Merge branch 'next/arm64' into next/dt

Merging in the few patches I had kept separate from main next/dt, since others
got merged here directly.

* next/arm64:
  arm64: defconfig: Enable PCI generic host bridge by default
  arm64: Juno: Add support for the PCIe host bridge on Juno R1
  Documentation: of: Document the bindings used by Juno R1 PCIe host bridge
  arm64: dts: mt8173: Add clocks for SCPSYS unit
  arm64: dts: mt8173: Add subsystem clock controller device nodes
  + Linux 4.3-rc5

43 files changed, 409 insertions, 84 deletions

diff --git a/arch/alpha/include/asm/word-at-a-time.h b/arch/alpha/include/asm/word-at-a-time.h
index 6b340d0f1521..902e6ab00a06 100644
--- a/arch/alpha/include/asm/word-at-a-time.h
+++ b/arch/alpha/include/asm/word-at-a-time.h
@@ -52,4 +52,6 @@ static inline unsigned long find_zero(unsigned long bits)
 #endif
 }
 
+#define zero_bytemask(mask) ((2ul << (find_zero(mask) * 8)) - 1)
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index 66da0d1d9d8a..0f5dcd418af8 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -197,6 +197,7 @@
 				regulator-name = "P1.8V_LDO_OUT10";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
 			};
 
 			ldo11_reg: LDO11 {
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index df9aee92ecf4..1b3d6c769a3c 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -1117,7 +1117,7 @@
 		interrupt-parent = <&combiner>;
 		interrupts = <3 0>;
 		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMD1M0>, <&clock CLK_FIMD1>;
+		clocks = <&clock CLK_SMMU_FIMD1M1>, <&clock CLK_FIMD1>;
 		power-domains = <&disp_pd>;
 		#iommu-cells = <0>;
 	};
diff --git a/arch/arm/boot/dts/imx53-qsrb.dts b/arch/arm/boot/dts/imx53-qsrb.dts
index 66e47de5e826..96d7eede412e 100644
--- a/arch/arm/boot/dts/imx53-qsrb.dts
+++ b/arch/arm/boot/dts/imx53-qsrb.dts
@@ -36,7 +36,7 @@
 		pinctrl-0 = <&pinctrl_pmic>;
 		reg = <0x08>;
 		interrupt-parent = <&gpio5>;
-		interrupts = <23 0x8>;
+		interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
 		regulators {
 			sw1_reg: sw1a {
 				regulator-name = "SW1";
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index c3e3ca9362fb..cd170376eaca 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -15,6 +15,7 @@
 #include <dt-bindings/clock/imx5-clock.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	aliases {
diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi
index 3373fd958e95..a50356243888 100644
--- a/arch/arm/boot/dts/imx6qdl-rex.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi
@@ -35,7 +35,6 @@
 			compatible = "regulator-fixed";
 			reg = <1>;
 			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbh1>;
 			regulator-name = "usbh1_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
@@ -47,7 +46,6 @@
 			compatible = "regulator-fixed";
 			reg = <2>;
 			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbotg>;
 			regulator-name = "usb_otg_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index ae5eb281d43a..e07ae5d45e19 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -1627,6 +1627,7 @@
 				"mix.0", "mix.1",
 				"dvc.0", "dvc.1",
 				"clk_a", "clk_b", "clk_c", "clk_i";
+		power-domains = <&cpg_clocks>;
 
 		status = "disabled";
 
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 3b8e26dde36d..328f48bd15e7 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -1677,6 +1677,7 @@
 				"mix.0", "mix.1",
 				"dvc.0", "dvc.1",
 				"clk_a", "clk_b", "clk_c", "clk_i";
+		power-domains = <&cpg_clocks>;
 
 		status = "disabled";
 
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index 9bdf54795f05..56978199c479 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -20,6 +20,7 @@
 #include <asm/cputype.h>
 #include <asm/cp15.h>
 #include <asm/mcpm.h>
+#include <asm/smp_plat.h>
 
 #include "regs-pmu.h"
 #include "common.h"
@@ -70,7 +71,31 @@ static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster)
 		cluster >= EXYNOS5420_NR_CLUSTERS)
 		return -EINVAL;
 
-	exynos_cpu_power_up(cpunr);
+	if (!exynos_cpu_power_state(cpunr)) {
+		exynos_cpu_power_up(cpunr);
+
+		/*
+		 * This assumes the cluster number of the big cores(Cortex A15)
+		 * is 0 and the Little cores(Cortex A7) is 1.
+		 * When the system was booted from the Little core,
+		 * they should be reset during power up cpu.
+		 */
+		if (cluster &&
+		    cluster == MPIDR_AFFINITY_LEVEL(cpu_logical_map(0), 1)) {
+			/*
+			 * Before we reset the Little cores, we should wait
+			 * the SPARE2 register is set to 1 because the init
+			 * codes of the iROM will set the register after
+			 * initialization.
+			 */
+			while (!pmu_raw_readl(S5P_PMU_SPARE2))
+				udelay(10);
+
+			pmu_raw_writel(EXYNOS5420_KFC_CORE_RESET(cpu),
+					EXYNOS_SWRESET);
+		}
+	}
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-exynos/regs-pmu.h b/arch/arm/mach-exynos/regs-pmu.h
index b7614333d296..fba9068ed260 100644
--- a/arch/arm/mach-exynos/regs-pmu.h
+++ b/arch/arm/mach-exynos/regs-pmu.h
@@ -513,6 +513,12 @@ static inline unsigned int exynos_pmu_cpunr(unsigned int mpidr)
 #define SPREAD_ENABLE						0xF
 #define SPREAD_USE_STANDWFI					0xF
 
+#define EXYNOS5420_KFC_CORE_RESET0				BIT(8)
+#define EXYNOS5420_KFC_ETM_RESET0				BIT(20)
+
+#define EXYNOS5420_KFC_CORE_RESET(_nr)				\
+	((EXYNOS5420_KFC_CORE_RESET0 | EXYNOS5420_KFC_ETM_RESET0) << (_nr))
+
 #define EXYNOS5420_BB_CON1					0x0784
 #define EXYNOS5420_BB_SEL_EN					BIT(31)
 #define EXYNOS5420_BB_PMOS_EN					BIT(7)
diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts
index 5eef4aa0c532..62a5a3cf4414 100644
--- a/arch/arm64/boot/dts/arm/juno-r1.dts
+++ b/arch/arm64/boot/dts/arm/juno-r1.dts
@@ -141,6 +141,26 @@
 
 	#include "juno-base.dtsi"
 
+	pcie-controller@40000000 {
+		compatible = "arm,juno-r1-pcie", "plda,xpressrich3-axi", "pci-host-ecam-generic";
+		device_type = "pci";
+		reg = <0 0x40000000 0 0x10000000>;	/* ECAM config space */
+		bus-range = <0 255>;
+		linux,pci-domain = <0>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		dma-coherent;
+		ranges = <0x01000000 0x00 0x5f800000 0x00 0x5f800000 0x0 0x00800000>,
+			 <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>,
+			 <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>;
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &gic 0 0 0 136 4>,
+				<0 0 0 2 &gic 0 0 0 137 4>,
+				<0 0 0 3 &gic 0 0 0 138 4>,
+				<0 0 0 4 &gic 0 0 0 139 4>;
+		msi-parent = <&v2m_0>;
+	};
 };
 
 &memtimer {
diff --git a/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
index 2eef4a279131..f77ddaf21d04 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
@@ -586,3 +586,106 @@
 		samsung,pin-drv = <2>;
 	};
 };
+
+&pinctrl_bus1 {
+	gpf0: gpf0 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf1: gpf1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf2: gpf2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf3: gpf3 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf4: gpf4 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpf5: gpf5 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg1: gpg1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpg2: gpg2 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gph1: gph1 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	gpv6: gpv6 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	spi5_bus: spi5-bus {
+		samsung,pins = "gpf2-0", "gpf2-1", "gpf2-2", "gpf2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	ufs_refclk_out: ufs-refclk-out {
+		samsung,pins = "gpg2-4";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <2>;
+	};
+
+	ufs_rst_n: ufs-rst-n {
+		samsung,pins = "gph1-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi
index d7a37c3a6b52..f9c5a549c2c0 100644
--- a/arch/arm64/boot/dts/exynos/exynos7.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi
@@ -26,6 +26,7 @@
 		pinctrl5 = &pinctrl_ese;
 		pinctrl6 = &pinctrl_fsys0;
 		pinctrl7 = &pinctrl_fsys1;
+		pinctrl8 = &pinctrl_bus1;
 	};
 
 	cpus {
@@ -278,6 +279,12 @@
 			interrupts = <0 203 0>;
 		};
 
+		pinctrl_bus1: pinctrl@14870000 {
+			compatible = "samsung,exynos7-pinctrl";
+			reg = <0x14870000 0x1000>;
+			interrupts = <0 384 0>;
+		};
+
 		hsi2c_0: hsi2c@13640000 {
 			compatible = "samsung,exynos7-hsi2c";
 			reg = <0x13640000 0x1000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 4be66cadbc7c..811cb760ba49 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -387,6 +387,24 @@
 	};
 };
 
+&pio {
+	spi_pins_a: spi0 {
+		pins_spi {
+			pinmux = <MT8173_PIN_69_SPI_CK__FUNC_SPI_CK_0_>,
+				<MT8173_PIN_70_SPI_MI__FUNC_SPI_MI_0_>,
+				<MT8173_PIN_71_SPI_MO__FUNC_SPI_MO_0_>,
+				<MT8173_PIN_72_SPI_CS__FUNC_SPI_CS_0_>;
+		};
+	};
+};
+
+&spi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi_pins_a>;
+	mediatek,pad-select = <0>;
+	status = "okay";
+};
+
 &uart0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 06a15644be38..4dd5f93d0303 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -116,6 +116,13 @@
 		clock-output-names = "clk32k";
 	};
 
+	cpum_ck: oscillator@2 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+		clock-output-names = "cpum_ck";
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupt-parent = <&gic>;
@@ -227,8 +234,10 @@
 			#power-domain-cells = <1>;
 			reg = <0 0x10006000 0 0x1000>;
 			clocks = <&clk26m>,
-				 <&topckgen CLK_TOP_MM_SEL>;
-			clock-names = "mfg", "mm";
+				 <&topckgen CLK_TOP_MM_SEL>,
+				 <&topckgen CLK_TOP_VENC_SEL>,
+				 <&topckgen CLK_TOP_VENC_LT_SEL>;
+			clock-names = "mfg", "mm", "venc", "venc_lt";
 			infracfg = <&infracfg>;
 		};
 
@@ -365,7 +374,20 @@
 			status = "disabled";
 		};
 
-		i2c3: i2c3@11010000 {
+		spi: spi@1100a000 {
+			compatible = "mediatek,mt8173-spi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x1100a000 0 0x1000>;
+			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&topckgen CLK_TOP_SYSPLL3_D2>,
+				 <&topckgen CLK_TOP_SPI_SEL>,
+				 <&pericfg CLK_PERI_SPI0>;
+			clock-names = "parent-clk", "sel-clk", "spi-clk";
+			status = "disabled";
+		};
+
+		i2c3: i2c@11010000 {
 			compatible = "mediatek,mt8173-i2c";
 			reg = <0 0x11010000 0 0x70>,
 			      <0 0x11000280 0 0x80>;
@@ -381,7 +403,7 @@
 			status = "disabled";
 		};
 
-		i2c4: i2c4@11011000 {
+		i2c4: i2c@11011000 {
 			compatible = "mediatek,mt8173-i2c";
 			reg = <0 0x11011000 0 0x70>,
 			      <0 0x11000300 0 0x80>;
@@ -397,7 +419,7 @@
 			status = "disabled";
 		};
 
-		i2c6: i2c6@11013000 {
+		i2c6: i2c@11013000 {
 			compatible = "mediatek,mt8173-i2c";
 			reg = <0 0x11013000 0 0x70>,
 			      <0 0x11000080 0 0x80>;
@@ -487,6 +509,36 @@
 			clock-names = "source", "hclk";
 			status = "disabled";
 		};
+
+		mmsys: clock-controller@14000000 {
+			compatible = "mediatek,mt8173-mmsys", "syscon";
+			reg = <0 0x14000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		imgsys: clock-controller@15000000 {
+			compatible = "mediatek,mt8173-imgsys", "syscon";
+			reg = <0 0x15000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vdecsys: clock-controller@16000000 {
+			compatible = "mediatek,mt8173-vdecsys", "syscon";
+			reg = <0 0x16000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vencsys: clock-controller@18000000 {
+			compatible = "mediatek,mt8173-vencsys", "syscon";
+			reg = <0 0x18000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		vencltsys: clock-controller@19000000 {
+			compatible = "mediatek,mt8173-vencltsys", "syscon";
+			reg = <0 0x19000000 0 0x1000>;
+			#clock-cells = <1>;
+		};
 	};
 };
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 8f07e923dd5f..feab9af9bf78 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -50,6 +50,7 @@ CONFIG_ARCH_XGENE=y
 CONFIG_ARCH_ZYNQMP=y
 CONFIG_PCI=y
 CONFIG_PCI_MSI=y
+CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index cebf78661a55..253021ef2769 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -201,7 +201,7 @@ void unregister_step_hook(struct step_hook *hook)
 }
 
 /*
- * Call registered single step handers
+ * Call registered single step handlers
  * There is no Syndrome info to check for determining the handler.
  * So we call all the registered handlers, until the right handler is
  * found which returns zero.
@@ -271,20 +271,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-static DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_SPINLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_add(&hook->node, &break_hook);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_add_rcu(&hook->node, &break_hook);
+	spin_unlock(&break_hook_lock);
 }
 
 void unregister_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&break_hook_lock);
+	synchronize_rcu();
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
@@ -292,11 +293,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 	struct break_hook *hook;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
-	read_lock(&break_hook_lock);
-	list_for_each_entry(hook, &break_hook, node)
+	rcu_read_lock();
+	list_for_each_entry_rcu(hook, &break_hook, node)
 		if ((esr & hook->esr_mask) == hook->esr_val)
 			fn = hook->fn;
-	read_unlock(&break_hook_lock);
+	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index f341866aa810..c08b9ad6f429 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -85,7 +85,7 @@ bool aarch64_insn_is_branch_imm(u32 insn)
 		aarch64_insn_is_bcond(insn));
 }
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
@@ -131,13 +131,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn)
 	unsigned long flags = 0;
 	int ret;
 
-	spin_lock_irqsave(&patch_lock, flags);
+	raw_spin_lock_irqsave(&patch_lock, flags);
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
 	ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
 
 	patch_unmap(FIX_TEXT_POKE0);
-	spin_unlock_irqrestore(&patch_lock, flags);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 6bab21f84a9f..232247945b1c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -364,6 +364,8 @@ static void __init relocate_initrd(void)
 		to_free = ram_end - orig_start;
 
 	size = orig_end - orig_start;
+	if (!size)
+		return;
 
 	/* initrd needs to be relocated completely inside linear mapping */
 	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index aba9ead1384c..9fadf6d7039b 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -287,6 +287,7 @@ retry:
 			 * starvation.
 			 */
 			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			mm_flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 70e6ae1e7006..373cb23301e3 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -73,4 +73,5 @@ generic-y += uaccess.h
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 9e777cd42b67..d10fd80dbb7e 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -256,6 +256,7 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
  */
 #define ioremap_nocache(offset, size)					\
 	__ioremap_mode((offset), (size), _CACHE_UNCACHED)
+#define ioremap_uc ioremap_nocache
 
 /*
  * ioremap_cachable -	map bus memory into CPU space
diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h
index c4ddc4f0d2dc..23cd9b118c9e 100644
--- a/arch/mips/include/uapi/asm/swab.h
+++ b/arch/mips/include/uapi/asm/swab.h
@@ -13,16 +13,15 @@
 
 #define __SWAB_64_THRU_32__
 
-#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||		\
-    defined(_MIPS_ARCH_LOONGSON3A)
+#if !defined(__mips16) &&					\
+	((defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||	\
+	 defined(_MIPS_ARCH_LOONGSON3A))
 
-static inline __attribute__((nomips16)) __attribute_const__
-		__u16 __arch_swab16(__u16 x)
+static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips32r2		\n"
-	"	.set	nomips16		\n"
 	"	wsbh	%0, %1			\n"
 	"	.set	pop			\n"
 	: "=r" (x)
@@ -32,13 +31,11 @@ static inline __attribute__((nomips16)) __attribute_const__
 }
 #define __arch_swab16 __arch_swab16
 
-static inline __attribute__((nomips16)) __attribute_const__
-		__u32 __arch_swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips32r2		\n"
-	"	.set	nomips16		\n"
 	"	wsbh	%0, %1			\n"
 	"	rotr	%0, %0, 16		\n"
 	"	.set	pop			\n"
@@ -54,13 +51,11 @@ static inline __attribute__((nomips16)) __attribute_const__
  * 64-bit kernel on r2 CPUs.
  */
 #ifdef __mips64
-static inline __attribute__((nomips16)) __attribute_const__
-		__u64 __arch_swab64(__u64 x)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips64r2		\n"
-	"	.set	nomips16		\n"
 	"	dsbh	%0, %1			\n"
 	"	dshd	%0, %0			\n"
 	"	.set	pop			\n"
@@ -71,5 +66,5 @@ static inline __attribute__((nomips16)) __attribute_const__
 }
 #define __arch_swab64 __arch_swab64
 #endif /* __mips64 */
-#endif /* MIPS R2 or newer or Loongson 3A */
+#endif /* (not __mips16) and (MIPS R2 or newer or Loongson 3A) */
 #endif /* _ASM_SWAB_H */
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index ac1662956e0c..ab9f4e0ed4cf 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -7,4 +7,3 @@ generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += vtime.h
-generic-y += word-at-a-time.h
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index 5b3a903adae6..e4396a7d0f7c 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -40,6 +40,11 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 	return (val + c->high_bits) & ~rhs;
 }
 
+static inline unsigned long zero_bytemask(unsigned long mask)
+{
+	return ~1ul << __fls(mask);
+}
+
 #else
 
 #ifdef CONFIG_64BIT
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index d4788111c161..fac6ac9790fa 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -10,7 +10,7 @@ targets += misc.o piggy.o sizes.h head.o
 
 KBUILD_CFLAGS := -m64 -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
+KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 0c98f1508542..ed7da281df66 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -381,7 +381,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 82083e1fbdc4..9858b14cde1e 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -377,7 +377,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index c05c9e0821e3..7f14f80717d4 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -377,7 +377,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h
index 2a0efc63b9e5..dc19ee0c92aa 100644
--- a/arch/s390/include/asm/numa.h
+++ b/arch/s390/include/asm/numa.h
@@ -19,7 +19,7 @@ int numa_pfn_to_nid(unsigned long pfn);
 int __node_distance(int a, int b);
 void numa_update_cpu_topology(void);
 
-extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+extern cpumask_t node_to_cpumask_map[MAX_NUMNODES];
 extern int numa_debug_enabled;
 
 #else
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 27ebde643933..94fc55fc72ce 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -68,7 +68,7 @@ static inline int cpu_to_node(int cpu)
 #define cpumask_of_node cpumask_of_node
 static inline const struct cpumask *cpumask_of_node(int node)
 {
-	return node_to_cpumask_map[node];
+	return &node_to_cpumask_map[node];
 }
 
 /*
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 48c9af7a7683..3aeeb1b562c0 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -176,6 +176,7 @@ int main(void)
 	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));
 	DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area));
 	DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr));
+	DEFINE(__LC_PERCPU_OFFSET, offsetof(struct _lowcore, percpu_offset));
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 09b039d7983d..582fe44ab07c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -733,6 +733,14 @@ ENTRY(psw_idle)
 	stg	%r3,__SF_EMPTY(%r15)
 	larl	%r1,.Lpsw_idle_lpsw+4
 	stg	%r1,__SF_EMPTY+8(%r15)
+#ifdef CONFIG_SMP
+	larl	%r1,smp_cpu_mtid
+	llgf	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	.Lpsw_idle_stcctm
+	.insn	rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15)
+.Lpsw_idle_stcctm:
+#endif
 	STCK	__CLOCK_IDLE_ENTER(%r2)
 	stpt	__TIMER_IDLE_ENTER(%r2)
 .Lpsw_idle_lpsw:
@@ -1159,7 +1167,27 @@ cleanup_critical:
 	jhe	1f
 	mvc	__CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2)
 	mvc	__TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2)
-1:	# account system time going idle
+1:	# calculate idle cycles
+#ifdef CONFIG_SMP
+	clg	%r9,BASED(.Lcleanup_idle_insn)
+	jl	3f
+	larl	%r1,smp_cpu_mtid
+	llgf	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	3f
+	.insn	rsy,0xeb0000000017,%r1,5,__SF_EMPTY+80(%r15)
+	larl	%r3,mt_cycles
+	ag	%r3,__LC_PERCPU_OFFSET
+	la	%r4,__SF_EMPTY+16(%r15)
+2:	lg	%r0,0(%r3)
+	slg	%r0,0(%r4)
+	alg	%r0,64(%r4)
+	stg	%r0,0(%r3)
+	la	%r3,8(%r3)
+	la	%r4,8(%r4)
+	brct	%r1,2b
+#endif
+3:	# account system time going idle
 	lg	%r9,__LC_STEAL_TIMER
 	alg	%r9,__CLOCK_IDLE_ENTER(%r2)
 	slg	%r9,__LC_LAST_UPDATE_CLOCK
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c8653435c70d..dafc44f519c3 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -25,7 +25,7 @@ static DEFINE_SPINLOCK(virt_timer_lock);
 static atomic64_t virt_timer_current;
 static atomic64_t virt_timer_elapsed;
 
-static DEFINE_PER_CPU(u64, mt_cycles[32]);
+DEFINE_PER_CPU(u64, mt_cycles[8]);
 static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 };
 static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 };
 static DEFINE_PER_CPU(u64, mt_scaling_jiffies);
@@ -60,6 +60,34 @@ static inline int virt_timer_forward(u64 elapsed)
 	return elapsed >= atomic64_read(&virt_timer_current);
 }
 
+static void update_mt_scaling(void)
+{
+	u64 cycles_new[8], *cycles_old;
+	u64 delta, fac, mult, div;
+	int i;
+
+	stcctm5(smp_cpu_mtid + 1, cycles_new);
+	cycles_old = this_cpu_ptr(mt_cycles);
+	fac = 1;
+	mult = div = 0;
+	for (i = 0; i <= smp_cpu_mtid; i++) {
+		delta = cycles_new[i] - cycles_old[i];
+		div += delta;
+		mult *= i + 1;
+		mult += delta * fac;
+		fac *= i + 1;
+	}
+	div *= fac;
+	if (div > 0) {
+		/* Update scaling factor */
+		__this_cpu_write(mt_scaling_mult, mult);
+		__this_cpu_write(mt_scaling_div, div);
+		memcpy(cycles_old, cycles_new,
+		       sizeof(u64) * (smp_cpu_mtid + 1));
+	}
+	__this_cpu_write(mt_scaling_jiffies, jiffies_64);
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
@@ -69,7 +97,6 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, clock, user, system, steal;
 	u64 user_scaled, system_scaled;
-	int i;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -85,34 +112,10 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
 	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
 
-	/* Do MT utilization calculation */
+	/* Update MT utilization calculation */
 	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) {
-		u64 cycles_new[32], *cycles_old;
-		u64 delta, fac, mult, div;
-
-		cycles_old = this_cpu_ptr(mt_cycles);
-		if (stcctm5(smp_cpu_mtid + 1, cycles_new) < 2) {
-			fac = 1;
-			mult = div = 0;
-			for (i = 0; i <= smp_cpu_mtid; i++) {
-				delta = cycles_new[i] - cycles_old[i];
-				div += delta;
-				mult *= i + 1;
-				mult += delta * fac;
-				fac *= i + 1;
-			}
-			div *= fac;
-			if (div > 0) {
-				/* Update scaling factor */
-				__this_cpu_write(mt_scaling_mult, mult);
-				__this_cpu_write(mt_scaling_div, div);
-				memcpy(cycles_old, cycles_new,
-				       sizeof(u64) * (smp_cpu_mtid + 1));
-			}
-		}
-		__this_cpu_write(mt_scaling_jiffies, jiffies_64);
-	}
+	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+		update_mt_scaling();
 
 	user = S390_lowcore.user_timer - ti->user_timer;
 	S390_lowcore.steal_timer -= user;
@@ -181,6 +184,11 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	S390_lowcore.last_update_timer = get_vtimer();
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
 
+	/* Update MT utilization calculation */
+	if (smp_cpu_mtid &&
+	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+		update_mt_scaling();
+
 	system = S390_lowcore.system_timer - ti->system_timer;
 	S390_lowcore.steal_timer -= system;
 	ti->system_timer = S390_lowcore.system_timer;
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index 7de4e2f780d7..30b2698a28e2 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -368,7 +368,7 @@ static void topology_add_core(struct toptree *core)
 		cpumask_copy(&top->thread_mask, &core->mask);
 		cpumask_copy(&top->core_mask, &core_mc(core)->mask);
 		cpumask_copy(&top->book_mask, &core_book(core)->mask);
-		cpumask_set_cpu(cpu, node_to_cpumask_map[core_node(core)->id]);
+		cpumask_set_cpu(cpu, &node_to_cpumask_map[core_node(core)->id]);
 		top->node_id = core_node(core)->id;
 	}
 }
@@ -383,7 +383,7 @@ static void toptree_to_topology(struct toptree *numa)
 
 	/* Clear all node masks */
 	for (i = 0; i < MAX_NUMNODES; i++)
-		cpumask_clear(node_to_cpumask_map[i]);
+		cpumask_clear(&node_to_cpumask_map[i]);
 
 	/* Rebuild all masks */
 	toptree_for_each(core, numa, CORE)
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 09b1d2355bd9..43f32ce60aa3 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -23,7 +23,7 @@
 pg_data_t *node_data[MAX_NUMNODES];
 EXPORT_SYMBOL(node_data);
 
-cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+cpumask_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
 const struct numa_mode numa_mode_plain = {
@@ -144,7 +144,7 @@ void __init numa_setup(void)
 static int __init numa_init_early(void)
 {
 	/* Attach all possible CPUs to node 0 for now. */
-	cpumask_copy(node_to_cpumask_map[0], cpu_possible_mask);
+	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
 	return 0;
 }
 early_initcall(numa_init_early);
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 0b6cacaad933..ba35c41c71ff 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -40,5 +40,4 @@ generic-y += termbits.h
 generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += types.h
-generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/tile/include/asm/word-at-a-time.h b/arch/tile/include/asm/word-at-a-time.h
index 9e5ce0d7b292..b66a693c2c34 100644
--- a/arch/tile/include/asm/word-at-a-time.h
+++ b/arch/tile/include/asm/word-at-a-time.h
@@ -6,7 +6,7 @@
 struct word_at_a_time { /* unused */ };
 #define WORD_AT_A_TIME_CONSTANTS {}
 
-/* Generate 0x01 byte values for non-zero bytes using a SIMD instruction. */
+/* Generate 0x01 byte values for zero bytes using a SIMD instruction. */
 static inline unsigned long has_zero(unsigned long val, unsigned long *data,
 				     const struct word_at_a_time *c)
 {
@@ -33,4 +33,10 @@ static inline long find_zero(unsigned long mask)
 #endif
 }
 
+#ifdef __BIG_ENDIAN
+#define zero_bytemask(mask) (~1ul << (63 - __builtin_clzl(mask)))
+#else
+#define zero_bytemask(mask) ((2ul << __builtin_ctzl(mask)) - 1)
+#endif
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 328c8352480c..96d058a87100 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1308,6 +1308,7 @@ config HIGHMEM
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && !HIGHMEM4G
+	select SWIOTLB
 	---help---
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 83aea8055119..4c20dd333412 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc)
 	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
 }
 
-static inline int
+static inline long
 HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 {
-	return _hypercall2(int, memory_op, cmd, arg);
+	return _hypercall2(long, memory_op, cmd, arg);
 }
 
 static inline int
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 30d12afe52ed..993b7a71386d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,10 @@
 #include <linux/memblock.h>
 #include <linux/edd.h>
 
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
@@ -1077,6 +1081,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		/* Fast syscall setup is all done in hypercalls, so
 		   these are all ignored.  Stub them out here to stop
 		   Xen console noise. */
+		break;
 
 	default:
 		if (!pmu_msr_write(msr, low, high, &ret))
@@ -1807,6 +1812,21 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -1826,6 +1846,10 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
 }
 #endif
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index bfc08b13044b..660b3cfef234 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -112,6 +112,15 @@ static unsigned long *p2m_identity;
 static pte_t *p2m_missing_pte;
 static pte_t *p2m_identity_pte;
 
+/*
+ * Hint at last populated PFN.
+ *
+ * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack
+ * can avoid scanning the whole P2M (which may be sized to account for
+ * hotplugged memory).
+ */
+static unsigned long xen_p2m_last_pfn;
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -270,7 +279,7 @@ void xen_setup_mfn_list_list(void)
 	else
 		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
 			virt_to_mfn(p2m_top_mfn);
-	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
+	HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
 	HYPERVISOR_shared_info->arch.p2m_generation = 0;
 	HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr;
 	HYPERVISOR_shared_info->arch.p2m_cr3 =
@@ -406,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void)
 	static struct vm_struct vm;
 	unsigned long p2m_limit;
 
+	xen_p2m_last_pfn = xen_max_p2m_pfn;
+
 	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
 	vm.flags = VM_ALLOC;
 	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
@@ -608,6 +619,12 @@ static bool alloc_p2m(unsigned long pfn)
 			free_p2m_page(p2m);
 	}
 
+	/* Expanded the p2m? */
+	if (pfn > xen_p2m_last_pfn) {
+		xen_p2m_last_pfn = pfn;
+		HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f5ef6746d47a..1c30e4ab1022 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -548,7 +548,7 @@ static unsigned long __init xen_get_max_pages(void)
 {
 	unsigned long max_pages, limit;
 	domid_t domid = DOMID_SELF;
-	int ret;
+	long ret;
 
 	limit = xen_get_pages_limit();
 	max_pages = limit;
@@ -798,7 +798,7 @@ char * __init xen_memory_setup(void)
 		xen_ignore_unusable();
 
 	/* Make sure the Xen-supplied memory map is well-ordered. */
-	sanitize_e820_map(xen_e820_map, xen_e820_map_entries,
+	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
 			  &xen_e820_map_entries);
 
 	max_pages = xen_get_max_pages();