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

Minor conflicts in drivers/net/ethernet/mellanox/mlx5/core/en_rep.c,
we had some overlapping changes:

1) In 'net' MLX5E_PARAMS_LOG_{SQ,RQ}_SIZE -->
   MLX5E_REP_PARAMS_LOG_{SQ,RQ}_SIZE

2) In 'net-next' params->log_rq_size is renamed to be
   params->log_rq_mtu_frames.

3) In 'net-next' params->hard_mtu is added.

Signed-off-by: David S. Miller <davem@davemloft.net>

55 files changed, 398 insertions, 317 deletions

diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 78a647080ebc..199ebc1c4538 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -22,6 +22,7 @@ config ARM_PTDUMP_DEBUGFS
 
 config DEBUG_WX
 	bool "Warn on W+X mappings at boot"
+	depends on MMU
 	select ARM_PTDUMP_CORE
 	---help---
 		Generate a warning if any W+X mappings are found at boot.
diff --git a/arch/arm/boot/deflate_xip_data.sh b/arch/arm/boot/deflate_xip_data.sh
index 1189598a25eb..5e7d758ebdd6 100755
--- a/arch/arm/boot/deflate_xip_data.sh
+++ b/arch/arm/boot/deflate_xip_data.sh
@@ -30,7 +30,7 @@ esac
 
 sym_val() {
 	# extract hex value for symbol in $1
-	local val=$($NM "$VMLINUX" | sed -n "/ $1$/{s/ .*$//p;q}")
+	local val=$($NM "$VMLINUX" 2>/dev/null | sed -n "/ $1\$/{s/ .*$//p;q}")
 	[ "$val" ] || { echo "can't find $1 in $VMLINUX" 1>&2; exit 1; }
 	# convert from hex to decimal
 	echo $((0x$val))
@@ -48,12 +48,12 @@ data_end=$(($_edata_loc - $base_offset))
 file_end=$(stat -c "%s" "$XIPIMAGE")
 if [ "$file_end" != "$data_end" ]; then
 	printf "end of xipImage doesn't match with _edata_loc (%#x vs %#x)\n" \
-	       $(($file_end + $base_offset)) $_edata_loc 2>&1
+	       $(($file_end + $base_offset)) $_edata_loc 1>&2
 	exit 1;
 fi
 
 # be ready to clean up
-trap 'rm -f "$XIPIMAGE.tmp"' 0 1 2 3
+trap 'rm -f "$XIPIMAGE.tmp"; exit 1' 1 2 3
 
 # substitute the data section by a compressed version
 $DD if="$XIPIMAGE" count=$data_start iflag=count_bytes of="$XIPIMAGE.tmp"
diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi
index b0d8431a3700..ae2b8c952e80 100644
--- a/arch/arm/boot/dts/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed-g4.dtsi
@@ -42,6 +42,11 @@
 		};
 	};
 
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0x40000000 0>;
+	};
+
 	ahb {
 		compatible = "simple-bus";
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi
index 40de3b66c33f..2477ebc11d9d 100644
--- a/arch/arm/boot/dts/aspeed-g5.dtsi
+++ b/arch/arm/boot/dts/aspeed-g5.dtsi
@@ -42,6 +42,11 @@
 		};
 	};
 
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0>;
+	};
+
 	ahb {
 		compatible = "simple-bus";
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index a7a5dc7b2700..e7d2db839d70 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -82,7 +82,7 @@
 		enable-active-high;
 	};
 
-	reg_usb_otg2_vbus: regulator-usb-otg1-vbus {
+	reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
 		compatible = "regulator-fixed";
 		regulator-name = "usb_otg2_vbus";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 6102e4e7f35c..354aff45c1af 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -927,6 +927,7 @@
 	i2s: i2s@ff890000 {
 		compatible = "rockchip,rk3288-i2s", "rockchip,rk3066-i2s";
 		reg = <0x0 0xff890000 0x0 0x10000>;
+		#sound-dai-cells = <0>;
 		interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1176,6 +1177,7 @@
 		compatible = "rockchip,rk3288-dw-hdmi";
 		reg = <0x0 0xff980000 0x0 0x20000>;
 		reg-io-width = <4>;
+		#sound-dai-cells = <0>;
 		rockchip,grf = <&grf>;
 		interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru  PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>;
diff --git a/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts b/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts
index 51e6f1d21c32..b2758dd8ce43 100644
--- a/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts
@@ -42,7 +42,6 @@
 
 /dts-v1/;
 #include "sun6i-a31s.dtsi"
-#include "sunxi-common-regulators.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 
 / {
@@ -99,6 +98,7 @@
 	pinctrl-0 = <&gmac_pins_rgmii_a>, <&gmac_phy_reset_pin_bpi_m2>;
 	phy = <&phy1>;
 	phy-mode = "rgmii";
+	phy-supply = <&reg_dldo1>;
 	snps,reset-gpio = <&pio 0 21 GPIO_ACTIVE_HIGH>; /* PA21 */
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 30000>;
@@ -118,7 +118,7 @@
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_bpi_m2>;
-	vmmc-supply = <&reg_vcc3v0>;
+	vmmc-supply = <&reg_dcdc1>;
 	bus-width = <4>;
 	cd-gpios = <&pio 0 4 GPIO_ACTIVE_HIGH>; /* PA4 */
 	cd-inverted;
@@ -132,7 +132,7 @@
 &mmc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins_a>;
-	vmmc-supply = <&reg_vcc3v0>;
+	vmmc-supply = <&reg_aldo1>;
 	mmc-pwrseq = <&mmc2_pwrseq>;
 	bus-width = <4>;
 	non-removable;
@@ -163,6 +163,8 @@
 		reg = <0x68>;
 		interrupt-parent = <&nmi_intc>;
 		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		eldoin-supply = <&reg_dcdc1>;
+		x-powers,drive-vbus-en;
 	};
 };
 
@@ -193,7 +195,28 @@
 
 #include "axp22x.dtsi"
 
+&reg_aldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
+&reg_aldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <2500000>;
+	regulator-max-microvolt = <2500000>;
+	regulator-name = "vcc-gmac";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "avcc";
+};
+
 &reg_dc5ldo {
+	regulator-always-on;
 	regulator-min-microvolt = <700000>;
 	regulator-max-microvolt = <1320000>;
 	regulator-name = "vdd-cpus";
@@ -233,6 +256,40 @@
 	regulator-name = "vcc-dram";
 };
 
+&reg_dldo1 {
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-mac";
+};
+
+&reg_dldo2 {
+	regulator-min-microvolt = <2800000>;
+	regulator-max-microvolt = <2800000>;
+	regulator-name = "avdd-csi";
+};
+
+&reg_dldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-pb";
+};
+
+&reg_eldo1 {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+	regulator-name = "vdd-csi";
+	status = "okay";
+};
+
+&reg_ldo_io1 {
+	regulator-always-on;
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+	regulator-name = "vcc-pm-cpus";
+	status = "okay";
+};
+
 &uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
index 9c99e817535e..5b85889f82ee 100644
--- a/arch/arm/include/asm/vdso.h
+++ b/arch/arm/include/asm/vdso.h
@@ -12,8 +12,6 @@ struct mm_struct;
 
 void arm_install_vdso(struct mm_struct *mm, unsigned long addr);
 
-extern char vdso_start, vdso_end;
-
 extern unsigned int vdso_total_pages;
 
 #else /* CONFIG_VDSO */
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index a4d6dc0f2427..f4dd7f9663c1 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -39,6 +39,8 @@
 
 static struct page **vdso_text_pagelist;
 
+extern char vdso_start[], vdso_end[];
+
 /* Total number of pages needed for the data and text portions of the VDSO. */
 unsigned int vdso_total_pages __ro_after_init;
 
@@ -197,13 +199,13 @@ static int __init vdso_init(void)
 	unsigned int text_pages;
 	int i;
 
-	if (memcmp(&vdso_start, "\177ELF", 4)) {
+	if (memcmp(vdso_start, "\177ELF", 4)) {
 		pr_err("VDSO is not a valid ELF object!\n");
 		return -ENOEXEC;
 	}
 
-	text_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
-	pr_debug("vdso: %i text pages at base %p\n", text_pages, &vdso_start);
+	text_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+	pr_debug("vdso: %i text pages at base %p\n", text_pages, vdso_start);
 
 	/* Allocate the VDSO text pagelist */
 	vdso_text_pagelist = kcalloc(text_pages, sizeof(struct page *),
@@ -218,7 +220,7 @@ static int __init vdso_init(void)
 	for (i = 0; i < text_pages; i++) {
 		struct page *page;
 
-		page = virt_to_page(&vdso_start + i * PAGE_SIZE);
+		page = virt_to_page(vdso_start + i * PAGE_SIZE);
 		vdso_text_pagelist[i] = page;
 	}
 
@@ -229,7 +231,7 @@ static int __init vdso_init(void)
 
 	cntvct_ok = cntvct_functional();
 
-	patch_vdso(&vdso_start);
+	patch_vdso(vdso_start);
 
 	return 0;
 }
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index a3e78074be70..62eb7d668890 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -127,8 +127,8 @@ static struct gpiod_lookup_table mmc_gpios_table = {
 	.dev_id = "da830-mmc.0",
 	.table = {
 		/* CD: gpio3_12: gpio60: chip 1 contains gpio range 32-63*/
-		GPIO_LOOKUP("davinci_gpio.1", 28, "cd", GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP("davinci_gpio.1", 29, "wp", GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", 28, "cd", GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", 29, "wp", GPIO_ACTIVE_LOW),
 	},
 };
 
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 7e5d7a083707..36cd23c8be9b 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -133,6 +133,9 @@ static void __init u8500_init_machine(void)
 	if (of_machine_is_compatible("st-ericsson,u8540"))
 		of_platform_populate(NULL, u8500_local_bus_nodes,
 				     u8540_auxdata_lookup, NULL);
+	else
+		of_platform_populate(NULL, u8500_local_bus_nodes,
+				     NULL, NULL);
 }
 
 static const char * stericsson_dt_platform_compat[] = {
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index d443e481c3e9..8805a59bae53 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -888,11 +888,8 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 	timer->irq = irq->start;
 	timer->pdev = pdev;
 
-	/* Skip pm_runtime_enable for OMAP1 */
-	if (!(timer->capability & OMAP_TIMER_NEEDS_RESET)) {
-		pm_runtime_enable(dev);
-		pm_runtime_irq_safe(dev);
-	}
+	pm_runtime_enable(dev);
+	pm_runtime_irq_safe(dev);
 
 	if (!timer->reserved) {
 		ret = pm_runtime_get_sync(dev);
diff --git a/arch/arm/plat-omap/include/plat/sram.h b/arch/arm/plat-omap/include/plat/sram.h
index fb061cf0d736..30a07730807a 100644
--- a/arch/arm/plat-omap/include/plat/sram.h
+++ b/arch/arm/plat-omap/include/plat/sram.h
@@ -5,13 +5,4 @@ void omap_map_sram(unsigned long start, unsigned long size,
 			unsigned long skip, int cached);
 void omap_sram_reset(void);
 
-extern void *omap_sram_push_address(unsigned long size);
-
-/* Macro to push a function to the internal SRAM, using the fncpy API */
-#define omap_sram_push(funcp, size) ({				\
-	typeof(&(funcp)) _res = NULL;				\
-	void *_sram_address = omap_sram_push_address(size);	\
-	if (_sram_address)					\
-		_res = fncpy(_sram_address, &(funcp), size);	\
-	_res;							\
-})
+extern void *omap_sram_push(void *funcp, unsigned long size);
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index a5bc92d7e476..921840acf65c 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -23,6 +23,7 @@
 #include <asm/fncpy.h>
 #include <asm/tlb.h>
 #include <asm/cacheflush.h>
+#include <asm/set_memory.h>
 
 #include <asm/mach/map.h>
 
@@ -42,7 +43,7 @@ static void __iomem *omap_sram_ceil;
  * Note that fncpy requires the returned address to be aligned
  * to an 8-byte boundary.
  */
-void *omap_sram_push_address(unsigned long size)
+static void *omap_sram_push_address(unsigned long size)
 {
 	unsigned long available, new_ceil = (unsigned long)omap_sram_ceil;
 
@@ -60,6 +61,30 @@ void *omap_sram_push_address(unsigned long size)
 	return (void *)omap_sram_ceil;
 }
 
+void *omap_sram_push(void *funcp, unsigned long size)
+{
+	void *sram;
+	unsigned long base;
+	int pages;
+	void *dst = NULL;
+
+	sram = omap_sram_push_address(size);
+	if (!sram)
+		return NULL;
+
+	base = (unsigned long)sram & PAGE_MASK;
+	pages = PAGE_ALIGN(size) / PAGE_SIZE;
+
+	set_memory_rw(base, pages);
+
+	dst = fncpy(sram, funcp, size);
+
+	set_memory_ro(base, pages);
+	set_memory_x(base, pages);
+
+	return dst;
+}
+
 /*
  * The SRAM context is lost during off-idle and stack
  * needs to be reset.
@@ -75,6 +100,9 @@ void omap_sram_reset(void)
 void __init omap_map_sram(unsigned long start, unsigned long size,
 				 unsigned long skip, int cached)
 {
+	unsigned long base;
+	int pages;
+
 	if (size == 0)
 		return;
 
@@ -95,4 +123,10 @@ void __init omap_map_sram(unsigned long start, unsigned long size,
 	 */
 	memset_io(omap_sram_base + omap_sram_skip, 0,
 		  omap_sram_size - omap_sram_skip);
+
+	base = (unsigned long)omap_sram_base;
+	pages = PAGE_ALIGN(omap_sram_size) / PAGE_SIZE;
+
+	set_memory_ro(base, pages);
+	set_memory_x(base, pages);
 }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 03c6a3c72f9c..4c375e11ae95 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -648,7 +648,7 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
  */
 static int vfp_dying_cpu(unsigned int cpu)
 {
-	vfp_force_reload(cpu, current_thread_info());
+	vfp_current_hw_state[cpu] = NULL;
 	return 0;
 }
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index 03f195025390..204bdb9857b9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -406,8 +406,9 @@
 	wlan_pd_n: wlan-pd-n {
 		compatible = "regulator-fixed";
 		regulator-name = "wlan_pd_n";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wlan_module_reset_l>;
 
-		/* Note the wlan_module_reset_l pinctrl */
 		enable-active-high;
 		gpio = <&gpio1 11 GPIO_ACTIVE_HIGH>;
 
@@ -983,12 +984,6 @@ ap_i2c_audio: &i2c8 {
 	pinctrl-0 = <
 		&ap_pwroff	/* AP will auto-assert this when in S3 */
 		&clk_32k	/* This pin is always 32k on gru boards */
-
-		/*
-		 * We want this driven low ASAP; firmware should help us, but
-		 * we can help ourselves too.
-		 */
-		&wlan_module_reset_l
 	>;
 
 	pcfg_output_low: pcfg-output-low {
@@ -1168,12 +1163,7 @@ ap_i2c_audio: &i2c8 {
 		};
 
 		wlan_module_reset_l: wlan-module-reset-l {
-			/*
-			 * We want this driven low ASAP (As {Soon,Strongly} As
-			 * Possible), to avoid leakage through the powered-down
-			 * WiFi.
-			 */
-			rockchip,pins = <1 11 RK_FUNC_GPIO &pcfg_output_low>;
+			rockchip,pins = <1 11 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
 
 		bt_host_wake_l: bt-host-wake-l {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 2605118d4b4c..0b81ca1d07e7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -411,8 +411,8 @@
 			reg = <0x0 0xfe800000 0x0 0x100000>;
 			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>;
 			dr_mode = "otg";
-			phys = <&u2phy0_otg>, <&tcphy0_usb3>;
-			phy-names = "usb2-phy", "usb3-phy";
+			phys = <&u2phy0_otg>;
+			phy-names = "usb2-phy";
 			phy_type = "utmi_wide";
 			snps,dis_enblslpm_quirk;
 			snps,dis-u2-freeclk-exists-quirk;
@@ -444,8 +444,8 @@
 			reg = <0x0 0xfe900000 0x0 0x100000>;
 			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>;
 			dr_mode = "otg";
-			phys = <&u2phy1_otg>, <&tcphy1_usb3>;
-			phy-names = "usb2-phy", "usb3-phy";
+			phys = <&u2phy1_otg>;
+			phy-names = "usb2-phy";
 			phy_type = "utmi_wide";
 			snps,dis_enblslpm_quirk;
 			snps,dis-u2-freeclk-exists-quirk;
diff --git a/arch/mips/lantiq/Kconfig b/arch/mips/lantiq/Kconfig
index 692ae85a3e3d..8e3a1fc2bc39 100644
--- a/arch/mips/lantiq/Kconfig
+++ b/arch/mips/lantiq/Kconfig
@@ -13,6 +13,8 @@ choice
 config SOC_AMAZON_SE
 	bool "Amazon SE"
 	select SOC_TYPE_XWAY
+	select MFD_SYSCON
+	select MFD_CORE
 
 config SOC_XWAY
 	bool "XWAY"
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 52500d3b7004..e0af39b33e28 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -549,9 +549,9 @@ void __init ltq_soc_init(void)
 		clkdev_add_static(ltq_ar9_cpu_hz(), ltq_ar9_fpi_hz(),
 				ltq_ar9_fpi_hz(), CLOCK_250M);
 		clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P);
-		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0);
+		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM);
 		clkdev_add_pmu("1f203034.usb2-phy", "phy", 1, 0, PMU_USB1_P);
-		clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1);
+		clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1 | PMU_AHBM);
 		clkdev_add_pmu("1e180000.etop", "switch", 1, 0, PMU_SWITCH);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
@@ -560,7 +560,7 @@ void __init ltq_soc_init(void)
 	} else {
 		clkdev_add_static(ltq_danube_cpu_hz(), ltq_danube_fpi_hz(),
 				ltq_danube_fpi_hz(), ltq_danube_pp32_hz());
-		clkdev_add_pmu("1f203018.usb2-phy", "ctrl", 1, 0, PMU_USB0);
+		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM);
 		clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c
index 1b274742077d..d2718de60b9b 100644
--- a/arch/mips/ralink/mt7621.c
+++ b/arch/mips/ralink/mt7621.c
@@ -170,6 +170,28 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 	u32 n1;
 	u32 rev;
 
+	/* Early detection of CMP support */
+	mips_cm_probe();
+	mips_cpc_probe();
+
+	if (mips_cps_numiocu(0)) {
+		/*
+		 * mips_cm_probe() wipes out bootloader
+		 * config for CM regions and we have to configure them
+		 * again. This SoC cannot talk to pamlbus devices
+		 * witout proper iocu region set up.
+		 *
+		 * FIXME: it would be better to do this with values
+		 * from DT, but we need this very early because
+		 * without this we cannot talk to pretty much anything
+		 * including serial.
+		 */
+		write_gcr_reg0_base(MT7621_PALMBUS_BASE);
+		write_gcr_reg0_mask(~MT7621_PALMBUS_SIZE |
+				    CM_GCR_REGn_MASK_CMTGT_IOCU0);
+		__sync();
+	}
+
 	n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0);
 	n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1);
 
@@ -194,26 +216,6 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 
 	rt2880_pinmux_data = mt7621_pinmux_data;
 
-	/* Early detection of CMP support */
-	mips_cm_probe();
-	mips_cpc_probe();
-
-	if (mips_cps_numiocu(0)) {
-		/*
-		 * mips_cm_probe() wipes out bootloader
-		 * config for CM regions and we have to configure them
-		 * again. This SoC cannot talk to pamlbus devices
-		 * witout proper iocu region set up.
-		 *
-		 * FIXME: it would be better to do this with values
-		 * from DT, but we need this very early because
-		 * without this we cannot talk to pretty much anything
-		 * including serial.
-		 */
-		write_gcr_reg0_base(MT7621_PALMBUS_BASE);
-		write_gcr_reg0_mask(~MT7621_PALMBUS_SIZE |
-				    CM_GCR_REGn_MASK_CMTGT_IOCU0);
-	}
 
 	if (!register_cps_smp_ops())
 		return;
diff --git a/arch/mips/ralink/reset.c b/arch/mips/ralink/reset.c
index 64543d66e76b..e9531fea23a2 100644
--- a/arch/mips/ralink/reset.c
+++ b/arch/mips/ralink/reset.c
@@ -96,16 +96,9 @@ static void ralink_restart(char *command)
 	unreachable();
 }
 
-static void ralink_halt(void)
-{
-	local_irq_disable();
-	unreachable();
-}
-
 static int __init mips_reboot_setup(void)
 {
 	_machine_restart = ralink_restart;
-	_machine_halt = ralink_halt;
 
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 0abeb0e2d616..37671feb2bf6 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -87,6 +87,9 @@ typedef struct {
 	/* Number of bits in the mm_cpumask */
 	atomic_t active_cpus;
 
+	/* Number of users of the external (Nest) MMU */
+	atomic_t copros;
+
 	/* NPU NMMU context */
 	struct npu_context *npu_context;
 
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 8eea90f80e45..19b45ba6caf9 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -47,9 +47,6 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad
 #endif
 extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
-extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-				     unsigned long page_size);
-extern void radix__flush_tlb_lpid(unsigned long lpid);
 extern void radix__flush_tlb_all(void);
 extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 					unsigned long address);
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index a2c5c95882cf..2e2bacbdf6ed 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -203,6 +203,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x2000000000000000)
 #define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x4000000000000000)
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x8000000000000000)
 
@@ -465,7 +466,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
-	    CPU_FTR_PKEY)
+	    CPU_FTR_PKEY | CPU_FTR_P9_TLBIE_BUG)
 #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
 			     (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 051b3d63afe3..3a15b6db9501 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -92,15 +92,23 @@ static inline void dec_mm_active_cpus(struct mm_struct *mm)
 static inline void mm_context_add_copro(struct mm_struct *mm)
 {
 	/*
-	 * On hash, should only be called once over the lifetime of
-	 * the context, as we can't decrement the active cpus count
-	 * and flush properly for the time being.
+	 * If any copro is in use, increment the active CPU count
+	 * in order to force TLB invalidations to be global as to
+	 * propagate to the Nest MMU.
 	 */
-	inc_mm_active_cpus(mm);
+	if (atomic_inc_return(&mm->context.copros) == 1)
+		inc_mm_active_cpus(mm);
 }
 
 static inline void mm_context_remove_copro(struct mm_struct *mm)
 {
+	int c;
+
+	c = atomic_dec_if_positive(&mm->context.copros);
+
+	/* Detect imbalance between add and remove */
+	WARN_ON(c < 0);
+
 	/*
 	 * Need to broadcast a global flush of the full mm before
 	 * decrementing active_cpus count, as the next TLBI may be
@@ -111,7 +119,7 @@ static inline void mm_context_remove_copro(struct mm_struct *mm)
 	 * for the time being. Invalidations will remain global if
 	 * used on hash.
 	 */
-	if (radix_enabled()) {
+	if (c == 0 && radix_enabled()) {
 		flush_all_mm(mm);
 		dec_mm_active_cpus(mm);
 	}
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 945e2c29ad2d..8ca5d5b74618 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -709,6 +709,9 @@ static __init void cpufeatures_cpu_quirks(void)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
 	else if ((version & 0xffffefff) == 0x004e0201)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+
+	if ((version & 0xffff0000) == 0x004e0000)
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
 }
 
 static void __init cpufeatures_setup_finished(void)
@@ -720,6 +723,9 @@ static void __init cpufeatures_setup_finished(void)
 		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
 	}
 
+	/* Make sure powerpc_base_platform is non-NULL */
+	powerpc_base_platform = cur_cpu_spec->platform;
+
 	system_registers.lpcr = mfspr(SPRN_LPCR);
 	system_registers.hfscr = mfspr(SPRN_HFSCR);
 	system_registers.fscr = mfspr(SPRN_FSCR);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3ac87e53b3da..1ecfd8ffb098 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -706,7 +706,7 @@ EXC_COMMON_BEGIN(bad_addr_slb)
 	ld	r3, PACA_EXSLB+EX_DAR(r13)
 	std	r3, _DAR(r1)
 	beq	cr6, 2f
-	li	r10, 0x480		/* fix trap number for I-SLB miss */
+	li	r10, 0x481		/* fix trap number for I-SLB miss */
 	std	r10, _TRAP(r1)
 2:	bl	save_nvgprs
 	addi	r3, r1, STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index f88038847790..061aa0f47bb1 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -476,6 +476,14 @@ void force_external_irq_replay(void)
 	 */
 	WARN_ON(!arch_irqs_disabled());
 
+	/*
+	 * Interrupts must always be hard disabled before irq_happened is
+	 * modified (to prevent lost update in case of interrupt between
+	 * load and store).
+	 */
+	__hard_irq_disable();
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
 	/* Indicate in the PACA that we have an interrupt to replay */
 	local_paca->irq_happened |= PACA_IRQ_EE;
 }
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 5cb4e4687107..5d9bafe9a371 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -157,6 +157,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
 		     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
+		asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
+			     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 8888e625a999..e1c083fbe434 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -473,6 +473,17 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 			trace_tlbie(kvm->arch.lpid, 0, rbvalues[i],
 				kvm->arch.lpid, 0, 0, 0);
 		}
+
+		if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+			/*
+			 * Need the extra ptesync to make sure we don't
+			 * re-order the tlbie
+			 */
+			asm volatile("ptesync": : :"memory");
+			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+				     "r" (rbvalues[0]), "r" (kvm->arch.lpid));
+		}
+
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 		kvm->arch.tlbie_lock = 0;
 	} else {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index d33264697a31..f86a20270e50 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1557,6 +1557,24 @@ mc_cont:
 	ptesync
 3:	stw	r5,VCPU_SLB_MAX(r9)
 
+	/* load host SLB entries */
+BEGIN_MMU_FTR_SECTION
+	b	0f
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
+	ld	r8,PACA_SLBSHADOWPTR(r13)
+
+	.rept	SLB_NUM_BOLTED
+	li	r3, SLBSHADOW_SAVEAREA
+	LDX_BE	r5, r8, r3
+	addi	r3, r3, 8
+	LDX_BE	r6, r8, r3
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r8,r8,16
+	.endr
+0:
+
 guest_bypass:
 	stw	r12, STACK_SLOT_TRAP(r1)
 	mr 	r3, r12
@@ -2018,23 +2036,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r8
 	isync
 48:
-	/* load host SLB entries */
-BEGIN_MMU_FTR_SECTION
-	b	0f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
-	ld	r8,PACA_SLBSHADOWPTR(r13)
-
-	.rept	SLB_NUM_BOLTED
-	li	r3, SLBSHADOW_SAVEAREA
-	LDX_BE	r5, r8, r3
-	addi	r3, r3, 8
-	LDX_BE	r6, r8, r3
-	andis.	r7,r5,SLB_ESID_V@h
-	beq	1f
-	slbmte	r6,r5
-1:	addi	r8,r8,16
-	.endr
-0:
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	/* Finish timing, if we have a vcpu */
 	ld	r4, HSTATE_KVM_VCPU(r13)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index a0675e91ad7d..656933c85925 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -201,6 +201,15 @@ static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 	return va;
 }
 
+static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		/* Need the extra ptesync to ensure we don't reorder tlbie*/
+		asm volatile("ptesync": : :"memory");
+		___tlbie(vpn, psize, apsize, ssize);
+	}
+}
+
 static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long rb;
@@ -278,6 +287,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
 		asm volatile("ptesync": : :"memory");
 	} else {
 		__tlbie(vpn, psize, apsize, ssize);
+		fixup_tlbie(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -771,7 +781,7 @@ static void native_hpte_clear(void)
  */
 static void native_flush_hash_range(unsigned long number, int local)
 {
-	unsigned long vpn;
+	unsigned long vpn = 0;
 	unsigned long hash, index, hidx, shift, slot;
 	struct hash_pte *hptep;
 	unsigned long hpte_v;
@@ -843,6 +853,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 				__tlbie(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
+		/*
+		 * Just do one more with the last used values.
+		 */
+		fixup_tlbie(vpn, psize, psize, ssize);
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
 
 		if (lock_tlbie)
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 929d9ef7083f..3f980baade4c 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -173,6 +173,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	mm_iommu_init(mm);
 #endif
 	atomic_set(&mm->context.active_cpus, 0);
+	atomic_set(&mm->context.copros, 0);
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 28c980eb4422..adf469f312f2 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -481,6 +481,7 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
 	}
+	/* do we need fixup here ?*/
 	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 71d1b19ad1c0..a07f5372a4bf 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -119,6 +119,49 @@ static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbiel_va(unsigned long va, unsigned long pid,
+			       unsigned long ap, unsigned long ric)
+{
+	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 */
+
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 1, rb, rs, ric, prs, r);
+}
+
+static inline void __tlbie_va(unsigned long va, unsigned long pid,
+			      unsigned long ap, unsigned long ric)
+{
+	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 */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static inline void fixup_tlbie(void)
+{
+	unsigned long pid = 0;
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+	}
+}
+
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
@@ -151,24 +194,25 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
 	asm volatile("ptesync": : :"memory");
-	__tlbie_pid(pid, ric);
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-}
 
-static inline void __tlbiel_va(unsigned long va, unsigned long pid,
-			       unsigned long ap, unsigned long ric)
-{
-	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 */
-
-	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 1, rb, rs, ric, prs, r);
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid(pid, RIC_FLUSH_TLB);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid(pid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid(pid, RIC_FLUSH_ALL);
+	}
+	fixup_tlbie();
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
 static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
@@ -203,22 +247,6 @@ static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
 	asm volatile("ptesync": : :"memory");
 }
 
-static inline void __tlbie_va(unsigned long va, unsigned long pid,
-			     unsigned long ap, unsigned long ric)
-{
-	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 */
-
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
-
 static inline void __tlbie_va_range(unsigned long start, unsigned long end,
 				    unsigned long pid, unsigned long page_size,
 				    unsigned long psize)
@@ -237,6 +265,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 
 	asm volatile("ptesync": : :"memory");
 	__tlbie_va(va, pid, ap, ric);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -248,6 +277,7 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	if (also_pwc)
 		__tlbie_pid(pid, RIC_FLUSH_PWC);
 	__tlbie_va_range(start, end, pid, page_size, psize);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -311,6 +341,16 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
+static bool mm_needs_flush_escalation(struct mm_struct *mm)
+{
+	/*
+	 * P9 nest MMU has issues with the page walk cache
+	 * caching PTEs and not flushing them properly when
+	 * RIC = 0 for a PID/LPID invalidate
+	 */
+	return atomic_read(&mm->context.copros) != 0;
+}
+
 #ifdef CONFIG_SMP
 void radix__flush_tlb_mm(struct mm_struct *mm)
 {
@@ -321,9 +361,12 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 		return;
 
 	preempt_disable();
-	if (!mm_is_thread_local(mm))
-		_tlbie_pid(pid, RIC_FLUSH_TLB);
-	else
+	if (!mm_is_thread_local(mm)) {
+		if (mm_needs_flush_escalation(mm))
+			_tlbie_pid(pid, RIC_FLUSH_ALL);
+		else
+			_tlbie_pid(pid, RIC_FLUSH_TLB);
+	} else
 		_tlbiel_pid(pid, RIC_FLUSH_TLB);
 	preempt_enable();
 }
@@ -435,10 +478,14 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	}
 
 	if (full) {
-		if (local)
+		if (local) {
 			_tlbiel_pid(pid, RIC_FLUSH_TLB);
-		else
-			_tlbie_pid(pid, RIC_FLUSH_TLB);
+		} else {
+			if (mm_needs_flush_escalation(mm))
+				_tlbie_pid(pid, RIC_FLUSH_ALL);
+			else
+				_tlbie_pid(pid, RIC_FLUSH_TLB);
+		}
 	} else {
 		bool hflush = false;
 		unsigned long hstart, hend;
@@ -465,6 +512,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
 						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+			fixup_tlbie();
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
 		}
 	}
@@ -548,6 +596,9 @@ static inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
 	}
 
 	if (full) {
+		if (!local && mm_needs_flush_escalation(mm))
+			also_pwc = true;
+
 		if (local)
 			_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
 		else
@@ -603,46 +654,6 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-			      unsigned long page_size)
-{
-	unsigned long rb,rs,prs,r;
-	unsigned long ap;
-	unsigned long ric = RIC_FLUSH_TLB;
-
-	ap = mmu_get_ap(radix_get_mmu_psize(page_size));
-	rb = gpa & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = lpid & ((1UL << 32) - 1);
-	prs = 0; /* process scoped */
-	r = 1;   /* raidx format */
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
-}
-EXPORT_SYMBOL(radix__flush_tlb_lpid_va);
-
-void radix__flush_tlb_lpid(unsigned long lpid)
-{
-	unsigned long rb,rs,prs,r;
-	unsigned long ric = RIC_FLUSH_ALL;
-
-	rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
-	rs = lpid & ((1UL << 32) - 1);
-	prs = 0; /* partition scoped */
-	r = 1;   /* raidx format */
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
-}
-EXPORT_SYMBOL(radix__flush_tlb_lpid);
-
 void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
 				unsigned long start, unsigned long end)
 {
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8b8d2297d486..638411f22267 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -315,19 +315,6 @@ config X86_L1_CACHE_SHIFT
 	default "4" if MELAN || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
-config X86_PPRO_FENCE
-	bool "PentiumPro memory ordering errata workaround"
-	depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1
-	---help---
-	  Old PentiumPro multiprocessor systems had errata that could cause
-	  memory operations to violate the x86 ordering standard in rare cases.
-	  Enabling this option will attempt to work around some (but not all)
-	  occurrences of this problem, at the cost of much heavier spinlock and
-	  memory barrier operations.
-
-	  If unsure, say n here. Even distro kernels should think twice before
-	  enabling this: there are few systems, and an unlikely bug.
-
 config X86_F00F_BUG
 	def_bool y
 	depends on M586MMX || M586TSC || M586 || M486
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 498c1b812300..1c4d012550ec 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -223,6 +223,15 @@ KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
+#
+# The 64-bit kernel must be aligned to 2MB.  Pass -z max-page-size=0x200000 to
+# the linker to force 2MB page size regardless of the default page size used
+# by the linker.
+#
+ifdef CONFIG_X86_64
+LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
+endif
+
 # Speed up the build
 KBUILD_CFLAGS += -pipe
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 98761a1576ce..252fee320816 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -309,6 +309,10 @@ static void parse_elf(void *output)
 
 		switch (phdr->p_type) {
 		case PT_LOAD:
+#ifdef CONFIG_X86_64
+			if ((phdr->p_align % 0x200000) != 0)
+				error("Alignment of LOAD segment isn't multiple of 2MB");
+#endif
 #ifdef CONFIG_RELOCATABLE
 			dest = output;
 			dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR);
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 805f52703ee3..18ed349b4f83 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1138,7 +1138,7 @@ apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
 #endif /* CONFIG_HYPERV */
 
 idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3			do_int3			has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3			do_int3			has_error_code=0
 idtentry stack_segment		do_stack_segment	has_error_code=1
 
 #ifdef CONFIG_XEN
diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 7780bbfb06ef..9242b28418d5 100644
--- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
@@ -5,8 +5,6 @@
 #undef CONFIG_OPTIMIZE_INLINING
 #endif
 
-#undef CONFIG_X86_PPRO_FENCE
-
 #ifdef CONFIG_X86_64
 
 /*
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 8560ef68a9d6..317be365bce3 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -347,7 +347,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
 	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
 	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
 #if CONFIG_PGTABLE_LEVELS >= 5
-	p4d->p4d |= _PAGE_USER;
+	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
 #endif
 	pud = pud_offset(p4d, VSYSCALL_ADDR);
 	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 140d33288e78..88797c80b3e0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2118,7 +2118,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 			event->destroy(event);
 	}
 
-	if (READ_ONCE(x86_pmu.attr_rdpmc))
+	if (READ_ONCE(x86_pmu.attr_rdpmc) &&
+	    !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
 		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
 
 	return err;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 56457cb73448..1e41d7508d99 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2952,9 +2952,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
 	return intel_pebs_aliases_precdist(event);
 }
 
-static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 {
-	unsigned long flags = x86_pmu.free_running_flags;
+	unsigned long flags = x86_pmu.large_pebs_flags;
 
 	if (event->attr.use_clockid)
 		flags &= ~PERF_SAMPLE_TIME;
@@ -2976,8 +2976,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (!event->attr.freq) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
-			      ~intel_pmu_free_running_flags(event)))
-				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+			      ~intel_pmu_large_pebs_flags(event)))
+				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
@@ -3194,7 +3194,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
 			X86_CONFIG(.event=0xc0, .umask=0x01)) {
 		if (left < 128)
 			left = 128;
-		left &= ~0x3fu;
+		left &= ~0x3fULL;
 	}
 	return left;
 }
@@ -3460,7 +3460,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32-bit width,
@@ -3502,7 +3502,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32 bit width,
 	 * so we install an artificial 1<<31 period regardless of
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 18c25ab28557..d8015235ba76 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs++;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs--;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -1530,7 +1530,7 @@ void __init intel_ds_init(void)
 			x86_pmu.pebs_record_size =
 						sizeof(struct pebs_record_skl);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
-			x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
 		default:
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 22ec65bc033a..c98b943e58b4 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3),
 	EVENT_EXTRA_END
 };
 
@@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
 	NULL,
 };
 
+/*
+ * To determine the number of CHAs, it should read bits 27:0 in the CAPID6
+ * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083.
+ */
+#define SKX_CAPID6		0x9c
+#define SKX_CHA_BIT_MASK	GENMASK(27, 0)
+
 static int skx_count_chabox(void)
 {
-	struct pci_dev *chabox_dev = NULL;
-	int bus, count = 0;
+	struct pci_dev *dev = NULL;
+	u32 val = 0;
 
-	while (1) {
-		chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
-		if (!chabox_dev)
-			break;
-		if (count == 0)
-			bus = chabox_dev->bus->number;
-		if (bus != chabox_dev->bus->number)
-			break;
-		count++;
-	}
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev);
+	if (!dev)
+		goto out;
 
-	pci_dev_put(chabox_dev);
-	return count;
+	pci_read_config_dword(dev, SKX_CAPID6, &val);
+	val &= SKX_CHA_BIT_MASK;
+out:
+	pci_dev_put(dev);
+	return hweight32(val);
 }
 
 void skx_uncore_cpu_init(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78f91ec1056e..39cd0615f04f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -69,7 +69,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
 
 
 struct amd_nb {
@@ -88,7 +88,7 @@ struct amd_nb {
  * REGS_USER can be handled for events limited to ring 3.
  *
  */
-#define PEBS_FREERUNNING_FLAGS \
+#define LARGE_PEBS_FLAGS \
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
@@ -608,7 +608,7 @@ struct x86_pmu {
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	int 		max_pebs_events;
-	unsigned long	free_running_flags;
+	unsigned long	large_pebs_flags;
 
 	/*
 	 * Intel LBR
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index e1259f043ae9..042b5e892ed1 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -52,11 +52,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 #define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
 					   "lfence", X86_FEATURE_LFENCE_RDTSC)
 
-#ifdef CONFIG_X86_PPRO_FENCE
-#define dma_rmb()	rmb()
-#else
 #define dma_rmb()	barrier()
-#endif
 #define dma_wmb()	barrier()
 
 #ifdef CONFIG_X86_32
@@ -68,30 +64,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 #define __smp_wmb()	barrier()
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
-#if defined(CONFIG_X86_PPRO_FENCE)
-
-/*
- * For this option x86 doesn't have a strong TSO memory
- * model and we should fall back to full barriers.
- */
-
-#define __smp_store_release(p, v)					\
-do {									\
-	compiletime_assert_atomic_type(*p);				\
-	__smp_mb();							\
-	WRITE_ONCE(*p, v);						\
-} while (0)
-
-#define __smp_load_acquire(p)						\
-({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
-	compiletime_assert_atomic_type(*p);				\
-	__smp_mb();							\
-	___p1;								\
-})
-
-#else /* regular x86 TSO memory ordering */
-
 #define __smp_store_release(p, v)					\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
@@ -107,8 +79,6 @@ do {									\
 	___p1;								\
 })
 
-#endif
-
 /* Atomic operations are already serializing on x86 */
 #define __smp_mb__before_atomic()	barrier()
 #define __smp_mb__after_atomic()	barrier()
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 95e948627fd0..f6e5b9375d8c 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -232,21 +232,6 @@ extern void set_iounmap_nonlazy(void);
  */
 #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
 
-/*
- *	Cache management
- *
- *	This needed for two cases
- *	1. Out of order aware processors
- *	2. Accidentally out of order processors (PPro errata #51)
- */
-
-static inline void flush_write_buffers(void)
-{
-#if defined(CONFIG_X86_PPRO_FENCE)
-	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
-#endif
-}
-
 #endif /* __KERNEL__ */
 
 extern void native_io_delay(void);
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 56d99be3706a..50bee5fe1140 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -160,7 +160,6 @@ static const __initconst struct idt_data early_pf_idts[] = {
  */
 static const __initconst struct idt_data dbg_idts[] = {
 	INTG(X86_TRAP_DB,	debug),
-	INTG(X86_TRAP_BP,	int3),
 };
 #endif
 
@@ -183,7 +182,6 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
 static const __initconst struct idt_data ist_idts[] = {
 	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
 	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
-	SISTG(X86_TRAP_BP,	int3,		DEBUG_STACK),
 	ISTG(X86_TRAP_DF,	double_fault,	DOUBLEFAULT_STACK),
 #ifdef CONFIG_X86_MCE
 	ISTG(X86_TRAP_MC,	&machine_check,	MCE_STACK),
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index bc1a27280c4b..fae86e36e399 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -546,7 +546,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -635,7 +635,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
 	int cpu;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
 				GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 618285e475c6..ac7ea3a8242f 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -37,7 +37,6 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
 	WARN_ON(size == 0);
 	if (!check_addr("map_single", dev, bus, size))
 		return NOMMU_MAPPING_ERROR;
-	flush_write_buffers();
 	return bus;
 }
 
@@ -72,25 +71,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 			return 0;
 		s->dma_length = s->length;
 	}
-	flush_write_buffers();
 	return nents;
 }
 
-static void nommu_sync_single_for_device(struct device *dev,
-			dma_addr_t addr, size_t size,
-			enum dma_data_direction dir)
-{
-	flush_write_buffers();
-}
-
-
-static void nommu_sync_sg_for_device(struct device *dev,
-			struct scatterlist *sg, int nelems,
-			enum dma_data_direction dir)
-{
-	flush_write_buffers();
-}
-
 static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr == NOMMU_MAPPING_ERROR;
@@ -101,8 +84,6 @@ const struct dma_map_ops nommu_dma_ops = {
 	.free			= dma_generic_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
-	.sync_single_for_device = nommu_sync_single_for_device,
-	.sync_sg_for_device	= nommu_sync_sg_for_device,
 	.is_phys		= 1,
 	.mapping_error		= nommu_mapping_error,
 	.dma_supported		= x86_dma_supported,
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 3d9b2308e7fa..03f3d7695dac 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -577,7 +577,6 @@ do_general_protection(struct pt_regs *regs, long error_code)
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
-/* May run on IST stack. */
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -592,6 +591,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	if (poke_int3_handler(regs))
 		return;
 
+	/*
+	 * Use ist_enter despite the fact that we don't use an IST stack.
+	 * We can be called from a kprobe in non-CONTEXT_KERNEL kernel
+	 * mode or even during context tracking state changes.
+	 *
+	 * This means that we can't schedule.  That's okay.
+	 */
 	ist_enter(regs);
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -609,15 +615,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 			SIGTRAP) == NOTIFY_STOP)
 		goto exit;
 
-	/*
-	 * Let others (NMI) know that the debug stack is in use
-	 * as we may switch to the interrupt stack.
-	 */
-	debug_stack_usage_inc();
 	cond_local_irq_enable(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	cond_local_irq_disable(regs);
-	debug_stack_usage_dec();
+
 exit:
 	ist_exit(regs);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2d87603f9179..657c93409042 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10711,6 +10711,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control, vmcs12_exec_ctrl;
 
+	if (vmx->nested.dirty_vmcs12) {
+		prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
+		vmx->nested.dirty_vmcs12 = false;
+	}
+
 	/*
 	 * First, the fields that are shadowed.  This must be kept in sync
 	 * with vmx_shadow_fields.h.
@@ -10948,11 +10953,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
 	vmx_set_efer(vcpu, vcpu->arch.efer);
 
-	if (vmx->nested.dirty_vmcs12) {
-		prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
-		vmx->nested.dirty_vmcs12 = false;
-	}
-
 	/* Shadow page tables on either EPT or shadow page tables. */
 	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
 				entry_failure_code))
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c310a8284358..f9cfbc0d1f33 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -227,7 +227,7 @@ int __init efi_alloc_page_tables(void)
 	if (!pud) {
 		if (CONFIG_PGTABLE_LEVELS > 4)
 			free_page((unsigned long) pgd_page_vaddr(*pgd));
-		free_page((unsigned long)efi_pgd);
+		free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
 		return -ENOMEM;
 	}
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index b7d73400ea29..f31e5d903161 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -30,11 +30,7 @@
 
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_X86_PPRO_FENCE
-#define dma_rmb()	rmb()
-#else /* CONFIG_X86_PPRO_FENCE */
 #define dma_rmb()	barrier()
-#endif /* CONFIG_X86_PPRO_FENCE */
 #define dma_wmb()	barrier()
 
 #include <asm-generic/barrier.h>