Merge branch 'linux-linaro-lsk-v4.4' into linux-linaro-lsk-v4.4-android

30 files changed, 376 insertions, 182 deletions

diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index a633be3defda..cd316021d6ce 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -303,16 +303,6 @@
 		gpio = <&expander0 4 GPIO_ACTIVE_HIGH>;
 	};
 
-	reg_usb2_1_vbus: v5-vbus1 {
-		compatible = "regulator-fixed";
-		regulator-name = "v5.0-vbus1";
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		enable-active-high;
-		regulator-always-on;
-		gpio = <&expander0 4 GPIO_ACTIVE_HIGH>;
-	};
-
 	reg_sata0: pwr-sata0 {
 		compatible = "regulator-fixed";
 		regulator-name = "pwr_en_sata0";
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 131614f28e75..569026e8f96c 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -86,10 +86,12 @@
 			macb0: ethernet@f8020000 {
 				phy-mode = "rmii";
 				status = "okay";
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>;
 
 				phy0: ethernet-phy@1 {
 					interrupt-parent = <&pioE>;
-					interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 					reg = <1>;
 				};
 			};
@@ -152,6 +154,10 @@
 						atmel,pins =
 							<AT91_PIOE 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
 					};
+					pinctrl_macb0_phy_irq: macb0_phy_irq_0 {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
 				};
 			};
 		};
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 2d4a33100af6..4e98cda97403 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -160,8 +160,15 @@
 			};
 
 			macb0: ethernet@f8020000 {
+				pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>;
 				phy-mode = "rmii";
 				status = "okay";
+
+				ethernet-phy@1 {
+					reg = <0x1>;
+					interrupt-parent = <&pioE>;
+					interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
+				};
 			};
 
 			mmc1: mmc@fc000000 {
@@ -193,6 +200,10 @@
 
 			pinctrl@fc06a000 {
 				board {
+					pinctrl_macb0_phy_irq: macb0_phy_irq {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>;
+					};
 					pinctrl_mmc0_cd: mmc0_cd {
 						atmel,pins =
 							<AT91_PIOE 5 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 36387b11451d..80f6c786a37e 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -122,6 +122,7 @@
 		interrupt-parent = <&gpio5>;
 		interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */
 		ref-clock-frequency = <26000000>;
+		tcxo-clock-frequency = <26000000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 5cf76a1c5c75..41e80e7f20be 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -130,6 +130,16 @@
 	};
 };
 
+&gpio8 {
+	/* TI trees use GPIO instead of msecure, see also muxing */
+	p234 {
+		gpio-hog;
+		gpios = <10 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "gpio8_234/msecure";
+	};
+};
+
 &omap5_pmx_core {
 	pinctrl-names = "default";
 	pinctrl-0 = <
@@ -213,6 +223,13 @@
 		>;
 	};
 
+	/* TI trees use GPIO mode; msecure mode does not work reliably? */
+	palmas_msecure_pins: palmas_msecure_pins {
+		pinctrl-single,pins = <
+			OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */
+		>;
+	};
+
 	usbhost_pins: pinmux_usbhost_pins {
 		pinctrl-single,pins = <
 			0x84 (PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */
@@ -278,6 +295,12 @@
 			&usbhost_wkup_pins
 	>;
 
+	palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins {
+		pinctrl-single,pins = <
+			OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */
+		>;
+	};
+
 	usbhost_wkup_pins: pinmux_usbhost_wkup_pins {
 		pinctrl-single,pins = <
 			0x1A (PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */
@@ -345,6 +368,8 @@
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>;
 
 		extcon_usb3: palmas_usb {
 			compatible = "ti,palmas-usb-vid";
@@ -358,6 +383,14 @@
 			#clock-cells = <0>;
 		};
 
+		rtc {
+			compatible = "ti,palmas-rtc";
+			interrupt-parent = <&palmas>;
+			interrupts = <8 IRQ_TYPE_NONE>;
+			ti,backup-battery-chargeable;
+			ti,backup-battery-charge-high-current;
+		};
+
 		palmas_pmic {
 			compatible = "ti,palmas-pmic";
 			interrupt-parent = <&palmas>;
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 2193637b9cd2..3daf8d5d7878 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -1342,7 +1342,7 @@
 			dbgu: serial@fc069000 {
 				compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart";
 				reg = <0xfc069000 0x200>;
-				interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>;
+				interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>;
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_dbgu>;
 				clocks = <&dbgu_clk>;
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index d0c743853318..27a333eb8987 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -127,22 +127,14 @@
 			};
 			mmcsd_default_mode: mmcsd_default {
 				mmcsd_default_cfg1 {
-					/* MCCLK */
-					pins = "GPIO8_B10";
-					ste,output = <0>;
-				};
-				mmcsd_default_cfg2 {
-					/* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */
-					pins = "GPIO10_C11", "GPIO15_A12",
-					"GPIO16_C13", "GPIO23_D15";
-					ste,output = <1>;
-				};
-				mmcsd_default_cfg3 {
-					/* MCCMD, MCDAT3-0, MCMSFBCLK */
-					pins = "GPIO9_A10", "GPIO11_B11",
-					"GPIO12_A11", "GPIO13_C12",
-					"GPIO14_B12", "GPIO24_C15";
-					ste,input = <1>;
+					/*
+					 * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2
+					 * MCCMD, MCDAT3-0, MCMSFBCLK
+					 */
+					pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11",
+					       "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12",
+					       "GPIO16_C13", "GPIO23_D15", "GPIO24_C15";
+					ste,output = <2>;
 				};
 			};
 		};
@@ -802,10 +794,21 @@
 			clock-names = "mclk", "apb_pclk";
 			interrupt-parent = <&vica>;
 			interrupts = <22>;
-			max-frequency = <48000000>;
+			max-frequency = <400000>;
 			bus-width = <4>;
 			cap-mmc-highspeed;
 			cap-sd-highspeed;
+			full-pwr-cycle;
+			/*
+			 * The STw4811 circuit used with the Nomadik strictly
+			 * requires that all of these signal direction pins be
+			 * routed and used for its 4-bit levelshifter.
+			 */
+			st,sig-dir-dat0;
+			st,sig-dir-dat2;
+			st,sig-dir-dat31;
+			st,sig-dir-cmd;
+			st,sig-pin-fbclk;
 			pinctrl-names = "default";
 			pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>;
 			vmmc-supply = <&vmmc_regulator>;
diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c
index 2dc6da70ae59..d7ed252708c5 100644
--- a/arch/arm/common/icst.c
+++ b/arch/arm/common/icst.c
@@ -16,7 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-
+#include <asm/div64.h>
 #include <asm/hardware/icst.h>
 
 /*
@@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div);
 
 unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco)
 {
-	return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]);
+	u64 dividend = p->ref * 2 * (u64)(vco.v + 8);
+	u32 divisor = (vco.r + 2) * p->s2div[vco.s];
+
+	do_div(dividend, divisor);
+	return (unsigned long)dividend;
 }
 
 EXPORT_SYMBOL(icst_hz);
@@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq)
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index eafd120b53f1..1b9f0520dea9 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -86,13 +86,18 @@ ENTRY(enable_omap3630_toggle_l2_on_restore)
 	stmfd	sp!, {lr}	@ save registers on stack
 	/* Setup so that we will disable and enable l2 */
 	mov	r1, #0x1
-	adrl	r2, l2dis_3630	@ may be too distant for plain adr
-	str	r1, [r2]
+	adrl	r3, l2dis_3630_offset	@ may be too distant for plain adr
+	ldr	r2, [r3]		@ value for offset
+	str	r1, [r2, r3]		@ write to l2dis_3630
 	ldmfd	sp!, {pc}	@ restore regs and return
 ENDPROC(enable_omap3630_toggle_l2_on_restore)
 
-	.text
-/* Function to call rom code to save secure ram context */
+/*
+ * Function to call rom code to save secure ram context. This gets
+ * relocated to SRAM, so it can be all in .data section. Otherwise
+ * we need to initialize api_params separately.
+ */
+	.data
 	.align	3
 ENTRY(save_secure_ram_context)
 	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
@@ -126,6 +131,8 @@ ENDPROC(save_secure_ram_context)
 ENTRY(save_secure_ram_context_sz)
 	.word	. - save_secure_ram_context
 
+	.text
+
 /*
  * ======================
  * == Idle entry point ==
@@ -289,12 +296,6 @@ wait_sdrc_ready:
 	bic	r5, r5, #0x40
 	str	r5, [r4]
 
-/*
- * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a
- * base instead.
- * Be careful not to clobber r7 when maintaing this code.
- */
-
 is_dll_in_lock_mode:
 	/* Is dll in lock mode? */
 	ldr	r4, sdrc_dlla_ctrl
@@ -302,11 +303,7 @@ is_dll_in_lock_mode:
 	tst	r5, #0x4
 	bne	exit_nonoff_modes	@ Return if locked
 	/* wait till dll locks */
-	adr	r7, kick_counter
 wait_dll_lock_timed:
-	ldr	r4, wait_dll_lock_counter
-	add	r4, r4, #1
-	str	r4, [r7, #wait_dll_lock_counter - kick_counter]
 	ldr	r4, sdrc_dlla_status
 	/* Wait 20uS for lock */
 	mov	r6, #8
@@ -330,9 +327,6 @@ kick_dll:
 	orr	r6, r6, #(1<<3)		@ enable dll
 	str	r6, [r4]
 	dsb
-	ldr	r4, kick_counter
-	add	r4, r4, #1
-	str	r4, [r7]		@ kick_counter
 	b	wait_dll_lock_timed
 
 exit_nonoff_modes:
@@ -360,15 +354,6 @@ sdrc_dlla_status:
 	.word	SDRC_DLLA_STATUS_V
 sdrc_dlla_ctrl:
 	.word	SDRC_DLLA_CTRL_V
-	/*
-	 * When exporting to userspace while the counters are in SRAM,
-	 * these 2 words need to be at the end to facilitate retrival!
-	 */
-kick_counter:
-	.word	0
-wait_dll_lock_counter:
-	.word	0
-
 ENTRY(omap3_do_wfi_sz)
 	.word	. - omap3_do_wfi
 
@@ -437,7 +422,9 @@ ENTRY(omap3_restore)
 	cmp	r2, #0x0	@ Check if target power state was OFF or RET
 	bne	logic_l1_restore
 
-	ldr	r0, l2dis_3630
+	adr	r1, l2dis_3630_offset	@ address for offset
+	ldr	r0, [r1]		@ value for offset
+	ldr	r0, [r1, r0]		@ value at l2dis_3630
 	cmp	r0, #0x1	@ should we disable L2 on 3630?
 	bne	skipl2dis
 	mrc	p15, 0, r0, c1, c0, 1
@@ -449,12 +436,14 @@ skipl2dis:
 	and	r1, #0x700
 	cmp	r1, #0x300
 	beq	l2_inv_gp
+	adr	r0, l2_inv_api_params_offset
+	ldr	r3, [r0]
+	add	r3, r3, r0		@ r3 points to dummy parameters
 	mov	r0, #40			@ set service ID for PPA
 	mov	r12, r0			@ copy secure Service ID in r12
 	mov	r1, #0			@ set task id for ROM code in r1
 	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
-	adr	r3, l2_inv_api_params	@ r3 points to dummy parameters
 	dsb				@ data write barrier
 	dmb				@ data memory barrier
 	smc	#1			@ call SMI monitor (smi #1)
@@ -488,8 +477,8 @@ skipl2dis:
 	b	logic_l1_restore
 
 	.align
-l2_inv_api_params:
-	.word	0x1, 0x00
+l2_inv_api_params_offset:
+	.long	l2_inv_api_params - .
 l2_inv_gp:
 	/* Execute smi to invalidate L2 cache */
 	mov r12, #0x1			@ set up to invalidate L2
@@ -506,7 +495,9 @@ l2_inv_gp:
 	mov	r12, #0x2
 	smc	#0			@ Call SMI monitor (smieq)
 logic_l1_restore:
-	ldr	r1, l2dis_3630
+	adr	r0, l2dis_3630_offset	@ adress for offset
+	ldr	r1, [r0]		@ value for offset
+	ldr	r1, [r0, r1]		@ value at l2dis_3630
 	cmp	r1, #0x1		@ Test if L2 re-enable needed on 3630
 	bne	skipl2reen
 	mrc	p15, 0, r1, c1, c0, 1
@@ -535,9 +526,17 @@ control_stat:
 	.word	CONTROL_STAT
 control_mem_rta:
 	.word	CONTROL_MEM_RTA_CTRL
+l2dis_3630_offset:
+	.long	l2dis_3630 - .
+
+	.data
 l2dis_3630:
 	.word	0
 
+	.data
+l2_inv_api_params:
+	.word	0x1, 0x00
+
 /*
  * Internal functions
  */
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index 9b09d85d811a..c7a3b4aab4b5 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -29,12 +29,6 @@
 	dsb
 .endm
 
-ppa_zero_params:
-	.word		0x0
-
-ppa_por_params:
-	.word		1, 0
-
 #ifdef CONFIG_ARCH_OMAP4
 
 /*
@@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume)
 	beq	skip_ns_smp_enable
 ppa_actrl_retry:
 	mov     r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX
-	adr	r3, ppa_zero_params		@ Pointer to parameters
+	adr	r1, ppa_zero_params_offset
+	ldr	r3, [r1]
+	add	r3, r3, r1			@ Pointer to ppa_zero_params
 	mov	r1, #0x0			@ Process ID
 	mov	r2, #0x4			@ Flag
 	mov	r6, #0xff
@@ -303,7 +299,9 @@ skip_ns_smp_enable:
 	ldr     r0, =OMAP4_PPA_L2_POR_INDEX
 	ldr     r1, =OMAP44XX_SAR_RAM_BASE
 	ldr     r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET]
-	adr     r3, ppa_por_params
+	adr     r1, ppa_por_params_offset
+	ldr	r3, [r1]
+	add	r3, r3, r1			@ Pointer to ppa_por_params
 	str     r4, [r3, #0x04]
 	mov	r1, #0x0			@ Process ID
 	mov	r2, #0x4			@ Flag
@@ -328,6 +326,8 @@ skip_l2en:
 #endif
 
 	b	cpu_resume			@ Jump to generic resume
+ppa_por_params_offset:
+	.long	ppa_por_params - .
 ENDPROC(omap4_cpu_resume)
 #endif	/* CONFIG_ARCH_OMAP4 */
 
@@ -380,4 +380,13 @@ ENTRY(omap_do_wfi)
 	nop
 
 	ldmfd	sp!, {pc}
+ppa_zero_params_offset:
+	.long	ppa_zero_params - .
 ENDPROC(omap_do_wfi)
+
+	.data
+ppa_zero_params:
+	.word		0
+
+ppa_por_params:
+	.word		1, 0
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 6ad554b01e95..ddfb97a299f2 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void)
 		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
 	if (!ret)
 		ret = register_iommu_dma_ops_notifier(&amba_bustype);
+
+	/* handle devices queued before this arch_initcall */
+	if (!ret)
+		__iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
 	return ret;
 }
 arch_initcall(__iommu_dma_init);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 3571c7309c5e..cf6240741134 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages,
 	if (end < MODULES_VADDR || end >= MODULES_END)
 		return -EINVAL;
 
+	if (!numpages)
+		return 0;
+
 	data.set_mask = set_mask;
 	data.clear_mask = clear_mask;
 
diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c
index 0392112a5d70..a5ecef7188ba 100644
--- a/arch/m32r/kernel/setup.c
+++ b/arch/m32r/kernel/setup.c
@@ -81,7 +81,10 @@ static struct resource code_resource = {
 };
 
 unsigned long memory_start;
+EXPORT_SYMBOL(memory_start);
+
 unsigned long memory_end;
+EXPORT_SYMBOL(memory_end);
 
 void __init setup_arch(char **);
 int get_cpuinfo(char *);
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 7d56a9ccb752..a65d888716c4 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -54,24 +54,12 @@ static inline pte_t huge_pte_wrprotect(pte_t pte)
 	return pte_wrprotect(pte);
 }
 
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	pte_t old_pte = *ptep;
-	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
-}
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep);
 
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	int changed = !pte_same(*ptep, pte);
-	if (changed) {
-		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
-		flush_tlb_page(vma, addr);
-	}
-	return changed;
-}
+					     pte_t pte, int dirty);
 
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h
index d7034728f377..1c75565d984b 100644
--- a/arch/parisc/include/uapi/asm/siginfo.h
+++ b/arch/parisc/include/uapi/asm/siginfo.h
@@ -1,6 +1,10 @@
 #ifndef _PARISC_SIGINFO_H
 #define _PARISC_SIGINFO_H
 
+#if defined(__LP64__)
+#define __ARCH_SI_PREAMBLE_SIZE   (4 * sizeof(int))
+#endif
+
 #include <asm-generic/siginfo.h>
 
 #undef NSIGTRAP
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index f6fdc77a72bd..54ba39262b82 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -105,15 +105,13 @@ static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long ad
 	addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT;
 
 	for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) {
-		mtsp(mm->context, 1);
-		pdtlb(addr);
-		if (unlikely(split_tlb))
-			pitlb(addr);
+		purge_tlb_entries(mm, addr);
 		addr += (1UL << REAL_HPAGE_SHIFT);
 	}
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+/* __set_huge_pte_at() must be called holding the pa_tlb_lock. */
+static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	unsigned long addr_start;
@@ -123,14 +121,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	addr_start = addr;
 
 	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		/* Directly write pte entry.  We could call set_pte_at(mm, addr, ptep, entry)
-		 * instead, but then we get double locking on pa_tlb_lock. */
-		*ptep = entry;
+		set_pte(ptep, entry);
 		ptep++;
 
-		/* Drop the PAGE_SIZE/non-huge tlb entry */
-		purge_tlb_entries(mm, addr);
-
 		addr += PAGE_SIZE;
 		pte_val(entry) += PAGE_SIZE;
 	}
@@ -138,18 +131,61 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	purge_tlb_entries_huge(mm, addr_start);
 }
 
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry)
+{
+	unsigned long flags;
+
+	purge_tlb_start(flags);
+	__set_huge_pte_at(mm, addr, ptep, entry);
+	purge_tlb_end(flags);
+}
+
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
+	unsigned long flags;
 	pte_t entry;
 
+	purge_tlb_start(flags);
 	entry = *ptep;
-	set_huge_pte_at(mm, addr, ptep, __pte(0));
+	__set_huge_pte_at(mm, addr, ptep, __pte(0));
+	purge_tlb_end(flags);
 
 	return entry;
 }
 
+
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
+{
+	unsigned long flags;
+	pte_t old_pte;
+
+	purge_tlb_start(flags);
+	old_pte = *ptep;
+	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+	purge_tlb_end(flags);
+}
+
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep,
+				pte_t pte, int dirty)
+{
+	unsigned long flags;
+	int changed;
+
+	purge_tlb_start(flags);
+	changed = !pte_same(*ptep, pte);
+	if (changed) {
+		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	}
+	purge_tlb_end(flags);
+	return changed;
+}
+
+
 int pmd_huge(pmd_t pmd)
 {
 	return 0;
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index c5eb86f3d452..867c39b45df6 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -81,6 +81,7 @@ struct pci_dn;
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
 #define EEH_PE_REMOVED		(1 << 10)	/* Removed permanently	*/
+#define EEH_PE_PRI_BUS		(1 << 11)	/* Cached primary bus   */
 
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 8d14feb40f12..f69ecaa7ce33 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -564,6 +564,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus) {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(bus);
 		pci_unlock_rescan_remove();
@@ -803,6 +804,7 @@ perm_error:
 	 * the their PCI config any more.
 	 */
 	if (frozen_bus) {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
 		pci_lock_rescan_remove();
@@ -886,6 +888,7 @@ static void eeh_handle_special_event(void)
 					continue;
 
 				/* Notify all devices to be down */
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 				bus = eeh_pe_bus_get(phb_pe);
 				eeh_pe_dev_traverse(pe,
 					eeh_report_failure, NULL);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 8654cb166c19..98f81800e00c 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
 const char *eeh_pe_loc_get(struct eeh_pe *pe)
 {
 	struct pci_bus *bus = eeh_pe_bus_get(pe);
-	struct device_node *dn = pci_bus_to_OF_node(bus);
+	struct device_node *dn;
 	const char *loc = NULL;
 
-	if (!dn)
-		goto out;
+	while (bus) {
+		dn = pci_bus_to_OF_node(bus);
+		if (!dn) {
+			bus = bus->parent;
+			continue;
+		}
 
-	/* PHB PE or root PE ? */
-	if (pci_is_root_bus(bus)) {
-		loc = of_get_property(dn, "ibm,loc-code", NULL);
-		if (!loc)
+		if (pci_is_root_bus(bus))
 			loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
+		else
+			loc = of_get_property(dn, "ibm,slot-location-code",
+					      NULL);
+
 		if (loc)
-			goto out;
+			return loc;
 
-		/* Check the root port */
-		dn = dn->child;
-		if (!dn)
-			goto out;
+		bus = bus->parent;
 	}
 
-	loc = of_get_property(dn, "ibm,loc-code", NULL);
-	if (!loc)
-		loc = of_get_property(dn, "ibm,slot-location-code", NULL);
-
-out:
-	return loc ? loc : "N/A";
+	return "N/A";
 }
 
 /**
@@ -931,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 		bus = pe->phb->bus;
 	} else if (pe->type & EEH_PE_BUS ||
 		   pe->type & EEH_PE_DEVICE) {
-		if (pe->bus) {
+		if (pe->state & EEH_PE_PRI_BUS) {
 			bus = pe->bus;
 			goto out;
 		}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 3c6badcd53ef..e57cc383e5da 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 2:	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
-	rlwimi	r5, r4, 1, DAWRX_WT
+	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
 	std	r4, VCPU_DAWR(r3)
 	std	r5, VCPU_DAWRX(r3)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6fd2405c7f4a..a3b182dcb823 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
@@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
+			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index e1c90725522a..2ba602591a20 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	 * PCI devices of the PE are expected to be removed prior
 	 * to PE reset.
 	 */
-	if (!edev->pe->bus)
+	if (!(edev->pe->state & EEH_PE_PRI_BUS)) {
 		edev->pe->bus = pci_find_bus(hose->global_number,
 					     pdn->busno);
+		if (edev->pe->bus)
+			edev->pe->state |= EEH_PE_PRI_BUS;
+	}
 
 	/*
 	 * Enable EEH explicitly so that we will do EEH check
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 414fd1a00fda..e40d0714679e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3034,6 +3034,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
        .dma_dev_setup = pnv_pci_dma_dev_setup,
+       .dma_bus_setup = pnv_pci_dma_bus_setup,
 #ifdef CONFIG_PCI_MSI
        .setup_msi_irqs = pnv_setup_msi_irqs,
        .teardown_msi_irqs = pnv_teardown_msi_irqs,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index f2dd77234240..ad8c3f4a5e0b 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -601,6 +601,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 	u64 rpn = __pa(uaddr) >> tbl->it_page_shift;
 	long i;
 
+	if (proto_tce & TCE_PCI_WRITE)
+		proto_tce |= TCE_PCI_READ;
+
 	for (i = 0; i < npages; i++) {
 		unsigned long newtce = proto_tce |
 			((rpn + i) << tbl->it_page_shift);
@@ -622,6 +625,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
 
 	BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl));
 
+	if (newtce & TCE_PCI_WRITE)
+		newtce |= TCE_PCI_READ;
+
 	oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
 	*hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
 	*direction = iommu_tce_direction(oldtce);
@@ -762,6 +768,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		phb->dma_dev_setup(phb, pdev);
 }
 
+void pnv_pci_dma_bus_setup(struct pci_bus *bus)
+{
+	struct pci_controller *hose = bus->sysdata;
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+
+	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+		if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
+			continue;
+
+		if (!pe->pbus)
+			continue;
+
+		if (bus->number == ((pe->rid >> 8) & 0xFF)) {
+			pe->pbus = bus;
+			break;
+		}
+	}
+}
+
 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 c8ff50e90766..36a99feab7d8 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -235,6 +235,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
 extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
+extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
 extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
 extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
index 712b13047b41..3a33124e9112 100644
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3)
 	# done with the slightly better performing SSSE3 byte shuffling,
 	# 7/12-bit word rotation uses traditional shift+OR.
 
-	sub		$0x40,%rsp
+	mov		%rsp,%r11
+	sub		$0x80,%rsp
+	and		$~63,%rsp
 
 	# x0..15[0-3] = s0..3[0..3]
 	movq		0x00(%rdi),%xmm1
@@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3)
 	pxor		%xmm1,%xmm15
 	movdqu		%xmm15,0xf0(%rsi)
 
-	add		$0x40,%rsp
+	mov		%r11,%rsp
 	ret
 ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index a471cadb9630..79c91853e50e 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -363,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
 }
 static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
 {
+	pgprotval_t val = pgprot_val(pgprot);
 	pgprot_t new;
-	unsigned long val;
 
-	val = pgprot_val(pgprot);
 	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
 		((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
 	return new;
 }
 static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
 {
+	pgprotval_t val = pgprot_val(pgprot);
 	pgprot_t new;
-	unsigned long val;
 
-	val = pgprot_val(pgprot);
 	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
 			  ((val & _PAGE_PAT_LARGE) >>
 			   (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 982ce34f4a9b..27f89c79a44b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
+
+	/* If size is less than 8 bytes, go to 4-byte copy */
 	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	jb .L_4b_nocache_copy_entry
+
+	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
+
+	/* Set 4x8-byte copy count and remainder */
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_8b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
 	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
+	jnz .L_4x8b_nocache_copy_loop
+
+	/* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
+	jz .L_4b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:	movq (%rsi),%r8
+21:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
 	leaq 8(%rdi),%rdi
 	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
+	jnz .L_8b_nocache_copy_loop
+
+	/* If no byte left, we're done */
+.L_4b_nocache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* If destination is not 4-byte aligned, go to byte copy: */
+	movl %edi,%ecx
+	andl $3,%ecx
+	jnz .L_1b_cache_copy_entry
+
+	/* Set 4-byte copy count (1 or 0) and remainder */
 	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
+	andl $3,%edx
+	shrl $2,%ecx
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4-byte nocache copy: */
+30:	movl (%rsi),%r8d
+31:	movnti %r8d,(%rdi)
+	leaq 4(%rsi),%rsi
+	leaq 4(%rdi),%rdi
+
+	/* If no bytes left, we're done: */
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
+	movl %edx,%ecx
+.L_1b_cache_copy_loop:
+40:	movb (%rsi),%al
+41:	movb %al,(%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
+	jnz .L_1b_cache_copy_loop
+
+	/* Finished copying; fence the prior stores */
+.L_finish_copy:
+	xorl %eax,%eax
 	ASM_CLAC
 	sfence
 	ret
 
 	.section .fixup,"ax"
-30:	shll $6,%ecx
+.L_fixup_4x8b_copy:
+	shll $6,%ecx
 	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
+	jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+	lea (%rdx,%rcx,8),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+	lea (%rdx,%rcx,4),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+	movl %ecx,%edx
+.L_fixup_handle_tail:
+	sfence
 	jmp copy_user_handle_tail
 	.previous
 
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
+	_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(30b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(31b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
+	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index eef44d9a3f77..e830c71a1323 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
+	if (pmd_huge(*pmd_k))
+		return 0;
+
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -360,8 +363,6 @@ void vmalloc_sync_all(void)
  * 64-bit:
  *
  *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
  */
 static noinline int vmalloc_fault(unsigned long address)
 {
@@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud_ref))
 		return -1;
 
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
+	if (pud_huge(*pud))
+		return 0;
+
 	pmd = pmd_offset(pud, address);
 	pmd_ref = pmd_offset(pud_ref, address);
 	if (pmd_none(*pmd_ref))
 		return -1;
 
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
+	if (pmd_huge(*pmd))
+		return 0;
+
 	pte_ref = pte_offset_kernel(pmd_ref, address);
 	if (!pte_present(*pte_ref))
 		return -1;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a3137a4feed1..db20ee9a413a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -33,7 +33,7 @@ struct cpa_data {
 	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
-	int		numpages;
+	unsigned long	numpages;
 	int		flags;
 	unsigned long	pfn;
 	unsigned	force_split : 1;
@@ -1345,7 +1345,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 * CPA operation. Either a large page has been
 		 * preserved or a single page update happened.
 		 */
-		BUG_ON(cpa->numpages > numpages);
+		BUG_ON(cpa->numpages > numpages || !cpa->numpages);
 		numpages -= cpa->numpages;
 		if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
 			cpa->curpage++;