Merge tag 'kvm-for-3.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into kvm-next

145 files changed, 1580 insertions, 429 deletions

diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index b9d6a8b485e0..6d1e43d46187 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -38,6 +38,7 @@ dtb-$(CONFIG_ARCH_AT91) += at91sam9g35ek.dtb
 dtb-$(CONFIG_ARCH_AT91) += at91sam9x25ek.dtb
 dtb-$(CONFIG_ARCH_AT91) += at91sam9x35ek.dtb
 # sama5d3
+dtb-$(CONFIG_ARCH_AT91)	+= at91-sama5d3_xplained.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d31ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d33ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d34ek.dtb
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
new file mode 100644
index 000000000000..ce1375595e5f
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -0,0 +1,229 @@
+/*
+ * at91-sama5d3_xplained.dts - Device Tree file for the SAMA5D3 Xplained board
+ *
+ *  Copyright (C) 2014 Atmel,
+ *		  2014 Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+/dts-v1/;
+#include "sama5d36.dtsi"
+
+/ {
+	model = "SAMA5D3 Xplained";
+	compatible = "atmel,sama5d3-xplained", "atmel,sama5d3", "atmel,sama5";
+
+	chosen {
+		bootargs = "console=ttyS0,115200";
+	};
+
+	memory {
+		reg = <0x20000000 0x10000000>;
+	};
+
+	ahb {
+		apb {
+			mmc0: mmc@f0000000 {
+				pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_dat4_7 &pinctrl_mmc0_cd>;
+				status = "okay";
+				slot@0 {
+					reg = <0>;
+					bus-width = <8>;
+					cd-gpios = <&pioE 0 GPIO_ACTIVE_LOW>;
+				};
+			};
+
+			spi0: spi@f0004000 {
+				cs-gpios = <&pioD 13 0>;
+				status = "okay";
+			};
+
+			can0: can@f000c000 {
+				status = "okay";
+			};
+
+			i2c0: i2c@f0014000 {
+				status = "okay";
+			};
+
+			i2c1: i2c@f0018000 {
+				status = "okay";
+			};
+
+			macb0: ethernet@f0028000 {
+				phy-mode = "rgmii";
+				status = "okay";
+			};
+
+			usart0: serial@f001c000 {
+				status = "okay";
+			};
+
+			usart1: serial@f0020000 {
+				pinctrl-0 = <&pinctrl_usart1 &pinctrl_usart1_rts_cts>;
+				status = "okay";
+			};
+
+			uart0: serial@f0024000 {
+				status = "okay";
+			};
+
+			mmc1: mmc@f8000000 {
+				pinctrl-0 = <&pinctrl_mmc1_clk_cmd_dat0 &pinctrl_mmc1_dat1_3 &pinctrl_mmc1_cd>;
+				status = "okay";
+				slot@0 {
+					reg = <0>;
+					bus-width = <4>;
+					cd-gpios = <&pioE 1 GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			spi1: spi@f8008000 {
+				cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>;
+				status = "okay";
+			};
+
+			adc0: adc@f8018000 {
+				pinctrl-0 = <
+					&pinctrl_adc0_adtrg
+					&pinctrl_adc0_ad0
+					&pinctrl_adc0_ad1
+					&pinctrl_adc0_ad2
+					&pinctrl_adc0_ad3
+					&pinctrl_adc0_ad4
+					&pinctrl_adc0_ad5
+					&pinctrl_adc0_ad6
+					&pinctrl_adc0_ad7
+					&pinctrl_adc0_ad8
+					&pinctrl_adc0_ad9
+					>;
+				status = "okay";
+			};
+
+			i2c2: i2c@f801c000 {
+				dmas = <0>, <0>;	/* Do not use DMA for i2c2 */
+				status = "okay";
+			};
+
+			macb1: ethernet@f802c000 {
+				phy-mode = "rmii";
+				status = "okay";
+			};
+
+			dbgu: serial@ffffee00 {
+				status = "okay";
+			};
+
+			pinctrl@fffff200 {
+				board {
+					pinctrl_mmc0_cd: mmc0_cd {
+						atmel,pins =
+							<AT91_PIOE 0 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_mmc1_cd: mmc1_cd {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_usba_vbus: usba_vbus {
+						atmel,pins =
+							<AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>;	/* PE9, conflicts with A9 */
+					};
+				};
+			};
+
+			pmc: pmc@fffffc00 {
+				main: mainck {
+					clock-frequency = <12000000>;
+				};
+			};
+		};
+
+		nand0: nand@60000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "hw";
+			atmel,has-pmecc;
+			atmel,pmecc-cap = <4>;
+			atmel,pmecc-sector-size = <512>;
+			nand-on-flash-bbt;
+			status = "okay";
+
+			at91bootstrap@0 {
+				label = "at91bootstrap";
+				reg = <0x0 0x40000>;
+			};
+
+			bootloader@40000 {
+				label = "bootloader";
+				reg = <0x40000 0x80000>;
+			};
+
+			bootloaderenv@c0000 {
+				label = "bootloader env";
+				reg = <0xc0000 0xc0000>;
+			};
+
+			dtb@180000 {
+				label = "device tree";
+				reg = <0x180000 0x80000>;
+			};
+
+			kernel@200000 {
+				label = "kernel";
+				reg = <0x200000 0x600000>;
+			};
+
+			rootfs@800000 {
+				label = "rootfs";
+				reg = <0x800000 0x0f800000>;
+			};
+		};
+
+		usb0: gadget@00500000 {
+			atmel,vbus-gpio = <&pioE 9 GPIO_ACTIVE_HIGH>;	/* PE9, conflicts with A9 */
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usba_vbus>;
+			status = "okay";
+		};
+
+		usb1: ohci@00600000 {
+			num-ports = <3>;
+			atmel,vbus-gpio = <0
+					   &pioE 3 GPIO_ACTIVE_LOW
+					   &pioE 4 GPIO_ACTIVE_LOW
+					  >;
+			status = "okay";
+		};
+
+		usb2: ehci@00700000 {
+			status = "okay";
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		bp3 {
+			label = "PB_USER";
+			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
+			linux,code = <0x104>;
+			gpio-key,wakeup;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		d2 {
+			label = "d2";
+			gpios = <&pioE 23 GPIO_ACTIVE_LOW>;	/* PE23, conflicts with A23, CTS2 */
+			linux,default-trigger = "heartbeat";
+		};
+
+		d3 {
+			label = "d3";
+			gpios = <&pioE 24 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 0042f73068b0..fece8665fb63 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -523,7 +523,7 @@
 			};
 
 			i2c0: i2c@fff88000 {
-				compatible = "atmel,at91sam9263-i2c";
+				compatible = "atmel,at91sam9260-i2c";
 				reg = <0xfff88000 0x100>;
 				interrupts = <13 IRQ_TYPE_LEVEL_HIGH 6>;
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index e9487f6f0166..924a6a6ffd0f 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -124,6 +124,10 @@
 			nand-on-flash-bbt;
 			status = "okay";
 		};
+
+		usb0: ohci@00500000 {
+			status = "okay";
+		};
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 52447c17537a..3d5faf85f51b 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1228,7 +1228,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>,
 				 <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 0c1e8d871ed1..6cb9b68e2188 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -188,7 +188,6 @@
 		msp2: msp@80117000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&msp2_default_mode>;
-			status = "okay";
 		};
 
 		msp3: msp@80125000 {
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 040bb0eba152..10666ca8aee1 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -315,7 +315,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <55>;
 			clocks = <&ahb_gates 17>;
@@ -323,7 +323,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index ea16054857a4..64961595e8d6 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -278,7 +278,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <55>;
 			clocks = <&ahb_gates 17>;
@@ -286,7 +286,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 119f066f0d98..9ff09484847b 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -340,7 +340,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <0 55 4>;
 			clocks = <&ahb_gates 17>;
@@ -348,7 +348,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 845bc745706b..ee6982976d66 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -29,6 +29,7 @@ CONFIG_ARCH_OMAP3=y
 CONFIG_ARCH_OMAP4=y
 CONFIG_SOC_OMAP5=y
 CONFIG_SOC_AM33XX=y
+CONFIG_SOC_DRA7XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SOCFPGA=y
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 1d3153c7eb41..816db0bf2dd8 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -55,6 +55,7 @@
  * The bits we set in HCR:
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until MMU and caches are on)
  * TSW:		Trap cache operations by set/way
  * TWI:		Trap WFI
  * TWE:		Trap WFE
@@ -68,8 +69,7 @@
  */
 #define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
 			HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
-			HCR_TWE | HCR_SWIO | HCR_TIDCP)
-#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+			HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP)
 
 /* System Control Register (SCTLR) bits */
 #define SCTLR_TE	(1 << 30)
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 661da11f76f4..53b3c4a50d5c 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -48,7 +48,9 @@
 #define c13_TID_URO	26	/* Thread ID, User R/O */
 #define c13_TID_PRIV	27	/* Thread ID, Privileged */
 #define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
-#define NR_CP15_REGS	29	/* Number of regs (incl. invalid) */
+#define c10_AMAIR0	29	/* Auxilary Memory Attribute Indirection Reg0 */
+#define c10_AMAIR1	30	/* Auxilary Memory Attribute Indirection Reg1 */
+#define NR_CP15_REGS	31	/* Number of regs (incl. invalid) */
 
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 098f7dd6d564..09af14999c9b 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -101,6 +101,12 @@ struct kvm_vcpu_arch {
 	/* The CPU type we expose to the VM */
 	u32 midr;
 
+	/* HYP trapping configuration */
+	u32 hcr;
+
+	/* Interrupt related fields */
+	u32 irq_lines;		/* IRQ and FIQ levels */
+
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
@@ -128,9 +134,6 @@ struct kvm_vcpu_arch {
 	/* IO related fields */
 	struct kvm_decode mmio_decode;
 
-	/* Interrupt related fields */
-	u32 irq_lines;		/* IRQ and FIQ levels */
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 2d122adcdb22..5c7aa3c1519f 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -114,11 +114,34 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= L_PMD_S2_RDWR;
 }
 
+/* Open coded p*d_addr_end that can deal with 64bit addresses */
+#define kvm_pgd_addr_end(addr, end)					\
+({	u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;		\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
+#define kvm_pud_addr_end(addr,end)		(end)
+
+#define kvm_pmd_addr_end(addr, end)					\
+({	u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK;		\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
-					      unsigned long size)
+#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
+	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					     unsigned long size)
+{
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
+	
 	/*
 	 * If we are going to insert an instruction page and the icache is
 	 * either VIPT or PIPT, there is a potential problem where the host
@@ -139,9 +162,10 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
 #define kvm_virt_to_phys(x)		virt_to_idmap((unsigned long)(x))
 
+void stage2_flush_vm(struct kvm *kvm);
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index ded041711beb..85598b5d1efd 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -174,6 +174,7 @@ int main(void)
   DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
   DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
   DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
+  DEFINE(VCPU_HCR,		offsetof(struct kvm_vcpu, arch.hcr));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
   DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248ea5669..bd18bb8b2770 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
 				    unsigned long cmd,
 				    void *v)
 {
-	if (cmd == CPU_PM_EXIT) {
+	if (cmd == CPU_PM_EXIT &&
+	    __hyp_get_vectors() == hyp_default_vectors) {
 		cpu_init_hyp_mode(NULL);
 		return NOTIFY_OK;
 	}
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 78c0885d6501..c58a35116f63 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -23,6 +23,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <trace/events/kvm.h>
@@ -205,6 +206,44 @@ done:
 }
 
 /*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct coproc_params *p,
+			  const struct coproc_reg *r)
+{
+	BUG_ON(!p->is_write);
+
+	vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+	if (p->is_64bit)
+		vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+
+	return true;
+}
+
+/*
+ * SCTLR accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ *
+ * Used by the cpu-specific code.
+ */
+bool access_sctlr(struct kvm_vcpu *vcpu,
+		  const struct coproc_params *p,
+		  const struct coproc_reg *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+/*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
  * NAKed, so it will read the PMCR anyway.
@@ -261,33 +300,36 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
 			NULL, reset_val, c1_CPACR, 0x00000000 },
 
-	/* TTBR0/TTBR1: swapped by interrupt.S. */
-	{ CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
-	{ CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
-
-	/* TTBCR: swapped by interrupt.S. */
+	/* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */
+	{ CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 },
+	{ CRn(2), CRm( 0), Op1( 0), Op2( 0), is32,
+			access_vm_reg, reset_unknown, c2_TTBR0 },
+	{ CRn(2), CRm( 0), Op1( 0), Op2( 1), is32,
+			access_vm_reg, reset_unknown, c2_TTBR1 },
 	{ CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_val, c2_TTBCR, 0x00000000 },
+			access_vm_reg, reset_val, c2_TTBCR, 0x00000000 },
+	{ CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 },
+
 
 	/* DACR: swapped by interrupt.S. */
 	{ CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c3_DACR },
+			access_vm_reg, reset_unknown, c3_DACR },
 
 	/* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */
 	{ CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c5_DFSR },
+			access_vm_reg, reset_unknown, c5_DFSR },
 	{ CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c5_IFSR },
+			access_vm_reg, reset_unknown, c5_IFSR },
 	{ CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c5_ADFSR },
+			access_vm_reg, reset_unknown, c5_ADFSR },
 	{ CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c5_AIFSR },
+			access_vm_reg, reset_unknown, c5_AIFSR },
 
 	/* DFAR/IFAR: swapped by interrupt.S. */
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c6_DFAR },
+			access_vm_reg, reset_unknown, c6_DFAR },
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_unknown, c6_IFAR },
+			access_vm_reg, reset_unknown, c6_IFAR },
 
 	/* PAR swapped by interrupt.S */
 	{ CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
@@ -324,9 +366,15 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */
 	{ CRn(10), CRm( 2), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c10_PRRR},
+			access_vm_reg, reset_unknown, c10_PRRR},
 	{ CRn(10), CRm( 2), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c10_NMRR},
+			access_vm_reg, reset_unknown, c10_NMRR},
+
+	/* AMAIR0/AMAIR1: swapped by interrupt.S. */
+	{ CRn(10), CRm( 3), Op1( 0), Op2( 0), is32,
+			access_vm_reg, reset_unknown, c10_AMAIR0},
+	{ CRn(10), CRm( 3), Op1( 0), Op2( 1), is32,
+			access_vm_reg, reset_unknown, c10_AMAIR1},
 
 	/* VBAR: swapped by interrupt.S. */
 	{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
@@ -334,7 +382,7 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 1), is32,
-			NULL, reset_val, c13_CID, 0x00000000 },
+			access_vm_reg, reset_val, c13_CID, 0x00000000 },
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 2), is32,
 			NULL, reset_unknown, c13_TID_URW },
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 3), is32,
@@ -443,7 +491,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct coproc_params params;
 
-	params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+	params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
 	params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
 	params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
 	params.is_64bit = true;
@@ -451,7 +499,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf;
 	params.Op2 = 0;
 	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
-	params.CRn = 0;
+	params.CRm = 0;
 
 	return emulate_cp15(vcpu, &params);
 }
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 0461d5c8d3de..1a44bbe39643 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -58,8 +58,8 @@ static inline void print_cp_instr(const struct coproc_params *p)
 {
 	/* Look, we even formatted it for you to paste into the table! */
 	if (p->is_64bit) {
-		kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n",
-			      p->CRm, p->Op1, p->is_write ? "write" : "read");
+		kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n",
+			      p->CRn, p->Op1, p->is_write ? "write" : "read");
 	} else {
 		kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32,"
 			      " func_%s },\n",
@@ -135,13 +135,13 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 		return -1;
 	if (i1->CRn != i2->CRn)
 		return i1->CRn - i2->CRn;
-	if (i1->is_64 != i2->is_64)
-		return i2->is_64 - i1->is_64;
 	if (i1->CRm != i2->CRm)
 		return i1->CRm - i2->CRm;
 	if (i1->Op1 != i2->Op1)
 		return i1->Op1 - i2->Op1;
-	return i1->Op2 - i2->Op2;
+	if (i1->Op2 != i2->Op2)
+		return i1->Op2 - i2->Op2;
+	return i2->is_64 - i1->is_64;
 }
 
 
@@ -153,4 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 #define is64		.is_64 = true
 #define is32		.is_64 = false
 
+bool access_sctlr(struct kvm_vcpu *vcpu,
+		  const struct coproc_params *p,
+		  const struct coproc_reg *r);
+
 #endif /* __ARM_KVM_COPROC_LOCAL_H__ */
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index bb0cac1410cc..e6f4ae48bda9 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -34,7 +34,7 @@
 static const struct coproc_reg a15_regs[] = {
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_val, c1_SCTLR, 0x00C50078 },
+			access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
 };
 
 static struct kvm_coproc_target_table a15_target_table = {
diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c
index 1df767331588..17fc7cd479d3 100644
--- a/arch/arm/kvm/coproc_a7.c
+++ b/arch/arm/kvm/coproc_a7.c
@@ -37,7 +37,7 @@
 static const struct coproc_reg a7_regs[] = {
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_val, c1_SCTLR, 0x00C50878 },
+			access_sctlr, reset_val, c1_SCTLR, 0x00C50878 },
 };
 
 static struct kvm_coproc_target_table a7_target_table = {
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 2786eae10c0d..b23a59c1c522 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,6 +38,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.hcr = HCR_GUEST_MASK;
 	return 0;
 }
 
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc15539bad2..0d68d4073068 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@ after_vfp_restore:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@ hyp_hvc:
 host_switch_to_hyp:
 	pop	{r0, r1, r2}
 
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
 	push	{lr}
 	mrs	lr, SPSR
 	push	{lr}
@@ -378,7 +387,7 @@ THUMB(	orr	lr, #1)
 	pop	{lr}
 	msr	SPSR_csxf, lr
 	pop	{lr}
-	eret
+1:	eret
 
 guest_trap:
 	load_vcpu			@ Load VCPU pointer to r0
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 6f18695a09cb..76af93025574 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -303,13 +303,17 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
 	mrrc	p15, 0, r4, r5, c7	@ PAR
+	mrc	p15, 0, r6, c10, c3, 0	@ AMAIR0
+	mrc	p15, 0, r7, c10, c3, 1	@ AMAIR1
 
 	.if \store_to_vcpu == 0
-	push	{r2,r4-r5}
+	push	{r2,r4-r7}
 	.else
 	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
 	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
 	strd	r4, r5, [r12]
+	str	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+	str	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
 	.endif
 .endm
 
@@ -322,15 +326,19 @@ vcpu	.req	r0		@ vcpu pointer always in r0
  */
 .macro write_cp15_state read_from_vcpu
 	.if \read_from_vcpu == 0
-	pop	{r2,r4-r5}
+	pop	{r2,r4-r7}
 	.else
 	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
 	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
 	ldrd	r4, r5, [r12]
+	ldr	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+	ldr	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
 	.endif
 
 	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
 	mcrr	p15, 0, r4, r5, c7	@ PAR
+	mcr	p15, 0, r6, c10, c3, 0	@ AMAIR0
+	mcr	p15, 0, r7, c10, c3, 1	@ AMAIR1
 
 	.if \read_from_vcpu == 0
 	pop	{r2-r12}
@@ -597,17 +605,14 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 /* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
 .macro configure_hyp_role operation
-	mrc	p15, 4, r2, c1, c1, 0	@ HCR
-	bic	r2, r2, #HCR_VIRT_EXCP_MASK
-	ldr	r3, =HCR_GUEST_MASK
 	.if \operation == vmentry
-	orr	r2, r2, r3
+	ldr	r2, [vcpu, #VCPU_HCR]
 	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
 	orr	r2, r2, r3
 	.else
-	bic	r2, r2, r3
+	mov	r2, #0
 	.endif
-	mcr	p15, 4, r2, c1, c1, 0
+	mcr	p15, 4, r2, c1, c1, 0	@ HCR
 .endm
 
 .macro load_vcpu
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7789857d1470..80bb1e6c2c29 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -144,8 +144,9 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	while (addr < end) {
 		pgd = pgdp + pgd_index(addr);
 		pud = pud_offset(pgd, addr);
+		pte = NULL;
 		if (pud_none(*pud)) {
-			addr = pud_addr_end(addr, end);
+			addr = kvm_pud_addr_end(addr, end);
 			continue;
 		}
 
@@ -155,13 +156,13 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 			 * move on.
 			 */
 			clear_pud_entry(kvm, pud, addr);
-			addr = pud_addr_end(addr, end);
+			addr = kvm_pud_addr_end(addr, end);
 			continue;
 		}
 
 		pmd = pmd_offset(pud, addr);
 		if (pmd_none(*pmd)) {
-			addr = pmd_addr_end(addr, end);
+			addr = kvm_pmd_addr_end(addr, end);
 			continue;
 		}
 
@@ -174,12 +175,12 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 		/*
 		 * If the pmd entry is to be cleared, walk back up the ladder
 		 */
-		if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
+		if (kvm_pmd_huge(*pmd) || (pte && page_empty(pte))) {
 			clear_pmd_entry(kvm, pmd, addr);
-			next = pmd_addr_end(addr, end);
+			next = kvm_pmd_addr_end(addr, end);
 			if (page_empty(pmd) && !page_empty(pud)) {
 				clear_pud_entry(kvm, pud, addr);
-				next = pud_addr_end(addr, end);
+				next = kvm_pud_addr_end(addr, end);
 			}
 		}
 
@@ -187,6 +188,99 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	}
 }
 
+static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+			kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (kvm_pmd_huge(*pmd)) {
+				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+				kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
+			} else {
+				stage2_flush_ptes(kvm, pmd, addr, next);
+			}
+		}
+	} while (pmd++, addr = next, addr != end);
+}
+
+static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			if (pud_huge(*pud)) {
+				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+				kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
+			} else {
+				stage2_flush_pmds(kvm, pud, addr, next);
+			}
+		}
+	} while (pud++, addr = next, addr != end);
+}
+
+static void stage2_flush_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+	phys_addr_t next;
+	pgd_t *pgd;
+
+	pgd = kvm->arch.pgd + pgd_index(addr);
+	do {
+		next = kvm_pgd_addr_end(addr, end);
+		stage2_flush_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the stage 2 page tables and invalidate any cache lines
+ * backing memory already mapped to the VM.
+ */
+void stage2_flush_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_flush_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 /**
  * free_boot_hyp_pgd - free HYP boot page tables
  *
@@ -715,7 +809,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_s2pmd_writable(&new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE);
+		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, PAGE_S2);
@@ -723,7 +817,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_icache_guest_page(kvm, hva, PAGE_SIZE);
+		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
 	}
 
diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig
index 8f4649b301b2..1abae5f6a418 100644
--- a/arch/arm/mach-hisi/Kconfig
+++ b/arch/arm/mach-hisi/Kconfig
@@ -8,7 +8,7 @@ config ARCH_HI3xxx
 	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
-	select HAVE_ARM_TWD
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select PINCTRL
 	select PINCTRL_SINGLE
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index af2e582d2b74..4d677f442539 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -482,6 +482,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	if (IS_ENABLED(CONFIG_PCI_IMX6))
 		clk_set_parent(clk[lvds1_sel], clk[sata_ref]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index 3781a1853998..4c86f3035205 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -266,6 +266,9 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	/* Audio-related clocks configuration */
 	clk_set_parent(clks[IMX6SL_CLK_SPDIF0_SEL], clks[IMX6SL_CLK_PLL3_PFD3]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index 9d47adc078aa..7a9b98589db7 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -236,8 +236,6 @@ void __init imx6q_pm_init(void)
 		regmap_update_bits(gpr, IOMUXC_GPR1, IMX6Q_GPR1_GINT,
 				   IMX6Q_GPR1_GINT);
 
-	/* Set initial power mode */
-	imx6q_set_lpm(WAIT_CLOCKED);
 
 	suspend_set_ops(&imx6q_pm_ops);
 }
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index ba470d64493b..3795ae28a613 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -2,7 +2,6 @@ config ARCH_MOXART
 	bool "MOXA ART SoC" if ARCH_MULTI_V4T
 	select CPU_FA526
 	select ARM_DMA_MEM_BUFFERABLE
-	select DMA_OF
 	select USE_OF
 	select CLKSRC_OF
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 653b489479e0..e2ce4f8366a7 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -54,7 +54,7 @@ config SOC_OMAP5
 	select ARM_GIC
 	select CPU_V7
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c
index c9f309ae88c5..8b90c4f2d430 100644
--- a/arch/arm/mach-pxa/am300epd.c
+++ b/arch/arm/mach-pxa/am300epd.c
@@ -30,6 +30,7 @@
 
 #include <mach/gumstix.h>
 #include <mach/mfp-pxa25x.h>
+#include <mach/irqs.h>
 #include <linux/platform_data/video-pxafb.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h
index 954641e6c8b1..1b0825911e62 100644
--- a/arch/arm/mach-pxa/include/mach/balloon3.h
+++ b/arch/arm/mach-pxa/include/mach/balloon3.h
@@ -14,6 +14,8 @@
 #ifndef ASM_ARCH_BALLOON3_H
 #define ASM_ARCH_BALLOON3_H
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
 enum balloon3_features {
 	BALLOON3_FEATURE_OHCI,
 	BALLOON3_FEATURE_MMC,
diff --git a/arch/arm/mach-pxa/include/mach/corgi.h b/arch/arm/mach-pxa/include/mach/corgi.h
index f3c3493b468d..c030d955bbd7 100644
--- a/arch/arm/mach-pxa/include/mach/corgi.h
+++ b/arch/arm/mach-pxa/include/mach/corgi.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_ARCH_CORGI_H
 #define __ASM_ARCH_CORGI_H  1
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
 
 /*
  * Corgi (Non Standard) GPIO Definitions
diff --git a/arch/arm/mach-pxa/include/mach/csb726.h b/arch/arm/mach-pxa/include/mach/csb726.h
index 2628e7b72116..00cfbbbf73f7 100644
--- a/arch/arm/mach-pxa/include/mach/csb726.h
+++ b/arch/arm/mach-pxa/include/mach/csb726.h
@@ -11,6 +11,8 @@
 #ifndef CSB726_H
 #define CSB726_H
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 #define CSB726_GPIO_IRQ_LAN	52
 #define CSB726_GPIO_IRQ_SM501	53
 #define CSB726_GPIO_MMC_DETECT	100
diff --git a/arch/arm/mach-pxa/include/mach/gumstix.h b/arch/arm/mach-pxa/include/mach/gumstix.h
index dba14b6503ad..f7df27bbb42e 100644
--- a/arch/arm/mach-pxa/include/mach/gumstix.h
+++ b/arch/arm/mach-pxa/include/mach/gumstix.h
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /* BTRESET - Reset line to Bluetooth module, active low signal. */
 #define GPIO_GUMSTIX_BTRESET          7
diff --git a/arch/arm/mach-pxa/include/mach/idp.h b/arch/arm/mach-pxa/include/mach/idp.h
index 22a96f87232b..7e63f4680271 100644
--- a/arch/arm/mach-pxa/include/mach/idp.h
+++ b/arch/arm/mach-pxa/include/mach/idp.h
@@ -23,6 +23,7 @@
  * IDP hardware.
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 #define IDP_FLASH_PHYS		(PXA_CS0_PHYS)
 #define IDP_ALT_FLASH_PHYS	(PXA_CS1_PHYS)
diff --git a/arch/arm/mach-pxa/include/mach/palmld.h b/arch/arm/mach-pxa/include/mach/palmld.h
index 2c4471336570..b184f296023b 100644
--- a/arch/arm/mach-pxa/include/mach/palmld.h
+++ b/arch/arm/mach-pxa/include/mach/palmld.h
@@ -13,6 +13,8 @@
 #ifndef _INCLUDE_PALMLD_H_
 #define _INCLUDE_PALMLD_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmt5.h b/arch/arm/mach-pxa/include/mach/palmt5.h
index 0bd4f036c72f..e342c5921405 100644
--- a/arch/arm/mach-pxa/include/mach/palmt5.h
+++ b/arch/arm/mach-pxa/include/mach/palmt5.h
@@ -15,6 +15,8 @@
 #ifndef _INCLUDE_PALMT5_H_
 #define _INCLUDE_PALMT5_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h
index c383a21680b6..81c727b3cfd2 100644
--- a/arch/arm/mach-pxa/include/mach/palmtc.h
+++ b/arch/arm/mach-pxa/include/mach/palmtc.h
@@ -16,6 +16,8 @@
 #ifndef _INCLUDE_PALMTC_H_
 #define _INCLUDE_PALMTC_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h
index f2e530380253..92bc1f05300d 100644
--- a/arch/arm/mach-pxa/include/mach/palmtx.h
+++ b/arch/arm/mach-pxa/include/mach/palmtx.h
@@ -16,6 +16,8 @@
 #ifndef _INCLUDE_PALMTX_H_
 #define _INCLUDE_PALMTX_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h
index 6bf28de228bd..86ebd7b6c960 100644
--- a/arch/arm/mach-pxa/include/mach/pcm027.h
+++ b/arch/arm/mach-pxa/include/mach/pcm027.h
@@ -23,6 +23,8 @@
  * Definitions of CPU card resources only
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /* phyCORE-PXA270 (PCM027) Interrupts */
 #define PCM027_IRQ(x)          (IRQ_BOARD_START + (x))
 #define PCM027_BTDET_IRQ       PCM027_IRQ(0)
diff --git a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
index 0260aaa2fc17..7e544c14967e 100644
--- a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
+++ b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
@@ -20,6 +20,7 @@
  */
 
 #include <mach/pcm027.h>
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /*
  * definitions relevant only when the PCM-990
diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h
index f32ff75dcca8..b56b19351a03 100644
--- a/arch/arm/mach-pxa/include/mach/poodle.h
+++ b/arch/arm/mach-pxa/include/mach/poodle.h
@@ -15,6 +15,8 @@
 #ifndef __ASM_ARCH_POODLE_H
 #define __ASM_ARCH_POODLE_H  1
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /*
  * GPIOs
  */
diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/include/mach/spitz.h
index 0bfe6507c95d..25c9f62e46aa 100644
--- a/arch/arm/mach-pxa/include/mach/spitz.h
+++ b/arch/arm/mach-pxa/include/mach/spitz.h
@@ -15,8 +15,8 @@
 #define __ASM_ARCH_SPITZ_H  1
 #endif
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */
 #include <linux/fb.h>
-#include <linux/gpio.h>
 
 /* Spitz/Akita GPIOs */
 
diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index 2bb0e862598c..0497d95cef25 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_ARCH_TOSA_H_
 #define _ASM_ARCH_TOSA_H_ 1
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
 /*  TOSA Chip selects  */
 #define TOSA_LCDC_PHYS		PXA_CS4_PHYS
 /* Internel Scoop */
diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h
index d2ca01053f69..ae3ca013afab 100644
--- a/arch/arm/mach-pxa/include/mach/trizeps4.h
+++ b/arch/arm/mach-pxa/include/mach/trizeps4.h
@@ -10,6 +10,8 @@
 #ifndef _TRIPEPS4_H_
 #define _TRIPEPS4_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /* physical memory regions */
 #define TRIZEPS4_FLASH_PHYS	(PXA_CS0_PHYS)  /* Flash region */
 #define TRIZEPS4_DISK_PHYS	(PXA_CS1_PHYS)  /* Disk On Chip region */
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 338640631e08..05fa505df585 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -8,7 +8,7 @@ config ARCH_SHMOBILE_MULTI
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select ARM_GIC
 	select MIGHT_HAVE_CACHE_L2X0
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 1db2a5ca9ab8..8c09a8393fb6 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -25,6 +25,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/of.h>
+#include <linux/memblock.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
 
@@ -41,6 +42,18 @@
 
 void __iomem *zynq_scu_base;
 
+/**
+ * zynq_memory_init - Initialize special memory
+ *
+ * We need to stop things allocating the low memory as DMA can't work in
+ * the 1st 512K of memory.
+ */
+static void __init zynq_memory_init(void)
+{
+	if (!__pa(PAGE_OFFSET))
+		memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+}
+
 static struct platform_device zynq_cpuidle_device = {
 	.name = "cpuidle-zynq",
 };
@@ -117,5 +130,6 @@ DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform")
 	.init_machine	= zynq_init_machine,
 	.init_time	= zynq_timer_init,
 	.dt_compat	= zynq_dt_match,
+	.reserve	= zynq_memory_init,
 	.restart	= zynq_system_reset,
 MACHINE_END
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dd4327f09ba4..27bbcfc7202a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -36,6 +36,7 @@ config ARM64
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
+	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 84139be62ae6..7959dd0ca5d5 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
@@ -19,6 +18,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -27,6 +27,7 @@ CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
+CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
@@ -42,14 +43,17 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
-CONFIG_BLK_DEV=y
+CONFIG_DMA_CMA=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_PATA_PLATFORM=y
+CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
-CONFIG_MII=y
 CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_SERIO_I8042 is not set
@@ -62,13 +66,19 @@ CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_FB=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 01de5aaa3edc..0237f0867e37 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -54,8 +54,7 @@ static inline void atomic_add(int i, atomic_t *v)
 "	stxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline int atomic_add_return(int i, atomic_t *v)
@@ -64,14 +63,15 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	int result;
 
 	asm volatile("// atomic_add_return\n"
-"1:	ldaxr	%w0, %2\n"
+"1:	ldxr	%w0, %2\n"
 "	add	%w0, %w0, %w3\n"
 "	stlxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -86,8 +86,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 "	stxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline int atomic_sub_return(int i, atomic_t *v)
@@ -96,14 +95,15 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	int result;
 
 	asm volatile("// atomic_sub_return\n"
-"1:	ldaxr	%w0, %2\n"
+"1:	ldxr	%w0, %2\n"
 "	sub	%w0, %w0, %w3\n"
 "	stlxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -112,17 +112,20 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	unsigned long tmp;
 	int oldval;
 
+	smp_mb();
+
 	asm volatile("// atomic_cmpxchg\n"
-"1:	ldaxr	%w1, %2\n"
+"1:	ldxr	%w1, %2\n"
 "	cmp	%w1, %w3\n"
 "	b.ne	2f\n"
-"	stlxr	%w0, %w4, %2\n"
+"	stxr	%w0, %w4, %2\n"
 "	cbnz	%w0, 1b\n"
 "2:"
 	: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
 	: "Ir" (old), "r" (new)
-	: "cc", "memory");
+	: "cc");
 
+	smp_mb();
 	return oldval;
 }
 
@@ -173,8 +176,7 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 "	stxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline long atomic64_add_return(long i, atomic64_t *v)
@@ -183,14 +185,15 @@ static inline long atomic64_add_return(long i, atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile("// atomic64_add_return\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	add	%0, %0, %3\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -205,8 +208,7 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 "	stxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline long atomic64_sub_return(long i, atomic64_t *v)
@@ -215,14 +217,15 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile("// atomic64_sub_return\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	sub	%0, %0, %3\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -231,17 +234,20 @@ static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
 	long oldval;
 	unsigned long res;
 
+	smp_mb();
+
 	asm volatile("// atomic64_cmpxchg\n"
-"1:	ldaxr	%1, %2\n"
+"1:	ldxr	%1, %2\n"
 "	cmp	%1, %3\n"
 "	b.ne	2f\n"
-"	stlxr	%w0, %4, %2\n"
+"	stxr	%w0, %4, %2\n"
 "	cbnz	%w0, 1b\n"
 "2:"
 	: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
 	: "Ir" (old), "r" (new)
-	: "cc", "memory");
+	: "cc");
 
+	smp_mb();
 	return oldval;
 }
 
@@ -253,11 +259,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile("// atomic64_dec_if_positive\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	subs	%0, %0, #1\n"
 "	b.mi	2f\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b\n"
+"	dmb	ish\n"
 "2:"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	:
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 78e20ba8806b..409ca370cfe2 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -25,7 +25,7 @@
 #define wfi()		asm volatile("wfi" : : : "memory")
 
 #define isb()		asm volatile("isb" : : : "memory")
-#define dsb()		asm volatile("dsb sy" : : : "memory")
+#define dsb(opt)	asm volatile("dsb sy" : : : "memory")
 
 #define mb()		dsb()
 #define rmb()		asm volatile("dsb ld" : : : "memory")
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index fea9ee327206..889324981aa4 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -116,6 +116,7 @@ extern void flush_dcache_page(struct page *);
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");
+	dsb();
 }
 
 #define flush_dcache_mmap_lock(mapping) \
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 56166d7f4a25..57c0fa7bf711 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -29,44 +29,45 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	switch (size) {
 	case 1:
 		asm volatile("//	__xchg1\n"
-		"1:	ldaxrb	%w0, %2\n"
+		"1:	ldxrb	%w0, %2\n"
 		"	stlxrb	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 2:
 		asm volatile("//	__xchg2\n"
-		"1:	ldaxrh	%w0, %2\n"
+		"1:	ldxrh	%w0, %2\n"
 		"	stlxrh	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 4:
 		asm volatile("//	__xchg4\n"
-		"1:	ldaxr	%w0, %2\n"
+		"1:	ldxr	%w0, %2\n"
 		"	stlxr	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 8:
 		asm volatile("//	__xchg8\n"
-		"1:	ldaxr	%0, %2\n"
+		"1:	ldxr	%0, %2\n"
 		"	stlxr	%w1, %3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	default:
 		BUILD_BUG();
 	}
 
+	smp_mb();
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 78834123a32e..c4a7f940b387 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -42,7 +42,7 @@
 #define ESR_EL1_EC_SP_ALIGN	(0x26)
 #define ESR_EL1_EC_FP_EXC32	(0x28)
 #define ESR_EL1_EC_FP_EXC64	(0x2C)
-#define ESR_EL1_EC_SERRROR	(0x2F)
+#define ESR_EL1_EC_SERROR	(0x2F)
 #define ESR_EL1_EC_BREAKPT_EL0	(0x30)
 #define ESR_EL1_EC_BREAKPT_EL1	(0x31)
 #define ESR_EL1_EC_SOFTSTP_EL0	(0x32)
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 78cc3aba5d69..5f750dc96e0f 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -24,10 +24,11 @@
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 	asm volatile(							\
-"1:	ldaxr	%w1, %2\n"						\
+"1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w3, %w0, %2\n"						\
 "	cbnz	%w3, 1b\n"						\
+"	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
@@ -40,7 +41,7 @@
 "	.popsection\n"							\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "cc", "memory")
+	: "memory")
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -111,11 +112,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-"1:	ldaxr	%w1, %2\n"
+"1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
 "	cbnz	%w3, 3f\n"
 "2:	stlxr	%w3, %w5, %2\n"
 "	cbnz	%w3, 1b\n"
+"	dmb	ish\n"
 "3:\n"
 "	.pushsection .fixup,\"ax\"\n"
 "4:	mov	%w0, %w6\n"
@@ -127,7 +129,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 "	.popsection\n"
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
-	: "cc", "memory");
+	: "memory");
 
 	*uval = val;
 	return ret;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index c98ef4771c73..00fbaa75dc7b 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -62,6 +62,7 @@
  * RW:		64bit by default, can be overriden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * TSW:		Trap cache operations by set/way
  * TWE:		Trap WFE
  * TWI:		Trap WFI
@@ -74,7 +75,7 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
-			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_IMO | HCR_FMO | \
 			 HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
@@ -231,7 +232,7 @@
 #define ESR_EL2_EC_SP_ALIGN	(0x26)
 #define ESR_EL2_EC_FP_EXC32	(0x28)
 #define ESR_EL2_EC_FP_EXC64	(0x2C)
-#define ESR_EL2_EC_SERRROR	(0x2F)
+#define ESR_EL2_EC_SERROR	(0x2F)
 #define ESR_EL2_EC_BREAKPT	(0x30)
 #define ESR_EL2_EC_BREAKPT_HYP	(0x31)
 #define ESR_EL2_EC_SOFTSTP	(0x32)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b25763bc0ec4..9fcd54b1e16d 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -79,7 +79,8 @@
 #define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
 #define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
 #define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
-#define c10_AMAIR	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
 #define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
 #define NR_CP15_REGS	(NR_SYS_REGS * 2)
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 7f1f9408ff66..7d29847a893b 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -106,7 +106,6 @@ static inline bool kvm_is_write_fault(unsigned long esr)
 	return true;
 }
 
-static inline void kvm_clean_dcache_area(void *addr, size_t size) {}
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
@@ -122,11 +121,25 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= PMD_S2_RDWR;
 }
 
+#define kvm_pgd_addr_end(addr, end)	pgd_addr_end(addr, end)
+#define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
+#define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
-					      unsigned long size)
+#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
+	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					     unsigned long size)
+{
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
+
 	if (!icache_is_aliasing()) {		/* PIPT */
 		flush_icache_range(hva, hva + size);
 	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
@@ -135,8 +148,9 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
 #define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
 
+void stage2_flush_vm(struct kvm *kvm);
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 3d5cf064d7a1..c45b7b1b7197 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -132,7 +132,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	"	cbnz	%w0, 2b\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
@@ -146,7 +146,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	"1:\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
-	: "cc", "memory");
+	: "memory");
 
 	return !tmp;
 }
@@ -187,7 +187,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 	"	cbnz	%w1, 2b\n"
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -201,7 +201,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	"	cbnz	%w1, 1b\n"
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
@@ -216,7 +216,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	"1:\n"
 	: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 
 	return !tmp2;
 }
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 58125bf008d3..bb8eb8a78e67 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -399,7 +399,10 @@ __SYSCALL(374, compat_sys_sendmmsg)
 __SYSCALL(375, sys_setns)
 __SYSCALL(376, compat_sys_process_vm_readv)
 __SYSCALL(377, compat_sys_process_vm_writev)
-__SYSCALL(378, sys_ni_syscall)			/* 378 for kcmp */
+__SYSCALL(378, sys_kcmp)
+__SYSCALL(379, sys_finit_module)
+__SYSCALL(380, sys_sched_setattr)
+__SYSCALL(381, sys_sched_getattr)
 
 #define __NR_compat_syscalls		379
 
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 63c48ffdf230..7787208e8cc6 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -38,12 +38,13 @@ __kuser_cmpxchg64:			// 0xffff0f60
 	.inst	0xe92d00f0		//	push		{r4, r5, r6, r7}
 	.inst	0xe1c040d0		//	ldrd		r4, r5, [r0]
 	.inst	0xe1c160d0		//	ldrd		r6, r7, [r1]
-	.inst	0xe1b20e9f		// 1:	ldaexd		r0, r1, [r2]
+	.inst	0xe1b20f9f		// 1:	ldrexd		r0, r1, [r2]
 	.inst	0xe0303004		//	eors		r3, r0, r4
 	.inst	0x00313005		//	eoreqs		r3, r1, r5
 	.inst	0x01a23e96		//	stlexdeq	r3, r6, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffff9		//	beq		1b
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe8bd00f0		//	pop		{r4, r5, r6, r7}
 	.inst	0xe12fff1e		//	bx		lr
@@ -55,11 +56,12 @@ __kuser_memory_barrier:			// 0xffff0fa0
 
 	.align	5
 __kuser_cmpxchg:			// 0xffff0fc0
-	.inst	0xe1923e9f		// 1:	ldaex		r3, [r2]
+	.inst	0xe1923f9f		// 1:	ldrex		r3, [r2]
 	.inst	0xe0533000		//	subs		r3, r3, r0
 	.inst	0x01823e91		//	stlexeq		r3, r1, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffffa		//	beq		1b
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe12fff1e		//	bx		lr
 
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 65d40cf6945a..a7149cae1615 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -238,6 +238,8 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->use_syscall			= use_syscall;
 	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
 	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
 	if (!use_syscall) {
 		vdso_data->cs_cycle_last	= tk->clock->cycle_last;
@@ -245,8 +247,6 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->xtime_clock_nsec	= tk->xtime_nsec;
 		vdso_data->cs_mult		= tk->mult;
 		vdso_data->cs_shift		= tk->shift;
-		vdso_data->wtm_clock_sec	= tk->wall_to_monotonic.tv_sec;
-		vdso_data->wtm_clock_nsec	= tk->wall_to_monotonic.tv_nsec;
 	}
 
 	smp_wmb();
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d8064af42e62..6d20b7d162d8 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -48,7 +48,7 @@ $(obj-vdso): %.o: %.S
 
 # Actual build commands
 quiet_cmd_vdsold = VDSOL $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index f0a6d10b5211..fe652ffd34c2 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -103,6 +103,8 @@ ENTRY(__kernel_clock_gettime)
 	bl	__do_get_tspec
 	seqcnt_check w9, 1b
 
+	mov	x30, x2
+
 	cmp	w0, #CLOCK_MONOTONIC
 	b.ne	6f
 
@@ -118,6 +120,9 @@ ENTRY(__kernel_clock_gettime)
 	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
 	b.ne	8f
 
+	/* xtime_coarse_nsec is already right-shifted */
+	mov	x12, #0
+
 	/* Get coarse timespec. */
 	adr	vdso_data, _vdso_data
 3:	seqcnt_acquire
@@ -156,7 +161,7 @@ ENTRY(__kernel_clock_gettime)
 	lsr	x11, x11, x12
 	stp	x10, x11, [x1, #TSPEC_TV_SEC]
 	mov	x0, xzr
-	ret	x2
+	ret
 7:
 	mov	x30, x2
 8:	/* Syscall fallback. */
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36e10ff..2c56012cb2d2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@ __hyp_panic_str:
 
 	.align	2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	ret
@@ -737,7 +755,12 @@ el1_sync:					// Guest trapped into EL2
 	pop	x2, x3
 	pop	x0, x1
 
-	push	lr, xzr
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@ el1_sync:					// Guest trapped into EL2
 	blr	lr
 
 	pop	lr, xzr
-	eret
+2:	eret
 
 el1_trap:
 	/*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 02e9d09e1d80..03244582bc55 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -27,6 +27,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <trace/events/kvm.h>
@@ -121,6 +122,48 @@ done:
 }
 
 /*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	unsigned long val;
+
+	BUG_ON(!p->is_write);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	if (!p->is_aarch32) {
+		vcpu_sys_reg(vcpu, r->reg) = val;
+	} else {
+		vcpu_cp15(vcpu, r->reg) = val & 0xffffffffUL;
+		if (!p->is_32bit)
+			vcpu_cp15(vcpu, r->reg + 1) = val >> 32;
+	}
+	return true;
+}
+
+/*
+ * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ */
+static bool access_sctlr(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr_el2 &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+/*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
  * NAKed, so it will read the PMCR anyway.
@@ -185,32 +228,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_mpidr, MPIDR_EL1 },
 	/* SCTLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, SCTLR_EL1, 0x00C50078 },
+	  access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
 	/* CPACR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
 	  NULL, reset_val, CPACR_EL1, 0 },
 	/* TTBR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, TTBR0_EL1 },
+	  access_vm_reg, reset_unknown, TTBR0_EL1 },
 	/* TTBR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
-	  NULL, reset_unknown, TTBR1_EL1 },
+	  access_vm_reg, reset_unknown, TTBR1_EL1 },
 	/* TCR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
-	  NULL, reset_val, TCR_EL1, 0 },
+	  access_vm_reg, reset_val, TCR_EL1, 0 },
 
 	/* AFSR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
-	  NULL, reset_unknown, AFSR0_EL1 },
+	  access_vm_reg, reset_unknown, AFSR0_EL1 },
 	/* AFSR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
-	  NULL, reset_unknown, AFSR1_EL1 },
+	  access_vm_reg, reset_unknown, AFSR1_EL1 },
 	/* ESR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, ESR_EL1 },
+	  access_vm_reg, reset_unknown, ESR_EL1 },
 	/* FAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, FAR_EL1 },
+	  access_vm_reg, reset_unknown, FAR_EL1 },
 	/* PAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
 	  NULL, reset_unknown, PAR_EL1 },
@@ -224,17 +267,17 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, MAIR_EL1 },
+	  access_vm_reg, reset_unknown, MAIR_EL1 },
 	/* AMAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
-	  NULL, reset_amair_el1, AMAIR_EL1 },
+	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
 	/* VBAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, VBAR_EL1, 0 },
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
-	  NULL, reset_val, CONTEXTIDR_EL1, 0 },
+	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	/* TPIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
 	  NULL, reset_unknown, TPIDR_EL1 },
@@ -305,14 +348,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_val, FPEXC32_EL2, 0x70 },
 };
 
-/* Trapped cp15 registers */
+/*
+ * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
+ * depending on the way they are accessed (as a 32bit or a 64bit
+ * register).
+ */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
+	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+
 	/*
 	 * DC{C,I,CI}SW operations:
 	 */
 	{ Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
+
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake },
@@ -326,6 +387,14 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake },
+
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+
+	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 
 /* Target specific emulation tables */
@@ -437,6 +506,8 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	int Rt2 = (hsr >> 10) & 0xf;
 
+	params.is_aarch32 = true;
+	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -480,6 +551,8 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = true;
+	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt  = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -549,6 +622,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = false;
+	params.is_32bit = false;
 	params.Op0 = (esr >> 20) & 3;
 	params.Op1 = (esr >> 14) & 0x7;
 	params.CRn = (esr >> 10) & 0xf;
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index d50d3722998e..d411e251412c 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -30,6 +30,8 @@ struct sys_reg_params {
 	u8	Op2;
 	u8	Rt;
 	bool	is_write;
+	bool	is_aarch32;
+	bool	is_32bit;	/* Only valid if is_aarch32 is true */
 };
 
 struct sys_reg_desc {
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
index e5db797790d3..7dac371cc9a2 100644
--- a/arch/arm64/lib/bitops.S
+++ b/arch/arm64/lib/bitops.S
@@ -46,11 +46,12 @@ ENTRY(	\name	)
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
 	lsl	x4, x2, x3		// Create mask
-1:	ldaxr	x2, [x1]
+1:	ldxr	x2, [x1]
 	lsr	x0, x2, x3		// Save old value of bit
 	\instr	x2, x2, x4		// toggle bit
 	stlxr	w5, x2, [x1]
 	cbnz	w5, 1b
+	dmb	ish
 	and	x0, x0, #1
 3:	ret
 ENDPROC(\name	)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 45b5ab54c9ee..fbd76785c5db 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -45,6 +45,7 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_DMA_CMA)) {
 		struct page *page;
 
+		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
 							get_order(size));
 		if (!page)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f557ebbe7013..f8dc7e8fce6f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -203,10 +203,18 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 	do {
 		next = pmd_addr_end(addr, end);
 		/* try section mapping first */
-		if (((addr | next | phys) & ~SECTION_MASK) == 0)
+		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
+			pmd_t old_pmd =*pmd;
 			set_pmd(pmd, __pmd(phys | prot_sect_kernel));
-		else
+			/*
+			 * Check for previous table entries created during
+			 * boot (__create_page_tables) and flush them.
+			 */
+			if (!pmd_none(old_pmd))
+				flush_tlb_all();
+		} else {
 			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));
+		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
 }
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 7083cdada657..62c6101df260 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -32,17 +32,10 @@
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *new_pgd;
-
 	if (PGD_SIZE == PAGE_SIZE)
-		new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+		return (pgd_t *)get_zeroed_page(GFP_KERNEL);
 	else
-		new_pgd = kzalloc(PGD_SIZE, GFP_KERNEL);
-
-	if (!new_pgd)
-		return NULL;
-
-	return new_pgd;
+		return kzalloc(PGD_SIZE, GFP_KERNEL);
 }
 
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index afd45e0d552e..ae763d8bf55a 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			312 /* length of syscall table */
+#define NR_syscalls			314 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 34fd6fe46da1..715e85f858de 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -325,5 +325,7 @@
 #define __NR_process_vm_writev		1333
 #define __NR_accept4			1334
 #define __NR_finit_module		1335
+#define __NR_sched_setattr		1336
+#define __NR_sched_getattr		1337
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index ddea607f948a..fa8d61a312a7 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1773,6 +1773,8 @@ sys_call_table:
 	data8 sys_process_vm_writev
 	data8 sys_accept4
 	data8 sys_finit_module			// 1335
+	data8 sys_sched_setattr
+	data8 sys_sched_getattr
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h
index 05b7d39e4391..66fc24c24238 100644
--- a/arch/microblaze/include/asm/delay.h
+++ b/arch/microblaze/include/asm/delay.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_MICROBLAZE_DELAY_H
 #define _ASM_MICROBLAZE_DELAY_H
 
+#include <linux/param.h>
+
 extern inline void __delay(unsigned long loops)
 {
 	asm volatile ("# __delay		\n\t"		\
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index a2cea7206077..3fbb7f1db3bc 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -89,6 +89,11 @@ static inline unsigned int readl(const volatile void __iomem *addr)
 {
 	return le32_to_cpu(*(volatile unsigned int __force *)addr);
 }
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return le64_to_cpu(__raw_readq(addr));
+}
 static inline void writeb(unsigned char v, volatile void __iomem *addr)
 {
 	*(volatile unsigned char __force *)addr = v;
@@ -101,6 +106,7 @@ static inline void writel(unsigned int v, volatile void __iomem *addr)
 {
 	*(volatile unsigned int __force *)addr = cpu_to_le32(v);
 }
+#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr)
 
 /* ioread and iowrite variants. thease are for now same as __raw_
  * variants of accessors. we might check for endianess in the feature
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index b7fb0438458c..17645b2e2f07 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -66,7 +66,7 @@ real_start:
 	mts	rmsr, r0
 /* Disable stack protection from bootloader */
 	mts	rslr, r0
-	addi	r8, r0, 0xFFFFFFF
+	addi	r8, r0, 0xFFFFFFFF
 	mts	rshr, r8
 /*
  * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc'
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 11f3ad20321c..5483906e0f86 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -534,13 +534,10 @@ static int __init db1000_dev_init(void)
 		s0 = AU1100_GPIO1_INT;
 		s1 = AU1100_GPIO4_INT;
 
+		gpio_request(19, "sd0_cd");
+		gpio_request(20, "sd1_cd");
 		gpio_direction_input(19);	/* sd0 cd# */
 		gpio_direction_input(20);	/* sd1 cd# */
-		gpio_direction_input(21);	/* touch pendown# */
-		gpio_direction_input(207);	/* SPI MISO */
-		gpio_direction_output(208, 0);	/* SPI MOSI */
-		gpio_direction_output(209, 1);	/* SPI SCK */
-		gpio_direction_output(210, 1);	/* SPI CS# */
 
 		/* spi_gpio on SSI0 pins */
 		pfc = __raw_readl((void __iomem *)SYS_PINFUNC);
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index cfe092fc720d..6b9749540edf 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -74,6 +74,8 @@ static inline int __enable_fpu(enum fpu_mode mode)
 	default:
 		BUG();
 	}
+
+	return SIGFPE;
 }
 
 #define __disable_fpu()							\
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 1dee279f9665..d6e154a9e6a5 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -369,16 +369,18 @@
 #define __NR_process_vm_writev		(__NR_Linux + 346)
 #define __NR_kcmp			(__NR_Linux + 347)
 #define __NR_finit_module		(__NR_Linux + 348)
+#define __NR_sched_setattr		(__NR_Linux + 349)
+#define __NR_sched_getattr		(__NR_Linux + 350)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		348
+#define __NR_Linux_syscalls		350
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		348
+#define __NR_O32_Linux_syscalls		350
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -695,16 +697,18 @@
 #define __NR_kcmp			(__NR_Linux + 306)
 #define __NR_finit_module		(__NR_Linux + 307)
 #define __NR_getdents64			(__NR_Linux + 308)
+#define __NR_sched_setattr		(__NR_Linux + 309)
+#define __NR_sched_getattr		(__NR_Linux + 310)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		308
+#define __NR_Linux_syscalls		310
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		308
+#define __NR_64_Linux_syscalls		310
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1025,15 +1029,17 @@
 #define __NR_process_vm_writev		(__NR_Linux + 310)
 #define __NR_kcmp			(__NR_Linux + 311)
 #define __NR_finit_module		(__NR_Linux + 312)
+#define __NR_sched_setattr		(__NR_Linux + 313)
+#define __NR_sched_getattr		(__NR_Linux + 314)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		312
+#define __NR_Linux_syscalls		314
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		312
+#define __NR_N32_Linux_syscalls		314
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index e8e541b40d86..a5b14f48e1af 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -563,3 +563,5 @@ EXPORT(sys_call_table)
 	PTR	sys_process_vm_writev
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 4350 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 57e3742fec59..b56e254beb15 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -425,4 +425,6 @@ EXPORT(sys_call_table)
 	PTR	sys_kcmp
 	PTR	sys_finit_module
 	PTR	sys_getdents64
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 5310 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 2f48f5934399..f7e5b72cf481 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -418,4 +418,6 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_process_vm_writev	/* 6310 */
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f1acdb429f4f..6788727d91af 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -541,4 +541,6 @@ EXPORT(sys32_call_table)
 	PTR	compat_sys_process_vm_writev
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 4350 */
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 88d0962de65a..2bedafea3d94 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -33,22 +33,9 @@
 
 int hpux_execve(struct pt_regs *regs)
 {
-	int error;
-	struct filename *filename;
-
-	filename = getname((const char __user *) regs->gr[26]);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-
-	error = do_execve(filename->name,
+	return  do_execve(getname((const char __user *) regs->gr[26]),
 			  (const char __user *const __user *) regs->gr[25],
 			  (const char __user *const __user *) regs->gr[24]);
-
-	putname(filename);
-
-out:
-	return error;
 }
 
 struct hpux_dirent {
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index e27e9ad6818e..150866b2a3fe 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -134,6 +134,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 }
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
+extern int __dma_set_mask(struct device *dev, u64 dma_mask);
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index f7a8036579b5..42632c7a2a4e 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -77,6 +77,7 @@ struct iommu_table {
 #ifdef CONFIG_IOMMU_API
 	struct iommu_group *it_group;
 #endif
+	void (*set_bypass)(struct iommu_table *tbl, bool enable);
 };
 
 /* Pure 2^n version of get_order */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4ee06fe15de4..d0e784e0ff48 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,6 +8,7 @@
 
 #ifdef __powerpc64__
 
+extern char __start_interrupts[];
 extern char __end_interrupts[];
 
 extern char __prom_init_toc_start[];
@@ -21,6 +22,17 @@ static inline int in_kernel_text(unsigned long addr)
 	return 0;
 }
 
+static inline int overlaps_interrupt_vector_text(unsigned long start,
+							unsigned long end)
+{
+	unsigned long real_start, real_end;
+	real_start = __start_interrupts - _stext;
+	real_end = __end_interrupts - _stext;
+
+	return start < (unsigned long)__va(real_end) &&
+		(unsigned long)__va(real_start) < end;
+}
+
 static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 {
 	return start < (unsigned long)__init_end &&
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 8032b97ccdcb..ee78f6e49d64 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
-int dma_set_mask(struct device *dev, u64 dma_mask)
+int __dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	if (ppc_md.dma_set_mask)
-		return ppc_md.dma_set_mask(dev, dma_mask);
 	if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
 		return dma_ops->set_dma_mask(dev, dma_mask);
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
@@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 	*dev->dma_mask = dma_mask;
 	return 0;
 }
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (ppc_md.dma_set_mask)
+		return ppc_md.dma_set_mask(dev, dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
 EXPORT_SYMBOL(dma_set_mask);
 
 u64 dma_get_required_mask(struct device *dev)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7bb30dca4e19..fdc679d309ec 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -362,9 +362,13 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	 */
 	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
 		return NULL;
+
 	driver = eeh_pcid_get(dev);
-	if (driver && driver->err_handler)
-		return NULL;
+	if (driver) {
+		eeh_pcid_put(dev);
+		if (driver->err_handler)
+			return NULL;
+	}
 
 	/* Remove it from PCI subsystem */
 	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d773dd440a45..88e3ec6e1d96 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	memset(tbl->it_map, 0xff, sz);
 	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
 
+	/*
+	 * Disable iommu bypass, otherwise the user can DMA to all of
+	 * our physical memory via the bypass window instead of just
+	 * the pages that has been explicitly mapped into the iommu
+	 */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, false);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_take_ownership);
@@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl)
 	/* Restore bit#0 set by iommu_init_table() */
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
+
+	/* The kernel owns the device now, we can restore the iommu bypass */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, true);
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9729b23bfb0a..1d0848bba049 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -559,8 +559,13 @@ void exc_lvl_ctx_init(void)
 #ifdef CONFIG_PPC64
 		cpu_nr = i;
 #else
+#ifdef CONFIG_SMP
 		cpu_nr = get_hard_smp_processor_id(i);
+#else
+		cpu_nr = 0;
 #endif
+#endif
+
 		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
 		tp = critirq_ctx[cpu_nr];
 		tp->cpu = cpu_nr;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 75d4f7340da8..015ae55c1868 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
 
 /* Values we need to export to the second kernel via the device tree. */
 static phys_addr_t kernel_end;
+static phys_addr_t crashk_base;
 static phys_addr_t crashk_size;
+static unsigned long long mem_limit;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
@@ -207,7 +209,7 @@ static struct property kernel_end_prop = {
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
 	.length = sizeof(phys_addr_t),
-	.value = &crashk_res.start,
+	.value = &crashk_base
 };
 
 static struct property crashk_size_prop = {
@@ -219,9 +221,11 @@ static struct property crashk_size_prop = {
 static struct property memory_limit_prop = {
 	.name = "linux,memory-limit",
 	.length = sizeof(unsigned long long),
-	.value = &memory_limit,
+	.value = &mem_limit,
 };
 
+#define cpu_to_be_ulong	__PASTE(cpu_to_be, BITS_PER_LONG)
+
 static void __init export_crashk_values(struct device_node *node)
 {
 	struct property *prop;
@@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node)
 		of_remove_property(node, prop);
 
 	if (crashk_res.start != 0) {
+		crashk_base = cpu_to_be_ulong(crashk_res.start),
 		of_add_property(node, &crashk_base_prop);
-		crashk_size = resource_size(&crashk_res);
+		crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
 		of_add_property(node, &crashk_size_prop);
 	}
 
@@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node)
 	 * memory_limit is required by the kexec-tools to limit the
 	 * crash regions to the actual memory used.
 	 */
+	mem_limit = cpu_to_be_ulong(memory_limit);
 	of_update_property(node, &memory_limit_prop);
 }
 
@@ -264,7 +270,7 @@ static int __init kexec_setup(void)
 		of_remove_property(node, prop);
 
 	/* information needed by userspace when using default_machine_kexec */
-	kernel_end = __pa(_end);
+	kernel_end = cpu_to_be_ulong(__pa(_end));
 	of_add_property(node, &kernel_end_prop);
 
 	export_crashk_values(node);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index be4e6d648f60..59d229a2a3e0 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image)
 
 /* Values we need to export to the second kernel via the device tree. */
 static unsigned long htab_base;
+static unsigned long htab_size;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -379,7 +380,7 @@ static struct property htab_base_prop = {
 static struct property htab_size_prop = {
 	.name = "linux,htab-size",
 	.length = sizeof(unsigned long),
-	.value = &htab_size_bytes,
+	.value = &htab_size,
 };
 
 static int __init export_htab_values(void)
@@ -403,8 +404,9 @@ static int __init export_htab_values(void)
 	if (prop)
 		of_remove_property(node, prop);
 
-	htab_base = __pa(htab_address);
+	htab_base = cpu_to_be64(__pa(htab_address));
 	of_add_property(node, &htab_base_prop);
+	htab_size = cpu_to_be64(htab_size_bytes);
 	of_add_property(node, &htab_size_prop);
 
 	of_node_put(node);
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1ab001..1482327cfeba 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -69,8 +69,8 @@ _GLOBAL(relocate)
 	 * R_PPC64_RELATIVE ones.
 	 */
 	mtctr	r8
-5:	lwz	r0,12(9)	/* ELF64_R_TYPE(reloc->r_info) */
-	cmpwi	r0,R_PPC64_RELATIVE
+5:	ld	r0,8(9)		/* ELF64_R_TYPE(reloc->r_info) */
+	cmpdi	r0,R_PPC64_RELATIVE
 	bne	6f
 	ld	r6,0(r9)	/* reloc->r_offset */
 	ld	r0,16(r9)	/* reloc->r_addend */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 2b0da27eaee4..04cc4fcca78b 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -247,7 +247,12 @@ static void __init exc_lvl_early_init(void)
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
 	for_each_possible_cpu(i) {
+#ifdef CONFIG_SMP
 		hw_cpu = get_hard_smp_processor_id(i);
+#else
+		hw_cpu = 0;
+#endif
+
 		critirq_ctx[hw_cpu] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index de6881259aef..d766d6ee33fe 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,20 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/*
+		 * If relocatable, check if it overlaps interrupt vectors that
+		 * are copied down to real 0. For relocatable kernel
+		 * (e.g. kdump case) we copy interrupt vectors down to real
+		 * address 0. Mark that region as executable. This is
+		 * because on p8 system with relocation on exception feature
+		 * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
+		 * in order to execute the interrupt handlers in virtual
+		 * mode the vector region need to be marked as executable.
+		 */
+		if ((PHYSICAL_START > MEMORY_START) &&
+			overlaps_interrupt_vector_text(vaddr, vaddr + step))
+				tprot &= ~HPTE_R_N;
+
 		hash = hpt_hash(vpn, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29b89e863d7c..67cf22083f4c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1147,6 +1147,9 @@ static void power_pmu_enable(struct pmu *pmu)
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
+	if (cpuhw->bhrb_users)
+		ppmu->config_bhrb(cpuhw->bhrb_filter);
+
 	write_mmcr0(cpuhw, mmcr0);
 
 	/*
@@ -1158,8 +1161,6 @@ static void power_pmu_enable(struct pmu *pmu)
 	}
 
  out:
-	if (cpuhw->bhrb_users)
-		ppmu->config_bhrb(cpuhw->bhrb_filter);
 
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index a3f7abd2f13f..96cee20dcd34 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -25,6 +25,37 @@
 #define PM_BRU_FIN			0x10068
 #define PM_BR_MPRED_CMPL		0x400f6
 
+/* All L1 D cache load references counted at finish, gated by reject */
+#define PM_LD_REF_L1			0x100ee
+/* Load Missed L1 */
+#define PM_LD_MISS_L1			0x3e054
+/* Store Missed L1 */
+#define PM_ST_MISS_L1			0x300f0
+/* L1 cache data prefetches */
+#define PM_L1_PREF			0x0d8b8
+/* Instruction fetches from L1 */
+#define PM_INST_FROM_L1			0x04080
+/* Demand iCache Miss */
+#define PM_L1_ICACHE_MISS		0x200fd
+/* Instruction Demand sectors wriittent into IL1 */
+#define PM_L1_DEMAND_WRITE		0x0408c
+/* Instruction prefetch written into IL1 */
+#define PM_IC_PREF_WRITE		0x0408e
+/* The data cache was reloaded from local core's L3 due to a demand load */
+#define PM_DATA_FROM_L3			0x4c042
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+#define PM_DATA_FROM_L3MISS		0x300fe
+/* All successful D-side store dispatches for this thread */
+#define PM_L2_ST			0x17080
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+#define PM_L2_ST_MISS			0x17082
+/* Total HW L3 prefetches(Load+store) */
+#define PM_L3_PREF_ALL			0x4e052
+/* Data PTEG reload */
+#define PM_DTLB_MISS			0x300fc
+/* ITLB Reloaded */
+#define PM_ITLB_MISS			0x400fc
+
 
 /*
  * Raw event encoding for POWER8:
@@ -557,6 +588,8 @@ static int power8_generic_events[] = {
 	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BRU_FIN,
 	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1,
 };
 
 static u64 power8_bhrb_filter_map(u64 branch_sample_type)
@@ -596,6 +629,116 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter)
 	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
 }
 
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+			[ C(RESULT_MISS)   ] = PM_LD_MISS_L1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ST_MISS_L1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_PREF,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+			[ C(RESULT_MISS)   ] = PM_L1_ICACHE_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L2_ST,
+			[ C(RESULT_MISS)   ] = PM_L2_ST_MISS,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_DTLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ITLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_BRU_FIN,
+			[ C(RESULT_MISS)   ] = PM_BR_MPRED_CMPL,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
 static struct power_pmu power8_pmu = {
 	.name			= "POWER8",
 	.n_counter		= 6,
@@ -611,6 +754,7 @@ static struct power_pmu power8_pmu = {
 	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
+	.cache_events		= &power8_cache_events,
 	.attr_groups		= power8_pmu_attr_groups,
 	.bhrb_nr		= 32,
 };
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7d6dcc6d5fa9..3b2b4fb3585b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/memblock.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
+	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
 	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
+static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
+				     struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	uint64_t top;
+	bool bypass = false;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return -ENODEV;;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (pe->tce_bypass_enabled) {
+		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		bypass = (dma_mask >= top);
+	}
+
+	if (bypass) {
+		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
+		set_dma_ops(&pdev->dev, &dma_direct_ops);
+		set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	} else {
+		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
+		set_dma_ops(&pdev->dev, &dma_iommu_ops);
+		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	}
+	return 0;
+}
+
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
 	struct pci_dev *dev;
@@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
 }
 
+static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+{
+	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+					      tce32_table);
+	uint16_t window_id = (pe->pe_number << 1 ) + 1;
+	int64_t rc;
+
+	pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
+	if (enable) {
+		phys_addr_t top = memblock_end_of_DRAM();
+
+		top = roundup_pow_of_two(top);
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     top);
+	} else {
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     0);
+
+		/*
+		 * We might want to reset the DMA ops of all devices on
+		 * this PE. However in theory, that shouldn't be necessary
+		 * as this is used for VFIO/KVM pass-through and the device
+		 * hasn't yet been returned to its kernel driver
+		 */
+	}
+	if (rc)
+		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
+	else
+		pe->tce_bypass_enabled = enable;
+}
+
+static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
+					  struct pnv_ioda_pe *pe)
+{
+	/* TVE #1 is selected by PCI address bit 59 */
+	pe->tce_bypass_base = 1ull << 59;
+
+	/* Install set_bypass callback for VFIO */
+	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+
+	/* Enable bypass by default */
+	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+}
+
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe)
 {
@@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
+	/* Also create a bypass window */
+	pnv_pci_ioda2_setup_bypass_pe(phb, pe);
 	return;
 fail:
 	if (pe->tce32_seg >= 0)
@@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b555ebc57ef5..95633d79ef5d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -634,6 +634,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb && phb->dma_set_mask)
+		return phb->dma_set_mask(phb, pdev, dma_mask);
+	return __dma_set_mask(&pdev->dev, dma_mask);
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 13f1942a9a5f..cde169442775 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -54,7 +54,9 @@ struct pnv_ioda_pe {
 	struct iommu_table	tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
-	/* XXX TODO: Add support for additional 64-bit iommus */
+	/* 64-bit TCE bypass region */
+	bool			tce_bypass_enabled;
+	uint64_t		tce_bypass_base;
 
 	/* MSIs. MVE index is identical for for 32 and 64 bit MSI
 	 * and -1 if not supported. (It's actually identical to the
@@ -113,6 +115,8 @@ struct pnv_phb {
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
+			    u64 dma_mask);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index de6819be1f95..0051e108ef0f 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,12 +7,20 @@ extern void pnv_smp_init(void);
 static inline void pnv_smp_init(void) { }
 #endif
 
+struct pci_dev;
+
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
+extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
+
+static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	return -ENODEV;
+}
 #endif
 
 extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f65c97c..110f4fbd319f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/bug.h>
 #include <linux/cpuidle.h>
+#include <linux/pci.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -141,6 +142,13 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
+static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (dev_is_pci(dev))
+		return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
+
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -238,6 +246,7 @@ define_machine(powernv) {
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = powernv_idle,
 	.calibrate_decr		= generic_calibrate_decr,
+	.dma_set_mask		= pnv_dma_set_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 37300f6ee244..80b1d57c306a 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -20,6 +20,7 @@ config PPC_PSERIES
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
 	select HOTPLUG_CPU if SMP
+	select ARCH_RANDOM
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 8e639d7cbda7..972df0ffd4dc 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -430,8 +430,7 @@ static void pSeries_machine_kexec(struct kimage *image)
 {
 	long rc;
 
-	if (firmware_has_feature(FW_FEATURE_SET_MODE) &&
-	    (image->type != KEXEC_TYPE_CRASH)) {
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		rc = pSeries_disable_reloc_on_exc();
 		if (rc != H_SUCCESS)
 			pr_warning("Warning: Failed to disable relocation on "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0e166ed4cd16..8209744b2829 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -886,25 +886,25 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 
 	/* Default: read HW settings */
 	if (flow_type == IRQ_TYPE_DEFAULT) {
-		switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
-			       MPIC_INFO(VECPRI_SENSE_MASK))) {
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_EDGE_RISING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_EDGE_FALLING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_LEVEL_HIGH;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_LEVEL_LOW;
-				break;
-		}
+		int vold_ps;
+
+		vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
+				  MPIC_INFO(VECPRI_SENSE_MASK));
+
+		if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_EDGE_RISING;
+		else if	(vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_EDGE_FALLING;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_LEVEL_HIGH;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_LEVEL_LOW;
+		else
+			WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold);
 	}
 
 	/* Apply to irq desc */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a90731b3d44a..b07909850f77 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -309,16 +309,23 @@ static void get_output_lock(void)
 
 	if (xmon_speaker == me)
 		return;
+
 	for (;;) {
-		if (xmon_speaker == 0) {
-			last_speaker = cmpxchg(&xmon_speaker, 0, me);
-			if (last_speaker == 0)
-				return;
-		}
-		timeout = 10000000;
+		last_speaker = cmpxchg(&xmon_speaker, 0, me);
+		if (last_speaker == 0)
+			return;
+
+		/*
+		 * Wait a full second for the lock, we might be on a slow
+		 * console, but check every 100us.
+		 */
+		timeout = 10000;
 		while (xmon_speaker == last_speaker) {
-			if (--timeout > 0)
+			if (--timeout > 0) {
+				udelay(100);
 				continue;
+			}
+
 			/* hostile takeover */
 			prev = cmpxchg(&xmon_speaker, last_speaker, me);
 			if (prev == last_speaker)
@@ -397,7 +404,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 	}
 
 	xmon_fault_jmp[cpu] = recurse_jmp;
-	cpumask_set_cpu(cpu, &cpus_in_xmon);
 
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
@@ -419,6 +425,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		release_output_lock();
 	}
 
+	cpumask_set_cpu(cpu, &cpus_in_xmon);
+
  waiting:
 	secondary = 1;
 	while (secondary && !xmon_gate) {
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 4c4a1cef5208..47c8630c93cd 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -529,6 +529,7 @@ static int __init appldata_init(void)
 {
 	int rc;
 
+	init_virt_timer(&appldata_timer);
 	appldata_timer.function = appldata_timer_function;
 	appldata_timer.data = (unsigned long) &appldata_work;
 
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b3feabd39f31..cf3c0089bef2 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/spinlock.h>
 #include "crypt_s390.h"
 
 #define AES_KEYLEN_128		1
@@ -32,6 +33,7 @@
 #define AES_KEYLEN_256		4
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 static char keylen_flag;
 
 struct s390_aes_ctx {
@@ -758,43 +760,67 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return aes_set_key(tfm, in_key, key_len);
 }
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* only use complete blocks, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+	for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE,
+		       AES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, AES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 			 struct s390_aes_ctx *sctx, struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[AES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
 
 	if (!walk->nbytes)
 		return ret;
 
-	memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= AES_BLOCK_SIZE) {
-			/* only use complete blocks, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-						 nbytes & ~(AES_BLOCK_SIZE - 1);
-			for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE,
-				       AES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = AES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, sctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > AES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
-			crypto_inc(ctrblk, AES_BLOCK_SIZE);
+			crypto_inc(ctrptr, AES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	}
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
@@ -802,14 +828,15 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, sctx->key, buf, in,
-				       AES_BLOCK_SIZE, ctrblk);
+				       AES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != AES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, AES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, AES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE);
+
 	return ret;
 }
 
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 200f2a1b599d..0a5aac8a9412 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -25,6 +25,7 @@
 #define DES3_KEY_SIZE	(3 * DES_KEY_SIZE)
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 
 struct s390_des_ctx {
 	u8 iv[DES_BLOCK_SIZE];
@@ -105,29 +106,35 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func,
 }
 
 static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
-			    u8 *iv, struct blkcipher_walk *walk)
+			    struct blkcipher_walk *walk)
 {
+	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	int ret = blkcipher_walk_virt(desc, walk);
 	unsigned int nbytes = walk->nbytes;
+	struct {
+		u8 iv[DES_BLOCK_SIZE];
+		u8 key[DES3_KEY_SIZE];
+	} param;
 
 	if (!nbytes)
 		goto out;
 
-	memcpy(iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.key, ctx->key, DES3_KEY_SIZE);
 	do {
 		/* only use complete blocks */
 		unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1);
 		u8 *out = walk->dst.virt.addr;
 		u8 *in = walk->src.virt.addr;
 
-		ret = crypt_s390_kmc(func, iv, out, in, n);
+		ret = crypt_s390_kmc(func, &param, out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
 		nbytes &= DES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	} while ((nbytes = walk->nbytes));
-	memcpy(walk->iv, iv, DES_BLOCK_SIZE);
+	memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
 
 out:
 	return ret;
@@ -179,22 +186,20 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk);
 }
 
 static int cbc_des_decrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des_alg = {
@@ -327,22 +332,20 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk);
 }
 
 static int cbc_des3_decrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des3_alg = {
@@ -366,54 +369,80 @@ static struct crypto_alg cbc_des3_alg = {
 	}
 };
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* align to block size, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1);
+	for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, DES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
-			    struct s390_des_ctx *ctx, struct blkcipher_walk *walk)
+			    struct s390_des_ctx *ctx,
+			    struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[DES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
+
+	if (!walk->nbytes)
+		return ret;
 
-	memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= DES_BLOCK_SIZE) {
-			/* align to block size, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-				nbytes & ~(DES_BLOCK_SIZE - 1);
-			for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE,
-				       DES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = DES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, ctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > DES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE,
 				       DES_BLOCK_SIZE);
-			crypto_inc(ctrblk, DES_BLOCK_SIZE);
+			crypto_inc(ctrptr, DES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
-
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	}
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, ctx->key, buf, in,
-				       DES_BLOCK_SIZE, ctrblk);
+				       DES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != DES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, DES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, DES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE);
 	return ret;
 }
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae2579c..d7c00507568a 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@ ENTRY(startup_continue)
 	.quad	0			# cr12: tracing off
 	.quad	0			# cr13: home space segment table
 	.quad	0xc0000000		# cr14: machine check handling off
-	.quad	0			# cr15: linkage stack operations
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
 .Lpcmsk:.quad	0x0000000180000000
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
@@ -67,12 +67,15 @@ ENTRY(startup_continue)
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
-.Lduct: .long	0,0,0,0,.Lduald,0,0,0
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
 	.long	0,0,0,0,0,0,0,0
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
 	.align	128
 .Lduald:.rept	8
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 
 ENTRY(_ehead)
 
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e9dfb0..27c50f4d90cb 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
 
 #define ESSA_SET_STABLE		1
 #define ESSA_SET_UNUSED		2
@@ -41,6 +43,14 @@ void __init cmma_init(void)
 
 	if (!cmma_flag)
 		return;
+	/*
+	 * Disable CMM for dump, otherwise  the tprot based memory
+	 * detection can fail because of unstable pages.
+	 */
+	if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+		cmma_flag = 0;
+		return;
+	}
 	asm volatile(
 		"       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
 		"0:     la      %0,0\n"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 940e50ebfafa..0af5250d914f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -444,6 +444,7 @@ config X86_INTEL_MID
 	bool "Intel MID platform support"
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
 	depends on PCI
 	depends on PCI_GOANY
 	depends on X86_IO_APIC
@@ -1051,9 +1052,9 @@ config MICROCODE_INTEL
 	  This options enables microcode patch loading support for Intel
 	  processors.
 
-	  For latest news and information on obtaining all the required
-	  Intel ingredients for this driver, check:
-	  <http://www.urbanmyth.org/microcode/>.
+	  For the current Intel microcode data package go to
+	  <https://downloadcenter.intel.com> and search for
+	  'Linux Processor Microcode Data File'.
 
 config MICROCODE_AMD
 	bool "AMD microcode loading support"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 0f3621ed1db6..321a52ccf63a 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -184,6 +184,7 @@ config HAVE_MMIOTRACE_SUPPORT
 config X86_DECODER_SELFTEST
 	bool "x86 instruction decoder selftest"
 	depends on DEBUG_KERNEL && KPROBES
+	depends on !COMPILE_TEST
 	---help---
 	 Perform x86 instruction decoder selftests at build time.
 	 This option is useful for checking the sanity of x86 instruction
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index a54ee1d054d9..aaac3b2fb746 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
 extern int amd_numa_init(void);
 extern int amd_get_subcaches(int);
-extern int amd_set_subcaches(int, int);
+extern int amd_set_subcaches(int, unsigned long);
 
 struct amd_l3_cache {
 	unsigned indices;
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3b978c472d08..3d6b9f81cc68 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -132,6 +132,8 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
 extern void efi_setup_page_tables(void);
 extern void __init old_map_region(efi_memory_desc_t *md);
+extern void __init runtime_code_page_mkexec(void);
+extern void __init efi_runtime_mkexec(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index bbc8b12fa443..5ad38ad07890 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -445,10 +445,20 @@ static inline int pte_same(pte_t a, pte_t b)
 	return a.pte == b.pte;
 }
 
+static inline int pteval_present(pteval_t pteval)
+{
+	/*
+	 * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this
+	 * way clearly states that the intent is that protnone and numa
+	 * hinting ptes are considered present for the purposes of
+	 * pagetable operations like zapping, protection changes, gup etc.
+	 */
+	return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA);
+}
+
 static inline int pte_present(pte_t a)
 {
-	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
-			       _PAGE_NUMA);
+	return pteval_present(pte_flags(a));
 }
 
 #define pte_accessible pte_accessible
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e6d90babc245..04905bfc508b 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr)
  */
 static inline void __flush_tlb_up(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 }
 
 static inline void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb_all();
 }
 
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 787e1bb5aafc..3e276eb23d1b 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -52,8 +52,7 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 extern int m2p_add_override(unsigned long mfn, struct page *page,
 			    struct gnttab_map_grant_ref *kmap_op);
 extern int m2p_remove_override(struct page *page,
-			       struct gnttab_map_grant_ref *kmap_op,
-			       unsigned long mfn);
+				struct gnttab_map_grant_ref *kmap_op);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
@@ -122,7 +121,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 		pfn = m2p_find_override_pfn(mfn, ~0);
 	}
 
-	/*
+	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
 	 * entry doesn't map back to the mfn and m2p_override doesn't have a
 	 * valid entry for it.
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 59554dca96ec..dec8de4e1663 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -179,7 +179,7 @@ int amd_get_subcaches(int cpu)
 	return (mask >> (4 * cuid)) & 0xf;
 }
 
-int amd_set_subcaches(int cpu, int mask)
+int amd_set_subcaches(int cpu, unsigned long mask)
 {
 	static unsigned int reset, ban;
 	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d3153e281d72..c67ffa686064 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -767,10 +767,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 
 static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
 {
-	tlb_flushall_shift = 5;
-
-	if (c->x86 <= 0x11)
-		tlb_flushall_shift = 4;
+	tlb_flushall_shift = 6;
 }
 
 static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 24b6fd10625a..8e28bf2fc3ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
-	if (cpu_has(c, X86_FEATURE_SMAP))
+	if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
 		set_in_cr4(X86_CR4_SMAP);
+#else
+		clear_in_cr4(X86_CR4_SMAP);
+#endif
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3db61c644e44..5cd9bfabd645 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -640,21 +640,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
 	case 0x61d: /* six-core 45 nm xeon "Dunnington" */
 		tlb_flushall_shift = -1;
 		break;
+	case 0x63a: /* Ivybridge */
+		tlb_flushall_shift = 2;
+		break;
 	case 0x61a: /* 45 nm nehalem, "Bloomfield" */
 	case 0x61e: /* 45 nm nehalem, "Lynnfield" */
 	case 0x625: /* 32 nm nehalem, "Clarkdale" */
 	case 0x62c: /* 32 nm nehalem, "Gulftown" */
 	case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
 	case 0x62f: /* 32 nm Xeon E7 */
-		tlb_flushall_shift = 6;
-		break;
 	case 0x62a: /* SandyBridge */
 	case 0x62d: /* SandyBridge, "Romely-EP" */
-		tlb_flushall_shift = 5;
-		break;
-	case 0x63a: /* Ivybridge */
-		tlb_flushall_shift = 1;
-		break;
 	default:
 		tlb_flushall_shift = 6;
 	}
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 8384c0fa206f..617a9e284245 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
 
 	uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
+
+static void __init get_bsp_sig(void)
+{
+	unsigned int bsp = boot_cpu_data.cpu_index;
+	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+
+	if (!uci->cpu_sig.sig)
+		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+}
 #else
 void load_ucode_amd_ap(void)
 {
@@ -337,31 +346,37 @@ void load_ucode_amd_ap(void)
 
 int __init save_microcode_in_initrd_amd(void)
 {
+	unsigned long cont;
 	enum ucode_state ret;
 	u32 eax;
 
-#ifdef CONFIG_X86_32
-	unsigned int bsp = boot_cpu_data.cpu_index;
-	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
-
-	if (!uci->cpu_sig.sig)
-		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+	if (!container)
+		return -EINVAL;
 
+#ifdef CONFIG_X86_32
+	get_bsp_sig();
+	cont = (unsigned long)container;
+#else
 	/*
-	 * Take into account the fact that the ramdisk might get relocated
-	 * and therefore we need to recompute the container's position in
-	 * virtual memory space.
+	 * We need the physical address of the container for both bitness since
+	 * boot_params.hdr.ramdisk_image is a physical address.
 	 */
-	container = (u8 *)(__va((u32)relocated_ramdisk) +
-			   ((u32)container - boot_params.hdr.ramdisk_image));
+	cont = __pa(container);
 #endif
+
+	/*
+	 * Take into account the fact that the ramdisk might get relocated and
+	 * therefore we need to recompute the container's position in virtual
+	 * memory space.
+	 */
+	if (relocated_ramdisk)
+		container = (u8 *)(__va(relocated_ramdisk) +
+			     (cont - boot_params.hdr.ramdisk_image));
+
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
 			ucode_new_rev);
 
-	if (!container)
-		return -EINVAL;
-
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ce2d0a2c3e4f..0e25a1bc5ab5 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d4bdd253fea7..e6253195a301 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa_symbol(ip));
 
-	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+	return ip;
 }
 
 static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
+	ip = text_ip_addr(ip);
+
 	/* replace the text with the new text */
-	if (do_ftrace_mod_code(ip, new_code))
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	sync_core();
@@ -221,37 +222,51 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 	return -EINVAL;
 }
 
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
 {
-	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	unsigned char old[MCOUNT_INSN_SIZE];
 	int ret;
 
-	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, (unsigned long)func);
+	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+	ftrace_update_func = ip;
+	/* Make sure the breakpoints see the ftrace_update_func update */
+	smp_wmb();
 
 	/* See comment above by declaration of modifying_ftrace_code */
 	atomic_inc(&modifying_ftrace_code);
 
 	ret = ftrace_modify_code(ip, old, new);
 
+	atomic_dec(&modifying_ftrace_code);
+
+	return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char *new;
+	int ret;
+
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
 	/* Also update the regs callback function */
 	if (!ret) {
 		ip = (unsigned long)(&ftrace_regs_call);
-		memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(ip, (unsigned long)func);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = update_ftrace_func(ip, new);
 	}
 
-	atomic_dec(&modifying_ftrace_code);
-
 	return ret;
 }
 
 static int is_ftrace_caller(unsigned long ip)
 {
-	if (ip == (unsigned long)(&ftrace_call) ||
-		ip == (unsigned long)(&ftrace_regs_call))
+	if (ip == ftrace_update_func)
 		return 1;
 
 	return 0;
@@ -677,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data)
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
 
-static int ftrace_mod_jmp(unsigned long ip,
-			  int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
-	unsigned char code[MCOUNT_INSN_SIZE];
+	static union ftrace_code_union calc;
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	/* Jmp not a call (ignore the .e8) */
+	calc.e8		= 0xe9;
+	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
 
-	if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
-		return -EINVAL;
+	/*
+	 * ftrace external locks synchronize the access to the static variable.
+	 */
+	return calc.code;
+}
 
-	*(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+	unsigned char *new;
 
-	if (do_ftrace_mod_code(ip, &code))
-		return -EPERM;
+	new = ftrace_jmp_replace(ip, (unsigned long)func);
 
-	return 0;
+	return update_ftrace_func(ip, new);
 }
 
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
 
-	old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_graph_caller);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
-
-	old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
 
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
 
 #endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index dbb60878b744..d99f31d9a750 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -266,6 +266,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
+ * below, which is protected by stop_machine().  Putting them on the stack
+ * results in a stack frame overflow.  Dynamically allocating could result in a
+ * failure so declare these two cpumasks as global.
+ */
+static struct cpumask affinity_new, online_new;
+
 /*
  * This cpu is going to be removed and its vectors migrated to the remaining
  * online cpus.  Check to see if there are enough vectors in the remaining cpus.
@@ -277,7 +285,6 @@ int check_irq_vectors_for_cpu_disable(void)
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
-	struct cpumask affinity_new, online_new;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2e4c02..7c6acd4b8995 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
 			quirk_amd_nb_node);
 
 #endif
+
+#ifdef CONFIG_PCI
+/*
+ * Processor does not ensure DRAM scrub read/write sequence
+ * is atomic wrt accesses to CC6 save state area. Therefore
+ * if a concurrent scrub read/write access is to same address
+ * the entry may appear as if it is not written. This quirk
+ * applies to Fam16h models 00h-0Fh
+ *
+ * See "Revision Guide" for AMD F16h models 00h-0fh,
+ * document 51810 rev. 3.04, Nov 2013
+ */
+static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
+{
+	u32 val;
+
+	/*
+	 * Suggested workaround:
+	 * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b
+	 */
+	pci_read_config_dword(dev, 0x58, &val);
+	if (val & 0x1F) {
+		val &= ~(0x1F);
+		pci_write_config_dword(dev, 0x58, val);
+	}
+
+	pci_read_config_dword(dev, 0x5C, &val);
+	if (val & BIT(0)) {
+		val &= ~BIT(0);
+		pci_write_config_dword(dev, 0x5c, val);
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
+			amd_disable_seq_and_redirect_scrub);
+
+#endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19e5adb49a27..acb3b606613e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -209,7 +209,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	 * dance when its actually needed.
 	 */
 
-	preempt_disable();
+	preempt_disable_notrace();
 	data = this_cpu_read(cyc2ns.head);
 	tail = this_cpu_read(cyc2ns.tail);
 
@@ -229,7 +229,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 		if (!--data->__count)
 			this_cpu_write(cyc2ns.tail, data);
 	}
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return ns;
 }
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index aaa60f347b73..f5704d9e5ddc 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1e91a246e996..a45bcac45645 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6225,7 +6225,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		frag->len -= len;
 	}
 
-	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 
 		/* FIXME: return into emulator if single-stepping.  */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d591c895803..6dea040cc3a1 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1001,6 +1001,12 @@ static int fault_in_kernel_space(unsigned long address)
 
 static inline bool smap_violation(int error_code, struct pt_regs *regs)
 {
+	if (!IS_ENABLED(CONFIG_X86_SMAP))
+		return false;
+
+	if (!static_cpu_has(X86_FEATURE_SMAP))
+		return false;
+
 	if (error_code & PF_USER)
 		return false;
 
@@ -1087,11 +1093,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
+	if (unlikely(smap_violation(error_code, regs))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
 	/*
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 81b2750f3666..27aa0455fab3 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -493,14 +493,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 		struct numa_memblk *mb = &mi->blk[i];
 		memblock_set_node(mb->start, mb->end - mb->start,
 				  &memblock.memory, mb->nid);
-
-		/*
-		 * At this time, all memory regions reserved by memblock are
-		 * used by the kernel. Set the nid in memblock.reserved will
-		 * mark out all the nodes the kernel resides in.
-		 */
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
 	}
 
 	/*
@@ -565,10 +557,21 @@ static void __init numa_init_array(void)
 static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
-	nodemask_t numa_kernel_nodes;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
 	unsigned long start, end;
 	struct memblock_type *type = &memblock.reserved;
 
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
 	/* Mark all kernel nodes. */
 	for (i = 0; i < type->cnt; i++)
 		node_set(type->regions[i].nid, numa_kernel_nodes);
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 0342d27ca798..47b6436e41c2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 			nid, start, end);
 	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
 	printk(KERN_DEBUG "  ");
+	start = round_down(start, PAGES_PER_SECTION);
+	end = round_up(end, PAGES_PER_SECTION);
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
 		physnode_map[pfn / PAGES_PER_SECTION] = nid;
 		printk(KERN_CONT "%lx ", pfn);
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1a25187e151e..1953e9c9391a 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,15 +42,25 @@ static __init inline int srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-/* Callback for SLIT parsing */
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
 	int i, j;
 
-	for (i = 0; i < slit->locality_count; i++)
-		for (j = 0; j < slit->locality_count; j++)
+	for (i = 0; i < slit->locality_count; i++) {
+		if (pxm_to_node(i) == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < slit->locality_count; j++) {
+			if (pxm_to_node(j) == NUMA_NO_NODE)
+				continue;
 			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
 				slit->entry[slit->locality_count * i + j]);
+		}
+	}
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3bbac8..dd8dda167a24 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@ static void flush_tlb_func(void *info)
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,44 +151,19 @@ void flush_tlb_current_task(void)
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-/*
- * It can find out the THP large page, or
- * HUGETLB page in tlb_flush when THP disabled
- */
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	unsigned long addr = ALIGN(start, HPAGE_SIZE);
-	for (; addr < end; addr += HPAGE_SIZE) {
-		pgd = pgd_offset(mm, addr);
-		if (likely(!pgd_none(*pgd))) {
-			pud = pud_offset(pgd, addr);
-			if (likely(!pud_none(*pud))) {
-				pmd = pmd_offset(pud, addr);
-				if (likely(!pmd_none(*pmd)))
-					if (pmd_large(*pmd))
-						return addr;
-			}
-		}
-	}
-	return 0;
-}
-
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
 	unsigned long addr;
 	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
 
 	preempt_disable();
 	if (current->active_mm != mm)
@@ -210,21 +185,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		tlb_entries = tlb_lli_4k[ENTRIES];
 	else
 		tlb_entries = tlb_lld_4k[ENTRIES];
+
 	/* Assume all of TLB entries was occupied by this task */
-	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	if (nr_base_pages > act_entries) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-		if (has_large_page(mm, start, end)) {
-			local_flush_tlb();
-			goto flush_all;
-		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,7 +236,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -270,7 +244,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 7145ec63c520..f15103dff4b4 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -42,14 +42,15 @@ void __init efi_bgrt_init(void)
 
 	if (bgrt_tab->header.length < sizeof(*bgrt_tab))
 		return;
-	if (bgrt_tab->version != 1)
+	if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
 		return;
 	if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
 		return;
 
 	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
 	if (!image) {
-		image = ioremap(bgrt_tab->image_address, sizeof(bmp_header));
+		image = early_memremap(bgrt_tab->image_address,
+				       sizeof(bmp_header));
 		ioremapped = true;
 		if (!image)
 			return;
@@ -57,7 +58,7 @@ void __init efi_bgrt_init(void)
 
 	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
 	if (ioremapped)
-		iounmap(image);
+		early_iounmap(image, sizeof(bmp_header));
 	bgrt_image_size = bmp_header.size;
 
 	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL);
@@ -65,7 +66,8 @@ void __init efi_bgrt_init(void)
 		return;
 
 	if (ioremapped) {
-		image = ioremap(bgrt_tab->image_address, bmp_header.size);
+		image = early_memremap(bgrt_tab->image_address,
+				       bmp_header.size);
 		if (!image) {
 			kfree(bgrt_image);
 			bgrt_image = NULL;
@@ -75,5 +77,5 @@ void __init efi_bgrt_init(void)
 
 	memcpy_fromio(bgrt_image, image, bgrt_image_size);
 	if (ioremapped)
-		iounmap(image);
+		early_iounmap(image, bmp_header.size);
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d62ec87a2b26..1a201ac7cef8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -792,7 +792,7 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
 		set_memory_nx(addr, npages);
 }
 
-static void __init runtime_code_page_mkexec(void)
+void __init runtime_code_page_mkexec(void)
 {
 	efi_memory_desc_t *md;
 	void *p;
@@ -1069,8 +1069,7 @@ void __init efi_enter_virtual_mode(void)
 	efi.update_capsule = virt_efi_update_capsule;
 	efi.query_capsule_caps = virt_efi_query_capsule_caps;
 
-	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
-		runtime_code_page_mkexec();
+	efi_runtime_mkexec();
 
 	kfree(new_memmap);
 
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 249b183cf417..0b74cdf7f816 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -77,3 +77,9 @@ void efi_call_phys_epilog(void)
 
 	local_irq_restore(efi_rt_eflags);
 }
+
+void __init efi_runtime_mkexec(void)
+{
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6284f158a47d..0c2a234fef1e 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -233,3 +233,12 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 {
 	efi_setup = phys_addr + sizeof(struct setup_data);
 }
+
+void __init efi_runtime_mkexec(void)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a4d7b647867f..201d09a7c46b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1473,6 +1473,18 @@ static void xen_pvh_set_cr_flags(int cpu)
 	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
 	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
 	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
+
+	if (!cpu)
+		return;
+	/*
+	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
+	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+	*/
+	if (cpu_has_pse)
+		set_in_cr4(X86_CR4_PSE);
+
+	if (cpu_has_pge)
+		set_in_cr4(X86_CR4_PGE);
 }
 
 /*
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2423ef04ffea..256282e7888b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 /* Assume pteval_t is equivalent to all the other *val_t types. */
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
-	if (val & _PAGE_PRESENT) {
+	if (pteval_present(val)) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		unsigned long pfn = mfn_to_pfn(mfn);
 
@@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 
 static pteval_t pte_pfn_to_mfn(pteval_t val)
 {
-	if (val & _PAGE_PRESENT) {
+	if (pteval_present(val)) {
 		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & PTE_FLAGS_MASK;
 		unsigned long mfn;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8009acbe41e4..696c694986d0 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -899,6 +899,13 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 					"m2p_add_override: pfn %lx not mapped", pfn))
 			return -EINVAL;
 	}
+	WARN_ON(PagePrivate(page));
+	SetPagePrivate(page);
+	set_page_private(page, mfn);
+	page->index = pfn_to_mfn(pfn);
+
+	if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
+		return -ENOMEM;
 
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
@@ -937,16 +944,19 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
 int m2p_remove_override(struct page *page,
-			struct gnttab_map_grant_ref *kmap_op,
-			unsigned long mfn)
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
+	unsigned long mfn;
 	unsigned long pfn;
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
 
 	pfn = page_to_pfn(page);
+	mfn = get_phys_to_machine(pfn);
+	if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT))
+		return -EINVAL;
 
 	if (!PageHighMem(page)) {
 		address = (unsigned long)__va(pfn << PAGE_SHIFT);
@@ -960,7 +970,10 @@ int m2p_remove_override(struct page *page,
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_del(&page->lru);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
+	WARN_ON(!PagePrivate(page));
+	ClearPagePrivate(page);
 
+	set_phys_to_machine(pfn, page->index);
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;