Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Several cases of overlapping changes, except the packet scheduler conflicts which deal with the addition of the free list parameter to qdisc_enqueue(). Signed-off-by: David S. Miller <davem@davemloft.net>
author: David S. Miller <davem@davemloft.net> 2016-06-30 05:03:36 -0400
committer: David S. Miller <davem@davemloft.net> 2016-06-30 05:03:36 -0400
commit: ee58b57100ca953da7320c285315a95db2f7053d (patch)
tree: 77b815a31240adc4d6326346908137fc6c2c3a96 /arch
parent: 6f30e8b022c8e3a722928ddb1a2ae0be852fcc0e (diff)
parent: e7bdea7750eb2a64aea4a08fa5c0a31719c8155d (diff)
150 files changed, 873 insertions, 482 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index d794384a0404..15996290fed4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -226,8 +226,8 @@ config ARCH_INIT_TASK
 config ARCH_TASK_STRUCT_ALLOCATOR
        bool
-# Select if arch has its private alloc_thread_info() function
+# Select if arch has its private alloc_thread_stack() function
-config ARCH_THREAD_INFO_ALLOCATOR
+config ARCH_THREAD_STACK_ALLOCATOR
        bool
 # Select if arch wants to size task_struct dynamically via arch_task_struct_size:
@@ -606,6 +606,9 @@ config HAVE_ARCH_HASH
          file which provides platform-specific implementations of some
          functions in <linux/hash.h> or fs/namei.c.
+config ISA_BUS_API
+        def_bool ISA
 #
 # ABI hall of shame
 #
diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h
index aab14a019c20..c2ebb6f36c9d 100644
--- a/arch/alpha/include/asm/pgalloc.h
+++ b/arch/alpha/include/asm/pgalloc.h
@@ -40,7 +40,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pmd_t *
 pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        return ret;
 }
@@ -53,7 +53,7 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        return pte;
 }
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 86ed671286df..3749234b7419 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -95,7 +95,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
        pte_t *pte;
-        pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO,
+        pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
                                         __get_order_pte());
        return pte;
@@ -107,7 +107,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
        pgtable_t pte_pg;
        struct page *page;
-        pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+        pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte());
        if (!pte_pg)
                return 0;
        memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t));
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 06b6c2d695bf..414b42710a36 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -741,6 +741,7 @@ dtb-$(CONFIG_MACH_SUN7I) += \
        sun7i-a20-olimex-som-evb.dtb \
        sun7i-a20-olinuxino-lime.dtb \
        sun7i-a20-olinuxino-lime2.dtb \
+        sun7i-a20-olinuxino-lime2-emmc.dtb \
        sun7i-a20-olinuxino-micro.dtb \
        sun7i-a20-orangepi.dtb \
        sun7i-a20-orangepi-mini.dtb \
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index d82dd6e3f9b1..5687d6b4da60 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -418,7 +418,7 @@
        status = "okay";
        pinctrl-names = "default";
        pinctrl-0 = <&i2c0_pins>;
-        clock-frequency = <400000>;
+        clock-frequency = <100000>;
        tps@24 {
                compatible = "ti,tps65218";
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index b01a5948cdd0..0e63b9dff6e7 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -60,10 +60,26 @@
                tps659038_pmic {
                        compatible = "ti,tps659038-pmic";
+                        smps12-in-supply = <&vmain>;
+                        smps3-in-supply = <&vmain>;
+                        smps45-in-supply = <&vmain>;
+                        smps6-in-supply = <&vmain>;
+                        smps7-in-supply = <&vmain>;
+                        smps8-in-supply = <&vmain>;
+                        smps9-in-supply = <&vmain>;
+                        ldo1-in-supply = <&vmain>;
+                        ldo2-in-supply = <&vmain>;
+                        ldo3-in-supply = <&vmain>;
+                        ldo4-in-supply = <&vmain>;
+                        ldo9-in-supply = <&vmain>;
+                        ldoln-in-supply = <&vmain>;
+                        ldousb-in-supply = <&vmain>;
+                        ldortc-in-supply = <&vmain>;
                        regulators {
                                smps12_reg: smps12 {
                                        /* VDD_MPU */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps12";
                                        regulator-min-microvolt = <850000>;
                                        regulator-max-microvolt = <1250000>;
@@ -73,7 +89,6 @@
                                smps3_reg: smps3 {
                                        /* VDD_DDR EMIF1 EMIF2 */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps3";
                                        regulator-min-microvolt = <1350000>;
                                        regulator-max-microvolt = <1350000>;
@@ -84,7 +99,6 @@
                                smps45_reg: smps45 {
                                        /* VDD_DSPEVE on AM572 */
                                        /* VDD_IVA + VDD_DSP on AM571 */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps45";
                                        regulator-min-microvolt = <850000>;
                                        regulator-max-microvolt = <1250000>;
@@ -94,7 +108,6 @@
                                smps6_reg: smps6 {
                                        /* VDD_GPU */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps6";
                                        regulator-min-microvolt = <850000>;
                                        regulator-max-microvolt = <1250000>;
@@ -104,7 +117,6 @@
                                smps7_reg: smps7 {
                                        /* VDD_CORE */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps7";
                                        regulator-min-microvolt = <850000>;
                                        regulator-max-microvolt = <1150000>;
@@ -115,13 +127,11 @@
                                smps8_reg: smps8 {
                                        /* 5728 - VDD_IVAHD */
                                        /* 5718 - N.C. test point */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps8";
                                };
                                smps9_reg: smps9 {
                                        /* VDD_3_3D */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "smps9";
                                        regulator-min-microvolt = <3300000>;
                                        regulator-max-microvolt = <3300000>;
@@ -132,7 +142,6 @@
                                ldo1_reg: ldo1 {
                                        /* VDDSHV8 - VSDMMC  */
                                        /* NOTE: on rev 1.3a, data supply */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldo1";
                                        regulator-min-microvolt = <1800000>;
                                        regulator-max-microvolt = <3300000>;
@@ -142,7 +151,6 @@
                                ldo2_reg: ldo2 {
                                        /* VDDSH18V */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldo2";
                                        regulator-min-microvolt = <1800000>;
                                        regulator-max-microvolt = <1800000>;
@@ -152,7 +160,6 @@
                                ldo3_reg: ldo3 {
                                        /* R1.3a 572x V1_8PHY_LDO3: USB, SATA */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldo3";
                                        regulator-min-microvolt = <1800000>;
                                        regulator-max-microvolt = <1800000>;
@@ -162,7 +169,6 @@
                                ldo4_reg: ldo4 {
                                        /* R1.3a 572x V1_8PHY_LDO4: PCIE, HDMI*/
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldo4";
                                        regulator-min-microvolt = <1800000>;
                                        regulator-max-microvolt = <1800000>;
@@ -174,7 +180,6 @@
                                ldo9_reg: ldo9 {
                                        /* VDD_RTC  */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldo9";
                                        regulator-min-microvolt = <840000>;
                                        regulator-max-microvolt = <1160000>;
@@ -184,7 +189,6 @@
                                ldoln_reg: ldoln {
                                        /* VDDA_1V8_PLL */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldoln";
                                        regulator-min-microvolt = <1800000>;
                                        regulator-max-microvolt = <1800000>;
@@ -194,7 +198,6 @@
                                ldousb_reg: ldousb {
                                        /* VDDA_3V_USB: VDDA_USBHS33 */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldousb";
                                        regulator-min-microvolt = <3300000>;
                                        regulator-max-microvolt = <3300000>;
@@ -204,7 +207,6 @@
                                ldortc_reg: ldortc {
                                        /* VDDA_RTC  */
-                                        vin-supply = <&vmain>;
                                        regulator-name = "ldortc";
                                        regulator-min-microvolt = <1800000>;
                                        regulator-max-microvolt = <1800000>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index cbc17b0794b1..4128fa91823c 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -93,6 +93,10 @@
        };
 };
+&mmc1 {
+        status = "disabled";
+};
 &mmc2 {
        pinctrl-names = "default";
        pinctrl-0 = <&sd1_pins>;
@@ -101,6 +105,10 @@
        cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
 };
+&mmc3 {
+        status = "disabled";
+};
 &pincntl {
        sd1_pins: pinmux_sd1_pins {
                pinctrl-single,pins = <
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 5d4313fd5a46..3f184863e0c5 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -45,6 +45,14 @@
        phy-mode = "rgmii";
 };
+&mmc1 {
+        status = "disabled";
+};
+&mmc2 {
+        status = "disabled";
+};
 &mmc3 {
        pinctrl-names = "default";
        pinctrl-0 = <&sd2_pins>;
@@ -53,6 +61,7 @@
        dmas = <&edma_xbar 8 0 1        /* use SDTXEVT1 instead of MCASP0TX */
                &edma_xbar 9 0 2>;      /* use SDRXEVT1 instead of MCASP0RX */
        dma-names = "tx", "rx";
+        non-removable;
 };
 &pincntl {
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index f8b39a5a487a..de559f6e4fee 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1451,6 +1451,8 @@
                        ti,hwmods = "gpmc";
                        reg = <0x50000000 0x37c>;      /* device IO registers */
                        interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
+                        dmas = <&edma_xbar 4 0>;
+                        dma-names = "rxtx";
                        gpmc,num-cs = <8>;
                        gpmc,num-waitpins = <2>;
                        #address-cells = <2>;
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index 4220eeffc65a..5e06020f450b 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -107,8 +107,8 @@
        reg = <0x58000000 0x80>,
              <0x58004054 0x4>,
              <0x58004300 0x20>,
-              <0x58005054 0x4>,
+              <0x58009054 0x4>,
-              <0x58005300 0x20>;
+              <0x58009300 0x20>;
        reg-names = "dss", "pll1_clkctrl", "pll1",
                    "pll2_clkctrl", "pll2";
diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
index ddfe1f558c10..fa14f77df563 100644
--- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi
+++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
@@ -242,7 +242,7 @@
        hpd-gpios = <&gpx0 7 GPIO_ACTIVE_HIGH>;
        ports {
-                port0 {
+                port {
                        dp_out: endpoint {
                                remote-endpoint = <&bridge_in>;
                        };
@@ -485,13 +485,20 @@
                edid-emulation = <5>;
                ports {
-                        port0 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        port@0 {
+                                reg = <0>;
                                bridge_out: endpoint {
                                        remote-endpoint = <&panel_in>;
                                };
                        };
-                        port1 {
+                        port@1 {
+                                reg = <1>;
                                bridge_in: endpoint {
                                        remote-endpoint = <&dp_out>;
                                };
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index f9d2e4f1a0e0..1de972d46a87 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -163,7 +163,7 @@
        hpd-gpios = <&gpx2 6 GPIO_ACTIVE_HIGH>;
        ports {
-                port0 {
+                port {
                        dp_out: endpoint {
                                remote-endpoint = <&bridge_in>;
                        };
@@ -631,13 +631,20 @@
                use-external-pwm;
                ports {
-                        port0 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        port@0 {
+                                reg = <0>;
                                bridge_out: endpoint {
                                        remote-endpoint = <&panel_in>;
                                };
                        };
-                        port1 {
+                        port@1 {
+                                reg = <1>;
                                bridge_in: endpoint {
                                        remote-endpoint = <&dp_out>;
                                };
diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts
index 76056ba92ced..ed449827c3d3 100644
--- a/arch/arm/boot/dts/omap3-evm-37xx.dts
+++ b/arch/arm/boot/dts/omap3-evm-37xx.dts
@@ -85,7 +85,7 @@
                        OMAP3_CORE1_IOPAD(0x2158, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_clk.sdmmc2_clk */
                        OMAP3_CORE1_IOPAD(0x215a, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_cmd.sdmmc2_cmd */
                        OMAP3_CORE1_IOPAD(0x215c, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat0.sdmmc2_dat0 */
-                        OMAP3_CORE1_IOPAD(0x215e, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */
+                        OMAP3_CORE1_IOPAD(0x215e, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */
                        OMAP3_CORE1_IOPAD(0x2160, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat2.sdmmc2_dat2 */
                        OMAP3_CORE1_IOPAD(0x2162, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat3.sdmmc2_dat3 */
                >;
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index 41f5d386f21f..f4f2ce46d681 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -188,6 +188,7 @@
        vmmc-supply = <&vmmc1>;
        vmmc_aux-supply = <&vsim>;
        bus-width = <4>;
+        cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>;
 };
 &mmc3 {
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index d6f839cab649..b6971060648a 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -194,6 +194,12 @@
                        OMAP3630_CORE2_IOPAD(0x25f8, PIN_OUTPUT | MUX_MODE4) /* etk_d14.gpio_28 */
                >;
        };
+        mmc1_wp_pins: pinmux_mmc1_cd_pins {
+                pinctrl-single,pins = <
+                        OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT | MUX_MODE4)   /* etk_d15.gpio_29 */
+                >;
+        };
 };
 &i2c3 {
@@ -250,3 +256,8 @@
                };
        };
 };
+&mmc1 {
+        pinctrl-0 = <&mmc1_pins &mmc1_wp_pins>;
+        wp-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>; /* gpio_29 */
+};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index d9e2d9c6e999..2b74a81d1de2 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -288,7 +288,7 @@
                pinctrl-single,pins = <
                        OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */
                        OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1)               /* ssi1_flag_tx */
-                        OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+                        OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4)                /* ssi1_wake_tx (cawake) */
                        OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1)               /* ssi1_dat_tx */
                        OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1)                /* ssi1_dat_rx */
                        OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1)                /* ssi1_flag_rx */
@@ -300,7 +300,7 @@
        modem_pins: pinmux_modem {
                pinctrl-single,pins = <
                        OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE4)               /* gpio 70 => cmt_apeslpx */
-                        OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio 72 => ape_rst_rq */
+                        OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | MUX_MODE4)                /* gpio 72 => ape_rst_rq */
                        OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE4)               /* gpio 73 => cmt_rst_rq */
                        OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE4)               /* gpio 74 => cmt_en */
                        OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE4)               /* gpio 75 => cmt_rst */
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index a00ca761675d..927b17fc4ed8 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -97,7 +97,7 @@
                        OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1)            /* ssi1_dat_tx */
                        OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1)            /* ssi1_flag_tx */
                        OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1)      /* ssi1_rdy_tx */
-                        OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+                        OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4)        /* ssi1_wake_tx (cawake) */
                        OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1)             /* ssi1_dat_rx */
                        OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1)             /* ssi1_flag_rx */
                        OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE1)            /* ssi1_rdy_rx */
@@ -110,7 +110,7 @@
                        OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE7)            /* ssi1_dat_tx */
                        OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE7)            /* ssi1_flag_tx */
                        OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLDOWN | MUX_MODE7)    /* ssi1_rdy_tx */
-                        OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+                        OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4)        /* ssi1_wake_tx (cawake) */
                        OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE7)             /* ssi1_dat_rx */
                        OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE7)             /* ssi1_flag_rx */
                        OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE4)            /* ssi1_rdy_rx */
@@ -120,7 +120,7 @@
        modem_pins1: pinmux_modem_core1_pins {
                pinctrl-single,pins = <
-                        OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio_34 (ape_rst_rq) */
+                        OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | MUX_MODE4)        /* gpio_34 (ape_rst_rq) */
                        OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE4)            /* gpio_88 (cmt_rst_rq) */
                        OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE4)            /* gpio_93 (cmt_apeslpx) */
                >;
diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts
index f19170bdcc1f..c29b41dc7b95 100644
--- a/arch/arm/boot/dts/omap3-zoom3.dts
+++ b/arch/arm/boot/dts/omap3-zoom3.dts
@@ -98,7 +98,7 @@
                pinctrl-single,pins = <
                        OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */
                        OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0)               /* uart2_rts.uart2_rts */
-                        OMAP3_CORE1_IOPAD(0x217a, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */
+                        OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0)                /* uart2_rx.uart2_rx */
                        OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0)               /* uart2_tx.uart2_tx */
                >;
        };
@@ -107,7 +107,7 @@
                pinctrl-single,pins = <
                        OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0)       /* uart3_cts_rctx.uart3_cts_rctx */
                        OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0)               /* uart3_rts_sd.uart3_rts_sd */
-                        OMAP3_CORE1_IOPAD(0x219e, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */
+                        OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0)                /* uart3_rx_irrx.uart3_rx_irrx */
                        OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0)               /* uart3_tx_irtx.uart3_tx_irtx */
                >;
        };
@@ -125,7 +125,7 @@
                pinctrl-single,pins = <
                        OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2)      /* etk_clk.sdmmc3_clk */
                        OMAP3630_CORE2_IOPAD(0x25e4, PIN_INPUT_PULLUP | MUX_MODE2)      /* etk_d4.sdmmc3_dat0 */
-                        OMAP3630_CORE2_IOPAD(0x25e6, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */
+                        OMAP3630_CORE2_IOPAD(0x25e6, PIN_INPUT_PULLUP | MUX_MODE2)      /* etk_d5.sdmmc3_dat1 */
                        OMAP3630_CORE2_IOPAD(0x25e8, PIN_INPUT_PULLUP | MUX_MODE2)      /* etk_d6.sdmmc3_dat2 */
                        OMAP3630_CORE2_IOPAD(0x25e2, PIN_INPUT_PULLUP | MUX_MODE2)      /* etk_d3.sdmmc3_dat3 */
                >;
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index dc759a3028b7..5d5b620b7d9b 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -14,6 +14,29 @@
                display0 = &hdmi0;
        };
+        vmain: fixedregulator-vmain {
+                compatible = "regulator-fixed";
+                regulator-name = "vmain";
+                regulator-min-microvolt = <5000000>;
+                regulator-max-microvolt = <5000000>;
+        };
+        vsys_cobra: fixedregulator-vsys_cobra {
+                compatible = "regulator-fixed";
+                regulator-name = "vsys_cobra";
+                vin-supply = <&vmain>;
+                regulator-min-microvolt = <5000000>;
+                regulator-max-microvolt = <5000000>;
+        };
+        vdds_1v8_main: fixedregulator-vdds_1v8_main {
+                compatible = "regulator-fixed";
+                regulator-name = "vdds_1v8_main";
+                vin-supply = <&smps7_reg>;
+                regulator-min-microvolt = <1800000>;
+                regulator-max-microvolt = <1800000>;
+        };
        vmmcsd_fixed: fixedregulator-mmcsd {
                compatible = "regulator-fixed";
                regulator-name = "vmmcsd_fixed";
@@ -309,7 +332,7 @@
        wlcore_irq_pin: pinmux_wlcore_irq_pin {
                pinctrl-single,pins = <
-                        OMAP5_IOPAD(0x40, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE6)     /* llia_wakereqin.gpio1_wk14 */
+                        OMAP5_IOPAD(0x40, PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */
                >;
        };
 };
@@ -409,6 +432,26 @@
                        ti,ldo6-vibrator;
+                        smps123-in-supply = <&vsys_cobra>;
+                        smps45-in-supply = <&vsys_cobra>;
+                        smps6-in-supply = <&vsys_cobra>;
+                        smps7-in-supply = <&vsys_cobra>;
+                        smps8-in-supply = <&vsys_cobra>;
+                        smps9-in-supply = <&vsys_cobra>;
+                        smps10_out2-in-supply = <&vsys_cobra>;
+                        smps10_out1-in-supply = <&vsys_cobra>;
+                        ldo1-in-supply = <&vsys_cobra>;
+                        ldo2-in-supply = <&vsys_cobra>;
+                        ldo3-in-supply = <&vdds_1v8_main>;
+                        ldo4-in-supply = <&vdds_1v8_main>;
+                        ldo5-in-supply = <&vsys_cobra>;
+                        ldo6-in-supply = <&vdds_1v8_main>;
+                        ldo7-in-supply = <&vsys_cobra>;
+                        ldo8-in-supply = <&vsys_cobra>;
+                        ldo9-in-supply = <&vmmcsd_fixed>;
+                        ldoln-in-supply = <&vsys_cobra>;
+                        ldousb-in-supply = <&vsys_cobra>;
                        regulators {
                                smps123_reg: smps123 {
                                        /* VDD_OPP_MPU */
@@ -600,7 +643,8 @@
                pinctrl-0 = <&twl6040_pins>;
                interrupts = <GIC_SPI 119 IRQ_TYPE_NONE>; /* IRQ_SYS_2N cascaded to gic */
-                ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>;  /* gpio line 141 */
+                /* audpwron gpio defined in the board specific dts */
                vio-supply = <&smps7_reg>;
                v2v1-supply = <&smps9_reg>;
diff --git a/arch/arm/boot/dts/omap5-igep0050.dts b/arch/arm/boot/dts/omap5-igep0050.dts
index 46ecb1dd3b5c..f75ce02fb398 100644
--- a/arch/arm/boot/dts/omap5-igep0050.dts
+++ b/arch/arm/boot/dts/omap5-igep0050.dts
@@ -35,6 +35,22 @@
        };
 };
+/* LDO4 is VPP1 - ball AD9 */
+&ldo4_reg {
+        regulator-min-microvolt = <2000000>;
+        regulator-max-microvolt = <2000000>;
+};
+/*
+ * LDO7 is used for HDMI: VDDA_DSIPORTA - ball AA33, VDDA_DSIPORTC - ball AE33,
+ * VDDA_HDMI - ball AN25
+ */
+&ldo7_reg {
+        status = "okay";
+        regulator-min-microvolt = <1800000>;
+        regulator-max-microvolt = <1800000>;
+};
 &omap5_pmx_core {
        i2c4_pins: pinmux_i2c4_pins {
                pinctrl-single,pins = <
@@ -52,3 +68,13 @@
                <&gpio7 3 0>;           /* 195, SDA */
 };
+&twl6040 {
+        ti,audpwron-gpio = <&gpio5 16 GPIO_ACTIVE_HIGH>;  /* gpio line 144 */
+};
+&twl6040_pins {
+        pinctrl-single,pins = <
+                OMAP5_IOPAD(0x1c4, PIN_OUTPUT | MUX_MODE6)      /* mcspi1_somi.gpio5_144 */
+                OMAP5_IOPAD(0x1ca, PIN_OUTPUT | MUX_MODE6)      /* perslimbus2_clock.gpio5_145 */
+        >;
+};
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 60b3fbb3bf07..a51e60518eb6 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -51,3 +51,13 @@
                <&gpio9 1 GPIO_ACTIVE_HIGH>,    /* TCA6424A P00, LS OE */
                <&gpio7 1 GPIO_ACTIVE_HIGH>;    /* GPIO 193, HPD */
 };
+&twl6040 {
+        ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>;  /* gpio line 141 */
+};
+&twl6040_pins {
+        pinctrl-single,pins = <
+                OMAP5_IOPAD(0x1be, PIN_OUTPUT | MUX_MODE6)      /* mcspi1_somi.gpio5_141 */
+        >;
+};
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
index a3601e4c0a2e..b844473601d2 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
@@ -136,6 +136,7 @@
 &gmac1 {
        status = "okay";
        phy-mode = "rgmii";
+        phy-handle = <&phy1>;
        snps,reset-gpio = <&porta 0 GPIO_ACTIVE_LOW>;
        snps,reset-active-low;
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index ad8ba10764a3..d294e82447a2 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -24,18 +24,21 @@
                        compatible = "shared-dma-pool";
                        reg = <0x40000000 0x01000000>;
                        no-map;
+                        status = "disabled";
                };
                gp1_reserved: rproc@41000000 {
                        compatible = "shared-dma-pool";
                        reg = <0x41000000 0x01000000>;
                        no-map;
+                        status = "disabled";
                };
                audio_reserved: rproc@42000000 {
                        compatible = "shared-dma-pool";
                        reg = <0x42000000 0x01000000>;
                        no-map;
+                        status = "disabled";
                };
                dmu_reserved: rproc@43000000 {
diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
index 68b479b8772c..73c133f5e79c 100644
--- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
@@ -176,8 +176,6 @@
 };
 &reg_dc1sw {
-        regulator-min-microvolt = <3000000>;
-        regulator-max-microvolt = <3000000>;
        regulator-name = "vcc-lcd";
 };
diff --git a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
index 360adfb1e9ca..d6ad6196a768 100644
--- a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
@@ -135,8 +135,6 @@
 &reg_dc1sw {
        regulator-name = "vcc-lcd-usb2";
-        regulator-min-microvolt = <3000000>;
-        regulator-max-microvolt = <3000000>;
 };
 &reg_dc5ldo {
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 10f49ab5328e..47195e8690b4 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -82,6 +82,7 @@ CONFIG_TOUCHSCREEN_MMS114=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_MAX77693_HAPTIC=y
 CONFIG_INPUT_MAX8997_HAPTIC=y
+CONFIG_KEYBOARD_SAMSUNG=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_SAMSUNG=y
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 8f857564657f..8a5fff1b7f6f 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -264,6 +264,7 @@ CONFIG_KEYBOARD_TEGRA=y
 CONFIG_KEYBOARD_SPEAR=y
 CONFIG_KEYBOARD_ST_KEYSCAN=y
 CONFIG_KEYBOARD_CROS_EC=m
+CONFIG_KEYBOARD_SAMSUNG=m
 CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_MOUSE_CYAPA=m
 CONFIG_MOUSE_ELAN_I2C=y
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 19cfab526d13..20febb368844 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -29,7 +29,7 @@
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+        return (pmd_t *)get_zeroed_page(GFP_KERNEL);
 }
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index aeddd28b3595..92fd2c8a9af0 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_large(pmd)          (pmd_val(pmd) & 2)
 #define pmd_bad(pmd)            (pmd_val(pmd) & 2)
+#define pmd_present(pmd)        (pmd_val(pmd))
 #define copy_pmd(pmdpd,pmdps)           \
        do {                            \
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index fa70db7c714b..2a029bceaf2f 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -211,6 +211,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
                                                : !!(pmd_val(pmd) & (val)))
 #define pmd_isclear(pmd, val)   (!(pmd_val(pmd) & (val)))
+#define pmd_present(pmd)        (pmd_isset((pmd), L_PMD_SECT_VALID))
 #define pmd_young(pmd)          (pmd_isset((pmd), PMD_SECT_AF))
 #define pte_special(pte)        (pte_isset((pte), L_PTE_SPECIAL))
 static inline pte_t pte_mkspecial(pte_t pte)
@@ -249,10 +250,10 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #define pfn_pmd(pfn,prot)       (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 #define mk_pmd(page,prot)       pfn_pmd(page_to_pfn(page),prot)
-/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
-        return __pmd(0);
+        return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID);
 }
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 348caabb7625..d62204060cbe 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 #define pgd_offset_k(addr)      pgd_offset(&init_mm, addr)
 #define pmd_none(pmd)           (!pmd_val(pmd))
-#define pmd_present(pmd)        (pmd_val(pmd))
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index df90bc59bfce..861521606c6d 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -486,7 +486,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 {
-        trace_ipi_raise(target, ipi_types[ipinr]);
+        trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
        __smp_cross_call(target, ipinr);
 }
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index e65aa7d11b20..20dcf6e904b2 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -61,7 +61,6 @@ config ARCH_EXYNOS4
        select CLKSRC_SAMSUNG_PWM if CPU_EXYNOS4210
        select CPU_EXYNOS4210
        select GIC_NON_BANKED
-        select KEYBOARD_SAMSUNG if INPUT_KEYBOARD
        select MIGHT_HAVE_CACHE_L2X0
        help
          Samsung EXYNOS4 (Cortex-A9) SoC based systems
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index a38b16b69923..b56de4b8cdf2 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev)
 static void __init imx6ul_enet_phy_init(void)
 {
        if (IS_BUILTIN(CONFIG_PHYLIB))
-                phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff,
+                phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK,
                                           ksz8081_phy_fixup);
 }
diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 5d7fb596bf4a..bf608441b357 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -43,8 +43,8 @@
 #define OTHERS_MASK                     (MODEM_IRQ_MASK | HOOK_SWITCH_MASK)
 /* IRQ handler register bitmasks */
-#define DEFERRED_FIQ_MASK               (0x1 << (INT_DEFERRED_FIQ % IH2_BASE))
+#define DEFERRED_FIQ_MASK               OMAP_IRQ_BIT(INT_DEFERRED_FIQ)
-#define GPIO_BANK1_MASK                 (0x1 << INT_GPIO_BANK1)
+#define GPIO_BANK1_MASK                 OMAP_IRQ_BIT(INT_GPIO_BANK1)
 /* Driver buffer byte offsets */
 #define BUF_MASK                        (FIQ_MASK * 4)
@@ -110,7 +110,7 @@ ENTRY(qwerty_fiqin_start)
        mov r8, #2                              @ reset FIQ agreement
        str r8, [r12, #IRQ_CONTROL_REG_OFFSET]
-        cmp r10, #INT_GPIO_BANK1                @ is it GPIO bank interrupt?
+        cmp r10, #(INT_GPIO_BANK1 - NR_IRQS_LEGACY)     @ is it GPIO interrupt?
        beq gpio                                @ yes - process it
        mov r8, #1
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index d1f12095f315..ec760ae2f917 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -109,7 +109,8 @@ void __init ams_delta_init_fiq(void)
         * Since no set_type() method is provided by OMAP irq chip,
         * switch to edge triggered interrupt type manually.
         */
-        offset = IRQ_ILR0_REG_OFFSET + INT_DEFERRED_FIQ * 0x4;
+        offset = IRQ_ILR0_REG_OFFSET +
+                        ((INT_DEFERRED_FIQ - NR_IRQS_LEGACY) & 0x1f) * 0x4;
        val = omap_readl(DEFERRED_FIQ_IH_BASE + offset) & ~(1 << 1);
        omap_writel(val, DEFERRED_FIQ_IH_BASE + offset);
@@ -149,7 +150,7 @@ void __init ams_delta_init_fiq(void)
        /*
         * Redirect GPIO interrupts to FIQ
         */
-        offset = IRQ_ILR0_REG_OFFSET + INT_GPIO_BANK1 * 0x4;
+        offset = IRQ_ILR0_REG_OFFSET + (INT_GPIO_BANK1 - NR_IRQS_LEGACY) * 0x4;
        val = omap_readl(OMAP_IH1_BASE + offset) | 1;
        omap_writel(val, OMAP_IH1_BASE + offset);
 }
diff --git a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
index adb5e7649659..6dfc3e1210a3 100644
--- a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
+++ b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
@@ -14,6 +14,8 @@
 #ifndef __AMS_DELTA_FIQ_H
 #define __AMS_DELTA_FIQ_H
+#include <mach/irqs.h>
 /*
 * Interrupt number used for passing control from FIQ to IRQ.
 * IRQ12, described as reserved, has been selected.
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 0517f0c1581a..1a648e9dfaa0 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -17,6 +17,7 @@ config ARCH_OMAP3
        select PM_OPP if PM
        select PM if CPU_IDLE
        select SOC_HAS_OMAP2_SDRC
+        select ARM_ERRATA_430973
 config ARCH_OMAP4
        bool "TI OMAP4"
@@ -36,6 +37,7 @@ config ARCH_OMAP4
        select PM if CPU_IDLE
        select ARM_ERRATA_754322
        select ARM_ERRATA_775420
+        select OMAP_INTERCONNECT
 config SOC_OMAP5
        bool "TI OMAP5"
@@ -67,6 +69,8 @@ config SOC_AM43XX
        select HAVE_ARM_SCU
        select GENERIC_CLOCKEVENTS_BROADCAST
        select HAVE_ARM_TWD
+        select ARM_ERRATA_754322
+        select ARM_ERRATA_775420
 config SOC_DRA7XX
        bool "TI DRA7XX"
@@ -240,4 +244,12 @@ endmenu
 endif
+config OMAP5_ERRATA_801819
+        bool "Errata 801819: An eviction from L1 data cache might stall indefinitely"
+        depends on SOC_OMAP5 || SOC_DRA7XX
+        help
+          A livelock can occur in the L2 cache arbitration that might prevent
+          a snoop from completing. Under certain conditions this can cause the
+          system to deadlock.
 endmenu
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index af2851fbcdf0..bae263fba640 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -46,6 +46,7 @@
 #define OMAP5_DRA7_MON_SET_CNTFRQ_INDEX 0x109
 #define OMAP5_MON_AMBA_IF_INDEX         0x108
+#define OMAP5_DRA7_MON_SET_ACR_INDEX    0x107
 /* Secure PPA(Primary Protected Application) APIs */
 #define OMAP4_PPA_L2_POR_INDEX          0x23
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index c625cc10d9f9..8cd1de914ee4 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -50,6 +50,39 @@ void __iomem *omap4_get_scu_base(void)
        return scu_base;
 }
+#ifdef CONFIG_OMAP5_ERRATA_801819
+void omap5_erratum_workaround_801819(void)
+{
+        u32 acr, revidr;
+        u32 acr_mask;
+        /* REVIDR[3] indicates erratum fix available on silicon */
+        asm volatile ("mrc p15, 0, %0, c0, c0, 6" : "=r" (revidr));
+        if (revidr & (0x1 << 3))
+                return;
+        asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr));
+        /*
+         * BIT(27) - Disables streaming. All write-allocate lines allocate in
+         * the L1 or L2 cache.
+         * BIT(25) - Disables streaming. All write-allocate lines allocate in
+         * the L1 cache.
+         */
+        acr_mask = (0x3 << 25) | (0x3 << 27);
+        /* do we already have it done.. if yes, skip expensive smc */
+        if ((acr & acr_mask) == acr_mask)
+                return;
+        acr |= acr_mask;
+        omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr);
+        pr_debug("%s: ARM erratum workaround 801819 applied on CPU%d\n",
+                 __func__, smp_processor_id());
+}
+#else
+static inline void omap5_erratum_workaround_801819(void) { }
+#endif
 static void omap4_secondary_init(unsigned int cpu)
 {
        /*
@@ -64,12 +97,15 @@ static void omap4_secondary_init(unsigned int cpu)
                omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX,
                                                        4, 0, 0, 0, 0, 0);
-        /*
+        if (soc_is_omap54xx() || soc_is_dra7xx()) {
-         * Configure the CNTFRQ register for the secondary cpu's which
+                /*
-         * indicates the frequency of the cpu local timers.
+                 * Configure the CNTFRQ register for the secondary cpu's which
-         */
+                 * indicates the frequency of the cpu local timers.
-        if (soc_is_omap54xx() || soc_is_dra7xx())
+                 */
                set_cntfreq();
+                /* Configure ACR to disable streaming WA for 801819 */
+                omap5_erratum_workaround_801819();
+        }
        /*
         * Synchronise with the boot thread.
@@ -218,6 +254,8 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
        if (cpu_is_omap446x())
                startup_addr = omap4460_secondary_startup;
+        if (soc_is_dra74x() || soc_is_omap54xx())
+                omap5_erratum_workaround_801819();
        /*
         * Write the address of secondary startup routine into the
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 78af6d8cf2e2..daf2753de7aa 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -186,8 +186,9 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag)
                        trace_state = (PWRDM_TRACE_STATES_FLAG |
                                       ((next & OMAP_POWERSTATE_MASK) << 8) |
                                       ((prev & OMAP_POWERSTATE_MASK) << 0));
-                        trace_power_domain_target(pwrdm->name, trace_state,
+                        trace_power_domain_target_rcuidle(pwrdm->name,
-                                                  smp_processor_id());
+                                                          trace_state,
+                                                          smp_processor_id());
                }
                break;
        default:
@@ -523,8 +524,8 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
        if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
                /* Trace the pwrdm desired target state */
-                trace_power_domain_target(pwrdm->name, pwrst,
+                trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
-                                          smp_processor_id());
+                                                  smp_processor_id());
                /* Program the pwrdm desired target state */
                ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);
        }
diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c
index 0ec2d00f4237..eb350a673133 100644
--- a/arch/arm/mach-omap2/powerdomains7xx_data.c
+++ b/arch/arm/mach-omap2/powerdomains7xx_data.c
@@ -36,14 +36,7 @@ static struct powerdomain iva_7xx_pwrdm = {
        .prcm_offs        = DRA7XX_PRM_IVA_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
-        .pwrsts_logic_ret = PWRSTS_OFF,
        .banks            = 4,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* hwa_mem */
-                [1] = PWRSTS_OFF_RET,   /* sl2_mem */
-                [2] = PWRSTS_OFF_RET,   /* tcm1_mem */
-                [3] = PWRSTS_OFF_RET,   /* tcm2_mem */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* hwa_mem */
                [1] = PWRSTS_ON,        /* sl2_mem */
@@ -76,12 +69,7 @@ static struct powerdomain ipu_7xx_pwrdm = {
        .prcm_offs        = DRA7XX_PRM_IPU_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
-        .pwrsts_logic_ret = PWRSTS_OFF,
        .banks            = 2,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* aessmem */
-                [1] = PWRSTS_OFF_RET,   /* periphmem */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* aessmem */
                [1] = PWRSTS_ON,        /* periphmem */
@@ -95,11 +83,7 @@ static struct powerdomain dss_7xx_pwrdm = {
        .prcm_offs        = DRA7XX_PRM_DSS_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
-        .pwrsts_logic_ret = PWRSTS_OFF,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* dss_mem */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* dss_mem */
        },
@@ -111,13 +95,8 @@ static struct powerdomain l4per_7xx_pwrdm = {
        .name             = "l4per_pwrdm",
        .prcm_offs        = DRA7XX_PRM_L4PER_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
-        .pwrsts           = PWRSTS_RET_ON,
+        .pwrsts           = PWRSTS_ON,
-        .pwrsts_logic_ret = PWRSTS_RET,
        .banks            = 2,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* nonretained_bank */
-                [1] = PWRSTS_OFF_RET,   /* retained_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* nonretained_bank */
                [1] = PWRSTS_ON,        /* retained_bank */
@@ -132,9 +111,6 @@ static struct powerdomain gpu_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* gpu_mem */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* gpu_mem */
        },
@@ -148,8 +124,6 @@ static struct powerdomain wkupaon_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* wkup_bank */
        },
@@ -161,15 +135,7 @@ static struct powerdomain core_7xx_pwrdm = {
        .prcm_offs        = DRA7XX_PRM_CORE_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_ON,
-        .pwrsts_logic_ret = PWRSTS_RET,
        .banks            = 5,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* core_nret_bank */
-                [1] = PWRSTS_OFF_RET,   /* core_ocmram */
-                [2] = PWRSTS_OFF_RET,   /* core_other_bank */
-                [3] = PWRSTS_OFF_RET,   /* ipu_l2ram */
-                [4] = PWRSTS_OFF_RET,   /* ipu_unicache */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* core_nret_bank */
                [1] = PWRSTS_ON,        /* core_ocmram */
@@ -226,11 +192,7 @@ static struct powerdomain vpe_7xx_pwrdm = {
        .prcm_offs        = DRA7XX_PRM_VPE_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
-        .pwrsts_logic_ret = PWRSTS_OFF,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* vpe_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* vpe_bank */
        },
@@ -260,14 +222,8 @@ static struct powerdomain l3init_7xx_pwrdm = {
        .name             = "l3init_pwrdm",
        .prcm_offs        = DRA7XX_PRM_L3INIT_INST,
        .prcm_partition   = DRA7XX_PRM_PARTITION,
-        .pwrsts           = PWRSTS_RET_ON,
+        .pwrsts           = PWRSTS_ON,
-        .pwrsts_logic_ret = PWRSTS_RET,
        .banks            = 3,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* gmac_bank */
-                [1] = PWRSTS_OFF_RET,   /* l3init_bank1 */
-                [2] = PWRSTS_OFF_RET,   /* l3init_bank2 */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* gmac_bank */
                [1] = PWRSTS_ON,        /* l3init_bank1 */
@@ -283,9 +239,6 @@ static struct powerdomain eve3_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* eve3_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* eve3_bank */
        },
@@ -299,9 +252,6 @@ static struct powerdomain emu_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* emu_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* emu_bank */
        },
@@ -314,11 +264,6 @@ static struct powerdomain dsp2_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 3,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* dsp2_edma */
-                [1] = PWRSTS_OFF_RET,   /* dsp2_l1 */
-                [2] = PWRSTS_OFF_RET,   /* dsp2_l2 */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* dsp2_edma */
                [1] = PWRSTS_ON,        /* dsp2_l1 */
@@ -334,11 +279,6 @@ static struct powerdomain dsp1_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 3,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* dsp1_edma */
-                [1] = PWRSTS_OFF_RET,   /* dsp1_l1 */
-                [2] = PWRSTS_OFF_RET,   /* dsp1_l2 */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* dsp1_edma */
                [1] = PWRSTS_ON,        /* dsp1_l1 */
@@ -354,9 +294,6 @@ static struct powerdomain cam_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* vip_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* vip_bank */
        },
@@ -370,9 +307,6 @@ static struct powerdomain eve4_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* eve4_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* eve4_bank */
        },
@@ -386,9 +320,6 @@ static struct powerdomain eve2_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* eve2_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* eve2_bank */
        },
@@ -402,9 +333,6 @@ static struct powerdomain eve1_7xx_pwrdm = {
        .prcm_partition   = DRA7XX_PRM_PARTITION,
        .pwrsts           = PWRSTS_OFF_ON,
        .banks            = 1,
-        .pwrsts_mem_ret = {
-                [0] = PWRSTS_OFF_RET,   /* eve1_bank */
-        },
        .pwrsts_mem_on  = {
                [0] = PWRSTS_ON,        /* eve1_bank */
        },
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 5b385bb8aff9..cb9497a20fb3 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -496,8 +496,7 @@ void __init omap_init_time(void)
        __omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon",
                        2, "timer_sys_ck", NULL, false);
-        if (of_have_populated_dt())
+        clocksource_probe();
-                clocksource_probe();
 }
 #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX)
@@ -505,6 +504,8 @@ void __init omap3_secure_sync32k_timer_init(void)
 {
        __omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure",
                        2, "timer_sys_ck", NULL, false);
+        clocksource_probe();
 }
 #endif /* CONFIG_ARCH_OMAP3 */
@@ -513,6 +514,8 @@ void __init omap3_gptimer_timer_init(void)
 {
        __omap_sync32k_timer_init(2, "timer_sys_ck", NULL,
                        1, "timer_sys_ck", "ti,timer-alwon", true);
+        clocksource_probe();
 }
 #endif
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 84baa16f4c0b..e93aa6734147 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -68,7 +68,7 @@
 #include <linux/platform_data/asoc-s3c.h>
 #include <linux/platform_data/spi-s3c64xx.h>
-static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
+#define samsung_device_dma_mask (*((u64[]) { DMA_BIT_MASK(32) }))
 /* AC97 */
 #ifdef CONFIG_CPU_S3C2440
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 7085e322dc42..648a32c89541 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -95,7 +95,7 @@ boot := arch/arm64/boot
 Image: vmlinux
        $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-Image.%: vmlinux
+Image.%: Image
        $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 zinstall install:
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 3a4e9a2ab313..fbafa24cd533 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -125,7 +125,7 @@
                #size-cells = <1>;
                #interrupts-cells = <3>;
-                compatible = "arm,amba-bus";
+                compatible = "simple-bus";
                interrupt-parent = <&gic>;
                ranges;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 46f325a143b0..d7f8e06910bc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -163,7 +163,7 @@
        };
        amba {
-                compatible = "arm,amba-bus";
+                compatible = "simple-bus";
                #address-cells = <2>;
                #size-cells = <2>;
                ranges;
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c8120c..da84645525b9 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
 #endif /* !__ASSEMBLY__ */
 /*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
 *
 * General purpose regs:
 *     r0-r30: 64 bit
 *     sp,pc : 64 bit
- *     pstate  : 64 bit
+ *     pstate  : 32 bit
- *     Total: 34
+ *     Total: 33 + 1
 * FPU regs:
 *     f0-f31: 128 bit
- *     Total: 32
- * Extra regs
 *     fpsr & fpcr: 32 bit
- *     Total: 2
+ *     Total: 32 + 2
 *
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
 */
-#define _GP_REGS                34
+#define _GP_REGS                33
 #define _FP_REGS                32
-#define _EXTRA_REGS             2
+#define _EXTRA_REGS             3
 /*
 * general purpose registers size in bytes.
 * pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585d085a..d25f4f137c2a 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 #define check_pgt_cache()               do { } while (0)
-#define PGALLOC_GFP     (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP     (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #define PGD_SIZE        (PTRS_PER_PGD * sizeof(pgd_t))
 #if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e50405274..022644704a93 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
        cpu_park_loop();
 }
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
 #endif /* ifndef __ASSEMBLY__ */
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682bfe002..e875a5a551d7 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
        unsigned int tmp;
        arch_spinlock_t lockval;
+        u32 owner;
+        /*
+         * Ensure prior spin_lock operations to other locks have completed
+         * on this CPU before we test whether "lock" is locked.
+         */
+        smp_mb();
+        owner = READ_ONCE(lock->owner) << 16;
        asm volatile(
 "       sevl\n"
 "1:     wfe\n"
 "2:     ldaxr   %w0, %2\n"
+        /* Is the lock free? */
 "       eor     %w1, %w0, %w0, ror #16\n"
-"       cbnz    %w1, 1b\n"
+"       cbz     %w1, 3f\n"
+        /* Lock taken -- has there been a subsequent unlock->lock transition? */
+"       eor     %w1, %w3, %w0, lsl #16\n"
+"       cbz     %w1, 1b\n"
+        /*
+         * The owner has been updated, so there was an unlock->lock
+         * transition that we missed. That means we can rely on the
+         * store-release of the unlock operation paired with the
+         * load-acquire of the lock operation to publish any of our
+         * previous stores to the new lock owner and therefore don't
+         * need to bother with the writeback below.
+         */
+"       b       4f\n"
+"3:\n"
+        /*
+         * Serialise against any concurrent lockers by writing back the
+         * unlocked lock value
+         */
        ARM64_LSE_ATOMIC_INSN(
        /* LL/SC */
 "       stxr    %w1, %w0, %2\n"
-"       cbnz    %w1, 2b\n", /* Serialise against any concurrent lockers */
-        /* LSE atomics */
 "       nop\n"
-"       nop\n")
+"       nop\n",
+        /* LSE atomics */
+"       mov     %w1, %w0\n"
+"       cas     %w0, %w0, %2\n"
+"       eor     %w1, %w1, %w0\n")
+        /* Somebody else wrote to the lock, GOTO 10 and reload the value */
+"       cbnz    %w1, 2b\n"
+"4:"
        : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-        :
+        : "r" (owner)
        : "memory");
 }
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+        smp_mb(); /* See arch_spin_unlock_wait */
        return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d740f4..21ab5df9fa76 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
+#include <asm/smp.h>
 #include <asm/suspend.h>
 #include <asm/virt.h>
@@ -236,6 +237,11 @@ int swsusp_arch_suspend(void)
        unsigned long flags;
        struct sleep_stack_data state;
+        if (cpus_are_stuck_in_kernel()) {
+                pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+                return -EBUSY;
+        }
        local_dbg_save(flags);
        if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b67531a13136..b5f063e5eff7 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
        { "x30", 8, offsetof(struct pt_regs, regs[30])},
        { "sp", 8, offsetof(struct pt_regs, sp)},
        { "pc", 8, offsetof(struct pt_regs, pc)},
-        { "pstate", 8, offsetof(struct pt_regs, pstate)},
+        /*
+         * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote
+         * protocol disagrees. Therefore we must extract only the lower
+         * 32-bits. Look for the big comment in asm/kgdb.h for more
+         * detail.
+         */
+        { "pstate", 4, offsetof(struct pt_regs, pstate)
+#ifdef CONFIG_CPU_BIG_ENDIAN
+                                                        + 4
+#endif
+        },
        { "v0", 16, -1 },
        { "v1", 16, -1 },
        { "v2", 16, -1 },
@@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
        memset((char *)gdb_regs, 0, NUMREGBYTES);
        thread_regs = task_pt_regs(task);
        memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+        /* Special case for PSTATE (check comments in asm/kgdb.h for details) */
+        dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs);
 }
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e0842cb3b..62ff3c0622e2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier)
 {
        return -EINVAL;
 }
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+        int any_cpu = raw_smp_processor_id();
+        if (cpu_ops[any_cpu]->cpu_die)
+                return true;
+#endif
+        return false;
+}
+bool cpus_are_stuck_in_kernel(void)
+{
+        bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+        return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f7cf463107df..2a43012616b7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
        /*
         * We need to switch to kernel mode so that we can use __get_user
-         * to safely read from kernel space.  Note that we now dump the
+         * to safely read from kernel space.
-         * code first, just in case the backtrace kills us.
         */
        fs = get_fs();
        set_fs(KERNEL_DS);
@@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where)
        print_ip_sym(where);
 }
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
        unsigned long addr = instruction_pointer(regs);
-        mm_segment_t fs;
        char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
        int i;
-        /*
-         * We need to switch to kernel mode so that we can use __get_user
-         * to safely read from kernel space.  Note that we now dump the
-         * code first, just in case the backtrace kills us.
-         */
-        fs = get_fs();
-        set_fs(KERNEL_DS);
        for (i = -4; i < 1; i++) {
                unsigned int val, bad;
@@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
                }
        }
        printk("%sCode: %s\n", lvl, str);
+}
-        set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+        if (!user_mode(regs)) {
+                mm_segment_t fs = get_fs();
+                set_fs(KERNEL_DS);
+                __dump_instr(lvl, regs);
+                set_fs(fs);
+        } else {
+                __dump_instr(lvl, regs);
+        }
 }
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b397802088..efcf1f7ef1e4 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
                                                 &asid_generation);
        flush_context(cpu);
-        /* We have at least 1 ASID per CPU, so this will always succeed */
+        /* We have more ASIDs than CPUs, so this will always succeed */
        asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 set_asid:
@@ -227,8 +227,11 @@ switch_mm_fastpath:
 static int asids_init(void)
 {
        asid_bits = get_cpu_asid_bits();
-        /* If we end up with more CPUs than ASIDs, expect things to crash */
+        /*
-        WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+         * Expect allocation after rollover to fail if we don't have at least
+         * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+         */
+        WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
        atomic64_set(&asid_generation, ASID_FIRST_VERSION);
        asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
                           GFP_KERNEL);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5954881a35ac..013e2cbe7924 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
         * PTE_RDONLY is cleared by default in the asm below, so set it in
         * back if necessary (read-only or clean PTE).
         */
-        if (!pte_write(entry) || !dirty)
+        if (!pte_write(entry) || !pte_sw_dirty(entry))
                pte_val(entry) |= PTE_RDONLY;
        /*
@@ -441,7 +441,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
        return 1;
 }
-static struct fault_info {
+static const struct fault_info {
        int     (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
        int     sig;
        int     code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea8ce68..43a76b07eb32 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
        struct page *page = pte_page(pte);
-        /* no flushing needed for anonymous pages */
-        if (!page_mapping(page))
-                return;
        if (!test_and_set_bit(PG_dcache_clean, &page->flags))
                sync_icache_aliases(page_address(page),
                                    PAGE_SIZE << compound_order(page));
diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h
index 1aba19d68c5e..db039cb368be 100644
--- a/arch/avr32/include/asm/pgalloc.h
+++ b/arch/avr32/include/asm/pgalloc.h
@@ -43,7 +43,7 @@ static inline void pgd_ctor(void *x)
 */
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-        return quicklist_alloc(QUICK_PGD, GFP_KERNEL | __GFP_REPEAT, pgd_ctor);
+        return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor);
 }
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -54,7 +54,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+        return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 }
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -63,7 +63,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
        struct page *page;
        void *pg;
-        pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+        pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
        if (!pg)
                return NULL;
diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h
index 235ece437ddd..42f1affb9c2d 100644
--- a/arch/cris/include/asm/pgalloc.h
+++ b/arch/cris/include/asm/pgalloc.h
@@ -24,14 +24,14 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        return pte;
 }
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
        struct page *pte;
-        pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+        pte = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
        if (!pte)
                return NULL;
        if (!pgtable_page_ctor(pte)) {
diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 41907d25ed38..c9ed14f6c67d 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -22,7 +22,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE)));
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
        if (pte)
                clear_page(pte);
        return pte;
@@ -33,9 +33,9 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
        struct page *page;
 #ifdef CONFIG_HIGHPTE
-        page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+        page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
 #else
-        page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+        page = alloc_pages(GFP_KERNEL, 0);
 #endif
        if (!page)
                return NULL;
diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h
index 77da3b0ae3c2..eeebf862c46c 100644
--- a/arch/hexagon/include/asm/pgalloc.h
+++ b/arch/hexagon/include/asm/pgalloc.h
@@ -64,7 +64,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
        struct page *pte;
-        pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+        pte = alloc_page(GFP_KERNEL | __GFP_ZERO);
        if (!pte)
                return NULL;
        if (!pgtable_page_ctor(pte)) {
@@ -78,7 +78,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        gfp_t flags =  GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+        gfp_t flags =  GFP_KERNEL | __GFP_ZERO;
        return (pte_t *) __get_free_page(flags);
 }
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index f80758cb7157..e109ee95e919 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -45,7 +45,7 @@ config IA64
        select GENERIC_SMP_IDLE_THREAD
        select ARCH_INIT_TASK
        select ARCH_TASK_STRUCT_ALLOCATOR
-        select ARCH_THREAD_INFO_ALLOCATOR
+        select ARCH_THREAD_STACK_ALLOCATOR
        select ARCH_CLOCKSOURCE_DATA
        select GENERIC_TIME_VSYSCALL_OLD
        select SYSCTL_ARCH_UNALIGN_NO_WARN
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index aa995b67c3f5..d1212b84fb83 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -48,15 +48,15 @@ struct thread_info {
 #ifndef ASM_OFFSETS_C
 /* how to get the thread information struct from C */
 #define current_thread_info()   ((struct thread_info *) ((char *) current + IA64_TASK_SIZE))
-#define alloc_thread_info_node(tsk, node)       \
+#define alloc_thread_stack_node(tsk, node)      \
-                ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
+                ((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE))
 #define task_thread_info(tsk)   ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
 #else
 #define current_thread_info()   ((struct thread_info *) 0)
-#define alloc_thread_info_node(tsk, node)       ((struct thread_info *) 0)
+#define alloc_thread_stack_node(tsk, node)      ((unsigned long *) 0)
 #define task_thread_info(tsk)   ((struct thread_info *) 0)
 #endif
-#define free_thread_info(ti)    /* nothing */
+#define free_thread_stack(ti)   /* nothing */
 #define task_stack_page(tsk)    ((void *)(tsk))
 #define __HAVE_THREAD_FUNCTIONS
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index f9efe9739d3f..0eaa89f3defd 100644
--- a/arch/ia64/kernel/init_task.c
+++ b/arch/ia64/kernel/init_task.c
@@ -26,6 +26,7 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 * handled. This is done by having a special ".data..init_task" section...
 */
 #define init_thread_info        init_task_mem.s.thread_info
+#define init_stack              init_task_mem.stack
 union {
        struct {
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index f9924fbcfe42..fb95aed5f428 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -14,7 +14,7 @@ extern const char bad_pmd_string[];
 extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
        unsigned long address)
 {
-        unsigned long page = __get_free_page(GFP_DMA|__GFP_REPEAT);
+        unsigned long page = __get_free_page(GFP_DMA);
        if (!page)
                return NULL;
@@ -51,7 +51,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
 static inline struct page *pte_alloc_one(struct mm_struct *mm,
        unsigned long address)
 {
-        struct page *page = alloc_pages(GFP_DMA|__GFP_REPEAT, 0);
+        struct page *page = alloc_pages(GFP_DMA, 0);
        pte_t *pte;
        if (!page)
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 24bcba496c75..c895b987202c 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -11,7 +11,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad
 {
        pte_t *pte;
-        pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        if (pte) {
                __flush_page_to_ram(pte);
                flush_tlb_kernel_page(pte);
@@ -32,7 +32,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres
        struct page *page;
        pte_t *pte;
-        page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+        page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
        if(!page)
                return NULL;
        if (!pgtable_page_ctor(page)) {
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index 0931388de47f..1901f61f926f 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -37,7 +37,7 @@ do {							\
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        unsigned long page = __get_free_page(GFP_KERNEL|__GFP_REPEAT);
+        unsigned long page = __get_free_page(GFP_KERNEL);
        if (!page)
                return NULL;
@@ -49,7 +49,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
                                        unsigned long address)
 {
-        struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+        struct page *page = alloc_pages(GFP_KERNEL, 0);
        if (page == NULL)
                return NULL;
diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h
index 3104df0a4822..c2caa1ee4360 100644
--- a/arch/metag/include/asm/pgalloc.h
+++ b/arch/metag/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT |
+        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-                                              __GFP_ZERO);
        return pte;
 }
@@ -51,7 +50,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
                                      unsigned long address)
 {
        struct page *pte;
-        pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+        pte = alloc_pages(GFP_KERNEL  | __GFP_ZERO, 0);
        if (!pte)
                return NULL;
        if (!pgtable_page_ctor(pte)) {
diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index 61436d69775c..7c89390c0c13 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -116,9 +116,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
        struct page *ptepage;
 #ifdef CONFIG_HIGHPTE
-        int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT;
+        int flags = GFP_KERNEL | __GFP_HIGHMEM;
 #else
-        int flags = GFP_KERNEL | __GFP_REPEAT;
+        int flags = GFP_KERNEL;
 #endif
        ptepage = alloc_pages(flags, 0);
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4f4520e779a5..eb99fcc76088 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -239,8 +239,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
        pte_t *pte;
        if (mem_init_done) {
-                pte = (pte_t *)__get_free_page(GFP_KERNEL |
+                pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-                                        __GFP_REPEAT | __GFP_ZERO);
        } else {
                pte = (pte_t *)early_get_page();
                if (pte)
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 6733ac575da4..36a391d289aa 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -74,7 +74,7 @@
 #define KVM_GUEST_KUSEG                 0x00000000UL
 #define KVM_GUEST_KSEG0                 0x40000000UL
 #define KVM_GUEST_KSEG23                0x60000000UL
-#define KVM_GUEST_KSEGX(a)              ((_ACAST32_(a)) & 0x60000000)
+#define KVM_GUEST_KSEGX(a)              ((_ACAST32_(a)) & 0xe0000000)
 #define KVM_GUEST_CPHYSADDR(a)          ((_ACAST32_(a)) & 0x1fffffff)
 #define KVM_GUEST_CKSEG0ADDR(a)         (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0)
@@ -338,6 +338,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE 64
 struct kvm_vcpu_arch {
        void *host_ebase, *guest_ebase;
+        int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
        unsigned long host_stack;
        unsigned long host_gp;
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index b336037e8768..93c079a1cfc8 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -69,7 +69,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
        pte_t *pte;
-        pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, PTE_ORDER);
+        pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
        return pte;
 }
@@ -79,7 +79,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
        struct page *pte;
-        pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+        pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
        if (!pte)
                return NULL;
        clear_highpage(pte);
@@ -113,7 +113,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
        pmd_t *pmd;
-        pmd = (pmd_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PMD_ORDER);
+        pmd = (pmd_t *) __get_free_pages(GFP_KERNEL, PMD_ORDER);
        if (pmd)
                pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table);
        return pmd;
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 396df6eb0a12..645c8a1982a7 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1636,6 +1636,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
                if (index < 0) {
                        vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK);
                        vcpu->arch.host_cp0_badvaddr = va;
+                        vcpu->arch.pc = curr_pc;
                        er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run,
                                                         vcpu);
                        preempt_enable();
@@ -1647,6 +1648,8 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
                         * invalid exception to the guest
                         */
                        if (!TLB_IS_VALID(*tlb, va)) {
+                                vcpu->arch.host_cp0_badvaddr = va;
+                                vcpu->arch.pc = curr_pc;
                                er = kvm_mips_emulate_tlbinv_ld(cause, NULL,
                                                                run, vcpu);
                                preempt_enable();
@@ -1666,7 +1669,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
                        cache, op, base, arch->gprs[base], offset);
                er = EMULATE_FAIL;
                preempt_enable();
-                goto dont_update_pc;
+                goto done;
        }
@@ -1694,16 +1697,20 @@ skip_fault:
                kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
                        cache, op, base, arch->gprs[base], offset);
                er = EMULATE_FAIL;
-                preempt_enable();
-                goto dont_update_pc;
        }
        preempt_enable();
+done:
+        /* Rollback PC only if emulation was unsuccessful */
+        if (er == EMULATE_FAIL)
+                vcpu->arch.pc = curr_pc;
 dont_update_pc:
-        /* Rollback PC */
+        /*
-        vcpu->arch.pc = curr_pc;
+         * This is for exceptions whose emulation updates the PC, so do not
-done:
+         * overwrite the PC under any circumstances
+         */
        return er;
 }
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdfad703..2143884709e4 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
+extern char __kvm_mips_vcpu_run_end[];
 extern char mips32_exception[], mips32_exceptionEnd[];
 extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 3ef03009de5f..828fcfc1cd7f 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1)
        /* Jump to guest */
        eret
+EXPORT(__kvm_mips_vcpu_run_end)
 VECTOR(MIPSX(exception), unknown)
 /* Find out what mode we came from and jump to the proper handler. */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index dc052fb5c7a2..44da5259f390 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
        memcpy(gebase + offset, mips32_GuestException,
               mips32_GuestExceptionEnd - mips32_GuestException);
+#ifdef MODULE
+        offset += mips32_GuestExceptionEnd - mips32_GuestException;
+        memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+               __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+        vcpu->arch.vcpu_run = gebase + offset;
+#else
+        vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
        /* Invalidate the icache for these ranges */
        local_flush_icache_range((unsigned long)gebase,
                                (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
@@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
        /* Disable hardware page table walking while in guest */
        htw_stop();
-        r = __kvm_mips_vcpu_run(run, vcpu);
+        r = vcpu->arch.vcpu_run(run, vcpu);
        /* Re-enable HTW before enabling interrupts */
        htw_start();
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index 4861a78c7160..f5f90bbf019d 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -115,7 +115,7 @@ static inline unsigned long current_stack_pointer(void)
 }
 #ifndef CONFIG_KGDB
-void arch_release_thread_info(struct thread_info *ti);
+void arch_release_thread_stack(unsigned long *stack);
 #endif
 #define get_thread_info(ti)     get_task_struct((ti)->task)
 #define put_thread_info(ti)     put_task_struct((ti)->task)
diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c
index 99770823451a..2d7986c386fe 100644
--- a/arch/mn10300/kernel/kgdb.c
+++ b/arch/mn10300/kernel/kgdb.c
@@ -397,8 +397,9 @@ static bool kgdb_arch_undo_singlestep(struct pt_regs *regs)
 * single-step state is cleared.  At this point the breakpoints should have
 * been removed by __switch_to().
 */
-void arch_release_thread_info(struct thread_info *ti)
+void arch_release_thread_stack(unsigned long *stack)
 {
+        struct thread_info *ti = (void *)stack;
        if (kgdb_sstep_thread == ti) {
                kgdb_sstep_thread = NULL;
diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c
index e77a7c728081..9577cf768875 100644
--- a/arch/mn10300/mm/pgtable.c
+++ b/arch/mn10300/mm/pgtable.c
@@ -63,7 +63,7 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
        if (pte)
                clear_page(pte);
        return pte;
@@ -74,9 +74,9 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
        struct page *pte;
 #ifdef CONFIG_HIGHPTE
-        pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+        pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
 #else
-        pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+        pte = alloc_pages(GFP_KERNEL, 0);
 #endif
        if (!pte)
                return NULL;
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index 6e2985e0a7b9..bb47d08c8ef7 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
        pte_t *pte;
-        pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
+        pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
-                                        PTE_ORDER);
        return pte;
 }
@@ -53,7 +52,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 {
        struct page *pte;
-        pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+        pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
        if (pte) {
                if (!pgtable_page_ctor(pte)) {
                        __free_page(pte);
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 21484e5b9e9a..87eebd185089 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -77,7 +77,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
                                         unsigned long address)
 {
        struct page *pte;
-        pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+        pte = alloc_pages(GFP_KERNEL, 0);
        if (!pte)
                return NULL;
        clear_page(page_address(pte));
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index 62b08ef392be..5b2a95116e8f 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -122,7 +122,7 @@ pte_t __init_refok *pte_alloc_one_kernel(struct mm_struct *mm,
        pte_t *pte;
        if (likely(mem_init_done)) {
-                pte = (pte_t *) __get_free_page(GFP_KERNEL | __GFP_REPEAT);
+                pte = (pte_t *) __get_free_page(GFP_KERNEL);
        } else {
                pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
 #if 0
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f2fd327dce2e..f08dda3f0995 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -63,8 +63,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
+        pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER);
-                                               PMD_ORDER);
        if (pmd)
                memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
        return pmd;
@@ -124,7 +123,7 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
        if (!page)
                return NULL;
        if (!pgtable_page_ctor(page)) {
@@ -137,7 +136,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
 {
-        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        return pte;
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 01f7464d9fea..0a9d439bcda6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -128,7 +128,7 @@ config PPC
        select IRQ_FORCED_THREADING
        select HAVE_RCU_TABLE_FREE if SMP
        select HAVE_SYSCALL_TRACEPOINTS
-        select HAVE_CBPF_JIT
+        select HAVE_CBPF_JIT if CPU_BIG_ENDIAN
        select HAVE_ARCH_JUMP_LABEL
        select ARCH_HAVE_NMI_SAFE_CMPXCHG
        select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index a2350194fc76..8e21bb492dca 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -102,7 +102,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
                                  unsigned long address)
 {
-        tlb_flush_pgtable(tlb, address);
        pgtable_page_dtor(table);
        pgtable_free_tlb(tlb, page_address(table), 0);
 }
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 290157e8d5b2..74839f24f412 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -88,6 +88,7 @@
 #define HPTE_R_RPN_SHIFT        12
 #define HPTE_R_RPN              ASM_CONST(0x0ffffffffffff000)
 #define HPTE_R_PP               ASM_CONST(0x0000000000000003)
+#define HPTE_R_PPP              ASM_CONST(0x8000000000000003)
 #define HPTE_R_N                ASM_CONST(0x0000000000000004)
 #define HPTE_R_G                ASM_CONST(0x0000000000000008)
 #define HPTE_R_M                ASM_CONST(0x0000000000000010)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 488279edb1f0..cd5e7aa8cc34 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -41,7 +41,7 @@ extern struct kmem_cache *pgtable_cache[];
                        pgtable_cache[(shift) - 1];     \
                })
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
 extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int);
 extern void pte_fragment_free(unsigned long *, int);
@@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
        return (pgd_t *)__get_free_page(PGALLOC_GFP);
 #else
        struct page *page;
-        page = alloc_pages(PGALLOC_GFP, 4);
+        page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4);
        if (!page)
                return NULL;
        return (pgd_t *) page_address(page);
@@ -93,8 +93,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
+        return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
-                                GFP_KERNEL|__GFP_REPEAT);
 }
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -110,13 +109,17 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
                                  unsigned long address)
 {
+        /*
+         * By now all the pud entries should be none entries. So go
+         * ahead and flush the page walk cache
+         */
+        flush_tlb_pgtable(tlb, address);
        pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE);
 }
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
+        return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
-                                GFP_KERNEL|__GFP_REPEAT);
 }
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -127,6 +130,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
                                  unsigned long address)
 {
+        /*
+         * By now all the pud entries should be none entries. So go
+         * ahead and flush the page walk cache
+         */
+        flush_tlb_pgtable(tlb, address);
        return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX);
 }
@@ -151,7 +159,7 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+        return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -198,7 +206,11 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
                                  unsigned long address)
 {
-        tlb_flush_pgtable(tlb, address);
+        /*
+         * By now all the pud entries should be none entries. So go
+         * ahead and flush the page walk cache
+         */
+        flush_tlb_pgtable(tlb, address);
        pgtable_free_tlb(tlb, table, 0);
 }
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 937d4e247ac3..df294224e280 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -228,5 +228,20 @@ extern void radix__vmemmap_remove_mapping(unsigned long start,
 extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
                                 pgprot_t flags, unsigned int psz);
+static inline unsigned long radix__get_tree_size(void)
+{
+        unsigned long rts_field;
+        /*
+         * we support 52 bits, hence 52-31 = 21, 0b10101
+         * RTS encoding details
+         * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
+         * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
+         */
+        rts_field = (0x5UL << 5); /* 6 - 8 bits */
+        rts_field |= (0x2UL << 61);
+        return rts_field;
+}
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 13ef38828dfe..3fa94fcac628 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
 extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
                                    unsigned long ap, int nid);
+extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__tlb_flush(struct mmu_gather *tlb);
 #ifdef CONFIG_SMP
 extern void radix__flush_tlb_mm(struct mm_struct *mm);
 extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
                              unsigned long ap, int nid);
+extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 #else
 #define radix__flush_tlb_mm(mm)         radix__local_flush_tlb_mm(mm)
 #define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr)
 #define radix___flush_tlb_page(mm,addr,p,i)     radix___local_flush_tlb_page(mm,addr,p,i)
+#define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr)
 #endif
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index d98424ae356c..96e5769b18b0 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -72,5 +72,19 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 #define flush_tlb_mm(mm)                local_flush_tlb_mm(mm)
 #define flush_tlb_page(vma, addr)       local_flush_tlb_page(vma, addr)
 #endif /* CONFIG_SMP */
+/*
+ * flush the page walk cache for the address
+ */
+static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+        /*
+         * Flush the page table walk cache on freeing a page table. We already
+         * have marked the upper/higher level page table entry none by now.
+         * So it is safe to flush PWC here.
+         */
+        if (!radix_enabled())
+                return;
+        radix__flush_tlb_pwc(tlb, address);
+}
 #endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */
diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h
index 54f591e9572e..c0a69ae92256 100644
--- a/arch/powerpc/include/asm/book3s/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/pgalloc.h
@@ -4,11 +4,6 @@
 #include <linux/mm.h>
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
-                                     unsigned long address)
-{
-}
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/pgalloc.h>
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 0c12a3bfe2ab..897d2e1c8a9b 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -57,8 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
+        return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
-                                GFP_KERNEL|__GFP_REPEAT);
 }
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -88,7 +87,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+        return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -172,7 +171,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-        pte_fragment_fre((unsigned long *)pte, 1);
+        pte_fragment_free((unsigned long *)pte, 1);
 }
 static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
@@ -190,8 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
+        return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
-                                GFP_KERNEL|__GFP_REPEAT);
 }
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2714a3b81d24..b5f73cb5eeb6 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -642,7 +642,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
                if (pe->type & EEH_PE_VF) {
                        eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
                } else {
-                        eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
                        pci_lock_rescan_remove();
                        pci_hp_remove_devices(bus);
                        pci_unlock_rescan_remove();
@@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
                 */
                edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
                eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-                if (pe->type & EEH_PE_VF)
+                if (pe->type & EEH_PE_VF) {
                        eeh_add_virt_device(edev, NULL);
-                else
+                } else {
+                        eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
                        pci_hp_add_devices(bus);
+                }
        } else if (frozen_bus && rmv_data->removed) {
                pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
                ssleep(5);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4c9440629128..8bcc1b457115 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1399,11 +1399,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX)
        lwz     r9,PACA_EXSLB+EX_CCR(r13)       /* get saved CR */
        mtlr    r10
-BEGIN_MMU_FTR_SECTION
-        b       2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
        andi.   r10,r12,MSR_RI  /* check for unrecoverable exception */
+BEGIN_MMU_FTR_SECTION
        beq-    2f
+FTR_SECTION_ELSE
+        b       2f
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
 .machine        push
 .machine        "power4"
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index ccd2037c797f..6ee4b72cda42 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -719,7 +719,7 @@ unsigned char ibm_architecture_vec[] = {
         * must match by the macro below. Update the definition if
         * the structure layout changes.
         */
-#define IBM_ARCH_VEC_NRCORES_OFFSET     125
+#define IBM_ARCH_VEC_NRCORES_OFFSET     133
        W(NR_CPUS),                     /* number of cores supported */
        0,
        0,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 30a03c03fe73..060b140f03c6 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -377,7 +377,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 #else
        BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-                     offsetof(struct thread_fp_state, fpr[32][0]));
+                     offsetof(struct thread_fp_state, fpr[32]));
        return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
                                   &target->thread.fp_state, 0, -1);
@@ -405,7 +405,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
        return 0;
 #else
        BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-                     offsetof(struct thread_fp_state, fpr[32][0]));
+                     offsetof(struct thread_fp_state, fpr[32]));
        return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
                                  &target->thread.fp_state, 0, -1);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index d873f6507f72..f8a871a72985 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
                        DBG_LOW(" -> hit\n");
                        /* Update the HPTE */
                        hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-                                                ~(HPTE_R_PP | HPTE_R_N)) |
+                                                ~(HPTE_R_PPP | HPTE_R_N)) |
-                                               (newpp & (HPTE_R_PP | HPTE_R_N |
+                                               (newpp & (HPTE_R_PPP | HPTE_R_N |
                                                         HPTE_R_C)));
                }
                native_unlock_hpte(hptep);
@@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
        /* Update the HPTE */
        hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-                        ~(HPTE_R_PP | HPTE_R_N)) |
+                                ~(HPTE_R_PPP | HPTE_R_N)) |
-                (newpp & (HPTE_R_PP | HPTE_R_N)));
+                               (newpp & (HPTE_R_PPP | HPTE_R_N)));
        /*
         * Ensure it is out of the tlb too. Bolted entries base and
         * actual page size will be same.
@@ -550,7 +550,11 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
                }
        }
        /* This works for all page sizes, and for 256M and 1T segments */
-        *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
+        if (cpu_has_feature(CPU_FTR_ARCH_300))
+                *ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT;
+        else
+                *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
        shift = mmu_psize_defs[size].shift;
        avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index b2740c67e172..5b22ba0b58bc 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -201,9 +201,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
        /*
         * We can't allow hardware to update hpte bits. Hence always
         * set 'R' bit and set 'C' if it is a write fault
-         * Memory coherence is always enabled
         */
-        rflags |=  HPTE_R_R | HPTE_R_M;
+        rflags |=  HPTE_R_R;
        if (pteflags & _PAGE_DIRTY)
                rflags |= HPTE_R_C;
@@ -213,10 +212,15 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
        if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT)
                rflags |= HPTE_R_I;
-        if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT)
+        else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
                rflags |= (HPTE_R_I | HPTE_R_G);
-        if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+        else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
-                rflags |= (HPTE_R_I | HPTE_R_W);
+                rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
+        else
+                /*
+                 * Add memory coherence if cache inhibited is not set
+                 */
+                rflags |= HPTE_R_M;
        return rflags;
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5aac1a3f86cd..119d18611500 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -73,7 +73,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
        cachep = PGT_CACHE(pdshift - pshift);
 #endif
-        new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
+        new = kmem_cache_zalloc(cachep, GFP_KERNEL);
        BUG_ON(pshift > HUGEPD_SHIFT_MASK);
        BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 227b2a6c4544..196222227e82 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -65,7 +65,7 @@ static int radix__init_new_context(struct mm_struct *mm, int index)
        /*
         * set the process table entry,
         */
-        rts_field = 3ull << PPC_BITLSHIFT(2);
+        rts_field = radix__get_tree_size();
        process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE);
        return 0;
 }
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index c939e6e57a9e..e58707deef5c 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -160,9 +160,8 @@ redo:
        process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
        /*
         * Fill in the process table.
-         * we support 52 bits, hence 52-28 = 24, 11000
         */
-        rts_field = 3ull << PPC_BITLSHIFT(2);
+        rts_field = radix__get_tree_size();
        process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);
        /*
         * Fill in the partition table. We are suppose to use effective address
@@ -176,10 +175,8 @@ redo:
 static void __init radix_init_partition_table(void)
 {
        unsigned long rts_field;
-        /*
-         * we support 52 bits, hence 52-28 = 24, 11000
+        rts_field = radix__get_tree_size();
-         */
-        rts_field = 3ull << PPC_BITLSHIFT(2);
        BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
        partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index bf7bf32b54f8..7f922f557936 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -84,7 +84,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
        pte_t *pte;
        if (slab_is_available()) {
-                pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+                pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        } else {
                pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
                if (pte)
@@ -97,7 +97,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
        struct page *ptepage;
-        gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+        gfp_t flags = GFP_KERNEL | __GFP_ZERO;
        ptepage = alloc_pages(flags, 0);
        if (!ptepage)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index e009e0604a8a..f5e8d4edb808 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -350,8 +350,7 @@ static pte_t *get_from_cache(struct mm_struct *mm)
 static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 {
        void *ret = NULL;
-        struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+        struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-                                       __GFP_REPEAT | __GFP_ZERO);
        if (!page)
                return NULL;
        if (!kernel && !pgtable_page_ctor(page)) {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0fdaf93a3e09..ab2f60e812e2 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -18,16 +18,20 @@
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbiel_pid(unsigned long pid, int set)
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+static inline void __tlbiel_pid(unsigned long pid, int set,
+                                unsigned long ric)
 {
-        unsigned long rb,rs,ric,prs,r;
+        unsigned long rb,rs,prs,r;
        rb = PPC_BIT(53); /* IS = 1 */
        rb |= set << PPC_BITLSHIFT(51);
        rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
        prs = 1; /* process scoped */
        r = 1;   /* raidx format */
-        ric = 2;  /* invalidate all the caches */
        asm volatile("ptesync": : :"memory");
        asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set)
 /*
 * We use 128 set in radix mode and 256 set in hpt mode.
 */
-static inline void _tlbiel_pid(unsigned long pid)
+static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 {
        int set;
        for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
-                __tlbiel_pid(pid, set);
+                __tlbiel_pid(pid, set, ric);
        }
        return;
 }
-static inline void _tlbie_pid(unsigned long pid)
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
-        unsigned long rb,rs,ric,prs,r;
+        unsigned long rb,rs,prs,r;
        rb = PPC_BIT(53); /* IS = 1 */
        rs = pid << PPC_BITLSHIFT(31);
        prs = 1; /* process scoped */
        r = 1;   /* raidx format */
-        ric = 2;  /* invalidate all the caches */
        asm volatile("ptesync": : :"memory");
        asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -67,16 +70,15 @@ static inline void _tlbie_pid(unsigned long pid)
 }
 static inline void _tlbiel_va(unsigned long va, unsigned long pid,
-                              unsigned long ap)
+                              unsigned long ap, unsigned long ric)
 {
-        unsigned long rb,rs,ric,prs,r;
+        unsigned long rb,rs,prs,r;
        rb = va & ~(PPC_BITMASK(52, 63));
        rb |= ap << PPC_BITLSHIFT(58);
        rs = pid << PPC_BITLSHIFT(31);
        prs = 1; /* process scoped */
        r = 1;   /* raidx format */
-        ric = 0;  /* no cluster flush yet */
        asm volatile("ptesync": : :"memory");
        asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -86,16 +88,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 }
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
-                             unsigned long ap)
+                             unsigned long ap, unsigned long ric)
 {
-        unsigned long rb,rs,ric,prs,r;
+        unsigned long rb,rs,prs,r;
        rb = va & ~(PPC_BITMASK(52, 63));
        rb |= ap << PPC_BITLSHIFT(58);
        rs = pid << PPC_BITLSHIFT(31);
        prs = 1; /* process scoped */
        r = 1;   /* raidx format */
-        ric = 0;  /* no cluster flush yet */
        asm volatile("ptesync": : :"memory");
        asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -117,25 +118,40 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 */
 void radix__local_flush_tlb_mm(struct mm_struct *mm)
 {
-        unsigned int pid;
+        unsigned long pid;
        preempt_disable();
        pid = mm->context.id;
        if (pid != MMU_NO_CONTEXT)
-                _tlbiel_pid(pid);
+                _tlbiel_pid(pid, RIC_FLUSH_ALL);
        preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
+void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+        unsigned long pid;
+        struct mm_struct *mm = tlb->mm;
+        preempt_disable();
+        pid = mm->context.id;
+        if (pid != MMU_NO_CONTEXT)
+                _tlbiel_pid(pid, RIC_FLUSH_PWC);
+        preempt_enable();
+}
+EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
 void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
                            unsigned long ap, int nid)
 {
-        unsigned int pid;
+        unsigned long pid;
        preempt_disable();
        pid = mm ? mm->context.id : 0;
        if (pid != MMU_NO_CONTEXT)
-                _tlbiel_va(vmaddr, pid, ap);
+                _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
        preempt_enable();
 }
@@ -160,7 +176,7 @@ static int mm_is_core_local(struct mm_struct *mm)
 void radix__flush_tlb_mm(struct mm_struct *mm)
 {
-        unsigned int pid;
+        unsigned long pid;
        preempt_disable();
        pid = mm->context.id;
@@ -172,20 +188,46 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
                if (lock_tlbie)
                        raw_spin_lock(&native_tlbie_lock);
-                _tlbie_pid(pid);
+                _tlbie_pid(pid, RIC_FLUSH_ALL);
                if (lock_tlbie)
                        raw_spin_unlock(&native_tlbie_lock);
        } else
-                _tlbiel_pid(pid);
+                _tlbiel_pid(pid, RIC_FLUSH_ALL);
 no_context:
        preempt_enable();
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
+void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+        unsigned long pid;
+        struct mm_struct *mm = tlb->mm;
+        preempt_disable();
+        pid = mm->context.id;
+        if (unlikely(pid == MMU_NO_CONTEXT))
+                goto no_context;
+        if (!mm_is_core_local(mm)) {
+                int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+                if (lock_tlbie)
+                        raw_spin_lock(&native_tlbie_lock);
+                _tlbie_pid(pid, RIC_FLUSH_PWC);
+                if (lock_tlbie)
+                        raw_spin_unlock(&native_tlbie_lock);
+        } else
+                _tlbiel_pid(pid, RIC_FLUSH_PWC);
+no_context:
+        preempt_enable();
+}
+EXPORT_SYMBOL(radix__flush_tlb_pwc);
 void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
                       unsigned long ap, int nid)
 {
-        unsigned int pid;
+        unsigned long pid;
        preempt_disable();
        pid = mm ? mm->context.id : 0;
@@ -196,11 +238,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
                if (lock_tlbie)
                        raw_spin_lock(&native_tlbie_lock);
-                _tlbie_va(vmaddr, pid, ap);
+                _tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
                if (lock_tlbie)
                        raw_spin_unlock(&native_tlbie_lock);
        } else
-                _tlbiel_va(vmaddr, pid, ap);
+                _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 bail:
        preempt_enable();
 }
@@ -224,7 +266,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
        if (lock_tlbie)
                raw_spin_lock(&native_tlbie_lock);
-        _tlbie_pid(0);
+        _tlbie_pid(0, RIC_FLUSH_ALL);
        if (lock_tlbie)
                raw_spin_unlock(&native_tlbie_lock);
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index b7dfc1359d01..3e8865b187de 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -927,7 +927,7 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
        dn = pci_device_to_OF_node(dev);
        pdn = PCI_DN(dn);
        buid = pdn->phb->buid;
-        cfg_addr = (pdn->busno << 8) | pdn->devfn;
+        cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
        ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
                  cfg_addr, BUID_HI(buid), BUID_LO(buid));
@@ -956,7 +956,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
        dn = pci_device_to_OF_node(dev);
        pdn = PCI_DN(dn);
        buid = pdn->phb->buid;
-        cfg_addr = (pdn->busno << 8) | pdn->devfn;
+        cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
        do {
                /* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index 5e04f3cbd320..8ae236b0f80b 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc)
                "       la      %0,0\n"
                "1:\n"
                EX_TABLE(0b,1b)
-                : "=d" (rc), "=d" (orig_fpc)
+                : "=d" (rc), "=&d" (orig_fpc)
                : "d" (fpc), "0" (-EINVAL));
        return rc;
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 37b9017c6a96..ac82e8eb936d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -245,6 +245,7 @@ struct kvm_vcpu_stat {
        u32 exit_stop_request;
        u32 exit_validity;
        u32 exit_instruction;
+        u32 exit_pei;
        u32 halt_successful_poll;
        u32 halt_attempted_poll;
        u32 halt_poll_invalid;
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f20abdb5630a..d14069d4b88d 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2064,12 +2064,5 @@ void s390_reset_system(void)
        S390_lowcore.program_new_psw.addr =
                (unsigned long) s390_base_pgm_handler;
-        /*
-         * Clear subchannel ID and number to signal new kernel that no CCW or
-         * SCSI IPL has been done (for kexec and kdump)
-         */
-        S390_lowcore.subchannel_id = 0;
-        S390_lowcore.subchannel_nr = 0;
        do_reset_calls();
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 59215c518f37..7ec63b1d920d 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -649,6 +649,8 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
 /* Performance monitoring unit for s390x */
 static struct pmu cpumf_pmu = {
+        .task_ctx_nr  = perf_sw_context,
+        .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
        .pmu_enable   = cpumf_pmu_enable,
        .pmu_disable  = cpumf_pmu_disable,
        .event_init   = cpumf_pmu_event_init,
@@ -708,12 +710,6 @@ static int __init cpumf_pmu_init(void)
                goto out;
        }
-        /* The CPU measurement counter facility does not have overflow
-         * interrupts to do sampling.  Sampling must be provided by
-         * external means, for example, by timers.
-         */
-        cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
        cpumf_pmu.attr_groups = cpumf_cf_event_group();
        rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
        if (rc) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 2e6b54e4d3f9..252157181302 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -341,6 +341,8 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 static int handle_partial_execution(struct kvm_vcpu *vcpu)
 {
+        vcpu->stat.exit_pei++;
        if (vcpu->arch.sie_block->ipa == 0xb254)        /* MVPG */
                return handle_mvpg_pei(vcpu);
        if (vcpu->arch.sie_block->ipa >> 8 == 0xae)     /* SIGP */
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6d8ec3ac9dd8..43f2a2b80490 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -61,6 +61,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
        { "exit_external_request", VCPU_STAT(exit_external_request) },
        { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
        { "exit_instruction", VCPU_STAT(exit_instruction) },
+        { "exit_pei", VCPU_STAT(exit_pei) },
        { "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
        { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
        { "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
@@ -657,7 +658,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
                kvm->arch.model.cpuid = proc->cpuid;
                lowest_ibc = sclp.ibc >> 16 & 0xfff;
                unblocked_ibc = sclp.ibc & 0xfff;
-                if (lowest_ibc) {
+                if (lowest_ibc && proc->ibc) {
                        if (proc->ibc > unblocked_ibc)
                                kvm->arch.model.ibc = unblocked_ibc;
                        else if (proc->ibc < lowest_ibc)
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e8b5962ac12a..e2565d2d0c32 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
                        return table;
        }
        /* Allocate a fresh page */
-        page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+        page = alloc_page(GFP_KERNEL);
        if (!page)
                return NULL;
        if (!pgtable_page_ctor(page)) {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4324b87f9398..9f0ce0e6eeb4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -437,7 +437,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
        pgste = pgste_get_lock(ptep);
        pgstev = pgste_val(pgste);
        pte = *ptep;
-        if (pte_swap(pte) &&
+        if (!reset && pte_swap(pte) &&
            ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
             (pgstev & _PGSTE_GPS_ZERO))) {
                ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 2e067657db98..49b012d78c1a 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
        pte_t *pte;
-        pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
+        pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
-                                        PTE_ORDER);
        return pte;
 }
@@ -53,7 +52,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
        struct page *pte;
-        pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+        pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
        if (!pte)
                return NULL;
        clear_highpage(pte);
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index a33673b3687d..f3f42c84c40f 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                                          unsigned long address)
 {
-        return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+        return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 }
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -43,7 +43,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
        struct page *page;
        void *pg;
-        pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+        pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
        if (!pg)
                return NULL;
        page = virt_to_page(pg);
diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c
index 26e03a1f7ca4..a62bd8696779 100644
--- a/arch/sh/mm/pgtable.c
+++ b/arch/sh/mm/pgtable.c
@@ -1,7 +1,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
-#define PGALLOC_GFP GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO
 static struct kmem_cache *pgd_cachep;
 #if PAGETABLE_LEVELS > 2
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5e3187185b4a..3529f1378cd8 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -41,8 +41,7 @@ static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(pgtable_cache,
+        return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
-                                GFP_KERNEL|__GFP_REPEAT);
 }
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -52,8 +51,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(pgtable_cache,
+        return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
-                                GFP_KERNEL|__GFP_REPEAT);
 }
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 14bb0d5ed3c6..aec508e37490 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2704,8 +2704,7 @@ void __flush_tlb_all(void)
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
                            unsigned long address)
 {
-        struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+        struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-                                       __GFP_REPEAT | __GFP_ZERO);
        pte_t *pte = NULL;
        if (page)
@@ -2717,8 +2716,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 pgtable_t pte_alloc_one(struct mm_struct *mm,
                        unsigned long address)
 {
-        struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+        struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-                                       __GFP_REPEAT | __GFP_ZERO);
        if (!page)
                return NULL;
        if (!pgtable_page_ctor(page)) {
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 4b7cef9e94e0..c1467ac59ce6 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -78,7 +78,7 @@ struct thread_info {
 #ifndef __ASSEMBLY__
-void arch_release_thread_info(struct thread_info *info);
+void arch_release_thread_stack(unsigned long *stack);
 /* How to get the thread information struct from C. */
 register unsigned long stack_pointer __asm__("sp");
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 6b705ccc9cc1..a465d8372edd 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -73,8 +73,9 @@ void arch_cpu_idle(void)
 /*
 * Release a thread_info structure
 */
-void arch_release_thread_info(struct thread_info *info)
+void arch_release_thread_stack(unsigned long *stack)
 {
+        struct thread_info *info = (void *)stack;
        struct single_step_state *step_state = info->step_state;
        if (step_state) {
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 7bf2491a9c1f..c4d5bf841a7f 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -231,7 +231,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address,
                               int order)
 {
-        gfp_t flags = GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO;
+        gfp_t flags = GFP_KERNEL|__GFP_ZERO;
        struct page *p;
        int i;
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index b2a2dff50b4e..e7437ec62710 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -204,7 +204,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
        pte_t *pte;
-        pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
        return pte;
 }
@@ -212,7 +212,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
        struct page *pte;
-        pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+        pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
        if (!pte)
                return NULL;
        if (!pgtable_page_ctor(pte)) {
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
index 2e02d1356fdf..26775793c204 100644
--- a/arch/unicore32/include/asm/pgalloc.h
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -28,7 +28,7 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
 #define pgd_alloc(mm)                   get_pgd_slow(mm)
 #define pgd_free(mm, pgd)               free_pgd_slow(mm, pgd)
-#define PGALLOC_GFP     (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP     (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 /*
 * Allocate one PTE table.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0a7b885964ba..d9a94da0c29f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2439,6 +2439,15 @@ config PCI_CNB20LE_QUIRK
 source "drivers/pci/Kconfig"
+config ISA_BUS
+        bool "ISA-style bus support on modern systems" if EXPERT
+        select ISA_BUS_API
+        help
+          Enables ISA-style drivers on modern systems. This is necessary to
+          support PC/104 devices on X86_64 platforms.
+          If unsure, say N.
 # x86_64 have no ISA slots, but can have ISA-style DMA.
 config ISA_DMA_API
        bool "ISA-style DMA support" if (X86_64 && EXPERT)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 700a9c6e6159..be8e688fa0d4 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage
        for i in lib lib64 share end ; do \
                if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
                        cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+                        if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \
+                                cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \
+                        fi ; \
                        break ; \
                fi ; \
                if [ $$i = end ] ; then exit 1 ; fi ; \
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 99c4bab123cd..e30eef4f29a6 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -714,7 +714,7 @@ static void cleanup_rapl_pmus(void)
        int i;
        for (i = 0; i < rapl_pmus->maxpkg; i++)
-                kfree(rapl_pmus->pmus + i);
+                kfree(rapl_pmus->pmus[i]);
        kfree(rapl_pmus);
 }
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b2625867ebd1..874e8bd64d1d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2868,27 +2868,10 @@ static struct intel_uncore_type bdx_uncore_cbox = {
        .format_group           = &hswep_uncore_cbox_format_group,
 };
-static struct intel_uncore_type bdx_uncore_sbox = {
-        .name                   = "sbox",
-        .num_counters           = 4,
-        .num_boxes              = 4,
-        .perf_ctr_bits          = 48,
-        .event_ctl              = HSWEP_S0_MSR_PMON_CTL0,
-        .perf_ctr               = HSWEP_S0_MSR_PMON_CTR0,
-        .event_mask             = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
-        .box_ctl                = HSWEP_S0_MSR_PMON_BOX_CTL,
-        .msr_offset             = HSWEP_SBOX_MSR_OFFSET,
-        .ops                    = &hswep_uncore_sbox_msr_ops,
-        .format_group           = &hswep_uncore_sbox_format_group,
-};
-#define BDX_MSR_UNCORE_SBOX     3
 static struct intel_uncore_type *bdx_msr_uncores[] = {
        &bdx_uncore_ubox,
        &bdx_uncore_cbox,
        &hswep_uncore_pcu,
-        &bdx_uncore_sbox,
        NULL,
 };
@@ -2897,10 +2880,6 @@ void bdx_uncore_cpu_init(void)
        if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
                bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
        uncore_msr_uncores = bdx_msr_uncores;
-        /* BDX-DE doesn't have SBOX */
-        if (boot_cpu_data.x86_model == 86)
-                uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 }
 static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
new file mode 100644
index 000000000000..6999f7d01a0d
--- /dev/null
+++ b/arch/x86/include/asm/intel-family.h
@@ -0,0 +1,68 @@
+#ifndef _ASM_X86_INTEL_FAMILY_H
+#define _ASM_X86_INTEL_FAMILY_H
+/*
+ * "Big Core" Processors (Branded as Core, Xeon, etc...)
+ *
+ * The "_X" parts are generally the EP and EX Xeons, or the
+ * "Extreme" ones, like Broadwell-E.
+ *
+ * Things ending in "2" are usually because we have no better
+ * name for them.  There's no processor called "WESTMERE2".
+ */
+#define INTEL_FAM6_CORE_YONAH           0x0E
+#define INTEL_FAM6_CORE2_MEROM          0x0F
+#define INTEL_FAM6_CORE2_MEROM_L        0x16
+#define INTEL_FAM6_CORE2_PENRYN         0x17
+#define INTEL_FAM6_CORE2_DUNNINGTON     0x1D
+#define INTEL_FAM6_NEHALEM              0x1E
+#define INTEL_FAM6_NEHALEM_EP           0x1A
+#define INTEL_FAM6_NEHALEM_EX           0x2E
+#define INTEL_FAM6_WESTMERE             0x25
+#define INTEL_FAM6_WESTMERE2            0x1F
+#define INTEL_FAM6_WESTMERE_EP          0x2C
+#define INTEL_FAM6_WESTMERE_EX          0x2F
+#define INTEL_FAM6_SANDYBRIDGE          0x2A
+#define INTEL_FAM6_SANDYBRIDGE_X        0x2D
+#define INTEL_FAM6_IVYBRIDGE            0x3A
+#define INTEL_FAM6_IVYBRIDGE_X          0x3E
+#define INTEL_FAM6_HASWELL_CORE         0x3C
+#define INTEL_FAM6_HASWELL_X            0x3F
+#define INTEL_FAM6_HASWELL_ULT          0x45
+#define INTEL_FAM6_HASWELL_GT3E         0x46
+#define INTEL_FAM6_BROADWELL_CORE       0x3D
+#define INTEL_FAM6_BROADWELL_XEON_D     0x56
+#define INTEL_FAM6_BROADWELL_GT3E       0x47
+#define INTEL_FAM6_BROADWELL_X          0x4F
+#define INTEL_FAM6_SKYLAKE_MOBILE       0x4E
+#define INTEL_FAM6_SKYLAKE_DESKTOP      0x5E
+#define INTEL_FAM6_SKYLAKE_X            0x55
+#define INTEL_FAM6_KABYLAKE_MOBILE      0x8E
+#define INTEL_FAM6_KABYLAKE_DESKTOP     0x9E
+/* "Small Core" Processors (Atom) */
+#define INTEL_FAM6_ATOM_PINEVIEW        0x1C
+#define INTEL_FAM6_ATOM_LINCROFT        0x26
+#define INTEL_FAM6_ATOM_PENWELL         0x27
+#define INTEL_FAM6_ATOM_CLOVERVIEW      0x35
+#define INTEL_FAM6_ATOM_CEDARVIEW       0x36
+#define INTEL_FAM6_ATOM_SILVERMONT1     0x37 /* BayTrail/BYT / Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT2     0x4D /* Avaton/Rangely */
+#define INTEL_FAM6_ATOM_AIRMONT         0x4C /* CherryTrail / Braswell */
+#define INTEL_FAM6_ATOM_MERRIFIELD1     0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MERRIFIELD2     0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_GOLDMONT        0x5C
+#define INTEL_FAM6_ATOM_DENVERTON       0x5F /* Goldmont Microserver */
+/* Xeon Phi */
+#define INTEL_FAM6_XEON_PHI_KNL         0x57 /* Knights Landing */
+#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4421b5da409d..d1d1e5094c28 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -38,12 +38,11 @@ typedef u8 kprobe_opcode_t;
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
 #define MAX_STACK_SIZE 64
-#define MIN_STACK_SIZE(ADDR)                                           \
+#define CUR_STACK_SIZE(ADDR) \
-        (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
+        (current_top_of_stack() - (unsigned long)(ADDR))
-                              THREAD_SIZE - (unsigned long)(ADDR)))    \
+#define MIN_STACK_SIZE(ADDR)                            \
-         ? (MAX_STACK_SIZE)                                            \
+        (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ?        \
-         : (((unsigned long)current_thread_info()) +                   \
+         MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR))
-            THREAD_SIZE - (unsigned long)(ADDR)))
 #define flush_insn_slot(p)      do { } while (0)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0fbe7e70dc1..69e62862b622 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #include <linux/irqbypass.h>
 #include <linux/hyperv.h>
+#include <asm/apic.h>
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
@@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+static inline int kvm_cpu_get_apicid(int mps_cpu)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+        return __default_cpu_present_to_apicid(mps_cpu);
+#else
+        WARN_ON_ONCE(1);
+        return BAD_APICID;
+#endif
+}
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 7dc1d8fef7fd..b5fee97813cd 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -122,7 +122,7 @@ notrace static inline void native_write_msr(unsigned int msr,
                     "2:\n"
                     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
                     : : "c" (msr), "a"(low), "d" (high) : "memory");
-        if (msr_tracepoint_active(__tracepoint_read_msr))
+        if (msr_tracepoint_active(__tracepoint_write_msr))
                do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
@@ -141,7 +141,7 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
                     : "c" (msr), "0" (low), "d" (high),
                       [fault] "i" (-EIO)
                     : "memory");
-        if (msr_tracepoint_active(__tracepoint_read_msr))
+        if (msr_tracepoint_active(__tracepoint_write_msr))
                do_trace_write_msr(msr, ((u64)high << 32 | low), err);
        return err;
 }
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index bf7f8b55b0f9..574c23cf761a 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -81,7 +81,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
        struct page *page;
-        page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+        page = alloc_pages(GFP_KERNEL |  __GFP_ZERO, 0);
        if (!page)
                return NULL;
        if (!pgtable_pmd_page_ctor(page)) {
@@ -125,7 +125,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+        return (pud_t *)get_zeroed_page(GFP_KERNEL);
 }
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 7c247e7404be..0944218af9e2 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -14,7 +14,7 @@ extern int kstack_depth_to_print;
 struct thread_info;
 struct stacktrace_ops;
-typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+typedef unsigned long (*walk_stack_t)(struct task_struct *task,
                                      unsigned long *stack,
                                      unsigned long bp,
                                      const struct stacktrace_ops *ops,
@@ -23,13 +23,13 @@ typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
                                      int *graph);
 extern unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
                    unsigned long *stack, unsigned long bp,
                    const struct stacktrace_ops *ops, void *data,
                    unsigned long *end, int *graph);
 extern unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
                       unsigned long *stack, unsigned long bp,
                       const struct stacktrace_ops *ops, void *data,
                       unsigned long *end, int *graph);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 84e33ff5a6d5..446702ed99dc 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2588,8 +2588,8 @@ static struct resource * __init ioapic_setup_resources(void)
                res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
                snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
                mem += IOAPIC_RESOURCE_NAME_SIZE;
+                ioapics[i].iomem_res = &res[num];
                num++;
-                ioapics[i].iomem_res = res;
        }
        ioapic_resources = res;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c343a54bed39..f5c69d8974e1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -674,14 +674,14 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
        u64 value;
        /* re-enable TopologyExtensions if switched off by BIOS */
-        if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+        if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
            !cpu_has(c, X86_FEATURE_TOPOEXT)) {
                if (msr_set_bit(0xc0011005, 54) > 0) {
                        rdmsrl(0xc0011005, value);
                        if (value & BIT_64(54)) {
                                set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-                                pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+                                pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
                        }
                }
        }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2bb25c3fe2e8..ef8017ca5ba9 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -42,16 +42,14 @@ void printk_address(unsigned long address)
 static void
 print_ftrace_graph_addr(unsigned long addr, void *data,
                        const struct stacktrace_ops *ops,
-                        struct thread_info *tinfo, int *graph)
+                        struct task_struct *task, int *graph)
 {
-        struct task_struct *task;
        unsigned long ret_addr;
        int index;
        if (addr != (unsigned long)return_to_handler)
                return;
-        task = tinfo->task;
        index = task->curr_ret_stack;
        if (!task->ret_stack || index < *graph)
@@ -68,7 +66,7 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
 static inline void
 print_ftrace_graph_addr(unsigned long addr, void *data,
                        const struct stacktrace_ops *ops,
-                        struct thread_info *tinfo, int *graph)
+                        struct task_struct *task, int *graph)
 { }
 #endif
@@ -79,10 +77,10 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
 * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
 */
-static inline int valid_stack_ptr(struct thread_info *tinfo,
+static inline int valid_stack_ptr(struct task_struct *task,
                        void *p, unsigned int size, void *end)
 {
-        void *t = tinfo;
+        void *t = task_stack_page(task);
        if (end) {
                if (p < end && p >= (end-THREAD_SIZE))
                        return 1;
@@ -93,14 +91,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo,
 }
 unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
                unsigned long *stack, unsigned long bp,
                const struct stacktrace_ops *ops, void *data,
                unsigned long *end, int *graph)
 {
        struct stack_frame *frame = (struct stack_frame *)bp;
-        while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+        while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
                unsigned long addr;
                addr = *stack;
@@ -112,7 +110,7 @@ print_context_stack(struct thread_info *tinfo,
                        } else {
                                ops->address(data, addr, 0);
                        }
-                        print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+                        print_ftrace_graph_addr(addr, data, ops, task, graph);
                }
                stack++;
        }
@@ -121,7 +119,7 @@ print_context_stack(struct thread_info *tinfo,
 EXPORT_SYMBOL_GPL(print_context_stack);
 unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
                       unsigned long *stack, unsigned long bp,
                       const struct stacktrace_ops *ops, void *data,
                       unsigned long *end, int *graph)
@@ -129,7 +127,7 @@ print_context_stack_bp(struct thread_info *tinfo,
        struct stack_frame *frame = (struct stack_frame *)bp;
        unsigned long *ret_addr = &frame->return_address;
-        while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
+        while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) {
                unsigned long addr = *ret_addr;
                if (!__kernel_text_address(addr))
@@ -139,7 +137,7 @@ print_context_stack_bp(struct thread_info *tinfo,
                        break;
                frame = frame->next_frame;
                ret_addr = &frame->return_address;
-                print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+                print_ftrace_graph_addr(addr, data, ops, task, graph);
        }
        return (unsigned long)frame;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 464ffd69b92e..fef917e79b9d 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -61,15 +61,13 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                bp = stack_frame(task, regs);
        for (;;) {
-                struct thread_info *context;
                void *end_stack;
                end_stack = is_hardirq_stack(stack, cpu);
                if (!end_stack)
                        end_stack = is_softirq_stack(stack, cpu);
-                context = task_thread_info(task);
+                bp = ops->walk_stack(task, stack, bp, ops, data,
-                bp = ops->walk_stack(context, stack, bp, ops, data,
                                     end_stack, &graph);
                /* Stop if not on irq stack */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5f1c6266eb30..d558a8a49016 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -153,7 +153,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                const struct stacktrace_ops *ops, void *data)
 {
        const unsigned cpu = get_cpu();
-        struct thread_info *tinfo;
        unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
        unsigned long dummy;
        unsigned used = 0;
@@ -179,7 +178,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
         * current stack address. If the stacks consist of nested
         * exceptions
         */
-        tinfo = task_thread_info(task);
        while (!done) {
                unsigned long *stack_end;
                enum stack_type stype;
@@ -202,7 +200,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                        if (ops->stack(data, id) < 0)
                                break;
-                        bp = ops->walk_stack(tinfo, stack, bp, ops,
+                        bp = ops->walk_stack(task, stack, bp, ops,
                                             data, stack_end, &graph);
                        ops->stack(data, "<EOE>");
                        /*
@@ -218,7 +216,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                        if (ops->stack(data, "IRQ") < 0)
                                break;
-                        bp = ops->walk_stack(tinfo, stack, bp,
+                        bp = ops->walk_stack(task, stack, bp,
                                     ops, data, stack_end, &graph);
                        /*
                         * We link to the next stack (which would be
@@ -240,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
        /*
         * This handles the process stack:
         */
-        bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+        bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
        put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 4d38416e2a7f..04f89caef9c4 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -57,7 +57,7 @@
 # error "Need more than one PGD for the ESPFIX hack"
 #endif
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 /* This contains the *bottom* address of the espfix stack */
 DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f29a9c8..c627bf8d98ad 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -130,11 +130,9 @@ void irq_ctx_init(int cpu)
 void do_softirq_own_stack(void)
 {
-        struct thread_info *curstk;
        struct irq_stack *irqstk;
        u32 *isp, *prev_esp;
-        curstk = current_stack();
        irqstk = __this_cpu_read(softirq_stack);
        /* build the stack frame on the softirq stack */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 38cf7a741250..7847e5c0e0b5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
                 * normal page fault.
                 */
                regs->ip = (unsigned long)cur->addr;
+                /*
+                 * Trap flag (TF) has been set here because this fault
+                 * happened where the single stepping will be done.
+                 * So clear it by resetting the current kprobe:
+                 */
+                regs->flags &= ~X86_EFLAGS_TF;
+                /*
+                 * If the TF flag was set before the kprobe hit,
+                 * don't touch it:
+                 */
                regs->flags |= kcb->kprobe_old_flags;
                if (kcb->kprobe_status == KPROBE_REENTER)
                        restore_previous_kprobe(kcb);
                else
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d1590486204a..00f03d82e69a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -96,6 +96,12 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
                local_irq_disable();
 }
+/*
+ * In IST context, we explicitly disable preemption.  This serves two
+ * purposes: it makes it much less likely that we would accidentally
+ * schedule in IST context and it will force a warning if we somehow
+ * manage to schedule by accident.
+ */
 void ist_enter(struct pt_regs *regs)
 {
        if (user_mode(regs)) {
@@ -110,13 +116,7 @@ void ist_enter(struct pt_regs *regs)
                rcu_nmi_enter();
        }
-        /*
+        preempt_disable();
-         * We are atomic because we're on the IST stack; or we're on
-         * x86_32, in which case we still shouldn't schedule; or we're
-         * on x86_64 and entered from user mode, in which case we're
-         * still atomic unless ist_begin_non_atomic is called.
-         */
-        preempt_count_add(HARDIRQ_OFFSET);
        /* This code is a bit fragile.  Test it. */
        RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
@@ -124,7 +124,7 @@ void ist_enter(struct pt_regs *regs)
 void ist_exit(struct pt_regs *regs)
 {
-        preempt_count_sub(HARDIRQ_OFFSET);
+        preempt_enable_no_resched();
        if (!user_mode(regs))
                rcu_nmi_exit();
@@ -155,7 +155,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
        BUG_ON((unsigned long)(current_top_of_stack() -
                               current_stack_pointer()) >= THREAD_SIZE);
-        preempt_count_sub(HARDIRQ_OFFSET);
+        preempt_enable_no_resched();
 }
 /**
@@ -165,7 +165,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 */
 void ist_end_non_atomic(void)
 {
-        preempt_count_add(HARDIRQ_OFFSET);
+        preempt_disable();
 }
 static nokprobe_inline int
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1163e8173e5a..16ef31b87452 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO);
 /* enable / disable AVIC */
 static int avic;
+#ifdef CONFIG_X86_LOCAL_APIC
 module_param(avic, int, S_IRUGO);
+#endif
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void)
        } else
                kvm_disable_tdp();
-        if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)))
+        if (avic) {
-                avic = false;
+                if (!npt_enabled ||
+                    !boot_cpu_has(X86_FEATURE_AVIC) ||
-        if (avic)
+                    !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
-                pr_info("AVIC enabled\n");
+                        avic = false;
+                else
+                        pr_info("AVIC enabled\n");
+        }
        return 0;
@@ -1324,7 +1329,7 @@ free_avic:
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
        u64 entry;
-        int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu);
+        int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
        struct vcpu_svm *svm = to_svm(vcpu);
        if (!kvm_vcpu_apicv_active(vcpu))
@@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
        u64 entry;
        /* ID = 0xff (broadcast), ID > 0xff (reserved) */
-        int h_physical_id = __default_cpu_present_to_apicid(cpu);
+        int h_physical_id = kvm_cpu_get_apicid(cpu);
        struct vcpu_svm *svm = to_svm(vcpu);
        if (!kvm_vcpu_apicv_active(vcpu))
@@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
        if (avic_vcpu_is_running(vcpu))
                wrmsrl(SVM_AVIC_DOORBELL,
-                       __default_cpu_present_to_apicid(vcpu->cpu));
+                       kvm_cpu_get_apicid(vcpu->cpu));
        else
                kvm_vcpu_wake_up(vcpu);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fb93010beaa4..003618e324ce 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
        unsigned int dest;
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-                !irq_remapping_cap(IRQ_POSTING_CAP))
+                !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+                !kvm_vcpu_apicv_active(vcpu))
                return;
        do {
@@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
        struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-                !irq_remapping_cap(IRQ_POSTING_CAP))
+                !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+                !kvm_vcpu_apicv_active(vcpu))
                return;
        /* Set SN when the vCPU is preempted */
@@ -10714,7 +10716,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
        struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-                !irq_remapping_cap(IRQ_POSTING_CAP))
+                !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+                !kvm_vcpu_apicv_active(vcpu))
                return 0;
        vcpu->pre_pcpu = vcpu->cpu;
@@ -10780,7 +10783,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
        unsigned long flags;
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-                !irq_remapping_cap(IRQ_POSTING_CAP))
+                !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+                !kvm_vcpu_apicv_active(vcpu))
                return;
        do {
@@ -10833,7 +10837,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
        int idx, ret = -EINVAL;
        if (!kvm_arch_has_assigned_device(kvm) ||
-                !irq_remapping_cap(IRQ_POSTING_CAP))
+                !irq_remapping_cap(IRQ_POSTING_CAP) ||
+                !kvm_vcpu_apicv_active(kvm->vcpus[0]))
                return 0;
        idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e25043..aa0ff4b02a96 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
 #include <asm/fixmap.h>
 #include <asm/mtrr.h>
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
 #ifdef CONFIG_HIGHPTE
 #define PGALLOC_USER_GFP __GFP_HIGHMEM
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6e7242be1c87..b226b3f497f1 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -139,7 +139,7 @@ int __init efi_alloc_page_tables(void)
        if (efi_enabled(EFI_OLD_MEMMAP))
                return 0;
-        gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
+        gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
        efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
        if (!efi_pgd)
                return -ENOMEM;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 478a2de543a5..67433714b791 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
        /* NOTE: The loop is more greedy than the cleanup_highmap variant.
         * We include the PMD passed in on _both_ boundaries. */
-        for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+        for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
                        pmd++, vaddr += PMD_SIZE) {
                if (pmd_none(*pmd))
                        continue;
@@ -1551,41 +1551,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
-#ifdef CONFIG_X86_32
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-        /* If there's an existing pte, then don't allow _PAGE_RW to be set */
-        if (pte_val_ma(*ptep) & _PAGE_PRESENT)
-                pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
-                               pte_val_ma(pte));
-        return pte;
-}
-#else /* CONFIG_X86_64 */
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-        unsigned long pfn;
-        if (xen_feature(XENFEAT_writable_page_tables) ||
-            xen_feature(XENFEAT_auto_translated_physmap) ||
-            xen_start_info->mfn_list >= __START_KERNEL_map)
-                return pte;
-        /*
-         * Pages belonging to the initial p2m list mapped outside the default
-         * address range must be mapped read-only. This region contains the
-         * page tables for mapping the p2m list, too, and page tables MUST be
-         * mapped read-only.
-         */
-        pfn = pte_pfn(pte);
-        if (pfn >= xen_start_info->first_p2m_pfn &&
-            pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
-                pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
-        return pte;
-}
-#endif /* CONFIG_X86_64 */
 /*
 * Init-time set_pte while constructing initial pagetables, which
 * doesn't allow RO page table pages to be remapped RW.
@@ -1600,13 +1565,37 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 * so always write the PTE directly and rely on Xen trapping and
 * emulating any updates as necessary.
 */
-static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+__visible pte_t xen_make_pte_init(pteval_t pte)
 {
-        if (pte_mfn(pte) != INVALID_P2M_ENTRY)
+#ifdef CONFIG_X86_64
-                pte = mask_rw_pte(ptep, pte);
+        unsigned long pfn;
-        else
-                pte = __pte_ma(0);
+        /*
+         * Pages belonging to the initial p2m list mapped outside the default
+         * address range must be mapped read-only. This region contains the
+         * page tables for mapping the p2m list, too, and page tables MUST be
+         * mapped read-only.
+         */
+        pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+        if (xen_start_info->mfn_list < __START_KERNEL_map &&
+            pfn >= xen_start_info->first_p2m_pfn &&
+            pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+                pte &= ~_PAGE_RW;
+#endif
+        pte = pte_pfn_to_mfn(pte);
+        return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+#ifdef CONFIG_X86_32
+        /* If there's an existing pte, then don't allow _PAGE_RW to be set */
+        if (pte_mfn(pte) != INVALID_P2M_ENTRY
+            && pte_val_ma(*ptep) & _PAGE_PRESENT)
+                pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+                               pte_val_ma(pte));
+#endif
        native_set_pte(ptep, pte);
 }
@@ -2407,6 +2396,7 @@ static void __init xen_post_allocator_init(void)
        pv_mmu_ops.alloc_pud = xen_alloc_pud;
        pv_mmu_ops.release_pud = xen_release_pud;
 #endif
+        pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
 #ifdef CONFIG_X86_64
        pv_mmu_ops.write_cr3 = &xen_write_cr3;
@@ -2455,7 +2445,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
        .pte_val = PV_CALLEE_SAVE(xen_pte_val),
        .pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
-        .make_pte = PV_CALLEE_SAVE(xen_make_pte),
+        .make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
        .make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
 #ifdef CONFIG_X86_PAE
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index cab9f766bb06..dd2a49a8aacc 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -182,7 +182,7 @@ static void * __ref alloc_p2m_page(void)
        if (unlikely(!slab_is_available()))
                return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE);
-        return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
+        return (void *)__get_free_page(GFP_KERNEL);
 }
 static void __ref free_p2m_page(void *p)
diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index d38eb9237e64..1065bc8bcae5 100644
--- a/arch/xtensa/include/asm/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
@@ -44,7 +44,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
        pte_t *ptep;
        int i;
-        ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+        ptep = (pte_t *)__get_free_page(GFP_KERNEL);
        if (!ptep)
                return NULL;
        for (i = 0; i < 1024; i++)
author	David S. Miller <davem@davemloft.net>	2016-06-30 05:03:36 -0400
committer	David S. Miller <davem@davemloft.net>	2016-06-30 05:03:36 -0400
commit	ee58b57100ca953da7320c285315a95db2f7053d (patch)
tree	77b815a31240adc4d6326346908137fc6c2c3a96 /arch
parent	6f30e8b022c8e3a722928ddb1a2ae0be852fcc0e (diff)
parent	e7bdea7750eb2a64aea4a08fa5c0a31719c8155d (diff)