400f4)
+EVENT(PM_MRK_GRP_IC_MISS,                     0x40038)
+EVENT(PM_MRK_DATA_FROM_L3,                    0x1d048)
+EVENT(PM_CMPLU_STALL_DCACHE_MISS,             0x20016)
+EVENT(PM_PTEG_FROM_RL2L3_SHR,                 0x2c054)
+EVENT(PM_LSU_FLUSH_LRQ,                       0x0c8b8)
+EVENT(PM_MRK_DERAT_MISS_64K,                  0x2d05c)
+EVENT(PM_INST_PTEG_FROM_DL2L3_MOD,            0x4e054)
+EVENT(PM_L2_ST_MISS,                          0x26082)
+EVENT(PM_MRK_PTEG_FROM_L21_SHR,               0x4d056)
+EVENT(PM_LWSYNC,                              0x0d094)
+EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM_STRIDE,  0x0d0bc)
+EVENT(PM_MRK_LSU_FLUSH_LRQ,                   0x0d088)
+EVENT(PM_INST_IMC_MATCH_CMPL,                 0x100f0)
+EVENT(PM_NEST_PAIR3_AND,                      0x40883)
+EVENT(PM_PB_RETRY_SYS_PUMP,                   0x40081)
+EVENT(PM_MRK_INST_FIN,                        0x30030)
+EVENT(PM_MRK_PTEG_FROM_DL2L3_SHR,             0x3d054)
+EVENT(PM_INST_FROM_L31_MOD,                   0x14044)
+EVENT(PM_MRK_DTLB_MISS_64K,                   0x3d05e)
+EVENT(PM_LSU_FIN,                             0x30066)
+EVENT(PM_MRK_LSU_REJECT,                      0x40064)
+EVENT(PM_L2_CO_FAIL_BUSY,                     0x16382)
+EVENT(PM_MEM0_WQ_DISP,                        0x40083)
+EVENT(PM_DATA_FROM_L31_MOD,                   0x1c044)
+EVENT(PM_THERMAL_WARN,                        0x10016)
+EVENT(PM_VSU0_4FLOP,                          0x0a09c)
+EVENT(PM_BR_MPRED_CCACHE,                     0x040a4)
+EVENT(PM_CMPLU_STALL_IFU,                     0x4004c)
+EVENT(PM_L1_DEMAND_WRITE,                     0x0408c)
+EVENT(PM_FLUSH_BR_MPRED,                      0x02084)
+EVENT(PM_MRK_DTLB_MISS_16G,                   0x1d05e)
+EVENT(PM_MRK_PTEG_FROM_DMEM,                  0x2d052)
+EVENT(PM_L2_RCST_DISP,                        0x36280)
+EVENT(PM_CMPLU_STALL,                         0x4000a)
+EVENT(PM_LSU_PARTIAL_CDF,                     0x0c0aa)
+EVENT(PM_DISP_CLB_HELD_SB,                    0x020a8)
+EVENT(PM_VSU0_FMA_DOUBLE,                     0x0a090)
+EVENT(PM_FXU0_BUSY_FXU1_IDLE,                 0x3000e)
+EVENT(PM_IC_DEMAND_CYC,                       0x10018)
+EVENT(PM_MRK_DATA_FROM_L21_SHR,               0x3d04e)
+EVENT(PM_MRK_LSU_FLUSH_UST,                   0x0d086)
+EVENT(PM_INST_PTEG_FROM_L3MISS,               0x2e058)
+EVENT(PM_VSU_DENORM,                          0x0a8ac)
+EVENT(PM_MRK_LSU_PARTIAL_CDF,                 0x0d080)
+EVENT(PM_INST_FROM_L21_SHR,                   0x3404e)
+EVENT(PM_IC_PREF_WRITE,                       0x0408e)
+EVENT(PM_BR_PRED,                             0x0409c)
+EVENT(PM_INST_FROM_DMEM,                      0x1404a)
+EVENT(PM_IC_PREF_CANCEL_ALL,                  0x04890)
+EVENT(PM_LSU_DC_PREF_STREAM_CONFIRM,          0x0d8b4)
+EVENT(PM_MRK_LSU_FLUSH_SRQ,                   0x0d08a)
+EVENT(PM_MRK_FIN_STALL_CYC,                   0x1003c)
+EVENT(PM_L2_RCST_DISP_FAIL_OTHER,             0x46280)
+EVENT(PM_VSU1_DD_ISSUED,                      0x0b098)
+EVENT(PM_PTEG_FROM_L31_SHR,                   0x2c056)
+EVENT(PM_DATA_FROM_L21_SHR,                   0x3c04e)
+EVENT(PM_LSU0_NCLD,                           0x0c08c)
+EVENT(PM_VSU1_4FLOP,                          0x0a09e)
+EVENT(PM_VSU1_8FLOP,                          0x0a0a2)
+EVENT(PM_VSU_8FLOP,                           0x0a8a0)
+EVENT(PM_LSU_LMQ_SRQ_EMPTY_CYC,               0x2003e)
+EVENT(PM_DTLB_MISS_64K,                       0x3c05e)
+EVENT(PM_THRD_CONC_RUN_INST,                  0x300f4)
+EVENT(PM_MRK_PTEG_FROM_L2,                    0x1d050)
+EVENT(PM_PB_SYS_PUMP,                         0x20081)
+EVENT(PM_VSU_FIN,                             0x0a8bc)
+EVENT(PM_MRK_DATA_FROM_L31_MOD,               0x1d044)
+EVENT(PM_THRD_PRIO_0_1_CYC,                   0x040b0)
+EVENT(PM_DERAT_MISS_64K,                      0x2c05c)
+EVENT(PM_PMC2_REWIND,                         0x30020)
+EVENT(PM_INST_FROM_L2,                        0x14040)
+EVENT(PM_GRP_BR_MPRED_NONSPEC,                0x1000a)
+EVENT(PM_INST_DISP,                           0x200f2)
+EVENT(PM_MEM0_RD_CANCEL_TOTAL,                0x30083)
+EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM,         0x0d0b4)
+EVENT(PM_L1_DCACHE_RELOAD_VALID,              0x300f6)
+EVENT(PM_VSU_SCALAR_DOUBLE_ISSUED,            0x0b888)
+EVENT(PM_L3_PREF_HIT,                         0x3f080)
+EVENT(PM_MRK_PTEG_FROM_L31_MOD,               0x1d054)
+EVENT(PM_CMPLU_STALL_STORE,                   0x2004a)
+EVENT(PM_MRK_FXU_FIN,                         0x20038)
+EVENT(PM_PMC4_OVERFLOW,                       0x10010)
+EVENT(PM_MRK_PTEG_FROM_L3,                    0x2d050)
+EVENT(PM_LSU0_LMQ_LHR_MERGE,                  0x0d098)
+EVENT(PM_BTAC_HIT,                            0x0508a)
+EVENT(PM_L3_RD_BUSY,                          0x4f082)
+EVENT(PM_LSU0_L1_SW_PREF,                     0x0c09c)
+EVENT(PM_INST_FROM_L2MISS,                    0x44048)
+EVENT(PM_LSU0_DC_PREF_STREAM_ALLOC,           0x0d0a8)
+EVENT(PM_L2_ST,                               0x16082)
+EVENT(PM_VSU0_DENORM,                         0x0a0ac)
+EVENT(PM_MRK_DATA_FROM_DL2L3_SHR,             0x3d044)
+EVENT(PM_BR_PRED_CR_TA,                       0x048aa)
+EVENT(PM_VSU0_FCONV,                          0x0a0b0)
+EVENT(PM_MRK_LSU_FLUSH_ULD,                   0x0d084)
+EVENT(PM_BTAC_MISS,                           0x05088)
+EVENT(PM_MRK_LD_MISS_EXPOSED_CYC_COUNT,       0x1003f)
+EVENT(PM_MRK_DATA_FROM_L2,                    0x1d040)
+EVENT(PM_LSU_DCACHE_RELOAD_VALID,             0x0d0a2)
+EVENT(PM_VSU_FMA,                             0x0a884)
+EVENT(PM_LSU0_FLUSH_SRQ,                      0x0c0bc)
+EVENT(PM_LSU1_L1_PREF,                        0x0d0ba)
+EVENT(PM_IOPS_CMPL,                           0x10014)
+EVENT(PM_L2_SYS_PUMP,                         0x36482)
+EVENT(PM_L2_RCLD_BUSY_RC_FULL,                0x46282)
+EVENT(PM_LSU_LMQ_S0_ALLOC,                    0x0d0a1)
+EVENT(PM_FLUSH_DISP_SYNC,                     0x02088)
+EVENT(PM_MRK_DATA_FROM_DL2L3_MOD_CYC,         0x4002a)
+EVENT(PM_L2_IC_INV,                           0x26180)
+EVENT(PM_MRK_DATA_FROM_L21_MOD_CYC,           0x40024)
+EVENT(PM_L3_PREF_LDST,                        0x0d8ac)
+EVENT(PM_LSU_SRQ_EMPTY_CYC,                   0x40008)
+EVENT(PM_LSU_LMQ_S0_VALID,                    0x0d0a0)
+EVENT(PM_FLUSH_PARTIAL,                       0x02086)
+EVENT(PM_VSU1_FMA_DOUBLE,                     0x0a092)
+EVENT(PM_1PLUS_PPC_DISP,                      0x400f2)
+EVENT(PM_DATA_FROM_L2MISS,                    0x200fe)
+EVENT(PM_SUSPENDED,                           0x00000)
+EVENT(PM_VSU0_FMA,                            0x0a084)
+EVENT(PM_CMPLU_STALL_SCALAR,                  0x40012)
+EVENT(PM_STCX_FAIL,                           0x0c09a)
+EVENT(PM_VSU0_FSQRT_FDIV_DOUBLE,              0x0a094)
+EVENT(PM_DC_PREF_DST,                         0x0d0b0)
+EVENT(PM_VSU1_SCAL_SINGLE_ISSUED,             0x0b086)
+EVENT(PM_L3_HIT,                              0x1f080)
+EVENT(PM_L2_GLOB_GUESS_WRONG,                 0x26482)
+EVENT(PM_MRK_DFU_FIN,                         0x20032)
+EVENT(PM_INST_FROM_L1,                        0x04080)
+EVENT(PM_BRU_FIN,                             0x10068)
+EVENT(PM_IC_DEMAND_REQ,                       0x04088)
+EVENT(PM_VSU1_FSQRT_FDIV_DOUBLE,              0x0a096)
+EVENT(PM_VSU1_FMA,                            0x0a086)
+EVENT(PM_MRK_LD_MISS_L1,                      0x20036)
+EVENT(PM_VSU0_2FLOP_DOUBLE,                   0x0a08c)
+EVENT(PM_LSU_DC_PREF_STRIDED_STREAM_CONFIRM,  0x0d8bc)
+EVENT(PM_INST_PTEG_FROM_L31_SHR,              0x2e056)
+EVENT(PM_MRK_LSU_REJECT_ERAT_MISS,            0x30064)
+EVENT(PM_MRK_DATA_FROM_L2MISS,                0x4d048)
+EVENT(PM_DATA_FROM_RL2L3_SHR,                 0x1c04c)
+EVENT(PM_INST_FROM_PREF,                      0x14046)
+EVENT(PM_VSU1_SQ,                             0x0b09e)
+EVENT(PM_L2_LD_DISP,                          0x36180)
+EVENT(PM_L2_DISP_ALL,                         0x46080)
+EVENT(PM_THRD_GRP_CMPL_BOTH_CYC,              0x10012)
+EVENT(PM_VSU_FSQRT_FDIV_DOUBLE,               0x0a894)
+EVENT(PM_BR_MPRED,                            0x400f6)
+EVENT(PM_INST_PTEG_FROM_DL2L3_SHR,            0x3e054)
+EVENT(PM_VSU_1FLOP,                           0x0a880)
+EVENT(PM_HV_CYC,                              0x2000a)
+EVENT(PM_MRK_LSU_FIN,                         0x40032)
+EVENT(PM_MRK_DATA_FROM_RL2L3_SHR,             0x1d04c)
+EVENT(PM_DTLB_MISS_16M,                       0x4c05e)
+EVENT(PM_LSU1_LMQ_LHR_MERGE,                  0x0d09a)
+EVENT(PM_IFU_FIN,                             0x40066)
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index d1821b8bbc4c..56c67bca2f75 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -53,37 +53,13 @@
 /*
  * Power7 event codes.
  */
-#define PME_PM_CYC                      0x1e
-#define PME_PM_GCT_NOSLOT_CYC           0x100f8
-#define PME_PM_CMPLU_STALL              0x4000a
-#define PME_PM_INST_CMPL                0x2
-#define PME_PM_LD_REF_L1                0xc880
-#define PME_PM_LD_MISS_L1               0x400f0
-#define PME_PM_BRU_FIN                  0x10068
-#define PME_PM_BR_MPRED                 0x400f6
-
-#define PME_PM_CMPLU_STALL_FXU                  0x20014
-#define PME_PM_CMPLU_STALL_DIV                  0x40014
-#define PME_PM_CMPLU_STALL_SCALAR               0x40012
-#define PME_PM_CMPLU_STALL_SCALAR_LONG          0x20018
-#define PME_PM_CMPLU_STALL_VECTOR               0x2001c
-#define PME_PM_CMPLU_STALL_VECTOR_LONG          0x4004a
-#define PME_PM_CMPLU_STALL_LSU                  0x20012
-#define PME_PM_CMPLU_STALL_REJECT               0x40016
-#define PME_PM_CMPLU_STALL_ERAT_MISS            0x40018
-#define PME_PM_CMPLU_STALL_DCACHE_MISS          0x20016
-#define PME_PM_CMPLU_STALL_STORE                0x2004a
-#define PME_PM_CMPLU_STALL_THRD                 0x1001c
-#define PME_PM_CMPLU_STALL_IFU                  0x4004c
-#define PME_PM_CMPLU_STALL_BRU                  0x4004e
-#define PME_PM_GCT_NOSLOT_IC_MISS               0x2001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED              0x4001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS      0x4001c
-#define PME_PM_GRP_CMPL                         0x30004
-#define PME_PM_1PLUS_PPC_CMPL                   0x100f2
-#define PME_PM_CMPLU_STALL_DFU                  0x2003c
-#define PME_PM_RUN_CYC                          0x200f4
-#define PME_PM_RUN_INST_CMPL                    0x400fa
+#define EVENT(_name, _code) \
+        PME_##_name = _code,
+
+enum {
+#include "power7-events-list.h"
+};
+#undef EVENT
 
 /*
  * Layout of constraint bits:
@@ -398,96 +374,36 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 };
 
 
-GENERIC_EVENT_ATTR(cpu-cycles,                  CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-frontend,     GCT_NOSLOT_CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-backend,      CMPLU_STALL);
-GENERIC_EVENT_ATTR(instructions,                INST_CMPL);
-GENERIC_EVENT_ATTR(cache-references,            LD_REF_L1);
-GENERIC_EVENT_ATTR(cache-misses,                LD_MISS_L1);
-GENERIC_EVENT_ATTR(branch-instructions,         BRU_FIN);
-GENERIC_EVENT_ATTR(branch-misses,               BR_MPRED);
-
-POWER_EVENT_ATTR(CYC,                           CYC);
-POWER_EVENT_ATTR(GCT_NOSLOT_CYC,                GCT_NOSLOT_CYC);
-POWER_EVENT_ATTR(CMPLU_STALL,                   CMPLU_STALL);
-POWER_EVENT_ATTR(INST_CMPL,                     INST_CMPL);
-POWER_EVENT_ATTR(LD_REF_L1,                     LD_REF_L1);
-POWER_EVENT_ATTR(LD_MISS_L1,                    LD_MISS_L1);
-POWER_EVENT_ATTR(BRU_FIN,                       BRU_FIN)
-POWER_EVENT_ATTR(BR_MPRED,                      BR_MPRED);
-
-POWER_EVENT_ATTR(CMPLU_STALL_FXU,               CMPLU_STALL_FXU);
-POWER_EVENT_ATTR(CMPLU_STALL_DIV,               CMPLU_STALL_DIV);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR,            CMPLU_STALL_SCALAR);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG,       CMPLU_STALL_SCALAR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR,            CMPLU_STALL_VECTOR);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG,       CMPLU_STALL_VECTOR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_LSU,               CMPLU_STALL_LSU);
-POWER_EVENT_ATTR(CMPLU_STALL_REJECT,            CMPLU_STALL_REJECT);
-
-POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS,         CMPLU_STALL_ERAT_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS,       CMPLU_STALL_DCACHE_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_STORE,             CMPLU_STALL_STORE);
-POWER_EVENT_ATTR(CMPLU_STALL_THRD,              CMPLU_STALL_THRD);
-POWER_EVENT_ATTR(CMPLU_STALL_IFU,               CMPLU_STALL_IFU);
-POWER_EVENT_ATTR(CMPLU_STALL_BRU,               CMPLU_STALL_BRU);
-POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS,            GCT_NOSLOT_IC_MISS);
-
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED,           GCT_NOSLOT_BR_MPRED);
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS,   GCT_NOSLOT_BR_MPRED_IC_MISS);
-POWER_EVENT_ATTR(GRP_CMPL,                      GRP_CMPL);
-POWER_EVENT_ATTR(1PLUS_PPC_CMPL,                1PLUS_PPC_CMPL);
-POWER_EVENT_ATTR(CMPLU_STALL_DFU,               CMPLU_STALL_DFU);
-POWER_EVENT_ATTR(RUN_CYC,                       RUN_CYC);
-POWER_EVENT_ATTR(RUN_INST_CMPL,                 RUN_INST_CMPL);
+GENERIC_EVENT_ATTR(cpu-cycles,                  PM_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,     PM_GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,      PM_CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,                PM_INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references,            PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,                PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions,         PM_BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses,               PM_BR_MPRED);
+
+#define EVENT(_name, _code)     POWER_EVENT_ATTR(_name, _name);
+#include "power7-events-list.h"
+#undef EVENT
+
+#define EVENT(_name, _code)     POWER_EVENT_PTR(_name),
 
 static struct attribute *power7_events_attr[] = {
-        GENERIC_EVENT_PTR(CYC),
-        GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
-        GENERIC_EVENT_PTR(CMPLU_STALL),
-        GENERIC_EVENT_PTR(INST_CMPL),
-        GENERIC_EVENT_PTR(LD_REF_L1),
-        GENERIC_EVENT_PTR(LD_MISS_L1),
-        GENERIC_EVENT_PTR(BRU_FIN),
-        GENERIC_EVENT_PTR(BR_MPRED),
-
-        POWER_EVENT_PTR(CYC),
-        POWER_EVENT_PTR(GCT_NOSLOT_CYC),
-        POWER_EVENT_PTR(CMPLU_STALL),
-        POWER_EVENT_PTR(INST_CMPL),
-        POWER_EVENT_PTR(LD_REF_L1),
-        POWER_EVENT_PTR(LD_MISS_L1),
-        POWER_EVENT_PTR(BRU_FIN),
-        POWER_EVENT_PTR(BR_MPRED),
-
-        POWER_EVENT_PTR(CMPLU_STALL_FXU),
-        POWER_EVENT_PTR(CMPLU_STALL_DIV),
-        POWER_EVENT_PTR(CMPLU_STALL_SCALAR),
-        POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG),
-        POWER_EVENT_PTR(CMPLU_STALL_VECTOR),
-        POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG),
-        POWER_EVENT_PTR(CMPLU_STALL_LSU),
-        POWER_EVENT_PTR(CMPLU_STALL_REJECT),
-
-        POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS),
-        POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS),
-        POWER_EVENT_PTR(CMPLU_STALL_STORE),
-        POWER_EVENT_PTR(CMPLU_STALL_THRD),
-        POWER_EVENT_PTR(CMPLU_STALL_IFU),
-        POWER_EVENT_PTR(CMPLU_STALL_BRU),
-        POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS),
-        POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED),
-
-        POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS),
-        POWER_EVENT_PTR(GRP_CMPL),
-        POWER_EVENT_PTR(1PLUS_PPC_CMPL),
-        POWER_EVENT_PTR(CMPLU_STALL_DFU),
-        POWER_EVENT_PTR(RUN_CYC),
-        POWER_EVENT_PTR(RUN_INST_CMPL),
+        GENERIC_EVENT_PTR(PM_CYC),
+        GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC),
+        GENERIC_EVENT_PTR(PM_CMPLU_STALL),
+        GENERIC_EVENT_PTR(PM_INST_CMPL),
+        GENERIC_EVENT_PTR(PM_LD_REF_L1),
+        GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+        GENERIC_EVENT_PTR(PM_BRU_FIN),
+        GENERIC_EVENT_PTR(PM_BR_MPRED),
+
+        #include "power7-events-list.h"
+        #undef EVENT
         NULL
 };
 
-
 static struct attribute_group power7_pmu_events_group = {
         .name = "events",
         .attrs = power7_events_attr,
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 9f8671a44551..d276cd3edd8f 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -539,65 +539,6 @@ static int zip_oops(size_t text_len)
 }
 
 #ifdef CONFIG_PSTORE
-/* Derived from logfs_uncompress */
-int nvram_decompress(void *in, void *out, size_t inlen, size_t outlen)
-{
-        int err, ret;
-
-        ret = -EIO;
-        err = zlib_inflateInit(&stream);
-        if (err != Z_OK)
-                goto error;
-
-        stream.next_in = in;
-        stream.avail_in = inlen;
-        stream.total_in = 0;
-        stream.next_out = out;
-        stream.avail_out = outlen;
-        stream.total_out = 0;
-
-        err = zlib_inflate(&stream, Z_FINISH);
-        if (err != Z_STREAM_END)
-                goto error;
-
-        err = zlib_inflateEnd(&stream);
-        if (err != Z_OK)
-                goto error;
-
-        ret = stream.total_out;
-error:
-        return ret;
-}
-
-static int unzip_oops(char *oops_buf, char *big_buf)
-{
-        struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
-        u64 timestamp = oops_hdr->timestamp;
-        char *big_oops_data = NULL;
-        char *oops_data_buf = NULL;
-        size_t big_oops_data_sz;
-        int unzipped_len;
-
-        big_oops_data = big_buf + sizeof(struct oops_log_info);
-        big_oops_data_sz = big_oops_buf_sz - sizeof(struct oops_log_info);
-        oops_data_buf = oops_buf + sizeof(struct oops_log_info);
-
-        unzipped_len = nvram_decompress(oops_data_buf, big_oops_data,
-                                        oops_hdr->report_length,
-                                        big_oops_data_sz);
-
-        if (unzipped_len < 0) {
-                pr_err("nvram: decompression failed; returned %d\n",
-                                                                unzipped_len);
-                return -1;
-        }
-        oops_hdr = (struct oops_log_info *)big_buf;
-        oops_hdr->version = OOPS_HDR_VERSION;
-        oops_hdr->report_length = (u16) unzipped_len;
-        oops_hdr->timestamp = timestamp;
-        return 0;
-}
-
 static int nvram_pstore_open(struct pstore_info *psi)
 {
         /* Reset the iterator to start reading partitions again */
@@ -613,7 +554,7 @@ static int nvram_pstore_open(struct pstore_info *psi)
  * @part:               pstore writes data to registered buffer in parts,
  *                      part number will indicate the same.
  * @count:              Indicates oops count
- * @hsize:              Size of header added by pstore
+ * @compressed:         Flag to indicate the log is compressed
  * @size:               number of bytes written to the registered buffer
  * @psi:                registered pstore_info structure
  *
@@ -624,7 +565,7 @@ static int nvram_pstore_open(struct pstore_info *psi)
 static int nvram_pstore_write(enum pstore_type_id type,
                                 enum kmsg_dump_reason reason,
                                 u64 *id, unsigned int part, int count,
-                                size_t hsize, size_t size,
+                                bool compressed, size_t size,
                                 struct pstore_info *psi)
 {
         int rc;
@@ -640,30 +581,11 @@ static int nvram_pstore_write(enum pstore_type_id type,
         oops_hdr->report_length = (u16) size;
         oops_hdr->timestamp = get_seconds();
 
-        if (big_oops_buf) {
-                rc = zip_oops(size);
-                /*
-                 * If compression fails copy recent log messages from
-                 * big_oops_buf to oops_data.
-                 */
-                if (rc != 0) {
-                        size_t diff = size - oops_data_sz + hsize;
-
-                        if (size > oops_data_sz) {
-                                memcpy(oops_data, big_oops_buf, hsize);
-                                memcpy(oops_data + hsize, big_oops_buf + diff,
-                                        oops_data_sz - hsize);
-
-                                oops_hdr->report_length = (u16) oops_data_sz;
-                        } else
-                                memcpy(oops_data, big_oops_buf, size);
-                } else
-                        err_type = ERR_TYPE_KERNEL_PANIC_GZ;
-        }
+        if (compressed)
+                err_type = ERR_TYPE_KERNEL_PANIC_GZ;
 
         rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
-                (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
-                count);
+                (int) (sizeof(*oops_hdr) + size), err_type, count);
 
         if (rc != 0)
                 return rc;
@@ -679,16 +601,15 @@ static int nvram_pstore_write(enum pstore_type_id type,
  */
 static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
                                 int *count, struct timespec *time, char **buf,
-                                struct pstore_info *psi)
+                                bool *compressed, struct pstore_info *psi)
 {
         struct oops_log_info *oops_hdr;
         unsigned int err_type, id_no, size = 0;
         struct nvram_os_partition *part = NULL;
-        char *buff = NULL, *big_buff = NULL;
-        int rc, sig = 0;
+        char *buff = NULL;
+        int sig = 0;
         loff_t p;
 
-read_partition:
         read_type++;
 
         switch (nvram_type_ids[read_type]) {
@@ -749,30 +670,32 @@ read_partition:
                 *id = id_no;
 
         if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
-                oops_hdr = (struct oops_log_info *)buff;
-                *buf = buff + sizeof(*oops_hdr);
-
-                if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) {
-                        big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL);
-                        if (!big_buff)
-                                return -ENOMEM;
-
-                        rc = unzip_oops(buff, big_buff);
+                size_t length, hdr_size;
 
-                        if (rc != 0) {
-                                kfree(buff);
-                                kfree(big_buff);
-                                goto read_partition;
-                        }
-
-                        oops_hdr = (struct oops_log_info *)big_buff;
-                        *buf = big_buff + sizeof(*oops_hdr);
-                        kfree(buff);
+                oops_hdr = (struct oops_log_info *)buff;
+                if (oops_hdr->version < OOPS_HDR_VERSION) {
+                        /* Old format oops header had 2-byte record size */
+                        hdr_size = sizeof(u16);
+                        length = oops_hdr->version;
+                        time->tv_sec = 0;
+                        time->tv_nsec = 0;
+                } else {
+                        hdr_size = sizeof(*oops_hdr);
+                        length = oops_hdr->report_length;
+                        time->tv_sec = oops_hdr->timestamp;
+                        time->tv_nsec = 0;
                 }
+                *buf = kmalloc(length, GFP_KERNEL);
+                if (*buf == NULL)
+                        return -ENOMEM;
+                memcpy(*buf, buff + hdr_size, length);
+                kfree(buff);
 
-                time->tv_sec = oops_hdr->timestamp;
-                time->tv_nsec = 0;
-                return oops_hdr->report_length;
+                if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
+                        *compressed = true;
+                else
+                        *compressed = false;
+                return length;
         }
 
         *buf = buff;
@@ -791,13 +714,8 @@ static int nvram_pstore_init(void)
 {
         int rc = 0;
 
-        if (big_oops_buf) {
-                nvram_pstore_info.buf = big_oops_buf;
-                nvram_pstore_info.bufsize = big_oops_buf_sz;
-        } else {
-                nvram_pstore_info.buf = oops_data;
-                nvram_pstore_info.bufsize = oops_data_sz;
-        }
+        nvram_pstore_info.buf = oops_data;
+        nvram_pstore_info.bufsize = oops_data_sz;
 
         rc = pstore_register(&nvram_pstore_info);
         if (rc != 0)
@@ -836,6 +754,11 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
         oops_data = oops_buf + sizeof(struct oops_log_info);
         oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
 
+        rc = nvram_pstore_init();
+
+        if (!rc)
+                return;
+
         /*
          * Figure compression (preceded by elimination of each line's <n>
          * severity prefix) will reduce the oops/panic report to at most
@@ -844,8 +767,8 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
         big_oops_buf_sz = (oops_data_sz * 100) / 45;
         big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
         if (big_oops_buf) {
-                stream.workspace = kmalloc(zlib_deflate_workspacesize(
-                                WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+                stream.workspace =  kmalloc(zlib_deflate_workspacesize(
+                                        WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
                 if (!stream.workspace) {
                         pr_err("nvram: No memory for compression workspace; "
                                 "skipping compression of %s partition data\n",
@@ -859,11 +782,6 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
                 stream.workspace = NULL;
         }
 
-        rc = nvram_pstore_init();
-
-        if (!rc)
-                return;
-
         rc = kmsg_dump_register(&nvram_kmsg_dumper);
         if (rc != 0) {
                 pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 22f75b504f7f..8b7892bf6d8b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -116,8 +116,10 @@ config S390
         select HAVE_FUNCTION_GRAPH_TRACER
         select HAVE_FUNCTION_TRACER
         select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+        select HAVE_GENERIC_HARDIRQS
         select HAVE_KERNEL_BZIP2
         select HAVE_KERNEL_GZIP
+        select HAVE_KERNEL_LZ4
         select HAVE_KERNEL_LZMA
         select HAVE_KERNEL_LZO
         select HAVE_KERNEL_XZ
@@ -227,11 +229,12 @@ config MARCH_Z196
           not work on older machines.
 
 config MARCH_ZEC12
-        bool "IBM zEC12"
+        bool "IBM zBC12 and zEC12"
         select HAVE_MARCH_ZEC12_FEATURES if 64BIT
         help
-          Select this to enable optimizations for IBM zEC12 (2827 series). The
-          kernel will be slightly faster but will not work on older machines.
+          Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and
+          2827 series). The kernel will be slightly faster but will not work on
+          older machines.
 
 endchoice
 
@@ -443,6 +446,16 @@ config PCI_NR_FUNCTIONS
           This allows you to specify the maximum number of PCI functions which
           this kernel will support.
 
+config PCI_NR_MSI
+        int "Maximum number of MSI interrupts (64-32768)"
+        range 64 32768
+        default "256"
+        help
+          This defines the number of virtual interrupts the kernel will
+          provide for MSI interrupts. If you configure your system to have
+          too few drivers will fail to allocate MSI interrupts for all
+          PCI devices.
+
 source "drivers/pci/Kconfig"
 source "drivers/pci/pcie/Kconfig"
 source "drivers/pci/hotplug/Kconfig"
@@ -709,6 +722,7 @@ config S390_GUEST
         def_bool y
         prompt "s390 support for virtio devices"
         depends on 64BIT
+        select TTY
         select VIRTUALIZATION
         select VIRTIO
         select VIRTIO_CONSOLE
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 3ad8f61c9985..866ecbe670e4 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -6,9 +6,9 @@
 
 BITS := $(if $(CONFIG_64BIT),64,31)
 
-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \
-           vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo misc.o piggy.o \
-           sizes.h head$(BITS).o
+targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
+targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
+targets += misc.o piggy.o sizes.h head$(BITS).o
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
@@ -48,6 +48,7 @@ vmlinux.bin.all-y := $(obj)/vmlinux.bin
 
 suffix-$(CONFIG_KERNEL_GZIP)  := gz
 suffix-$(CONFIG_KERNEL_BZIP2) := bz2
+suffix-$(CONFIG_KERNEL_LZ4)  := lz4
 suffix-$(CONFIG_KERNEL_LZMA)  := lzma
 suffix-$(CONFIG_KERNEL_LZO)  := lzo
 suffix-$(CONFIG_KERNEL_XZ)  := xz
@@ -56,6 +57,8 @@ $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
         $(call if_changed,gzip)
 $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y)
         $(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y)
+        $(call if_changed,lz4)
 $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
         $(call if_changed,lzma)
 $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index c4c6a1cf221b..57cbaff1f397 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -47,6 +47,10 @@ static unsigned long free_mem_end_ptr;
 #include "../../../../lib/decompress_bunzip2.c"
 #endif
 
+#ifdef CONFIG_KERNEL_LZ4
+#include "../../../../lib/decompress_unlz4.c"
+#endif
+
 #ifdef CONFIG_KERNEL_LZMA
 #include "../../../../lib/decompress_unlzma.c"
 #endif
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 4066cee0c2d2..4bbb5957ed1b 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -9,6 +9,8 @@
 #ifndef _ASM_S390_AIRQ_H
 #define _ASM_S390_AIRQ_H
 
+#include <linux/bit_spinlock.h>
+
 struct airq_struct {
         struct hlist_node list;         /* Handler queueing. */
         void (*handler)(struct airq_struct *);  /* Thin-interrupt handler */
@@ -23,4 +25,69 @@ struct airq_struct {
 int register_adapter_interrupt(struct airq_struct *airq);
 void unregister_adapter_interrupt(struct airq_struct *airq);
 
+/* Adapter interrupt bit vector */
+struct airq_iv {
+        unsigned long *vector;  /* Adapter interrupt bit vector */
+        unsigned long *avail;   /* Allocation bit mask for the bit vector */
+        unsigned long *bitlock; /* Lock bit mask for the bit vector */
+        unsigned long *ptr;     /* Pointer associated with each bit */
+        unsigned int *data;     /* 32 bit value associated with each bit */
+        unsigned long bits;     /* Number of bits in the vector */
+        unsigned long end;      /* Number of highest allocated bit + 1 */
+        spinlock_t lock;        /* Lock to protect alloc & free */
+};
+
+#define AIRQ_IV_ALLOC   1       /* Use an allocation bit mask */
+#define AIRQ_IV_BITLOCK 2       /* Allocate the lock bit mask */
+#define AIRQ_IV_PTR     4       /* Allocate the ptr array */
+#define AIRQ_IV_DATA    8       /* Allocate the data array */
+
+struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
+void airq_iv_release(struct airq_iv *iv);
+unsigned long airq_iv_alloc_bit(struct airq_iv *iv);
+void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit);
+unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
+                           unsigned long end);
+
+static inline unsigned long airq_iv_end(struct airq_iv *iv)
+{
+        return iv->end;
+}
+
+static inline void airq_iv_lock(struct airq_iv *iv, unsigned long bit)
+{
+        const unsigned long be_to_le = BITS_PER_LONG - 1;
+        bit_spin_lock(bit ^ be_to_le, iv->bitlock);
+}
+
+static inline void airq_iv_unlock(struct airq_iv *iv, unsigned long bit)
+{
+        const unsigned long be_to_le = BITS_PER_LONG - 1;
+        bit_spin_unlock(bit ^ be_to_le, iv->bitlock);
+}
+
+static inline void airq_iv_set_data(struct airq_iv *iv, unsigned long bit,
+                                    unsigned int data)
+{
+        iv->data[bit] = data;
+}
+
+static inline unsigned int airq_iv_get_data(struct airq_iv *iv,
+                                            unsigned long bit)
+{
+        return iv->data[bit];
+}
+
+static inline void airq_iv_set_ptr(struct airq_iv *iv, unsigned long bit,
+                                   unsigned long ptr)
+{
+        iv->ptr[bit] = ptr;
+}
+
+static inline unsigned long airq_iv_get_ptr(struct airq_iv *iv,
+                                            unsigned long bit)
+{
+        return iv->ptr[bit];
+}
+
 #endif /* _ASM_S390_AIRQ_H */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 4d8604e311f3..10135a38673c 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -216,7 +216,7 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr)
         addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         asm volatile(
                 "       oc      %O0(1,%R0),%1"
-                : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
+                : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc");
 }
 
 static inline void 
@@ -244,7 +244,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr)
         addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         asm volatile(
                 "       nc      %O0(1,%R0),%1"
-                : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" );
+                : "+Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc");
 }
 
 static inline void 
@@ -271,7 +271,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr)
         addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         asm volatile(
                 "       xc      %O0(1,%R0),%1"
-                : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
+                : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc");
 }
 
 static inline void 
@@ -301,7 +301,7 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr)
         ch = *(unsigned char *) addr;
         asm volatile(
                 "       oc      %O0(1,%R0),%1"
-                : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7])
+                : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7])
                 : "cc", "memory");
         return (ch >> (nr & 7)) & 1;
 }
@@ -320,7 +320,7 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr)
         ch = *(unsigned char *) addr;
         asm volatile(
                 "       nc      %O0(1,%R0),%1"
-                : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7])
+                : "+Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7])
                 : "cc", "memory");
         return (ch >> (nr & 7)) & 1;
 }
@@ -339,7 +339,7 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr)
         ch = *(unsigned char *) addr;
         asm volatile(
                 "       xc      %O0(1,%R0),%1"
-                : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7])
+                : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7])
                 : "cc", "memory");
         return (ch >> (nr & 7)) & 1;
 }
@@ -693,7 +693,7 @@ static inline int find_next_bit_left(const unsigned long *addr,
         size -= offset;
         p = addr + offset / BITS_PER_LONG;
         if (bit) {
-                set = __flo_word(0, *p & (~0UL << bit));
+                set = __flo_word(0, *p & (~0UL >> bit));
                 if (set >= size)
                         return size + offset;
                 if (set < BITS_PER_LONG)
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index ffb898961c8d..d42625053c37 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -296,6 +296,7 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1,
         return 0;
 }
 
+void channel_subsystem_reinit(void);
 extern void css_schedule_reprobe(void);
 
 extern void reipl_ccw_dev(struct ccw_dev_id *id);
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index 0c82ba86e997..a908d2941c5d 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -20,4 +20,9 @@
 
 #define HARDIRQ_BITS    8
 
+static inline void ack_bad_irq(unsigned int irq)
+{
+        printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index bd90359d6d22..11eae5f55b70 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -17,6 +17,9 @@
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
                      pte_t *ptep, pte_t pte);
+pte_t huge_ptep_get(pte_t *ptep);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+                              unsigned long addr, pte_t *ptep);
 
 /*
  * If the arch doesn't supply something else, assume that hugepage
@@ -38,147 +41,75 @@ static inline int prepare_hugepage_range(struct file *file,
 int arch_prepare_hugepage(struct page *page);
 void arch_release_hugepage(struct page *page);
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+                                  pte_t *ptep)
 {
-        pte_val(pte) |= _PAGE_RO;
-        return pte;
+        pte_val(*ptep) = _SEGMENT_ENTRY_EMPTY;
 }
 
-static inline int huge_pte_none(pte_t pte)
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+                                         unsigned long address, pte_t *ptep)
 {
-        return (pte_val(pte) & _SEGMENT_ENTRY_INV) &&
-                !(pte_val(pte) & _SEGMENT_ENTRY_RO);
+        huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+                                             unsigned long addr, pte_t *ptep,
+                                             pte_t pte, int dirty)
 {
-        pte_t pte = *ptep;
-        unsigned long mask;
-
-        if (!MACHINE_HAS_HPAGE) {
-                ptep = (pte_t *) (pte_val(pte) & _SEGMENT_ENTRY_ORIGIN);
-                if (ptep) {
-                        mask = pte_val(pte) &
-                                (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
-                        pte = pte_mkhuge(*ptep);
-                        pte_val(pte) |= mask;
-                }
+        int changed = !pte_same(huge_ptep_get(ptep), pte);
+        if (changed) {
+                huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+                set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
         }
-        return pte;
+        return changed;
 }
 
-static inline void __pmd_csp(pmd_t *pmdp)
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+                                           unsigned long addr, pte_t *ptep)
 {
-        register unsigned long reg2 asm("2") = pmd_val(*pmdp);
-        register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
-                                               _SEGMENT_ENTRY_INV;
-        register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
-
-        asm volatile(
-                "       csp %1,%3"
-                : "=m" (*pmdp)
-                : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+        pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+        set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
 
-static inline void huge_ptep_invalidate(struct mm_struct *mm,
-                                        unsigned long address, pte_t *ptep)
-{
-        pmd_t *pmdp = (pmd_t *) ptep;
-
-        if (MACHINE_HAS_IDTE)
-                __pmd_idte(address, pmdp);
-        else
-                __pmd_csp(pmdp);
-        pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY;
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-                                            unsigned long addr, pte_t *ptep)
-{
-        pte_t pte = huge_ptep_get(ptep);
-
-        huge_ptep_invalidate(mm, addr, ptep);
-        return pte;
-}
-
-#define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \
-({                                                                          \
-        int __changed = !pte_same(huge_ptep_get(__ptep), __entry);          \
-        if (__changed) {                                                    \
-                huge_ptep_invalidate((__vma)->vm_mm, __addr, __ptep);       \
-                set_huge_pte_at((__vma)->vm_mm, __addr, __ptep, __entry);   \
-        }                                                                   \
-        __changed;                                                          \
-})
-
-#define huge_ptep_set_wrprotect(__mm, __addr, __ptep)                   \
-({                                                                      \
-        pte_t __pte = huge_ptep_get(__ptep);                            \
-        if (huge_pte_write(__pte)) {                                    \
-                huge_ptep_invalidate(__mm, __addr, __ptep);             \
-                set_huge_pte_at(__mm, __addr, __ptep,                   \
-                                huge_pte_wrprotect(__pte));             \
-        }                                                               \
-})
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-                                         unsigned long address, pte_t *ptep)
+static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
 {
-        huge_ptep_invalidate(vma->vm_mm, address, ptep);
+        return mk_pte(page, pgprot);
 }
 
-static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
+static inline int huge_pte_none(pte_t pte)
 {
-        pte_t pte;
-        pmd_t pmd;
-
-        pmd = mk_pmd_phys(page_to_phys(page), pgprot);
-        pte_val(pte) = pmd_val(pmd);
-        return pte;
+        return pte_none(pte);
 }
 
 static inline int huge_pte_write(pte_t pte)
 {
-        pmd_t pmd;
-
-        pmd_val(pmd) = pte_val(pte);
-        return pmd_write(pmd);
+        return pte_write(pte);
 }
 
 static inline int huge_pte_dirty(pte_t pte)
 {
-        /* No dirty bit in the segment table entry. */
-        return 0;
+        return pte_dirty(pte);
 }
 
 static inline pte_t huge_pte_mkwrite(pte_t pte)
 {
-        pmd_t pmd;
-
-        pmd_val(pmd) = pte_val(pte);
-        pte_val(pte) = pmd_val(pmd_mkwrite(pmd));
-        return pte;
+        return pte_mkwrite(pte);
 }
 
 static inline pte_t huge_pte_mkdirty(pte_t pte)
 {
-        /* No dirty bit in the segment table entry. */
-        return pte;
+        return pte_mkdirty(pte);
 }
 
-static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
+static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
-        pmd_t pmd;
-
-        pmd_val(pmd) = pte_val(pte);
-        pte_val(pte) = pmd_val(pmd_modify(pmd, newprot));
-        return pte;
+        return pte_wrprotect(pte);
 }
 
-static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
-                                  pte_t *ptep)
+static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 {
-        pmd_clear((pmd_t *) ptep);
+        return pte_modify(pte, newprot);
 }
 
 #endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/s390/include/asm/hw_irq.h b/arch/s390/include/asm/hw_irq.h
index 7e3d2586c1ff..ee96a8b697f9 100644
--- a/arch/s390/include/asm/hw_irq.h
+++ b/arch/s390/include/asm/hw_irq.h
@@ -4,19 +4,8 @@
 #include <linux/msi.h>
 #include <linux/pci.h>
 
-static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
-{
-        return __irq_get_msi_desc(irq);
-}
-
-/* Must be called with msi map lock held */
-static inline int irq_set_msi_desc(unsigned int irq, struct msi_desc *msi)
-{
-        if (!msi)
-                return -EINVAL;
-
-        msi->irq = irq;
-        return 0;
-}
+void __init init_airq_interrupts(void);
+void __init init_cio_interrupts(void);
+void __init init_ext_interrupts(void);
 
 #endif
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 87c17bfb2968..1eaa3625803c 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -1,17 +1,28 @@
 #ifndef _ASM_IRQ_H
 #define _ASM_IRQ_H
 
+#define EXT_INTERRUPT   1
+#define IO_INTERRUPT    2
+#define THIN_INTERRUPT  3
+
+#define NR_IRQS_BASE    4
+
+#ifdef CONFIG_PCI_NR_MSI
+# define NR_IRQS        (NR_IRQS_BASE + CONFIG_PCI_NR_MSI)
+#else
+# define NR_IRQS        NR_IRQS_BASE
+#endif
+
+/* This number is used when no interrupt has been assigned */
+#define NO_IRQ          0
+
+#ifndef __ASSEMBLY__
+
 #include <linux/hardirq.h>
 #include <linux/percpu.h>
 #include <linux/cache.h>
 #include <linux/types.h>
 
-enum interruption_main_class {
-        EXTERNAL_INTERRUPT,
-        IO_INTERRUPT,
-        NR_IRQS
-};
-
 enum interruption_class {
         IRQEXT_CLK,
         IRQEXT_EXC,
@@ -72,14 +83,8 @@ void service_subclass_irq_unregister(void);
 void measurement_alert_subclass_register(void);
 void measurement_alert_subclass_unregister(void);
 
-#ifdef CONFIG_LOCKDEP
-#  define disable_irq_nosync_lockdep(irq)       disable_irq_nosync(irq)
-#  define disable_irq_nosync_lockdep_irqsave(irq, flags) \
-                                                disable_irq_nosync(irq)
-#  define disable_irq_lockdep(irq)              disable_irq(irq)
-#  define enable_irq_lockdep(irq)               enable_irq(irq)
-#  define enable_irq_lockdep_irqrestore(irq, flags) \
-                                                enable_irq(irq)
-#endif
+#define irq_canonicalize(irq)  (irq)
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_IRQ_H */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 084e7755ed9b..7b7fce4e8469 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -77,8 +77,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
         WARN_ON(atomic_read(&prev->context.attach_count) < 0);
         atomic_inc(&next->context.attach_count);
         /* Check for TLBs not flushed yet */
-        if (next->context.flush_mm)
-                __tlb_flush_mm(next);
+        __tlb_flush_mm_lazy(next);
 }
 
 #define enter_lazy_tlb(mm,tsk)  do { } while (0)
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 5d64fb7619cc..1e51f2915b2e 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -32,16 +32,6 @@
 
 void storage_key_init_range(unsigned long start, unsigned long end);
 
-static inline unsigned long pfmf(unsigned long function, unsigned long address)
-{
-        asm volatile(
-                "       .insn   rre,0xb9af0000,%[function],%[address]"
-                : [address] "+a" (address)
-                : [function] "d" (function)
-                : "memory");
-        return address;
-}
-
 static inline void clear_page(void *page)
 {
         register unsigned long reg1 asm ("1") = 0;
@@ -150,15 +140,6 @@ static inline int page_reset_referenced(unsigned long addr)
 #define _PAGE_FP_BIT            0x08    /* HW fetch protection bit      */
 #define _PAGE_ACC_BITS          0xf0    /* HW access control bits       */
 
-/*
- * Test and clear referenced bit in storage key.
- */
-#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
-static inline int page_test_and_clear_young(unsigned long pfn)
-{
-        return page_reset_referenced(pfn << PAGE_SHIFT);
-}
-
 struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 6e577ba0e5da..c290f13d1c47 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -6,6 +6,7 @@
 /* must be set before including pci_clp.h */
 #define PCI_BAR_COUNT   6
 
+#include <linux/pci.h>
 #include <asm-generic/pci.h>
 #include <asm-generic/pci-dma-compat.h>
 #include <asm/pci_clp.h>
@@ -53,14 +54,9 @@ struct zpci_fmb {
         atomic64_t unmapped_pages;
 } __packed __aligned(16);
 
-struct msi_map {
-        unsigned long irq;
-        struct msi_desc *msi;
-        struct hlist_node msi_chain;
-};
-
-#define ZPCI_NR_MSI_VECS        64
-#define ZPCI_MSI_MASK           (ZPCI_NR_MSI_VECS - 1)
+#define ZPCI_MSI_VEC_BITS       11
+#define ZPCI_MSI_VEC_MAX        (1 << ZPCI_MSI_VEC_BITS)
+#define ZPCI_MSI_VEC_MASK       (ZPCI_MSI_VEC_MAX - 1)
 
 enum zpci_state {
         ZPCI_FN_STATE_RESERVED,
@@ -91,8 +87,7 @@ struct zpci_dev {
 
         /* IRQ stuff */
         u64             msi_addr;       /* MSI address */
-        struct zdev_irq_map *irq_map;
-        struct msi_map *msi_map[ZPCI_NR_MSI_VECS];
+        struct airq_iv *aibv;           /* adapter interrupt bit vector */
         unsigned int    aisb;           /* number of the summary bit */
 
         /* DMA stuff */
@@ -122,11 +117,6 @@ struct zpci_dev {
         struct dentry   *debugfs_perf;
 };
 
-struct pci_hp_callback_ops {
-        int (*create_slot)      (struct zpci_dev *zdev);
-        void (*remove_slot)     (struct zpci_dev *zdev);
-};
-
 static inline bool zdev_enabled(struct zpci_dev *zdev)
 {
         return (zdev->fh & (1UL << 31)) ? true : false;
@@ -146,32 +136,38 @@ int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
 int zpci_unregister_ioat(struct zpci_dev *, u8);
 
 /* CLP */
-int clp_find_pci_devices(void);
+int clp_scan_pci_devices(void);
+int clp_rescan_pci_devices(void);
+int clp_rescan_pci_devices_simple(void);
 int clp_add_pci_device(u32, u32, int);
 int clp_enable_fh(struct zpci_dev *, u8);
 int clp_disable_fh(struct zpci_dev *);
 
-/* MSI */
-struct msi_desc *__irq_get_msi_desc(unsigned int);
-int zpci_msi_set_mask_bits(struct msi_desc *, u32, u32);
-int zpci_setup_msi_irq(struct zpci_dev *, struct msi_desc *, unsigned int, int);
-void zpci_teardown_msi_irq(struct zpci_dev *, struct msi_desc *);
-int zpci_msihash_init(void);
-void zpci_msihash_exit(void);
-
 #ifdef CONFIG_PCI
 /* Error handling and recovery */
 void zpci_event_error(void *);
 void zpci_event_availability(void *);
+void zpci_rescan(void);
 #else /* CONFIG_PCI */
 static inline void zpci_event_error(void *e) {}
 static inline void zpci_event_availability(void *e) {}
+static inline void zpci_rescan(void) {}
 #endif /* CONFIG_PCI */
 
+#ifdef CONFIG_HOTPLUG_PCI_S390
+int zpci_init_slot(struct zpci_dev *);
+void zpci_exit_slot(struct zpci_dev *);
+#else /* CONFIG_HOTPLUG_PCI_S390 */
+static inline int zpci_init_slot(struct zpci_dev *zdev)
+{
+        return 0;
+}
+static inline void zpci_exit_slot(struct zpci_dev *zdev) {}
+#endif /* CONFIG_HOTPLUG_PCI_S390 */
+
 /* Helpers */
 struct zpci_dev *get_zdev(struct pci_dev *);
 struct zpci_dev *get_zdev_by_fid(u32);
-bool zpci_fid_present(u32);
 
 /* sysfs */
 int zpci_sysfs_add_device(struct device *);
@@ -181,14 +177,6 @@ void zpci_sysfs_remove_device(struct device *);
 int zpci_dma_init(void);
 void zpci_dma_exit(void);
 
-/* Hotplug */
-extern struct mutex zpci_list_lock;
-extern struct list_head zpci_list;
-extern unsigned int s390_pci_probe;
-
-void zpci_register_hp_ops(struct pci_hp_callback_ops *);
-void zpci_deregister_hp_ops(void);
-
 /* FMB */
 int zpci_fmb_enable_device(struct zpci_dev *);
 int zpci_fmb_disable_device(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index e6a2bdd4d705..df6eac9f0cb4 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -79,11 +79,11 @@ struct zpci_fib {
 } __packed;
 
 
-int s390pci_mod_fc(u64 req, struct zpci_fib *fib);
-int s390pci_refresh_trans(u64 fn, u64 addr, u64 range);
-int s390pci_load(u64 *data, u64 req, u64 offset);
-int s390pci_store(u64 data, u64 req, u64 offset);
-int s390pci_store_block(const u64 *data, u64 req, u64 offset);
-void set_irq_ctrl(u16 ctl, char *unused, u8 isc);
+int zpci_mod_fc(u64 req, struct zpci_fib *fib);
+int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
+int zpci_load(u64 *data, u64 req, u64 offset);
+int zpci_store(u64 data, u64 req, u64 offset);
+int zpci_store_block(const u64 *data, u64 req, u64 offset);
+void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
 
 #endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index 83a9caa6ae53..d194d544d694 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
         u64 data;                                                               \
         int rc;                                                                 \
                                                                                 \
-        rc = s390pci_load(&data, req, ZPCI_OFFSET(addr));                       \
+        rc = zpci_load(&data, req, ZPCI_OFFSET(addr));                          \
         if (rc)                                                                 \
                 data = -1ULL;                                                   \
         return (RETTYPE) data;                                                  \
@@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val,				\
         u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);               \
         u64 data = (VALTYPE) val;                                               \
                                                                                 \
-        s390pci_store(data, req, ZPCI_OFFSET(addr));                            \
+        zpci_store(data, req, ZPCI_OFFSET(addr));                               \
 }
 
 zpci_read(8, u64)
@@ -83,7 +83,7 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len
                 val = 0;                /* let FW report error */
                 break;
         }
-        return s390pci_store(val, req, offset);
+        return zpci_store(val, req, offset);
 }
 
 static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
@@ -91,7 +91,7 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
         u64 data;
         int cc;
 
-        cc = s390pci_load(&data, req, offset);
+        cc = zpci_load(&data, req, offset);
         if (cc)
                 goto out;
 
@@ -115,7 +115,7 @@ out:
 
 static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
 {
-        return s390pci_store_block(data, req, offset);
+        return zpci_store_block(data, req, offset);
 }
 
 static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 75fb726de91f..9f215b40109e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -217,63 +217,57 @@ extern unsigned long MODULES_END;
 
 /* Hardware bits in the page table entry */
 #define _PAGE_CO        0x100           /* HW Change-bit override */
-#define _PAGE_RO        0x200           /* HW read-only bit  */
+#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 */
 
 /* Software bits in the page table entry */
-#define _PAGE_SWT       0x001           /* SW pte type bit t */
-#define _PAGE_SWX       0x002           /* SW pte type bit x */
-#define _PAGE_SWC       0x004           /* SW pte changed bit */
-#define _PAGE_SWR       0x008           /* SW pte referenced bit */
-#define _PAGE_SWW       0x010           /* SW pte write bit */
-#define _PAGE_SPECIAL   0x020           /* SW associated with special page */
+#define _PAGE_PRESENT   0x001           /* SW pte present bit */
+#define _PAGE_TYPE      0x002           /* SW pte type bit */
+#define _PAGE_YOUNG     0x004           /* SW pte young bit */
+#define _PAGE_DIRTY     0x008           /* SW pte dirty bit */
+#define _PAGE_READ      0x010           /* SW pte read bit */
+#define _PAGE_WRITE     0x020           /* SW pte write bit */
+#define _PAGE_SPECIAL   0x040           /* SW associated with special page */
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK          (PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \
-                                 _PAGE_SWC | _PAGE_SWR)
-
-/* Six different types of pages. */
-#define _PAGE_TYPE_EMPTY        0x400
-#define _PAGE_TYPE_NONE         0x401
-#define _PAGE_TYPE_SWAP         0x403
-#define _PAGE_TYPE_FILE         0x601   /* bit 0x002 is used for offset !! */
-#define _PAGE_TYPE_RO           0x200
-#define _PAGE_TYPE_RW           0x000
+                                 _PAGE_DIRTY | _PAGE_YOUNG)
 
 /*
- * Only four types for huge pages, using the invalid bit and protection bit
- * of a segment table entry.
- */
-#define _HPAGE_TYPE_EMPTY       0x020   /* _SEGMENT_ENTRY_INV */
-#define _HPAGE_TYPE_NONE        0x220
-#define _HPAGE_TYPE_RO          0x200   /* _SEGMENT_ENTRY_RO  */
-#define _HPAGE_TYPE_RW          0x000
-
-/*
- * PTE type bits are rather complicated. handle_pte_fault uses pte_present,
- * pte_none and pte_file to find out the pte type WITHOUT holding the page
- * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to
- * invalidate a given pte. ipte sets the hw invalid bit and clears all tlbs
- * for the page. The page table entry is set to _PAGE_TYPE_EMPTY afterwards.
- * This change is done while holding the lock, but the intermediate step
- * of a previously valid pte with the hw invalid bit set can be observed by
- * handle_pte_fault. That makes it necessary that all valid pte types with
- * the hw invalid bit set must be distinguishable from the four pte types
- * empty, none, swap and file.
+ * handle_pte_fault uses pte_present, pte_none and pte_file to find out the
+ * pte type WITHOUT holding the page table lock. The _PAGE_PRESENT bit
+ * is used to distinguish present from not-present ptes. It is changed only
+ * with the page table lock held.
+ *
+ * The following table gives the different possible bit combinations for
+ * the pte hardware and software bits in the last 12 bits of a pte:
  *
- *                      irxt  ipte  irxt
- * _PAGE_TYPE_EMPTY     1000   ->   1000
- * _PAGE_TYPE_NONE      1001   ->   1001
- * _PAGE_TYPE_SWAP      1011   ->   1011
- * _PAGE_TYPE_FILE      11?1   ->   11?1
- * _PAGE_TYPE_RO        0100   ->   1100
- * _PAGE_TYPE_RW        0000   ->   1000
+ *                              842100000000
+ *                              000084210000
+ *                              000000008421
+ *                              .IR...wrdytp
+ * empty                        .10...000000
+ * swap                         .10...xxxx10
+ * file                         .11...xxxxx0
+ * prot-none, clean, old        .11...000001
+ * prot-none, clean, young      .11...000101
+ * prot-none, dirty, old        .10...001001
+ * prot-none, dirty, young      .10...001101
+ * read-only, clean, old        .11...010001
+ * read-only, clean, young      .01...010101
+ * read-only, dirty, old        .11...011001
+ * read-only, dirty, young      .01...011101
+ * read-write, clean, old       .11...110001
+ * read-write, clean, young     .01...110101
+ * read-write, dirty, old       .10...111001
+ * read-write, dirty, young     .00...111101
  *
- * pte_none is true for bits combinations 1000, 1010, 1100, 1110
- * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001
- * pte_file is true for bits combinations 1101, 1111
- * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid.
+ * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001
+ * pte_none    is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400
+ * pte_file    is true for the bit pattern .11...xxxxx0, (pte & 0x601) == 0x600
+ * pte_swap    is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402
  */
 
 #ifndef CONFIG_64BIT
@@ -286,14 +280,25 @@ extern unsigned long MODULES_END;
 #define _ASCE_TABLE_LENGTH      0x7f    /* 128 x 64 entries = 8k            */
 
 /* Bits in the segment table entry */
+#define _SEGMENT_ENTRY_BITS     0x7fffffffUL    /* Valid segment table bits */
 #define _SEGMENT_ENTRY_ORIGIN   0x7fffffc0UL    /* page table origin        */
-#define _SEGMENT_ENTRY_RO       0x200   /* page protection bit              */
-#define _SEGMENT_ENTRY_INV      0x20    /* invalid segment table entry      */
+#define _SEGMENT_ENTRY_PROTECT  0x200   /* page protection bit              */
+#define _SEGMENT_ENTRY_INVALID  0x20    /* invalid segment table entry      */
 #define _SEGMENT_ENTRY_COMMON   0x10    /* common segment bit               */
 #define _SEGMENT_ENTRY_PTL      0x0f    /* page table length                */
+#define _SEGMENT_ENTRY_NONE     _SEGMENT_ENTRY_PROTECT
 
 #define _SEGMENT_ENTRY          (_SEGMENT_ENTRY_PTL)
-#define _SEGMENT_ENTRY_EMPTY    (_SEGMENT_ENTRY_INV)
+#define _SEGMENT_ENTRY_EMPTY    (_SEGMENT_ENTRY_INVALID)
+
+/*
+ * Segment table entry encoding (I = invalid, R = read-only bit):
+ *              ..R...I.....
+ * prot-none    ..1...1.....
+ * read-only    ..1...0.....
+ * read-write   ..0...0.....
+ * empty        ..0...1.....
+ */
 
 /* Page status table bits for virtualization */
 #define PGSTE_ACC_BITS  0xf0000000UL
@@ -303,9 +308,7 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT    0x00200000UL
 #define PGSTE_GR_BIT    0x00040000UL
 #define PGSTE_GC_BIT    0x00020000UL
-#define PGSTE_UR_BIT    0x00008000UL
-#define PGSTE_UC_BIT    0x00004000UL    /* user dirty (migration) */
-#define PGSTE_IN_BIT    0x00002000UL    /* IPTE notify bit */
+#define PGSTE_IN_BIT    0x00008000UL    /* IPTE notify bit */
 
 #else /* CONFIG_64BIT */
 
@@ -324,8 +327,8 @@ extern unsigned long MODULES_END;
 
 /* Bits in the region table entry */
 #define _REGION_ENTRY_ORIGIN    ~0xfffUL/* region/segment table origin      */
-#define _REGION_ENTRY_RO        0x200   /* region protection bit            */
-#define _REGION_ENTRY_INV       0x20    /* invalid region table entry       */
+#define _REGION_ENTRY_PROTECT   0x200   /* region protection bit            */
+#define _REGION_ENTRY_INVALID   0x20    /* invalid region table entry       */
 #define _REGION_ENTRY_TYPE_MASK 0x0c    /* region/segment table type mask   */
 #define _REGION_ENTRY_TYPE_R1   0x0c    /* region first table type          */
 #define _REGION_ENTRY_TYPE_R2   0x08    /* region second table type         */
@@ -333,29 +336,47 @@ extern unsigned long MODULES_END;
 #define _REGION_ENTRY_LENGTH    0x03    /* region third length              */
 
 #define _REGION1_ENTRY          (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_LENGTH)
-#define _REGION1_ENTRY_EMPTY    (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INV)
+#define _REGION1_ENTRY_EMPTY    (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID)
 #define _REGION2_ENTRY          (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_LENGTH)
-#define _REGION2_ENTRY_EMPTY    (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INV)
+#define _REGION2_ENTRY_EMPTY    (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID)
 #define _REGION3_ENTRY          (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
-#define _REGION3_ENTRY_EMPTY    (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV)
+#define _REGION3_ENTRY_EMPTY    (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
 
 #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
+#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff1ff33UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address        */
 #define _SEGMENT_ENTRY_ORIGIN   ~0x7ffUL/* segment table origin             */
-#define _SEGMENT_ENTRY_RO       0x200   /* page protection bit              */
-#define _SEGMENT_ENTRY_INV      0x20    /* invalid segment table entry      */
+#define _SEGMENT_ENTRY_PROTECT  0x200   /* page protection bit              */
+#define _SEGMENT_ENTRY_INVALID  0x20    /* invalid segment table entry      */
 
 #define _SEGMENT_ENTRY          (0)
-#define _SEGMENT_ENTRY_EMPTY    (_SEGMENT_ENTRY_INV)
+#define _SEGMENT_ENTRY_EMPTY    (_SEGMENT_ENTRY_INVALID)
 
 #define _SEGMENT_ENTRY_LARGE    0x400   /* STE-format control, large page   */
 #define _SEGMENT_ENTRY_CO       0x100   /* change-recording override   */
+#define _SEGMENT_ENTRY_SPLIT    0x001   /* THP splitting bit */
+#define _SEGMENT_ENTRY_YOUNG    0x002   /* SW segment young bit */
+#define _SEGMENT_ENTRY_NONE     _SEGMENT_ENTRY_YOUNG
+
+/*
+ * Segment table entry encoding (R = read-only, I = invalid, y = young bit):
+ *                      ..R...I...y.
+ * prot-none, old       ..0...1...1.
+ * prot-none, young     ..1...1...1.
+ * read-only, old       ..1...1...0.
+ * read-only, young     ..1...0...1.
+ * read-write, old      ..0...1...0.
+ * read-write, young    ..0...0...1.
+ * The segment table origin is used to distinguish empty (origin==0) from
+ * read-write, old segment table entries (origin!=0)
+ */
+
 #define _SEGMENT_ENTRY_SPLIT_BIT 0      /* THP splitting bit number */
-#define _SEGMENT_ENTRY_SPLIT    (1UL << _SEGMENT_ENTRY_SPLIT_BIT)
 
 /* Set of bits not changed in pmd_modify */
 #define _SEGMENT_CHG_MASK       (_SEGMENT_ENTRY_ORIGIN | _SEGMENT_ENTRY_LARGE \
@@ -369,9 +390,7 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT    0x0020000000000000UL
 #define PGSTE_GR_BIT    0x0004000000000000UL
 #define PGSTE_GC_BIT    0x0002000000000000UL
-#define PGSTE_UR_BIT    0x0000800000000000UL
-#define PGSTE_UC_BIT    0x0000400000000000UL    /* user dirty (migration) */
-#define PGSTE_IN_BIT    0x0000200000000000UL    /* IPTE notify bit */
+#define PGSTE_IN_BIT    0x0000800000000000UL    /* IPTE notify bit */
 
 #endif /* CONFIG_64BIT */
 
@@ -386,14 +405,18 @@ extern unsigned long MODULES_END;
 /*
  * Page protection definitions.
  */
-#define PAGE_NONE       __pgprot(_PAGE_TYPE_NONE)
-#define PAGE_RO         __pgprot(_PAGE_TYPE_RO)
-#define PAGE_RW         __pgprot(_PAGE_TYPE_RO | _PAGE_SWW)
-#define PAGE_RWC        __pgprot(_PAGE_TYPE_RW | _PAGE_SWW | _PAGE_SWC)
-
-#define PAGE_KERNEL     PAGE_RWC
-#define PAGE_SHARED     PAGE_KERNEL
-#define PAGE_COPY       PAGE_RO
+#define PAGE_NONE       __pgprot(_PAGE_PRESENT | _PAGE_INVALID)
+#define PAGE_READ       __pgprot(_PAGE_PRESENT | _PAGE_READ | \
+                                 _PAGE_INVALID | _PAGE_PROTECT)
+#define PAGE_WRITE      __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+                                 _PAGE_INVALID | _PAGE_PROTECT)
+
+#define PAGE_SHARED     __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+                                 _PAGE_YOUNG | _PAGE_DIRTY)
+#define PAGE_KERNEL     __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+                                 _PAGE_YOUNG | _PAGE_DIRTY)
+#define PAGE_KERNEL_RO  __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \
+                                 _PAGE_PROTECT)
 
 /*
  * On s390 the page table entry has an invalid bit and a read-only bit.
@@ -402,35 +425,31 @@ extern unsigned long MODULES_END;
  */
          /*xwr*/
 #define __P000  PAGE_NONE
-#define __P001  PAGE_RO
-#define __P010  PAGE_RO
-#define __P011  PAGE_RO
-#define __P100  PAGE_RO
-#define __P101  PAGE_RO
-#define __P110  PAGE_RO
-#define __P111  PAGE_RO
+#define __P001  PAGE_READ
+#define __P010  PAGE_READ
+#define __P011  PAGE_READ
+#define __P100  PAGE_READ
+#define __P101  PAGE_READ
+#define __P110  PAGE_READ
+#define __P111  PAGE_READ
 
 #define __S000  PAGE_NONE
-#define __S001  PAGE_RO
-#define __S010  PAGE_RW
-#define __S011  PAGE_RW
-#define __S100  PAGE_RO
-#define __S101  PAGE_RO
-#define __S110  PAGE_RW
-#define __S111  PAGE_RW
+#define __S001  PAGE_READ
+#define __S010  PAGE_WRITE
+#define __S011  PAGE_WRITE
+#define __S100  PAGE_READ
+#define __S101  PAGE_READ
+#define __S110  PAGE_WRITE
+#define __S111  PAGE_WRITE
 
 /*
  * Segment entry (large page) protection definitions.
  */
-#define SEGMENT_NONE    __pgprot(_HPAGE_TYPE_NONE)
-#define SEGMENT_RO      __pgprot(_HPAGE_TYPE_RO)
-#define SEGMENT_RW      __pgprot(_HPAGE_TYPE_RW)
-
-static inline int mm_exclusive(struct mm_struct *mm)
-{
-        return likely(mm == current->active_mm &&
-                      atomic_read(&mm->context.attach_count) <= 1);
-}
+#define SEGMENT_NONE    __pgprot(_SEGMENT_ENTRY_INVALID | \
+                                 _SEGMENT_ENTRY_NONE)
+#define SEGMENT_READ    __pgprot(_SEGMENT_ENTRY_INVALID | \
+                                 _SEGMENT_ENTRY_PROTECT)
+#define SEGMENT_WRITE   __pgprot(_SEGMENT_ENTRY_INVALID)
 
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
@@ -467,7 +486,7 @@ static inline int pgd_none(pgd_t pgd)
 {
         if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
                 return 0;
-        return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL;
+        return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL;
 }
 
 static inline int pgd_bad(pgd_t pgd)
@@ -478,7 +497,7 @@ static inline int pgd_bad(pgd_t pgd)
          * invalid for either table entry.
          */
         unsigned long mask =
-                ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
+                ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
                 ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
         return (pgd_val(pgd) & mask) != 0;
 }
@@ -494,7 +513,7 @@ static inline int pud_none(pud_t pud)
 {
         if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
                 return 0;
-        return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL;
+        return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL;
 }
 
 static inline int pud_large(pud_t pud)
@@ -512,7 +531,7 @@ static inline int pud_bad(pud_t pud)
          * invalid for either table entry.
          */
         unsigned long mask =
-                ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
+                ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
                 ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
         return (pud_val(pud) & mask) != 0;
 }
@@ -521,30 +540,36 @@ static inline int pud_bad(pud_t pud)
 
 static inline int pmd_present(pmd_t pmd)
 {
-        unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO;
-        return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE ||
-               !(pmd_val(pmd) & _SEGMENT_ENTRY_INV);
+        return pmd_val(pmd) != _SEGMENT_ENTRY_INVALID;
 }
 
 static inline int pmd_none(pmd_t pmd)
 {
-        return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) &&
-               !(pmd_val(pmd) & _SEGMENT_ENTRY_RO);
+        return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID;
 }
 
 static inline int pmd_large(pmd_t pmd)
 {
 #ifdef CONFIG_64BIT
-        return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE);
+        return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
 #else
         return 0;
 #endif
 }
 
+static inline int pmd_prot_none(pmd_t pmd)
+{
+        return (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) &&
+                (pmd_val(pmd) & _SEGMENT_ENTRY_NONE);
+}
+
 static inline int pmd_bad(pmd_t pmd)
 {
-        unsigned long mask = ~_SEGMENT_ENTRY_ORIGIN & ~_SEGMENT_ENTRY_INV;
-        return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY;
+#ifdef CONFIG_64BIT
+        if (pmd_large(pmd))
+                return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
+#endif
+        return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
 #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
@@ -563,31 +588,40 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #define __HAVE_ARCH_PMD_WRITE
 static inline int pmd_write(pmd_t pmd)
 {
-        return (pmd_val(pmd) & _SEGMENT_ENTRY_RO) == 0;
+        if (pmd_prot_none(pmd))
+                return 0;
+        return (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) == 0;
 }
 
 static inline int pmd_young(pmd_t pmd)
 {
-        return 0;
+        int young = 0;
+#ifdef CONFIG_64BIT
+        if (pmd_prot_none(pmd))
+                young = (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) != 0;
+        else
+                young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
+#endif
+        return young;
 }
 
-static inline int pte_none(pte_t pte)
+static inline int pte_present(pte_t pte)
 {
-        return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT);
+        /* Bit pattern: (pte & 0x001) == 0x001 */
+        return (pte_val(pte) & _PAGE_PRESENT) != 0;
 }
 
-static inline int pte_present(pte_t pte)
+static inline int pte_none(pte_t pte)
 {
-        unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT | _PAGE_SWX;
-        return (pte_val(pte) & mask) == _PAGE_TYPE_NONE ||
-                (!(pte_val(pte) & _PAGE_INVALID) &&
-                 !(pte_val(pte) & _PAGE_SWT));
+        /* Bit pattern: pte == 0x400 */
+        return pte_val(pte) == _PAGE_INVALID;
 }
 
 static inline int pte_file(pte_t pte)
 {
-        unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT;
-        return (pte_val(pte) & mask) == _PAGE_TYPE_FILE;
+        /* Bit pattern: (pte & 0x601) == 0x600 */
+        return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | _PAGE_PRESENT))
+                == (_PAGE_INVALID | _PAGE_PROTECT);
 }
 
 static inline int pte_special(pte_t pte)
@@ -634,6 +668,15 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 #endif
 }
 
+static inline pgste_t pgste_get(pte_t *ptep)
+{
+        unsigned long pgste = 0;
+#ifdef CONFIG_PGSTE
+        pgste = *(unsigned long *)(ptep + PTRS_PER_PTE);
+#endif
+        return __pgste(pgste);
+}
+
 static inline void pgste_set(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
@@ -644,33 +687,28 @@ static inline void pgste_set(pte_t *ptep, pgste_t pgste)
 static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-        unsigned long address, bits;
-        unsigned char skey;
+        unsigned long address, bits, skey;
 
         if (pte_val(*ptep) & _PAGE_INVALID)
                 return pgste;
         address = pte_val(*ptep) & PAGE_MASK;
-        skey = page_get_storage_key(address);
+        skey = (unsigned long) page_get_storage_key(address);
         bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
-        /* Clear page changed & referenced bit in the storage key */
-        if (bits & _PAGE_CHANGED)
+        if (!(pgste_val(pgste) & PGSTE_HC_BIT) && (bits & _PAGE_CHANGED)) {
+                /* Transfer dirty + referenced bit to host bits in pgste */
+                pgste_val(pgste) |= bits << 52;
                 page_set_storage_key(address, skey ^ bits, 0);
-        else if (bits)
+        } else if (!(pgste_val(pgste) & PGSTE_HR_BIT) &&
+                   (bits & _PAGE_REFERENCED)) {
+                /* Transfer referenced bit to host bit in pgste */
+                pgste_val(pgste) |= PGSTE_HR_BIT;
                 page_reset_referenced(address);
+        }
         /* Transfer page changed & referenced bit to guest bits in pgste */
         pgste_val(pgste) |= bits << 48;         /* GR bit & GC bit */
-        /* Get host changed & referenced bits from pgste */
-        bits |= (pgste_val(pgste) & (PGSTE_HR_BIT | PGSTE_HC_BIT)) >> 52;
-        /* Transfer page changed & referenced bit to kvm user bits */
-        pgste_val(pgste) |= bits << 45;         /* PGSTE_UR_BIT & PGSTE_UC_BIT */
-        /* Clear relevant host bits in pgste. */
-        pgste_val(pgste) &= ~(PGSTE_HR_BIT | PGSTE_HC_BIT);
-        pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
         /* Copy page access key and fetch protection bit to pgste */
-        pgste_val(pgste) |=
-                (unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
-        /* Transfer referenced bit to pte */
-        pte_val(*ptep) |= (bits & _PAGE_REFERENCED) << 1;
+        pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
+        pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 #endif
         return pgste;
 
@@ -679,24 +717,11 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-        int young;
-
         if (pte_val(*ptep) & _PAGE_INVALID)
                 return pgste;
         /* Get referenced bit from storage key */
-        young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
-        if (young)
-                pgste_val(pgste) |= PGSTE_GR_BIT;
-        /* Get host referenced bit from pgste */
-        if (pgste_val(pgste) & PGSTE_HR_BIT) {
-                pgste_val(pgste) &= ~PGSTE_HR_BIT;
-                young = 1;
-        }
-        /* Transfer referenced bit to kvm user bits and pte */
-        if (young) {
-                pgste_val(pgste) |= PGSTE_UR_BIT;
-                pte_val(*ptep) |= _PAGE_SWR;
-        }
+        if (page_reset_referenced(pte_val(*ptep) & PAGE_MASK))
+                pgste_val(pgste) |= PGSTE_HR_BIT | PGSTE_GR_BIT;
 #endif
         return pgste;
 }
@@ -723,13 +748,13 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
 
 static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
 {
-        if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_SWW)) {
+        if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_WRITE)) {
                 /*
                  * Without enhanced suppression-on-protection force
                  * the dirty bit on for all writable ptes.
                  */
-                pte_val(entry) |= _PAGE_SWC;
-                pte_val(entry) &= ~_PAGE_RO;
+                pte_val(entry) |= _PAGE_DIRTY;
+                pte_val(entry) &= ~_PAGE_PROTECT;
         }
         *ptep = entry;
 }
@@ -841,21 +866,17 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
  */
 static inline int pte_write(pte_t pte)
 {
-        return (pte_val(pte) & _PAGE_SWW) != 0;
+        return (pte_val(pte) & _PAGE_WRITE) != 0;
 }
 
 static inline int pte_dirty(pte_t pte)
 {
-        return (pte_val(pte) & _PAGE_SWC) != 0;
+        return (pte_val(pte) & _PAGE_DIRTY) != 0;
 }
 
 static inline int pte_young(pte_t pte)
 {
-#ifdef CONFIG_PGSTE
-        if (pte_val(pte) & _PAGE_SWR)
-                return 1;
-#endif
-        return 0;
+        return (pte_val(pte) & _PAGE_YOUNG) != 0;
 }
 
 /*
@@ -880,12 +901,12 @@ static inline void pud_clear(pud_t *pud)
 
 static inline void pmd_clear(pmd_t *pmdp)
 {
-        pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+        pmd_val(*pmdp) = _SEGMENT_ENTRY_INVALID;
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-        pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+        pte_val(*ptep) = _PAGE_INVALID;
 }
 
 /*
@@ -896,55 +917,63 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
         pte_val(pte) &= _PAGE_CHG_MASK;
         pte_val(pte) |= pgprot_val(newprot);
-        if ((pte_val(pte) & _PAGE_SWC) && (pte_val(pte) & _PAGE_SWW))
-                pte_val(pte) &= ~_PAGE_RO;
+        /*
+         * newprot for PAGE_NONE, PAGE_READ and PAGE_WRITE has the
+         * invalid bit set, clear it again for readable, young pages
+         */
+        if ((pte_val(pte) & _PAGE_YOUNG) && (pte_val(pte) & _PAGE_READ))
+                pte_val(pte) &= ~_PAGE_INVALID;
+        /*
+         * newprot for PAGE_READ and PAGE_WRITE has the page protection
+         * bit set, clear it again for writable, dirty pages
+         */
+        if ((pte_val(pte) & _PAGE_DIRTY) && (pte_val(pte) & _PAGE_WRITE))
+                pte_val(pte) &= ~_PAGE_PROTECT;
         return pte;
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-        pte_val(pte) &= ~_PAGE_SWW;
-        /* Do not clobber _PAGE_TYPE_NONE pages!  */
-        if (!(pte_val(pte) & _PAGE_INVALID))
-                pte_val(pte) |= _PAGE_RO;
+        pte_val(pte) &= ~_PAGE_WRITE;
+        pte_val(pte) |= _PAGE_PROTECT;
         return pte;
 }
 
 static inline pte_t pte_mkwrite(pte_t pte)
 {
-        pte_val(pte) |= _PAGE_SWW;
-        if (pte_val(pte) & _PAGE_SWC)
-                pte_val(pte) &= ~_PAGE_RO;
+        pte_val(pte) |= _PAGE_WRITE;
+        if (pte_val(pte) & _PAGE_DIRTY)
+                pte_val(pte) &= ~_PAGE_PROTECT;
         return pte;
 }
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-        pte_val(pte) &= ~_PAGE_SWC;
-        /* Do not clobber _PAGE_TYPE_NONE pages!  */
-        if (!(pte_val(pte) & _PAGE_INVALID))
-                pte_val(pte) |= _PAGE_RO;
+        pte_val(pte) &= ~_PAGE_DIRTY;
+        pte_val(pte) |= _PAGE_PROTECT;
         return pte;
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-        pte_val(pte) |= _PAGE_SWC;
-        if (pte_val(pte) & _PAGE_SWW)
-                pte_val(pte) &= ~_PAGE_RO;
+        pte_val(pte) |= _PAGE_DIRTY;
+        if (pte_val(pte) & _PAGE_WRITE)
+                pte_val(pte) &= ~_PAGE_PROTECT;
         return pte;
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-#ifdef CONFIG_PGSTE
-        pte_val(pte) &= ~_PAGE_SWR;
-#endif
+        pte_val(pte) &= ~_PAGE_YOUNG;
+        pte_val(pte) |= _PAGE_INVALID;
         return pte;
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
+        pte_val(pte) |= _PAGE_YOUNG;
+        if (pte_val(pte) & _PAGE_READ)
+                pte_val(pte) &= ~_PAGE_INVALID;
         return pte;
 }
 
@@ -957,7 +986,7 @@ static inline pte_t pte_mkspecial(pte_t pte)
 #ifdef CONFIG_HUGETLB_PAGE
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-        pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
+        pte_val(pte) |= _PAGE_LARGE;
         return pte;
 }
 #endif
@@ -974,8 +1003,8 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
                 pgste = pgste_update_all(ptep, pgste);
-                dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
-                pgste_val(pgste) &= ~PGSTE_UC_BIT;
+                dirty = !!(pgste_val(pgste) & PGSTE_HC_BIT);
+                pgste_val(pgste) &= ~PGSTE_HC_BIT;
                 pgste_set_unlock(ptep, pgste);
                 return dirty;
         }
@@ -994,59 +1023,75 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
                 pgste = pgste_update_young(ptep, pgste);
-                young = !!(pgste_val(pgste) & PGSTE_UR_BIT);
-                pgste_val(pgste) &= ~PGSTE_UR_BIT;
+                young = !!(pgste_val(pgste) & PGSTE_HR_BIT);
+                pgste_val(pgste) &= ~PGSTE_HR_BIT;
                 pgste_set_unlock(ptep, pgste);
         }
         return young;
 }
 
+static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
+{
+        if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+#ifndef CONFIG_64BIT
+                /* pto must point to the start of the segment table */
+                pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
+#else
+                /* ipte in zarch mode can do the math */
+                pte_t *pto = ptep;
+#endif
+                asm volatile(
+                        "       ipte    %2,%3"
+                        : "=m" (*ptep) : "m" (*ptep),
+                          "a" (pto), "a" (address));
+        }
+}
+
+static inline void ptep_flush_lazy(struct mm_struct *mm,
+                                   unsigned long address, pte_t *ptep)
+{
+        int active = (mm == current->active_mm) ? 1 : 0;
+
+        if (atomic_read(&mm->context.attach_count) > active)
+                __ptep_ipte(address, ptep);
+        else
+                mm->context.flush_mm = 1;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
                                             unsigned long addr, pte_t *ptep)
 {
         pgste_t pgste;
         pte_t pte;
+        int young;
 
         if (mm_has_pgste(vma->vm_mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste = pgste_update_young(ptep, pgste);
-                pte = *ptep;
-                *ptep = pte_mkold(pte);
-                pgste_set_unlock(ptep, pgste);
-                return pte_young(pte);
+                pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
         }
-        return 0;
+
+        pte = *ptep;
+        __ptep_ipte(addr, ptep);
+        young = pte_young(pte);
+        pte = pte_mkold(pte);
+
+        if (mm_has_pgste(vma->vm_mm)) {
+                pgste_set_pte(ptep, pte);
+                pgste_set_unlock(ptep, pgste);
+        } else
+                *ptep = pte;
+
+        return young;
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
 static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
                                          unsigned long address, pte_t *ptep)
 {
-        /* No need to flush TLB
-         * On s390 reference bits are in storage key and never in TLB
-         * With virtualization we handle the reference bit, without we
-         * we can simply return */
         return ptep_test_and_clear_young(vma, address, ptep);
 }
 
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
-{
-        if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-#ifndef CONFIG_64BIT
-                /* pto must point to the start of the segment table */
-                pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
-#else
-                /* ipte in zarch mode can do the math */
-                pte_t *pto = ptep;
-#endif
-                asm volatile(
-                        "       ipte    %2,%3"
-                        : "=m" (*ptep) : "m" (*ptep),
-                          "a" (pto), "a" (address));
-        }
-}
-
 /*
  * This is hard to understand. ptep_get_and_clear and ptep_clear_flush
  * both clear the TLB for the unmapped pte. The reason is that
@@ -1067,16 +1112,14 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
         pgste_t pgste;
         pte_t pte;
 
-        mm->context.flush_mm = 1;
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
                 pgste = pgste_ipte_notify(mm, address, ptep, pgste);
         }
 
         pte = *ptep;
-        if (!mm_exclusive(mm))
-                __ptep_ipte(address, ptep);
-        pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+        ptep_flush_lazy(mm, address, ptep);
+        pte_val(*ptep) = _PAGE_INVALID;
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_update_all(&pte, pgste);
@@ -1093,15 +1136,14 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
         pgste_t pgste;
         pte_t pte;
 
-        mm->context.flush_mm = 1;
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
                 pgste_ipte_notify(mm, address, ptep, pgste);
         }
 
         pte = *ptep;
-        if (!mm_exclusive(mm))
-                __ptep_ipte(address, ptep);
+        ptep_flush_lazy(mm, address, ptep);
+        pte_val(*ptep) |= _PAGE_INVALID;
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_update_all(&pte, pgste);
@@ -1117,7 +1159,7 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
         pgste_t pgste;
 
         if (mm_has_pgste(mm)) {
-                pgste = *(pgste_t *)(ptep + PTRS_PER_PTE);
+                pgste = pgste_get(ptep);
                 pgste_set_key(ptep, pgste, pte);
                 pgste_set_pte(ptep, pte);
                 pgste_set_unlock(ptep, pgste);
@@ -1139,7 +1181,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 
         pte = *ptep;
         __ptep_ipte(address, ptep);
-        pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+        pte_val(*ptep) = _PAGE_INVALID;
 
         if (mm_has_pgste(vma->vm_mm)) {
                 pgste = pgste_update_all(&pte, pgste);
@@ -1163,18 +1205,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
         pgste_t pgste;
         pte_t pte;
 
-        if (mm_has_pgste(mm)) {
+        if (!full && mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
-                if (!full)
-                        pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+                pgste = pgste_ipte_notify(mm, address, ptep, pgste);
         }
 
         pte = *ptep;
         if (!full)
-                __ptep_ipte(address, ptep);
-        pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+                ptep_flush_lazy(mm, address, ptep);
+        pte_val(*ptep) = _PAGE_INVALID;
 
-        if (mm_has_pgste(mm)) {
+        if (!full && mm_has_pgste(mm)) {
                 pgste = pgste_update_all(&pte, pgste);
                 pgste_set_unlock(ptep, pgste);
         }
@@ -1189,14 +1230,12 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
         pte_t pte = *ptep;
 
         if (pte_write(pte)) {
-                mm->context.flush_mm = 1;
                 if (mm_has_pgste(mm)) {
                         pgste = pgste_get_lock(ptep);
                         pgste = pgste_ipte_notify(mm, address, ptep, pgste);
                 }
 
-                if (!mm_exclusive(mm))
-                        __ptep_ipte(address, ptep);
+                ptep_flush_lazy(mm, address, ptep);
                 pte = pte_wrprotect(pte);
 
                 if (mm_has_pgste(mm)) {
@@ -1240,7 +1279,7 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
         pte_t __pte;
         pte_val(__pte) = physpage + pgprot_val(pgprot);
-        return __pte;
+        return pte_mkyoung(__pte);
 }
 
 static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
@@ -1248,10 +1287,8 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
         unsigned long physpage = page_to_phys(page);
         pte_t __pte = mk_pte_phys(physpage, pgprot);
 
-        if ((pte_val(__pte) & _PAGE_SWW) && PageDirty(page)) {
-                pte_val(__pte) |= _PAGE_SWC;
-                pte_val(__pte) &= ~_PAGE_RO;
-        }
+        if (pte_write(__pte) && PageDirty(page))
+                __pte = pte_mkdirty(__pte);
         return __pte;
 }
 
@@ -1313,7 +1350,7 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
         unsigned long sto = (unsigned long) pmdp -
                             pmd_index(address) * sizeof(pmd_t);
 
-        if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) {
+        if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)) {
                 asm volatile(
                         "       .insn   rrf,0xb98e0000,%2,%3,0,0"
                         : "=m" (*pmdp)
@@ -1324,24 +1361,68 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
         }
 }
 
+static inline void __pmd_csp(pmd_t *pmdp)
+{
+        register unsigned long reg2 asm("2") = pmd_val(*pmdp);
+        register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
+                                               _SEGMENT_ENTRY_INVALID;
+        register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
+
+        asm volatile(
+                "       csp %1,%3"
+                : "=m" (*pmdp)
+                : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+}
+
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
 static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 {
         /*
-         * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx)
+         * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
          * Convert to segment table entry format.
          */
         if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
                 return pgprot_val(SEGMENT_NONE);
-        if (pgprot_val(pgprot) == pgprot_val(PAGE_RO))
-                return pgprot_val(SEGMENT_RO);
-        return pgprot_val(SEGMENT_RW);
+        if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
+                return pgprot_val(SEGMENT_READ);
+        return pgprot_val(SEGMENT_WRITE);
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+#ifdef CONFIG_64BIT
+        if (pmd_prot_none(pmd)) {
+                pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+        } else {
+                pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+                pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
+        }
+#endif
+        return pmd;
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+#ifdef CONFIG_64BIT
+        if (pmd_prot_none(pmd)) {
+                pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
+        } else {
+                pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
+                pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
+        }
+#endif
+        return pmd;
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
+        int young;
+
+        young = pmd_young(pmd);
         pmd_val(pmd) &= _SEGMENT_CHG_MASK;
         pmd_val(pmd) |= massage_pgprot_pmd(newprot);
+        if (young)
+                pmd = pmd_mkyoung(pmd);
         return pmd;
 }
 
@@ -1349,14 +1430,14 @@ static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
 {
         pmd_t __pmd;
         pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot);
-        return __pmd;
+        return pmd_mkyoung(__pmd);
 }
 
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
-        /* Do not clobber _HPAGE_TYPE_NONE pages! */
-        if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV))
-                pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO;
+        /* Do not clobber PROT_NONE segments! */
+        if (!pmd_prot_none(pmd))
+                pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
         return pmd;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */
@@ -1378,7 +1459,7 @@ static inline int pmd_trans_splitting(pmd_t pmd)
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
                               pmd_t *pmdp, pmd_t entry)
 {
-        if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1)
+        if (!(pmd_val(entry) & _SEGMENT_ENTRY_INVALID) && MACHINE_HAS_EDAT1)
                 pmd_val(entry) |= _SEGMENT_ENTRY_CO;
         *pmdp = entry;
 }
@@ -1391,7 +1472,9 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
-        pmd_val(pmd) |= _SEGMENT_ENTRY_RO;
+        /* Do not clobber PROT_NONE segments! */
+        if (!pmd_prot_none(pmd))
+                pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
         return pmd;
 }
 
@@ -1401,50 +1484,16 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
         return pmd;
 }
 
-static inline pmd_t pmd_mkold(pmd_t pmd)
-{
-        /* No referenced bit in the segment table entry. */
-        return pmd;
-}
-
-static inline pmd_t pmd_mkyoung(pmd_t pmd)
-{
-        /* No referenced bit in the segment table entry. */
-        return pmd;
-}
-
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
                                             unsigned long address, pmd_t *pmdp)
 {
-        unsigned long pmd_addr = pmd_val(*pmdp) & HPAGE_MASK;
-        long tmp, rc;
-        int counter;
+        pmd_t pmd;
 
-        rc = 0;
-        if (MACHINE_HAS_RRBM) {
-                counter = PTRS_PER_PTE >> 6;
-                asm volatile(
-                        "0:     .insn   rre,0xb9ae0000,%0,%3\n" /* rrbm */
-                        "       ogr     %1,%0\n"
-                        "       la      %3,0(%4,%3)\n"
-                        "       brct    %2,0b\n"
-                        : "=&d" (tmp), "+&d" (rc), "+d" (counter),
-                          "+a" (pmd_addr)
-                        : "a" (64 * 4096UL) : "cc");
-                rc = !!rc;
-        } else {
-                counter = PTRS_PER_PTE;
-                asm volatile(
-                        "0:     rrbe    0,%2\n"
-                        "       la      %2,0(%3,%2)\n"
-                        "       brc     12,1f\n"
-                        "       lhi     %0,1\n"
-                        "1:     brct    %1,0b\n"
-                        : "+d" (rc), "+d" (counter), "+a" (pmd_addr)
-                        : "a" (4096UL) : "cc");
-        }
-        return rc;
+        pmd = *pmdp;
+        __pmd_idte(address, pmdp);
+        *pmdp = pmd_mkold(pmd);
+        return pmd_young(pmd);
 }
 
 #define __HAVE_ARCH_PMDP_GET_AND_CLEAR
@@ -1510,10 +1559,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
  * exception will occur instead of a page translation exception. The
  * specifiation exception has the bad habit not to store necessary
  * information in the lowcore.
- * Bit 21 and bit 22 are the page invalid bit and the page protection
- * bit. We set both to indicate a swapped page.
- * Bit 30 and 31 are used to distinguish the different page types. For
- * a swapped page these bits need to be zero.
+ * Bits 21, 22, 30 and 31 are used to indicate the page type.
+ * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
  * This leaves the bits 1-19 and bits 24-29 to store type and offset.
  * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19
  * plus 24 for the offset.
@@ -1527,10 +1574,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
  * exception will occur instead of a page translation exception. The
  * specifiation exception has the bad habit not to store necessary
  * information in the lowcore.
- * Bit 53 and bit 54 are the page invalid bit and the page protection
- * bit. We set both to indicate a swapped page.
- * Bit 62 and 63 are used to distinguish the different page types. For
- * a swapped page these bits need to be zero.
+ * Bits 53, 54, 62 and 63 are used to indicate the page type.
+ * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
  * This leaves the bits 0-51 and bits 56-61 to store type and offset.
  * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51
  * plus 56 for the offset.
@@ -1547,7 +1592,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 {
         pte_t pte;
         offset &= __SWP_OFFSET_MASK;
-        pte_val(pte) = _PAGE_TYPE_SWAP | ((type & 0x1f) << 2) |
+        pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) |
                 ((offset & 1UL) << 7) | ((offset & ~1UL) << 11);
         return pte;
 }
@@ -1570,7 +1615,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 
 #define pgoff_to_pte(__off) \
         ((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \
-                   | _PAGE_TYPE_FILE })
+                   | _PAGE_INVALID | _PAGE_PROTECT })
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/s390/include/asm/serial.h b/arch/s390/include/asm/serial.h
new file mode 100644
index 000000000000..5b3e48ef534b
--- /dev/null
+++ b/arch/s390/include/asm/serial.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_S390_SERIAL_H
+#define _ASM_S390_SERIAL_H
+
+#define BASE_BAUD 0
+
+#endif /* _ASM_S390_SERIAL_H */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 80b6f11263c4..6dbd559763c9 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -8,6 +8,7 @@
 #define __ASM_SWITCH_TO_H
 
 #include <linux/thread_info.h>
+#include <asm/ptrace.h>
 
 extern struct task_struct *__switch_to(void *, void *);
 extern void update_cr_regs(struct task_struct *task);
@@ -68,12 +69,16 @@ static inline void restore_fp_regs(s390_fp_regs *fpregs)
 
 static inline void save_access_regs(unsigned int *acrs)
 {
-        asm volatile("stam 0,15,%0" : "=Q" (*acrs));
+        typedef struct { int _[NUM_ACRS]; } acrstype;
+
+        asm volatile("stam 0,15,%0" : "=Q" (*(acrstype *)acrs));
 }
 
 static inline void restore_access_regs(unsigned int *acrs)
 {
-        asm volatile("lam 0,15,%0" : : "Q" (*acrs));
+        typedef struct { int _[NUM_ACRS]; } acrstype;
+
+        asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs));
 }
 
 #define switch_to(prev,next,last) do {                                  \
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b75d7d686684..2cb846c4b37f 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -32,6 +32,7 @@ struct mmu_gather {
         struct mm_struct *mm;
         struct mmu_table_batch *batch;
         unsigned int fullmm;
+        unsigned long start, end;
 };
 
 struct mmu_table_batch {
@@ -48,10 +49,13 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
                                   struct mm_struct *mm,
-                                  unsigned int full_mm_flush)
+                                  unsigned long start,
+                                  unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->start = start;
+        tlb->end = end;
+        tlb->fullmm = !(start | (end+1));
         tlb->batch = NULL;
         if (tlb->fullmm)
                 __tlb_flush_mm(mm);
@@ -59,13 +63,14 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
+        __tlb_flush_mm_lazy(tlb->mm);
         tlb_table_flush(tlb);
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
                                   unsigned long start, unsigned long end)
 {
-        tlb_table_flush(tlb);
+        tlb_flush_mmu(tlb);
 }
 
 /*
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 6b32af30878c..f9fef0425fee 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -86,7 +86,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
                 __tlb_flush_full(mm);
 }
 
-static inline void __tlb_flush_mm_cond(struct mm_struct * mm)
+static inline void __tlb_flush_mm_lazy(struct mm_struct * mm)
 {
         if (mm->context.flush_mm) {
                 __tlb_flush_mm(mm);
@@ -118,13 +118,13 @@ static inline void __tlb_flush_mm_cond(struct mm_struct * mm)
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
-        __tlb_flush_mm_cond(mm);
+        __tlb_flush_mm_lazy(mm);
 }
 
 static inline void flush_tlb_range(struct vm_area_struct *vma,
                                    unsigned long start, unsigned long end)
 {
-        __tlb_flush_mm_cond(vma->vm_mm);
+        __tlb_flush_mm_lazy(vma->vm_mm);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start,
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index be7a408be7a1..cc30d1fb000c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -18,6 +18,7 @@
 #include <asm/unistd.h>
 #include <asm/page.h>
 #include <asm/sigp.h>
+#include <asm/irq.h>
 
 __PT_R0      =  __PT_GPRS
 __PT_R1      =  __PT_GPRS + 4
@@ -435,6 +436,11 @@ io_skip:
 io_loop:
         l       %r1,BASED(.Ldo_IRQ)
         lr      %r2,%r11                # pass pointer to pt_regs
+        lhi     %r3,IO_INTERRUPT
+        tm      __PT_INT_CODE+8(%r11),0x80      # adapter interrupt ?
+        jz      io_call
+        lhi     %r3,THIN_INTERRUPT
+io_call:
         basr    %r14,%r1                # call do_IRQ
         tm      __LC_MACHINE_FLAGS+2,0x10       # MACHINE_FLAG_LPAR
         jz      io_return
@@ -584,9 +590,10 @@ ext_skip:
         mvc     __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
         mvc     __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
         TRACE_IRQS_OFF
+        l       %r1,BASED(.Ldo_IRQ)
         lr      %r2,%r11                # pass pointer to pt_regs
-        l       %r1,BASED(.Ldo_extint)
-        basr    %r14,%r1                # call do_extint
+        lhi     %r3,EXT_INTERRUPT
+        basr    %r14,%r1                # call do_IRQ
         j       io_return
 
 /*
@@ -879,13 +886,13 @@ cleanup_idle:
         stm     %r9,%r10,__LC_SYSTEM_TIMER
         mvc     __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
         # prepare return psw
-        n       %r8,BASED(cleanup_idle_wait)    # clear wait state bit
+        n       %r8,BASED(cleanup_idle_wait)    # clear irq & wait state bits
         l       %r9,24(%r11)                    # return from psw_idle
         br      %r14
 cleanup_idle_insn:
         .long   psw_idle_lpsw + 0x80000000
 cleanup_idle_wait:
-        .long   0xfffdffff
+        .long   0xfcfdffff
 
 /*
  * Integer constants
@@ -902,7 +909,6 @@ cleanup_idle_wait:
 .Ldo_machine_check:     .long   s390_do_machine_check
 .Lhandle_mcck:          .long   s390_handle_mcck
 .Ldo_IRQ:               .long   do_IRQ
-.Ldo_extint:            .long   do_extint
 .Ldo_signal:            .long   do_signal
 .Ldo_notify_resume:     .long   do_notify_resume
 .Ldo_per_trap:          .long   do_per_trap
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 1c039d0c24c7..2b2188b97c6a 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -19,6 +19,7 @@
 #include <asm/unistd.h>
 #include <asm/page.h>
 #include <asm/sigp.h>
+#include <asm/irq.h>
 
 __PT_R0      =  __PT_GPRS
 __PT_R1      =  __PT_GPRS + 8
@@ -468,6 +469,11 @@ io_skip:
         xc      __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 io_loop:
         lgr     %r2,%r11                # pass pointer to pt_regs
+        lghi    %r3,IO_INTERRUPT
+        tm      __PT_INT_CODE+8(%r11),0x80      # adapter interrupt ?
+        jz      io_call
+        lghi    %r3,THIN_INTERRUPT
+io_call:
         brasl   %r14,do_IRQ
         tm      __LC_MACHINE_FLAGS+6,0x10       # MACHINE_FLAG_LPAR
         jz      io_return
@@ -623,7 +629,8 @@ ext_skip:
         TRACE_IRQS_OFF
         xc      __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
         lgr     %r2,%r11                # pass pointer to pt_regs
-        brasl   %r14,do_extint
+        lghi    %r3,EXT_INTERRUPT
+        brasl   %r14,do_IRQ
         j       io_return
 
 /*
@@ -922,7 +929,7 @@ cleanup_idle:
         stg     %r9,__LC_SYSTEM_TIMER
         mvc     __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
         # prepare return psw
-        nihh    %r8,0xfffd              # clear wait state bit
+        nihh    %r8,0xfcfd              # clear irq & wait state bits
         lg      %r9,48(%r11)            # return from psw_idle
         br      %r14
 cleanup_idle_insn:
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 54b0995514e8..b34ba0ea96a9 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <asm/cputime.h>
 #include <asm/lowcore.h>
 #include <asm/irq.h>
+#include <asm/hw_irq.h>
 #include "entry.h"
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -42,9 +43,10 @@ struct irq_class {
  * Since the external and I/O interrupt fields are already sums we would end
  * up with having a sum which accounts each interrupt twice.
  */
-static const struct irq_class irqclass_main_desc[NR_IRQS] = {
-        [EXTERNAL_INTERRUPT] = {.name = "EXT"},
-        [IO_INTERRUPT]       = {.name = "I/O"}
+static const struct irq_class irqclass_main_desc[NR_IRQS_BASE] = {
+        [EXT_INTERRUPT]  = {.name = "EXT"},
+        [IO_INTERRUPT]   = {.name = "I/O"},
+        [THIN_INTERRUPT] = {.name = "AIO"},
 };
 
 /*
@@ -86,6 +88,28 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
         [CPU_RST]    = {.name = "RST", .desc = "[CPU] CPU Restart"},
 };
 
+void __init init_IRQ(void)
+{
+        irq_reserve_irqs(0, THIN_INTERRUPT);
+        init_cio_interrupts();
+        init_airq_interrupts();
+        init_ext_interrupts();
+}
+
+void do_IRQ(struct pt_regs *regs, int irq)
+{
+        struct pt_regs *old_regs;
+
+        old_regs = set_irq_regs(regs);
+        irq_enter();
+        if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
+                /* Serve timer interrupts first. */
+                clock_comparator_work();
+        generic_handle_irq(irq);
+        irq_exit();
+        set_irq_regs(old_regs);
+}
+
 /*
  * show_interrupts is needed by /proc/interrupts.
  */
@@ -100,27 +124,36 @@ int show_interrupts(struct seq_file *p, void *v)
                 for_each_online_cpu(cpu)
                         seq_printf(p, "CPU%d       ", cpu);
                 seq_putc(p, '\n');
+                goto out;
         }
         if (irq < NR_IRQS) {
+                if (irq >= NR_IRQS_BASE)
+                        goto out;
                 seq_printf(p, "%s: ", irqclass_main_desc[irq].name);
                 for_each_online_cpu(cpu)
-                        seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[irq]);
+                        seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
                 seq_putc(p, '\n');
-                goto skip_arch_irqs;
+                goto out;
         }
         for (irq = 0; irq < NR_ARCH_IRQS; irq++) {
                 seq_printf(p, "%s: ", irqclass_sub_desc[irq].name);
                 for_each_online_cpu(cpu)
-                        seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).irqs[irq]);
+                        seq_printf(p, "%10u ",
+                                   per_cpu(irq_stat, cpu).irqs[irq]);
                 if (irqclass_sub_desc[irq].desc)
                         seq_printf(p, "  %s", irqclass_sub_desc[irq].desc);
                 seq_putc(p, '\n');
         }
-skip_arch_irqs:
+out:
         put_online_cpus();
         return 0;
 }
 
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+        return 0;
+}
+
 /*
  * Switch to the asynchronous interrupt stack for softirq execution.
  */
@@ -159,14 +192,6 @@ asmlinkage void do_softirq(void)
         local_irq_restore(flags);
 }
 
-#ifdef CONFIG_PROC_FS
-void init_irq_proc(void)
-{
-        if (proc_mkdir("irq", NULL))
-                create_prof_cpu_mask();
-}
-#endif
-
 /*
  * ext_int_hash[index] is the list head for all external interrupts that hash
  * to this index.
@@ -183,14 +208,6 @@ struct ext_int_info {
 /* ext_int_hash_lock protects the handler lists for external interrupts */
 DEFINE_SPINLOCK(ext_int_hash_lock);
 
-static void __init init_external_interrupts(void)
-{
-        int idx;
-
-        for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
-                INIT_LIST_HEAD(&ext_int_hash[idx]);
-}
-
 static inline int ext_hash(u16 code)
 {
         return (code + (code >> 9)) & 0xff;
@@ -234,20 +251,13 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 }
 EXPORT_SYMBOL(unregister_external_interrupt);
 
-void __irq_entry do_extint(struct pt_regs *regs)
+static irqreturn_t do_ext_interrupt(int irq, void *dummy)
 {
+        struct pt_regs *regs = get_irq_regs();
         struct ext_code ext_code;
-        struct pt_regs *old_regs;
         struct ext_int_info *p;
         int index;
 
-        old_regs = set_irq_regs(regs);
-        irq_enter();
-        if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) {
-                /* Serve timer interrupts first. */
-                clock_comparator_work();
-        }
-        kstat_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL);
         ext_code = *(struct ext_code *) &regs->int_code;
         if (ext_code.code != 0x1004)
                 __get_cpu_var(s390_idle).nohz_delay = 1;
@@ -259,13 +269,25 @@ void __irq_entry do_extint(struct pt_regs *regs)
                         p->handler(ext_code, regs->int_parm,
                                    regs->int_parm_long);
         rcu_read_unlock();
-        irq_exit();
-        set_irq_regs(old_regs);
+
+        return IRQ_HANDLED;
 }
 
-void __init init_IRQ(void)
+static struct irqaction external_interrupt = {
+        .name    = "EXT",
+        .handler = do_ext_interrupt,
+};
+
+void __init init_ext_interrupts(void)
 {
-        init_external_interrupts();
+        int idx;
+
+        for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
+                INIT_LIST_HEAD(&ext_int_hash[idx]);
+
+        irq_set_chip_and_handler(EXT_INTERRUPT,
+                                 &dummy_irq_chip, handle_percpu_irq);
+        setup_irq(EXT_INTERRUPT, &external_interrupt);
 }
 
 static DEFINE_SPINLOCK(sc_irq_lock);
@@ -313,69 +335,3 @@ void measurement_alert_subclass_unregister(void)
         spin_unlock(&ma_subclass_lock);
 }
 EXPORT_SYMBOL(measurement_alert_subclass_unregister);
-
-#ifdef CONFIG_SMP
-void synchronize_irq(unsigned int irq)
-{
-        /*
-         * Not needed, the handler is protected by a lock and IRQs that occur
-         * after the handler is deleted are just NOPs.
-         */
-}
-EXPORT_SYMBOL_GPL(synchronize_irq);
-#endif
-
-#ifndef CONFIG_PCI
-
-/* Only PCI devices have dynamically-defined IRQ handlers */
-
-int request_irq(unsigned int irq, irq_handler_t handler,
-                unsigned long irqflags, const char *devname, void *dev_id)
-{
-        return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(request_irq);
-
-void free_irq(unsigned int irq, void *dev_id)
-{
-        WARN_ON(1);
-}
-EXPORT_SYMBOL_GPL(free_irq);
-
-void enable_irq(unsigned int irq)
-{
-        WARN_ON(1);
-}
-EXPORT_SYMBOL_GPL(enable_irq);
-
-void disable_irq(unsigned int irq)
-{
-        WARN_ON(1);
-}
-EXPORT_SYMBOL_GPL(disable_irq);
-
-#endif /* !CONFIG_PCI */
-
-void disable_irq_nosync(unsigned int irq)
-{
-        disable_irq(irq);
-}
-EXPORT_SYMBOL_GPL(disable_irq_nosync);
-
-unsigned long probe_irq_on(void)
-{
-        return 0;
-}
-EXPORT_SYMBOL_GPL(probe_irq_on);
-
-int probe_irq_off(unsigned long val)
-{
-        return 0;
-}
-EXPORT_SYMBOL_GPL(probe_irq_off);
-
-unsigned int probe_irq_mask(unsigned long val)
-{
-        return val;
-}
-EXPORT_SYMBOL_GPL(probe_irq_mask);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3388b2b2a07d..adbbe7f1cb0d 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -105,14 +105,31 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn)
                 fixup |= FIXUP_RETURN_REGISTER;
                 break;
         case 0xeb:
-                if ((insn[2] & 0xff) == 0x44 || /* bxhg  */
-                    (insn[2] & 0xff) == 0x45)   /* bxleg */
+                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;
 }
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 504175ebf8b0..c4c033819879 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -214,10 +214,7 @@ static int notrace s390_revalidate_registers(struct mci *mci)
                         : "0", "cc");
 #endif
         /* Revalidate clock comparator register */
-        if (S390_lowcore.clock_comparator == -1)
-                set_clock_comparator(S390_lowcore.mcck_clock);
-        else
-                set_clock_comparator(S390_lowcore.clock_comparator);
+        set_clock_comparator(S390_lowcore.clock_comparator);
         /* Check if old PSW is valid */
         if (!mci->wp)
                 /*
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index a6fc037671b1..500aa1029bcb 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -52,12 +52,13 @@ static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs)
 
 static bool is_in_guest(struct pt_regs *regs)
 {
-        unsigned long ip = instruction_pointer(regs);
-
         if (user_mode(regs))
                 return false;
-
-        return ip == (unsigned long) &sie_exit;
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+        return instruction_pointer(regs) == (unsigned long) &sie_exit;
+#else
+        return false;
+#endif
 }
 
 static unsigned long guest_is_user_mode(struct pt_regs *regs)
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 2bc3eddae34a..c5dbb335716d 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -71,6 +71,7 @@ void arch_cpu_idle(void)
         }
         /* Halt the cpu and keep track of cpu time accounting. */
         vtime_stop_cpu();
+        local_irq_enable();
 }
 
 void arch_cpu_idle_exit(void)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index e9fadb04e3c6..9556905bd3ce 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -60,11 +60,11 @@ void update_cr_regs(struct task_struct *task)
 
                 __ctl_store(cr, 0, 2);
                 cr_new[1] = cr[1];
-                /* Set or clear transaction execution TXC/PIFO bits 8 and 9. */
+                /* Set or clear transaction execution TXC bit 8. */
                 if (task->thread.per_flags & PER_FLAG_NO_TE)
-                        cr_new[0] = cr[0] & ~(3UL << 54);
+                        cr_new[0] = cr[0] & ~(1UL << 55);
                 else
-                        cr_new[0] = cr[0] | (3UL << 54);
+                        cr_new[0] = cr[0] | (1UL << 55);
                 /* Set or clear transaction execution TDC bits 62 and 63. */
                 cr_new[2] = cr[2] & ~3UL;
                 if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
@@ -1299,7 +1299,7 @@ int regs_query_register_offset(const char *name)
 
         if (!name || *name != 'r')
                 return -EINVAL;
-        if (strict_strtoul(name + 1, 10, &offset))
+        if (kstrtoul(name + 1, 10, &offset))
                 return -EINVAL;
         if (offset >= NUM_GPRS)
                 return -EINVAL;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 497451ec5e26..aeed8a61fa0d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -994,6 +994,7 @@ static void __init setup_hwcaps(void)
                 strcpy(elf_platform, "z196");
                 break;
         case 0x2827:
+        case 0x2828:
                 strcpy(elf_platform, "zEC12");
                 break;
         }
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index c479d2f9605b..737bff38e3ee 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -10,6 +10,9 @@
 #include <linux/suspend.h>
 #include <linux/mm.h>
 #include <asm/ctl_reg.h>
+#include <asm/ipl.h>
+#include <asm/cio.h>
+#include <asm/pci.h>
 
 /*
  * References to section boundaries
@@ -211,3 +214,11 @@ void restore_processor_state(void)
         __ctl_set_bit(0,28);
         local_mcck_enable();
 }
+
+/* Called at the end of swsusp_arch_resume */
+void s390_early_resume(void)
+{
+        lgr_info_log();
+        channel_subsystem_reinit();
+        zpci_rescan();
+}
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index c487be4cfc81..6b09fdffbd2f 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -281,11 +281,8 @@ restore_registers:
         lghi    %r2,0
         brasl   %r14,arch_set_page_states
 
-        /* Log potential guest relocation */
-        brasl   %r14,lgr_info_log
-
-        /* Reinitialize the channel subsystem */
-        brasl   %r14,channel_subsystem_reinit
+        /* Call arch specific early resume code */
+        brasl   %r14,s390_early_resume
 
         /* Return 0 */
         lmg     %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 876546b9cfa1..064c3082ab33 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -92,7 +92,6 @@ void clock_comparator_work(void)
         struct clock_event_device *cd;
 
         S390_lowcore.clock_comparator = -1ULL;
-        set_clock_comparator(S390_lowcore.clock_comparator);
         cd = &__get_cpu_var(comparators);
         cd->event_handler(cd);
 }
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index d7776281cb60..05d75c413137 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -63,7 +63,7 @@ static int __init vdso_setup(char *s)
         else if (strncmp(s, "off", 4) == 0)
                 vdso_enabled = 0;
         else {
-                rc = strict_strtoul(s, 0, &val);
+                rc = kstrtoul(s, 0, &val);
                 vdso_enabled = rc ? 0 : !!val;
         }
         return !rc;
@@ -113,11 +113,11 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore)
 
         clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
                     PAGE_SIZE << SEGMENT_ORDER);
-        clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY,
+        clear_table((unsigned long *) page_table, _PAGE_INVALID,
                     256*sizeof(unsigned long));
 
         *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
-        *(unsigned long *) page_table = _PAGE_RO + page_frame;
+        *(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
 
         psal = (u32 *) (page_table + 256*sizeof(unsigned long));
         aste = psal + 32;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ba694d2ba51e..34c1c9a90be2 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -702,14 +702,25 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
                 return rc;
 
         vcpu->arch.sie_block->icptcode = 0;
-        preempt_disable();
-        kvm_guest_enter();
-        preempt_enable();
         VCPU_EVENT(vcpu, 6, "entering sie flags %x",
                    atomic_read(&vcpu->arch.sie_block->cpuflags));
         trace_kvm_s390_sie_enter(vcpu,
                                  atomic_read(&vcpu->arch.sie_block->cpuflags));
+
+        /*
+         * As PF_VCPU will be used in fault handler, between guest_enter
+         * and guest_exit should be no uaccess.
+         */
+        preempt_disable();
+        kvm_guest_enter();
+        preempt_enable();
         rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
+        kvm_guest_exit();
+
+        VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+                   vcpu->arch.sie_block->icptcode);
+        trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
+
         if (rc > 0)
                 rc = 0;
         if (rc < 0) {
@@ -721,10 +732,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
                         rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
                 }
         }
-        VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
-                   vcpu->arch.sie_block->icptcode);
-        trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
-        kvm_guest_exit();
 
         memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
         return rc;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 0da3e6eb6be6..4cdc54e63ebc 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -16,6 +16,7 @@
 #include <linux/errno.h>
 #include <linux/compat.h>
 #include <asm/asm-offsets.h>
+#include <asm/facility.h>
 #include <asm/current.h>
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
@@ -532,8 +533,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
                 return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
         /* Only provide non-quiescing support if the host supports it */
-        if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ &&
-            S390_lowcore.stfl_fac_list & 0x00020000)
+        if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ && !test_facility(14))
                 return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
         /* No support for conditional-SSKE */
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index c61b9fad43cc..57c87d7d7ede 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -44,7 +44,6 @@ static void __udelay_disabled(unsigned long long usecs)
         do {
                 set_clock_comparator(end);
                 vtime_stop_cpu();
-                local_irq_disable();
         } while (get_tod_clock() < end);
         lockdep_on();
         __ctl_load(cr0, 0, 0);
@@ -64,7 +63,6 @@ static void __udelay_enabled(unsigned long long usecs)
                         set_clock_comparator(end);
                 }
                 vtime_stop_cpu();
-                local_irq_disable();
                 if (clock_saved)
                         local_tick_enable(clock_saved);
         } while (get_tod_clock() < end);
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 50ea137a2d3c..1694d738b175 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -86,28 +86,28 @@ static unsigned long follow_table(struct mm_struct *mm,
         switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
         case _ASCE_TYPE_REGION1:
                 table = table + ((address >> 53) & 0x7ff);
-                if (unlikely(*table & _REGION_ENTRY_INV))
+                if (unlikely(*table & _REGION_ENTRY_INVALID))
                         return -0x39UL;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 /* fallthrough */
         case _ASCE_TYPE_REGION2:
                 table = table + ((address >> 42) & 0x7ff);
-                if (unlikely(*table & _REGION_ENTRY_INV))
+                if (unlikely(*table & _REGION_ENTRY_INVALID))
                         return -0x3aUL;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 /* fallthrough */
         case _ASCE_TYPE_REGION3:
                 table = table + ((address >> 31) & 0x7ff);
-                if (unlikely(*table & _REGION_ENTRY_INV))
+                if (unlikely(*table & _REGION_ENTRY_INVALID))
                         return -0x3bUL;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 /* fallthrough */
         case _ASCE_TYPE_SEGMENT:
                 table = table + ((address >> 20) & 0x7ff);
-                if (unlikely(*table & _SEGMENT_ENTRY_INV))
+                if (unlikely(*table & _SEGMENT_ENTRY_INVALID))
                         return -0x10UL;
                 if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) {
-                        if (write && (*table & _SEGMENT_ENTRY_RO))
+                        if (write && (*table & _SEGMENT_ENTRY_PROTECT))
                                 return -0x04UL;
                         return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) +
                                 (address & ~_SEGMENT_ENTRY_ORIGIN_LARGE);
@@ -117,7 +117,7 @@ static unsigned long follow_table(struct mm_struct *mm,
         table = table + ((address >> 12) & 0xff);
         if (unlikely(*table & _PAGE_INVALID))
                 return -0x11UL;
-        if (write && (*table & _PAGE_RO))
+        if (write && (*table & _PAGE_PROTECT))
                 return -0x04UL;
         return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
 }
@@ -130,13 +130,13 @@ static unsigned long follow_table(struct mm_struct *mm,
         unsigned long *table = (unsigned long *)__pa(mm->pgd);
 
         table = table + ((address >> 20) & 0x7ff);
-        if (unlikely(*table & _SEGMENT_ENTRY_INV))
+        if (unlikely(*table & _SEGMENT_ENTRY_INVALID))
                 return -0x10UL;
         table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
         table = table + ((address >> 12) & 0xff);
         if (unlikely(*table & _PAGE_INVALID))
                 return -0x11UL;
-        if (write && (*table & _PAGE_RO))
+        if (write && (*table & _PAGE_PROTECT))
                 return -0x04UL;
         return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
 }
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 3ad65b04ac15..46d517c3c763 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -53,7 +53,7 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level)
                 seq_printf(m, "I\n");
                 return;
         }
-        seq_printf(m, "%s", pr & _PAGE_RO ? "RO " : "RW ");
+        seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW ");
         seq_printf(m, "%s", pr & _PAGE_CO ? "CO " : "   ");
         seq_putc(m, '\n');
 }
@@ -105,12 +105,12 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 }
 
 /*
- * The actual page table walker functions. In order to keep the implementation
- * of print_prot() short, we only check and pass _PAGE_INVALID and _PAGE_RO
- * flags to note_page() if a region, segment or page table entry is invalid or
- * read-only.
- * After all it's just a hint that the current level being walked contains an
- * invalid or read-only entry.
+ * The actual page table walker functions. In order to keep the
+ * implementation of print_prot() short, we only check and pass
+ * _PAGE_INVALID and _PAGE_PROTECT flags to note_page() if a region,
+ * segment or page table entry is invalid or read-only.
+ * After all it's just a hint that the current level being walked
+ * contains an invalid or read-only entry.
  */
 static void walk_pte_level(struct seq_file *m, struct pg_state *st,
                            pmd_t *pmd, unsigned long addr)
@@ -122,14 +122,14 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st,
         for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) {
                 st->current_address = addr;
                 pte = pte_offset_kernel(pmd, addr);
-                prot = pte_val(*pte) & (_PAGE_RO | _PAGE_INVALID);
+                prot = pte_val(*pte) & (_PAGE_PROTECT | _PAGE_INVALID);
                 note_page(m, st, prot, 4);
                 addr += PAGE_SIZE;
         }
 }
 
 #ifdef CONFIG_64BIT
-#define _PMD_PROT_MASK (_SEGMENT_ENTRY_RO | _SEGMENT_ENTRY_CO)
+#define _PMD_PROT_MASK (_SEGMENT_ENTRY_PROTECT | _SEGMENT_ENTRY_CO)
 #else
 #define _PMD_PROT_MASK 0
 #endif
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 1f5315d1215c..5d758db27bdc 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -24,7 +24,7 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
         pte_t *ptep, pte;
         struct page *page;
 
-        mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
+        mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
 
         ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
         do {
@@ -55,8 +55,8 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
         struct page *head, *page, *tail;
         int refs;
 
-        result = write ? 0 : _SEGMENT_ENTRY_RO;
-        mask = result | _SEGMENT_ENTRY_INV;
+        result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
+        mask = result | _SEGMENT_ENTRY_INVALID;
         if ((pmd_val(pmd) & mask) != result)
                 return 0;
         VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 121089d57802..248445f92604 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -8,21 +8,127 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 
+static inline pmd_t __pte_to_pmd(pte_t pte)
+{
+        int none, young, prot;
+        pmd_t pmd;
+
+        /*
+         * Convert encoding               pte bits        pmd bits
+         *                              .IR...wrdytp    ..R...I...y.
+         * empty                        .10...000000 -> ..0...1...0.
+         * prot-none, clean, old        .11...000001 -> ..0...1...1.
+         * prot-none, clean, young      .11...000101 -> ..1...1...1.
+         * prot-none, dirty, old        .10...001001 -> ..0...1...1.
+         * prot-none, dirty, young      .10...001101 -> ..1...1...1.
+         * read-only, clean, old        .11...010001 -> ..1...1...0.
+         * read-only, clean, young      .01...010101 -> ..1...0...1.
+         * read-only, dirty, old        .11...011001 -> ..1...1...0.
+         * read-only, dirty, young      .01...011101 -> ..1...0...1.
+         * read-write, clean, old       .11...110001 -> ..0...1...0.
+         * read-write, clean, young     .01...110101 -> ..0...0...1.
+         * read-write, dirty, old       .10...111001 -> ..0...1...0.
+         * read-write, dirty, young     .00...111101 -> ..0...0...1.
+         * Huge ptes are dirty by definition, a clean pte is made dirty
+         * by the conversion.
+         */
+        if (pte_present(pte)) {
+                pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
+                if (pte_val(pte) & _PAGE_INVALID)
+                        pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
+                none = (pte_val(pte) & _PAGE_PRESENT) &&
+                        !(pte_val(pte) & _PAGE_READ) &&
+                        !(pte_val(pte) & _PAGE_WRITE);
+                prot = (pte_val(pte) & _PAGE_PROTECT) &&
+                        !(pte_val(pte) & _PAGE_WRITE);
+                young = pte_val(pte) & _PAGE_YOUNG;
+                if (none || young)
+                        pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+                if (prot || (none && young))
+                        pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+        } else
+                pmd_val(pmd) = _SEGMENT_ENTRY_INVALID;
+        return pmd;
+}
+
+static inline pte_t __pmd_to_pte(pmd_t pmd)
+{
+        pte_t pte;
+
+        /*
+         * Convert encoding       pmd bits        pte bits
+         *                      ..R...I...y.    .IR...wrdytp
+         * empty                ..0...1...0. -> .10...000000
+         * prot-none, old       ..0...1...1. -> .10...001001
+         * prot-none, young     ..1...1...1. -> .10...001101
+         * read-only, old       ..1...1...0. -> .11...011001
+         * read-only, young     ..1...0...1. -> .01...011101
+         * read-write, old      ..0...1...0. -> .10...111001
+         * read-write, young    ..0...0...1. -> .00...111101
+         * Huge ptes are dirty by definition
+         */
+        if (pmd_present(pmd)) {
+                pte_val(pte) = _PAGE_PRESENT | _PAGE_LARGE | _PAGE_DIRTY |
+                        (pmd_val(pmd) & PAGE_MASK);
+                if (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID)
+                        pte_val(pte) |= _PAGE_INVALID;
+                if (pmd_prot_none(pmd)) {
+                        if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT)
+                                pte_val(pte) |= _PAGE_YOUNG;
+                } else {
+                        pte_val(pte) |= _PAGE_READ;
+                        if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT)
+                                pte_val(pte) |= _PAGE_PROTECT;
+                        else
+                                pte_val(pte) |= _PAGE_WRITE;
+                        if (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)
+                                pte_val(pte) |= _PAGE_YOUNG;
+                }
+        } else
+                pte_val(pte) = _PAGE_INVALID;
+        return pte;
+}
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-                                   pte_t *pteptr, pte_t pteval)
+                     pte_t *ptep, pte_t pte)
 {
-        pmd_t *pmdp = (pmd_t *) pteptr;
-        unsigned long mask;
+        pmd_t pmd;
 
+        pmd = __pte_to_pmd(pte);
         if (!MACHINE_HAS_HPAGE) {
-                pteptr = (pte_t *) pte_page(pteval)[1].index;
-                mask = pte_val(pteval) &
-                                (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
-                pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask;
+                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_t *) ptep = pmd;
+}
+
+pte_t huge_ptep_get(pte_t *ptep)
+{
+        unsigned long origin;
+        pmd_t pmd;
+
+        pmd = *(pmd_t *) ptep;
+        if (!MACHINE_HAS_HPAGE && pmd_present(pmd)) {
+                origin = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN;
+                pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
+                pmd_val(pmd) |= *(unsigned long *) origin;
         }
+        return __pmd_to_pte(pmd);
+}
 
-        pmd_val(*pmdp) = pte_val(pteval);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+                              unsigned long addr, pte_t *ptep)
+{
+        pmd_t *pmdp = (pmd_t *) ptep;
+        pte_t pte = huge_ptep_get(ptep);
+
+        if (MACHINE_HAS_IDTE)
+                __pmd_idte(addr, pmdp);
+        else
+                __pmd_csp(pmdp);
+        pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+        return pte;
 }
 
 int arch_prepare_hugepage(struct page *page)
@@ -58,7 +164,7 @@ void arch_release_hugepage(struct page *page)
         ptep = (pte_t *) page[1].index;
         if (!ptep)
                 return;
-        clear_table((unsigned long *) ptep, _PAGE_TYPE_EMPTY,
+        clear_table((unsigned long *) ptep, _PAGE_INVALID,
                     PTRS_PER_PTE * sizeof(pte_t));
         page_table_free(&init_mm, (unsigned long *) ptep);
         page[1].index = 0;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ce36ea80e4f9..ad446b0c55b6 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -69,6 +69,7 @@ static void __init setup_zero_pages(void)
                 order = 2;
                 break;
         case 0x2827:    /* zEC12 */
+        case 0x2828:    /* zEC12 */
         default:
                 order = 5;
                 break;
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 80adfbf75065..990397420e6b 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -118,7 +118,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
                 pte = pte_offset_kernel(pmd, address);
                 if (!enable) {
                         __ptep_ipte(address, pte);
-                        pte_val(*pte) = _PAGE_TYPE_EMPTY;
+                        pte_val(*pte) = _PAGE_INVALID;
                         continue;
                 }
                 pte_val(*pte) = __pa(address);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index a8154a1a2c94..6d16132d0850 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -161,7 +161,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table)
         struct gmap_rmap *rmap;
         struct page *page;
 
-        if (*table & _SEGMENT_ENTRY_INV)
+        if (*table & _SEGMENT_ENTRY_INVALID)
                 return 0;
         page = pfn_to_page(*table >> PAGE_SHIFT);
         mp = (struct gmap_pgtable *) page->index;
@@ -172,7 +172,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table)
                 kfree(rmap);
                 break;
         }
-        *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+        *table = mp->vmaddr | _SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_PROTECT;
         return 1;
 }
 
@@ -258,7 +258,7 @@ static int gmap_alloc_table(struct gmap *gmap,
                 return -ENOMEM;
         new = (unsigned long *) page_to_phys(page);
         crst_table_init(new, init);
-        if (*table & _REGION_ENTRY_INV) {
+        if (*table & _REGION_ENTRY_INVALID) {
                 list_add(&page->lru, &gmap->crst_list);
                 *table = (unsigned long) new | _REGION_ENTRY_LENGTH |
                         (*table & _REGION_ENTRY_TYPE_MASK);
@@ -292,22 +292,22 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
         for (off = 0; off < len; off += PMD_SIZE) {
                 /* Walk the guest addr space page table */
                 table = gmap->table + (((to + off) >> 53) & 0x7ff);
-                if (*table & _REGION_ENTRY_INV)
+                if (*table & _REGION_ENTRY_INVALID)
                         goto out;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + (((to + off) >> 42) & 0x7ff);
-                if (*table & _REGION_ENTRY_INV)
+                if (*table & _REGION_ENTRY_INVALID)
                         goto out;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + (((to + off) >> 31) & 0x7ff);
-                if (*table & _REGION_ENTRY_INV)
+                if (*table & _REGION_ENTRY_INVALID)
                         goto out;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + (((to + off) >> 20) & 0x7ff);
 
                 /* Clear segment table entry in guest address space. */
                 flush |= gmap_unlink_segment(gmap, table);
-                *table = _SEGMENT_ENTRY_INV;
+                *table = _SEGMENT_ENTRY_INVALID;
         }
 out:
         spin_unlock(&gmap->mm->page_table_lock);
@@ -345,17 +345,17 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
         for (off = 0; off < len; off += PMD_SIZE) {
                 /* Walk the gmap address space page table */
                 table = gmap->table + (((to + off) >> 53) & 0x7ff);
-                if ((*table & _REGION_ENTRY_INV) &&
+                if ((*table & _REGION_ENTRY_INVALID) &&
                     gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY))
                         goto out_unmap;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + (((to + off) >> 42) & 0x7ff);
-                if ((*table & _REGION_ENTRY_INV) &&
+                if ((*table & _REGION_ENTRY_INVALID) &&
                     gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY))
                         goto out_unmap;
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + (((to + off) >> 31) & 0x7ff);
-                if ((*table & _REGION_ENTRY_INV) &&
+                if ((*table & _REGION_ENTRY_INVALID) &&
                     gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY))
                         goto out_unmap;
                 table = (unsigned long *) (*table & _REGION_ENTRY_ORIGIN);
@@ -363,7 +363,8 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 
                 /* Store 'from' address in an invalid segment table entry. */
                 flush |= gmap_unlink_segment(gmap, table);
-                *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off);
+                *table =  (from + off) | (_SEGMENT_ENTRY_INVALID |
+                                          _SEGMENT_ENTRY_PROTECT);
         }
         spin_unlock(&gmap->mm->page_table_lock);
         up_read(&gmap->mm->mmap_sem);
@@ -384,15 +385,15 @@ static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap)
         unsigned long *table;
 
         table = gmap->table + ((address >> 53) & 0x7ff);
-        if (unlikely(*table & _REGION_ENTRY_INV))
+        if (unlikely(*table & _REGION_ENTRY_INVALID))
                 return ERR_PTR(-EFAULT);
         table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
         table = table + ((address >> 42) & 0x7ff);
-        if (unlikely(*table & _REGION_ENTRY_INV))
+        if (unlikely(*table & _REGION_ENTRY_INVALID))
                 return ERR_PTR(-EFAULT);
         table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
         table = table + ((address >> 31) & 0x7ff);
-        if (unlikely(*table & _REGION_ENTRY_INV))
+        if (unlikely(*table & _REGION_ENTRY_INVALID))
                 return ERR_PTR(-EFAULT);
         table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
         table = table + ((address >> 20) & 0x7ff);
@@ -422,11 +423,11 @@ unsigned long __gmap_translate(unsigned long address, struct gmap *gmap)
                 return PTR_ERR(segment_ptr);
         /* Convert the gmap address to an mm address. */
         segment = *segment_ptr;
-        if (!(segment & _SEGMENT_ENTRY_INV)) {
+        if (!(segment & _SEGMENT_ENTRY_INVALID)) {
                 page = pfn_to_page(segment >> PAGE_SHIFT);
                 mp = (struct gmap_pgtable *) page->index;
                 return mp->vmaddr | (address & ~PMD_MASK);
-        } else if (segment & _SEGMENT_ENTRY_RO) {
+        } else if (segment & _SEGMENT_ENTRY_PROTECT) {
                 vmaddr = segment & _SEGMENT_ENTRY_ORIGIN;
                 return vmaddr | (address & ~PMD_MASK);
         }
@@ -517,8 +518,8 @@ static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table)
         page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
         mp = (struct gmap_pgtable *) page->index;
         list_for_each_entry_safe(rmap, next, &mp->mapper, list) {
-                *rmap->entry =
-                        _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+                *rmap->entry = mp->vmaddr | (_SEGMENT_ENTRY_INVALID |
+                                             _SEGMENT_ENTRY_PROTECT);
                 list_del(&rmap->list);
                 kfree(rmap);
                 flush = 1;
@@ -545,13 +546,13 @@ unsigned long __gmap_fault(unsigned long address, struct gmap *gmap)
         /* Convert the gmap address to an mm address. */
         while (1) {
                 segment = *segment_ptr;
-                if (!(segment & _SEGMENT_ENTRY_INV)) {
+                if (!(segment & _SEGMENT_ENTRY_INVALID)) {
                         /* Page table is present */
                         page = pfn_to_page(segment >> PAGE_SHIFT);
                         mp = (struct gmap_pgtable *) page->index;
                         return mp->vmaddr | (address & ~PMD_MASK);
                 }
-                if (!(segment & _SEGMENT_ENTRY_RO))
+                if (!(segment & _SEGMENT_ENTRY_PROTECT))
                         /* Nothing mapped in the gmap address space. */
                         break;
                 rc = gmap_connect_pgtable(address, segment, segment_ptr, gmap);
@@ -586,25 +587,25 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap)
         while (address < to) {
                 /* Walk the gmap address space page table */
                 table = gmap->table + ((address >> 53) & 0x7ff);
-                if (unlikely(*table & _REGION_ENTRY_INV)) {
+                if (unlikely(*table & _REGION_ENTRY_INVALID)) {
                         address = (address + PMD_SIZE) & PMD_MASK;
                         continue;
                 }
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + ((address >> 42) & 0x7ff);
-                if (unlikely(*table & _REGION_ENTRY_INV)) {
+                if (unlikely(*table & _REGION_ENTRY_INVALID)) {
                         address = (address + PMD_SIZE) & PMD_MASK;
                         continue;
                 }
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + ((address >> 31) & 0x7ff);
-                if (unlikely(*table & _REGION_ENTRY_INV)) {
+                if (unlikely(*table & _REGION_ENTRY_INVALID)) {
                         address = (address + PMD_SIZE) & PMD_MASK;
                         continue;
                 }
                 table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
                 table = table + ((address >> 20) & 0x7ff);
-                if (unlikely(*table & _SEGMENT_ENTRY_INV)) {
+                if (unlikely(*table & _SEGMENT_ENTRY_INVALID)) {
                         address = (address + PMD_SIZE) & PMD_MASK;
                         continue;
                 }
@@ -687,7 +688,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long start, unsigned long len)
                         continue;
                 /* Set notification bit in the pgste of the pte */
                 entry = *ptep;
-                if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_RO)) == 0) {
+                if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
                         pgste = pgste_get_lock(ptep);
                         pgste_val(pgste) |= PGSTE_IN_BIT;
                         pgste_set_unlock(ptep, pgste);
@@ -752,8 +753,9 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
         page->index = (unsigned long) mp;
         atomic_set(&page->_mapcount, 3);
         table = (unsigned long *) page_to_phys(page);
-        clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
-        clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+        clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+        clear_table(table + PTRS_PER_PTE, PGSTE_HR_BIT | PGSTE_HC_BIT,
+                    PAGE_SIZE/2);
         return table;
 }
 
@@ -791,26 +793,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
         pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
         pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
         if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-                unsigned long address, bits;
-                unsigned char skey;
+                unsigned long address, bits, skey;
 
                 address = pte_val(*ptep) & PAGE_MASK;
-                skey = page_get_storage_key(address);
+                skey = (unsigned long) page_get_storage_key(address);
                 bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
+                skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
                 /* Set storage key ACC and FP */
-                page_set_storage_key(address,
-                                (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)),
-                                !nq);
-
+                page_set_storage_key(address, skey, !nq);
                 /* Merge host changed & referenced into pgste  */
                 pgste_val(new) |= bits << 52;
-                /* Transfer skey changed & referenced bit to kvm user bits */
-                pgste_val(new) |= bits << 45;   /* PGSTE_UR_BIT & PGSTE_UC_BIT */
         }
         /* changing the guest storage key is considered a change of the page */
         if ((pgste_val(new) ^ pgste_val(old)) &
             (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
-                pgste_val(new) |= PGSTE_UC_BIT;
+                pgste_val(new) |= PGSTE_HC_BIT;
 
         pgste_set_unlock(ptep, new);
         pte_unmap_unlock(*ptep, ptl);
@@ -878,7 +875,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr)
                 pgtable_page_ctor(page);
                 atomic_set(&page->_mapcount, 1);
                 table = (unsigned long *) page_to_phys(page);
-                clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+                clear_table(table, _PAGE_INVALID, PAGE_SIZE);
                 spin_lock_bh(&mm->context.list_lock);
                 list_add(&page->lru, &mm->context.pgtable_list);
         } else {
@@ -1007,7 +1004,6 @@ void tlb_table_flush(struct mmu_gather *tlb)
         struct mmu_table_batch **batch = &tlb->batch;
 
         if (*batch) {
-                __tlb_flush_mm(tlb->mm);
                 call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
                 *batch = NULL;
         }
@@ -1017,11 +1013,12 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
         struct mmu_table_batch **batch = &tlb->batch;
 
+        tlb->mm->context.flush_mm = 1;
         if (*batch == NULL) {
                 *batch = (struct mmu_table_batch *)
                         __get_free_page(GFP_NOWAIT | __GFP_NOWARN);
                 if (*batch == NULL) {
-                        __tlb_flush_mm(tlb->mm);
+                        __tlb_flush_mm_lazy(tlb->mm);
                         tlb_remove_table_one(table);
                         return;
                 }
@@ -1029,7 +1026,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
         }
         (*batch)->tables[(*batch)->nr++] = table;
         if ((*batch)->nr == MAX_TABLE_BATCH)
-                tlb_table_flush(tlb);
+                tlb_flush_mmu(tlb);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -1198,9 +1195,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
                 list_del(lh);
         }
         ptep = (pte_t *) pgtable;
-        pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+        pte_val(*ptep) = _PAGE_INVALID;
         ptep++;
-        pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+        pte_val(*ptep) = _PAGE_INVALID;
         return pgtable;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 8b268fcc4612..bcfb70b60be6 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -69,7 +69,7 @@ static pte_t __ref *vmem_pte_alloc(unsigned long address)
                 pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
         if (!pte)
                 return NULL;
-        clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY,
+        clear_table((unsigned long *) pte, _PAGE_INVALID,
                     PTRS_PER_PTE * sizeof(pte_t));
         return pte;
 }
@@ -101,7 +101,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
                     !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) {
                         pud_val(*pu_dir) = __pa(address) |
                                 _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE |
-                                (ro ? _REGION_ENTRY_RO : 0);
+                                (ro ? _REGION_ENTRY_PROTECT : 0);
                         address += PUD_SIZE;
                         continue;
                 }
@@ -118,7 +118,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
                     !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) {
                         pmd_val(*pm_dir) = __pa(address) |
                                 _SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
-                                (ro ? _SEGMENT_ENTRY_RO : 0);
+                                _SEGMENT_ENTRY_YOUNG |
+                                (ro ? _SEGMENT_ENTRY_PROTECT : 0);
                         address += PMD_SIZE;
                         continue;
                 }
@@ -131,7 +132,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
                 }
 
                 pt_dir = pte_offset_kernel(pm_dir, address);
-                pte_val(*pt_dir) = __pa(address) | (ro ? _PAGE_RO : 0);
+                pte_val(*pt_dir) = __pa(address) |
+                        pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL);
                 address += PAGE_SIZE;
         }
         ret = 0;
@@ -154,7 +156,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
         pte_t *pt_dir;
         pte_t  pte;
 
-        pte_val(pte) = _PAGE_TYPE_EMPTY;
+        pte_val(pte) = _PAGE_INVALID;
         while (address < end) {
                 pg_dir = pgd_offset_k(address);
                 if (pgd_none(*pg_dir)) {
@@ -255,7 +257,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
                         new_page =__pa(vmem_alloc_pages(0));
                         if (!new_page)
                                 goto out;
-                        pte_val(*pt_dir) = __pa(new_page);
+                        pte_val(*pt_dir) =
+                                __pa(new_page) | pgprot_val(PAGE_KERNEL);
                 }
                 address += PAGE_SIZE;
         }
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index ffeb17ce7f31..930783d2c99b 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -440,7 +440,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
                 switch (id.machine) {
                 case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
                 case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
-                case 0x2827:              ops->cpu_type = "s390/zEC12"; break;
+                case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
                 default: return -ENODEV;
                 }
         }
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 086a2e37935d..a9e1dc4ae442 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -2,5 +2,5 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)       += pci.o pci_dma.o pci_clp.o pci_msi.o pci_sysfs.o \
+obj-$(CONFIG_PCI)       += pci.o pci_dma.o pci_clp.o pci_sysfs.o \
                            pci_event.o pci_debug.o pci_insn.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index e2956ad39a4f..f17a8343e360 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -42,45 +42,26 @@
 #define SIC_IRQ_MODE_SINGLE             1
 
 #define ZPCI_NR_DMA_SPACES              1
-#define ZPCI_MSI_VEC_BITS               6
 #define ZPCI_NR_DEVICES                 CONFIG_PCI_NR_FUNCTIONS
 
 /* list of all detected zpci devices */
-LIST_HEAD(zpci_list);
-EXPORT_SYMBOL_GPL(zpci_list);
-DEFINE_MUTEX(zpci_list_lock);
-EXPORT_SYMBOL_GPL(zpci_list_lock);
+static LIST_HEAD(zpci_list);
+static DEFINE_SPINLOCK(zpci_list_lock);
 
-static struct pci_hp_callback_ops *hotplug_ops;
+static void zpci_enable_irq(struct irq_data *data);
+static void zpci_disable_irq(struct irq_data *data);
 
-static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
-static DEFINE_SPINLOCK(zpci_domain_lock);
-
-struct callback {
-        irq_handler_t   handler;
-        void            *data;
+static struct irq_chip zpci_irq_chip = {
+        .name = "zPCI",
+        .irq_unmask = zpci_enable_irq,
+        .irq_mask = zpci_disable_irq,
 };
 
-struct zdev_irq_map {
-        unsigned long   aibv;           /* AI bit vector */
-        int             msi_vecs;       /* consecutive MSI-vectors used */
-        int             __unused;
-        struct callback cb[ZPCI_NR_MSI_VECS]; /* callback handler array */
-        spinlock_t      lock;           /* protect callbacks against de-reg */
-};
-
-struct intr_bucket {
-        /* amap of adapters, one bit per dev, corresponds to one irq nr */
-        unsigned long   *alloc;
-        /* AI summary bit, global page for all devices */
-        unsigned long   *aisb;
-        /* pointer to aibv and callback data in zdev */
-        struct zdev_irq_map *imap[ZPCI_NR_DEVICES];
-        /* protects the whole bucket struct */
-        spinlock_t      lock;
-};
+static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
+static DEFINE_SPINLOCK(zpci_domain_lock);
 
-static struct intr_bucket *bucket;
+static struct airq_iv *zpci_aisb_iv;
+static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
 
 /* Adapter interrupt definitions */
 static void zpci_irq_handler(struct airq_struct *airq);
@@ -96,27 +77,8 @@ static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
-/* highest irq summary bit */
-static int __read_mostly aisb_max;
-
-static struct kmem_cache *zdev_irq_cache;
 static struct kmem_cache *zdev_fmb_cache;
 
-static inline int irq_to_msi_nr(unsigned int irq)
-{
-        return irq & ZPCI_MSI_MASK;
-}
-
-static inline int irq_to_dev_nr(unsigned int irq)
-{
-        return irq >> ZPCI_MSI_VEC_BITS;
-}
-
-static inline struct zdev_irq_map *get_imap(unsigned int irq)
-{
-        return bucket->imap[irq_to_dev_nr(irq)];
-}
-
 struct zpci_dev *get_zdev(struct pci_dev *pdev)
 {
         return (struct zpci_dev *) pdev->sysdata;
@@ -126,22 +88,17 @@ struct zpci_dev *get_zdev_by_fid(u32 fid)
 {
         struct zpci_dev *tmp, *zdev = NULL;
 
-        mutex_lock(&zpci_list_lock);
+        spin_lock(&zpci_list_lock);
         list_for_each_entry(tmp, &zpci_list, entry) {
                 if (tmp->fid == fid) {
                         zdev = tmp;
                         break;
                 }
         }
-        mutex_unlock(&zpci_list_lock);
+        spin_unlock(&zpci_list_lock);
         return zdev;
 }
 
-bool zpci_fid_present(u32 fid)
-{
-        return (get_zdev_by_fid(fid) != NULL) ? true : false;
-}
-
 static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus)
 {
         return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL;
@@ -160,8 +117,7 @@ int pci_proc_domain(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_proc_domain);
 
 /* Modify PCI: Register adapter interruptions */
-static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
-                              u64 aibv)
+static int zpci_set_airq(struct zpci_dev *zdev)
 {
         u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
         struct zpci_fib *fib;
@@ -172,14 +128,14 @@ static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
                 return -ENOMEM;
 
         fib->isc = PCI_ISC;
-        fib->noi = zdev->irq_map->msi_vecs;
         fib->sum = 1;           /* enable summary notifications */
-        fib->aibv = aibv;
-        fib->aibvo = 0;         /* every function has its own page */
-        fib->aisb = (u64) bucket->aisb + aisb / 8;
-        fib->aisbo = aisb & ZPCI_MSI_MASK;
+        fib->noi = airq_iv_end(zdev->aibv);
+        fib->aibv = (unsigned long) zdev->aibv->vector;
+        fib->aibvo = 0;         /* each zdev has its own interrupt vector */
+        fib->aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
+        fib->aisbo = zdev->aisb & 63;
 
-        rc = s390pci_mod_fc(req, fib);
+        rc = zpci_mod_fc(req, fib);
         pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi);
 
         free_page((unsigned long) fib);
@@ -209,7 +165,7 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args
         fib->iota = args->iota;
         fib->fmb_addr = args->fmb_addr;
 
-        rc = s390pci_mod_fc(req, fib);
+        rc = zpci_mod_fc(req, fib);
         free_page((unsigned long) fib);
         return rc;
 }
@@ -234,7 +190,7 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
 }
 
 /* Modify PCI: Unregister adapter interruptions */
-static int zpci_unregister_airq(struct zpci_dev *zdev)
+static int zpci_clear_airq(struct zpci_dev *zdev)
 {
         struct mod_pci_args args = { 0, 0, 0, 0 };
 
@@ -283,7 +239,7 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
         u64 data;
         int rc;
 
-        rc = s390pci_load(&data, req, offset);
+        rc = zpci_load(&data, req, offset);
         if (!rc) {
                 data = data << ((8 - len) * 8);
                 data = le64_to_cpu(data);
@@ -301,25 +257,46 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 
         data = cpu_to_le64(data);
         data = data >> ((8 - len) * 8);
-        rc = s390pci_store(data, req, offset);
+        rc = zpci_store(data, req, offset);
         return rc;
 }
 
-void enable_irq(unsigned int irq)
+static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
+{
+        int offset, pos;
+        u32 mask_bits;
+
+        if (msi->msi_attrib.is_msix) {
+                offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+                        PCI_MSIX_ENTRY_VECTOR_CTRL;
+                msi->masked = readl(msi->mask_base + offset);
+                writel(flag, msi->mask_base + offset);
+        } else if (msi->msi_attrib.maskbit) {
+                pos = (long) msi->mask_base;
+                pci_read_config_dword(msi->dev, pos, &mask_bits);
+                mask_bits &= ~(mask);
+                mask_bits |= flag & mask;
+                pci_write_config_dword(msi->dev, pos, mask_bits);
+        } else
+                return 0;
+
+        msi->msi_attrib.maskbit = !!flag;
+        return 1;
+}
+
+static void zpci_enable_irq(struct irq_data *data)
 {
-        struct msi_desc *msi = irq_get_msi_desc(irq);
+        struct msi_desc *msi = irq_get_msi_desc(data->irq);
 
         zpci_msi_set_mask_bits(msi, 1, 0);
 }
-EXPORT_SYMBOL_GPL(enable_irq);
 
-void disable_irq(unsigned int irq)
+static void zpci_disable_irq(struct irq_data *data)
 {
-        struct msi_desc *msi = irq_get_msi_desc(irq);
+        struct msi_desc *msi = irq_get_msi_desc(data->irq);
 
         zpci_msi_set_mask_bits(msi, 1, 1);
 }
-EXPORT_SYMBOL_GPL(disable_irq);
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
@@ -404,152 +381,147 @@ static struct pci_ops pci_root_ops = {
         .write = pci_write,
 };
 
-/* store the last handled bit to implement fair scheduling of devices */
-static DEFINE_PER_CPU(unsigned long, next_sbit);
-
 static void zpci_irq_handler(struct airq_struct *airq)
 {
-        unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit);
-        int rescan = 0, max = aisb_max;
-        struct zdev_irq_map *imap;
+        unsigned long si, ai;
+        struct airq_iv *aibv;
+        int irqs_on = 0;
 
         inc_irq_stat(IRQIO_PCI);
-        sbit = start;
-
-scan:
-        /* find summary_bit */
-        for_each_set_bit_left_cont(sbit, bucket->aisb, max) {
-                clear_bit(63 - (sbit & 63), bucket->aisb + (sbit >> 6));
-                last = sbit;
+        for (si = 0;;) {
+                /* Scan adapter summary indicator bit vector */
+                si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv));
+                if (si == -1UL) {
+                        if (irqs_on++)
+                                /* End of second scan with interrupts on. */
+                                break;
+                        /* First scan complete, reenable interrupts. */
+                        zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+                        si = 0;
+                        continue;
+                }
 
-                /* find vector bit */
-                imap = bucket->imap[sbit];
-                for_each_set_bit_left(mbit, &imap->aibv, imap->msi_vecs) {
+                /* Scan the adapter interrupt vector for this device. */
+                aibv = zpci_aibv[si];
+                for (ai = 0;;) {
+                        ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
+                        if (ai == -1UL)
+                                break;
                         inc_irq_stat(IRQIO_MSI);
-                        clear_bit(63 - mbit, &imap->aibv);
-
-                        spin_lock(&imap->lock);
-                        if (imap->cb[mbit].handler)
-                                imap->cb[mbit].handler(mbit,
-                                        imap->cb[mbit].data);
-                        spin_unlock(&imap->lock);
+                        airq_iv_lock(aibv, ai);
+                        generic_handle_irq(airq_iv_get_data(aibv, ai));
+                        airq_iv_unlock(aibv, ai);
                 }
         }
-
-        if (rescan)
-                goto out;
-
-        /* scan the skipped bits */
-        if (start > 0) {
-                sbit = 0;
-                max = start;
-                start = 0;
-                goto scan;
-        }
-
-        /* enable interrupts again */
-        set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
-
-        /* check again to not lose initiative */
-        rmb();
-        max = aisb_max;
-        sbit = find_first_bit_left(bucket->aisb, max);
-        if (sbit != max) {
-                rescan++;
-                goto scan;
-        }
-out:
-        /* store next device bit to scan */
-        __get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last;
 }
 
-/* msi_vecs - number of requested interrupts, 0 place function to error state */
-static int zpci_setup_msi(struct pci_dev *pdev, int msi_vecs)
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
         struct zpci_dev *zdev = get_zdev(pdev);
-        unsigned int aisb, msi_nr;
+        unsigned int hwirq, irq, msi_vecs;
+        unsigned long aisb;
         struct msi_desc *msi;
+        struct msi_msg msg;
         int rc;
 
-        /* store the number of used MSI vectors */
-        zdev->irq_map->msi_vecs = min(msi_vecs, ZPCI_NR_MSI_VECS);
-
-        spin_lock(&bucket->lock);
-        aisb = find_first_zero_bit(bucket->alloc, PAGE_SIZE);
-        /* alloc map exhausted? */
-        if (aisb == PAGE_SIZE) {
-                spin_unlock(&bucket->lock);
-                return -EIO;
-        }
-        set_bit(aisb, bucket->alloc);
-        spin_unlock(&bucket->lock);
+        pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec);
+        if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
+                return -EINVAL;
+        msi_vecs = min(nvec, ZPCI_MSI_VEC_MAX);
+        msi_vecs = min_t(unsigned int, msi_vecs, CONFIG_PCI_NR_MSI);
 
+        /* Allocate adapter summary indicator bit */
+        rc = -EIO;
+        aisb = airq_iv_alloc_bit(zpci_aisb_iv);
+        if (aisb == -1UL)
+                goto out;
         zdev->aisb = aisb;
-        if (aisb + 1 > aisb_max)
-                aisb_max = aisb + 1;
 
-        /* wire up IRQ shortcut pointer */
-        bucket->imap[zdev->aisb] = zdev->irq_map;
-        pr_debug("%s: imap[%u] linked to %p\n", __func__, zdev->aisb, zdev->irq_map);
+        /* Create adapter interrupt vector */
+        rc = -ENOMEM;
+        zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+        if (!zdev->aibv)
+                goto out_si;
 
-        /* TODO: irq number 0 wont be found if we return less than requested MSIs.
-         * ignore it for now and fix in common code.
-         */
-        msi_nr = aisb << ZPCI_MSI_VEC_BITS;
+        /* Wire up shortcut pointer */
+        zpci_aibv[aisb] = zdev->aibv;
 
+        /* Request MSI interrupts */
+        hwirq = 0;
         list_for_each_entry(msi, &pdev->msi_list, list) {
-                rc = zpci_setup_msi_irq(zdev, msi, msi_nr,
-                                          aisb << ZPCI_MSI_VEC_BITS);
+                rc = -EIO;
+                irq = irq_alloc_desc(0);        /* Alloc irq on node 0 */
+                if (irq == NO_IRQ)
+                        goto out_msi;
+                rc = irq_set_msi_desc(irq, msi);
                 if (rc)
-                        return rc;
-                msi_nr++;
+                        goto out_msi;
+                irq_set_chip_and_handler(irq, &zpci_irq_chip,
+                                         handle_simple_irq);
+                msg.data = hwirq;
+                msg.address_lo = zdev->msi_addr & 0xffffffff;
+                msg.address_hi = zdev->msi_addr >> 32;
+                write_msi_msg(irq, &msg);
+                airq_iv_set_data(zdev->aibv, hwirq, irq);
+                hwirq++;
         }
 
-        rc = zpci_register_airq(zdev, aisb, (u64) &zdev->irq_map->aibv);
-        if (rc) {
-                clear_bit(aisb, bucket->alloc);
-                dev_err(&pdev->dev, "register MSI failed with: %d\n", rc);
-                return rc;
+        /* Enable adapter interrupts */
+        rc = zpci_set_airq(zdev);
+        if (rc)
+                goto out_msi;
+
+        return (msi_vecs == nvec) ? 0 : msi_vecs;
+
+out_msi:
+        list_for_each_entry(msi, &pdev->msi_list, list) {
+                if (hwirq-- == 0)
+                        break;
+                irq_set_msi_desc(msi->irq, NULL);
+                irq_free_desc(msi->irq);
+                msi->msg.address_lo = 0;
+                msi->msg.address_hi = 0;
+                msi->msg.data = 0;
+                msi->irq = 0;
         }
-        return (zdev->irq_map->msi_vecs == msi_vecs) ?
-                0 : zdev->irq_map->msi_vecs;
+        zpci_aibv[aisb] = NULL;
+        airq_iv_release(zdev->aibv);
+out_si:
+        airq_iv_free_bit(zpci_aisb_iv, aisb);
+out:
+        dev_err(&pdev->dev, "register MSI failed with: %d\n", rc);
+        return rc;
 }
 
-static void zpci_teardown_msi(struct pci_dev *pdev)
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
 {
         struct zpci_dev *zdev = get_zdev(pdev);
         struct msi_desc *msi;
-        int aisb, rc;
+        int rc;
 
-        rc = zpci_unregister_airq(zdev);
+        pr_info("%s: on pdev: %p\n", __func__, pdev);
+
+        /* Disable adapter interrupts */
+        rc = zpci_clear_airq(zdev);
         if (rc) {
                 dev_err(&pdev->dev, "deregister MSI failed with: %d\n", rc);
                 return;
         }
 
-        msi = list_first_entry(&pdev->msi_list, struct msi_desc, list);
-        aisb = irq_to_dev_nr(msi->irq);
-
-        list_for_each_entry(msi, &pdev->msi_list, list)
-                zpci_teardown_msi_irq(zdev, msi);
-
-        clear_bit(aisb, bucket->alloc);
-        if (aisb + 1 == aisb_max)
-                aisb_max--;
-}
-
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
-{
-        pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec);
-        if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
-                return -EINVAL;
-        return zpci_setup_msi(pdev, nvec);
-}
+        /* Release MSI interrupts */
+        list_for_each_entry(msi, &pdev->msi_list, list) {
+                zpci_msi_set_mask_bits(msi, 1, 1);
+                irq_set_msi_desc(msi->irq, NULL);
+                irq_free_desc(msi->irq);
+                msi->msg.address_lo = 0;
+                msi->msg.address_hi = 0;
+                msi->msg.data = 0;
+                msi->irq = 0;
+        }
 
-void arch_teardown_msi_irqs(struct pci_dev *pdev)
-{
-        pr_info("%s: on pdev: %p\n", __func__, pdev);
-        zpci_teardown_msi(pdev);
+        zpci_aibv[zdev->aisb] = NULL;
+        airq_iv_release(zdev->aibv);
+        airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
 }
 
 static void zpci_map_resources(struct zpci_dev *zdev)
@@ -564,8 +536,6 @@ static void zpci_map_resources(struct zpci_dev *zdev)
                         continue;
                 pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0);
                 pdev->resource[i].end = pdev->resource[i].start + len - 1;
-                pr_debug("BAR%i: -> start: %Lx  end: %Lx\n",
-                        i, pdev->resource[i].start, pdev->resource[i].end);
         }
 }
 
@@ -589,162 +559,47 @@ struct zpci_dev *zpci_alloc_device(void)
 
         /* Alloc memory for our private pci device data */
         zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
-        if (!zdev)
-                return ERR_PTR(-ENOMEM);
-
-        /* Alloc aibv & callback space */
-        zdev->irq_map = kmem_cache_zalloc(zdev_irq_cache, GFP_KERNEL);
-        if (!zdev->irq_map)
-                goto error;
-        WARN_ON((u64) zdev->irq_map & 0xff);
-        return zdev;
-
-error:
-        kfree(zdev);
-        return ERR_PTR(-ENOMEM);
+        return zdev ? : ERR_PTR(-ENOMEM);
 }
 
 void zpci_free_device(struct zpci_dev *zdev)
 {
-        kmem_cache_free(zdev_irq_cache, zdev->irq_map);
         kfree(zdev);
 }
 
-/*
- * Too late for any s390 specific setup, since interrupts must be set up
- * already which requires DMA setup too and the pci scan will access the
- * config space, which only works if the function handle is enabled.
- */
-int pcibios_enable_device(struct pci_dev *pdev, int mask)
-{
-        struct resource *res;
-        u16 cmd;
-        int i;
-
-        pci_read_config_word(pdev, PCI_COMMAND, &cmd);
-
-        for (i = 0; i < PCI_BAR_COUNT; i++) {
-                res = &pdev->resource[i];
-
-                if (res->flags & IORESOURCE_IO)
-                        return -EINVAL;
-
-                if (res->flags & IORESOURCE_MEM)
-                        cmd |= PCI_COMMAND_MEMORY;
-        }
-        pci_write_config_word(pdev, PCI_COMMAND, cmd);
-        return 0;
-}
-
 int pcibios_add_platform_entries(struct pci_dev *pdev)
 {
         return zpci_sysfs_add_device(&pdev->dev);
 }
 
-int zpci_request_irq(unsigned int irq, irq_handler_t handler, void *data)
-{
-        int msi_nr = irq_to_msi_nr(irq);
-        struct zdev_irq_map *imap;
-        struct msi_desc *msi;
-
-        msi = irq_get_msi_desc(irq);
-        if (!msi)
-                return -EIO;
-
-        imap = get_imap(irq);
-        spin_lock_init(&imap->lock);
-
-        pr_debug("%s: register handler for IRQ:MSI %d:%d\n", __func__, irq >> 6, msi_nr);
-        imap->cb[msi_nr].handler = handler;
-        imap->cb[msi_nr].data = data;
-
-        /*
-         * The generic MSI code returns with the interrupt disabled on the
-         * card, using the MSI mask bits. Firmware doesn't appear to unmask
-         * at that level, so we do it here by hand.
-         */
-        zpci_msi_set_mask_bits(msi, 1, 0);
-        return 0;
-}
-
-void zpci_free_irq(unsigned int irq)
-{
-        struct zdev_irq_map *imap = get_imap(irq);
-        int msi_nr = irq_to_msi_nr(irq);
-        unsigned long flags;
-
-        pr_debug("%s: for irq: %d\n", __func__, irq);
-
-        spin_lock_irqsave(&imap->lock, flags);
-        imap->cb[msi_nr].handler = NULL;
-        imap->cb[msi_nr].data = NULL;
-        spin_unlock_irqrestore(&imap->lock, flags);
-}
-
-int request_irq(unsigned int irq, irq_handler_t handler,
-                unsigned long irqflags, const char *devname, void *dev_id)
-{
-        pr_debug("%s: irq: %d  handler: %p  flags: %lx  dev: %s\n",
-                __func__, irq, handler, irqflags, devname);
-
-        return zpci_request_irq(irq, handler, dev_id);
-}
-EXPORT_SYMBOL_GPL(request_irq);
-
-void free_irq(unsigned int irq, void *dev_id)
-{
-        zpci_free_irq(irq);
-}
-EXPORT_SYMBOL_GPL(free_irq);
-
 static int __init zpci_irq_init(void)
 {
-        int cpu, rc;
-
-        bucket = kzalloc(sizeof(*bucket), GFP_KERNEL);
-        if (!bucket)
-                return -ENOMEM;
-
-        bucket->aisb = (unsigned long *) get_zeroed_page(GFP_KERNEL);
-        if (!bucket->aisb) {
-                rc = -ENOMEM;
-                goto out_aisb;
-        }
-
-        bucket->alloc = (unsigned long *) get_zeroed_page(GFP_KERNEL);
-        if (!bucket->alloc) {
-                rc = -ENOMEM;
-                goto out_alloc;
-        }
+        int rc;
 
         rc = register_adapter_interrupt(&zpci_airq);
         if (rc)
-                goto out_ai;
+                goto out;
         /* Set summary to 1 to be called every time for the ISC. */
         *zpci_airq.lsi_ptr = 1;
 
-        for_each_online_cpu(cpu)
-                per_cpu(next_sbit, cpu) = 0;
+        rc = -ENOMEM;
+        zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+        if (!zpci_aisb_iv)
+                goto out_airq;
 
-        spin_lock_init(&bucket->lock);
-        set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+        zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
         return 0;
 
-out_ai:
-        free_page((unsigned long) bucket->alloc);
-out_alloc:
-        free_page((unsigned long) bucket->aisb);
-out_aisb:
-        kfree(bucket);
+out_airq:
+        unregister_adapter_interrupt(&zpci_airq);
+out:
         return rc;
 }
 
 static void zpci_irq_exit(void)
 {
-        free_page((unsigned long) bucket->alloc);
-        free_page((unsigned long) bucket->aisb);
+        airq_iv_release(zpci_aisb_iv);
         unregister_adapter_interrupt(&zpci_airq);
-        kfree(bucket);
 }
 
 static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size,
@@ -801,16 +656,49 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 int pcibios_add_device(struct pci_dev *pdev)
 {
         struct zpci_dev *zdev = get_zdev(pdev);
+        struct resource *res;
+        int i;
+
+        zdev->pdev = pdev;
+        zpci_map_resources(zdev);
+
+        for (i = 0; i < PCI_BAR_COUNT; i++) {
+                res = &pdev->resource[i];
+                if (res->parent || !res->flags)
+                        continue;
+                pci_claim_resource(pdev, i);
+        }
+
+        return 0;
+}
+
+int pcibios_enable_device(struct pci_dev *pdev, int mask)
+{
+        struct zpci_dev *zdev = get_zdev(pdev);
+        struct resource *res;
+        u16 cmd;
+        int i;
 
         zdev->pdev = pdev;
         zpci_debug_init_device(zdev);
         zpci_fmb_enable_device(zdev);
         zpci_map_resources(zdev);
 
+        pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+        for (i = 0; i < PCI_BAR_COUNT; i++) {
+                res = &pdev->resource[i];
+
+                if (res->flags & IORESOURCE_IO)
+                        return -EINVAL;
+
+                if (res->flags & IORESOURCE_MEM)
+                        cmd |= PCI_COMMAND_MEMORY;
+        }
+        pci_write_config_word(pdev, PCI_COMMAND, cmd);
         return 0;
 }
 
-void pcibios_release_device(struct pci_dev *pdev)
+void pcibios_disable_device(struct pci_dev *pdev)
 {
         struct zpci_dev *zdev = get_zdev(pdev);
 
@@ -898,6 +786,8 @@ int zpci_enable_device(struct zpci_dev *zdev)
         rc = zpci_dma_init_device(zdev);
         if (rc)
                 goto out_dma;
+
+        zdev->state = ZPCI_FN_STATE_ONLINE;
         return 0;
 
 out_dma:
@@ -926,18 +816,16 @@ int zpci_create_device(struct zpci_dev *zdev)
                 rc = zpci_enable_device(zdev);
                 if (rc)
                         goto out_free;
-
-                zdev->state = ZPCI_FN_STATE_ONLINE;
         }
         rc = zpci_scan_bus(zdev);
         if (rc)
                 goto out_disable;
 
-        mutex_lock(&zpci_list_lock);
+        spin_lock(&zpci_list_lock);
         list_add_tail(&zdev->entry, &zpci_list);
-        if (hotplug_ops)
-                hotplug_ops->create_slot(zdev);
-        mutex_unlock(&zpci_list_lock);
+        spin_unlock(&zpci_list_lock);
+
+        zpci_init_slot(zdev);
 
         return 0;
 
@@ -967,15 +855,10 @@ static inline int barsize(u8 size)
 
 static int zpci_mem_init(void)
 {
-        zdev_irq_cache = kmem_cache_create("PCI_IRQ_cache", sizeof(struct zdev_irq_map),
-                                L1_CACHE_BYTES, SLAB_HWCACHE_ALIGN, NULL);
-        if (!zdev_irq_cache)
-                goto error_zdev;
-
         zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
                                 16, 0, NULL);
         if (!zdev_fmb_cache)
-                goto error_fmb;
+                goto error_zdev;
 
         /* TODO: use realloc */
         zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
@@ -986,8 +869,6 @@ static int zpci_mem_init(void)
 
 error_iomap:
         kmem_cache_destroy(zdev_fmb_cache);
-error_fmb:
-        kmem_cache_destroy(zdev_irq_cache);
 error_zdev:
         return -ENOMEM;
 }
@@ -995,28 +876,10 @@ error_zdev:
 static void zpci_mem_exit(void)
 {
         kfree(zpci_iomap_start);
-        kmem_cache_destroy(zdev_irq_cache);
         kmem_cache_destroy(zdev_fmb_cache);
 }
 
-void zpci_register_hp_ops(struct pci_hp_callback_ops *ops)
-{
-        mutex_lock(&zpci_list_lock);
-        hotplug_ops = ops;
-        mutex_unlock(&zpci_list_lock);
-}
-EXPORT_SYMBOL_GPL(zpci_register_hp_ops);
-
-void zpci_deregister_hp_ops(void)
-{
-        mutex_lock(&zpci_list_lock);
-        hotplug_ops = NULL;
-        mutex_unlock(&zpci_list_lock);
-}
-EXPORT_SYMBOL_GPL(zpci_deregister_hp_ops);
-
-unsigned int s390_pci_probe;
-EXPORT_SYMBOL_GPL(s390_pci_probe);
+static unsigned int s390_pci_probe;
 
 char * __init pcibios_setup(char *str)
 {
@@ -1044,16 +907,12 @@ static int __init pci_base_init(void)
 
         rc = zpci_debug_init();
         if (rc)
-                return rc;
+                goto out;
 
         rc = zpci_mem_init();
         if (rc)
                 goto out_mem;
 
-        rc = zpci_msihash_init();
-        if (rc)
-                goto out_hash;
-
         rc = zpci_irq_init();
         if (rc)
                 goto out_irq;
@@ -1062,7 +921,7 @@ static int __init pci_base_init(void)
         if (rc)
                 goto out_dma;
 
-        rc = clp_find_pci_devices();
+        rc = clp_scan_pci_devices();
         if (rc)
                 goto out_find;
 
@@ -1073,11 +932,15 @@ out_find:
 out_dma:
         zpci_irq_exit();
 out_irq:
-        zpci_msihash_exit();
-out_hash:
         zpci_mem_exit();
 out_mem:
         zpci_debug_exit();
+out:
         return rc;
 }
-subsys_initcall(pci_base_init);
+subsys_initcall_sync(pci_base_init);
+
+void zpci_rescan(void)
+{
+        clp_rescan_pci_devices_simple();
+}
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 2e9539625d93..475563c3d1e4 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -36,9 +36,9 @@ static inline u8 clp_instr(void *data)
         return cc;
 }
 
-static void *clp_alloc_block(void)
+static void *clp_alloc_block(gfp_t gfp_mask)
 {
-        return (void *) __get_free_pages(GFP_KERNEL, get_order(CLP_BLK_SIZE));
+        return (void *) __get_free_pages(gfp_mask, get_order(CLP_BLK_SIZE));
 }
 
 static void clp_free_block(void *ptr)
@@ -70,7 +70,7 @@ static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid)
         struct clp_req_rsp_query_pci_grp *rrb;
         int rc;
 
-        rrb = clp_alloc_block();
+        rrb = clp_alloc_block(GFP_KERNEL);
         if (!rrb)
                 return -ENOMEM;
 
@@ -113,7 +113,7 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh)
         struct clp_req_rsp_query_pci *rrb;
         int rc;
 
-        rrb = clp_alloc_block();
+        rrb = clp_alloc_block(GFP_KERNEL);
         if (!rrb)
                 return -ENOMEM;
 
@@ -179,9 +179,9 @@ error:
 static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 {
         struct clp_req_rsp_set_pci *rrb;
-        int rc, retries = 1000;
+        int rc, retries = 100;
 
-        rrb = clp_alloc_block();
+        rrb = clp_alloc_block(GFP_KERNEL);
         if (!rrb)
                 return -ENOMEM;
 
@@ -199,7 +199,7 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
                         retries--;
                         if (retries < 0)
                                 break;
-                        msleep(1);
+                        msleep(20);
                 }
         } while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
 
@@ -245,49 +245,12 @@ int clp_disable_fh(struct zpci_dev *zdev)
         return rc;
 }
 
-static void clp_check_pcifn_entry(struct clp_fh_list_entry *entry)
+static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
+                        void (*cb)(struct clp_fh_list_entry *entry))
 {
-        int present, rc;
-
-        if (!entry->vendor_id)
-                return;
-
-        /* TODO: be a little bit more scalable */
-        present = zpci_fid_present(entry->fid);
-
-        if (present)
-                pr_debug("%s: device %x already present\n", __func__, entry->fid);
-
-        /* skip already used functions */
-        if (present && entry->config_state)
-                return;
-
-        /* aev 306: function moved to stand-by state */
-        if (present && !entry->config_state) {
-                /*
-                 * The handle is already disabled, that means no iota/irq freeing via
-                 * the firmware interfaces anymore. Need to free resources manually
-                 * (DMA memory, debug, sysfs)...
-                 */
-                zpci_stop_device(get_zdev_by_fid(entry->fid));
-                return;
-        }
-
-        rc = clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
-        if (rc)
-                pr_err("Failed to add fid: 0x%x\n", entry->fid);
-}
-
-int clp_find_pci_devices(void)
-{
-        struct clp_req_rsp_list_pci *rrb;
         u64 resume_token = 0;
         int entries, i, rc;
 
-        rrb = clp_alloc_block();
-        if (!rrb)
-                return -ENOMEM;
-
         do {
                 memset(rrb, 0, sizeof(*rrb));
                 rrb->request.hdr.len = sizeof(rrb->request);
@@ -316,12 +279,101 @@ int clp_find_pci_devices(void)
                 resume_token = rrb->response.resume_token;
 
                 for (i = 0; i < entries; i++)
-                        clp_check_pcifn_entry(&rrb->response.fh_list[i]);
+                        cb(&rrb->response.fh_list[i]);
         } while (resume_token);
 
         pr_debug("Maximum number of supported PCI functions: %u\n",
                 rrb->response.max_fn);
 out:
+        return rc;
+}
+
+static void __clp_add(struct clp_fh_list_entry *entry)
+{
+        if (!entry->vendor_id)
+                return;
+
+        clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+}
+
+static void __clp_rescan(struct clp_fh_list_entry *entry)
+{
+        struct zpci_dev *zdev;
+
+        if (!entry->vendor_id)
+                return;
+
+        zdev = get_zdev_by_fid(entry->fid);
+        if (!zdev) {
+                clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+                return;
+        }
+
+        if (!entry->config_state) {
+                /*
+                 * The handle is already disabled, that means no iota/irq freeing via
+                 * the firmware interfaces anymore. Need to free resources manually
+                 * (DMA memory, debug, sysfs)...
+                 */
+                zpci_stop_device(zdev);
+        }
+}
+
+static void __clp_update(struct clp_fh_list_entry *entry)
+{
+        struct zpci_dev *zdev;
+
+        if (!entry->vendor_id)
+                return;
+
+        zdev = get_zdev_by_fid(entry->fid);
+        if (!zdev)
+                return;
+
+        zdev->fh = entry->fh;
+}
+
+int clp_scan_pci_devices(void)
+{
+        struct clp_req_rsp_list_pci *rrb;
+        int rc;
+
+        rrb = clp_alloc_block(GFP_KERNEL);
+        if (!rrb)
+                return -ENOMEM;
+
+        rc = clp_list_pci(rrb, __clp_add);
+
+        clp_free_block(rrb);
+        return rc;
+}
+
+int clp_rescan_pci_devices(void)
+{
+        struct clp_req_rsp_list_pci *rrb;
+        int rc;
+
+        rrb = clp_alloc_block(GFP_KERNEL);
+        if (!rrb)
+                return -ENOMEM;
+
+        rc = clp_list_pci(rrb, __clp_rescan);
+
+        clp_free_block(rrb);
+        return rc;
+}
+
+int clp_rescan_pci_devices_simple(void)
+{
+        struct clp_req_rsp_list_pci *rrb;
+        int rc;
+
+        rrb = clp_alloc_block(GFP_NOWAIT);
+        if (!rrb)
+                return -ENOMEM;
+
+        rc = clp_list_pci(rrb, __clp_update);
+
         clp_free_block(rrb);
         return rc;
 }
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index a2343c1f6e04..7e5573acb063 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -10,6 +10,7 @@
 #include <linux/export.h>
 #include <linux/iommu-helper.h>
 #include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
 
@@ -170,8 +171,8 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
                  */
                 goto no_refresh;
 
-        rc = s390pci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
-                                   nr_pages * PAGE_SIZE);
+        rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
+                                nr_pages * PAGE_SIZE);
 
 no_refresh:
         spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
@@ -407,7 +408,6 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 
 int zpci_dma_init_device(struct zpci_dev *zdev)
 {
-        unsigned int bitmap_order;
         int rc;
 
         spin_lock_init(&zdev->iommu_bitmap_lock);
@@ -421,12 +421,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 
         zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
         zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
-        bitmap_order = get_order(zdev->iommu_pages / 8);
-        pr_info("iommu_size: 0x%lx  iommu_pages: 0x%lx  bitmap_order: %i\n",
-                 zdev->iommu_size, zdev->iommu_pages, bitmap_order);
-
-        zdev->iommu_bitmap = (void *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
-                                                       bitmap_order);
+        zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
         if (!zdev->iommu_bitmap) {
                 rc = -ENOMEM;
                 goto out_reg;
@@ -451,8 +446,7 @@ void zpci_dma_exit_device(struct zpci_dev *zdev)
 {
         zpci_unregister_ioat(zdev, 0);
         dma_cleanup_tables(zdev);
-        free_pages((unsigned long) zdev->iommu_bitmap,
-                   get_order(zdev->iommu_pages / 8));
+        vfree(zdev->iommu_bitmap);
         zdev->iommu_bitmap = NULL;
         zdev->next_bit = 0;
 }
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index ec62e3a0dc09..0aecaf954845 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -69,7 +69,7 @@ static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf)
                 clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
                 break;
         case 0x0306:
-                clp_find_pci_devices();
+                clp_rescan_pci_devices();
                 break;
         default:
                 break;
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 22eeb9d7ffeb..85267c058af8 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -27,7 +27,7 @@ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
         return cc;
 }
 
-int s390pci_mod_fc(u64 req, struct zpci_fib *fib)
+int zpci_mod_fc(u64 req, struct zpci_fib *fib)
 {
         u8 cc, status;
 
@@ -61,7 +61,7 @@ static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
         return cc;
 }
 
-int s390pci_refresh_trans(u64 fn, u64 addr, u64 range)
+int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 {
         u8 cc, status;
 
@@ -78,7 +78,7 @@ int s390pci_refresh_trans(u64 fn, u64 addr, u64 range)
 }
 
 /* Set Interruption Controls */
-void set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
 {
         asm volatile (
                 "       .insn   rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
@@ -109,7 +109,7 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
         return cc;
 }
 
-int s390pci_load(u64 *data, u64 req, u64 offset)
+int zpci_load(u64 *data, u64 req, u64 offset)
 {
         u8 status;
         int cc;
@@ -125,7 +125,7 @@ int s390pci_load(u64 *data, u64 req, u64 offset)
                             __func__, cc, status, req, offset);
         return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(s390pci_load);
+EXPORT_SYMBOL_GPL(zpci_load);
 
 /* PCI Store */
 static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
@@ -147,7 +147,7 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
         return cc;
 }
 
-int s390pci_store(u64 data, u64 req, u64 offset)
+int zpci_store(u64 data, u64 req, u64 offset)
 {
         u8 status;
         int cc;
@@ -163,7 +163,7 @@ int s390pci_store(u64 data, u64 req, u64 offset)
                         __func__, cc, status, req, offset);
         return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(s390pci_store);
+EXPORT_SYMBOL_GPL(zpci_store);
 
 /* PCI Store Block */
 static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
@@ -183,7 +183,7 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
         return cc;
 }
 
-int s390pci_store_block(const u64 *data, u64 req, u64 offset)
+int zpci_store_block(const u64 *data, u64 req, u64 offset)
 {
         u8 status;
         int cc;
@@ -199,4 +199,4 @@ int s390pci_store_block(const u64 *data, u64 req, u64 offset)
                             __func__, cc, status, req, offset);
         return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(s390pci_store_block);
+EXPORT_SYMBOL_GPL(zpci_store_block);
diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c
deleted file mode 100644
index b097aed05a9b..000000000000
--- a/arch/s390/pci/pci_msi.c
+++ /dev/null
@@ -1,142 +0,0 @@
-/*
- * Copyright IBM Corp. 2012
- *
- * Author(s):
- *   Jan Glauber <jang@linux.vnet.ibm.com>
- */
-
-#define COMPONENT "zPCI"
-#define pr_fmt(fmt) COMPONENT ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/rculist.h>
-#include <linux/hash.h>
-#include <linux/pci.h>
-#include <linux/msi.h>
-#include <asm/hw_irq.h>
-
-/* mapping of irq numbers to msi_desc */
-static struct hlist_head *msi_hash;
-static const unsigned int msi_hash_bits = 8;
-#define MSI_HASH_BUCKETS (1U << msi_hash_bits)
-#define msi_hashfn(nr)  hash_long(nr, msi_hash_bits)
-
-static DEFINE_SPINLOCK(msi_map_lock);
-
-struct msi_desc *__irq_get_msi_desc(unsigned int irq)
-{
-        struct msi_map *map;
-
-        hlist_for_each_entry_rcu(map,
-                        &msi_hash[msi_hashfn(irq)], msi_chain)
-                if (map->irq == irq)
-                        return map->msi;
-        return NULL;
-}
-
-int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
-{
-        if (msi->msi_attrib.is_msix) {
-                int offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-                        PCI_MSIX_ENTRY_VECTOR_CTRL;
-                msi->masked = readl(msi->mask_base + offset);
-                writel(flag, msi->mask_base + offset);
-        } else {
-                if (msi->msi_attrib.maskbit) {
-                        int pos;
-                        u32 mask_bits;
-
-                        pos = (long) msi->mask_base;
-                        pci_read_config_dword(msi->dev, pos, &mask_bits);
-                        mask_bits &= ~(mask);
-                        mask_bits |= flag & mask;
-                        pci_write_config_dword(msi->dev, pos, mask_bits);
-                } else {
-                        return 0;
-                }
-        }
-
-        msi->msi_attrib.maskbit = !!flag;
-        return 1;
-}
-
-int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi,
-                        unsigned int nr, int offset)
-{
-        struct msi_map *map;
-        struct msi_msg msg;
-        int rc;
-
-        map = kmalloc(sizeof(*map), GFP_KERNEL);
-        if (map == NULL)
-                return -ENOMEM;
-
-        map->irq = nr;
-        map->msi = msi;
-        zdev->msi_map[nr & ZPCI_MSI_MASK] = map;
-        INIT_HLIST_NODE(&map->msi_chain);
-
-        pr_debug("%s hashing irq: %u  to bucket nr: %llu\n",
-                __func__, nr, msi_hashfn(nr));
-        hlist_add_head_rcu(&map->msi_chain, &msi_hash[msi_hashfn(nr)]);
-
-        spin_lock(&msi_map_lock);
-        rc = irq_set_msi_desc(nr, msi);
-        if (rc) {
-                spin_unlock(&msi_map_lock);
-                hlist_del_rcu(&map->msi_chain);
-                kfree(map);
-                zdev->msi_map[nr & ZPCI_MSI_MASK] = NULL;
-                return rc;
-        }
-        spin_unlock(&msi_map_lock);
-
-        msg.data = nr - offset;
-        msg.address_lo = zdev->msi_addr & 0xffffffff;
-        msg.address_hi = zdev->msi_addr >> 32;
-        write_msi_msg(nr, &msg);
-        return 0;
-}
-
-void zpci_teardown_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi)
-{
-        int irq = msi->irq & ZPCI_MSI_MASK;
-        struct msi_map *map;
-
-        msi->msg.address_lo = 0;
-        msi->msg.address_hi = 0;
-        msi->msg.data = 0;
-        msi->irq = 0;
-        zpci_msi_set_mask_bits(msi, 1, 1);
-
-        spin_lock(&msi_map_lock);
-        map = zdev->msi_map[irq];
-        hlist_del_rcu(&map->msi_chain);
-        kfree(map);
-        zdev->msi_map[irq] = NULL;
-        spin_unlock(&msi_map_lock);
-}
-
-/*
- * The msi hash table has 256 entries which is good for 4..20
- * devices (a typical device allocates 10 + CPUs MSI's). Maybe make
- * the hash table size adjustable later.
- */
-int __init zpci_msihash_init(void)
-{
-        unsigned int i;
-
-        msi_hash = kmalloc(MSI_HASH_BUCKETS * sizeof(*msi_hash), GFP_KERNEL);
-        if (!msi_hash)
-                return -ENOMEM;
-
-        for (i = 0; i < MSI_HASH_BUCKETS; i++)
-                INIT_HLIST_HEAD(&msi_hash[i]);
-        return 0;
-}
-
-void __init zpci_msihash_exit(void)
-{
-        kfree(msi_hash);
-}
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index e99a2557f186..cf8a12ff733b 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -48,11 +48,38 @@ static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL);
 
+static void recover_callback(struct device *dev)
+{
+        struct pci_dev *pdev = to_pci_dev(dev);
+        struct zpci_dev *zdev = get_zdev(pdev);
+        int ret;
+
+        pci_stop_and_remove_bus_device(pdev);
+        ret = zpci_disable_device(zdev);
+        if (ret)
+                return;
+
+        ret = zpci_enable_device(zdev);
+        if (ret)
+                return;
+
+        pci_rescan_bus(zdev->bus);
+}
+
+static ssize_t store_recover(struct device *dev, struct device_attribute *attr,
+                             const char *buf, size_t count)
+{
+        int rc = device_schedule_callback(dev, recover_callback);
+        return rc ? rc : count;
+}
+static DEVICE_ATTR(recover, S_IWUSR, NULL, store_recover);
+
 static struct device_attribute *zpci_dev_attrs[] = {
         &dev_attr_function_id,
         &dev_attr_function_handle,
         &dev_attr_pchid,
         &dev_attr_pfgid,
+        &dev_attr_recover,
         NULL,
 };
 
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index c8def8bc9020..5fc237581caf 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -87,6 +87,8 @@ config STACKTRACE_SUPPORT
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 config MMU
         def_bool y
 
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 1020dd85431a..1018ed3a3ca5 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -643,9 +643,9 @@ config KEXEC
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
-          initially work for you.  It may help to enable device hotplugging
-          support.  As of this writing the exact hardware interface is
-          strongly in flux, so no good recommendation can be made.
+          initially work for you.  As of this writing the exact hardware
+          interface is strongly in flux, so no good recommendation can be
+          made.
 
 config CRASH_DUMP
         bool "kernel crash dumps (EXPERIMENTAL)"
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index 102f5d58b037..60ed3e1c4b75 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -69,7 +69,6 @@ static void pcibios_scanbus(struct pci_channel *hose)
 
                 pci_bus_size_bridges(bus);
                 pci_bus_assign_resources(bus);
-                pci_enable_bridges(bus);
         } else {
                 pci_free_resource_list(&resources);
         }
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index e61d43d9f689..362192ed12fe 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,10 +36,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->start = start;
+        tlb->end = end;
+        tlb->fullmm = !(start | (end+1));
 
         init_tlb_gather(tlb);
 }
diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c
index d30622592116..e3abfd4277e2 100644
--- a/arch/sh/kernel/cpu/shmobile/cpuidle.c
+++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c
@@ -91,13 +91,11 @@ static struct cpuidle_driver cpuidle_driver = {
 
 int __init sh_mobile_setup_cpuidle(void)
 {
-        int ret;
-
         if (sh_mobile_sleep_supported & SUSP_SH_SF)
                 cpuidle_driver.states[1].disabled = false;
 
         if (sh_mobile_sleep_supported & SUSP_SH_STANDBY)
                 cpuidle_driver.states[2].disabled = false;
 
-        return cpuidle_register(&cpuidle_driver);
+        return cpuidle_register(&cpuidle_driver, NULL);
 }
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index d5e86c9f74fd..d15c0d8d550f 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -89,9 +89,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 #define topology_core_id(cpu)                   (cpu)
 #define topology_core_cpumask(cpu)              ((void)(cpu), cpu_online_mask)
 #define topology_thread_cpumask(cpu)            cpumask_of(cpu)
-
-/* indicates that pointers to the topology struct cpumask maps are valid */
-#define arch_provides_topology_pointers         yes
 #endif
 
 #endif /* _ASM_TILE_TOPOLOGY_H */
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index 11425633b2d7..6640e7bbeaa2 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -508,13 +508,8 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller)
                                                 rc_dev_cap.word);
 
         /* Configure PCI Express MPS setting. */
-        list_for_each_entry(child, &root_bus->children, node) {
-                struct pci_dev *self = child->self;
-                if (!self)
-                        continue;
-
-                pcie_bus_configure_settings(child, self->pcie_mpss);
-        }
+        list_for_each_entry(child, &root_bus->children, node)
+                pcie_bus_configure_settings(child);
 
         /*
          * Set the mac_config register in trio based on the MPS/MRS of the link.
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 4febacd1a8a1..29b0301c18aa 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,10 +45,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->start = start;
+        tlb->end = end;
+        tlb->fullmm = !(start | (end+1));
 
         init_tlb_gather(tlb);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b32ebf92b0ce..f16fc34e6608 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -16,6 +16,7 @@ config X86_64
         def_bool y
         depends on 64BIT
         select X86_DEV_DMA_OPS
+        select ARCH_USE_CMPXCHG_LOCKREF
 
 ### Arch settings
 config X86
@@ -81,7 +82,6 @@ config X86
         select HAVE_USER_RETURN_NOTIFIER
         select ARCH_BINFMT_ELF_RANDOMIZE_PIE
         select HAVE_ARCH_JUMP_LABEL
-        select HAVE_TEXT_POKE_SMP
         select HAVE_GENERIC_HARDIRQS
         select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
         select SPARSE_IRQ
@@ -1627,9 +1627,9 @@ config KEXEC
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
-          initially work for you.  It may help to enable device hotplugging
-          support.  As of this writing the exact hardware interface is
-          strongly in flux, so no good recommendation can be made.
+          initially work for you.  As of this writing the exact hardware
+          interface is strongly in flux, so no good recommendation can be
+          made.
 
 config CRASH_DUMP
         bool "kernel crash dumps"
@@ -2332,10 +2332,6 @@ config HAVE_ATOMIC_IOMAP
         def_bool y
         depends on X86_32
 
-config HAVE_TEXT_POKE_SMP
-        bool
-        select STOP_MACHINE if SMP
-
 config X86_DEV_DMA_OPS
         bool
         depends on X86_64 || STA2X11
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d606463aa6d6..b7388a425f09 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -225,7 +225,7 @@ static void low_free(unsigned long size, unsigned long addr)
         unsigned long nr_pages;
 
         nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-        efi_call_phys2(sys_table->boottime->free_pages, addr, size);
+        efi_call_phys2(sys_table->boottime->free_pages, addr, nr_pages);
 }
 
 static void find_bits(unsigned long mask, u8 *pos, u8 *size)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 474dc1b59f72..4299eb05023c 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -452,7 +452,7 @@ ia32_badsys:
 
         CFI_ENDPROC
         
-        .macro PTREGSCALL label, func, arg
+        .macro PTREGSCALL label, func
         ALIGN
 GLOBAL(\label)
         leaq \func(%rip),%rax
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 58ed6d96a6ac..0a3f9c9f98d5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -5,6 +5,7 @@
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
+#include <asm/ptrace.h>
 
 /*
  * Alternative inline assembly for SMP.
@@ -220,20 +221,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * no thread can be preempted in the instructions being modified (no iret to an
  * invalid instruction possible) or if the instructions are changed from a
  * consistent state to another consistent state atomically.
- * More care must be taken when modifying code in the SMP case because of
- * Intel's errata. text_poke_smp() takes care that errata, but still
- * doesn't support NMI/MCE handler code modifying.
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
-struct text_poke_param {
-        void *addr;
-        const void *opcode;
-        size_t len;
-};
-
 extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
-extern void text_poke_smp_batch(struct text_poke_param *params, int n);
+extern int poke_int3_handler(struct pt_regs *regs);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f8119b582c3c..1d2091a226bc 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -715,4 +715,6 @@ static inline void exiting_ack_irq(void)
         ack_APIC_irq();
 }
 
+extern void ioapic_zap_locks(void);
+
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 1c2d247f65ce..4582e8e1cd1a 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -3,21 +3,25 @@
 
 #ifdef __ASSEMBLY__
 # define __ASM_FORM(x)  x
+# define __ASM_FORM_RAW(x)     x
 # define __ASM_FORM_COMMA(x) x,
 #else
 # define __ASM_FORM(x)  " " #x " "
+# define __ASM_FORM_RAW(x)     #x
 # define __ASM_FORM_COMMA(x) " " #x ","
 #endif
 
 #ifdef CONFIG_X86_32
 # define __ASM_SEL(a,b) __ASM_FORM(a)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
 #else
 # define __ASM_SEL(a,b) __ASM_FORM(b)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
 #endif
 
 #define __ASM_SIZE(inst, ...)   __ASM_SEL(inst##l##__VA_ARGS__, \
                                           inst##q##__VA_ARGS__)
-#define __ASM_REG(reg)          __ASM_SEL(e##reg, r##reg)
+#define __ASM_REG(reg)         __ASM_SEL_RAW(e##reg, r##reg)
 
 #define _ASM_PTR        __ASM_SEL(.long, .quad)
 #define _ASM_ALIGN      __ASM_SEL(.balign 4, .balign 8)
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 6dfd0195bb55..41639ce8fd63 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -15,6 +15,14 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h>
 
+#if BITS_PER_LONG == 32
+# define _BITOPS_LONG_SHIFT 5
+#elif BITS_PER_LONG == 64
+# define _BITOPS_LONG_SHIFT 6
+#else
+# error "Unexpected BITS_PER_LONG"
+#endif
+
 #define BIT_64(n)                       (U64_C(1) << (n))
 
 /*
@@ -59,7 +67,7 @@
  * restricted to acting on a single-word quantity.
  */
 static __always_inline void
-set_bit(unsigned int nr, volatile unsigned long *addr)
+set_bit(long nr, volatile unsigned long *addr)
 {
         if (IS_IMMEDIATE(nr)) {
                 asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -81,7 +89,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static inline void __set_bit(long nr, volatile unsigned long *addr)
 {
         asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -97,7 +105,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
  * in order to ensure changes are visible on other processors.
  */
 static __always_inline void
-clear_bit(int nr, volatile unsigned long *addr)
+clear_bit(long nr, volatile unsigned long *addr)
 {
         if (IS_IMMEDIATE(nr)) {
                 asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -118,13 +126,13 @@ clear_bit(int nr, volatile unsigned long *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
         barrier();
         clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
         asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -141,7 +149,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
         barrier();
         __clear_bit(nr, addr);
@@ -159,7 +167,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static inline void __change_bit(long nr, volatile unsigned long *addr)
 {
         asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -173,7 +181,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(long nr, volatile unsigned long *addr)
 {
         if (IS_IMMEDIATE(nr)) {
                 asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -194,7 +202,7 @@ static inline void change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -212,7 +220,7 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
  * This is the same as test_and_set_bit on x86.
  */
 static __always_inline int
-test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 {
         return test_and_set_bit(nr, addr);
 }
@@ -226,7 +234,7 @@ test_and_set_bit_lock(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -245,7 +253,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -272,7 +280,7 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -284,7 +292,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -304,7 +312,7 @@ static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -315,13 +323,13 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
         return oldbit;
 }
 
-static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-        return ((1UL << (nr % BITS_PER_LONG)) &
-                (addr[nr / BITS_PER_LONG])) != 0;
+        return ((1UL << (nr & (BITS_PER_LONG-1))) &
+                (addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 {
         int oldbit;
 
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 653668d140f9..4a8cb8d7cbd5 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params)
          */
         if (boot_params->sentinel) {
                 /* fields in boot_params are left uninitialized, clear them */
-                memset(&boot_params->olpc_ofw_header, 0,
+                memset(&boot_params->ext_ramdisk_image, 0,
                        (char *)&boot_params->efi_info -
-                        (char *)&boot_params->olpc_ofw_header);
+                        (char *)&boot_params->ext_ramdisk_image);
                 memset(&boot_params->kbd_status, 0,
                        (char *)&boot_params->hdr -
                        (char *)&boot_params->kbd_status);
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 50e5c58ced23..4c019179a57d 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size);
+extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
 
 #ifdef CONFIG_MICROCODE_AMD_EARLY
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf36776106..be12c534fd59 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
                 /* Re-load page tables */
                 load_cr3(next->pgd);
 
-                /* stop flush ipis for the previous mm */
+                /* Stop flush ipis for the previous mm */
                 cpumask_clear_cpu(cpu, mm_cpumask(prev));
 
-                /*
-                 * load the LDT, if the LDT is different:
-                 */
+                /* Load the LDT, if the LDT is different: */
                 if (unlikely(prev->context.ldt != next->context.ldt))
                         load_LDT_nolock(&next->context);
         }
 #ifdef CONFIG_SMP
-        else {
+          else {
                 this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
                 BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
 
-                if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
-                        /* We were in lazy tlb mode and leave_mm disabled
+                if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+                        /*
+                         * On established mms, the mm_cpumask is only changed
+                         * from irq context, from ptep_clear_flush() while in
+                         * lazy tlb mode, and here. Irqs are blocked during
+                         * schedule, protecting us from simultaneous changes.
+                         */
+                        cpumask_set_cpu(cpu, mm_cpumask(next));
+                        /*
+                         * We were in lazy tlb mode and leave_mm disabled
                          * tlb flush IPI delivery. We must reload CR3
                          * to make sure to use no freed page tables.
                          */
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index 2c543fff241b..e7e6751648ed 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -16,6 +16,20 @@
  *
  * Atomically decrements @v and calls <fail_fn> if the result is negative.
  */
+#ifdef CC_HAVE_ASM_GOTO
+static inline void __mutex_fastpath_lock(atomic_t *v,
+                                         void (*fail_fn)(atomic_t *))
+{
+        asm volatile goto(LOCK_PREFIX "   decl %0\n"
+                          "   jns %l[exit]\n"
+                          : : "m" (v->counter)
+                          : "memory", "cc"
+                          : exit);
+        fail_fn(v);
+exit:
+        return;
+}
+#else
 #define __mutex_fastpath_lock(v, fail_fn)                       \
 do {                                                            \
         unsigned long dummy;                                    \
@@ -32,6 +46,7 @@ do {								\
                      : "rax", "rsi", "rdx", "rcx",              \
                        "r8", "r9", "r10", "r11", "memory");     \
 } while (0)
+#endif
 
 /**
  *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
@@ -56,6 +71,20 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
  *
  * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
  */
+#ifdef CC_HAVE_ASM_GOTO
+static inline void __mutex_fastpath_unlock(atomic_t *v,
+                                           void (*fail_fn)(atomic_t *))
+{
+        asm volatile goto(LOCK_PREFIX "   incl %0\n"
+                          "   jg %l[exit]\n"
+                          : : "m" (v->counter)
+                          : "memory", "cc"
+                          : exit);
+        fail_fn(v);
+exit:
+        return;
+}
+#else
 #define __mutex_fastpath_unlock(v, fail_fn)                     \
 do {                                                            \
         unsigned long dummy;                                    \
@@ -72,6 +101,7 @@ do {								\
                      : "rax", "rsi", "rdx", "rcx",              \
                        "r8", "r9", "r10", "r11", "memory");     \
 } while (0)
+#endif
 
 #define __mutex_slowpath_needs_to_unlock()      1
 
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index f2b489cf1602..3bf2dd0cf61f 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -55,9 +55,53 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/*
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and
+ * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset
+ * into this range.
+ */
+#define PTE_FILE_MAX_BITS       28
+#define PTE_FILE_SHIFT1         (_PAGE_BIT_PRESENT + 1)
+#define PTE_FILE_SHIFT2         (_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3         (_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT4         (_PAGE_BIT_SOFT_DIRTY + 1)
+#define PTE_FILE_BITS1          (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2          (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
+#define PTE_FILE_BITS3          (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
+
+#define pte_to_pgoff(pte)                                               \
+        ((((pte).pte_low >> (PTE_FILE_SHIFT1))                          \
+          & ((1U << PTE_FILE_BITS1) - 1)))                              \
+        + ((((pte).pte_low >> (PTE_FILE_SHIFT2))                        \
+            & ((1U << PTE_FILE_BITS2) - 1))                             \
+           << (PTE_FILE_BITS1))                                         \
+        + ((((pte).pte_low >> (PTE_FILE_SHIFT3))                        \
+            & ((1U << PTE_FILE_BITS3) - 1))                             \
+           << (PTE_FILE_BITS1 + PTE_FILE_BITS2))                        \
+        + ((((pte).pte_low >> (PTE_FILE_SHIFT4)))                       \
+            << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
+
+#define pgoff_to_pte(off)                                               \
+        ((pte_t) { .pte_low =                                           \
+         ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)  \
+         + ((((off) >> PTE_FILE_BITS1)                                  \
+             & ((1U << PTE_FILE_BITS2) - 1))                            \
+            << PTE_FILE_SHIFT2)                                         \
+         + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))               \
+             & ((1U << PTE_FILE_BITS3) - 1))                            \
+            << PTE_FILE_SHIFT3)                                         \
+         + ((((off) >>                                                  \
+              (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)))      \
+            << PTE_FILE_SHIFT4)                                         \
+         + _PAGE_FILE })
+
+#else /* CONFIG_MEM_SOFT_DIRTY */
+
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
- * split up the 29 bits of offset into this range:
+ * split up the 29 bits of offset into this range.
  */
 #define PTE_FILE_MAX_BITS       29
 #define PTE_FILE_SHIFT1         (_PAGE_BIT_PRESENT + 1)
@@ -88,6 +132,8 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
             << PTE_FILE_SHIFT3)                                         \
          + _PAGE_FILE })
 
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 4cc9f2b7cdc3..81bb91b49a88 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -179,6 +179,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
+ *
+ * For soft-dirty tracking 11 bit is taken from
+ * the low part of pte as well.
  */
 #define pte_to_pgoff(pte) ((pte).pte_high)
 #define pgoff_to_pte(off)                                               \
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 4e4765908af5..8d16befdec88 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -315,6 +315,36 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
         return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
 }
 
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+        return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+        return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+        return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+        return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+        return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+        return pte_flags(pte) & _PAGE_SOFT_DIRTY;
+}
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index c98ac63aae48..f4843e031131 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -61,12 +61,27 @@
  * they do not conflict with each other.
  */
 
+#define _PAGE_BIT_SOFT_DIRTY    _PAGE_BIT_HIDDEN
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
 #define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 0))
 #endif
 
+/*
+ * Tracking soft dirty bit when a page goes to a swap is tricky.
+ * We need a bit which can be stored in pte _and_ not conflict
+ * with swap entry format. On x86 bits 6 and 7 are *not* involved
+ * into swap entry computation, but bit 6 is used for nonlinear
+ * file mapping, so we borrow bit 7 for soft dirty tracking.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY    _PAGE_PSE
+#else
+#define _PAGE_SWP_SOFT_DIRTY    (_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 573c1ad4994e..4c2d31d941ea 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -942,35 +942,6 @@ extern int set_tsc_mode(unsigned int val);
 
 extern u16 amd_get_nb_id(int cpu);
 
-struct aperfmperf {
-        u64 aperf, mperf;
-};
-
-static inline void get_aperfmperf(struct aperfmperf *am)
-{
-        WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF));
-
-        rdmsrl(MSR_IA32_APERF, am->aperf);
-        rdmsrl(MSR_IA32_MPERF, am->mperf);
-}
-
-#define APERFMPERF_SHIFT 10
-
-static inline
-unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
-                                    struct aperfmperf *new)
-{
-        u64 aperf = new->aperf - old->aperf;
-        u64 mperf = new->mperf - old->mperf;
-        unsigned long ratio = aperf;
-
-        mperf >>= APERFMPERF_SHIFT;
-        if (mperf)
-                ratio = div64_u64(aperf, mperf);
-
-        return ratio;
-}
-
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692eaabab5..e0e668422c75 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -34,6 +34,11 @@
 # define UNLOCK_LOCK_PREFIX
 #endif
 
+static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+        return lock.tickets.head == lock.tickets.tail;
+}
+
 /*
  * Ticket locks are conceptually two parts, one indicating the current head of
  * the queue, and the other indicating the current tail. The lock is acquired
@@ -233,8 +238,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)   cpu_relax()
 #define arch_write_relax(lock)  cpu_relax()
 
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 9d09b4073b60..05af3b31d522 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -26,9 +26,9 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void sync_set_bit(int nr, volatile unsigned long *addr)
+static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-        asm volatile("lock; btsl %1,%0"
+        asm volatile("lock; bts %1,%0"
                      : "+m" (ADDR)
                      : "Ir" (nr)
                      : "memory");
@@ -44,9 +44,9 @@ static inline void sync_set_bit(int nr, volatile unsigned long *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
+static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-        asm volatile("lock; btrl %1,%0"
+        asm volatile("lock; btr %1,%0"
                      : "+m" (ADDR)
                      : "Ir" (nr)
                      : "memory");
@@ -61,9 +61,9 @@ static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void sync_change_bit(int nr, volatile unsigned long *addr)
+static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-        asm volatile("lock; btcl %1,%0"
+        asm volatile("lock; btc %1,%0"
                      : "+m" (ADDR)
                      : "Ir" (nr)
                      : "memory");
@@ -77,11 +77,11 @@ static inline void sync_change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
-        asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0"
+        asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
                      : "=r" (oldbit), "+m" (ADDR)
                      : "Ir" (nr) : "memory");
         return oldbit;
@@ -95,11 +95,11 @@ static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
-        asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0"
+        asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
                      : "=r" (oldbit), "+m" (ADDR)
                      : "Ir" (nr) : "memory");
         return oldbit;
@@ -113,11 +113,11 @@ static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
-        asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0"
+        asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
                      : "=r" (oldbit), "+m" (ADDR)
                      : "Ir" (nr) : "memory");
         return oldbit;
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 095b21507b6a..d35f24e231cd 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -124,9 +124,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #define topology_core_id(cpu)                   (cpu_data(cpu).cpu_core_id)
 #define topology_core_cpumask(cpu)              (per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)            (per_cpu(cpu_sibling_map, cpu))
-
-/* indicates that pointers to the topology cpumask_t maps are valid */
-#define arch_provides_topology_pointers         yes
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c91e8b9d588b..235be70d5bb4 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -49,6 +49,7 @@ extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
+extern int check_tsc_disabled(void);
 extern unsigned long native_calibrate_tsc(void);
 
 extern int tsc_clocksource_reliable;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5ee26875baea..5838fa911aa0 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -153,16 +153,19 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
  * Careful: we have to cast the result to the type of the pointer
  * for sign reasons.
  *
- * The use of %edx as the register specifier is a bit of a
+ * The use of _ASM_DX as the register specifier is a bit of a
  * simplification, as gcc only cares about it as the starting point
  * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits
  * (%ecx being the next register in gcc's x86 register sequence), and
  * %rdx on 64 bits.
+ *
+ * Clang/LLVM cares about the size of the register, but still wants
+ * the base register for something that ends up being a pair.
  */
 #define get_user(x, ptr)                                                \
 ({                                                                      \
         int __ret_gu;                                                   \
-        register __inttype(*(ptr)) __val_gu asm("%edx");                \
+        register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);            \
         __chk_user_ptr(ptr);                                            \
         might_fault();                                                  \
         asm volatile("call __get_user_%P3"                              \
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 2627a81253ee..81aa73b8ecf5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -199,7 +199,7 @@ static void acpi_register_lapic(int id, u8 enabled)
 {
         unsigned int ver = 0;
 
-        if (id >= (MAX_LOCAL_APIC-1)) {
+        if (id >= MAX_LOCAL_APIC) {
                 printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
                 return;
         }
@@ -1120,6 +1120,7 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
         int ioapic;
         int ioapic_pin;
         struct io_apic_irq_attr irq_attr;
+        int ret;
 
         if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
                 return gsi;
@@ -1149,7 +1150,9 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
         set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
                              trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
                              polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-        io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
+        ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
+        if (ret < 0)
+                gsi = INT_MIN;
 
         return gsi;
 }
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c15cf9a25e27..15e8563e5c24 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,7 @@
 #include <linux/memory.h>
 #include <linux/stop_machine.h>
 #include <linux/slab.h>
+#include <linux/kdebug.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
         return addr;
 }
 
-/*
- * Cross-modifying kernel text with stop_machine().
- * This code originally comes from immediate value.
- */
-static atomic_t stop_machine_first;
-static int wrote_text;
+static void do_sync_core(void *info)
+{
+        sync_core();
+}
 
-struct text_poke_params {
-        struct text_poke_param *params;
-        int nparams;
-};
+static bool bp_patching_in_progress;
+static void *bp_int3_handler, *bp_int3_addr;
 
-static int __kprobes stop_machine_text_poke(void *data)
+int poke_int3_handler(struct pt_regs *regs)
 {
-        struct text_poke_params *tpp = data;
-        struct text_poke_param *p;
-        int i;
+        /* bp_patching_in_progress */
+        smp_rmb();
 
-        if (atomic_xchg(&stop_machine_first, 0)) {
-                for (i = 0; i < tpp->nparams; i++) {
-                        p = &tpp->params[i];
-                        text_poke(p->addr, p->opcode, p->len);
-                }
-                smp_wmb();      /* Make sure other cpus see that this has run */
-                wrote_text = 1;
-        } else {
-                while (!wrote_text)
-                        cpu_relax();
-                smp_mb();       /* Load wrote_text before following execution */
-        }
+        if (likely(!bp_patching_in_progress))
+                return 0;
 
-        for (i = 0; i < tpp->nparams; i++) {
-                p = &tpp->params[i];
-                flush_icache_range((unsigned long)p->addr,
-                                   (unsigned long)p->addr + p->len);
-        }
-        /*
-         * Intel Archiecture Software Developer's Manual section 7.1.3 specifies
-         * that a core serializing instruction such as "cpuid" should be
-         * executed on _each_ core before the new instruction is made visible.
-         */
-        sync_core();
-        return 0;
-}
+        if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr)
+                return 0;
+
+        /* set up the specified breakpoint handler */
+        regs->ip = (unsigned long) bp_int3_handler;
+
+        return 1;
 
-/**
- * text_poke_smp - Update instructions on a live kernel on SMP
- * @addr: address to modify
- * @opcode: source of the copy
- * @len: length to copy
- *
- * Modify multi-byte instruction by using stop_machine() on SMP. This allows
- * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying
- * should be allowed, since stop_machine() does _not_ protect code against
- * NMI and MCE.
- *
- * Note: Must be called under get_online_cpus() and text_mutex.
- */
-void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
-{
-        struct text_poke_params tpp;
-        struct text_poke_param p;
-
-        p.addr = addr;
-        p.opcode = opcode;
-        p.len = len;
-        tpp.params = &p;
-        tpp.nparams = 1;
-        atomic_set(&stop_machine_first, 1);
-        wrote_text = 0;
-        /* Use __stop_machine() because the caller already got online_cpus. */
-        __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
-        return addr;
 }
 
 /**
- * text_poke_smp_batch - Update instructions on a live kernel on SMP
- * @params: an array of text_poke parameters
- * @n: the number of elements in params.
+ * text_poke_bp() -- update instructions on live kernel on SMP
+ * @addr:       address to patch
+ * @opcode:     opcode of new instruction
+ * @len:        length to copy
+ * @handler:    address to jump to when the temporary breakpoint is hit
  *
- * Modify multi-byte instruction by using stop_machine() on SMP. Since the
- * stop_machine() is heavy task, it is better to aggregate text_poke requests
- * and do it once if possible.
+ * Modify multi-byte instruction by using int3 breakpoint on SMP.
+ * We completely avoid stop_machine() here, and achieve the
+ * synchronization using int3 breakpoint.
  *
- * Note: Must be called under get_online_cpus() and text_mutex.
+ * The way it is done:
+ *      - add a int3 trap to the address that will be patched
+ *      - sync cores
+ *      - update all but the first byte of the patched range
+ *      - sync cores
+ *      - replace the first byte (int3) by the first byte of
+ *        replacing opcode
+ *      - sync cores
+ *
+ * Note: must be called under text_mutex.
  */
-void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
-        struct text_poke_params tpp = {.params = params, .nparams = n};
+        unsigned char int3 = 0xcc;
+
+        bp_int3_handler = handler;
+        bp_int3_addr = (u8 *)addr + sizeof(int3);
+        bp_patching_in_progress = true;
+        /*
+         * Corresponding read barrier in int3 notifier for
+         * making sure the in_progress flags is correctly ordered wrt.
+         * patching
+         */
+        smp_wmb();
+
+        text_poke(addr, &int3, sizeof(int3));
 
-        atomic_set(&stop_machine_first, 1);
-        wrote_text = 0;
-        __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
+        on_each_cpu(do_sync_core, NULL, 1);
+
+        if (len - sizeof(int3) > 0) {
+                /* patch all but the first byte */
+                text_poke((char *)addr + sizeof(int3),
+                          (const char *) opcode + sizeof(int3),
+                          len - sizeof(int3));
+                /*
+                 * According to Intel, this core syncing is very likely
+                 * not necessary and we'd be safe even without it. But
+                 * better safe than sorry (plus there's not only Intel).
+                 */
+                on_each_cpu(do_sync_core, NULL, 1);
+        }
+
+        /* patch the first byte */
+        text_poke(addr, opcode, sizeof(int3));
+
+        on_each_cpu(do_sync_core, NULL, 1);
+
+        bp_patching_in_progress = false;
+        smp_wmb();
+
+        return addr;
 }
+
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9ed796ccc32c..e63a5bd2a78f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1534,6 +1534,11 @@ void intel_ir_io_apic_print_entries(unsigned int apic,
         }
 }
 
+void ioapic_zap_locks(void)
+{
+        raw_spin_lock_init(&ioapic_lock);
+}
+
 __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
 {
         union IO_APIC_reg_00 reg_00;
@@ -3375,12 +3380,15 @@ int io_apic_setup_irq_pin_once(unsigned int irq, int node,
 {
         unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin;
         int ret;
+        struct IO_APIC_route_entry orig_entry;
 
         /* Avoid redundant programming */
         if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) {
-                pr_debug("Pin %d-%d already programmed\n",
-                         mpc_ioapic_id(ioapic_idx), pin);
-                return 0;
+                pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin);
+                orig_entry = ioapic_read_entry(attr->ioapic, pin);
+                if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity)
+                        return 0;
+                return -EBUSY;
         }
         ret = io_apic_setup_irq_pin(irq, node, attr);
         if (!ret)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 466e3d15de12..903a264af981 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -512,7 +512,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
-static bool cpu_has_amd_erratum(const int *erratum);
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 static void init_amd(struct cpuinfo_x86 *c)
 {
@@ -729,11 +729,11 @@ static void init_amd(struct cpuinfo_x86 *c)
                 value &= ~(1ULL << 24);
                 wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
 
-                if (cpu_has_amd_erratum(amd_erratum_383))
+                if (cpu_has_amd_erratum(c, amd_erratum_383))
                         set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
         }
 
-        if (cpu_has_amd_erratum(amd_erratum_400))
+        if (cpu_has_amd_erratum(c, amd_erratum_400))
                 set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
 
         rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
@@ -878,23 +878,13 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
         AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
-static bool cpu_has_amd_erratum(const int *erratum)
+
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
-        struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
         int osvw_id = *erratum++;
         u32 range;
         u32 ms;
 
-        /*
-         * If called early enough that current_cpu_data hasn't been initialized
-         * yet, fall back to boot_cpu_data.
-         */
-        if (cpu->x86 == 0)
-                cpu = &boot_cpu_data;
-
-        if (cpu->x86_vendor != X86_VENDOR_AMD)
-                return false;
-
         if (osvw_id >= 0 && osvw_id < 65536 &&
             cpu_has(cpu, X86_FEATURE_OSVW)) {
                 u64 osvw_len;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a7c7305030cc..8355c84b9729 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1884,6 +1884,7 @@ static struct pmu pmu = {
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
         userpg->cap_usr_time = 0;
+        userpg->cap_usr_time_zero = 0;
         userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
         userpg->pmc_width = x86_pmu.cntval_bits;
 
@@ -1897,6 +1898,11 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
         userpg->time_mult = this_cpu_read(cyc2ns);
         userpg->time_shift = CYC2NS_SCALE_FACTOR;
         userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+
+        if (sched_clock_stable && !check_tsc_disabled()) {
+                userpg->cap_usr_time_zero = 1;
+                userpg->time_zero = this_cpu_read(cyc2ns_offset);
+        }
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 97e557bc4c91..cc16faae0538 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -641,6 +641,8 @@ extern struct event_constraint intel_core2_pebs_event_constraints[];
 
 extern struct event_constraint intel_atom_pebs_event_constraints[];
 
+extern struct event_constraint intel_slm_pebs_event_constraints[];
+
 extern struct event_constraint intel_nehalem_pebs_event_constraints[];
 
 extern struct event_constraint intel_westmere_pebs_event_constraints[];
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 4cbe03287b08..beeb7cc07044 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -347,8 +347,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
         struct amd_nb *nb;
         int i;
 
-        nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
-                          cpu_to_node(cpu));
+        nb = kzalloc_node(sizeof(struct amd_nb), GFP_KERNEL, cpu_to_node(cpu));
         if (!nb)
                 return NULL;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index fbc9210b45bc..0abf6742a8b0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -81,7 +81,8 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
 
 static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
 {
-        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+        /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+        INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
         INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
         EVENT_EXTRA_END
 };
@@ -143,8 +144,9 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 
 static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
 {
-        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
-        INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+        /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+        INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+        INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
         INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
         EVENT_EXTRA_END
 };
@@ -162,16 +164,27 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
         EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_slm_event_constraints[] __read_mostly =
+{
+        FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+        FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+        FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */
+        FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+        EVENT_CONSTRAINT_END
+};
+
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
-        INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+        /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+        INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+        INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
         INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
         EVENT_EXTRA_END
 };
 
 static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
-        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
-        INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+        /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+        INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+        INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
         INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
         EVENT_EXTRA_END
 };
@@ -882,6 +895,140 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+static struct extra_reg intel_slm_extra_regs[] __read_mostly =
+{
+        /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+        INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffff, RSP_0),
+        INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffff, RSP_1),
+        EVENT_EXTRA_END
+};
+
+#define SLM_DMND_READ           SNB_DMND_DATA_RD
+#define SLM_DMND_WRITE          SNB_DMND_RFO
+#define SLM_DMND_PREFETCH       (SNB_PF_DATA_RD|SNB_PF_RFO)
+
+#define SLM_SNP_ANY             (SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM)
+#define SLM_LLC_ACCESS          SNB_RESP_ANY
+#define SLM_LLC_MISS            (SLM_SNP_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 slm_hw_cache_extra_regs
+                                [PERF_COUNT_HW_CACHE_MAX]
+                                [PERF_COUNT_HW_CACHE_OP_MAX]
+                                [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+        [ C(OP_READ) ] = {
+                [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
+                [ C(RESULT_MISS)   ] = SLM_DMND_READ|SLM_LLC_MISS,
+        },
+        [ C(OP_WRITE) ] = {
+                [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
+                [ C(RESULT_MISS)   ] = SLM_DMND_WRITE|SLM_LLC_MISS,
+        },
+        [ C(OP_PREFETCH) ] = {
+                [ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS,
+                [ C(RESULT_MISS)   ] = SLM_DMND_PREFETCH|SLM_LLC_MISS,
+        },
+ },
+};
+
+static __initconst const u64 slm_hw_cache_event_ids
+                                [PERF_COUNT_HW_CACHE_MAX]
+                                [PERF_COUNT_HW_CACHE_OP_MAX]
+                                [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+        [ C(OP_READ) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0x0104, /* LD_DCU_MISS */
+        },
+        [ C(OP_WRITE) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0,
+        },
+        [ C(OP_PREFETCH) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0,
+        },
+ },
+ [ C(L1I ) ] = {
+        [ C(OP_READ) ] = {
+                [ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */
+                [ C(RESULT_MISS)   ] = 0x0280, /* ICACGE.MISSES */
+        },
+        [ C(OP_WRITE) ] = {
+                [ C(RESULT_ACCESS) ] = -1,
+                [ C(RESULT_MISS)   ] = -1,
+        },
+        [ C(OP_PREFETCH) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0,
+        },
+ },
+ [ C(LL  ) ] = {
+        [ C(OP_READ) ] = {
+                /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+                [ C(RESULT_ACCESS) ] = 0x01b7,
+                /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+                [ C(RESULT_MISS)   ] = 0x01b7,
+        },
+        [ C(OP_WRITE) ] = {
+                /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+                [ C(RESULT_ACCESS) ] = 0x01b7,
+                /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+                [ C(RESULT_MISS)   ] = 0x01b7,
+        },
+        [ C(OP_PREFETCH) ] = {
+                /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+                [ C(RESULT_ACCESS) ] = 0x01b7,
+                /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+                [ C(RESULT_MISS)   ] = 0x01b7,
+        },
+ },
+ [ C(DTLB) ] = {
+        [ C(OP_READ) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0x0804, /* LD_DTLB_MISS */
+        },
+        [ C(OP_WRITE) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0,
+        },
+        [ C(OP_PREFETCH) ] = {
+                [ C(RESULT_ACCESS) ] = 0,
+                [ C(RESULT_MISS)   ] = 0,
+        },
+ },
+ [ C(ITLB) ] = {
+        [ C(OP_READ) ] = {
+                [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
+                [ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES */
+        },
+        [ C(OP_WRITE) ] = {
+                [ C(RESULT_ACCESS) ] = -1,
+                [ C(RESULT_MISS)   ] = -1,
+        },
+        [ C(OP_PREFETCH) ] = {
+                [ C(RESULT_ACCESS) ] = -1,
+                [ C(RESULT_MISS)   ] = -1,
+        },
+ },
+ [ C(BPU ) ] = {
+        [ C(OP_READ) ] = {
+                [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
+                [ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
+        },
+        [ C(OP_WRITE) ] = {
+                [ C(RESULT_ACCESS) ] = -1,
+                [ C(RESULT_MISS)   ] = -1,
+        },
+        [ C(OP_PREFETCH) ] = {
+                [ C(RESULT_ACCESS) ] = -1,
+                [ C(RESULT_MISS)   ] = -1,
+        },
+ },
+};
+
 static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
 {
         /* user explicitly requested branch sampling */
@@ -1301,11 +1448,11 @@ static void intel_fixup_er(struct perf_event *event, int idx)
 
         if (idx == EXTRA_REG_RSP_0) {
                 event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-                event->hw.config |= 0x01b7;
+                event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event;
                 event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
         } else if (idx == EXTRA_REG_RSP_1) {
                 event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-                event->hw.config |= 0x01bb;
+                event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event;
                 event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
         }
 }
@@ -2176,6 +2323,21 @@ __init int intel_pmu_init(void)
                 pr_cont("Atom events, ");
                 break;
 
+        case 55: /* Atom 22nm "Silvermont" */
+                memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
+                        sizeof(hw_cache_event_ids));
+                memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
+                       sizeof(hw_cache_extra_regs));
+
+                intel_pmu_lbr_init_atom();
+
+                x86_pmu.event_constraints = intel_slm_event_constraints;
+                x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
+                x86_pmu.extra_regs = intel_slm_extra_regs;
+                x86_pmu.er_flags |= ERF_HAS_RSP_1;
+                pr_cont("Silvermont events, ");
+                break;
+
         case 37: /* 32 nm nehalem, "Clarkdale" */
         case 44: /* 32 nm nehalem, "Gulftown" */
         case 47: /* 32 nm Xeon E7 */
@@ -2270,6 +2432,7 @@ __init int intel_pmu_init(void)
         case 70:
         case 71:
         case 63:
+        case 69:
                 x86_pmu.late_ack = true;
                 memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
                 memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3065c57a63c1..63438aad177f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -224,7 +224,7 @@ static int alloc_pebs_buffer(int cpu)
         if (!x86_pmu.pebs)
                 return 0;
 
-        buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+        buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
         if (unlikely(!buffer))
                 return -ENOMEM;
 
@@ -262,7 +262,7 @@ static int alloc_bts_buffer(int cpu)
         if (!x86_pmu.bts)
                 return 0;
 
-        buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+        buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
         if (unlikely(!buffer))
                 return -ENOMEM;
 
@@ -295,7 +295,7 @@ static int alloc_ds_buffer(int cpu)
         int node = cpu_to_node(cpu);
         struct debug_store *ds;
 
-        ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
+        ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
         if (unlikely(!ds))
                 return -ENOMEM;
 
@@ -517,6 +517,32 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
         EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_slm_pebs_event_constraints[] = {
+        INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */
+        INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */
+        INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */
+        INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */
+        INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */
+        INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */
+        INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */
+        INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */
+        INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */
+        INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */
+        INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */
+        INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */
+        INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */
+        INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */
+        INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */
+        INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */
+        INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */
+        INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */
+        INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */
+        INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
+        INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
+        INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+        EVENT_CONSTRAINT_END
+};
+
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
         INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index cad791dbde95..fd8011ed4dcd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -6,6 +6,8 @@ static struct intel_uncore_type **pci_uncores = empty_uncore;
 /* pci bus to socket mapping */
 static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
 
+static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+
 static DEFINE_RAW_SPINLOCK(uncore_box_lock);
 
 /* mask of cpus that collect uncore events */
@@ -45,6 +47,24 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
 
 static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
@@ -281,7 +301,7 @@ static struct attribute *snbep_uncore_cbox_formats_attr[] = {
 };
 
 static struct attribute *snbep_uncore_pcu_formats_attr[] = {
-        &format_attr_event.attr,
+        &format_attr_event_ext.attr,
         &format_attr_occ_sel.attr,
         &format_attr_edge.attr,
         &format_attr_inv.attr,
@@ -301,6 +321,24 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
         &format_attr_edge.attr,
         &format_attr_inv.attr,
         &format_attr_thresh8.attr,
+        &format_attr_match_rds.attr,
+        &format_attr_match_rnid30.attr,
+        &format_attr_match_rnid4.attr,
+        &format_attr_match_dnid.attr,
+        &format_attr_match_mc.attr,
+        &format_attr_match_opc.attr,
+        &format_attr_match_vnw.attr,
+        &format_attr_match0.attr,
+        &format_attr_match1.attr,
+        &format_attr_mask_rds.attr,
+        &format_attr_mask_rnid30.attr,
+        &format_attr_mask_rnid4.attr,
+        &format_attr_mask_dnid.attr,
+        &format_attr_mask_mc.attr,
+        &format_attr_mask_opc.attr,
+        &format_attr_mask_vnw.attr,
+        &format_attr_mask0.attr,
+        &format_attr_mask1.attr,
         NULL,
 };
 
@@ -314,8 +352,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = {
 static struct uncore_event_desc snbep_uncore_qpi_events[] = {
         INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
         INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-        INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x02,umask=0x08"),
-        INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x03,umask=0x04"),
+        INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+        INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
         { /* end: all zeroes */ },
 };
 
@@ -356,13 +394,16 @@ static struct intel_uncore_ops snbep_uncore_msr_ops = {
         SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
 
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT()                      \
+        .init_box       = snbep_uncore_pci_init_box,            \
+        .disable_box    = snbep_uncore_pci_disable_box,         \
+        .enable_box     = snbep_uncore_pci_enable_box,          \
+        .disable_event  = snbep_uncore_pci_disable_event,       \
+        .read_counter   = snbep_uncore_pci_read_counter
+
 static struct intel_uncore_ops snbep_uncore_pci_ops = {
-        .init_box       = snbep_uncore_pci_init_box,
-        .disable_box    = snbep_uncore_pci_disable_box,
-        .enable_box     = snbep_uncore_pci_enable_box,
-        .disable_event  = snbep_uncore_pci_disable_event,
-        .enable_event   = snbep_uncore_pci_enable_event,
-        .read_counter   = snbep_uncore_pci_read_counter,
+        SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+        .enable_event   = snbep_uncore_pci_enable_event,        \
 };
 
 static struct event_constraint snbep_uncore_cbox_constraints[] = {
@@ -726,6 +767,61 @@ static struct intel_uncore_type *snbep_msr_uncores[] = {
         NULL,
 };
 
+enum {
+        SNBEP_PCI_QPI_PORT0_FILTER,
+        SNBEP_PCI_QPI_PORT1_FILTER,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event *hwc = &event->hw;
+        struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+        struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+        if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+                reg1->idx = 0;
+                reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+                reg1->config = event->attr.config1;
+                reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+                reg2->config = event->attr.config2;
+        }
+        return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct pci_dev *pdev = box->pci_dev;
+        struct hw_perf_event *hwc = &event->hw;
+        struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+        struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+        if (reg1->idx != EXTRA_REG_NONE) {
+                int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+                struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
+                WARN_ON_ONCE(!filter_pdev);
+                if (filter_pdev) {
+                        pci_write_config_dword(filter_pdev, reg1->reg,
+                                                (u32)reg1->config);
+                        pci_write_config_dword(filter_pdev, reg1->reg + 4,
+                                                (u32)(reg1->config >> 32));
+                        pci_write_config_dword(filter_pdev, reg2->reg,
+                                                (u32)reg2->config);
+                        pci_write_config_dword(filter_pdev, reg2->reg + 4,
+                                                (u32)(reg2->config >> 32));
+                }
+        }
+
+        pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+        SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+        .enable_event           = snbep_qpi_enable_event,
+        .hw_config              = snbep_qpi_hw_config,
+        .get_constraint         = uncore_get_constraint,
+        .put_constraint         = uncore_put_constraint,
+};
+
 #define SNBEP_UNCORE_PCI_COMMON_INIT()                          \
         .perf_ctr       = SNBEP_PCI_PMON_CTR0,                  \
         .event_ctl      = SNBEP_PCI_PMON_CTL0,                  \
@@ -755,17 +851,18 @@ static struct intel_uncore_type snbep_uncore_imc = {
 };
 
 static struct intel_uncore_type snbep_uncore_qpi = {
-        .name           = "qpi",
-        .num_counters   = 4,
-        .num_boxes      = 2,
-        .perf_ctr_bits  = 48,
-        .perf_ctr       = SNBEP_PCI_PMON_CTR0,
-        .event_ctl      = SNBEP_PCI_PMON_CTL0,
-        .event_mask     = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
-        .box_ctl        = SNBEP_PCI_PMON_BOX_CTL,
-        .ops            = &snbep_uncore_pci_ops,
-        .event_descs    = snbep_uncore_qpi_events,
-        .format_group   = &snbep_uncore_qpi_format_group,
+        .name                   = "qpi",
+        .num_counters           = 4,
+        .num_boxes              = 2,
+        .perf_ctr_bits          = 48,
+        .perf_ctr               = SNBEP_PCI_PMON_CTR0,
+        .event_ctl              = SNBEP_PCI_PMON_CTL0,
+        .event_mask             = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+        .box_ctl                = SNBEP_PCI_PMON_BOX_CTL,
+        .num_shared_regs        = 1,
+        .ops                    = &snbep_uncore_qpi_ops,
+        .event_descs            = snbep_uncore_qpi_events,
+        .format_group           = &snbep_uncore_qpi_format_group,
 };
 
 
@@ -807,43 +904,53 @@ static struct intel_uncore_type *snbep_pci_uncores[] = {
 static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
         { /* Home Agent */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
-                .driver_data = SNBEP_PCI_UNCORE_HA,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
         },
         { /* MC Channel 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
-                .driver_data = SNBEP_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
         },
         { /* MC Channel 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
-                .driver_data = SNBEP_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
         },
         { /* MC Channel 2 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
-                .driver_data = SNBEP_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
         },
         { /* MC Channel 3 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
-                .driver_data = SNBEP_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
         },
         { /* QPI Port 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
-                .driver_data = SNBEP_PCI_UNCORE_QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
         },
         { /* QPI Port 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
-                .driver_data = SNBEP_PCI_UNCORE_QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
         },
         { /* R2PCIe */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
-                .driver_data = SNBEP_PCI_UNCORE_R2PCIE,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
         },
         { /* R3QPI Link 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
-                .driver_data = SNBEP_PCI_UNCORE_R3QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
         },
         { /* R3QPI Link 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
-                .driver_data = SNBEP_PCI_UNCORE_R3QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+        },
+        { /* QPI Port 0 filter  */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+                .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+                                                   SNBEP_PCI_QPI_PORT0_FILTER),
+        },
+        { /* QPI Port 0 filter  */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+                .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+                                                   SNBEP_PCI_QPI_PORT1_FILTER),
         },
         { /* end: all zeroes */ }
 };
@@ -1256,71 +1363,71 @@ static struct intel_uncore_type *ivt_pci_uncores[] = {
 static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = {
         { /* Home Agent 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
-                .driver_data = IVT_PCI_UNCORE_HA,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
         },
         { /* Home Agent 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
-                .driver_data = IVT_PCI_UNCORE_HA,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
         },
         { /* MC0 Channel 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
         },
         { /* MC0 Channel 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
         },
         { /* MC0 Channel 3 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
         },
         { /* MC0 Channel 4 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
         },
         { /* MC1 Channel 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
         },
         { /* MC1 Channel 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
         },
         { /* MC1 Channel 3 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
         },
         { /* MC1 Channel 4 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
-                .driver_data = IVT_PCI_UNCORE_IMC,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
         },
         { /* QPI0 Port 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
-                .driver_data = IVT_PCI_UNCORE_QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
         },
         { /* QPI0 Port 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
-                .driver_data = IVT_PCI_UNCORE_QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
         },
         { /* QPI1 Port 2 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
-                .driver_data = IVT_PCI_UNCORE_QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
         },
         { /* R2PCIe */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
-                .driver_data = IVT_PCI_UNCORE_R2PCIE,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
         },
         { /* R3QPI0 Link 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
-                .driver_data = IVT_PCI_UNCORE_R3QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
         },
         { /* R3QPI0 Link 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
-                .driver_data = IVT_PCI_UNCORE_R3QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
         },
         { /* R3QPI1 Link 2 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
-                .driver_data = IVT_PCI_UNCORE_R3QPI,
+                .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
         },
         { /* end: all zeroes */ }
 };
@@ -2606,7 +2713,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp
 
         size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
-        box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
+        box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu));
         if (!box)
                 return NULL;
 
@@ -3167,16 +3274,24 @@ static bool pcidrv_registered;
 /*
  * add a pci uncore device
  */
-static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
+static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
         struct intel_uncore_pmu *pmu;
         struct intel_uncore_box *box;
-        int i, phys_id;
+        struct intel_uncore_type *type;
+        int phys_id;
 
         phys_id = pcibus_to_physid[pdev->bus->number];
         if (phys_id < 0)
                 return -ENODEV;
 
+        if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
+                extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+                pci_set_drvdata(pdev, NULL);
+                return 0;
+        }
+
+        type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
         box = uncore_alloc_box(type, 0);
         if (!box)
                 return -ENOMEM;
@@ -3185,21 +3300,11 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
          * for performance monitoring unit with multiple boxes,
          * each box has a different function id.
          */
-        for (i = 0; i < type->num_boxes; i++) {
-                pmu = &type->pmus[i];
-                if (pmu->func_id == pdev->devfn)
-                        break;
-                if (pmu->func_id < 0) {
-                        pmu->func_id = pdev->devfn;
-                        break;
-                }
-                pmu = NULL;
-        }
-
-        if (!pmu) {
-                kfree(box);
-                return -EINVAL;
-        }
+        pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
+        if (pmu->func_id < 0)
+                pmu->func_id = pdev->devfn;
+        else
+                WARN_ON_ONCE(pmu->func_id != pdev->devfn);
 
         box->phys_id = phys_id;
         box->pci_dev = pdev;
@@ -3217,9 +3322,22 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
 static void uncore_pci_remove(struct pci_dev *pdev)
 {
         struct intel_uncore_box *box = pci_get_drvdata(pdev);
-        struct intel_uncore_pmu *pmu = box->pmu;
-        int cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+        struct intel_uncore_pmu *pmu;
+        int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
 
+        box = pci_get_drvdata(pdev);
+        if (!box) {
+                for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
+                        if (extra_pci_dev[phys_id][i] == pdev) {
+                                extra_pci_dev[phys_id][i] = NULL;
+                                break;
+                        }
+                }
+                WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX);
+                return;
+        }
+
+        pmu = box->pmu;
         if (WARN_ON_ONCE(phys_id != box->phys_id))
                 return;
 
@@ -3240,12 +3358,6 @@ static void uncore_pci_remove(struct pci_dev *pdev)
         kfree(box);
 }
 
-static int uncore_pci_probe(struct pci_dev *pdev,
-                            const struct pci_device_id *id)
-{
-        return uncore_pci_add(pci_uncores[id->driver_data], pdev);
-}
-
 static int __init uncore_pci_init(void)
 {
         int ret;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 47b3d00c9d89..a80ab71a883d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -12,6 +12,15 @@
 #define UNCORE_PMC_IDX_FIXED            UNCORE_PMC_IDX_MAX_GENERIC
 #define UNCORE_PMC_IDX_MAX              (UNCORE_PMC_IDX_FIXED + 1)
 
+#define UNCORE_PCI_DEV_DATA(type, idx)  ((type << 8) | idx)
+#define UNCORE_PCI_DEV_TYPE(data)       ((data >> 8) & 0xff)
+#define UNCORE_PCI_DEV_IDX(data)        (data & 0xff)
+#define UNCORE_EXTRA_PCI_DEV            0xff
+#define UNCORE_EXTRA_PCI_DEV_MAX        2
+
+/* support up to 8 sockets */
+#define UNCORE_SOCKET_MAX               8
+
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
 /* SNB event control */
@@ -108,6 +117,7 @@
                                 (SNBEP_PMON_CTL_EV_SEL_MASK | \
                                  SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
                                  SNBEP_PMON_CTL_EDGE_DET | \
+                                 SNBEP_PMON_CTL_EV_SEL_EXT | \
                                  SNBEP_PMON_CTL_INVERT | \
                                  SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
                                  SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 74467feb4dc5..e0e0841eef45 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -128,7 +128,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
         cpu_emergency_svm_disable();
 
         lapic_shutdown();
-#if defined(CONFIG_X86_IO_APIC)
+#ifdef CONFIG_X86_IO_APIC
+        /* Prevent crash_kexec() from deadlocking on ioapic_lock. */
+        ioapic_zap_locks();
         disable_IO_APIC();
 #endif
 #ifdef CONFIG_HPET_TIMER
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 94ab6b90dd3f..63bdb29b2549 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -196,15 +196,23 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 static void __init intel_remapping_check(int num, int slot, int func)
 {
         u8 revision;
+        u16 device;
 
+        device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
         revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
         /*
-         * Revision 0x13 of this chipset supports irq remapping
-         * but has an erratum that breaks its behavior, flag it as such
+         * Revision 13 of all triggering devices id in this quirk have
+         * a problem draining interrupts when irq remapping is enabled,
+         * and should be flagged as broken.  Additionally revisions 0x12
+         * and 0x22 of device id 0x3405 has this problem.
          */
         if (revision == 0x13)
                 set_irq_remapping_broken();
+        else if ((device == 0x3405) &&
+            ((revision == 0x12) ||
+             (revision == 0x22)))
+                set_irq_remapping_broken();
 
 }
 
@@ -239,6 +247,8 @@ static struct chipset early_qrk[] __initdata = {
           PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
         { PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
           PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+        { PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST,
+          PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
         { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
           PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
         {}
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 202d24f0f7e7..5d576ab34403 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -116,7 +116,7 @@ static void mxcsr_feature_mask_init(void)
 
         if (cpu_has_fxsr) {
                 memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-                asm volatile("fxsave %0" : : "m" (fx_scratch));
+                asm volatile("fxsave %0" : "+m" (fx_scratch));
                 mask = fx_scratch.mxcsr_mask;
                 if (mask == 0)
                         mask = 0x0000ffbf;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 2889b3d43882..460f5d9ceebb 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,7 +37,19 @@ static void __jump_label_transform(struct jump_entry *entry,
         } else
                 memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
 
-        (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+        /*
+         * Make text_poke_bp() a default fallback poker.
+         *
+         * At the time the change is being done, just ignore whether we
+         * are doing nop -> jump or jump -> nop transition, and assume
+         * always nop being the 'currently valid' instruction
+         *
+         */
+        if (poker)
+                (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+        else
+                text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE,
+                             (void *)entry->code + JUMP_LABEL_NOP_SIZE);
 }
 
 void arch_jump_label_transform(struct jump_entry *entry,
@@ -45,7 +57,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 {
         get_online_cpus();
         mutex_lock(&text_mutex);
-        __jump_label_transform(entry, type, text_poke_smp);
+        __jump_label_transform(entry, type, NULL);
         mutex_unlock(&text_mutex);
         put_online_cpus();
 }
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index 2e9d4b5af036..c6ee63f927ab 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to);
 extern void synthesize_relcall(void *from, void *to);
 
 #ifdef  CONFIG_OPTPROBES
-extern int arch_init_optprobes(void);
 extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
 extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
 #else   /* !CONFIG_OPTPROBES */
-static inline int arch_init_optprobes(void)
-{
-        return 0;
-}
 static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 {
         return 0;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 048852d06447..79a3f9682871 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 
 int __init arch_init_kprobes(void)
 {
-        return arch_init_optprobes();
+        return 0;
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 2c1ac2893365..898160b42e43 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -368,31 +368,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
         return 0;
 }
 
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
-        u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
-                                            u8 *insn_buf,
-                                            struct optimized_kprobe *op)
-{
-        s32 rel = (s32)((long)op->optinsn.insn -
-                        ((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
-        /* Backup instructions which will be replaced by jump address */
-        memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
-               RELATIVE_ADDR_SIZE);
-
-        insn_buf[0] = RELATIVEJUMP_OPCODE;
-        *(s32 *)(&insn_buf[1]) = rel;
-
-        tprm->addr = op->kp.addr;
-        tprm->opcode = insn_buf;
-        tprm->len = RELATIVEJUMP_SIZE;
-}
-
 /*
  * Replace breakpoints (int3) with relative jumps.
  * Caller must call with locking kprobe_mutex and text_mutex.
@@ -400,37 +375,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
 void __kprobes arch_optimize_kprobes(struct list_head *oplist)
 {
         struct optimized_kprobe *op, *tmp;
-        int c = 0;
+        u8 insn_buf[RELATIVEJUMP_SIZE];
 
         list_for_each_entry_safe(op, tmp, oplist, list) {
+                s32 rel = (s32)((long)op->optinsn.insn -
+                        ((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
                 WARN_ON(kprobe_disabled(&op->kp));
-                /* Setup param */
-                setup_optimize_kprobe(&jump_poke_params[c],
-                                      jump_poke_bufs[c].buf, op);
+
+                /* Backup instructions which will be replaced by jump address */
+                memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
+                       RELATIVE_ADDR_SIZE);
+
+                insn_buf[0] = RELATIVEJUMP_OPCODE;
+                *(s32 *)(&insn_buf[1]) = rel;
+
+                text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+                             op->optinsn.insn);
+
                 list_del_init(&op->list);
-                if (++c >= MAX_OPTIMIZE_PROBES)
-                        break;
         }
-
-        /*
-         * text_poke_smp doesn't support NMI/MCE code modifying.
-         * However, since kprobes itself also doesn't support NMI/MCE
-         * code probing, it's not a problem.
-         */
-        text_poke_smp_batch(jump_poke_params, c);
 }
 
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
-                                              u8 *insn_buf,
-                                              struct optimized_kprobe *op)
+/* Replace a relative jump with a breakpoint (int3).  */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
+        u8 insn_buf[RELATIVEJUMP_SIZE];
+
         /* Set int3 to first byte for kprobes */
         insn_buf[0] = BREAKPOINT_INSTRUCTION;
         memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-        tprm->addr = op->kp.addr;
-        tprm->opcode = insn_buf;
-        tprm->len = RELATIVEJUMP_SIZE;
+        text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+                     op->optinsn.insn);
 }
 
 /*
@@ -441,34 +417,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
                                     struct list_head *done_list)
 {
         struct optimized_kprobe *op, *tmp;
-        int c = 0;
 
         list_for_each_entry_safe(op, tmp, oplist, list) {
-                /* Setup param */
-                setup_unoptimize_kprobe(&jump_poke_params[c],
-                                        jump_poke_bufs[c].buf, op);
+                arch_unoptimize_kprobe(op);
                 list_move(&op->list, done_list);
-                if (++c >= MAX_OPTIMIZE_PROBES)
-                        break;
         }
-
-        /*
-         * text_poke_smp doesn't support NMI/MCE code modifying.
-         * However, since kprobes itself also doesn't support NMI/MCE
-         * code probing, it's not a problem.
-         */
-        text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
-        u8 buf[RELATIVEJUMP_SIZE];
-
-        /* Set int3 to first byte for kprobes */
-        buf[0] = BREAKPOINT_INSTRUCTION;
-        memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-        text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
 }
 
 int  __kprobes
@@ -488,22 +441,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
         }
         return 0;
 }
-
-int __kprobes arch_init_optprobes(void)
-{
-        /* Allocate code buffer and parameter array */
-        jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
-                                 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-        if (!jump_poke_bufs)
-                return -ENOMEM;
-
-        jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
-                                   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-        if (!jump_poke_params) {
-                kfree(jump_poke_bufs);
-                jump_poke_bufs = NULL;
-                return -ENOMEM;
-        }
-
-        return 0;
-}
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 47ebb1dbfbcb..7123b5df479d 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -145,10 +145,9 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
         return 0;
 }
 
-static unsigned int verify_patch_size(int cpu, u32 patch_size,
+static unsigned int verify_patch_size(u8 family, u32 patch_size,
                                       unsigned int size)
 {
-        struct cpuinfo_x86 *c = &cpu_data(cpu);
         u32 max_size;
 
 #define F1XH_MPB_MAX_SIZE 2048
@@ -156,7 +155,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 #define F15H_MPB_MAX_SIZE 4096
 #define F16H_MPB_MAX_SIZE 3458
 
-        switch (c->x86) {
+        switch (family) {
         case 0x14:
                 max_size = F14H_MPB_MAX_SIZE;
                 break;
@@ -220,12 +219,13 @@ int apply_microcode_amd(int cpu)
                 return 0;
         }
 
-        if (__apply_microcode_amd(mc_amd))
+        if (__apply_microcode_amd(mc_amd)) {
                 pr_err("CPU%d: update failed for patch_level=0x%08x\n",
                         cpu, mc_amd->hdr.patch_id);
-        else
-                pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
-                        mc_amd->hdr.patch_id);
+                return -1;
+        }
+        pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
+                mc_amd->hdr.patch_id);
 
         uci->cpu_sig.rev = mc_amd->hdr.patch_id;
         c->microcode = mc_amd->hdr.patch_id;
@@ -276,9 +276,8 @@ static void cleanup(void)
  * driver cannot continue functioning normally. In such cases, we tear
  * down everything we've used up so far and exit.
  */
-static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
+static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 {
-        struct cpuinfo_x86 *c = &cpu_data(cpu);
         struct microcode_header_amd *mc_hdr;
         struct ucode_patch *patch;
         unsigned int patch_size, crnt_size, ret;
@@ -298,7 +297,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
 
         /* check if patch is for the current family */
         proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
-        if (proc_fam != c->x86)
+        if (proc_fam != family)
                 return crnt_size;
 
         if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
@@ -307,7 +306,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
                 return crnt_size;
         }
 
-        ret = verify_patch_size(cpu, patch_size, leftover);
+        ret = verify_patch_size(family, patch_size, leftover);
         if (!ret) {
                 pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
                 return crnt_size;
@@ -338,7 +337,8 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
         return crnt_size;
 }
 
-static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
+                                             size_t size)
 {
         enum ucode_state ret = UCODE_ERROR;
         unsigned int leftover;
@@ -361,7 +361,7 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz
         }
 
         while (leftover) {
-                crnt_size = verify_and_add_patch(cpu, fw, leftover);
+                crnt_size = verify_and_add_patch(family, fw, leftover);
                 if (crnt_size < 0)
                         return ret;
 
@@ -372,22 +372,22 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz
         return UCODE_OK;
 }
 
-enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size)
+enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
         enum ucode_state ret;
 
         /* free old equiv table */
         free_equiv_cpu_table();
 
-        ret = __load_microcode_amd(cpu, data, size);
+        ret = __load_microcode_amd(family, data, size);
 
         if (ret != UCODE_OK)
                 cleanup();
 
 #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
         /* save BSP's matching patch for early load */
-        if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-                struct ucode_patch *p = find_patch(cpu);
+        if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
+                struct ucode_patch *p = find_patch(smp_processor_id());
                 if (p) {
                         memset(amd_bsp_mpb, 0, MPB_MAX_SIZE);
                         memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data),
@@ -440,7 +440,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
                 goto fw_release;
         }
 
-        ret = load_microcode_amd(cpu, fw->data, fw->size);
+        ret = load_microcode_amd(c->x86, fw->data, fw->size);
 
  fw_release:
         release_firmware(fw);
diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c
index 1d14ffee5749..6073104ccaa3 100644
--- a/arch/x86/kernel/microcode_amd_early.c
+++ b/arch/x86/kernel/microcode_amd_early.c
@@ -238,25 +238,17 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
         uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
 #else
-static void collect_cpu_info_amd_early(struct cpuinfo_x86 *c,
-                                                 struct ucode_cpu_info *uci)
+void load_ucode_amd_ap(void)
 {
+        unsigned int cpu = smp_processor_id();
+        struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
         u32 rev, eax;
 
         rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
         eax = cpuid_eax(0x00000001);
 
-        uci->cpu_sig.sig = eax;
         uci->cpu_sig.rev = rev;
-        c->microcode = rev;
-        c->x86 = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
-}
-
-void load_ucode_amd_ap(void)
-{
-        unsigned int cpu = smp_processor_id();
-
-        collect_cpu_info_amd_early(&cpu_data(cpu), ucode_cpu_info + cpu);
+        uci->cpu_sig.sig = eax;
 
         if (cpu && !ucode_loaded) {
                 void *ucode;
@@ -265,8 +257,10 @@ void load_ucode_amd_ap(void)
                         return;
 
                 ucode = (void *)(initrd_start + ucode_offset);
-                if (load_microcode_amd(0, ucode, ucode_size) != UCODE_OK)
+                eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+                if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK)
                         return;
+
                 ucode_loaded = true;
         }
 
@@ -278,6 +272,8 @@ int __init save_microcode_in_initrd_amd(void)
 {
         enum ucode_state ret;
         void *ucode;
+        u32 eax;
+
 #ifdef CONFIG_X86_32
         unsigned int bsp = boot_cpu_data.cpu_index;
         struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
@@ -293,7 +289,10 @@ int __init save_microcode_in_initrd_amd(void)
                 return 0;
 
         ucode = (void *)(initrd_start + ucode_offset);
-        ret = load_microcode_amd(0, ucode, ucode_size);
+        eax   = cpuid_eax(0x00000001);
+        eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+
+        ret = load_microcode_amd(eax, ucode, ucode_size);
         if (ret != UCODE_OK)
                 return -EINVAL;
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index dbded5aedb81..30277e27431a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
                                 *begin = new_begin;
                 }
         } else {
-                *begin = TASK_UNMAPPED_BASE;
+                *begin = current->mm->mmap_legacy_base;
                 *end = TASK_SIZE;
         }
 }
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index addf7b58f4e8..91a4496db434 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -301,6 +301,15 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
         return 0;
 }
 
+static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b)
+{
+        if (!tboot_enabled())
+                return 0;
+
+        pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
+        return -ENODEV;
+}
+
 static atomic_t ap_wfs_count;
 
 static int tboot_wait_for_aps(int num_aps)
@@ -422,6 +431,7 @@ static __init int tboot_late_init(void)
 #endif
 
         acpi_os_set_prepare_sleep(&tboot_sleep);
+        acpi_os_set_prepare_extended_sleep(&tboot_extended_sleep);
         return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1b23a1c92746..8c8093b146ca 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,6 +58,7 @@
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
+#include <asm/alternative.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
             ftrace_int3_handler(regs))
                 return;
 #endif
+        if (poke_int3_handler(regs))
+                return;
+
         prev_state = exception_enter();
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
         if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6ff49247edf8..930e5d48f560 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -89,6 +89,12 @@ int check_tsc_unstable(void)
 }
 EXPORT_SYMBOL_GPL(check_tsc_unstable);
 
+int check_tsc_disabled(void)
+{
+        return tsc_disabled;
+}
+EXPORT_SYMBOL_GPL(check_tsc_disabled);
+
 #ifdef CONFIG_X86_TSC
 int __init notsc_setup(char *str)
 {
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5d7e51f3fd28..533a85e3a07e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1,10 +1,8 @@
 # x86 Opcode Maps
 #
 # This is (mostly) based on following documentations.
-# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2
-#   (#325383-040US, October 2011)
-# - Intel(R) Advanced Vector Extensions Programming Reference
-#   (#319433-011,JUNE 2011).
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
+#   (#326018-047US, June 2013)
 #
 #<Opcode maps>
 # Table: table-name
@@ -29,6 +27,7 @@
 #  - (F3): the last prefix is 0xF3
 #  - (F2): the last prefix is 0xF2
 #  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
+#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
 
 Table: one byte opcode
 Referrer:
@@ -246,8 +245,8 @@ c2: RETN Iw (f64)
 c3: RETN
 c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
 c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
-c6: Grp11 Eb,Ib (1A)
-c7: Grp11 Ev,Iz (1A)
+c6: Grp11A Eb,Ib (1A)
+c7: Grp11B Ev,Iz (1A)
 c8: ENTER Iw,Ib
 c9: LEAVE (d64)
 ca: RETF Iw
@@ -293,8 +292,8 @@ ef: OUT DX,eAX
 # 0xf0 - 0xff
 f0: LOCK (Prefix)
 f1:
-f2: REPNE (Prefix)
-f3: REP/REPE (Prefix)
+f2: REPNE (Prefix) | XACQUIRE (Prefix)
+f3: REP/REPE (Prefix) | XRELEASE (Prefix)
 f4: HLT
 f5: CMC
 f6: Grp3_1 Eb (1A)
@@ -326,7 +325,8 @@ AVXcode: 1
 0a:
 0b: UD2 (1B)
 0c:
-0d: NOP Ev | GrpP
+# AMD's prefetch group. Intel supports prefetchw(/1) only.
+0d: GrpP
 0e: FEMMS
 # 3DNow! uses the last imm byte as opcode extension.
 0f: 3DNow! Pq,Qq,Ib
@@ -729,12 +729,12 @@ dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
 de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
 df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
-f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
 f2: ANDN Gy,By,Ey (v)
 f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: MULX By,Gy,rDX,Ey (F2),(v)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
 EndTable
 
@@ -861,8 +861,8 @@ EndTable
 
 GrpTable: Grp7
 0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
 5:
@@ -880,15 +880,21 @@ EndTable
 GrpTable: Grp9
 1: CMPXCHG8B/16B Mq/Mdq
 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq | VMPTRST Mq (F3)
+7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
 EndTable
 
 GrpTable: Grp10
 EndTable
 
-GrpTable: Grp11
-# Note: the operands are given by group opcode
-0: MOV
+# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
+GrpTable: Grp11A
+0: MOV Eb,Ib
+7: XABORT Ib (000),(11B)
+EndTable
+
+GrpTable: Grp11B
+0: MOV Eb,Iz
+7: XBEGIN Jz (000),(11B)
 EndTable
 
 GrpTable: Grp12
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 2ec29ac78ae6..04664cdb7fda 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -78,8 +78,8 @@ __ref void *alloc_low_pages(unsigned int num)
         return __va(pfn << PAGE_SHIFT);
 }
 
-/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE       (5 * PAGE_SIZE)
+/* need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS */
+#define INIT_PGT_BUF_SIZE       (6 * PAGE_SIZE)
 RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
 void  __init early_alloc_pgt_buf(void)
 {
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 62c29a5bfe26..25e7e1372bb2 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -112,11 +112,13 @@ static unsigned long mmap_legacy_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+        mm->mmap_legacy_base = mmap_legacy_base();
+        mm->mmap_base = mmap_base();
+
         if (mmap_is_legacy()) {
-                mm->mmap_base = mmap_legacy_base();
+                mm->mmap_base = mm->mmap_legacy_base;
                 mm->get_unmapped_area = arch_get_unmapped_area;
         } else {
-                mm->mmap_base = mmap_base();
                 mm->get_unmapped_area = arch_get_unmapped_area_topdown;
         }
 }
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index cdd0da9dd530..266ca912f62e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -146,6 +146,7 @@ int __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
         u64 start, end;
+        u32 hotpluggable;
         int node, pxm;
 
         if (srat_disabled())
@@ -154,7 +155,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
                 goto out_err_bad_srat;
         if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
                 goto out_err;
-        if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
+        hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+        if (hotpluggable && !save_add_info())
                 goto out_err;
 
         start = ma->base_address;
@@ -174,9 +176,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
         node_set(node, numa_nodes_parsed);
 
-        printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
-               node, pxm,
-               (unsigned long long) start, (unsigned long long) end - 1);
+        pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n",
+                node, pxm,
+                (unsigned long long) start, (unsigned long long) end - 1,
+                hotpluggable ? " hotplug" : "");
 
         return 0;
 out_err_bad_srat:
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d641897a1f4e..b30e937689d6 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -568,13 +568,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
          */
         if (bus) {
                 struct pci_bus *child;
-                list_for_each_entry(child, &bus->children, node) {
-                        struct pci_dev *self = child->self;
-                        if (!self)
-                                continue;
-
-                        pcie_bus_configure_settings(child, self->pcie_mpss);
-                }
+                list_for_each_entry(child, &bus->children, node)
+                        pcie_bus_configure_settings(child);
         }
 
         if (bus && node != -1) {
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 94919e307f8e..db6b1ab43255 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -210,6 +210,8 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
                 r = &dev->resource[idx];
                 if (!r->flags)
                         continue;
+                if (r->parent)  /* Already allocated */
+                        continue;
                 if (!r->start || pci_claim_resource(dev, idx) < 0) {
                         /*
                          * Something is wrong with the region.
@@ -318,6 +320,8 @@ static void pcibios_allocate_dev_rom_resource(struct pci_dev *dev)
         r = &dev->resource[PCI_ROM_RESOURCE];
         if (!r->flags || !r->start)
                 return;
+        if (r->parent) /* Already allocated */
+                return;
 
         if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
                 r->end -= r->start;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 082e88129712..5596c7bdd327 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -700,7 +700,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
         if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
                 return -ENODEV;
 
-        if (start > end)
+        if (start > end || !addr)
                 return -EINVAL;
 
         mutex_lock(&pci_mmcfg_lock);
@@ -716,11 +716,6 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
                 return -EEXIST;
         }
 
-        if (!addr) {
-                mutex_unlock(&pci_mmcfg_lock);
-                return -EINVAL;
-        }
-
         rc = -EBUSY;
         cfg = pci_mmconfig_alloc(seg, start, end, addr);
         if (cfg == NULL) {
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 6eb18c42a28a..903fded50786 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -23,11 +23,11 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/smp.h>
 
-#include <asm/acpi.h>
 #include <asm/segment.h>
-#include <asm/io.h>
-#include <asm/smp.h>
 #include <asm/pci_x86.h>
 #include <asm/hw_irq.h>
 #include <asm/io_apic.h>
@@ -43,7 +43,7 @@
 #define PCI_FIXED_BAR_4_SIZE    0x14
 #define PCI_FIXED_BAR_5_SIZE    0x1c
 
-static int pci_soc_mode = 0;
+static int pci_soc_mode;
 
 /**
  * fixed_bar_cap - return the offset of the fixed BAR cap if found
@@ -141,7 +141,8 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
  */
 static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 {
-        /* This is a workaround for A0 LNC bug where PCI status register does
+        /*
+         * This is a workaround for A0 LNC bug where PCI status register does
          * not have new CAP bit set. can not be written by SW either.
          *
          * PCI header type in real LNC indicates a single function device, this
@@ -154,7 +155,7 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
                                 || devfn == PCI_DEVFN(0, 0)
                                 || devfn == PCI_DEVFN(3, 0)))
                 return 1;
-        return 0; /* langwell on others */
+        return 0; /* Langwell on others */
 }
 
 static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
@@ -172,7 +173,8 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
 {
         int offset;
 
-        /* On MRST, there is no PCI ROM BAR, this will cause a subsequent read
+        /*
+         * On MRST, there is no PCI ROM BAR, this will cause a subsequent read
          * to ROM BAR return 0 then being ignored.
          */
         if (where == PCI_ROM_ADDRESS)
@@ -210,7 +212,8 @@ static int mrst_pci_irq_enable(struct pci_dev *dev)
 
         pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 
-        /* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
+        /*
+         * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
          * IOAPIC RTE entries, so we just enable RTE for the device.
          */
         irq_attr.ioapic = mp_find_ioapic(dev->irq);
@@ -235,7 +238,7 @@ struct pci_ops pci_mrst_ops = {
  */
 int __init pci_mrst_init(void)
 {
-        printk(KERN_INFO "Intel MID platform detected, using MID PCI ops\n");
+        pr_info("Intel MID platform detected, using MID PCI ops\n");
         pci_mmcfg_late_init();
         pcibios_enable_irq = mrst_pci_irq_enable;
         pci_root_ops = pci_mrst_ops;
@@ -244,17 +247,21 @@ int __init pci_mrst_init(void)
         return 1;
 }
 
-/* Langwell devices are not true pci devices, they are not subject to 10 ms
- * d3 to d0 delay required by pci spec.
+/*
+ * Langwell devices are not true PCI devices; they are not subject to 10 ms
+ * d3 to d0 delay required by PCI spec.
  */
 static void pci_d3delay_fixup(struct pci_dev *dev)
 {
-        /* PCI fixups are effectively decided compile time. If we have a dual
-           SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */
-        if (!pci_soc_mode)
-            return;
-        /* true pci devices in lincroft should allow type 1 access, the rest
-         * are langwell fake pci devices.
+        /*
+         * PCI fixups are effectively decided compile time. If we have a dual
+         * SoC/non-SoC kernel we don't want to mangle d3 on non-SoC devices.
+         */
+        if (!pci_soc_mode)
+                return;
+        /*
+         * True PCI devices in Lincroft should allow type 1 access, the rest
+         * are Langwell fake PCI devices.
          */
         if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID))
                 return;
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index e6773dc8ac41..093a892026f9 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -68,7 +68,7 @@ BEGIN {
 
         lprefix1_expr = "\\((66|!F3)\\)"
         lprefix2_expr = "\\(F3\\)"
-        lprefix3_expr = "\\((F2|!F3)\\)"
+        lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
         lprefix_expr = "\\((66|F2|F3)\\)"
         max_lprefix = 4
 
@@ -83,6 +83,8 @@ BEGIN {
         prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
         prefix_num["REPNE"] = "INAT_PFX_REPNE"
         prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+        prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
+        prefix_num["XRELEASE"] = "INAT_PFX_REPE"
         prefix_num["LOCK"] = "INAT_PFX_LOCK"
         prefix_num["SEG=CS"] = "INAT_PFX_CS"
         prefix_num["SEG=DS"] = "INAT_PFX_DS"
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 056d11faef21..8f3eea6b80c5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
         e820_add_region(start, end - start, type);
 }
 
+void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+{
+        struct e820entry *entry;
+        unsigned int i;
+
+        for (i = 0, entry = list; i < map_size; i++, entry++) {
+                if (entry->type == E820_UNUSABLE)
+                        entry->type = E820_RAM;
+        }
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -353,6 +364,17 @@ char * __init xen_memory_setup(void)
         }
         BUG_ON(rc);
 
+        /*
+         * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+         * regions, so if we're using the machine memory map leave the
+         * region as RAM as it is in the pseudo-physical map.
+         *
+         * UNUSABLE regions in domUs are not handled and will need
+         * a patch in the future.
+         */
+        if (xen_initial_domain())
+                xen_ignore_unusable(map, memmap.nr_entries);
+
         /* Make sure the Xen-supplied memory map is well-ordered. */
         sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index ca92754eb846..b81c88e51daa 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -694,8 +694,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
         int rc;
-        rc = native_cpu_up(cpu, tidle);
-        WARN_ON (xen_smp_intr_init(cpu));
+        /*
+         * xen_smp_intr_init() needs to run before native_cpu_up()
+         * so that IPI vectors are set up on the booting CPU before
+         * it is marked online in native_cpu_up().
+        */
+        rc = xen_smp_intr_init(cpu);
+        WARN_ON(rc);
+        if (!rc)
+                rc =  native_cpu_up(cpu, tidle);
         return rc;
 }