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

Conflicts:
	drivers/net/usb/r8152.c
	drivers/net/xen-netback/netback.c

Both the r8152 and netback conflicts were simple overlapping
changes.

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

46 files changed, 268 insertions, 382 deletions

diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 6b58c1de7577..400c663b21c2 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -282,7 +282,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 #else
 	/* if V-P const for loop, PTAG can be written once outside loop */
 	if (full_page_op)
-		write_aux_reg(ARC_REG_DC_PTAG, paddr);
+		write_aux_reg(aux_tag, paddr);
 #endif
 
 	while (num_lines-- > 0) {
@@ -296,7 +296,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 		write_aux_reg(aux_cmd, vaddr);
 		vaddr += L1_CACHE_BYTES;
 #else
-		write_aux_reg(aux, paddr);
+		write_aux_reg(aux_cmd, paddr);
 		paddr += L1_CACHE_BYTES;
 #endif
 	}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e25419817791..15949459611f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1578,6 +1578,7 @@ config BL_SWITCHER_DUMMY_IF
 
 choice
 	prompt "Memory split"
+	depends on MMU
 	default VMSPLIT_3G
 	help
 	  Select the desired split between kernel and user memory.
@@ -1595,6 +1596,7 @@ endchoice
 
 config PAGE_OFFSET
 	hex
+	default PHYS_OFFSET if !MMU
 	default 0x40000000 if VMSPLIT_1G
 	default 0x80000000 if VMSPLIT_2G
 	default 0xC0000000
@@ -1903,6 +1905,7 @@ config XEN
 	depends on ARM && AEABI && OF
 	depends on CPU_V7 && !CPU_V6
 	depends on !GENERIC_ATOMIC64
+	depends on MMU
 	select ARM_PSCI
 	select SWIOTLB_XEN
 	select ARCH_DMA_ADDR_T_64BIT
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index 47279aa96a6a..0714e0334e33 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 ashldi3.S
+bswapsdi2.S
 font.c
 lib1funcs.S
 hyp-stub.S
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index e491b82f8d67..792fde1b7f75 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -147,7 +147,7 @@
 	};
 
 	pinctrl@35004800 {
-		compatible = "brcm,capri-pinctrl";
+		compatible = "brcm,bcm11351-pinctrl";
 		reg = <0x35004800 0x430>;
 	};
 
diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts
index c551e4af4d83..d3b253bbc885 100644
--- a/arch/arm/boot/dts/omap3-gta04.dts
+++ b/arch/arm/boot/dts/omap3-gta04.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "OMAP3 GTA04";
-	compatible = "ti,omap3-gta04", "ti,omap3";
+	compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 25a2b5f652fd..f2779ac75872 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "IGEPv2 (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0020", "ti,omap3";
+	compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3";
 
 	leds {
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts
index 145c58cfc8ac..2793749eb1ba 100644
--- a/arch/arm/boot/dts/omap3-igep0030.dts
+++ b/arch/arm/boot/dts/omap3-igep0030.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "IGEP COM MODULE (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0030", "ti,omap3";
+	compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3";
 
 	leds {
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 10666ca8aee1..d4d2763f4794 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -426,7 +426,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 64961595e8d6..79fd412005b0 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -383,7 +383,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 320335abfccd..c463fd730c91 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -346,7 +346,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 9ff09484847b..6f25cf559ad0 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -454,7 +454,7 @@
 		rtc: rtc@01c20d00 {
 			compatible = "allwinner,sun7i-a20-rtc";
 			reg = <0x01c20d00 0x20>;
-			interrupts = <0 24 1>;
+			interrupts = <0 24 4>;
 		};
 
 		sid: eeprom@01c23800 {
@@ -463,7 +463,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <0 29 4>;
 		};
@@ -596,10 +596,10 @@
 		hstimer@01c60000 {
 			compatible = "allwinner,sun7i-a20-hstimer";
 			reg = <0x01c60000 0x1000>;
-			interrupts = <0 81 1>,
-				     <0 82 1>,
-				     <0 83 1>,
-				     <0 84 1>;
+			interrupts = <0 81 4>,
+				     <0 82 4>,
+				     <0 83 4>,
+				     <0 84 4>;
 			clocks = <&ahb_gates 28>;
 		};
 
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 00fe9e9710fd..27d69b558c5d 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -204,7 +204,10 @@ CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_ONESHOT=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 8756e4bcdba0..4afb376d9c7c 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -30,14 +30,15 @@
  */
 #define UL(x) _AC(x, UL)
 
+/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
+
 #ifdef CONFIG_MMU
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
-#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
 #define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
@@ -104,10 +105,6 @@
 #define END_MEM     		(UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
-#ifndef PAGE_OFFSET
-#define PAGE_OFFSET		PLAT_PHYS_OFFSET
-#endif
-
 /*
  * The module can be at any place in ram in nommu mode.
  */
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 47cd974e57ea..c96ecacb2021 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -177,6 +177,18 @@ __lookup_processor_type_data:
 	.long	__proc_info_end
 	.size	__lookup_processor_type_data, . - __lookup_processor_type_data
 
+__error_lpae:
+#ifdef CONFIG_DEBUG_LL
+	adr	r0, str_lpae
+	bl 	printascii
+	b	__error
+str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
+#else
+	b	__error
+#endif
+	.align
+ENDPROC(__error_lpae)
+
 __error_p:
 #ifdef CONFIG_DEBUG_LL
 	adr	r0, str_p1
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 914616e0bdcd..f5f381d91556 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -102,7 +102,7 @@ ENTRY(stext)
 	and	r3, r3, #0xf			@ extract VMSA support
 	cmp	r3, #5				@ long-descriptor translation table format?
  THUMB( it	lo )				@ force fixup-able long branch encoding
-	blo	__error_p			@ only classic page table format
+	blo	__error_lpae			@ only classic page table format
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 3b05aea56d1f..11ed9152e665 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -433,7 +433,9 @@ static const struct clk_ops dpll4_m5x2_ck_ops = {
 	.enable		= &omap2_dflt_clk_enable,
 	.disable	= &omap2_dflt_clk_disable,
 	.is_enabled	= &omap2_dflt_clk_is_enabled,
+	.set_rate	= &omap3_clkoutx2_set_rate,
 	.recalc_rate	= &omap3_clkoutx2_recalc,
+	.round_rate	= &omap3_clkoutx2_round_rate,
 };
 
 static const struct clk_ops dpll4_m5x2_ck_3630_ops = {
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 4c158c838d40..01fc710c8181 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -23,6 +23,8 @@
 #include "prm.h"
 #include "clockdomain.h"
 
+#define MAX_CPUS	2
+
 /* Machine specific information */
 struct idle_statedata {
 	u32 cpu_state;
@@ -48,11 +50,11 @@ static struct idle_statedata omap4_idle_data[] = {
 	},
 };
 
-static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS];
-static struct clockdomain *cpu_clkdm[NR_CPUS];
+static struct powerdomain *mpu_pd, *cpu_pd[MAX_CPUS];
+static struct clockdomain *cpu_clkdm[MAX_CPUS];
 
 static atomic_t abort_barrier;
-static bool cpu_done[NR_CPUS];
+static bool cpu_done[MAX_CPUS];
 static struct idle_statedata *state_ptr = &omap4_idle_data[0];
 
 /* Private functions */
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index 3185ced807c9..3c418ea54bbe 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -623,6 +623,32 @@ void omap3_dpll_deny_idle(struct clk_hw_omap *clk)
 
 /* Clock control for DPLL outputs */
 
+/* Find the parent DPLL for the given clkoutx2 clock */
+static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw)
+{
+	struct clk_hw_omap *pclk = NULL;
+	struct clk *parent;
+
+	/* Walk up the parents of clk, looking for a DPLL */
+	do {
+		do {
+			parent = __clk_get_parent(hw->clk);
+			hw = __clk_get_hw(parent);
+		} while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC));
+		if (!hw)
+			break;
+		pclk = to_clk_hw_omap(hw);
+	} while (pclk && !pclk->dpll_data);
+
+	/* clk does not have a DPLL as a parent?  error in the clock data */
+	if (!pclk) {
+		WARN_ON(1);
+		return NULL;
+	}
+
+	return pclk;
+}
+
 /**
  * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
  * @clk: DPLL output struct clk
@@ -637,27 +663,14 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 	unsigned long rate;
 	u32 v;
 	struct clk_hw_omap *pclk = NULL;
-	struct clk *parent;
 
 	if (!parent_rate)
 		return 0;
 
-	/* Walk up the parents of clk, looking for a DPLL */
-	do {
-		do {
-			parent = __clk_get_parent(hw->clk);
-			hw = __clk_get_hw(parent);
-		} while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC));
-		if (!hw)
-			break;
-		pclk = to_clk_hw_omap(hw);
-	} while (pclk && !pclk->dpll_data);
+	pclk = omap3_find_clkoutx2_dpll(hw);
 
-	/* clk does not have a DPLL as a parent?  error in the clock data */
-	if (!pclk) {
-		WARN_ON(1);
+	if (!pclk)
 		return 0;
-	}
 
 	dd = pclk->dpll_data;
 
@@ -672,6 +685,55 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 	return rate;
 }
 
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate)
+{
+	return 0;
+}
+
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *prate)
+{
+	const struct dpll_data *dd;
+	u32 v;
+	struct clk_hw_omap *pclk = NULL;
+
+	if (!*prate)
+		return 0;
+
+	pclk = omap3_find_clkoutx2_dpll(hw);
+
+	if (!pclk)
+		return 0;
+
+	dd = pclk->dpll_data;
+
+	/* TYPE J does not have a clkoutx2 */
+	if (dd->flags & DPLL_J_TYPE) {
+		*prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate);
+		return *prate;
+	}
+
+	WARN_ON(!dd->enable_mask);
+
+	v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
+	v >>= __ffs(dd->enable_mask);
+
+	/* If in bypass, the rate is fixed to the bypass rate*/
+	if (v != OMAP3XXX_EN_DPLL_LOCKED)
+		return *prate;
+
+	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+		unsigned long best_parent;
+
+		best_parent = (rate / 2);
+		*prate = __clk_round_rate(__clk_get_parent(hw->clk),
+				best_parent);
+	}
+
+	return *prate * 2;
+}
+
 /* OMAP3/4 non-CORE DPLL clkops */
 const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
 	.allow_idle	= omap3_dpll_allow_idle,
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 42d81885c700..1f33f5db10d5 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1947,29 +1947,31 @@ static int _ocp_softreset(struct omap_hwmod *oh)
 		goto dis_opt_clks;
 
 	_write_sysconfig(v, oh);
-	ret = _clear_softreset(oh, &v);
-	if (ret)
-		goto dis_opt_clks;
-
-	_write_sysconfig(v, oh);
 
 	if (oh->class->sysc->srst_udelay)
 		udelay(oh->class->sysc->srst_udelay);
 
 	c = _wait_softreset_complete(oh);
-	if (c == MAX_MODULE_SOFTRESET_WAIT)
+	if (c == MAX_MODULE_SOFTRESET_WAIT) {
 		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
 			   oh->name, MAX_MODULE_SOFTRESET_WAIT);
-	else
+		ret = -ETIMEDOUT;
+		goto dis_opt_clks;
+	} else {
 		pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
+	}
+
+	ret = _clear_softreset(oh, &v);
+	if (ret)
+		goto dis_opt_clks;
+
+	_write_sysconfig(v, oh);
 
 	/*
 	 * XXX add _HWMOD_STATE_WEDGED for modules that don't come back from
 	 * _wait_target_ready() or _reset()
 	 */
 
-	ret = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
-
 dis_opt_clks:
 	if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
 		_disable_optional_clocks(oh);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 18f333c440db..810c205d668b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1365,11 +1365,10 @@ static struct omap_hwmod_class_sysconfig dra7xx_spinlock_sysc = {
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
 	.syss_offs	= 0x0014,
-	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
-			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
-			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 3d5b24dcd9a4..c33e07e2f0d4 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -22,6 +22,8 @@
 #include "common-board-devices.h"
 #include "dss-common.h"
 #include "control.h"
+#include "omap-secure.h"
+#include "soc.h"
 
 struct pdata_init {
 	const char *compatible;
@@ -169,6 +171,22 @@ static void __init am3517_evm_legacy_init(void)
 	omap_ctrl_writel(v, AM35XX_CONTROL_IP_SW_RESET);
 	omap_ctrl_readl(AM35XX_CONTROL_IP_SW_RESET); /* OCP barrier */
 }
+
+static void __init nokia_n900_legacy_init(void)
+{
+	hsmmc2_internal_input_clk();
+
+	if (omap_type() == OMAP2_DEVICE_TYPE_SEC) {
+		if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) {
+			pr_info("RX-51: Enabling ARM errata 430973 workaround\n");
+			/* set IBE to 1 */
+			rx51_secure_update_aux_cr(BIT(6), 0);
+		} else {
+			pr_warning("RX-51: Not enabling ARM errata 430973 workaround\n");
+			pr_warning("Thumb binaries may crash randomly without this workaround\n");
+		}
+	}
+}
 #endif /* CONFIG_ARCH_OMAP3 */
 
 #ifdef CONFIG_ARCH_OMAP4
@@ -239,6 +257,7 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 #endif
 #ifdef CONFIG_ARCH_OMAP3
 	OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002030, "48002030.pinmux", &pcs_pdata),
+	OF_DEV_AUXDATA("ti,omap3-padconf", 0x480025a0, "480025a0.pinmux", &pcs_pdata),
 	OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002a00, "48002a00.pinmux", &pcs_pdata),
 	/* Only on am3517 */
 	OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
@@ -259,7 +278,7 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 static struct pdata_init pdata_quirks[] __initdata = {
 #ifdef CONFIG_ARCH_OMAP3
 	{ "compulab,omap3-sbc-t3730", omap3_sbc_t3730_legacy_init, },
-	{ "nokia,omap3-n900", hsmmc2_internal_input_clk, },
+	{ "nokia,omap3-n900", nokia_n900_legacy_init, },
 	{ "nokia,omap3-n9", hsmmc2_internal_input_clk, },
 	{ "nokia,omap3-n950", hsmmc2_internal_input_clk, },
 	{ "isee,omap3-igep0020", omap3_igep0020_legacy_init, },
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index 6334b96b4097..280f3c58abe5 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -183,11 +183,11 @@ void omap4_prminst_global_warm_sw_reset(void)
 					OMAP4_PRM_RSTCTRL_OFFSET);
 	v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK;
 	omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION,
-				 OMAP4430_PRM_DEVICE_INST,
+				 dev_inst,
 				 OMAP4_PRM_RSTCTRL_OFFSET);
 
 	/* OCP barrier */
 	v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION,
-				    OMAP4430_PRM_DEVICE_INST,
+				    dev_inst,
 				    OMAP4_PRM_RSTCTRL_OFFSET);
 }
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d2d3ee..50e1d850ee2e 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
 
+#include "hardware.h" /* Gives GPIO_MAX */
+
 extern void locomolcd_power(int on);
 
 #define COLLIE_SCOOP_GPIO_BASE	(GPIO_MAX + 1)
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 2b3a56414271..ef69152f9b52 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -264,6 +264,9 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 			note_page(st, addr, 3, pmd_val(*pmd));
 		else
 			walk_pte(st, pmd, addr);
+
+		if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1]))
+			note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1]));
 	}
 }
 
diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h
index 09c5a0f5f4d1..86648c083bb4 100644
--- a/arch/c6x/include/asm/cache.h
+++ b/arch/c6x/include/asm/cache.h
@@ -12,6 +12,7 @@
 #define _ASM_C6X_CACHE_H
 
 #include <linux/irqflags.h>
+#include <linux/init.h>
 
 /*
  * Cache line size
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index 184066ceb1f6..053c17b36559 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -144,7 +144,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
  * definition, which doesn't have the same semantics.  We don't want to
  * use -fno-builtin, so just hide the name ffs.
  */
-#define ffs kernel_ffs
+#define ffs(x) kernel_ffs(x)
 
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index a96bcf83a735..20e8a9b21d75 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 	/* attempt to allocate a granule's worth of cached memory pages */
 
 	page = alloc_pages_exact_node(nid,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
 	if (!page) {
 		mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8d4c247f1738..af064d28b365 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1048,6 +1048,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	flush_altivec_to_thread(src);
 	flush_vsx_to_thread(src);
 	flush_spe_to_thread(src);
+	/*
+	 * Flush TM state out so we can copy it.  __switch_to_tm() does this
+	 * flush but it removes the checkpointed state from the current CPU and
+	 * transitions the CPU out of TM mode.  Hence we need to call
+	 * tm_recheckpoint_new_task() (on the same task) to restore the
+	 * checkpointed state back and the TM mode.
+	 */
+	__switch_to_tm(src);
+	tm_recheckpoint_new_task(src);
 
 	*dst = *src;
 
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index 1482327cfeba..d88736fbece6 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -81,6 +81,7 @@ _GLOBAL(relocate)
 
 6:	blr
 
+.balign 8
 p_dyn:	.llong	__dynamic_start - 0b
 p_rela:	.llong	__rela_dyn_start - 0b
 p_st:	.llong	_stext - 0b
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 5ec1e47a0d77..e865d748179b 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -123,7 +123,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order)
 
 	area->nid = nid;
 	area->order = order;
-	area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+	area->pages = alloc_pages_exact_node(area->nid,
+						GFP_KERNEL|__GFP_THISNODE,
 						area->order);
 
 	if (!area->pages) {
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca5602c..f3aaf231b4e5 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@ config X86_USE_3DNOW
 	def_bool y
 	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
 
-config X86_OOSTORE
-	def_bool y
-	depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
 #
 # P6_NOPs are a relatively minor optimization that require a family >=
 # 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 04a48903b2eb..69bbb4845020 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -85,11 +85,7 @@
 #else
 # define smp_rmb()	barrier()
 #endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
+#define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
@@ -100,7 +96,7 @@
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
 #endif /* SMP */
 
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
  * For either of these options x86 doesn't have a strong TSO memory
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3d6b9f81cc68..acd86c850414 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -134,6 +134,7 @@ 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);
+extern void __init efi_apply_memmap_quirks(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34f69cb9350a..91d9c69a629e 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -237,7 +237,7 @@ memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
 
 static inline void flush_write_buffers(void)
 {
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
 #endif
 }
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index bf156ded74b5..0f62f5482d91 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -26,10 +26,9 @@
 # define LOCK_PTR_REG "D"
 #endif
 
-#if defined(CONFIG_X86_32) && \
-	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
 /*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * On PPro SMP, we use a locked operation to unlock
  * (PPro errata 66, 92)
  */
 # define UNLOCK_LOCK_PREFIX LOCK_PREFIX
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779edab684e..d8fba5c15fbd 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
-	u32 s = 1;
-
-	while (s <= x)
-		s <<= 1;
-
-	return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
-	u32 lo, hi;
-
-	hi = base & ~0xFFF;
-	lo = ~(size-1);		/* Size is a power of 2 so this makes a mask */
-	lo &= ~0xFFF;		/* Remove the ctrl value bits */
-	lo |= key;		/* Attribute we wish to set */
-	wrmsr(reg+MSR_IDT_MCR0, lo, hi);
-	mtrr_centaur_report_mcr(reg, lo, hi);	/* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
-	u32 clip = 0xFFFFFFFFUL;
-	u32 top = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		unsigned long start, end;
-
-		if (e820.map[i].addr > 0xFFFFFFFFUL)
-			continue;
-		/*
-		 * Don't MCR over reserved space. Ignore the ISA hole
-		 * we frob around that catastrophe already
-		 */
-		if (e820.map[i].type == E820_RESERVED) {
-			if (e820.map[i].addr >= 0x100000UL &&
-			    e820.map[i].addr < clip)
-				clip = e820.map[i].addr;
-			continue;
-		}
-		start = e820.map[i].addr;
-		end = e820.map[i].addr + e820.map[i].size;
-		if (start >= end)
-			continue;
-		if (end > top)
-			top = end;
-	}
-	/*
-	 * Everything below 'top' should be RAM except for the ISA hole.
-	 * Because of the limited MCR's we want to map NV/ACPI into our
-	 * MCR range for gunk in RAM
-	 *
-	 * Clip might cause us to MCR insufficient RAM but that is an
-	 * acceptable failure mode and should only bite obscure boxes with
-	 * a VESA hole at 15Mb
-	 *
-	 * The second case Clip sometimes kicks in is when the EBDA is marked
-	 * as reserved. Again we fail safe with reasonable results
-	 */
-	if (top > clip)
-		top = clip;
-
-	return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
-	u32 mem = ramtop();
-	u32 root = power2(mem);
-	u32 base = root;
-	u32 top = root;
-	u32 floor = 0;
-	int ct = 0;
-
-	while (ct < nr) {
-		u32 fspace = 0;
-		u32 high;
-		u32 low;
-
-		/*
-		 * Find the largest block we will fill going upwards
-		 */
-		high = power2(mem-top);
-
-		/*
-		 * Find the largest block we will fill going downwards
-		 */
-		low = base/2;
-
-		/*
-		 * Don't fill below 1Mb going downwards as there
-		 * is an ISA hole in the way.
-		 */
-		if (base <= 1024*1024)
-			low = 0;
-
-		/*
-		 * See how much space we could cover by filling below
-		 * the ISA hole
-		 */
-
-		if (floor == 0)
-			fspace = 512*1024;
-		else if (floor == 512*1024)
-			fspace = 128*1024;
-
-		/* And forget ROM space */
-
-		/*
-		 * Now install the largest coverage we get
-		 */
-		if (fspace > high && fspace > low) {
-			centaur_mcr_insert(ct, floor, fspace, key);
-			floor += fspace;
-		} else if (high > low) {
-			centaur_mcr_insert(ct, top, high, key);
-			top += high;
-		} else if (low > 0) {
-			base -= low;
-			centaur_mcr_insert(ct, base, low, key);
-		} else
-			break;
-		ct++;
-	}
-	/*
-	 * We loaded ct values. We now need to set the mask. The caller
-	 * must do this bit.
-	 */
-	return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
-	int used;
-	int i;
-
-	/*
-	 * Allocate up to 6 mcrs to mark as much of ram as possible
-	 * as write combining and weak write ordered.
-	 *
-	 * To experiment with: Linux never uses stack operations for
-	 * mmio spaces so we could globally enable stack operation wc
-	 *
-	 * Load the registers with type 31 - full write combining, all
-	 * writes weakly ordered.
-	 */
-	used = centaur_mcr_compute(6, 31);
-
-	/*
-	 * Wipe unused MCRs
-	 */
-	for (i = used; i < 8; i++)
-		wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
-	u32 lo, hi;
-	int used;
-	int i;
-
-	/*
-	 * Allocate up to 6 mcrs to mark as much of ram as possible
-	 * as write combining, weak store ordered.
-	 *
-	 * Load the registers with type 25
-	 *	8	-	weak write ordering
-	 *	16	-	weak read ordering
-	 *	1	-	write combining
-	 */
-	used = centaur_mcr_compute(6, 25);
-
-	/*
-	 * Mark the registers we are using.
-	 */
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	for (i = 0; i < used; i++)
-		lo |= 1<<(9+i);
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
-	/*
-	 * Wipe unused MCRs
-	 */
-
-	for (i = used; i < 8; i++)
-		wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
-	u32 lo, hi;
-	u32 key;
-
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	lo &= ~0x1C0;	/* blank bits 8-6 */
-	key = (lo>>17) & 7;
-	lo |= key<<6;	/* replace with unlock key */
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
-	u32 lo, hi;
-
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	lo &= ~0x1C0;	/* blank bits 8-6 */
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
 #define ACE_PRESENT	(1 << 6)
 #define ACE_ENABLED	(1 << 7)
 #define ACE_FCR		(1 << 28)	/* MSR_VIA_FCR */
@@ -362,20 +132,6 @@ static void init_centaur(struct cpuinfo_x86 *c)
 			fcr_clr = DPDC;
 			printk(KERN_NOTICE "Disabling bugged TSC.\n");
 			clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
-			centaur_create_optimal_mcr();
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 *
-			 * The C6 original lacks weak read order
-			 *
-			 * Note 0x120 is write only on Winchip 1
-			 */
-			wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
 			break;
 		case 8:
 			switch (c->x86_mask) {
@@ -392,40 +148,12 @@ static void init_centaur(struct cpuinfo_x86 *c)
 			fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
 				  E2MMX|EAMD3D;
 			fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-			winchip2_unprotect_mcr();
-			winchip2_create_optimal_mcr();
-			rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 */
-			lo |= 31;
-			wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			winchip2_protect_mcr();
-#endif
 			break;
 		case 9:
 			name = "3";
 			fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
 				  E2MMX|EAMD3D;
 			fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-			winchip2_unprotect_mcr();
-			winchip2_create_optimal_mcr();
-			rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 */
-			lo |= 31;
-			wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			winchip2_protect_mcr();
-#endif
 			break;
 		default:
 			name = "??";
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba27679f18..f36bd42d6f0c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers)
 	/* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
 	cld
+
+	cmpl $2,(%esp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
 	incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@ ex_entry:
 	pop %edx
 	pop %ecx
 	pop %eax
-	addl $8,%esp		/* drop vector number and error code */
 	decl %ss:early_recursion_flag
+is_nmi:
+	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb314c8..a468c0a65c42 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@ early_idt_handlers:
 ENTRY(early_idt_handler)
 	cld
 
+	cmpl $2,(%rsp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
 	popq %rdx
 	popq %rcx
 	popq %rax
-	addq $16,%rsp		# drop vector number and error code
 	decl early_recursion_flag(%rip)
+is_nmi:
+	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6dd2a2..d5dd80814419 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
 
 void __kernel_fpu_end(void)
 {
-	if (use_eager_fpu())
-		math_state_restore();
-	else
+	if (use_eager_fpu()) {
+		/*
+		 * For eager fpu, most the time, tsk_used_math() is true.
+		 * Restore the user math as we are done with the kernel usage.
+		 * At few instances during thread exit, signal handling etc,
+		 * tsk_used_math() is false. Those few places will take proper
+		 * actions, so we don't need to restore the math here.
+		 */
+		if (likely(tsk_used_math(current)))
+			math_state_restore();
+	} else {
 		stts();
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4b8995..ff898bbf579d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev)
 		return;
 
 	pci_read_config_dword(nb_ht, 0x60, &val);
-	node = val & 7;
+	node = pcibus_to_node(dev->bus) | (val & 7);
 	/*
 	 * Some hardware may return an invalid node ID,
 	 * so check it first:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e670354..ce72964b2f46 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1239,14 +1239,8 @@ void __init setup_arch(char **cmdline_p)
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, unmap the EFI memory map on
-	 * mismatched firmware/kernel archtectures since there is no
-	 * support for runtime services.
-	 */
-	if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
+	if (efi_enabled(EFI_BOOT))
+		efi_apply_memmap_quirks();
 #endif
 }
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e81df8fce027..2de1bc09a8d4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3002,10 +3002,8 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(svm);
-	if (irqchip_in_kernel(svm->vcpu.kvm)) {
-		clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+	if (irqchip_in_kernel(svm->vcpu.kvm))
 		return r;
-	}
 	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
 		return r;
 	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3567,6 +3565,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
 		return;
 
+	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	if (irr == -1)
 		return;
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 6dea040cc3a1..a10c8c792161 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1020,13 +1020,17 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
  */
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
-	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1034,9 +1038,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	tsk = current;
 	mm = tsk->mm;
 
-	/* Get the faulting address: */
-	address = read_cr2();
-
 	/*
 	 * Detect and handle instructions that would cause a page fault for
 	 * both a tracked kernel page and a userspace page.
@@ -1248,32 +1249,50 @@ good_area:
 	up_read(&mm->mmap_sem);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	unsigned long address = read_cr2(); /* Get the faulting address */
 	enum ctx_state prev_state;
 
+	/*
+	 * We must have this function tagged with __kprobes, notrace and call
+	 * read_cr2() before calling anything else. To avoid calling any kind
+	 * of tracing machinery before we've observed the CR2 value.
+	 *
+	 * exception_{enter,exit}() contain all sorts of tracepoints.
+	 */
+
 	prev_state = exception_enter();
-	__do_page_fault(regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
 
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
 				     unsigned long error_code)
 {
 	if (user_mode(regs))
-		trace_page_fault_user(read_cr2(), regs, error_code);
+		trace_page_fault_user(address, regs, error_code);
 	else
-		trace_page_fault_kernel(read_cr2(), regs, error_code);
+		trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	/*
+	 * The exception_enter and tracepoint processing could
+	 * trigger another page faults (user space callchain
+	 * reading) and destroy the original cr2 value, so read
+	 * the faulting address now.
+	 */
+	unsigned long address = read_cr2();
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
-	trace_page_fault_entries(regs, error_code);
-	__do_page_fault(regs, error_code);
+	trace_page_fault_entries(address, regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1b2152..01495755701b 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@ bpf_slow_path_byte_msh:
 	push	%r9;						\
 	push	SKBDATA;					\
 /* rsi already has offset */					\
-	mov	$SIZE,%ecx;	/* size */			\
+	mov	$SIZE,%edx;	/* size */			\
 	call	bpf_internal_load_pointer_neg_helper;		\
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1a201ac7cef8..b97acecf3fd9 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
+#include <asm/uv/uv.h>
 
 #define EFI_DEBUG
 
@@ -1210,3 +1211,22 @@ static int __init parse_efi_cmdline(char *str)
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_is_native()) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+}
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7d01b8c56c00..cc04e67bfd05 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -40,11 +40,7 @@
 #define smp_rmb()	barrier()
 #endif /* CONFIG_X86_PPRO_FENCE */
 
-#ifdef CONFIG_X86_OOSTORE
-#define smp_wmb()	wmb()
-#else /* CONFIG_X86_OOSTORE */
 #define smp_wmb()	barrier()
-#endif /* CONFIG_X86_OOSTORE */
 
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)