Merge tag 'v3.10' into sched/core

Merge in a recent upstream commit: c2853c8df57f include/linux/math64.h: add div64_ul() because: 72a4cf20cb71 sched: Change cfs_rq load avg to unsigned long relies on it. [ We don't rebase sched/core for this, because the handful of followup commits after the broken commit are not behavioral changes so are unlikely to be needed during bisection. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
author: Ingo Molnar <mingo@kernel.org> 2013-07-01 11:16:54 +0200
committer: Ingo Molnar <mingo@kernel.org> 2013-07-01 11:18:53 +0200
commit: 2fd1b487884310d0aa0c0640179dc7490ad86313 (patch)
tree: 1083dce15bd7dc0858c3883b8a361242046c5e09 /arch
parent: 333bb864f192015a53b5060b829089decd0220ef (diff)
parent: 8bb495e3f02401ee6f76d1b1d77f3ac9f079e376 (diff)
195 files changed, 1893 insertions, 1121 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 49d993cee51..136f263ed47 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1087,6 +1087,20 @@ if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
 
+config PJ4B_ERRATA_4742
+	bool "PJ4B Errata 4742: IDLE Wake Up Commands can Cause the CPU Core to Cease Operation"
+	depends on CPU_PJ4B && MACH_ARMADA_370
+	default y
+	help
+	  When coming out of either a Wait for Interrupt (WFI) or a Wait for
+	  Event (WFE) IDLE states, a specific timing sensitivity exists between
+	  the retiring WFI/WFE instructions and the newly issued subsequent
+	  instructions.  This sensitivity can result in a CPU hang scenario.
+	  Workaround:
+	  The software must insert either a Data Synchronization Barrier (DSB)
+	  or Data Memory Barrier (DMB) command immediately after the WFI/WFE
+	  instruction
+
 config ARM_ERRATA_326103
 	bool "ARM errata: FSR write bit incorrect on a SWP to read-only memory"
 	depends on CPU_V6
@@ -1189,6 +1203,16 @@ config PL310_ERRATA_588369
 	   is not correctly implemented in PL310 as clean lines are not
 	   invalidated as a result of these operations.
 
+config ARM_ERRATA_643719
+	bool "ARM errata: LoUIS bit field in CLIDR register is incorrect"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 643719 Cortex-A9 (prior to
+	  r1p0) erratum. On affected cores the LoUIS bit field of the CLIDR
+	  register returns zero when it should return one. The workaround
+	  corrects this value, ensuring cache maintenance operations which use
+	  it behave as intended and avoiding data corruption.
+
 config ARM_ERRATA_720789
 	bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
 	depends on CPU_V7
@@ -2006,7 +2030,7 @@ config XIP_PHYS_ADDR
 
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
-	depends on (!SMP || HOTPLUG_CPU)
+	depends on (!SMP || PM_SLEEP_SMP)
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 3580d57ea21..120b83bfde2 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -116,7 +116,8 @@ targets       := vmlinux vmlinux.lds \
 
 # Make sure files are removed during clean
 extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
-		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
+		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) \
+		 hyp-stub.S
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
@@ -124,7 +125,7 @@ KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
 ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
-asflags-y := -Wa,-march=all -DZIMAGE
+asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
 KBSS_SZ = $(shell $(CROSS_COMPILE)size $(obj)/../../../../vmlinux | \
diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S
index 6e8382d5b7a..5392ee63338 100644
--- a/arch/arm/boot/compressed/debug.S
+++ b/arch/arm/boot/compressed/debug.S
@@ -1,6 +1,8 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
+#ifndef CONFIG_DEBUG_SEMIHOSTING
+
 #include CONFIG_DEBUG_LL_INCLUDE
 
 ENTRY(putc)
@@ -10,3 +12,29 @@ ENTRY(putc)
 	busyuart r3, r1
 	mov	 pc, lr
 ENDPROC(putc)
+
+#else
+
+ENTRY(putc)
+	adr	r1, 1f
+	ldmia	r1, {r2, r3}
+	add	r2, r2, r1
+	ldr	r1, [r2, r3]
+	strb	r0, [r1]
+	mov	r0, #0x03		@ SYS_WRITEC
+   ARM(	svc	#0x123456	)
+ THUMB(	svc	#0xab		)
+	mov	pc, lr
+	.align	2
+1:	.word	_GLOBAL_OFFSET_TABLE_ - .
+	.word	semi_writec_buf(GOT)
+ENDPROC(putc)
+
+	.bss
+	.global	semi_writec_buf
+	.type   semi_writec_buf, %object
+semi_writec_buf:
+	.space	4
+	.size	semi_writec_buf, 4
+
+#endif
diff --git a/arch/arm/boot/compressed/head-sa1100.S b/arch/arm/boot/compressed/head-sa1100.S
index 6179d94dd5c..3115e313d9f 100644
--- a/arch/arm/boot/compressed/head-sa1100.S
+++ b/arch/arm/boot/compressed/head-sa1100.S
@@ -11,6 +11,7 @@
 #include <asm/mach-types.h>
 
 		.section        ".start", "ax"
+		.arch	armv4
 
 __SA1100_start:
 
diff --git a/arch/arm/boot/compressed/head-shark.S b/arch/arm/boot/compressed/head-shark.S
index 089c560e07f..92b56897ed6 100644
--- a/arch/arm/boot/compressed/head-shark.S
+++ b/arch/arm/boot/compressed/head-shark.S
@@ -18,6 +18,7 @@
 	
 		.section	".start", "ax"
 
+		.arch armv4
 		b	__beginning
 	
 __ofw_data:	.long	0				@ the number of memory blocks
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index fe4d9c3ad76..032a8d98714 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -11,6 +11,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
+	.arch	armv7-a
 /*
  * Debugging stuff
  *
@@ -805,8 +806,8 @@ call_cache_fn:	adr	r12, proc_types
 		.align	2
 		.type	proc_types,#object
 proc_types:
-		.word	0x00000000		@ old ARM ID
-		.word	0x0000f000
+		.word	0x41000000		@ old ARM ID
+		.word	0xff00f000
 		mov	pc, lr
  THUMB(		nop				)
 		mov	pc, lr
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 1460d9b88ad..8e1248f01fa 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -409,8 +409,8 @@
 			ti,hwmods = "gpmc";
 			reg = <0x50000000 0x2000>;
 			interrupts = <100>;
-			num-cs = <7>;
-			num-waitpins = <2>;
+			gpmc,num-cs = <7>;
+			gpmc,num-waitpins = <2>;
 			#address-cells = <2>;
 			#size-cells = <1>;
 			status = "disabled";
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 3ee63d128e2..76db557adbe 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -39,8 +39,9 @@
 	};
 
 	soc {
-		ranges = <0          0 0xd0000000 0x100000
-			  0xf0000000 0 0xf0000000 0x1000000>;
+		ranges = <0          0 0xd0000000 0x100000  /* Internal registers 1MiB */
+			  0xe0000000 0 0xe0000000 0x8100000 /* PCIe */
+			  0xf0000000 0 0xf0000000 0x1000000 /* Device Bus, NOR 16MiB  */>;
 
 		internal-regs {
 			serial@12000 {
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index 46b785064dd..fdea75c7341 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -27,8 +27,9 @@
 	};
 
 	soc {
-		ranges = <0          0 0xd0000000 0x100000
-			  0xf0000000 0 0xf0000000 0x8000000>;
+		ranges = <0          0 0xd0000000 0x100000	/* Internal registers 1MiB */
+			  0xe0000000 0 0xe0000000 0x8100000     /* PCIe */
+			  0xf0000000 0 0xf0000000 0x8000000     /* Device Bus, NOR 128MiB   */>;
 
 		internal-regs {
 			serial@12000 {
diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi
index f0052dccf9a..1e12aeff403 100644
--- a/arch/arm/boot/dts/bcm2835.dtsi
+++ b/arch/arm/boot/dts/bcm2835.dtsi
@@ -44,6 +44,7 @@
 			reg = <0x7e201000 0x1000>;
 			interrupts = <2 25>;
 			clock-frequency = <3000000>;
+			arm,primecell-periphid = <0x00241011>;
 		};
 
 		gpio: gpio {
diff --git a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
index d1650fb34c0..ded558bb0f3 100644
--- a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
@@ -763,7 +763,7 @@
 		};
 	};
 
-	pinctrl@03680000 {
+	pinctrl@03860000 {
 		gpz: gpz {
 			gpio-controller;
 			#gpio-cells = <2>;
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 0673524238a..fc9fb3d526e 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -161,9 +161,9 @@
 		interrupts = <0 50 0>;
 	};
 
-	pinctrl_3: pinctrl@03680000 {
+	pinctrl_3: pinctrl@03860000 {
 		compatible = "samsung,exynos5250-pinctrl";
-		reg = <0x0368000 0x1000>;
+		reg = <0x03860000 0x1000>;
 		interrupts = <0 47 0>;
 	};
 
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index d2550e0bca2..701153992c6 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -141,8 +141,8 @@
 				#size-cells = <0>;
 				compatible = "fsl,imx25-cspi", "fsl,imx35-cspi";
 				reg = <0x43fa4000 0x4000>;
-				clocks = <&clks 62>;
-				clock-names = "ipg";
+				clocks = <&clks 62>, <&clks 62>;
+				clock-names = "ipg", "per";
 				interrupts = <14>;
 				status = "disabled";
 			};
@@ -182,8 +182,8 @@
 				compatible = "fsl,imx25-cspi", "fsl,imx35-cspi";
 				reg = <0x50004000 0x4000>;
 				interrupts = <0>;
-				clocks = <&clks 80>;
-				clock-names = "ipg";
+				clocks = <&clks 80>, <&clks 80>;
+				clock-names = "ipg", "per";
 				status = "disabled";
 			};
 
@@ -210,8 +210,8 @@
 				#size-cells = <0>;
 				compatible = "fsl,imx25-cspi", "fsl,imx35-cspi";
 				reg = <0x50010000 0x4000>;
-				clocks = <&clks 79>;
-				clock-names = "ipg";
+				clocks = <&clks 79>, <&clks 79>;
+				clock-names = "ipg", "per";
 				interrupts = <13>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index ff4bd4873ed..75bd1138651 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -131,7 +131,7 @@
 				compatible = "fsl,imx27-cspi";
 				reg = <0x1000e000 0x1000>;
 				interrupts = <16>;
-				clocks = <&clks 53>, <&clks 0>;
+				clocks = <&clks 53>, <&clks 53>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
@@ -142,7 +142,7 @@
 				compatible = "fsl,imx27-cspi";
 				reg = <0x1000f000 0x1000>;
 				interrupts = <15>;
-				clocks = <&clks 52>, <&clks 0>;
+				clocks = <&clks 52>, <&clks 52>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
@@ -223,7 +223,7 @@
 				compatible = "fsl,imx27-cspi";
 				reg = <0x10017000 0x1000>;
 				interrupts = <6>;
-				clocks = <&clks 51>, <&clks 0>;
+				clocks = <&clks 51>, <&clks 51>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 21bb786c5b3..53fdde69bbf 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -631,7 +631,7 @@
 				compatible = "fsl,imx51-cspi", "fsl,imx35-cspi";
 				reg = <0x83fc0000 0x4000>;
 				interrupts = <38>;
-				clocks = <&clks 55>, <&clks 0>;
+				clocks = <&clks 55>, <&clks 55>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 845982eaac2..eb83aa039b8 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -714,7 +714,7 @@
 				compatible = "fsl,imx53-cspi", "fsl,imx35-cspi";
 				reg = <0x63fc0000 0x4000>;
 				interrupts = <38>;
-				clocks = <&clks 55>, <&clks 0>;
+				clocks = <&clks 55>, <&clks 55>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index 03bd60deb52..eeb734e2570 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -56,9 +56,23 @@
 	};
 };
 
+&omap4_pmx_wkup {
+	pinctrl-names = "default";
+	pinctrl-0 = <
+			&twl6030_wkup_pins
+	>;
+
+	twl6030_wkup_pins: pinmux_twl6030_wkup_pins {
+		pinctrl-single,pins = <
+			0x14 0x2        /* fref_clk0_out.sys_drm_msecure OUTPUT | MODE2 */
+		>;
+	};
+};
+
 &omap4_pmx_core {
 	pinctrl-names = "default";
 	pinctrl-0 = <
+			&twl6030_pins
 			&twl6040_pins
 			&mcpdm_pins
 			&mcbsp1_pins
@@ -66,6 +80,12 @@
 			&tpd12s015_pins
 	>;
 
+	twl6030_pins: pinmux_twl6030_pins {
+		pinctrl-single,pins = <
+			0x15e 0x4118	/* sys_nirq1.sys_nirq1 OMAP_WAKEUP_EN | INPUT_PULLUP | MODE0 */
+		>;
+	};
+
 	twl6040_pins: pinmux_twl6040_pins {
 		pinctrl-single,pins = <
 			0xe0 0x3	/* hdq_sio.gpio_127 OUTPUT | MODE3 */
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index a35d9cd5806..98505a2ef16 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -142,9 +142,23 @@
 	};
 };
 
+&omap4_pmx_wkup {
+	pinctrl-names = "default";
+	pinctrl-0 = <
+			&twl6030_wkup_pins
+	>;
+
+	twl6030_wkup_pins: pinmux_twl6030_wkup_pins {
+		pinctrl-single,pins = <
+			0x14 0x2        /* fref_clk0_out.sys_drm_msecure OUTPUT | MODE2 */
+		>;
+	};
+};
+
 &omap4_pmx_core {
 	pinctrl-names = "default";
 	pinctrl-0 = <
+			&twl6030_pins
 			&twl6040_pins
 			&mcpdm_pins
 			&dmic_pins
@@ -179,6 +193,12 @@
 		>;
 	};
 
+	twl6030_pins: pinmux_twl6030_pins {
+		pinctrl-single,pins = <
+			0x15e 0x4118	/* sys_nirq1.sys_nirq1 OMAP_WAKEUP_EN | INPUT_PULLUP | MODE0 */
+		>;
+	};
+
 	twl6040_pins: pinmux_twl6040_pins {
 		pinctrl-single,pins = <
 			0xe0 0x3	/* hdq_sio.gpio_127 OUTPUT | MODE3 */
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 3dd7ff82582..635cae28301 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -538,6 +538,7 @@
 			interrupts = <0 41 0x4>;
 			ti,hwmods = "timer5";
 			ti,timer-dsp;
+			ti,timer-pwm;
 		};
 
 		timer6: timer@4013a000 {
@@ -574,6 +575,7 @@
 			reg = <0x4803e000 0x80>;
 			interrupts = <0 45 0x4>;
 			ti,hwmods = "timer9";
+			ti,timer-pwm;
 		};
 
 		timer10: timer@48086000 {
@@ -581,6 +583,7 @@
 			reg = <0x48086000 0x80>;
 			interrupts = <0 46 0x4>;
 			ti,hwmods = "timer10";
+			ti,timer-pwm;
 		};
 
 		timer11: timer@48088000 {
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index bff71388e72..17d0ae8672f 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -320,9 +320,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 }
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
+extern void flush_kernel_dcache_page(struct page *);
 
 #define flush_dcache_mmap_lock(mapping) \
 	spin_lock_irq(&(mapping)->tree_lock)
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 7652712d1d1..dba62cb1ad0 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -32,6 +32,8 @@
 
 #define MPIDR_HWID_BITMASK 0xFFFFFF
 
+#define MPIDR_INVALID (~MPIDR_HWID_BITMASK)
+
 #define MPIDR_LEVEL_BITS 8
 #define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
 
diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h
index ac1dd54724b..8017e94acc5 100644
--- a/arch/arm/include/asm/glue-proc.h
+++ b/arch/arm/include/asm/glue-proc.h
@@ -230,6 +230,15 @@
 # endif
 #endif
 
+#ifdef CONFIG_CPU_PJ4B
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_pj4b
+# endif
+#endif
+
 #ifndef MULTI_CPU
 #define cpu_proc_init			__glue(CPU_NAME,_proc_init)
 #define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index 968c0a14e0a..209e6504922 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -30,8 +30,15 @@ static inline void set_my_cpu_offset(unsigned long off)
 static inline unsigned long __my_cpu_offset(void)
 {
 	unsigned long off;
-	/* Read TPIDRPRW */
-	asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : : "memory");
+	register unsigned long *sp asm ("sp");
+
+	/*
+	 * Read TPIDRPRW.
+	 * We want to allow caching the value, so avoid using volatile and
+	 * instead use a fake stack read to hazard against barrier().
+	 */
+	asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : "Q" (*sp));
+
 	return off;
 }
 #define __my_cpu_offset __my_cpu_offset()
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index aaa61b6f50f..e7898320273 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -49,7 +49,7 @@ static inline int cache_ops_need_broadcast(void)
 /*
  * Logical CPU mapping.
  */
-extern int __cpu_logical_map[];
+extern u32 __cpu_logical_map[];
 #define cpu_logical_map(cpu)	__cpu_logical_map[cpu]
 /*
  * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 99a19512ee2..bdf2b8458ec 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -33,18 +33,6 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-/*
- * We need to delay page freeing for SMP as other CPUs can access pages
- * which have been removed but not yet had their TLB entries invalidated.
- * Also, as ARMv7 speculative prefetch can drag new entries into the TLB,
- * we need to apply this same delaying tactic to ensure correct operation.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7)
-#define tlb_fast_mode(tlb)	0
-#else
-#define tlb_fast_mode(tlb)	1
-#endif
-
 #define MMU_GATHER_BUNDLE	8
 
 /*
@@ -112,12 +100,10 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
 	tlb_flush(tlb);
-	if (!tlb_fast_mode(tlb)) {
-		free_pages_and_swap_cache(tlb->pages, tlb->nr);
-		tlb->nr = 0;
-		if (tlb->pages == tlb->local)
-			__tlb_alloc_page(tlb);
-	}
+	free_pages_and_swap_cache(tlb->pages, tlb->nr);
+	tlb->nr = 0;
+	if (tlb->pages == tlb->local)
+		__tlb_alloc_page(tlb);
 }
 
 static inline void
@@ -178,11 +164,6 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 
 static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (tlb_fast_mode(tlb)) {
-		free_page_and_swap_cache(page);
-		return 1; /* avoid calling tlb_flush_mmu */
-	}
-
 	tlb->pages[tlb->nr++] = page;
 	VM_BUG_ON(tlb->nr > tlb->max);
 	return tlb->max - tlb->nr;
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 5af04f6daa3..5859c8bc727 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -82,7 +82,7 @@ void __init arm_dt_init_cpu_maps(void)
 	u32 i, j, cpuidx = 1;
 	u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0;
 
-	u32 tmp_map[NR_CPUS] = { [0 ... NR_CPUS-1] = UINT_MAX };
+	u32 tmp_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID };
 	bool bootcpu_valid = false;
 	cpus = of_find_node_by_path("/cpus");
 
@@ -92,6 +92,9 @@ void __init arm_dt_init_cpu_maps(void)
 	for_each_child_of_node(cpus, cpu) {
 		u32 hwid;
 
+		if (of_node_cmp(cpu->type, "cpu"))
+			continue;
+
 		pr_debug(" * %s...\n", cpu->full_name);
 		/*
 		 * A device tree containing CPU nodes with missing "reg"
@@ -149,9 +152,10 @@ void __init arm_dt_init_cpu_maps(void)
 		tmp_map[i] = hwid;
 	}
 
-	if (WARN(!bootcpu_valid, "DT missing boot CPU MPIDR[23:0], "
-				 "fall back to default cpu_logical_map\n"))
+	if (!bootcpu_valid) {
+		pr_warn("DT missing boot CPU MPIDR[23:0], fall back to default cpu_logical_map\n");
 		return;
+	}
 
 	/*
 	 * Since the boot CPU node contains proper data, and all nodes have
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 8ef8c933780..4fb074c446b 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -134,6 +134,10 @@ void machine_kexec(struct kimage *image)
 	unsigned long reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
+	if (num_online_cpus() > 1) {
+		pr_err("kexec: error: multiple CPUs still online\n");
+		return;
+	}
 
 	page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 282de4826ab..6e8931ccf13 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -184,30 +184,61 @@ int __init reboot_setup(char *str)
 
 __setup("reboot=", reboot_setup);
 
+/*
+ * Called by kexec, immediately prior to machine_kexec().
+ *
+ * This must completely disable all secondary CPUs; simply causing those CPUs
+ * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
+ * kexec'd kernel to use any and all RAM as it sees fit, without having to
+ * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
+ * functionality embodied in disable_nonboot_cpus() to achieve this.
+ */
 void machine_shutdown(void)
 {
-#ifdef CONFIG_SMP
-	smp_send_stop();
-#endif
+	disable_nonboot_cpus();
 }
 
+/*
+ * Halting simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this.
+ */
 void machine_halt(void)
 {
-	machine_shutdown();
+	smp_send_stop();
+
 	local_irq_disable();
 	while (1);
 }
 
+/*
+ * Power-off simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this. When the system power is turned off, it will take all CPUs
+ * with it.
+ */
 void machine_power_off(void)
 {
-	machine_shutdown();
+	smp_send_stop();
+
 	if (pm_power_off)
 		pm_power_off();
 }
 
+/*
+ * Restart requires that the secondary CPUs stop performing any activity
+ * while the primary CPU resets the system. Systems with a single CPU can
+ * use soft_restart() as their machine descriptor's .restart hook, since that
+ * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * provide a HW restart implementation, to ensure that all CPUs reset at once.
+ * This is required so that any code running after reset on the primary CPU
+ * doesn't have to co-ordinate with other CPUs to ensure they aren't still
+ * executing pre-reset code, and using RAM that the primary CPU's code wishes
+ * to use. Implementing such co-ordination would be essentially impossible.
+ */
 void machine_restart(char *cmd)
 {
-	machine_shutdown();
+	smp_send_stop();
 
 	arm_pm_restart(reboot_mode, cmd);
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1522c7ae31b..b4b1d397592 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -444,7 +444,7 @@ void notrace cpu_init(void)
 	    : "r14");
 }
 
-int __cpu_logical_map[NR_CPUS];
+u32 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID };
 
 void __init smp_setup_processor_id(void)
 {
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 550d63cef68..5919eb451bb 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -651,17 +651,6 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static void smp_kill_cpus(cpumask_t *mask)
-{
-	unsigned int cpu;
-	for_each_cpu(cpu, mask)
-		platform_cpu_kill(cpu);
-}
-#else
-static void smp_kill_cpus(cpumask_t *mask) { }
-#endif
-
 void smp_send_stop(void)
 {
 	unsigned long timeout;
@@ -679,8 +668,6 @@ void smp_send_stop(void)
 
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
-
-	smp_kill_cpus(&mask);
 }
 
 /*
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index f10316b4ecd..c5a59546a25 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -13,6 +13,7 @@
 
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/node.h>
@@ -200,6 +201,7 @@ static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
  * cpu topology table
  */
 struct cputopo_arm cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
 
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 37d216d814c..ef1703b9587 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -492,6 +492,11 @@ static void vcpu_pause(struct kvm_vcpu *vcpu)
 	wait_event_interruptible(*wq, !vcpu->arch.pause);
 }
 
+static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.target >= 0;
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -508,8 +513,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	int ret;
 	sigset_t sigsaved;
 
-	/* Make sure they initialize the vcpu with KVM_ARM_VCPU_INIT */
-	if (unlikely(vcpu->arch.target < 0))
+	if (unlikely(!kvm_vcpu_initialized(vcpu)))
 		return -ENOEXEC;
 
 	ret = kvm_vcpu_first_run_init(vcpu);
@@ -710,6 +714,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
 		struct kvm_one_reg reg;
+
+		if (unlikely(!kvm_vcpu_initialized(vcpu)))
+			return -ENOEXEC;
+
 		if (copy_from_user(&reg, argp, sizeof(reg)))
 			return -EFAULT;
 		if (ioctl == KVM_SET_ONE_REG)
@@ -722,6 +730,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_reg_list reg_list;
 		unsigned n;
 
+		if (unlikely(!kvm_vcpu_initialized(vcpu)))
+			return -ENOEXEC;
+
 		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
 			return -EFAULT;
 		n = reg_list.n;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 965706578f1..84ba67b982c 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -43,7 +43,14 @@ static phys_addr_t hyp_idmap_vector;
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+	/*
+	 * This function also gets called when dealing with HYP page
+	 * tables. As HYP doesn't have an associated struct kvm (and
+	 * the HYP page tables are fairly static), we don't do
+	 * anything there.
+	 */
+	if (kvm)
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
@@ -78,18 +85,20 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static void clear_pud_entry(pud_t *pud)
+static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
 	pmd_t *pmd_table = pmd_offset(pud, 0);
 	pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
 	pmd_free(NULL, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_pmd_entry(pmd_t *pmd)
+static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
 	pte_free_kernel(NULL, pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -100,11 +109,12 @@ static bool pmd_empty(pmd_t *pmd)
 	return page_count(pmd_page) == 1;
 }
 
-static void clear_pte_entry(pte_t *pte)
+static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
 {
 	if (pte_present(*pte)) {
 		kvm_set_pte(pte, __pte(0));
 		put_page(virt_to_page(pte));
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
 	}
 }
 
@@ -114,7 +124,8 @@ static bool pte_empty(pte_t *pte)
 	return page_count(pte_page) == 1;
 }
 
-static void unmap_range(pgd_t *pgdp, unsigned long long start, u64 size)
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+			unsigned long long start, u64 size)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -138,15 +149,15 @@ static void unmap_range(pgd_t *pgdp, unsigned long long start, u64 size)
 		}
 
 		pte = pte_offset_kernel(pmd, addr);
-		clear_pte_entry(pte);
+		clear_pte_entry(kvm, pte, addr);
 		range = PAGE_SIZE;
 
 		/* If we emptied the pte, walk back up the ladder */
 		if (pte_empty(pte)) {
-			clear_pmd_entry(pmd);
+			clear_pmd_entry(kvm, pmd, addr);
 			range = PMD_SIZE;
 			if (pmd_empty(pmd)) {
-				clear_pud_entry(pud);
+				clear_pud_entry(kvm, pud, addr);
 				range = PUD_SIZE;
 			}
 		}
@@ -165,14 +176,14 @@ void free_boot_hyp_pgd(void)
 	mutex_lock(&kvm_hyp_pgd_mutex);
 
 	if (boot_hyp_pgd) {
-		unmap_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
-		unmap_range(boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 		kfree(boot_hyp_pgd);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
-		unmap_range(hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
 	kfree(init_bounce_page);
 	init_bounce_page = NULL;
@@ -200,9 +211,10 @@ void free_hyp_pgds(void)
 
 	if (hyp_pgd) {
 		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
-			unmap_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
-			unmap_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+
 		kfree(hyp_pgd);
 		hyp_pgd = NULL;
 	}
@@ -393,7 +405,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
  */
 static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 {
-	unmap_range(kvm->arch.pgd, start, size);
+	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
 /**
@@ -675,7 +687,6 @@ static void handle_hva_to_gpa(struct kvm *kvm,
 static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 {
 	unmap_stage2_range(kvm, gpa, PAGE_SIZE);
-	kvm_tlb_flush_vmid_ipa(kvm, gpa);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c
index 027c9e7f0d1..f7e504b7874 100644
--- a/arch/arm/mach-exynos/common.c
+++ b/arch/arm/mach-exynos/common.c
@@ -386,6 +386,8 @@ int __init exynos_fdt_map_chipid(unsigned long node, const char *uname,
 
 void __init exynos_init_io(struct map_desc *mach_desc, int size)
 {
+	debug_ll_io_init();
+
 #ifdef CONFIG_OF
 	if (initial_boot_params)
 		of_scan_flat_dt(exynos_fdt_map_chipid, NULL);
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index dda9a2bd3ac..4e3148ce852 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -181,14 +181,14 @@ static const char *periph_clk2_sels[]	= { "pll3_usb_otg", "osc", "osc", "dummy",
 static const char *periph2_clk2_sels[]	= { "pll3_usb_otg", "pll2_bus", };
 static const char *periph_sels[]	= { "periph_pre", "periph_clk2", };
 static const char *periph2_sels[]	= { "periph2_pre", "periph2_clk2", };
-static const char *axi_sels[]		= { "periph", "pll2_pfd2_396m", "pll3_pfd1_540m", };
+static const char *axi_sels[]		= { "periph", "pll2_pfd2_396m", "periph", "pll3_pfd1_540m", };
 static const char *audio_sels[]	= { "pll4_post_div", "pll3_pfd2_508m", "pll3_pfd3_454m", "pll3_usb_otg", };
 static const char *gpu_axi_sels[]	= { "axi", "ahb", };
 static const char *gpu2d_core_sels[]	= { "axi", "pll3_usb_otg", "pll2_pfd0_352m", "pll2_pfd2_396m", };
 static const char *gpu3d_core_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", };
 static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll3_pfd0_720m", };
 static const char *ipu_sels[]		= { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", };
-static const char *ldb_di_sels[]	= { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", };
+static const char *ldb_di_sels[]	= { "pll5_video_div", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", };
 static const char *ipu_di_pre_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video_div", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", };
 static const char *ipu1_di0_sels[]	= { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
 static const char *ipu1_di1_sels[]	= { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
diff --git a/arch/arm/mach-kirkwood/board-ts219.c b/arch/arm/mach-kirkwood/board-ts219.c
index acb0187c7ee..4695d5f35fc 100644
--- a/arch/arm/mach-kirkwood/board-ts219.c
+++ b/arch/arm/mach-kirkwood/board-ts219.c
@@ -41,13 +41,3 @@ void __init qnap_dt_ts219_init(void)
 
 	pm_power_off = qnap_tsx1x_power_off;
 }
-
-/* FIXME: Will not work with DT. Maybe use MPP40_GPIO? */
-static int __init ts219_pci_init(void)
-{
-	if (machine_is_ts219())
-		kirkwood_pcie_init(KW_PCIE0);
-
-	return 0;
-}
-subsys_initcall(ts219_pci_init);
diff --git a/arch/arm/mach-kirkwood/mpp.c b/arch/arm/mach-kirkwood/mpp.c
index 827cde42414..e96fd71abd7 100644
--- a/arch/arm/mach-kirkwood/mpp.c
+++ b/arch/arm/mach-kirkwood/mpp.c
@@ -22,9 +22,10 @@ static unsigned int __init kirkwood_variant(void)
 
 	kirkwood_pcie_id(&dev, &rev);
 
-	if ((dev == MV88F6281_DEV_ID && rev >= MV88F6281_REV_A0) ||
-	    (dev == MV88F6282_DEV_ID))
+	if (dev == MV88F6281_DEV_ID && rev >= MV88F6281_REV_A0)
 		return MPP_F6281_MASK;
+	if (dev == MV88F6282_DEV_ID)
+		return MPP_F6282_MASK;
 	if (dev == MV88F6192_DEV_ID && rev >= MV88F6192_REV_A0)
 		return MPP_F6192_MASK;
 	if (dev == MV88F6180_DEV_ID)
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index 53e8391192c..5476669ba90 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -32,15 +32,21 @@ ENTRY(ll_set_cpu_coherent)
 
 	/* Add CPU to SMP group - Atomic */
 	add	r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET
-	ldr	r2, [r3]
+1:
+	ldrex	r2, [r3]
 	orr	r2, r2, r1
-	str	r2, [r3]
+	strex 	r0, r2, [r3]
+	cmp	r0, #0
+	bne 1b
 
 	/* Enable coherency on CPU - Atomic */
-	add	r3, r0, #ARMADA_XP_CFB_CFG_REG_OFFSET
-	ldr	r2, [r3]
+	add	r3, r3, #ARMADA_XP_CFB_CFG_REG_OFFSET
+1:
+	ldrex	r2, [r3]
 	orr	r2, r2, r1
-	str	r2, [r3]
+	strex	r0, r2, [r3]
+	cmp	r0, #0
+	bne 1b
 
 	dsb
 
diff --git a/arch/arm/mach-omap2/clock36xx.c b/arch/arm/mach-omap2/clock36xx.c
index 8f3bf4e5090..bbd6a3f717e 100644
--- a/arch/arm/mach-omap2/clock36xx.c
+++ b/arch/arm/mach-omap2/clock36xx.c
@@ -20,11 +20,12 @@
 
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/io.h>
 
 #include "clock.h"
 #include "clock36xx.h"
-
+#define to_clk_divider(_hw) container_of(_hw, struct clk_divider, hw)
 
 /**
  * omap36xx_pwrdn_clk_enable_with_hsdiv_restore - enable clocks suffering
@@ -39,29 +40,28 @@
  */
 int omap36xx_pwrdn_clk_enable_with_hsdiv_restore(struct clk_hw *clk)
 {
-	struct clk_hw_omap *parent;
+	struct clk_divider *parent;
 	struct clk_hw *parent_hw;
-	u32 dummy_v, orig_v, clksel_shift;
+	u32 dummy_v, orig_v;
 	int ret;
 
 	/* Clear PWRDN bit of HSDIVIDER */
 	ret = omap2_dflt_clk_enable(clk);
 
 	parent_hw = __clk_get_hw(__clk_get_parent(clk->clk));
-	parent = to_clk_hw_omap(parent_hw);
+	parent = to_clk_divider(parent_hw);
 
 	/* Restore the dividers */
 	if (!ret) {
-		clksel_shift = __ffs(parent->clksel_mask);
-		orig_v = __raw_readl(parent->clksel_reg);
+		orig_v = __raw_readl(parent->reg);
 		dummy_v = orig_v;
 
 		/* Write any other value different from the Read value */
-		dummy_v ^= (1 << clksel_shift);
-		__raw_writel(dummy_v, parent->clksel_reg);
+		dummy_v ^= (1 << parent->shift);
+		__raw_writel(dummy_v, parent->reg);
 
 		/* Write the original divider */
-		__raw_writel(orig_v, parent->clksel_reg);
+		__raw_writel(orig_v, parent->reg);
 	}
 
 	return ret;
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index 075f7cc5102..69337af748c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -2007,6 +2007,13 @@ static struct omap_hwmod am33xx_uart1_hwmod = {
 	},
 };
 
+/* uart2 */
+static struct omap_hwmod_dma_info uart2_edma_reqs[] = {
+	{ .name = "tx",	.dma_req = 28, },
+	{ .name = "rx",	.dma_req = 29, },
+	{ .dma_req = -1 }
+};
+
 static struct omap_hwmod_irq_info am33xx_uart2_irqs[] = {
 	{ .irq = 73 + OMAP_INTC_START, },
 	{ .irq = -1 },
@@ -2018,7 +2025,7 @@ static struct omap_hwmod am33xx_uart2_hwmod = {
 	.clkdm_name	= "l4ls_clkdm",
 	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart2_irqs,
-	.sdma_reqs	= uart1_edma_reqs,
+	.sdma_reqs	= uart2_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_ck",
 	.prcm		= {
 		.omap4	= {
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index c01859398b5..5a2d8034c8d 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -546,8 +546,10 @@ static void __init prcm_setup_regs(void)
 	/* Clear any pending PRCM interrupts */
 	omap2_prm_write_mod_reg(0, OCP_MOD, OMAP3_PRM_IRQSTATUS_MPU_OFFSET);
 
-	if (omap3_has_iva())
-		omap3_iva_idle();
+	/*
+	 * We need to idle iva2_pwrdm even on am3703 with no iva2.
+	 */
+	omap3_iva_idle();
 
 	omap3_d2d_idle();
 }
diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c
index 9936c180bf0..8f595c0cc8d 100644
--- a/arch/arm/mach-prima2/pm.c
+++ b/arch/arm/mach-prima2/pm.c
@@ -101,8 +101,10 @@ static int __init sirfsoc_of_pwrc_init(void)
 	struct device_node *np;
 
 	np = of_find_matching_node(NULL, pwrc_ids);
-	if (!np)
-		panic("unable to find compatible pwrc node in dtb\n");
+	if (!np) {
+		pr_err("unable to find compatible sirf pwrc node in dtb\n");
+		return -ENOENT;
+	}
 
 	/*
 	 * pwrc behind rtciobrg is not located in memory space
diff --git a/arch/arm/mach-prima2/rstc.c b/arch/arm/mach-prima2/rstc.c
index 435019ca0a4..d5e0cbc934c 100644
--- a/arch/arm/mach-prima2/rstc.c
+++ b/arch/arm/mach-prima2/rstc.c
@@ -28,8 +28,10 @@ static int __init sirfsoc_of_rstc_init(void)
 	struct device_node *np;
 
 	np = of_find_matching_node(NULL, rstc_ids);
-	if (!np)
-		panic("unable to find compatible rstc node in dtb\n");
+	if (!np) {
+		pr_err("unable to find compatible sirf rstc node in dtb\n");
+		return -ENOENT;
+	}
 
 	sirfsoc_rstc_base = of_iomap(np, 0);
 	if (!sirfsoc_rstc_base)
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index fdf3894b1cc..9696f364686 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -252,7 +252,7 @@ static struct sh_timer_config cmt10_platform_data = {
 	.name = "CMT10",
 	.channel_offset = 0x10,
 	.timer_bit = 0,
-	.clockevent_rating = 125,
+	.clockevent_rating = 80,
 	.clocksource_rating = 125,
 };
 
diff --git a/arch/arm/mach-ux500/board-mop500-regulators.c b/arch/arm/mach-ux500/board-mop500-regulators.c
index 33c353bc1c4..d6b7c8556fa 100644
--- a/arch/arm/mach-ux500/board-mop500-regulators.c
+++ b/arch/arm/mach-ux500/board-mop500-regulators.c
@@ -374,6 +374,7 @@ static struct ab8500_regulator_reg_init ab8500_reg_init[] = {
 static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
 	/* supplies to the display/camera */
 	[AB8500_LDO_AUX1] = {
+		.supply_regulator = "ab8500-ext-supply3",
 		.constraints = {
 			.name = "V-DISPLAY",
 			.min_uV = 2800000,
@@ -387,6 +388,7 @@ static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
 	},
 	/* supplies to the on-board eMMC */
 	[AB8500_LDO_AUX2] = {
+		.supply_regulator = "ab8500-ext-supply3",
 		.constraints = {
 			.name = "V-eMMC1",
 			.min_uV = 1100000,
@@ -402,6 +404,7 @@ static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
 	},
 	/* supply for VAUX3, supplies to SDcard slots */
 	[AB8500_LDO_AUX3] = {
+		.supply_regulator = "ab8500-ext-supply3",
 		.constraints = {
 			.name = "V-MMC-SD",
 			.min_uV = 1100000,
diff --git a/arch/arm/mach-ux500/cpuidle.c b/arch/arm/mach-ux500/cpuidle.c
index 317a2be129f..a45dd09daed 100644
--- a/arch/arm/mach-ux500/cpuidle.c
+++ b/arch/arm/mach-ux500/cpuidle.c
@@ -21,6 +21,7 @@
 #include <asm/proc-fns.h>
 
 #include "db8500-regs.h"
+#include "id.h"
 
 static atomic_t master = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(master_lock);
@@ -114,6 +115,9 @@ static struct cpuidle_driver ux500_idle_driver = {
 
 int __init ux500_idle_init(void)
 {
+	if (!(cpu_is_u8500_family() || cpu_is_ux540_family()))
+		return -ENODEV;
+
 	/* Configure wake up reasons */
 	prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) |
 			     PRCMU_WAKEUP(ABB));
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 15451ee4acc..515b00064da 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -92,6 +92,14 @@ ENTRY(v7_flush_dcache_louis)
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
 	ALT_SMP(ands	r3, r0, #(7 << 21))	@ extract LoUIS from clidr
 	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
+#ifdef CONFIG_ARM_ERRATA_643719
+	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
+	ALT_UP(moveq	pc, lr)			@ LoUU is zero, so nothing to do
+	ldreq	r1, =0x410fc090                 @ ID of ARM Cortex A9 r0p?
+	biceq	r2, r2, #0x0000000f             @ clear minor revision number
+	teqeq	r2, r1                          @ test for errata affected core and if so...
+	orreqs	r3, #(1 << 21)			@   fix LoUIS value (and set flags state to 'ne')
+#endif
 	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
 	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
 	moveq	pc, lr				@ return if level == 0
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 0d473cce501..32aa5861119 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -301,6 +301,39 @@ void flush_dcache_page(struct page *page)
 EXPORT_SYMBOL(flush_dcache_page);
 
 /*
+ * Ensure cache coherency for the kernel mapping of this page. We can
+ * assume that the page is pinned via kmap.
+ *
+ * If the page only exists in the page cache and there are no user
+ * space mappings, this is a no-op since the page was already marked
+ * dirty at creation.  Otherwise, we need to flush the dirty kernel
+ * cache lines directly.
+ */
+void flush_kernel_dcache_page(struct page *page)
+{
+	if (cache_is_vivt() || cache_is_vipt_aliasing()) {
+		struct address_space *mapping;
+
+		mapping = page_mapping(page);
+
+		if (!mapping || mapping_mapped(mapping)) {
+			void *addr;
+
+			addr = page_address(page);
+			/*
+			 * kmap_atomic() doesn't set the page virtual
+			 * address for highmem pages, and
+			 * kunmap_atomic() takes care of cache
+			 * flushing already.
+			 */
+			if (!IS_ENABLED(CONFIG_HIGHMEM) || addr)
+				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+		}
+	}
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+/*
  * Flush an anonymous page so that users of get_user_pages()
  * can safely access the data.  The expected sequence is:
  *
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e0d8565671a..4d409e6a552 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -616,10 +616,12 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 			unsigned long end, phys_addr_t phys,
 			const struct mem_type *type)
 {
+	pmd_t *p = pmd;
+
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * In classic MMU format, puds and pmds are folded in to
@@ -638,7 +640,7 @@ static void __init map_init_section(pmd_t *pmd, unsigned long addr,
 		phys += SECTION_SIZE;
 	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
-	flush_pmd_entry(pmd);
+	flush_pmd_entry(p);
 }
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
@@ -661,7 +663,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		 */
 		if (type->prot_sect &&
 				((addr | next | phys) & ~SECTION_MASK) == 0) {
-			map_init_section(pmd, addr, next, phys, type);
+			__map_init_section(pmd, addr, next, phys, type);
 		} else {
 			alloc_init_pte(pmd, addr, next,
 						__phys_to_pfn(phys), type);
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index d51225f90ae..eb5293a69a8 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -57,6 +57,12 @@ void flush_dcache_page(struct page *page)
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
+void flush_kernel_dcache_page(struct page *page)
+{
+	__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long uaddr, void *dst, const void *src,
 		       unsigned long len)
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index d217e9795d7..aaeb6c127c7 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -81,7 +81,6 @@ ENDPROC(cpu_fa526_reset)
  */
 	.align	4
 ENTRY(cpu_fa526_do_idle)
-	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
 	mov	pc, lr
 
 
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index f9a0aa725ea..e3c48a3fe06 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -333,3 +333,8 @@ ENTRY(\name\()_tlb_fns)
 	.endif
 	.size	\name\()_tlb_fns, . - \name\()_tlb_fns
 .endm
+
+.macro globl_equ x, y
+	.globl	\x
+	.equ	\x, \y
+.endm
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2c73a7301ff..e35fec34453 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -140,6 +140,29 @@ ENTRY(cpu_v7_do_resume)
 ENDPROC(cpu_v7_do_resume)
 #endif
 
+#ifdef CONFIG_CPU_PJ4B
+	globl_equ	cpu_pj4b_switch_mm,     cpu_v7_switch_mm
+	globl_equ	cpu_pj4b_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_pj4b_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_pj4b_proc_fin, 	cpu_v7_proc_fin
+	globl_equ	cpu_pj4b_reset,	   	cpu_v7_reset
+#ifdef CONFIG_PJ4B_ERRATA_4742
+ENTRY(cpu_pj4b_do_idle)
+	dsb					@ WFI may enter a low-power mode
+	wfi
+	dsb					@barrier
+	mov	pc, lr
+ENDPROC(cpu_pj4b_do_idle)
+#else
+	globl_equ	cpu_pj4b_do_idle,  	cpu_v7_do_idle
+#endif
+	globl_equ	cpu_pj4b_dcache_clean_area,	cpu_v7_dcache_clean_area
+	globl_equ	cpu_pj4b_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_pj4b_do_resume,	cpu_v7_do_resume
+	globl_equ	cpu_pj4b_suspend_size,	cpu_v7_suspend_size
+
+#endif
+
 	__CPUINIT
 
 /*
@@ -350,6 +373,9 @@ __v7_setup_stack:
 
 	@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
 	define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+#ifdef CONFIG_CPU_PJ4B
+	define_processor_functions pj4b, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+#endif
 
 	.section ".rodata"
 
@@ -362,7 +388,7 @@ __v7_setup_stack:
 	/*
 	 * Standard v7 proc info content
 	 */
-.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0
+.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions
 	ALT_SMP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
 			PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags)
 	ALT_UP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
@@ -375,7 +401,7 @@ __v7_setup_stack:
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \
 		HWCAP_EDSP | HWCAP_TLS | \hwcaps
 	.long	cpu_v7_name
-	.long	v7_processor_functions
+	.long	\proc_fns
 	.long	v7wbi_tlb_fns
 	.long	v6_user_fns
 	.long	v7_cache_fns
@@ -407,12 +433,14 @@ __v7_ca9mp_proc_info:
 	/*
 	 * Marvell PJ4B processor.
 	 */
+#ifdef CONFIG_CPU_PJ4B
 	.type   __v7_pj4b_proc_info, #object
 __v7_pj4b_proc_info:
-	.long	0x562f5840
-	.long	0xfffffff0
-	__v7_proc __v7_pj4b_setup
+	.long	0x560f5800
+	.long	0xff0fff00
+	__v7_proc __v7_pj4b_setup, proc_fns = pj4b_processor_functions
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
+#endif
 
 	/*
 	 * ARM Ltd. Cortex A7 processor.
diff --git a/arch/arm/plat-samsung/include/plat/uncompress.h b/arch/arm/plat-samsung/include/plat/uncompress.h
index 438b24846e7..02b66d723d1 100644
--- a/arch/arm/plat-samsung/include/plat/uncompress.h
+++ b/arch/arm/plat-samsung/include/plat/uncompress.h
@@ -66,6 +66,9 @@ uart_rd(unsigned int reg)
 
 static void putc(int ch)
 {
+	if (!config_enabled(CONFIG_DEBUG_LL))
+		return;
+
 	if (uart_rd(S3C2410_UFCON) & S3C2410_UFCON_FIFOMODE) {
 		int level;
 
@@ -118,7 +121,12 @@ static void arch_decomp_error(const char *x)
 #ifdef CONFIG_S3C_BOOT_UART_FORCE_FIFO
 static inline void arch_enable_uart_fifo(void)
 {
-	u32 fifocon = uart_rd(S3C2410_UFCON);
+	u32 fifocon;
+
+	if (!config_enabled(CONFIG_DEBUG_LL))
+		return;
+
+	fifocon = uart_rd(S3C2410_UFCON);
 
 	if (!(fifocon & S3C2410_UFCON_FIFOMODE)) {
 		fifocon |= S3C2410_UFCON_RESETBOTH;
diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c
index 53210ec4e8e..bd7124c87fe 100644
--- a/arch/arm/plat-samsung/pm.c
+++ b/arch/arm/plat-samsung/pm.c
@@ -16,6 +16,7 @@
 #include <linux/suspend.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
+#include <linux/of.h>
 #include <linux/serial_core.h>
 #include <linux/io.h>
 
@@ -261,7 +262,8 @@ static int s3c_pm_enter(suspend_state_t state)
 	 * require a full power-cycle)
 	*/
 
-	if (!any_allowed(s3c_irqwake_intmask, s3c_irqwake_intallow) &&
+	if (!of_have_populated_dt() &&
+	    !any_allowed(s3c_irqwake_intmask, s3c_irqwake_intallow) &&
 	    !any_allowed(s3c_irqwake_eintmask, s3c_irqwake_eintallow)) {
 		printk(KERN_ERR "%s: No wake-up sources!\n", __func__);
 		printk(KERN_ERR "%s: Aborting sleep\n", __func__);
@@ -270,8 +272,11 @@ static int s3c_pm_enter(suspend_state_t state)
 
 	/* save all necessary core registers not covered by the drivers */
 
-	samsung_pm_save_gpios();
-	samsung_pm_saved_gpios();
+	if (!of_have_populated_dt()) {
+		samsung_pm_save_gpios();
+		samsung_pm_saved_gpios();
+	}
+
 	s3c_pm_save_uarts();
 	s3c_pm_save_core();
 
@@ -310,8 +315,11 @@ static int s3c_pm_enter(suspend_state_t state)
 
 	s3c_pm_restore_core();
 	s3c_pm_restore_uarts();
-	samsung_pm_restore_gpios();
-	s3c_pm_restored_gpios();
+
+	if (!of_have_populated_dt()) {
+		samsung_pm_restore_gpios();
+		s3c_pm_restored_gpios();
+	}
 
 	s3c_pm_debug_init();
 
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 7df1aad29b6..41b4f626d55 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -34,6 +34,7 @@ EXPORT_SYMBOL(__strnlen_user);
 EXPORT_SYMBOL(__strncpy_from_user);
 
 EXPORT_SYMBOL(copy_page);
+EXPORT_SYMBOL(clear_page);
 
 EXPORT_SYMBOL(__copy_from_user);
 EXPORT_SYMBOL(__copy_to_user);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c7e047049f2..1d1314280a0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -390,6 +390,16 @@ el0_sync_compat:
 	b.eq	el0_fpsimd_exc
 	cmp	x24, #ESR_EL1_EC_UNKNOWN	// unknown exception in EL0
 	b.eq	el0_undef
+	cmp	x24, #ESR_EL1_EC_CP15_32	// CP15 MRC/MCR trap
+	b.eq	el0_undef
+	cmp	x24, #ESR_EL1_EC_CP15_64	// CP15 MRRC/MCRR trap
+	b.eq	el0_undef
+	cmp	x24, #ESR_EL1_EC_CP14_MR	// CP14 MRC/MCR trap
+	b.eq	el0_undef
+	cmp	x24, #ESR_EL1_EC_CP14_LS	// CP14 LDC/STC trap
+	b.eq	el0_undef
+	cmp	x24, #ESR_EL1_EC_CP14_64	// CP14 MRRC/MCRR trap
+	b.eq	el0_undef
 	cmp	x24, #ESR_EL1_EC_BREAKPT_EL0	// debug exception in EL0
 	b.ge	el0_dbg
 	b	el0_inv
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 1e49e5eb81e..9ba33c40cdf 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1336,6 +1336,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 		return;
 	}
 
+	perf_callchain_store(entry, regs->pc);
 	tail = (struct frame_tail __user *)regs->regs[29];
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH &&
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 61d7dd29f75..f30852d2859 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -267,7 +267,8 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 		return;
 #endif
 
-	if (show_unhandled_signals) {
+	if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
+	    printk_ratelimit()) {
 		pr_info("%s[%d]: undefined instruction: pc=%p\n",
 			current->comm, task_pid_nr(current), pc);
 		dump_instr(KERN_INFO, regs);
@@ -294,7 +295,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
 	}
 #endif
 
-	if (show_unhandled_signals) {
+	if (show_unhandled_signals && printk_ratelimit()) {
 		pr_info("%s[%d]: syscall %d\n", current->comm,
 			task_pid_nr(current), (int)regs->syscallno);
 		dump_instr("", regs);
@@ -310,14 +311,20 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
  */
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 {
+	siginfo_t info;
+	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
 	pr_crit("Bad mode in %s handler detected, code 0x%08x\n",
 		handler[reason], esr);
+	__show_regs(regs);
+
+	info.si_signo = SIGILL;
+	info.si_errno = 0;
+	info.si_code  = ILL_ILLOPC;
+	info.si_addr  = pc;
 
-	die("Oops - bad mode", regs, 0);
-	local_irq_disable();
-	panic("bad mode");
+	arm64_notify_die("Oops - bad mode", regs, &info, 0);
 }
 
 void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 98af6e760cc..1426468b77f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -113,7 +113,8 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 {
 	struct siginfo si;
 
-	if (show_unhandled_signals) {
+	if (show_unhandled_signals && unhandled_signal(tsk, sig) &&
+	    printk_ratelimit()) {
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
 			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
 			addr, esr);
diff --git a/arch/ia64/include/asm/irqflags.h b/arch/ia64/include/asm/irqflags.h
index 1bf2cf2f4ab..cec6c06b52c 100644
--- a/arch/ia64/include/asm/irqflags.h
+++ b/arch/ia64/include/asm/irqflags.h
@@ -11,6 +11,7 @@
 #define _ASM_IA64_IRQFLAGS_H
 
 #include <asm/pal.h>
+#include <asm/kregs.h>
 
 #ifdef CONFIG_IA64_DEBUG_IRQ
 extern unsigned long last_cli_ip;
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index c3ffe3e54ed..ef3a9de0195 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -46,12 +46,6 @@
 #include <asm/tlbflush.h>
 #include <asm/machvec.h>
 
-#ifdef CONFIG_SMP
-# define tlb_fast_mode(tlb)	((tlb)->nr == ~0U)
-#else
-# define tlb_fast_mode(tlb)	(1)
-#endif
-
 /*
  * If we can't allocate a page to make a big batch of page pointers
  * to work on, then just handle a few from the on-stack structure.
@@ -60,7 +54,7 @@
 
 struct mmu_gather {
 	struct mm_struct	*mm;
-	unsigned int		nr;		/* == ~0U => fast mode */
+	unsigned int		nr;
 	unsigned int		max;
 	unsigned char		fullmm;		/* non-zero means full mm flush */
 	unsigned char		need_flush;	/* really unmapped some PTEs? */
@@ -103,6 +97,7 @@ extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
 static inline void
 ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
 {
+	unsigned long i;
 	unsigned int nr;
 
 	if (!tlb->need_flush)
@@ -141,13 +136,11 @@ ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long e
 
 	/* lastly, release the freed pages */
 	nr = tlb->nr;
-	if (!tlb_fast_mode(tlb)) {
-		unsigned long i;
-		tlb->nr = 0;
-		tlb->start_addr = ~0UL;
-		for (i = 0; i < nr; ++i)
-			free_page_and_swap_cache(tlb->pages[i]);
-	}
+
+	tlb->nr = 0;
+	tlb->start_addr = ~0UL;
+	for (i = 0; i < nr; ++i)
+		free_page_and_swap_cache(tlb->pages[i]);
 }
 
 static inline void __tlb_alloc_page(struct mmu_gather *tlb)
@@ -167,20 +160,7 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_m
 	tlb->mm = mm;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
-	/*
-	 * Use fast mode if only 1 CPU is online.
-	 *
-	 * It would be tempting to turn on fast-mode for full_mm_flush as well.  But this
-	 * doesn't work because of speculative accesses and software prefetching: the page
-	 * table of "mm" may (and usually is) the currently active page table and even
-	 * though the kernel won't do any user-space accesses during the TLB shoot down, a
-	 * compiler might use speculation or lfetch.fault on what happens to be a valid
-	 * user-space address.  This in turn could trigger a TLB miss fault (or a VHPT
-	 * walk) and re-insert a TLB entry we just removed.  Slow mode avoids such
-	 * problems.  (We could make fast-mode work by switching the current task to a
-	 * different "mm" during the shootdown.) --davidm 08/02/2002
-	 */
-	tlb->nr = (num_online_cpus() == 1) ? ~0U : 0;
+	tlb->nr = 0;
 	tlb->fullmm = full_mm_flush;
 	tlb->start_addr = ~0UL;
 }
@@ -214,11 +194,6 @@ static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	tlb->need_flush = 1;
 
-	if (tlb_fast_mode(tlb)) {
-		free_page_and_swap_cache(page);
-		return 1; /* avoid calling tlb_flush_mmu */
-	}
-
 	if (!tlb->nr && tlb->pages == tlb->local)
 		__tlb_alloc_page(tlb);
 
diff --git a/arch/m68k/include/asm/gpio.h b/arch/m68k/include/asm/gpio.h
index 8cc83431805..2f6eec1e34b 100644
--- a/arch/m68k/include/asm/gpio.h
+++ b/arch/m68k/include/asm/gpio.h
@@ -86,6 +86,7 @@ static inline int gpio_cansleep(unsigned gpio)
 	return gpio < MCFGPIO_PIN_MAX ? 0 : __gpio_cansleep(gpio);
 }
 
+#ifndef CONFIG_GPIOLIB
 static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 {
 	int err;
@@ -105,5 +106,5 @@ static inline int gpio_request_one(unsigned gpio, unsigned long flags, const cha
 
 	return err;
 }
-
+#endif /* !CONFIG_GPIOLIB */
 #endif
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index d197e7ff62c..ac85f16534a 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -2752,11 +2752,9 @@ func_return	get_new_page
 #ifdef CONFIG_MAC
 
 L(scc_initable_mac):
-	.byte	9,12		/* Reset */
 	.byte	4,0x44		/* x16, 1 stopbit, no parity */
 	.byte	3,0xc0		/* receiver: 8 bpc */
 	.byte	5,0xe2		/* transmitter: 8 bpc, assert dtr/rts */
-	.byte	9,0		/* no interrupts */
 	.byte	10,0		/* NRZ */
 	.byte	11,0x50		/* use baud rate generator */
 	.byte	12,1,13,0	/* 38400 baud */
@@ -2899,6 +2897,7 @@ func_start	serial_init,%d0/%d1/%a0/%a1
 	is_not_mac(L(serial_init_not_mac))
 
 #ifdef SERIAL_DEBUG
+
 /* You may define either or both of these. */
 #define MAC_USE_SCC_A /* Modem port */
 #define MAC_USE_SCC_B /* Printer port */
@@ -2908,9 +2907,21 @@ func_start	serial_init,%d0/%d1/%a0/%a1
 #define mac_scc_cha_b_data_offset	0x4
 #define mac_scc_cha_a_data_offset	0x6
 
+#if defined(MAC_USE_SCC_A) || defined(MAC_USE_SCC_B)
+	movel	%pc@(L(mac_sccbase)),%a0
+	/* Reset SCC device */
+	moveb	#9,%a0@(mac_scc_cha_a_ctrl_offset)
+	moveb	#0xc0,%a0@(mac_scc_cha_a_ctrl_offset)
+	/* Wait for 5 PCLK cycles, which is about 68 CPU cycles */
+	/* 5 / 3.6864 MHz = approx. 1.36 us = 68 / 50 MHz */
+	movel	#35,%d0
+5:
+	subq	#1,%d0
+	jne	5b
+#endif
+
 #ifdef MAC_USE_SCC_A
 	/* Initialize channel A */
-	movel	%pc@(L(mac_sccbase)),%a0
 	lea	%pc@(L(scc_initable_mac)),%a1
 5:	moveb	%a1@+,%d0
 	jmi	6f
@@ -2922,9 +2933,6 @@ func_start	serial_init,%d0/%d1/%a0/%a1
 
 #ifdef MAC_USE_SCC_B
 	/* Initialize channel B */
-#ifndef MAC_USE_SCC_A	/* Load mac_sccbase only if needed */
-	movel	%pc@(L(mac_sccbase)),%a0
-#endif	/* MAC_USE_SCC_A */
 	lea	%pc@(L(scc_initable_mac)),%a1
 7:	moveb	%a1@+,%d0
 	jmi	8f
@@ -2933,6 +2941,7 @@ func_start	serial_init,%d0/%d1/%a0/%a1
 	jra	7b
 8:
 #endif	/* MAC_USE_SCC_B */
+
 #endif	/* SERIAL_DEBUG */
 
 	jra	L(serial_init_done)
@@ -3006,17 +3015,17 @@ func_start	serial_putc,%d0/%d1/%a0/%a1
 
 #ifdef SERIAL_DEBUG
 
-#ifdef MAC_USE_SCC_A
+#if defined(MAC_USE_SCC_A) || defined(MAC_USE_SCC_B)
 	movel	%pc@(L(mac_sccbase)),%a1
+#endif
+
+#ifdef MAC_USE_SCC_A
 3:	btst	#2,%a1@(mac_scc_cha_a_ctrl_offset)
 	jeq	3b
 	moveb	%d0,%a1@(mac_scc_cha_a_data_offset)
 #endif	/* MAC_USE_SCC_A */
 
 #ifdef MAC_USE_SCC_B
-#ifndef MAC_USE_SCC_A	/* Load mac_sccbase only if needed */
-	movel	%pc@(L(mac_sccbase)),%a1
-#endif	/* MAC_USE_SCC_A */
 4:	btst	#2,%a1@(mac_scc_cha_b_ctrl_offset)
 	jeq	4b
 	moveb	%d0,%a1@(mac_scc_cha_b_data_offset)
diff --git a/arch/metag/include/asm/hugetlb.h b/arch/metag/include/asm/hugetlb.h
index f545477e61f..471f481e67f 100644
--- a/arch/metag/include/asm/hugetlb.h
+++ b/arch/metag/include/asm/hugetlb.h
@@ -2,6 +2,7 @@
 #define _ASM_METAG_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
diff --git a/arch/microblaze/include/asm/cacheflush.h b/arch/microblaze/include/asm/cacheflush.h
index 0f553bc009a..ffea82a16d2 100644
--- a/arch/microblaze/include/asm/cacheflush.h
+++ b/arch/microblaze/include/asm/cacheflush.h
@@ -102,21 +102,23 @@ do { \
 
 #define flush_cache_range(vma, start, len) do { } while (0)
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
-do {									\
-	u32 addr = virt_to_phys(dst);					\
-	memcpy((dst), (src), (len));					\
-	if (vma->vm_flags & VM_EXEC) {					\
-		invalidate_icache_range((unsigned) (addr),		\
-					(unsigned) (addr) + PAGE_SIZE);	\
-		flush_dcache_range((unsigned) (addr),			\
-					(unsigned) (addr) + PAGE_SIZE);	\
-	}								\
-} while (0)
-
-#define copy_from_user_page(vma, page, vaddr, dst, src, len)		\
-do {									\
-	memcpy((dst), (src), (len));					\
-} while (0)
+static inline void copy_to_user_page(struct vm_area_struct *vma,
+				     struct page *page, unsigned long vaddr,
+				     void *dst, void *src, int len)
+{
+	u32 addr = virt_to_phys(dst);
+	memcpy(dst, src, len);
+	if (vma->vm_flags & VM_EXEC) {
+		invalidate_icache_range(addr, addr + PAGE_SIZE);
+		flush_dcache_range(addr, addr + PAGE_SIZE);
+	}
+}
+
+static inline void copy_from_user_page(struct vm_area_struct *vma,
+				       struct page *page, unsigned long vaddr,
+				       void *dst, void *src, int len)
+{
+	memcpy(dst, src, len);
+}
 
 #endif /* _ASM_MICROBLAZE_CACHEFLUSH_H */
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index efe59d88178..04e49553bdf 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -99,13 +99,13 @@ static inline int access_ok(int type, const void __user *addr,
 	if ((get_fs().seg < ((unsigned long)addr)) ||
 			(get_fs().seg < ((unsigned long)addr + size - 1))) {
 		pr_debug("ACCESS fail: %s at 0x%08x (size 0x%x), seg 0x%08x\n",
-			type ? "WRITE" : "READ ", (u32)addr, (u32)size,
+			type ? "WRITE" : "READ ", (__force u32)addr, (u32)size,
 			(u32)get_fs().seg);
 		return 0;
 	}
 ok:
 	pr_debug("ACCESS OK: %s at 0x%08x (size 0x%x), seg 0x%08x\n",
-			type ? "WRITE" : "READ ", (u32)addr, (u32)size,
+			type ? "WRITE" : "READ ", (__force u32)addr, (u32)size,
 			(u32)get_fs().seg);
 	return 1;
 }
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index b0baa299f89..01b1b3f94fe 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -428,13 +428,16 @@ static void octeon_restart(char *command)
  */
 static void octeon_kill_core(void *arg)
 {
-	mb();
-	if (octeon_is_simulation()) {
-		/* The simulator needs the watchdog to stop for dead cores */
-		cvmx_write_csr(CVMX_CIU_WDOGX(cvmx_get_core_num()), 0);
+	if (octeon_is_simulation())
 		/* A break instruction causes the simulator stop a core */
-		asm volatile ("sync\nbreak");
-	}
+		asm volatile ("break" ::: "memory");
+
+	local_irq_disable();
+	/* Disable watchdog on this core. */
+	cvmx_write_csr(CVMX_CIU_WDOGX(cvmx_get_core_num()), 0);
+	/* Spin in a low power mode. */
+	while (true)
+		asm volatile ("wait" ::: "memory");
 }
 
 
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 143875c6c95..4d6fa0bf130 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -496,10 +496,6 @@ struct kvm_mips_callbacks {
 			    uint32_t cause);
 	int (*irq_clear) (struct kvm_vcpu *vcpu, unsigned int priority,
 			  uint32_t cause);
-	int (*vcpu_ioctl_get_regs) (struct kvm_vcpu *vcpu,
-				    struct kvm_regs *regs);
-	int (*vcpu_ioctl_set_regs) (struct kvm_vcpu *vcpu,
-				    struct kvm_regs *regs);
 };
 extern struct kvm_mips_callbacks *kvm_mips_callbacks;
 int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks);
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 820116067c1..516e6e9a559 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -117,7 +117,7 @@ get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
 	if (! ((asid += ASID_INC) & ASID_MASK) ) {
 		if (cpu_has_vtag_icache)
 			flush_icache_all();
-#ifdef CONFIG_VIRTUALIZATION
+#ifdef CONFIG_KVM
 		kvm_local_flush_tlb_all();      /* start new asid cycle */
 #else
 		local_flush_tlb_all();	/* start new asid cycle */
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index a3186f2bb8a..5e6cd094739 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -16,6 +16,38 @@
 #include <asm/isadep.h>
 #include <uapi/asm/ptrace.h>
 
+/*
+ * This struct defines the way the registers are stored on the stack during a
+ * system call/exception. As usual the registers k0/k1 aren't being saved.
+ */
+struct pt_regs {
+#ifdef CONFIG_32BIT
+	/* Pad bytes for argument save space on the stack. */
+	unsigned long pad0[6];
+#endif
+
+	/* Saved main processor registers. */
+	unsigned long regs[32];
+
+	/* Saved special registers. */
+	unsigned long cp0_status;
+	unsigned long hi;
+	unsigned long lo;
+#ifdef CONFIG_CPU_HAS_SMARTMIPS
+	unsigned long acx;
+#endif
+	unsigned long cp0_badvaddr;
+	unsigned long cp0_cause;
+	unsigned long cp0_epc;
+#ifdef CONFIG_MIPS_MT_SMTC
+	unsigned long cp0_tcstatus;
+#endif /* CONFIG_MIPS_MT_SMTC */
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+	unsigned long long mpl[3];	  /* MTM{0,1,2} */
+	unsigned long long mtp[3];	  /* MTP{0,1,2} */
+#endif
+} __aligned(8);
+
 struct task_struct;
 
 extern int ptrace_getregs(struct task_struct *child, __s64 __user *data);
diff --git a/arch/mips/include/uapi/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h
index 85789eacbf1..f09ff5ae205 100644
--- a/arch/mips/include/uapi/asm/kvm.h
+++ b/arch/mips/include/uapi/asm/kvm.h
@@ -1,55 +1,135 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Copyright (C) 2013 Cavium, Inc.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #ifndef __LINUX_KVM_MIPS_H
 #define __LINUX_KVM_MIPS_H
 
 #include <linux/types.h>
 
-#define __KVM_MIPS
-
-#define N_MIPS_COPROC_REGS      32
-#define N_MIPS_COPROC_SEL   	8
+/*
+ * KVM MIPS specific structures and definitions.
+ *
+ * Some parts derived from the x86 version of this file.
+ */
 
-/* for KVM_GET_REGS and KVM_SET_REGS */
+/*
+ * for KVM_GET_REGS and KVM_SET_REGS
+ *
+ * If Config[AT] is zero (32-bit CPU), the register contents are
+ * stored in the lower 32-bits of the struct kvm_regs fields and sign
+ * extended to 64-bits.
+ */
 struct kvm_regs {
-	__u32 gprs[32];
-	__u32 hi;
-	__u32 lo;
-	__u32 pc;
-
-	__u32 cp0reg[N_MIPS_COPROC_REGS][N_MIPS_COPROC_SEL];
-};
-
-/* for KVM_GET_SREGS and KVM_SET_SREGS */
-struct kvm_sregs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 gpr[32];
+	__u64 hi;
+	__u64 lo;
+	__u64 pc;
 };
 
-/* for KVM_GET_FPU and KVM_SET_FPU */
+/*
+ * for KVM_GET_FPU and KVM_SET_FPU
+ *
+ * If Status[FR] is zero (32-bit FPU), the upper 32-bits of the FPRs
+ * are zero filled.
+ */
 struct kvm_fpu {
+	__u64 fpr[32];
+	__u32 fir;
+	__u32 fccr;
+	__u32 fexr;
+	__u32 fenr;
+	__u32 fcsr;
+	__u32 pad;
 };
 
+
+/*
+ * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access CP0
+ * registers.  The id field is broken down as follows:
+ *
+ *  bits[2..0]   - Register 'sel' index.
+ *  bits[7..3]   - Register 'rd'  index.
+ *  bits[15..8]  - Must be zero.
+ *  bits[31..16] - 1 -> CP0 registers.
+ *  bits[51..32] - Must be zero.
+ *  bits[63..52] - As per linux/kvm.h
+ *
+ * Other sets registers may be added in the future.  Each set would
+ * have its own identifier in bits[31..16].
+ *
+ * The registers defined in struct kvm_regs are also accessible, the
+ * id values for these are below.
+ */
+
+#define KVM_REG_MIPS_R0 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_MIPS_R1 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 1)
+#define KVM_REG_MIPS_R2 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 2)
+#define KVM_REG_MIPS_R3 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 3)
+#define KVM_REG_MIPS_R4 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 4)
+#define KVM_REG_MIPS_R5 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 5)
+#define KVM_REG_MIPS_R6 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 6)
+#define KVM_REG_MIPS_R7 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 7)
+#define KVM_REG_MIPS_R8 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 8)
+#define KVM_REG_MIPS_R9 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 9)
+#define KVM_REG_MIPS_R10 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 10)
+#define KVM_REG_MIPS_R11 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 11)
+#define KVM_REG_MIPS_R12 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 12)
+#define KVM_REG_MIPS_R13 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 13)
+#define KVM_REG_MIPS_R14 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 14)
+#define KVM_REG_MIPS_R15 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 15)
+#define KVM_REG_MIPS_R16 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 16)
+#define KVM_REG_MIPS_R17 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 17)
+#define KVM_REG_MIPS_R18 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 18)
+#define KVM_REG_MIPS_R19 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 19)
+#define KVM_REG_MIPS_R20 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 20)
+#define KVM_REG_MIPS_R21 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 21)
+#define KVM_REG_MIPS_R22 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 22)
+#define KVM_REG_MIPS_R23 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 23)
+#define KVM_REG_MIPS_R24 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 24)
+#define KVM_REG_MIPS_R25 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 25)
+#define KVM_REG_MIPS_R26 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 26)
+#define KVM_REG_MIPS_R27 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 27)
+#define KVM_REG_MIPS_R28 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 28)
+#define KVM_REG_MIPS_R29 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 29)
+#define KVM_REG_MIPS_R30 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 30)
+#define KVM_REG_MIPS_R31 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 31)
+
+#define KVM_REG_MIPS_HI (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 32)
+#define KVM_REG_MIPS_LO (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 33)
+#define KVM_REG_MIPS_PC (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 34)
+
+/*
+ * KVM MIPS specific structures and definitions
+ *
+ */
 struct kvm_debug_exit_arch {
+	__u64 epc;
 };
 
 /* for KVM_SET_GUEST_DEBUG */
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* dummy definition */
+struct kvm_sregs {
+};
+
 struct kvm_mips_interrupt {
 	/* in */
 	__u32 cpu;
 	__u32 irq;
 };
 
-/* definition of registers in kvm_run */
-struct kvm_sync_regs {
-};
-
 #endif /* __LINUX_KVM_MIPS_H */
diff --git a/arch/mips/include/uapi/asm/ptrace.h b/arch/mips/include/uapi/asm/ptrace.h
index 4d58d846870..b26f7e31727 100644
--- a/arch/mips/include/uapi/asm/ptrace.h
+++ b/arch/mips/include/uapi/asm/ptrace.h
@@ -22,16 +22,12 @@
 #define DSP_CONTROL	77
 #define ACX		78
 
+#ifndef __KERNEL__
 /*
  * This struct defines the way the registers are stored on the stack during a
  * system call/exception. As usual the registers k0/k1 aren't being saved.
  */
 struct pt_regs {
-#ifdef CONFIG_32BIT
-	/* Pad bytes for argument save space on the stack. */
-	unsigned long pad0[6];
-#endif
-
 	/* Saved main processor registers. */
 	unsigned long regs[32];
 
@@ -39,20 +35,11 @@ struct pt_regs {
 	unsigned long cp0_status;
 	unsigned long hi;
 	unsigned long lo;
-#ifdef CONFIG_CPU_HAS_SMARTMIPS
-	unsigned long acx;
-#endif
 	unsigned long cp0_badvaddr;
 	unsigned long cp0_cause;
 	unsigned long cp0_epc;
-#ifdef CONFIG_MIPS_MT_SMTC
-	unsigned long cp0_tcstatus;
-#endif /* CONFIG_MIPS_MT_SMTC */
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
-	unsigned long long mpl[3];	  /* MTM{0,1,2} */
-	unsigned long long mtp[3];	  /* MTP{0,1,2} */
-#endif
 } __attribute__ ((aligned (8)));
+#endif /* __KERNEL__ */
 
 /* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
 #define PTRACE_GETREGS		12
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index e06f777e9c4..1188e00bb12 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -119,4 +119,15 @@ MODULE_AUTHOR("Ralf Baechle (ralf@linux-mips.org)");
 #undef TASK_SIZE
 #define TASK_SIZE TASK_SIZE32
 
+#undef cputime_to_timeval
+#define cputime_to_timeval cputime_to_compat_timeval
+static __inline__ void
+cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
+{
+	unsigned long jiffies = cputime_to_jiffies(cputime);
+
+	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
+	value->tv_sec = jiffies / HZ;
+}
+
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 97c5a1668e5..202e581e609 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -162,4 +162,15 @@ MODULE_AUTHOR("Ralf Baechle (ralf@linux-mips.org)");
 #undef TASK_SIZE
 #define TASK_SIZE TASK_SIZE32
 
+#undef cputime_to_timeval
+#define cputime_to_timeval cputime_to_compat_timeval
+static __inline__ void
+cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
+{
+	unsigned long jiffies = cputime_to_jiffies(cputime);
+
+	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
+	value->tv_sec = jiffies / HZ;
+}
+
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index cf5509f13dd..dba90ec0dc3 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -25,12 +25,16 @@
 #define MCOUNT_OFFSET_INSNS 4
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
 /* Arch override because MIPS doesn't need to run this from stop_machine() */
 void arch_ftrace_update_code(int command)
 {
 	ftrace_modify_all_code(command);
 }
 
+#endif
+
 /*
  * Check if the address is in kernel space
  *
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 3b09b888afa..0c655deeea4 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -93,26 +93,27 @@ static void rm7k_wait_irqoff(void)
 }
 
 /*
- * The Au1xxx wait is available only if using 32khz counter or
- * external timer source, but specifically not CP0 Counter.
- * alchemy/common/time.c may override cpu_wait!
+ * Au1 'wait' is only useful when the 32kHz counter is used as timer,
+ * since coreclock (and the cp0 counter) stops upon executing it. Only an
+ * interrupt can wake it, so they must be enabled before entering idle modes.
  */
 static void au1k_wait(void)
 {
+	unsigned long c0status = read_c0_status() | 1;	/* irqs on */
+
 	__asm__(
 	"	.set	mips3			\n"
 	"	cache	0x14, 0(%0)		\n"
 	"	cache	0x14, 32(%0)		\n"
 	"	sync				\n"
-	"	nop				\n"
+	"	mtc0	%1, $12			\n" /* wr c0status */
 	"	wait				\n"
 	"	nop				\n"
 	"	nop				\n"
 	"	nop				\n"
 	"	nop				\n"
 	"	.set	mips0			\n"
-	: : "r" (au1k_wait));
-	local_irq_enable();
+	: : "r" (au1k_wait), "r" (c0status));
 }
 
 static int __initdata nowait;
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index 93c070b41b0..6fa198db899 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -40,6 +40,7 @@
 #include <asm/processor.h>
 #include <asm/vpe.h>
 #include <asm/rtlx.h>
+#include <asm/setup.h>
 
 static struct rtlx_info *rtlx;
 static int major;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e3be67012d7..a75ae40184a 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -897,22 +897,24 @@ out_sigsegv:
 
 asmlinkage void do_tr(struct pt_regs *regs)
 {
-	unsigned int opcode, tcode = 0;
+	u32 opcode, tcode = 0;
 	u16 instr[2];
-	unsigned long epc = exception_epc(regs);
+	unsigned long epc = msk_isa16_mode(exception_epc(regs));
 
-	if ((__get_user(instr[0], (u16 __user *)msk_isa16_mode(epc))) ||
-		(__get_user(instr[1], (u16 __user *)msk_isa16_mode(epc + 2))))
+	if (get_isa16_mode(regs->cp0_epc)) {
+		if (__get_user(instr[0], (u16 __user *)(epc + 0)) ||
+		    __get_user(instr[1], (u16 __user *)(epc + 2)))
 			goto out_sigsegv;
-	opcode = (instr[0] << 16) | instr[1];
-
-	/* Immediate versions don't provide a code.  */
-	if (!(opcode & OPCODE)) {
-		if (get_isa16_mode(regs->cp0_epc))
-			/* microMIPS */
-			tcode = (opcode >> 12) & 0x1f;
-		else
-			tcode = ((opcode >> 6) & ((1 << 10) - 1));
+		opcode = (instr[0] << 16) | instr[1];
+		/* Immediate versions don't provide a code.  */
+		if (!(opcode & OPCODE))
+			tcode = (opcode >> 12) & ((1 << 4) - 1);
+	} else {
+		if (__get_user(opcode, (u32 __user *)epc))
+			goto out_sigsegv;
+		/* Immediate versions don't provide a code.  */
+		if (!(opcode & OPCODE))
+			tcode = (opcode >> 6) & ((1 << 10) - 1);
 	}
 
 	do_trap_or_bp(regs, tcode, "Trap");
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index e0dad028979..dd203e59e6f 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -195,7 +195,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 long
 kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
-	return -EINVAL;
+	return -ENOIOCTLCMD;
 }
 
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
@@ -401,7 +401,7 @@ int
 kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 				    struct kvm_guest_debug *dbg)
 {
-	return -EINVAL;
+	return -ENOIOCTLCMD;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -475,14 +475,248 @@ int
 kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				struct kvm_mp_state *mp_state)
 {
-	return -EINVAL;
+	return -ENOIOCTLCMD;
 }
 
 int
 kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				struct kvm_mp_state *mp_state)
 {
-	return -EINVAL;
+	return -ENOIOCTLCMD;
+}
+
+#define MIPS_CP0_32(_R, _S)					\
+	(KVM_REG_MIPS | KVM_REG_SIZE_U32 | 0x10000 | (8 * (_R) + (_S)))
+
+#define MIPS_CP0_64(_R, _S)					\
+	(KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0x10000 | (8 * (_R) + (_S)))
+
+#define KVM_REG_MIPS_CP0_INDEX		MIPS_CP0_32(0, 0)
+#define KVM_REG_MIPS_CP0_ENTRYLO0	MIPS_CP0_64(2, 0)
+#define KVM_REG_MIPS_CP0_ENTRYLO1	MIPS_CP0_64(3, 0)
+#define KVM_REG_MIPS_CP0_CONTEXT	MIPS_CP0_64(4, 0)
+#define KVM_REG_MIPS_CP0_USERLOCAL	MIPS_CP0_64(4, 2)
+#define KVM_REG_MIPS_CP0_PAGEMASK	MIPS_CP0_32(5, 0)
+#define KVM_REG_MIPS_CP0_PAGEGRAIN	MIPS_CP0_32(5, 1)
+#define KVM_REG_MIPS_CP0_WIRED		MIPS_CP0_32(6, 0)
+#define KVM_REG_MIPS_CP0_HWRENA		MIPS_CP0_32(7, 0)
+#define KVM_REG_MIPS_CP0_BADVADDR	MIPS_CP0_64(8, 0)
+#define KVM_REG_MIPS_CP0_COUNT		MIPS_CP0_32(9, 0)
+#define KVM_REG_MIPS_CP0_ENTRYHI	MIPS_CP0_64(10, 0)
+#define KVM_REG_MIPS_CP0_COMPARE	MIPS_CP0_32(11, 0)
+#define KVM_REG_MIPS_CP0_STATUS		MIPS_CP0_32(12, 0)
+#define KVM_REG_MIPS_CP0_CAUSE		MIPS_CP0_32(13, 0)
+#define KVM_REG_MIPS_CP0_EBASE		MIPS_CP0_64(15, 1)
+#define KVM_REG_MIPS_CP0_CONFIG		MIPS_CP0_32(16, 0)
+#define KVM_REG_MIPS_CP0_CONFIG1	MIPS_CP0_32(16, 1)
+#define KVM_REG_MIPS_CP0_CONFIG2	MIPS_CP0_32(16, 2)
+#define KVM_REG_MIPS_CP0_CONFIG3	MIPS_CP0_32(16, 3)
+#define KVM_REG_MIPS_CP0_CONFIG7	MIPS_CP0_32(16, 7)
+#define KVM_REG_MIPS_CP0_XCONTEXT	MIPS_CP0_64(20, 0)
+#define KVM_REG_MIPS_CP0_ERROREPC	MIPS_CP0_64(30, 0)
+
+static u64 kvm_mips_get_one_regs[] = {
+	KVM_REG_MIPS_R0,
+	KVM_REG_MIPS_R1,
+	KVM_REG_MIPS_R2,
+	KVM_REG_MIPS_R3,
+	KVM_REG_MIPS_R4,
+	KVM_REG_MIPS_R5,
+	KVM_REG_MIPS_R6,
+	KVM_REG_MIPS_R7,
+	KVM_REG_MIPS_R8,
+	KVM_REG_MIPS_R9,
+	KVM_REG_MIPS_R10,
+	KVM_REG_MIPS_R11,
+	KVM_REG_MIPS_R12,
+	KVM_REG_MIPS_R13,
+	KVM_REG_MIPS_R14,
+	KVM_REG_MIPS_R15,
+	KVM_REG_MIPS_R16,
+	KVM_REG_MIPS_R17,
+	KVM_REG_MIPS_R18,
+	KVM_REG_MIPS_R19,
+	KVM_REG_MIPS_R20,
+	KVM_REG_MIPS_R21,
+	KVM_REG_MIPS_R22,
+	KVM_REG_MIPS_R23,
+	KVM_REG_MIPS_R24,
+	KVM_REG_MIPS_R25,
+	KVM_REG_MIPS_R26,
+	KVM_REG_MIPS_R27,
+	KVM_REG_MIPS_R28,
+	KVM_REG_MIPS_R29,
+	KVM_REG_MIPS_R30,
+	KVM_REG_MIPS_R31,
+
+	KVM_REG_MIPS_HI,
+	KVM_REG_MIPS_LO,
+	KVM_REG_MIPS_PC,
+
+	KVM_REG_MIPS_CP0_INDEX,
+	KVM_REG_MIPS_CP0_CONTEXT,
+	KVM_REG_MIPS_CP0_PAGEMASK,
+	KVM_REG_MIPS_CP0_WIRED,
+	KVM_REG_MIPS_CP0_BADVADDR,
+	KVM_REG_MIPS_CP0_ENTRYHI,
+	KVM_REG_MIPS_CP0_STATUS,
+	KVM_REG_MIPS_CP0_CAUSE,
+	/* EPC set via kvm_regs, et al. */
+	KVM_REG_MIPS_CP0_CONFIG,
+	KVM_REG_MIPS_CP0_CONFIG1,
+	KVM_REG_MIPS_CP0_CONFIG2,
+	KVM_REG_MIPS_CP0_CONFIG3,
+	KVM_REG_MIPS_CP0_CONFIG7,
+	KVM_REG_MIPS_CP0_ERROREPC
+};
+
+static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
+			    const struct kvm_one_reg *reg)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	s64 v;
+
+	switch (reg->id) {
+	case KVM_REG_MIPS_R0 ... KVM_REG_MIPS_R31:
+		v = (long)vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0];
+		break;
+	case KVM_REG_MIPS_HI:
+		v = (long)vcpu->arch.hi;
+		break;
+	case KVM_REG_MIPS_LO:
+		v = (long)vcpu->arch.lo;
+		break;
+	case KVM_REG_MIPS_PC:
+		v = (long)vcpu->arch.pc;
+		break;
+
+	case KVM_REG_MIPS_CP0_INDEX:
+		v = (long)kvm_read_c0_guest_index(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CONTEXT:
+		v = (long)kvm_read_c0_guest_context(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_PAGEMASK:
+		v = (long)kvm_read_c0_guest_pagemask(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_WIRED:
+		v = (long)kvm_read_c0_guest_wired(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_BADVADDR:
+		v = (long)kvm_read_c0_guest_badvaddr(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_ENTRYHI:
+		v = (long)kvm_read_c0_guest_entryhi(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_STATUS:
+		v = (long)kvm_read_c0_guest_status(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CAUSE:
+		v = (long)kvm_read_c0_guest_cause(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_ERROREPC:
+		v = (long)kvm_read_c0_guest_errorepc(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CONFIG:
+		v = (long)kvm_read_c0_guest_config(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CONFIG1:
+		v = (long)kvm_read_c0_guest_config1(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CONFIG2:
+		v = (long)kvm_read_c0_guest_config2(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CONFIG3:
+		v = (long)kvm_read_c0_guest_config3(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_CONFIG7:
+		v = (long)kvm_read_c0_guest_config7(cop0);
+		break;
+	default:
+		return -EINVAL;
+	}
+	if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) {
+		u64 __user *uaddr64 = (u64 __user *)(long)reg->addr;
+		return put_user(v, uaddr64);
+	} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32) {
+		u32 __user *uaddr32 = (u32 __user *)(long)reg->addr;
+		u32 v32 = (u32)v;
+		return put_user(v32, uaddr32);
+	} else {
+		return -EINVAL;
+	}
+}
+
+static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
+			    const struct kvm_one_reg *reg)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	u64 v;
+
+	if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) {
+		u64 __user *uaddr64 = (u64 __user *)(long)reg->addr;
+
+		if (get_user(v, uaddr64) != 0)
+			return -EFAULT;
+	} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32) {
+		u32 __user *uaddr32 = (u32 __user *)(long)reg->addr;
+		s32 v32;
+
+		if (get_user(v32, uaddr32) != 0)
+			return -EFAULT;
+		v = (s64)v32;
+	} else {
+		return -EINVAL;
+	}
+
+	switch (reg->id) {
+	case KVM_REG_MIPS_R0:
+		/* Silently ignore requests to set $0 */
+		break;
+	case KVM_REG_MIPS_R1 ... KVM_REG_MIPS_R31:
+		vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0] = v;
+		break;
+	case KVM_REG_MIPS_HI:
+		vcpu->arch.hi = v;
+		break;
+	case KVM_REG_MIPS_LO:
+		vcpu->arch.lo = v;
+		break;
+	case KVM_REG_MIPS_PC:
+		vcpu->arch.pc = v;
+		break;
+
+	case KVM_REG_MIPS_CP0_INDEX:
+		kvm_write_c0_guest_index(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_CONTEXT:
+		kvm_write_c0_guest_context(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_PAGEMASK:
+		kvm_write_c0_guest_pagemask(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_WIRED:
+		kvm_write_c0_guest_wired(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_BADVADDR:
+		kvm_write_c0_guest_badvaddr(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_ENTRYHI:
+		kvm_write_c0_guest_entryhi(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_STATUS:
+		kvm_write_c0_guest_status(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_CAUSE:
+		kvm_write_c0_guest_cause(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_ERROREPC:
+		kvm_write_c0_guest_errorepc(cop0, v);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
 }
 
 long
@@ -491,9 +725,38 @@ kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
 	long r;
-	int intr;
 
 	switch (ioctl) {
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG: {
+		struct kvm_one_reg reg;
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			return -EFAULT;
+		if (ioctl == KVM_SET_ONE_REG)
+			return kvm_mips_set_reg(vcpu, &reg);
+		else
+			return kvm_mips_get_reg(vcpu, &reg);
+	}
+	case KVM_GET_REG_LIST: {
+		struct kvm_reg_list __user *user_list = argp;
+		u64 __user *reg_dest;
+		struct kvm_reg_list reg_list;
+		unsigned n;
+
+		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
+			return -EFAULT;
+		n = reg_list.n;
+		reg_list.n = ARRAY_SIZE(kvm_mips_get_one_regs);
+		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
+			return -EFAULT;
+		if (n < reg_list.n)
+			return -E2BIG;
+		reg_dest = user_list->reg;
+		if (copy_to_user(reg_dest, kvm_mips_get_one_regs,
+				 sizeof(kvm_mips_get_one_regs)))
+			return -EFAULT;
+		return 0;
+	}
 	case KVM_NMI:
 		/* Treat the NMI as a CPU reset */
 		r = kvm_mips_reset_vcpu(vcpu);
@@ -505,8 +768,6 @@ kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 			if (copy_from_user(&irq, argp, sizeof(irq)))
 				goto out;
 
-			intr = (int)irq.irq;
-
 			kvm_debug("[%d] %s: irq: %d\n", vcpu->vcpu_id, __func__,
 				  irq.irq);
 
@@ -514,7 +775,7 @@ kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 			break;
 		}
 	default:
-		r = -EINVAL;
+		r = -ENOIOCTLCMD;
 	}
 
 out:
@@ -565,7 +826,7 @@ long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 
 	switch (ioctl) {
 	default:
-		r = -EINVAL;
+		r = -ENOIOCTLCMD;
 	}
 
 	return r;
@@ -593,13 +854,13 @@ void kvm_arch_exit(void)
 int
 kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	return -ENOTSUPP;
+	return -ENOIOCTLCMD;
 }
 
 int
 kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	return -ENOTSUPP;
+	return -ENOIOCTLCMD;
 }
 
 int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
@@ -609,12 +870,12 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	return -ENOTSUPP;
+	return -ENOIOCTLCMD;
 }
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	return -ENOTSUPP;
+	return -ENOIOCTLCMD;
 }
 
 int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
@@ -627,6 +888,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	int r;
 
 	switch (ext) {
+	case KVM_CAP_ONE_REG:
+		r = 1;
+		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
@@ -635,7 +899,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 		break;
 	}
 	return r;
-
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -677,28 +940,28 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	for (i = 0; i < 32; i++)
-		vcpu->arch.gprs[i] = regs->gprs[i];
-
+	for (i = 1; i < ARRAY_SIZE(vcpu->arch.gprs); i++)
+		vcpu->arch.gprs[i] = regs->gpr[i];
+	vcpu->arch.gprs[0] = 0; /* zero is special, and cannot be set. */
 	vcpu->arch.hi = regs->hi;
 	vcpu->arch.lo = regs->lo;
 	vcpu->arch.pc = regs->pc;
 
-	return kvm_mips_callbacks->vcpu_ioctl_set_regs(vcpu, regs);
+	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	for (i = 0; i < 32; i++)
-		regs->gprs[i] = vcpu->arch.gprs[i];
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.gprs); i++)
+		regs->gpr[i] = vcpu->arch.gprs[i];
 
 	regs->hi = vcpu->arch.hi;
 	regs->lo = vcpu->arch.lo;
 	regs->pc = vcpu->arch.pc;
 
-	return kvm_mips_callbacks->vcpu_ioctl_get_regs(vcpu, regs);
+	return 0;
 }
 
 void kvm_mips_comparecount_func(unsigned long data)
diff --git a/arch/mips/kvm/kvm_trap_emul.c b/arch/mips/kvm/kvm_trap_emul.c
index 466aeef044b..30d725321db 100644
--- a/arch/mips/kvm/kvm_trap_emul.c
+++ b/arch/mips/kvm/kvm_trap_emul.c
@@ -345,54 +345,6 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int
-kvm_trap_emul_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
-{
-	struct mips_coproc *cop0 = vcpu->arch.cop0;
-
-	kvm_write_c0_guest_index(cop0, regs->cp0reg[MIPS_CP0_TLB_INDEX][0]);
-	kvm_write_c0_guest_context(cop0, regs->cp0reg[MIPS_CP0_TLB_CONTEXT][0]);
-	kvm_write_c0_guest_badvaddr(cop0, regs->cp0reg[MIPS_CP0_BAD_VADDR][0]);
-	kvm_write_c0_guest_entryhi(cop0, regs->cp0reg[MIPS_CP0_TLB_HI][0]);
-	kvm_write_c0_guest_epc(cop0, regs->cp0reg[MIPS_CP0_EXC_PC][0]);
-
-	kvm_write_c0_guest_status(cop0, regs->cp0reg[MIPS_CP0_STATUS][0]);
-	kvm_write_c0_guest_cause(cop0, regs->cp0reg[MIPS_CP0_CAUSE][0]);
-	kvm_write_c0_guest_pagemask(cop0,
-				    regs->cp0reg[MIPS_CP0_TLB_PG_MASK][0]);
-	kvm_write_c0_guest_wired(cop0, regs->cp0reg[MIPS_CP0_TLB_WIRED][0]);
-	kvm_write_c0_guest_errorepc(cop0, regs->cp0reg[MIPS_CP0_ERROR_PC][0]);
-
-	return 0;
-}
-
-static int
-kvm_trap_emul_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
-{
-	struct mips_coproc *cop0 = vcpu->arch.cop0;
-
-	regs->cp0reg[MIPS_CP0_TLB_INDEX][0] = kvm_read_c0_guest_index(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_CONTEXT][0] = kvm_read_c0_guest_context(cop0);
-	regs->cp0reg[MIPS_CP0_BAD_VADDR][0] = kvm_read_c0_guest_badvaddr(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_HI][0] = kvm_read_c0_guest_entryhi(cop0);
-	regs->cp0reg[MIPS_CP0_EXC_PC][0] = kvm_read_c0_guest_epc(cop0);
-
-	regs->cp0reg[MIPS_CP0_STATUS][0] = kvm_read_c0_guest_status(cop0);
-	regs->cp0reg[MIPS_CP0_CAUSE][0] = kvm_read_c0_guest_cause(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_PG_MASK][0] =
-	    kvm_read_c0_guest_pagemask(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_WIRED][0] = kvm_read_c0_guest_wired(cop0);
-	regs->cp0reg[MIPS_CP0_ERROR_PC][0] = kvm_read_c0_guest_errorepc(cop0);
-
-	regs->cp0reg[MIPS_CP0_CONFIG][0] = kvm_read_c0_guest_config(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][1] = kvm_read_c0_guest_config1(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][2] = kvm_read_c0_guest_config2(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][3] = kvm_read_c0_guest_config3(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][7] = kvm_read_c0_guest_config7(cop0);
-
-	return 0;
-}
-
 static int kvm_trap_emul_vm_init(struct kvm *kvm)
 {
 	return 0;
@@ -471,8 +423,6 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = {
 	.dequeue_io_int = kvm_mips_dequeue_io_int_cb,
 	.irq_deliver = kvm_mips_irq_deliver_cb,
 	.irq_clear = kvm_mips_irq_clear_cb,
-	.vcpu_ioctl_get_regs = kvm_trap_emul_ioctl_get_regs,
-	.vcpu_ioctl_set_regs = kvm_trap_emul_ioctl_set_regs,
 };
 
 int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index ce9818eef7d..afeef93f81a 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -301,10 +301,6 @@ static u32 tlb_handler[128] __cpuinitdata;
 static struct uasm_label labels[128] __cpuinitdata;
 static struct uasm_reloc relocs[128] __cpuinitdata;
 
-#ifdef CONFIG_64BIT
-static int check_for_high_segbits __cpuinitdata;
-#endif
-
 static int check_for_high_segbits __cpuinitdata;
 
 static unsigned int kscratch_used_mask __cpuinitdata;
diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c
index fb1569580de..6b5f3406f41 100644
--- a/arch/mips/ralink/of.c
+++ b/arch/mips/ralink/of.c
@@ -88,7 +88,7 @@ void __init plat_mem_setup(void)
 	__dt_setup_arch(&__dtb_start);
 
 	if (soc_info.mem_size)
-		add_memory_region(soc_info.mem_base, soc_info.mem_size,
+		add_memory_region(soc_info.mem_base, soc_info.mem_size * SZ_1M,
 				  BOOT_MEM_RAM);
 	else
 		detect_memory_region(soc_info.mem_base,
diff --git a/arch/mn10300/include/asm/irqflags.h b/arch/mn10300/include/asm/irqflags.h
index 678f68d5f37..8730c0a3c37 100644
--- a/arch/mn10300/include/asm/irqflags.h
+++ b/arch/mn10300/include/asm/irqflags.h
@@ -13,9 +13,8 @@
 #define _ASM_IRQFLAGS_H
 
 #include <asm/cpu-regs.h>
-#ifndef __ASSEMBLY__
-#include <linux/smp.h>
-#endif
+/* linux/smp.h <- linux/irqflags.h needs asm/smp.h first */
+#include <asm/smp.h>
 
 /*
  * interrupt control
diff --git a/arch/mn10300/include/asm/smp.h b/arch/mn10300/include/asm/smp.h
index 6745dbe6494..56c42417d42 100644
--- a/arch/mn10300/include/asm/smp.h
+++ b/arch/mn10300/include/asm/smp.h
@@ -24,6 +24,7 @@
 #ifndef __ASSEMBLY__
 #include <linux/threads.h>
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 #endif
 
 #ifdef CONFIG_SMP
@@ -85,7 +86,7 @@ extern cpumask_t cpu_boot_map;
 extern void smp_init_cpus(void);
 extern void smp_cache_interrupt(void);
 extern void send_IPI_allbutself(int irq);
-extern int smp_nmi_call_function(smp_call_func_t func, void *info, int wait);
+extern int smp_nmi_call_function(void (*func)(void *), void *info, int wait);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
@@ -100,6 +101,7 @@ extern void __cpu_die(unsigned int cpu);
 #ifndef __ASSEMBLY__
 
 static inline void smp_init_cpus(void) {}
+#define raw_smp_processor_id() 0
 
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_SMP */
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 780560b330d..d7966e0f769 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -161,7 +161,7 @@ struct __large_struct { unsigned long buf[100]; };
 
 #define __get_user_check(x, ptr, size)					\
 ({									\
-	const __typeof__(ptr) __guc_ptr = (ptr);			\
+	const __typeof__(*(ptr))* __guc_ptr = (ptr);			\
 	int _e;								\
 	if (likely(__access_ok((unsigned long) __guc_ptr, (size))))	\
 		_e = __get_user_nocheck((x), __guc_ptr, (size));	\
diff --git a/arch/mn10300/kernel/setup.c b/arch/mn10300/kernel/setup.c
index 33c3bd1e5c6..ebac9c11f79 100644
--- a/arch/mn10300/kernel/setup.c
+++ b/arch/mn10300/kernel/setup.c
@@ -38,6 +38,7 @@ struct mn10300_cpuinfo boot_cpu_data;
 /* For PCI or other memory-mapped resources */
 unsigned long pci_mem_start = 0x18000000;
 
+static char __initdata cmd_line[COMMAND_LINE_SIZE];
 char redboot_command_line[COMMAND_LINE_SIZE] =
 	"console=ttyS0,115200 root=/dev/mtdblock3 rw";
 
@@ -74,45 +75,19 @@ static const char *const mn10300_cputypes[] = {
 };
 
 /*
- *
+ * Pick out the memory size.  We look for mem=size,
+ * where size is "size[KkMm]"
  */
-static void __init parse_mem_cmdline(char **cmdline_p)
+static int __init early_mem(char *p)
 {
-	char *from, *to, c;
-
-	/* save unparsed command line copy for /proc/cmdline */
-	strcpy(boot_command_line, redboot_command_line);
-
-	/* see if there's an explicit memory size option */
-	from = redboot_command_line;
-	to = redboot_command_line;
-	c = ' ';
-
-	for (;;) {
-		if (c == ' ' && !memcmp(from, "mem=", 4)) {
-			if (to != redboot_command_line)
-				to--;
-			memory_size = memparse(from + 4, &from);
-		}
-
-		c = *(from++);
-		if (!c)
-			break;
-
-		*(to++) = c;
-	}
-
-	*to = '\0';
-	*cmdline_p = redboot_command_line;
+	memory_size = memparse(p, &p);
 
 	if (memory_size == 0)
 		panic("Memory size not known\n");
 
-	memory_end = (unsigned long) CONFIG_KERNEL_RAM_BASE_ADDRESS +
-		memory_size;
-	if (memory_end > phys_memory_end)
-		memory_end = phys_memory_end;
+	return 0;
 }
+early_param("mem", early_mem);
 
 /*
  * architecture specific setup
@@ -125,7 +100,20 @@ void __init setup_arch(char **cmdline_p)
 	cpu_init();
 	unit_setup();
 	smp_init_cpus();
-	parse_mem_cmdline(cmdline_p);
+
+	/* save unparsed command line copy for /proc/cmdline */
+	strlcpy(boot_command_line, redboot_command_line, COMMAND_LINE_SIZE);
+
+	/* populate cmd_line too for later use, preserving boot_command_line */
+	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = cmd_line;
+
+	parse_early_param();
+
+	memory_end = (unsigned long) CONFIG_KERNEL_RAM_BASE_ADDRESS +
+		memory_size;
+	if (memory_end > phys_memory_end)
+		memory_end = phys_memory_end;
 
 	init_mm.start_code = (unsigned long)&_text;
 	init_mm.end_code = (unsigned long) &_etext;
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 197690068f8..96ec3982be8 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -66,7 +66,7 @@ KBUILD_CFLAGS_KERNEL += -mlong-calls
 endif
 
 # select which processor to optimise for
-cflags-$(CONFIG_PA7100)		+= -march=1.1 -mschedule=7100
+cflags-$(CONFIG_PA7000)		+= -march=1.1 -mschedule=7100
 cflags-$(CONFIG_PA7200)		+= -march=1.1 -mschedule=7200
 cflags-$(CONFIG_PA7100LC)	+= -march=1.1 -mschedule=7100LC
 cflags-$(CONFIG_PA7300LC)	+= -march=1.1 -mschedule=7300
diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h
index 0e625ab9aae..b6b34a0987e 100644
--- a/arch/parisc/include/asm/mmzone.h
+++ b/arch/parisc/include/asm/mmzone.h
@@ -27,7 +27,7 @@ extern struct node_map_data node_data[];
 
 #define PFNNID_SHIFT (30 - PAGE_SHIFT)
 #define PFNNID_MAP_MAX  512     /* support 512GB */
-extern unsigned char pfnnid_map[PFNNID_MAP_MAX];
+extern signed char pfnnid_map[PFNNID_MAP_MAX];
 
 #ifndef CONFIG_64BIT
 #define pfn_is_io(pfn) ((pfn & (0xf0000000UL >> PAGE_SHIFT)) == (0xf0000000UL >> PAGE_SHIFT))
@@ -39,17 +39,14 @@ extern unsigned char pfnnid_map[PFNNID_MAP_MAX];
 static inline int pfn_to_nid(unsigned long pfn)
 {
 	unsigned int i;
-	unsigned char r;
 
 	if (unlikely(pfn_is_io(pfn)))
 		return 0;
 
 	i = pfn >> PFNNID_SHIFT;
 	BUG_ON(i >= ARRAY_SIZE(pfnnid_map));
-	r = pfnnid_map[i];
-	BUG_ON(r == 0xff);
 
-	return (int)r;
+	return pfnnid_map[i];
 }
 
 static inline int pfn_valid(int pfn)
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 3234f492d57..465154076d2 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -225,4 +225,9 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 	return channel ? 15 : 14;
 }
 
+#define HAVE_PCI_MMAP
+
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+	enum pci_mmap_state mmap_state, int write_combine);
+
 #endif /* __ASM_PARISC_PCI_H */
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 5709c5e59be..14285caec71 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -394,7 +394,7 @@ EXPORT_SYMBOL(print_pci_hwpath);
 static void setup_bus_id(struct parisc_device *padev)
 {
 	struct hardware_path path;
-	char name[20];
+	char name[28];
 	char *output = name;
 	int i;
 
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index 9e2d2e40852..872275659d9 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -1205,6 +1205,7 @@ static struct hp_hardware hp_hardware_list[] = {
 	{HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, 
 	{HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, 
 	{HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, 
+	{HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"},
 	{HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, 
 	{HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, 
 	{HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 36d7f402e48..b743a80eaba 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -860,7 +860,7 @@ ENTRY(flush_dcache_page_asm)
 #endif
 
 	ldil		L%dcache_stride, %r1
-	ldw		R%dcache_stride(%r1), %r1
+	ldw		R%dcache_stride(%r1), r31
 
 #ifdef CONFIG_64BIT
 	depdi,z		1, 63-PAGE_SHIFT,1, %r25
@@ -868,26 +868,26 @@ ENTRY(flush_dcache_page_asm)
 	depwi,z		1, 31-PAGE_SHIFT,1, %r25
 #endif
 	add		%r28, %r25, %r25
-	sub		%r25, %r1, %r25
-
-
-1:      fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
+	sub		%r25, r31, %r25
+
+
+1:      fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
 	cmpb,COND(<<)		%r28, %r25,1b
-	fdc,m		%r1(%r28)
+	fdc,m		r31(%r28)
 
 	sync
 
@@ -936,7 +936,7 @@ ENTRY(flush_icache_page_asm)
 #endif
 
 	ldil		L%icache_stride, %r1
-	ldw		R%icache_stride(%r1), %r1
+	ldw		R%icache_stride(%r1), %r31
 
 #ifdef CONFIG_64BIT
 	depdi,z		1, 63-PAGE_SHIFT,1, %r25
@@ -944,28 +944,28 @@ ENTRY(flush_icache_page_asm)
 	depwi,z		1, 31-PAGE_SHIFT,1, %r25
 #endif
 	add		%r28, %r25, %r25
-	sub		%r25, %r1, %r25
+	sub		%r25, %r31, %r25
 
 
 	/* fic only has the type 26 form on PA1.1, requiring an
 	 * explicit space specification, so use %sr4 */
-1:      fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
+1:      fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
 	cmpb,COND(<<)	%r28, %r25,1b
-	fic,m		%r1(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
 
 	sync
 
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 60309051875..64f2764a8ce 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -220,6 +220,33 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 }
 
 
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state, int write_combine)
+{
+	unsigned long prot;
+
+	/*
+	 * I/O space can be accessed via normal processor loads and stores on
+	 * this platform but for now we elect not to do this and portable
+	 * drivers should not do this anyway.
+	 */
+	if (mmap_state == pci_mmap_io)
+		return -EINVAL;
+
+	if (write_combine)
+		return -EINVAL;
+
+	/*
+	 * Ignore write-combine; for now only return uncached mappings.
+	 */
+	prot = pgprot_val(vma->vm_page_prot);
+	prot |= _PAGE_NO_CACHE;
+	vma->vm_page_prot = __pgprot(prot);
+
+	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+		vma->vm_end - vma->vm_start, vma->vm_page_prot);
+}
+
 /*
  * A driver is enabling the device.  We make sure that all the appropriate
  * bits are set to allow the device to operate as the driver is expecting.
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 76b63e726a5..1e95b2000ce 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -69,7 +69,8 @@ void __init setup_cmdline(char **cmdline_p)
 		/* called from hpux boot loader */
 		boot_command_line[0] = '\0';
 	} else {
-		strcpy(boot_command_line, (char *)__va(boot_args[1]));
+		strlcpy(boot_command_line, (char *)__va(boot_args[1]),
+			COMMAND_LINE_SIZE);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 		if (boot_args[2] != 0) /* did palo pass us a ramdisk? */
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 1c965642068..505b56c6b9b 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -47,7 +47,7 @@ pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __attribute__ ((__section__ (".data..vm0.pt
 
 #ifdef CONFIG_DISCONTIGMEM
 struct node_map_data node_data[MAX_NUMNODES] __read_mostly;
-unsigned char pfnnid_map[PFNNID_MAP_MAX] __read_mostly;
+signed char pfnnid_map[PFNNID_MAP_MAX] __read_mostly;
 #endif
 
 static struct resource data_resource = {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 26807e5aff5..6f3887d884d 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -176,6 +176,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_CFAR			LONG_ASM_CONST(0x0100000000000000)
 #define	CPU_FTR_HAS_PPR			LONG_ASM_CONST(0x0200000000000000)
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
+#define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -394,19 +395,20 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_201 | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
 	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS | \
-	    CPU_FTR_HVMODE)
+	    CPU_FTR_HVMODE | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR | \
+	    CPU_FTR_DABRX)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -415,7 +417,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | \
-	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR)
+	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER8 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -430,14 +432,15 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_PAUSE_ZERO  | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
-	    CPU_FTR_UNALIGNED_LD_STD)
+	    CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_DABRX)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_PURR | CPU_FTR_REAL_LE)
+	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
 #define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \
-		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | CPU_FTR_ICSWX)
+		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \
+		     CPU_FTR_ICSWX | CPU_FTR_DABRX )
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 8e5fae8beaf..46793b58a76 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -513,7 +513,7 @@ label##_common:							\
  */
 #define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr)		  \
 	EXCEPTION_COMMON(trap, label, hdlr, ret_from_except_lite, \
-			 FINISH_NAP;RUNLATCH_ON;DISABLE_INTS)
+			 FINISH_NAP;DISABLE_INTS;RUNLATCH_ON)
 
 /*
  * When the idle code in power4_idle puts the CPU into NAP mode,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index cf4df8e2139..0c7f2bfcf13 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -264,6 +264,7 @@
 #define H_GET_MPP		0x2D4
 #define H_HOME_NODE_ASSOCIATIVITY 0x2EC
 #define H_BEST_ENERGY		0x2F4
+#define H_XIRR_X		0x2FC
 #define H_RANDOM		0x300
 #define H_COP			0x304
 #define H_GET_MPP_X		0x314
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index b9dd382cb34..851bac7afa4 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -54,8 +54,16 @@
 #define BOOKE_INTERRUPT_DEBUG 15
 
 /* E500 */
-#define BOOKE_INTERRUPT_SPE_UNAVAIL 32
-#define BOOKE_INTERRUPT_SPE_FP_DATA 33
+#define BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL 32
+#define BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST 33
+/*
+ * TODO: Unify 32-bit and 64-bit kernel exception handlers to use same defines
+ */
+#define BOOKE_INTERRUPT_SPE_UNAVAIL BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL
+#define BOOKE_INTERRUPT_SPE_FP_DATA BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST
+#define BOOKE_INTERRUPT_ALTIVEC_UNAVAIL BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL
+#define BOOKE_INTERRUPT_ALTIVEC_ASSIST \
+				BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST
 #define BOOKE_INTERRUPT_SPE_FP_ROUND 34
 #define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
 #define BOOKE_INTERRUPT_DOORBELL 36
@@ -67,10 +75,6 @@
 #define BOOKE_INTERRUPT_HV_SYSCALL 40
 #define BOOKE_INTERRUPT_HV_PRIV 41
 
-/* altivec */
-#define BOOKE_INTERRUPT_ALTIVEC_UNAVAIL 42
-#define BOOKE_INTERRUPT_ALTIVEC_ASSIST 43
-
 /* book3s */
 
 #define BOOK3S_INTERRUPT_SYSTEM_RESET	0x100
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cea8496091f..2f1b6c5f817 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -523,6 +523,17 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946)
 #define PPC440EP_ERR42
 #endif
 
+/* The following stops all load and store data streams associated with stream
+ * ID (ie. streams created explicitly).  The embedded and server mnemonics for
+ * dcbt are different so we use machine "power4" here explicitly.
+ */
+#define DCBT_STOP_ALL_STREAM_IDS(scratch)	\
+.machine push ;					\
+.machine "power4" ;				\
+       lis     scratch,0x60000000@h;		\
+       dcbt    r0,scratch,0b01010;		\
+.machine pop
+
 /*
  * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them
  * keep the address intact to be compatible with code shared with
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 594db6bc093..14a65836369 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -409,21 +409,16 @@ static inline void prefetchw(const void *x)
 #endif
 
 #ifdef CONFIG_PPC64
-static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32)
+static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 {
-	unsigned long sp;
-
 	if (is_32)
-		sp = regs->gpr[1] & 0x0ffffffffUL;
-	else
-		sp = regs->gpr[1];
-
+		return sp & 0x0ffffffffUL;
 	return sp;
 }
 #else
-static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32)
+static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 {
-	return regs->gpr[1];
+	return sp;
 }
 #endif
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a6136515c7f..4a9e408644f 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -111,17 +111,6 @@
 #define MSR_TM_TRANSACTIONAL(x)	(((x) & MSR_TS_MASK) == MSR_TS_T)
 #define MSR_TM_SUSPENDED(x)	(((x) & MSR_TS_MASK) == MSR_TS_S)
 
-/* Reason codes describing kernel causes for transaction aborts.  By
-   convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if
-   the failure is persistent.
-*/
-#define TM_CAUSE_RESCHED	0xfe
-#define TM_CAUSE_TLBI		0xfc
-#define TM_CAUSE_FAC_UNAV	0xfa
-#define TM_CAUSE_SYSCALL	0xf9 /* Persistent */
-#define TM_CAUSE_MISC		0xf6
-#define TM_CAUSE_SIGNAL		0xf4
-
 #if defined(CONFIG_PPC_BOOK3S_64)
 #define MSR_64BIT	MSR_SF
 
diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h
index fbe66c46389..9322c28aebd 100644
--- a/arch/powerpc/include/asm/signal.h
+++ b/arch/powerpc/include/asm/signal.h
@@ -3,5 +3,8 @@
 
 #define __ARCH_HAS_SA_RESTORER
 #include <uapi/asm/signal.h>
+#include <uapi/asm/ptrace.h>
+
+extern unsigned long get_tm_stackpointer(struct pt_regs *regs);
 
 #endif /* _ASM_POWERPC_SIGNAL_H */
diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h
index 4b4449abf3f..9dfbc34bdbf 100644
--- a/arch/powerpc/include/asm/tm.h
+++ b/arch/powerpc/include/asm/tm.h
@@ -5,6 +5,8 @@
  * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
  */
 
+#include <uapi/asm/tm.h>
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 extern void do_load_up_transact_fpu(struct thread_struct *thread);
 extern void do_load_up_transact_altivec(struct thread_struct *thread);
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index f7bca637074..5182c8622b5 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -40,6 +40,7 @@ header-y += statfs.h
 header-y += swab.h
 header-y += termbits.h
 header-y += termios.h
+header-y += tm.h
 header-y += types.h
 header-y += ucontext.h
 header-y += unistd.h
diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h
new file mode 100644
index 00000000000..85059a00f56
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/tm.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_POWERPC_TM_H
+#define _ASM_POWERPC_TM_H
+
+/* Reason codes describing kernel causes for transaction aborts.  By
+ * convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if
+ * the failure is persistent.  PAPR saves 0xff-0xe0 for the hypervisor.
+ */
+#define TM_CAUSE_PERSISTENT	0x01
+#define TM_CAUSE_RESCHED	0xde
+#define TM_CAUSE_TLBI		0xdc
+#define TM_CAUSE_FAC_UNAV	0xda
+#define TM_CAUSE_SYSCALL	0xd8  /* future use */
+#define TM_CAUSE_MISC		0xd6  /* future use */
+#define TM_CAUSE_SIGNAL		0xd4
+#define TM_CAUSE_ALIGNMENT	0xd2
+#define TM_CAUSE_EMULATE	0xd0
+
+#endif
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index c60bbec25c1..2a45d0f0438 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -452,7 +452,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.mmu_features		= MMU_FTRS_POWER8,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
-		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
@@ -482,7 +482,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7+ (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.cpu_user_features	= COMMON_USER2_POWER7,
+		.cpu_user_features2	= COMMON_USER2_POWER7,
 		.mmu_features		= MMU_FTRS_POWER7,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
@@ -507,7 +507,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.num_pmcs		= 6,
 		.pmc_type		= PPC_PMC_IBM,
 		.oprofile_cpu_type	= "ppc64/power8",
-		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
 		.platform		= "power8",
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d22e73e4618..22b45a4955c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -849,7 +849,7 @@ resume_kernel:
 	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
 	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r8,TI_FLAGS(r9)
-	andis.	r8,r8,_TIF_EMULATE_STACK_STORE@h
+	andis.	r0,r8,_TIF_EMULATE_STACK_STORE@h
 	beq+	1f
 
 	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 0e9095e47b5..8741c854e03 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -465,20 +465,6 @@ BEGIN_FTR_SECTION
 	std	r0, THREAD_EBBHR(r3)
 	mfspr	r0, SPRN_EBBRR
 	std	r0, THREAD_EBBRR(r3)
-
-	/* PMU registers made user read/(write) by EBB */
-	mfspr	r0, SPRN_SIAR
-	std	r0, THREAD_SIAR(r3)
-	mfspr	r0, SPRN_SDAR
-	std	r0, THREAD_SDAR(r3)
-	mfspr	r0, SPRN_SIER
-	std	r0, THREAD_SIER(r3)
-	mfspr	r0, SPRN_MMCR0
-	std	r0, THREAD_MMCR0(r3)
-	mfspr	r0, SPRN_MMCR2
-	std	r0, THREAD_MMCR2(r3)
-	mfspr	r0, SPRN_MMCRA
-	std	r0, THREAD_MMCRA(r3)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 #endif
 
@@ -501,6 +487,13 @@ BEGIN_FTR_SECTION
 	ldarx	r6,0,r1
 END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)
 
+#ifdef CONFIG_PPC_BOOK3S
+/* Cancel all explict user streams as they will have no use after context
+ * switch and will stop the HW from creating streams itself
+ */
+	DCBT_STOP_ALL_STREAM_IDS(r6)
+#endif
+
 	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */
 	std	r6,PACACURRENT(r13)	/* Set new 'current' */
 
@@ -574,20 +567,6 @@ BEGIN_FTR_SECTION
 	ld	r0, THREAD_EBBRR(r4)
 	mtspr	SPRN_EBBRR, r0
 
-	/* PMU registers made user read/(write) by EBB */
-	ld	r0, THREAD_SIAR(r4)
-	mtspr	SPRN_SIAR, r0
-	ld	r0, THREAD_SDAR(r4)
-	mtspr	SPRN_SDAR, r0
-	ld	r0, THREAD_SIER(r4)
-	mtspr	SPRN_SIER, r0
-	ld	r0, THREAD_MMCR0(r4)
-	mtspr	SPRN_MMCR0, r0
-	ld	r0, THREAD_MMCR2(r4)
-	mtspr	SPRN_MMCR2, r0
-	ld	r0, THREAD_MMCRA(r4)
-	mtspr	SPRN_MMCRA, r0
-
 	ld	r0,THREAD_TAR(r4)
 	mtspr	SPRN_TAR,r0
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e6eba1bf61a..40e4a17c8ba 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -454,38 +454,14 @@ BEGIN_FTR_SECTION
 	xori	r10,r10,(MSR_FE0|MSR_FE1)
 	mtmsrd	r10
 	sync
-	fmr	0,0
-	fmr	1,1
-	fmr	2,2
-	fmr	3,3
-	fmr	4,4
-	fmr	5,5
-	fmr	6,6
-	fmr	7,7
-	fmr	8,8
-	fmr	9,9
-	fmr	10,10
-	fmr	11,11
-	fmr	12,12
-	fmr	13,13
-	fmr	14,14
-	fmr	15,15
-	fmr	16,16
-	fmr	17,17
-	fmr	18,18
-	fmr	19,19
-	fmr	20,20
-	fmr	21,21
-	fmr	22,22
-	fmr	23,23
-	fmr	24,24
-	fmr	25,25
-	fmr	26,26
-	fmr	27,27
-	fmr	28,28
-	fmr	29,29
-	fmr	30,30
-	fmr	31,31
+
+#define FMR2(n)  fmr (n), (n) ; fmr n+1, n+1
+#define FMR4(n)  FMR2(n) ; FMR2(n+2)
+#define FMR8(n)  FMR4(n) ; FMR4(n+4)
+#define FMR16(n) FMR8(n) ; FMR8(n+8)
+#define FMR32(n) FMR16(n) ; FMR16(n+16)
+	FMR32(0)
+
 FTR_SECTION_ELSE
 /*
  * To denormalise we need to move a copy of the register to itself.
@@ -495,39 +471,25 @@ FTR_SECTION_ELSE
 	oris	r10,r10,MSR_VSX@h
 	mtmsrd	r10
 	sync
-	XVCPSGNDP(0,0,0)
-	XVCPSGNDP(1,1,1)
-	XVCPSGNDP(2,2,2)
-	XVCPSGNDP(3,3,3)
-	XVCPSGNDP(4,4,4)
-	XVCPSGNDP(5,5,5)
-	XVCPSGNDP(6,6,6)
-	XVCPSGNDP(7,7,7)
-	XVCPSGNDP(8,8,8)
-	XVCPSGNDP(9,9,9)
-	XVCPSGNDP(10,10,10)
-	XVCPSGNDP(11,11,11)
-	XVCPSGNDP(12,12,12)
-	XVCPSGNDP(13,13,13)
-	XVCPSGNDP(14,14,14)
-	XVCPSGNDP(15,15,15)
-	XVCPSGNDP(16,16,16)
-	XVCPSGNDP(17,17,17)
-	XVCPSGNDP(18,18,18)
-	XVCPSGNDP(19,19,19)
-	XVCPSGNDP(20,20,20)
-	XVCPSGNDP(21,21,21)
-	XVCPSGNDP(22,22,22)
-	XVCPSGNDP(23,23,23)
-	XVCPSGNDP(24,24,24)
-	XVCPSGNDP(25,25,25)
-	XVCPSGNDP(26,26,26)
-	XVCPSGNDP(27,27,27)
-	XVCPSGNDP(28,28,28)
-	XVCPSGNDP(29,29,29)
-	XVCPSGNDP(30,30,30)
-	XVCPSGNDP(31,31,31)
+
+#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1)
+#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2)
+#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4)
+#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8)
+#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16)
+	XVCPSGNDP32(0)
+
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
+
+BEGIN_FTR_SECTION
+	b	denorm_done
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER8 we need to do that for all 64 VSX registers
+ */
+	XVCPSGNDP32(32)
+denorm_done:
 	mtspr	SPRN_HSRR0,r11
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
@@ -721,7 +683,7 @@ machine_check_common:
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
 	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception)
+	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt)
 	STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
 #ifdef CONFIG_PPC_DOORBELL
 	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5cbcf4d5a80..ea185e0b3ca 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -162,7 +162,7 @@ notrace unsigned int __check_irq_replay(void)
 	 * in case we also had a rollover while hard disabled
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_DEC;
-	if (decrementer_check_overflow())
+	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
 		return 0x900;
 
 	/* Finally check if an external interrupt happened */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index e9acf50dd5b..f46914a0f33 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -657,15 +657,6 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
  *     ranges. However, some machines (thanks Apple !) tend to split their
  *     space into lots of small contiguous ranges. So we have to coalesce.
  *
- *   - We can only cope with all memory ranges having the same offset
- *     between CPU addresses and PCI addresses. Unfortunately, some bridges
- *     are setup for a large 1:1 mapping along with a small "window" which
- *     maps PCI address 0 to some arbitrary high address of the CPU space in
- *     order to give access to the ISA memory hole.
- *     The way out of here that I've chosen for now is to always set the
- *     offset based on the first resource found, then override it if we
- *     have a different offset and the previous was set by an ISA hole.
- *
  *   - Some busses have IO space not starting at 0, which causes trouble with
  *     the way we do our IO resource renumbering. The code somewhat deals with
  *     it for 64 bits but I would expect problems on 32 bits.
@@ -680,10 +671,9 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 	int rlen;
 	int pna = of_n_addr_cells(dev);
 	int np = pna + 5;
-	int memno = 0, isa_hole = -1;
+	int memno = 0;
 	u32 pci_space;
 	unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size;
-	unsigned long long isa_mb = 0;
 	struct resource *res;
 
 	printk(KERN_INFO "PCI host bridge %s %s ranges:\n",
@@ -777,8 +767,6 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			}
 			/* Handles ISA memory hole space here */
 			if (pci_addr == 0) {
-				isa_mb = cpu_addr;
-				isa_hole = memno;
 				if (primary || isa_mem_base == 0)
 					isa_mem_base = cpu_addr;
 				hose->isa_mem_phys = cpu_addr;
@@ -839,6 +827,7 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 	}
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 		struct resource *res = dev->resource + i;
+		struct pci_bus_region reg;
 		if (!res->flags)
 			continue;
 
@@ -847,8 +836,9 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		 * at 0 as unset as well, except if PCI_PROBE_ONLY is also set
 		 * since in that case, we don't want to re-assign anything
 		 */
+		pcibios_resource_to_bus(dev, &reg, res);
 		if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) ||
-		    (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
+		    (reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
 			/* Only print message if not re-assigning */
 			if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC))
 				pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] "
@@ -1004,7 +994,7 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		ppc_md.pci_dma_bus_setup(bus);
 }
 
-void pcibios_setup_device(struct pci_dev *dev)
+static void pcibios_setup_device(struct pci_dev *dev)
 {
 	/* Fixup NUMA node as it may not be setup yet by the generic
 	 * code and is needed by the DMA init
@@ -1025,6 +1015,17 @@ void pcibios_setup_device(struct pci_dev *dev)
 		ppc_md.pci_irq_fixup(dev);
 }
 
+int pcibios_add_device(struct pci_dev *dev)
+{
+	/*
+	 * We can only call pcibios_setup_device() after bus setup is complete,
+	 * since some of the platform specific DMA setup code depends on it.
+	 */
+	if (dev->bus->is_added)
+		pcibios_setup_device(dev);
+	return 0;
+}
+
 void pcibios_setup_bus_devices(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
@@ -1479,10 +1480,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 		if (ppc_md.pcibios_enable_device_hook(dev))
 			return -EINVAL;
 
-	/* avoid pcie irq fix up impact on cardbus */
-	if (dev->hdr_type != PCI_HEADER_TYPE_CARDBUS)
-		pcibios_setup_device(dev);
-
 	return pci_enable_resources(dev, mask);
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a902723fdc6..076d1242507 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -399,7 +399,8 @@ static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 {
 	mtspr(SPRN_DABR, dabr);
-	mtspr(SPRN_DABRX, dabrx);
+	if (cpu_has_feature(CPU_FTR_DABRX))
+		mtspr(SPRN_DABRX, dabrx);
 	return 0;
 }
 #else
@@ -1368,7 +1369,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 
 #ifdef CONFIG_PPC64
 /* Called with hard IRQs off */
-void __ppc64_runlatch_on(void)
+void notrace __ppc64_runlatch_on(void)
 {
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
@@ -1381,7 +1382,7 @@ void __ppc64_runlatch_on(void)
 }
 
 /* Called with hard IRQs off */
-void __ppc64_runlatch_off(void)
+void notrace __ppc64_runlatch_off(void)
 {
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 577a8aa69c6..457e97aa294 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -18,6 +18,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/debug.h>
+#include <asm/tm.h>
 
 #include "signal.h"
 
@@ -30,13 +31,13 @@ int show_unhandled_signals = 1;
 /*
  * Allocate space for the signal frame
  */
-void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp,
 			   size_t frame_size, int is_32)
 {
         unsigned long oldsp, newsp;
 
         /* Default to using normal stack */
-        oldsp = get_clean_sp(regs, is_32);
+        oldsp = get_clean_sp(sp, is_32);
 
 	/* Check for alt stack */
 	if ((ka->sa.sa_flags & SA_ONSTACK) &&
@@ -175,3 +176,38 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 
 	user_enter();
 }
+
+unsigned long get_tm_stackpointer(struct pt_regs *regs)
+{
+	/* When in an active transaction that takes a signal, we need to be
+	 * careful with the stack.  It's possible that the stack has moved back
+	 * up after the tbegin.  The obvious case here is when the tbegin is
+	 * called inside a function that returns before a tend.  In this case,
+	 * the stack is part of the checkpointed transactional memory state.
+	 * If we write over this non transactionally or in suspend, we are in
+	 * trouble because if we get a tm abort, the program counter and stack
+	 * pointer will be back at the tbegin but our in memory stack won't be
+	 * valid anymore.
+	 *
+	 * To avoid this, when taking a signal in an active transaction, we
+	 * need to use the stack pointer from the checkpointed state, rather
+	 * than the speculated state.  This ensures that the signal context
+	 * (written tm suspended) will be written below the stack required for
+	 * the rollback.  The transaction is aborted becuase of the treclaim,
+	 * so any memory written between the tbegin and the signal will be
+	 * rolled back anyway.
+	 *
+	 * For signals taken in non-TM or suspended mode, we use the
+	 * normal/non-checkpointed stack pointer.
+	 */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (MSR_TM_ACTIVE(regs->msr)) {
+		tm_enable();
+		tm_reclaim(&current->thread, regs->msr, TM_CAUSE_SIGNAL);
+		if (MSR_TM_TRANSACTIONAL(regs->msr))
+			return current->thread.ckpt_regs.gpr[1];
+	}
+#endif
+	return regs->gpr[1];
+}
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index ec84c901cea..c69b9aeb9f2 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -12,7 +12,7 @@
 
 extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
 
-extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+extern void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp,
 				  size_t frame_size, int is_32);
 
 extern int handle_signal32(unsigned long sig, struct k_sigaction *ka,
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 95068bf569a..201385c3a1a 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -503,12 +503,6 @@ static int save_tm_user_regs(struct pt_regs *regs,
 {
 	unsigned long msr = regs->msr;
 
-	/* tm_reclaim rolls back all reg states, updating thread.ckpt_regs,
-	 * thread.transact_fpr[], thread.transact_vr[], etc.
-	 */
-	tm_enable();
-	tm_reclaim(&current->thread, msr, TM_CAUSE_SIGNAL);
-
 	/* Make sure floating point registers are stored in regs */
 	flush_fp_to_thread(current);
 
@@ -965,7 +959,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 
 	/* Set up Signal Frame */
 	/* Put a Real Time Context onto stack */
-	rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf), 1);
+	rt_sf = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*rt_sf), 1);
 	addr = rt_sf;
 	if (unlikely(rt_sf == NULL))
 		goto badframe;
@@ -1403,7 +1397,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	unsigned long tramp;
 
 	/* Set up Signal Frame */
-	frame = get_sigframe(ka, regs, sizeof(*frame), 1);
+	frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 1);
 	if (unlikely(frame == NULL))
 		goto badframe;
 	sc = (struct sigcontext __user *) &frame->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c1794286098..345947367ec 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -154,11 +154,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
  * As above, but Transactional Memory is in use, so deliver sigcontexts
  * containing checkpointed and transactional register states.
  *
- * To do this, we treclaim to gather both sets of registers and set up the
- * 'normal' sigcontext registers with rolled-back register values such that a
- * simple signal handler sees a correct checkpointed register state.
- * If interested, a TM-aware sighandler can examine the transactional registers
- * in the 2nd sigcontext to determine the real origin of the signal.
+ * To do this, we treclaim (done before entering here) to gather both sets of
+ * registers and set up the 'normal' sigcontext registers with rolled-back
+ * register values such that a simple signal handler sees a correct
+ * checkpointed register state.  If interested, a TM-aware sighandler can
+ * examine the transactional registers in the 2nd sigcontext to determine the
+ * real origin of the signal.
  */
 static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 				 struct sigcontext __user *tm_sc,
@@ -184,16 +185,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 
 	BUG_ON(!MSR_TM_ACTIVE(regs->msr));
 
-	/* tm_reclaim rolls back all reg states, saving checkpointed (older)
-	 * GPRs to thread.ckpt_regs and (if used) FPRs to (newer)
-	 * thread.transact_fp and/or VRs to (newer) thread.transact_vr.
-	 * THEN we save out FP/VRs, if necessary, to the checkpointed (older)
-	 * thread.fr[]/vr[]s.  The transactional (newer) GPRs are on the
-	 * stack, in *regs.
-	 */
-	tm_enable();
-	tm_reclaim(&current->thread, msr, TM_CAUSE_SIGNAL);
-
 	flush_fp_to_thread(current);
 
 #ifdef CONFIG_ALTIVEC
@@ -711,7 +702,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info,
 	unsigned long newsp = 0;
 	long err = 0;
 
-	frame = get_sigframe(ka, regs, sizeof(*frame), 0);
+	frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 0);
 	if (unlikely(frame == NULL))
 		goto badframe;
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a7a648f6b75..c0e5caf8ccc 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -53,6 +53,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #include <asm/processor.h>
+#include <asm/tm.h>
 #endif
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
@@ -932,6 +933,28 @@ static int emulate_isel(struct pt_regs *regs, u32 instword)
 	return 0;
 }
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline bool tm_abort_check(struct pt_regs *regs, int cause)
+{
+        /* If we're emulating a load/store in an active transaction, we cannot
+         * emulate it as the kernel operates in transaction suspended context.
+         * We need to abort the transaction.  This creates a persistent TM
+         * abort so tell the user what caused it with a new code.
+	 */
+	if (MSR_TM_TRANSACTIONAL(regs->msr)) {
+		tm_enable();
+		tm_abort(cause);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool tm_abort_check(struct pt_regs *regs, int reason)
+{
+	return false;
+}
+#endif
+
 static int emulate_instruction(struct pt_regs *regs)
 {
 	u32 instword;
@@ -971,6 +994,9 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate load/store string insn. */
 	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
+		if (tm_abort_check(regs,
+				   TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
+			return -EINVAL;
 		PPC_WARN_EMULATED(string, regs);
 		return emulate_string_inst(regs, instword);
 	}
@@ -1139,6 +1165,16 @@ bail:
 	exception_exit(prev_state);
 }
 
+/*
+ * This occurs when running in hypervisor mode on POWER6 or later
+ * and an illegal instruction is encountered.
+ */
+void __kprobes emulation_assist_interrupt(struct pt_regs *regs)
+{
+	regs->msr |= REASON_ILLEGAL;
+	program_check_exception(regs);
+}
+
 void alignment_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -1148,6 +1184,9 @@ void alignment_exception(struct pt_regs *regs)
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
+	if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
+		goto bail;
+
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
 		fixed = fix_alignment(regs);
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 5dd3ab46997..ed038544814 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -441,6 +441,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	struct kvmppc_44x_tlbe *tlbe;
 	unsigned int gtlb_index;
+	int idx;
 
 	gtlb_index = kvmppc_get_gpr(vcpu, ra);
 	if (gtlb_index >= KVM44x_GUEST_TLB_SIZE) {
@@ -473,6 +474,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		return EMULATE_FAIL;
 	}
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	if (tlbe_is_host_safe(vcpu, tlbe)) {
 		gva_t eaddr;
 		gpa_t gpaddr;
@@ -489,6 +492,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
 	trace_kvm_gtlb_write(gtlb_index, tlbe->tid, tlbe->word0, tlbe->word1,
 			     tlbe->word2);
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9de24f8e03c..550f5928b39 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -562,6 +562,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	case H_CPPR:
 	case H_EOI:
 	case H_IPI:
+	case H_IPOLL:
+	case H_XIRR_X:
 		if (kvmppc_xics_enabled(vcpu)) {
 			ret = kvmppc_xics_hcall(vcpu, req);
 			break;
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index b24309c6c2d..da0e0bc268b 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -257,6 +257,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 	case H_CPPR:
 	case H_EOI:
 	case H_IPI:
+	case H_IPOLL:
+	case H_XIRR_X:
 		if (kvmppc_xics_enabled(vcpu))
 			return kvmppc_h_pr_xics_hcall(vcpu, cmd);
 		break;
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index f7a10375661..94c1dd46b83 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -650,6 +650,23 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
 	return H_SUCCESS;
 }
 
+static int kvmppc_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
+{
+	union kvmppc_icp_state state;
+	struct kvmppc_icp *icp;
+
+	icp = vcpu->arch.icp;
+	if (icp->server_num != server) {
+		icp = kvmppc_xics_find_server(vcpu->kvm, server);
+		if (!icp)
+			return H_PARAMETER;
+	}
+	state = ACCESS_ONCE(icp->state);
+	kvmppc_set_gpr(vcpu, 4, ((u32)state.cppr << 24) | state.xisr);
+	kvmppc_set_gpr(vcpu, 5, state.mfrr);
+	return H_SUCCESS;
+}
+
 static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
 {
 	union kvmppc_icp_state old_state, new_state;
@@ -787,6 +804,18 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	if (!xics || !vcpu->arch.icp)
 		return H_HARDWARE;
 
+	/* These requests don't have real-mode implementations at present */
+	switch (req) {
+	case H_XIRR_X:
+		res = kvmppc_h_xirr(vcpu);
+		kvmppc_set_gpr(vcpu, 4, res);
+		kvmppc_set_gpr(vcpu, 5, get_tb());
+		return rc;
+	case H_IPOLL:
+		rc = kvmppc_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4));
+		return rc;
+	}
+
 	/* Check for real mode returning too hard */
 	if (xics->real_mode)
 		return kvmppc_xics_rm_complete(vcpu, req);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 1020119226d..1a1b5118977 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -673,7 +673,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		ret = s;
 		goto out;
 	}
-	kvmppc_lazy_ee_enable();
 
 	kvm_guest_enter();
 
@@ -699,6 +698,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
+	kvmppc_lazy_ee_enable();
+
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
 	/* No need for kvm_guest_exit. It's done in handle_exit.
@@ -832,6 +833,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 {
 	int r = RESUME_HOST;
 	int s;
+	int idx;
+
+#ifdef CONFIG_PPC64
+	WARN_ON(local_paca->irq_happened != 0);
+#endif
+
+	/*
+	 * We enter with interrupts disabled in hardware, but
+	 * we need to call hard_irq_disable anyway to ensure that
+	 * the software state is kept in sync.
+	 */
+	hard_irq_disable();
 
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
@@ -1053,6 +1066,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		}
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
@@ -1075,6 +1090,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_account_exit(vcpu, MMIO_EXITS);
 		}
 
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 
@@ -1098,6 +1114,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
@@ -1114,6 +1132,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_MACHINE_CHECK);
 		}
 
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index c41a5a96b55..6d6f153b6c1 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -396,6 +396,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	struct kvm_book3e_206_tlb_entry *gtlbe;
 	int tlbsel, esel;
 	int recal = 0;
+	int idx;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
 	esel = get_tlb_esel(vcpu, tlbsel);
@@ -430,6 +431,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 			kvmppc_set_tlb1map_range(vcpu, gtlbe);
 	}
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
 		u64 eaddr = get_tlb_eaddr(gtlbe);
@@ -444,6 +447,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		kvmppc_mmu_map(vcpu, eaddr, raddr, index_of(tlbsel, esel));
 	}
 
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;
 }
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 753cc99eff2..19c8379575f 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -177,8 +177,6 @@ int kvmppc_core_check_processor_compat(void)
 		r = 0;
 	else if (strcmp(cur_cpu_spec->cpu_name, "e5500") == 0)
 		r = 0;
-	else if (strcmp(cur_cpu_spec->cpu_name, "e6500") == 0)
-		r = 0;
 	else
 		r = -ENOTSUPP;
 
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index 0ef75bf0695..395c594722a 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -28,13 +28,14 @@ _GLOBAL(copypage_power7)
 	 * aligned we don't need to clear the bottom 7 bits of either
 	 * address.
 	 */
-	ori	r9,r3,1		/* stream=1 */
+	ori	r9,r3,1		/* stream=1 => to */
 
 #ifdef CONFIG_PPC_64K_PAGES
-	lis	r7,0x0E01	/* depth=7, units=512 */
+	lis	r7,0x0E01	/* depth=7
+				 * units/cachelines=512 */
 #else
 	lis	r7,0x0E00	/* depth=7 */
-	ori	r7,r7,0x1000	/* units=32 */
+	ori	r7,r7,0x1000	/* units/cachelines=32 */
 #endif
 	ori	r10,r7,1	/* stream=1 */
 
@@ -43,12 +44,14 @@ _GLOBAL(copypage_power7)
 
 .machine push
 .machine "power4"
-	dcbt	r0,r4,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
+	/* setup read stream 0  */
+	dcbt	r0,r4,0b01000  	/* addr from */
+	dcbt	r0,r7,0b01010   /* length and depth from */
+	/* setup write stream 1 */
+	dcbtst	r0,r9,0b01000   /* addr to */
+	dcbtst	r0,r10,0b01010  /* length and depth to */
 	eieio
-	dcbt	r0,r8,0b01010	/* GO */
+	dcbt	r0,r8,0b01010	/* all streams GO */
 .machine pop
 
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 0d24ff15f5f..d1f11795a7a 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -318,12 +318,14 @@ err1;	stb	r0,0(r3)
 
 .machine push
 .machine "power4"
-	dcbt	r0,r6,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
+	/* setup read stream 0 */
+	dcbt	r0,r6,0b01000   /* addr from */
+	dcbt	r0,r7,0b01010   /* length and depth from */
+	/* setup write stream 1 */
+	dcbtst	r0,r9,0b01000   /* addr to */
+	dcbtst	r0,r10,0b01010  /* length and depth to */
 	eieio
-	dcbt	r0,r8,0b01010	/* GO */
+	dcbt	r0,r8,0b01010	/* all streams GO */
 .machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 6a2aead5b0e..4c122c3f162 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -336,11 +336,18 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 
 	hpte_v = hptep->v;
 	actual_psize = hpte_actual_psize(hptep, psize);
+	/*
+	 * We need to invalidate the TLB always because hpte_remove doesn't do
+	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
+	 * random entry from it. When we do that we don't invalidate the TLB
+	 * (hpte_remove) because we assume the old translation is still
+	 * technically "valid".
+	 */
 	if (actual_psize < 0) {
-		native_unlock_hpte(hptep);
-		return -1;
+		actual_psize = psize;
+		ret = -1;
+		goto err_out;
 	}
-	/* Even if we miss, we need to invalidate the TLB */
 	if (!HPTE_V_COMPARE(hpte_v, want_v)) {
 		DBG_LOW(" -> miss\n");
 		ret = -1;
@@ -350,6 +357,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
 	}
+err_out:
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
@@ -409,7 +417,7 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	hptep = htab_address + slot;
 	actual_psize = hpte_actual_psize(hptep, psize);
 	if (actual_psize < 0)
-		return;
+		actual_psize = psize;
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
@@ -437,21 +445,27 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	hpte_v = hptep->v;
 
 	actual_psize = hpte_actual_psize(hptep, psize);
+	/*
+	 * We need to invalidate the TLB always because hpte_remove doesn't do
+	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
+	 * random entry from it. When we do that we don't invalidate the TLB
+	 * (hpte_remove) because we assume the old translation is still
+	 * technically "valid".
+	 */
 	if (actual_psize < 0) {
+		actual_psize = psize;
 		native_unlock_hpte(hptep);
-		local_irq_restore(flags);
-		return;
+		goto err_out;
 	}
-	/* Even if we miss, we need to invalidate the TLB */
 	if (!HPTE_V_COMPARE(hpte_v, want_v))
 		native_unlock_hpte(hptep);
 	else
 		/* Invalidate the hpte. NOTE: this also unlocks it */
 		hptep->v = 0;
 
+err_out:
 	/* Invalidate the TLB */
 	tlbie(vpn, psize, actual_psize, ssize, local);
-
 	local_irq_restore(flags);
 }
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 237c8e5f264..77fdd2cef33 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -592,8 +592,14 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	do {
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_clear_bad(pmd))
+		if (!is_hugepd(pmd)) {
+			/*
+			 * if it is not hugepd pointer, we should already find
+			 * it cleared.
+			 */
+			WARN_ON(!pmd_none_or_clear_bad(pmd));
 			continue;
+		}
 #ifdef CONFIG_PPC_FSL_BOOK3E
 		/*
 		 * Increment next by the size of the huge mapping since
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 426180b8497..29c6482890c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -110,7 +110,7 @@ static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 
 static bool regs_use_siar(struct pt_regs *regs)
 {
-	return !!(regs->result & 1);
+	return !!regs->result;
 }
 
 /*
@@ -136,22 +136,30 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
  * If we're not doing instruction sampling, give them the SDAR
  * (sampled data address).  If we are doing instruction sampling, then
  * only give them the SDAR if it corresponds to the instruction
- * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC or
- * the [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA.
+ * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the
+ * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER.
  */
 static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 {
 	unsigned long mmcra = regs->dsisr;
-	unsigned long sdsync;
+	bool sdar_valid;
 
-	if (ppmu->flags & PPMU_SIAR_VALID)
-		sdsync = POWER7P_MMCRA_SDAR_VALID;
-	else if (ppmu->flags & PPMU_ALT_SIPR)
-		sdsync = POWER6_MMCRA_SDSYNC;
-	else
-		sdsync = MMCRA_SDSYNC;
+	if (ppmu->flags & PPMU_HAS_SIER)
+		sdar_valid = regs->dar & SIER_SDAR_VALID;
+	else {
+		unsigned long sdsync;
+
+		if (ppmu->flags & PPMU_SIAR_VALID)
+			sdsync = POWER7P_MMCRA_SDAR_VALID;
+		else if (ppmu->flags & PPMU_ALT_SIPR)
+			sdsync = POWER6_MMCRA_SDSYNC;
+		else
+			sdsync = MMCRA_SDSYNC;
+
+		sdar_valid = mmcra & sdsync;
+	}
 
-	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync))
+	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 }
 
@@ -181,11 +189,6 @@ static bool regs_sipr(struct pt_regs *regs)
 	return !!(regs->dsisr & sipr);
 }
 
-static bool regs_no_sipr(struct pt_regs *regs)
-{
-	return !!(regs->result & 2);
-}
-
 static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 {
 	if (regs->msr & MSR_PR)
@@ -208,7 +211,7 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 	 * SIAR which should give slightly more reliable
 	 * results
 	 */
-	if (regs_no_sipr(regs)) {
+	if (ppmu->flags & PPMU_NO_SIPR) {
 		unsigned long siar = mfspr(SPRN_SIAR);
 		if (siar >= PAGE_OFFSET)
 			return PERF_RECORD_MISC_KERNEL;
@@ -239,22 +242,9 @@ static inline void perf_read_regs(struct pt_regs *regs)
 	int use_siar;
 
 	regs->dsisr = mmcra;
-	regs->result = 0;
-
-	if (ppmu->flags & PPMU_NO_SIPR)
-		regs->result |= 2;
-
-	/*
-	 * On power8 if we're in random sampling mode, the SIER is updated.
-	 * If we're in continuous sampling mode, we don't have SIPR.
-	 */
-	if (ppmu->flags & PPMU_HAS_SIER) {
-		if (marked)
-			regs->dar = mfspr(SPRN_SIER);
-		else
-			regs->result |= 2;
-	}
 
+	if (ppmu->flags & PPMU_HAS_SIER)
+		regs->dar = mfspr(SPRN_SIER);
 
 	/*
 	 * If this isn't a PMU exception (eg a software event) the SIAR is
@@ -279,12 +269,12 @@ static inline void perf_read_regs(struct pt_regs *regs)
 		use_siar = 1;
 	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
 		use_siar = 0;
-	else if (!regs_no_sipr(regs) && regs_sipr(regs))
+	else if (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs))
 		use_siar = 0;
 	else
 		use_siar = 1;
 
-	regs->result |= use_siar;
+	regs->result = use_siar;
 }
 
 /*
@@ -308,8 +298,13 @@ static inline int siar_valid(struct pt_regs *regs)
 	unsigned long mmcra = regs->dsisr;
 	int marked = mmcra & MMCRA_SAMPLE_ENABLE;
 
-	if ((ppmu->flags & PPMU_SIAR_VALID) && marked)
-		return mmcra & POWER7P_MMCRA_SIAR_VALID;
+	if (marked) {
+		if (ppmu->flags & PPMU_HAS_SIER)
+			return regs->dar & SIER_SIAR_VALID;
+
+		if (ppmu->flags & PPMU_SIAR_VALID)
+			return mmcra & POWER7P_MMCRA_SIAR_VALID;
+	}
 
 	return 1;
 }
@@ -1763,7 +1758,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 			}
 		}
 	}
-	if ((!found) && printk_ratelimit())
+	if (!found && !nmi && printk_ratelimit())
 		printk(KERN_WARNING "Can't find PMC that caused IRQ\n");
 
 	/*
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 023b288f895..4459eff7a75 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -19,6 +19,8 @@ config PPC_PSERIES
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
+	select HOTPLUG if SMP
+	select HOTPLUG_CPU if SMP
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
index 5a4c8790305..5ce3ba7ad13 100644
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ b/arch/powerpc/platforms/pseries/eeh_cache.c
@@ -294,8 +294,6 @@ void __init eeh_addr_cache_build(void)
 	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
 
 	for_each_pci_dev(dev) {
-		eeh_addr_cache_insert_dev(dev);
-
 		dn = pci_device_to_OF_node(dev);
 		if (!dn)
 			continue;
@@ -308,6 +306,8 @@ void __init eeh_addr_cache_build(void)
 		dev->dev.archdata.edev = edev;
 		edev->pdev = dev;
 
+		eeh_addr_cache_insert_dev(dev);
+
 		eeh_sysfs_add_device(dev);
 	}
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index fe43d1aa2cf..9d4a9e8562b 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -639,7 +639,8 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 
 	if (pe->type & EEH_PE_PHB) {
 		bus = pe->phb->bus;
-	} else if (pe->type & EEH_PE_BUS) {
+	} else if (pe->type & EEH_PE_BUS ||
+		   pe->type & EEH_PE_DEVICE) {
 		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		pdev = eeh_dev_to_pci_dev(edev);
 		if (pdev)
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 19506f93573..b456b157d33 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -83,7 +83,11 @@ static int pseries_eeh_init(void)
 	ibm_configure_pe		= rtas_token("ibm,configure-pe");
 	ibm_configure_bridge		= rtas_token("ibm,configure-bridge");
 
-	/* necessary sanity check */
+	/*
+	 * Necessary sanity check. We needn't check "get-config-addr-info"
+	 * and its variant since the old firmware probably support address
+	 * of domain/bus/slot/function for EEH RTAS operations.
+	 */
 	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) {
 		pr_warning("%s: RTAS service <ibm,set-eeh-option> invalid\n",
 			__func__);
@@ -102,12 +106,6 @@ static int pseries_eeh_init(void)
 		pr_warning("%s: RTAS service <ibm,slot-error-detail> invalid\n",
 			__func__);
 		return -EINVAL;
-	} else if (ibm_get_config_addr_info2 == RTAS_UNKNOWN_SERVICE &&
-		   ibm_get_config_addr_info == RTAS_UNKNOWN_SERVICE) {
-		pr_warning("%s: RTAS service <ibm,get-config-addr-info2> and "
-			"<ibm,get-config-addr-info> invalid\n",
-			__func__);
-		return -EINVAL;
 	} else if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE &&
 		   ibm_configure_bridge == RTAS_UNKNOWN_SERVICE) {
 		pr_warning("%s: RTAS service <ibm,configure-pe> and "
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 028ac1f71b5..46ac1ddea68 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -97,22 +97,14 @@ static int fsl_indirect_read_config(struct pci_bus *bus, unsigned int devfn,
 	return indirect_read_config(bus, devfn, offset, len, val);
 }
 
-static struct pci_ops fsl_indirect_pci_ops =
+#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
+
+static struct pci_ops fsl_indirect_pcie_ops =
 {
 	.read = fsl_indirect_read_config,
 	.write = indirect_write_config,
 };
 
-static void __init fsl_setup_indirect_pci(struct pci_controller* hose,
-					  resource_size_t cfg_addr,
-					  resource_size_t cfg_data, u32 flags)
-{
-	setup_indirect_pci(hose, cfg_addr, cfg_data, flags);
-	hose->ops = &fsl_indirect_pci_ops;
-}
-
-#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
-
 #define MAX_PHYS_ADDR_BITS	40
 static u64 pci64_dma_offset = 1ull << MAX_PHYS_ADDR_BITS;
 
@@ -504,13 +496,15 @@ int __init fsl_add_bridge(struct platform_device *pdev, int is_primary)
 	if (!hose->private_data)
 		goto no_bridge;
 
-	fsl_setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4,
-			       PPC_INDIRECT_TYPE_BIG_ENDIAN);
+	setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4,
+			   PPC_INDIRECT_TYPE_BIG_ENDIAN);
 
 	if (in_be32(&pci->block_rev1) < PCIE_IP_REV_3_0)
 		hose->indirect_type |= PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK;
 
 	if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) {
+		/* use fsl_indirect_read_config for PCIe */
+		hose->ops = &fsl_indirect_pcie_ops;
 		/* For PCIE read HEADER_TYPE to identify controler mode */
 		early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type);
 		if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
@@ -814,8 +808,8 @@ int __init mpc83xx_add_bridge(struct device_node *dev)
 		if (ret)
 			goto err0;
 	} else {
-		fsl_setup_indirect_pci(hose, rsrc_cfg.start,
-				       rsrc_cfg.start + 4, 0);
+		setup_indirect_pci(hose, rsrc_cfg.start,
+				   rsrc_cfg.start + 4, 0);
 	}
 
 	printk(KERN_INFO "Found FSL PCI host bridge at 0x%016llx. "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0a13ecb270c..3cc2f9159ab 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -54,7 +54,7 @@ static DEFINE_RAW_SPINLOCK(mpic_lock);
 
 #ifdef CONFIG_PPC32	/* XXX for now */
 #ifdef CONFIG_IRQ_ALL_CPUS
-#define distribute_irqs	(!(mpic->flags & MPIC_SINGLE_DEST_CPU))
+#define distribute_irqs	(1)
 #else
 #define distribute_irqs	(0)
 #endif
@@ -1703,7 +1703,7 @@ void mpic_setup_this_cpu(void)
 	 * it differently, then we should make sure we also change the default
 	 * values of irq_desc[].affinity in irq.c.
  	 */
-	if (distribute_irqs) {
+	if (distribute_irqs && !(mpic->flags & MPIC_SINGLE_DEST_CPU)) {
 	 	for (i = 0; i < mpic->num_sources ; i++)
 			mpic_irq_write(i, MPIC_INFO(IRQ_DESTINATION),
 				mpic_irq_read(i, MPIC_INFO(IRQ_DESTINATION)) | msk);
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index bae0f402bf2..87a22092b68 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -212,7 +212,9 @@ appldata_timer_handler(ctl_table *ctl, int write,
 		return 0;
 	}
 	if (!write) {
-		len = sprintf(buf, appldata_timer_active ? "1\n" : "0\n");
+		strncpy(buf, appldata_timer_active ? "1\n" : "0\n",
+			ARRAY_SIZE(buf));
+		len = strnlen(buf, ARRAY_SIZE(buf));
 		if (len > *lenp)
 			len = *lenp;
 		if (copy_to_user(buffer, buf, len))
@@ -317,7 +319,8 @@ appldata_generic_handler(ctl_table *ctl, int write,
 		return 0;
 	}
 	if (!write) {
-		len = sprintf(buf, ops->active ? "1\n" : "0\n");
+		strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
+		len = strnlen(buf, ARRAY_SIZE(buf));
 		if (len > *lenp)
 			len = *lenp;
 		if (copy_to_user(buffer, buf, len)) {
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index 9411db653ba..2f8c1abeb08 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -50,9 +50,10 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
+	debug_dma_mapping_error(dev, dma_addr);
 	if (dma_ops->mapping_error)
 		return dma_ops->mapping_error(dev, dma_addr);
-	return (dma_addr == 0UL);
+	return (dma_addr == DMA_ERROR_CODE);
 }
 
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
@@ -71,8 +72,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	dma_ops->free(dev, size, cpu_addr, dma_handle, NULL);
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	dma_ops->free(dev, size, cpu_addr, dma_handle, NULL);
 }
 
 #endif /* _ASM_S390_DMA_MAPPING_H */
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 379d96e2105..fd9be010f9b 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -36,6 +36,7 @@ static inline void * phys_to_virt(unsigned long address)
 }
 
 void *xlate_dev_mem_ptr(unsigned long phys);
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
 void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
 
 /*
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 0f0de30e3e3..e8b6e5b8932 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -623,7 +623,7 @@ static inline pgste_t pgste_get_lock(pte_t *ptep)
 		"	csg	%0,%1,%2\n"
 		"	jl	0b\n"
 		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
-		: "Q" (ptep[PTRS_PER_PTE]) : "cc");
+		: "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory");
 #endif
 	return __pgste(new);
 }
@@ -635,18 +635,26 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 		"	nihh	%1,0xff7f\n"	/* clear RCP_PCL_BIT */
 		"	stg	%1,%0\n"
 		: "=Q" (ptep[PTRS_PER_PTE])
-		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) : "cc");
+		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
+		: "cc", "memory");
 	preempt_enable();
 #endif
 }
 
+static inline void pgste_set(pte_t *ptep, pgste_t pgste)
+{
+#ifdef CONFIG_PGSTE
+	*(pgste_t *)(ptep + PTRS_PER_PTE) = pgste;
+#endif
+}
+
 static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address, bits;
 	unsigned char skey;
 
-	if (!pte_present(*ptep))
+	if (pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	address = pte_val(*ptep) & PAGE_MASK;
 	skey = page_get_storage_key(address);
@@ -680,7 +688,7 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 #ifdef CONFIG_PGSTE
 	int young;
 
-	if (!pte_present(*ptep))
+	if (pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	/* Get referenced bit from storage key */
 	young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
@@ -704,17 +712,19 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address;
-	unsigned long okey, nkey;
+	unsigned long nkey;
 
-	if (!pte_present(entry))
+	if (pte_val(entry) & _PAGE_INVALID)
 		return;
+	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
 	address = pte_val(entry) & PAGE_MASK;
-	okey = nkey = page_get_storage_key(address);
-	nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
-	/* Set page access key and fetch protection bit from pgste */
-	nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
-	if (okey != nkey)
-		page_set_storage_key(address, nkey, 0);
+	/*
+	 * Set page access key and fetch protection bit from pgste.
+	 * The guest C/R information is still in the PGSTE, set real
+	 * key C/R to 0.
+	 */
+	nkey = (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
+	page_set_storage_key(address, nkey, 0);
 #endif
 }
 
@@ -1098,6 +1108,11 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
 	pte = *ptep;
 	if (!mm_exclusive(mm))
 		__ptep_ipte(address, ptep);
+
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_update_all(&pte, pgste);
+		pgste_set(ptep, pgste);
+	}
 	return pte;
 }
 
@@ -1105,9 +1120,13 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 					   unsigned long address,
 					   pte_t *ptep, pte_t pte)
 {
+	pgste_t pgste;
+
 	if (mm_has_pgste(mm)) {
+		pgste = *(pgste_t *)(ptep + PTRS_PER_PTE);
+		pgste_set_key(ptep, pgste, pte);
 		pgste_set_pte(ptep, pte);
-		pgste_set_unlock(ptep, *(pgste_t *)(ptep + PTRS_PER_PTE));
+		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
 }
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 29829747725..87acc38f73c 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -74,6 +74,8 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 
 static void show_trace(struct task_struct *task, unsigned long *stack)
 {
+	const unsigned long frame_size =
+		STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
 	register unsigned long __r15 asm ("15");
 	unsigned long sp;
 
@@ -82,11 +84,13 @@ static void show_trace(struct task_struct *task, unsigned long *stack)
 		sp = task ? task->thread.ksp : __r15;
 	printk("Call Trace:\n");
 #ifdef CONFIG_CHECK_STACK
-	sp = __show_trace(sp, S390_lowcore.panic_stack - 4096,
-			  S390_lowcore.panic_stack);
+	sp = __show_trace(sp,
+			  S390_lowcore.panic_stack + frame_size - 4096,
+			  S390_lowcore.panic_stack + frame_size);
 #endif
-	sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE,
-			  S390_lowcore.async_stack);
+	sp = __show_trace(sp,
+			  S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
+			  S390_lowcore.async_stack + frame_size);
 	if (task)
 		__show_trace(sp, (unsigned long) task_stack_page(task),
 			     (unsigned long) task_stack_page(task) + THREAD_SIZE);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index d8a6a385d04..feb719d3c85 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -754,9 +754,9 @@ static struct bin_attribute sys_reipl_fcp_scp_data_attr = {
 	.write = reipl_fcp_scpdata_write,
 };
 
-DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n",
+DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n",
 		   reipl_block_fcp->ipl_info.fcp.wwpn);
-DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n",
+DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n",
 		   reipl_block_fcp->ipl_info.fcp.lun);
 DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n",
 		   reipl_block_fcp->ipl_info.fcp.bootprog);
@@ -1323,9 +1323,9 @@ static struct shutdown_action __refdata reipl_action = {
 
 /* FCP dump device attributes */
 
-DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%016llx\n",
+DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n",
 		   dump_block_fcp->ipl_info.fcp.wwpn);
-DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%016llx\n",
+DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n",
 		   dump_block_fcp->ipl_info.fcp.lun);
 DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n",
 		   dump_block_fcp->ipl_info.fcp.bootprog);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index f7fb58903f6..dd3c1994b8b 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -311,3 +311,69 @@ void measurement_alert_subclass_unregister(void)
 	spin_unlock(&ma_subclass_lock);
 }
 EXPORT_SYMBOL(measurement_alert_subclass_unregister);
+
+#ifdef CONFIG_SMP
+void synchronize_irq(unsigned int irq)
+{
+	/*
+	 * Not needed, the handler is protected by a lock and IRQs that occur
+	 * after the handler is deleted are just NOPs.
+	 */
+}
+EXPORT_SYMBOL_GPL(synchronize_irq);
+#endif
+
+#ifndef CONFIG_PCI
+
+/* Only PCI devices have dynamically-defined IRQ handlers */
+
+int request_irq(unsigned int irq, irq_handler_t handler,
+		unsigned long irqflags, const char *devname, void *dev_id)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(request_irq);
+
+void free_irq(unsigned int irq, void *dev_id)
+{
+	WARN_ON(1);
+}
+EXPORT_SYMBOL_GPL(free_irq);
+
+void enable_irq(unsigned int irq)
+{
+	WARN_ON(1);
+}
+EXPORT_SYMBOL_GPL(enable_irq);
+
+void disable_irq(unsigned int irq)
+{
+	WARN_ON(1);
+}
+EXPORT_SYMBOL_GPL(disable_irq);
+
+#endif /* !CONFIG_PCI */
+
+void disable_irq_nosync(unsigned int irq)
+{
+	disable_irq(irq);
+}
+EXPORT_SYMBOL_GPL(disable_irq_nosync);
+
+unsigned long probe_irq_on(void)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(probe_irq_on);
+
+int probe_irq_off(unsigned long val)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(probe_irq_off);
+
+unsigned int probe_irq_mask(unsigned long val)
+{
+	return val;
+}
+EXPORT_SYMBOL_GPL(probe_irq_mask);
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index b6506ee32a3..29bd7bec417 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -225,7 +225,7 @@ _sclp_print:
 	ahi	%r2,1
 	ltr	%r0,%r0				# end of string?
 	jz	.LfinalizemtoS4
-	chi	%r0,0x15			# end of line (NL)?
+	chi	%r0,0x0a			# end of line (NL)?
 	jz	.LfinalizemtoS4
 	stc	%r0,0(%r6,%r7)			# copy to mto
 	la	%r11,0(%r6,%r7)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 05674b66900..4f977d0d25c 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -428,34 +428,27 @@ void smp_stop_cpu(void)
  * This is the main routine where commands issued by other
  * cpus are handled.
  */
-static void do_ext_call_interrupt(struct ext_code ext_code,
-				  unsigned int param32, unsigned long param64)
+static void smp_handle_ext_call(void)
 {
 	unsigned long bits;
-	int cpu;
-
-	cpu = smp_processor_id();
-	if (ext_code.code == 0x1202)
-		inc_irq_stat(IRQEXT_EXC);
-	else
-		inc_irq_stat(IRQEXT_EMS);
-	/*
-	 * handle bit signal external calls
-	 */
-	bits = xchg(&pcpu_devices[cpu].ec_mask, 0);
 
+	/* handle bit signal external calls */
+	bits = xchg(&pcpu_devices[smp_processor_id()].ec_mask, 0);
 	if (test_bit(ec_stop_cpu, &bits))
 		smp_stop_cpu();
-
 	if (test_bit(ec_schedule, &bits))
 		scheduler_ipi();
-
 	if (test_bit(ec_call_function, &bits))
 		generic_smp_call_function_interrupt();
-
 	if (test_bit(ec_call_function_single, &bits))
 		generic_smp_call_function_single_interrupt();
+}
 
+static void do_ext_call_interrupt(struct ext_code ext_code,
+				  unsigned int param32, unsigned long param64)
+{
+	inc_irq_stat(ext_code.code == 0x1202 ? IRQEXT_EXC : IRQEXT_EMS);
+	smp_handle_ext_call();
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
@@ -760,6 +753,8 @@ int __cpu_disable(void)
 {
 	unsigned long cregs[16];
 
+	/* Handle possible pending IPIs */
+	smp_handle_ext_call();
 	set_cpu_online(smp_processor_id(), false);
 	/* Disable pseudo page faults on this cpu. */
 	pfault_fini();
diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c
index 3cbd3b8bf31..cca388253a3 100644
--- a/arch/s390/mm/mem_detect.c
+++ b/arch/s390/mm/mem_detect.c
@@ -123,7 +123,8 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
 			continue;
 		} else if ((addr <= chunk->addr) &&
 			   (addr + size >= chunk->addr + chunk->size)) {
-			memset(chunk, 0 , sizeof(*chunk));
+			memmove(chunk, chunk + 1, (MEMORY_CHUNKS-i-1) * sizeof(*chunk));
+			memset(&mem_chunk[MEMORY_CHUNKS-1], 0, sizeof(*chunk));
 		} else if (addr + size < chunk->addr + chunk->size) {
 			chunk->size =  chunk->addr + chunk->size - addr - size;
 			chunk->addr = addr + size;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 18dc417aaf7..a938b548f07 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -492,7 +492,7 @@ static int gmap_connect_pgtable(unsigned long address, unsigned long segment,
 	mp = (struct gmap_pgtable *) page->index;
 	rmap->gmap = gmap;
 	rmap->entry = segment_ptr;
-	rmap->vmaddr = address;
+	rmap->vmaddr = address & PMD_MASK;
 	spin_lock(&mm->page_table_lock);
 	if (*segment_ptr == segment) {
 		list_add(&rmap->list, &mp->mapper);
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index e6f15b5d8b7..f1e5be85d59 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -302,15 +302,6 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 	return rc;
 }
 
-void synchronize_irq(unsigned int irq)
-{
-	/*
-	 * Not needed, the handler is protected by a lock and IRQs that occur
-	 * after the handler is deleted are just NOPs.
-	 */
-}
-EXPORT_SYMBOL_GPL(synchronize_irq);
-
 void enable_irq(unsigned int irq)
 {
 	struct msi_desc *msi = irq_get_msi_desc(irq);
@@ -327,30 +318,6 @@ void disable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(disable_irq);
 
-void disable_irq_nosync(unsigned int irq)
-{
-	disable_irq(irq);
-}
-EXPORT_SYMBOL_GPL(disable_irq_nosync);
-
-unsigned long probe_irq_on(void)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(probe_irq_on);
-
-int probe_irq_off(unsigned long val)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(probe_irq_off);
-
-unsigned int probe_irq_mask(unsigned long val)
-{
-	return val;
-}
-EXPORT_SYMBOL_GPL(probe_irq_mask);
-
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
 }
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index ff18e3cfb6b..7e4a97fbded 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += cputime.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
+generic-y += linkage.h
 generic-y += local64.h
 generic-y += mutex.h
 generic-y += irq_regs.h
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
index 15a716934e4..b836e9297f2 100644
--- a/arch/sparc/include/asm/leon.h
+++ b/arch/sparc/include/asm/leon.h
@@ -135,7 +135,7 @@ static inline int sparc_leon3_cpuid(void)
 
 #ifdef CONFIG_SMP
 # define LEON3_IRQ_IPI_DEFAULT		13
-# define LEON3_IRQ_TICKER		(leon3_ticker_irq)
+# define LEON3_IRQ_TICKER		(leon3_gptimer_irq)
 # define LEON3_IRQ_CROSS_CALL		15
 #endif
 
diff --git a/arch/sparc/include/asm/leon_amba.h b/arch/sparc/include/asm/leon_amba.h
index f3034eddf46..24ec48c3ff9 100644
--- a/arch/sparc/include/asm/leon_amba.h
+++ b/arch/sparc/include/asm/leon_amba.h
@@ -47,6 +47,7 @@ struct amba_prom_registers {
 #define LEON3_GPTIMER_LD 4
 #define LEON3_GPTIMER_IRQEN 8
 #define LEON3_GPTIMER_SEPIRQ 8
+#define LEON3_GPTIMER_TIMERS 0x7
 
 #define LEON23_REG_TIMER_CONTROL_EN    0x00000001 /* 1 = enable counting */
 /* 0 = hold scalar and counter */
diff --git a/arch/sparc/include/asm/linkage.h b/arch/sparc/include/asm/linkage.h
deleted file mode 100644
index 291c2d01c44..00000000000
--- a/arch/sparc/include/asm/linkage.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
-
-/* Nothing to see here... */
-
-#endif
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 75bb608c423..5ef48dab563 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -843,7 +843,8 @@ void ldom_reboot(const char *boot_command)
 		unsigned long len;
 
 		strcpy(full_boot_str, "boot ");
-		strcpy(full_boot_str + strlen("boot "), boot_command);
+		strlcpy(full_boot_str + strlen("boot "), boot_command,
+			sizeof(full_boot_str + strlen("boot ")));
 		len = strlen(full_boot_str);
 
 		if (reboot_data_supported) {
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 7c0231dabe4..b7c68976cbc 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -38,7 +38,6 @@ static DEFINE_SPINLOCK(leon_irq_lock);
 
 unsigned long leon3_gptimer_irq; /* interrupt controller irq number */
 unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
-int leon3_ticker_irq; /* Timer ticker IRQ */
 unsigned int sparc_leon_eirq;
 #define LEON_IMASK(cpu) (&leon3_irqctrl_regs->mask[cpu])
 #define LEON_IACK (&leon3_irqctrl_regs->iclear)
@@ -278,6 +277,9 @@ irqreturn_t leon_percpu_timer_ce_interrupt(int irq, void *unused)
 
 	leon_clear_profile_irq(cpu);
 
+	if (cpu == boot_cpu_id)
+		timer_interrupt(irq, NULL);
+
 	ce = &per_cpu(sparc32_clockevent, cpu);
 
 	irq_enter();
@@ -299,6 +301,7 @@ void __init leon_init_timers(void)
 	int icsel;
 	int ampopts;
 	int err;
+	u32 config;
 
 	sparc_config.get_cycles_offset = leon_cycles_offset;
 	sparc_config.cs_period = 1000000 / HZ;
@@ -377,23 +380,6 @@ void __init leon_init_timers(void)
 	LEON3_BYPASS_STORE_PA(
 			&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl, 0);
 
-#ifdef CONFIG_SMP
-	leon3_ticker_irq = leon3_gptimer_irq + 1 + leon3_gptimer_idx;
-
-	if (!(LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->config) &
-	      (1<<LEON3_GPTIMER_SEPIRQ))) {
-		printk(KERN_ERR "timer not configured with separate irqs\n");
-		BUG();
-	}
-
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].val,
-				0);
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].rld,
-				(((1000000/HZ) - 1)));
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].ctrl,
-				0);
-#endif
-
 	/*
 	 * The IRQ controller may (if implemented) consist of multiple
 	 * IRQ controllers, each mapped on a 4Kb boundary.
@@ -416,13 +402,6 @@ void __init leon_init_timers(void)
 	if (eirq != 0)
 		leon_eirq_setup(eirq);
 
-	irq = _leon_build_device_irq(NULL, leon3_gptimer_irq+leon3_gptimer_idx);
-	err = request_irq(irq, timer_interrupt, IRQF_TIMER, "timer", NULL);
-	if (err) {
-		printk(KERN_ERR "unable to attach timer IRQ%d\n", irq);
-		prom_halt();
-	}
-
 #ifdef CONFIG_SMP
 	{
 		unsigned long flags;
@@ -439,30 +418,31 @@ void __init leon_init_timers(void)
 	}
 #endif
 
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
-			      LEON3_GPTIMER_EN |
-			      LEON3_GPTIMER_RL |
-			      LEON3_GPTIMER_LD |
-			      LEON3_GPTIMER_IRQEN);
+	config = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->config);
+	if (config & (1 << LEON3_GPTIMER_SEPIRQ))
+		leon3_gptimer_irq += leon3_gptimer_idx;
+	else if ((config & LEON3_GPTIMER_TIMERS) > 1)
+		pr_warn("GPTIMER uses shared irqs, using other timers of the same core will fail.\n");
 
 #ifdef CONFIG_SMP
 	/* Install per-cpu IRQ handler for broadcasted ticker */
-	irq = leon_build_device_irq(leon3_ticker_irq, handle_percpu_irq,
+	irq = leon_build_device_irq(leon3_gptimer_irq, handle_percpu_irq,
 				    "per-cpu", 0);
 	err = request_irq(irq, leon_percpu_timer_ce_interrupt,
-			  IRQF_PERCPU | IRQF_TIMER, "ticker",
-			  NULL);
+			  IRQF_PERCPU | IRQF_TIMER, "timer", NULL);
+#else
+	irq = _leon_build_device_irq(NULL, leon3_gptimer_irq);
+	err = request_irq(irq, timer_interrupt, IRQF_TIMER, "timer", NULL);
+#endif
 	if (err) {
-		printk(KERN_ERR "unable to attach ticker IRQ%d\n", irq);
+		pr_err("Unable to attach timer IRQ%d\n", irq);
 		prom_halt();
 	}
-
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].ctrl,
+	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
 			      LEON3_GPTIMER_EN |
 			      LEON3_GPTIMER_RL |
 			      LEON3_GPTIMER_LD |
 			      LEON3_GPTIMER_IRQEN);
-#endif
 	return;
 bad:
 	printk(KERN_ERR "No Timer/irqctrl found\n");
diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c
index 7739a54315e..6df26e37f87 100644
--- a/arch/sparc/kernel/leon_pci_grpci1.c
+++ b/arch/sparc/kernel/leon_pci_grpci1.c
@@ -536,11 +536,9 @@ static int grpci1_of_probe(struct platform_device *ofdev)
 
 	/* find device register base address */
 	res = platform_get_resource(ofdev, IORESOURCE_MEM, 0);
-	regs = devm_request_and_ioremap(&ofdev->dev, res);
-	if (!regs) {
-		dev_err(&ofdev->dev, "io-regs mapping failed\n");
-		return -EADDRNOTAVAIL;
-	}
+	regs = devm_ioremap_resource(&ofdev->dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	/*
 	 * check that we're in Host Slot and that we can act as a Host Bridge
diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c
index bdf53d9a8d4..b0b3967a2dd 100644
--- a/arch/sparc/kernel/leon_pmc.c
+++ b/arch/sparc/kernel/leon_pmc.c
@@ -47,6 +47,10 @@ void pmc_leon_idle_fixup(void)
 	 * MMU does not get a TLB miss here by using the MMU BYPASS ASI.
 	 */
 	register unsigned int address = (unsigned int)leon3_irqctrl_regs;
+
+	/* Interrupts need to be enabled to not hang the CPU */
+	local_irq_enable();
+
 	__asm__ __volatile__ (
 		"wr	%%g0, %%asr19\n"
 		"lda	[%0] %1, %%g0\n"
@@ -60,6 +64,9 @@ void pmc_leon_idle_fixup(void)
  */
 void pmc_leon_idle(void)
 {
+	/* Interrupts need to be enabled to not hang the CPU */
+	local_irq_enable();
+
 	/* For systems without power-down, this will be no-op */
 	__asm__ __volatile__ ("wr	%g0, %asr19\n\t");
 }
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
index 9f20566b077..79cc0d1a477 100644
--- a/arch/sparc/kernel/prom_common.c
+++ b/arch/sparc/kernel/prom_common.c
@@ -54,6 +54,7 @@ EXPORT_SYMBOL(of_set_property_mutex);
 int of_set_property(struct device_node *dp, const char *name, void *val, int len)
 {
 	struct property **prevp;
+	unsigned long flags;
 	void *new_val;
 	int err;
 
@@ -64,7 +65,7 @@ int of_set_property(struct device_node *dp, const char *name, void *val, int len
 	err = -ENODEV;
 
 	mutex_lock(&of_set_property_mutex);
-	raw_spin_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	prevp = &dp->properties;
 	while (*prevp) {
 		struct property *prop = *prevp;
@@ -91,7 +92,7 @@ int of_set_property(struct device_node *dp, const char *name, void *val, int len
 		}
 		prevp = &(*prevp)->next;
 	}
-	raw_spin_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	mutex_unlock(&of_set_property_mutex);
 
 	/* XXX Upate procfs if necessary... */
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 38bf80a22f0..1434526970a 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -304,7 +304,7 @@ void __init setup_arch(char **cmdline_p)
 
 	/* Initialize PROM console and command line. */
 	*cmdline_p = prom_getbootargs();
-	strcpy(boot_command_line, *cmdline_p);
+	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
 	parse_early_param();
 
 	boot_flags_init(*cmdline_p);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 88a127b9c69..13785547e43 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -555,7 +555,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	/* Initialize PROM console and command line. */
 	*cmdline_p = prom_getbootargs();
-	strcpy(boot_command_line, *cmdline_p);
+	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
 	parse_early_param();
 
 	boot_flags_init(*cmdline_p);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index a7171997adf..04fd55a6e46 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1098,7 +1098,14 @@ static int __init grab_mblocks(struct mdesc_handle *md)
 		m->size = *val;
 		val = mdesc_get_property(md, node,
 					 "address-congruence-offset", NULL);
-		m->offset = *val;
+
+		/* The address-congruence-offset property is optional.
+		 * Explicity zero it be identifty this.
+		 */
+		if (val)
+			m->offset = *val;
+		else
+			m->offset = 0UL;
 
 		numadbg("MBLOCK[%d]: base[%llx] size[%llx] offset[%llx]\n",
 			count - 1, m->base, m->size, m->offset);
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 83d89bcb44a..37e7bc4c95b 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -85,8 +85,8 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 	}
 
 	if (!tb->active) {
-		global_flush_tlb_page(mm, vaddr);
 		flush_tsb_user_page(mm, vaddr);
+		global_flush_tlb_page(mm, vaddr);
 		goto out;
 	}
 
diff --git a/arch/sparc/prom/bootstr_32.c b/arch/sparc/prom/bootstr_32.c
index f5ec32e0d41..d2b49d2365e 100644
--- a/arch/sparc/prom/bootstr_32.c
+++ b/arch/sparc/prom/bootstr_32.c
@@ -23,23 +23,25 @@ prom_getbootargs(void)
 		return barg_buf;
 	}
 
-	switch(prom_vers) {
+	switch (prom_vers) {
 	case PROM_V0:
 		cp = barg_buf;
 		/* Start from 1 and go over fd(0,0,0)kernel */
-		for(iter = 1; iter < 8; iter++) {
+		for (iter = 1; iter < 8; iter++) {
 			arg = (*(romvec->pv_v0bootargs))->argv[iter];
 			if (arg == NULL)
 				break;
-			while(*arg != 0) {
+			while (*arg != 0) {
 				/* Leave place for space and null. */
-				if(cp >= barg_buf + BARG_LEN-2){
+				if (cp >= barg_buf + BARG_LEN - 2)
 					/* We might issue a warning here. */
 					break;
-				}
 				*cp++ = *arg++;
 			}
 			*cp++ = ' ';
+			if (cp >= barg_buf + BARG_LEN - 1)
+				/* We might issue a warning here. */
+				break;
 		}
 		*cp = 0;
 		break;
diff --git a/arch/sparc/prom/tree_64.c b/arch/sparc/prom/tree_64.c
index 92204c3800b..bd1b2a3ac34 100644
--- a/arch/sparc/prom/tree_64.c
+++ b/arch/sparc/prom/tree_64.c
@@ -39,7 +39,7 @@ inline phandle __prom_getchild(phandle node)
 	return prom_node_to_node("child", node);
 }
 
-inline phandle prom_getchild(phandle node)
+phandle prom_getchild(phandle node)
 {
 	phandle cnode;
 
@@ -72,7 +72,7 @@ inline phandle __prom_getsibling(phandle node)
 	return prom_node_to_node(prom_peer_name, node);
 }
 
-inline phandle prom_getsibling(phandle node)
+phandle prom_getsibling(phandle node)
 {
 	phandle sibnode;
 
@@ -89,7 +89,7 @@ EXPORT_SYMBOL(prom_getsibling);
 /* Return the length in bytes of property 'prop' at node 'node'.
  * Return -1 on error.
  */
-inline int prom_getproplen(phandle node, const char *prop)
+int prom_getproplen(phandle node, const char *prop)
 {
 	unsigned long args[6];
 
@@ -113,8 +113,8 @@ EXPORT_SYMBOL(prom_getproplen);
  * 'buffer' which has a size of 'bufsize'.  If the acquisition
  * was successful the length will be returned, else -1 is returned.
  */
-inline int prom_getproperty(phandle node, const char *prop,
-			    char *buffer, int bufsize)
+int prom_getproperty(phandle node, const char *prop,
+		     char *buffer, int bufsize)
 {
 	unsigned long args[8];
 	int plen;
@@ -141,7 +141,7 @@ EXPORT_SYMBOL(prom_getproperty);
 /* Acquire an integer property and return its value.  Returns -1
  * on failure.
  */
-inline int prom_getint(phandle node, const char *prop)
+int prom_getint(phandle node, const char *prop)
 {
 	int intprop;
 
@@ -235,7 +235,7 @@ static const char *prom_nextprop_name = "nextprop";
 /* Return the first property type for node 'node'.
  * buffer should be at least 32B in length
  */
-inline char *prom_firstprop(phandle node, char *buffer)
+char *prom_firstprop(phandle node, char *buffer)
 {
 	unsigned long args[7];
 
@@ -261,7 +261,7 @@ EXPORT_SYMBOL(prom_firstprop);
  * at node 'node' .  Returns NULL string if no more
  * property types for this node.
  */
-inline char *prom_nextprop(phandle node, const char *oprop, char *buffer)
+char *prom_nextprop(phandle node, const char *oprop, char *buffer)
 {
 	unsigned long args[7];
 	char buf[32];
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index 4385cb6fa00..a93b02a2522 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -84,4 +84,6 @@ uint64_t __ashrdi3(uint64_t, unsigned int);
 EXPORT_SYMBOL(__ashrdi3);
 uint64_t __ashldi3(uint64_t, unsigned int);
 EXPORT_SYMBOL(__ashldi3);
+int __ffsdi2(uint64_t);
+EXPORT_SYMBOL(__ffsdi2);
 #endif
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index d7d21851e60..3df3bd54449 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -147,7 +147,7 @@ void mconsole_proc(struct mc_request *req)
 	}
 
 	do {
-		loff_t pos;
+		loff_t pos = file->f_pos;
 		mm_segment_t old_fs = get_fs();
 		set_fs(KERNEL_DS);
 		len = vfs_read(file, buf, PAGE_SIZE - 1, &pos);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 685692c94f0..fe120da2562 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2265,6 +2265,7 @@ source "fs/Kconfig.binfmt"
 config IA32_EMULATION
 	bool "IA32 Emulation"
 	depends on X86_64
+	select BINFMT_ELF
 	select COMPAT_BINFMT_ELF
 	select HAVE_UID16
 	---help---
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 35ee62fccf9..c205035a6b9 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -251,51 +251,6 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 	*size = len;
 }
 
-static efi_status_t setup_efi_vars(struct boot_params *params)
-{
-	struct setup_data *data;
-	struct efi_var_bootdata *efidata;
-	u64 store_size, remaining_size, var_size;
-	efi_status_t status;
-
-	if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION)
-		return EFI_UNSUPPORTED;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	status = efi_call_phys4((void *)sys_table->runtime->query_variable_info,
-				EFI_VARIABLE_NON_VOLATILE |
-				EFI_VARIABLE_BOOTSERVICE_ACCESS |
-				EFI_VARIABLE_RUNTIME_ACCESS, &store_size,
-				&remaining_size, &var_size);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, sizeof(*efidata), &efidata);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	efidata->data.type = SETUP_EFI_VARS;
-	efidata->data.len = sizeof(struct efi_var_bootdata) -
-		sizeof(struct setup_data);
-	efidata->data.next = 0;
-	efidata->store_size = store_size;
-	efidata->remaining_size = remaining_size;
-	efidata->max_var_size = var_size;
-
-	if (data)
-		data->next = (unsigned long)efidata;
-	else
-		params->hdr.setup_data = (unsigned long)efidata;
-
-}
-
 static efi_status_t setup_efi_pci(struct boot_params *params)
 {
 	efi_pci_io_protocol *pci;
@@ -1202,8 +1157,6 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
 	setup_graphics(boot_params);
 
-	setup_efi_vars(boot_params);
-
 	setup_efi_pci(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 62fe22cd4cb..477e9d75149 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2681,56 +2681,68 @@ ENTRY(aesni_xts_crypt8)
 	addq %rcx, KEYP
 
 	movdqa IV, STATE1
-	pxor 0x00(INP), STATE1
+	movdqu 0x00(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x10(INP), STATE2
+	movdqu 0x10(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x20(INP), STATE3
+	movdqu 0x20(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x30(INP), STATE4
+	movdqu 0x30(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
 	call *%r11
 
-	pxor 0x00(OUTP), STATE1
+	movdqu 0x00(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE1
-	pxor 0x40(INP), STATE1
+	movdqu 0x40(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x40(OUTP)
 
-	pxor 0x10(OUTP), STATE2
+	movdqu 0x10(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x50(INP), STATE2
+	movdqu 0x50(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x50(OUTP)
 
-	pxor 0x20(OUTP), STATE3
+	movdqu 0x20(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x60(INP), STATE3
+	movdqu 0x60(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x60(OUTP)
 
-	pxor 0x30(OUTP), STATE4
+	movdqu 0x30(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x30(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x70(INP), STATE4
+	movdqu 0x70(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x70(OUTP)
 
 	_aesni_gf128mul_x_ble()
@@ -2738,16 +2750,20 @@ ENTRY(aesni_xts_crypt8)
 
 	call *%r11
 
-	pxor 0x40(OUTP), STATE1
+	movdqu 0x40(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x40(OUTP)
 
-	pxor 0x50(OUTP), STATE2
+	movdqu 0x50(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x50(OUTP)
 
-	pxor 0x60(OUTP), STATE3
+	movdqu 0x60(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x60(OUTP)
 
-	pxor 0x70(OUTP), STATE4
+	movdqu 0x70(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x70(OUTP)
 
 	ret
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 94c27df8a54..f247304299a 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -240,7 +240,7 @@ fold_64:
 	pand    %xmm3, %xmm1
 	PCLMULQDQ 0x00, CONSTANT, %xmm1
 	pxor    %xmm2, %xmm1
-	pextrd  $0x01, %xmm1, %eax
+	PEXTRD  0x01, %xmm1, %eax
 
 	ret
 ENDPROC(crc32_pclmul_le_16)
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 805078e0801..52ff81cce00 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -192,7 +192,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 	/* struct user */
 	DUMP_WRITE(&dump, sizeof(dump));
 	/* Now dump all of the user data.  Include malloced stuff as well */
-	DUMP_SEEK(PAGE_SIZE);
+	DUMP_SEEK(PAGE_SIZE - sizeof(dump));
 	/* now we start writing out the user space info */
 	set_fs(USER_DS);
 	/* Dump the data area */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 2fb5d5884e2..60c89f30c72 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -102,13 +102,6 @@ extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
 
-struct efi_var_bootdata {
-	struct setup_data data;
-	u64 store_size;
-	u64 remaining_size;
-	u64 max_var_size;
-};
-
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 280bf7fb6ab..3e115273ed8 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -9,12 +9,68 @@
 
 #define REG_NUM_INVALID		100
 
-#define REG_TYPE_R64		0
-#define REG_TYPE_XMM		1
+#define REG_TYPE_R32		0
+#define REG_TYPE_R64		1
+#define REG_TYPE_XMM		2
 #define REG_TYPE_INVALID	100
 
+	.macro R32_NUM opd r32
+	\opd = REG_NUM_INVALID
+	.ifc \r32,%eax
+	\opd = 0
+	.endif
+	.ifc \r32,%ecx
+	\opd = 1
+	.endif
+	.ifc \r32,%edx
+	\opd = 2
+	.endif
+	.ifc \r32,%ebx
+	\opd = 3
+	.endif
+	.ifc \r32,%esp
+	\opd = 4
+	.endif
+	.ifc \r32,%ebp
+	\opd = 5
+	.endif
+	.ifc \r32,%esi
+	\opd = 6
+	.endif
+	.ifc \r32,%edi
+	\opd = 7
+	.endif
+#ifdef CONFIG_X86_64
+	.ifc \r32,%r8d
+	\opd = 8
+	.endif
+	.ifc \r32,%r9d
+	\opd = 9
+	.endif
+	.ifc \r32,%r10d
+	\opd = 10
+	.endif
+	.ifc \r32,%r11d
+	\opd = 11
+	.endif
+	.ifc \r32,%r12d
+	\opd = 12
+	.endif
+	.ifc \r32,%r13d
+	\opd = 13
+	.endif
+	.ifc \r32,%r14d
+	\opd = 14
+	.endif
+	.ifc \r32,%r15d
+	\opd = 15
+	.endif
+#endif
+	.endm
+
 	.macro R64_NUM opd r64
 	\opd = REG_NUM_INVALID
+#ifdef CONFIG_X86_64
 	.ifc \r64,%rax
 	\opd = 0
 	.endif
@@ -63,6 +119,7 @@
 	.ifc \r64,%r15
 	\opd = 15
 	.endif
+#endif
 	.endm
 
 	.macro XMM_NUM opd xmm
@@ -118,10 +175,13 @@
 	.endm
 
 	.macro REG_TYPE type reg
+	R32_NUM reg_type_r32 \reg
 	R64_NUM reg_type_r64 \reg
 	XMM_NUM reg_type_xmm \reg
 	.if reg_type_r64 <> REG_NUM_INVALID
 	\type = REG_TYPE_R64
+	.elseif reg_type_r32 <> REG_NUM_INVALID
+	\type = REG_TYPE_R32
 	.elseif reg_type_xmm <> REG_NUM_INVALID
 	\type = REG_TYPE_XMM
 	.else
@@ -162,6 +222,16 @@
 	.byte \imm8
 	.endm
 
+	.macro PEXTRD imm8 xmm gpr
+	R32_NUM extrd_opd1 \gpr
+	XMM_NUM extrd_opd2 \xmm
+	PFX_OPD_SIZE
+	PFX_REX extrd_opd1 extrd_opd2
+	.byte 0x0f, 0x3a, 0x16
+	MODRM 0xc0 extrd_opd1 extrd_opd2
+	.byte \imm8
+	.endm
+
 	.macro AESKEYGENASSIST rcon xmm1 xmm2
 	XMM_NUM aeskeygen_opd1 \xmm1
 	XMM_NUM aeskeygen_opd2 \xmm2
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index ba870bb6dd8..57873beb329 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -41,4 +41,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
 
 extern void init_ISA_irqs(void);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+#endif
+
 #endif /* _ASM_X86_IRQ_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 6825e2efd1b..6bc3985ee47 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -60,11 +60,11 @@ static inline void __exit exit_amd_microcode(void) {}
 #ifdef CONFIG_MICROCODE_EARLY
 #define MAX_UCODE_COUNT 128
 extern void __init load_ucode_bsp(void);
-extern __init void load_ucode_ap(void);
+extern void __cpuinit load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 #else
 static inline void __init load_ucode_bsp(void) {}
-static inline __init void load_ucode_ap(void) {}
+static inline void __cpuinit load_ucode_ap(void) {}
 static inline int __init save_microcode_in_initrd(void)
 {
 	return 0;
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c0fa356e90d..86f9301903c 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -18,9 +18,7 @@ extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
-void arch_trigger_all_cpu_backtrace(void);
-#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
-#endif
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 #define NMI_FLAG_FIRST	1
 
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 08744242b8d..c15ddaf9071 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,7 +6,6 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
-#define SETUP_EFI_VARS			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 31cb9ae992b..a698d7165c9 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
  *
  */
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 #include <linux/cpumask.h>
 #include <linux/kdebug.h>
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 35ffda5d072..5f90b85ff22 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits)
 	if (mtrr_tom2)
 		x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base;
 
-	nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size);
 	/*
 	 * [0, 1M) should always be covered by var mtrr with WB
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
-	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
+	nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0,
 					1ULL<<(20 - PAGE_SHIFT));
-	/* Sort the ranges: */
-	sort_range(range, nr_range);
+	/* add from var mtrr at last */
+	nr_range = x86_get_mtrr_mem_range(range, nr_range,
+					  x_remove_base, x_remove_size);
 
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM covered: %ldM\n",
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f60d41ff9a9..a9e22073bd5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -165,13 +165,13 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
-	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
 static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 08f7e803909..321d65ebaff 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -115,8 +115,10 @@ startup_64:
 	movq	%rdi, %rax
 	shrq	$PUD_SHIFT, %rax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, (4096+0)(%rbx,%rax,8)
-	movq	%rdx, (4096+8)(%rbx,%rax,8)
+	movq	%rdx, 4096(%rbx,%rax,8)
+	incl	%eax
+	andl	$(PTRS_PER_PUD-1), %eax
+	movq	%rdx, 4096(%rbx,%rax,8)
 
 	addq	$8192, %rbx
 	movq	%rdi, %rax
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 245a71db401..cb339097b9e 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -22,23 +22,19 @@
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *
- * For now, with eagerfpu we will return interrupted kernel FPU
- * state as not-idle. TBD: Ideally we can change the return value
- * to something like __thread_has_fpu(current). But we need to
- * be careful of doing __thread_clear_has_fpu() before saving
- * the FPU etc for supporting nested uses etc. For now, take
- * the simple route!
- *
  * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
  * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
  * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return 1 unless we've already
+ * been eager and saved the state in kernel_fpu_begin().
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
 	if (use_eager_fpu())
-		return 0;
+		return __thread_has_fpu(current);
 
 	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
@@ -78,8 +74,8 @@ void __kernel_fpu_begin(void)
 	struct task_struct *me = current;
 
 	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
+		__save_init_fpu(me);
 		/* We do 'stts()' in __kernel_fpu_end() */
 	} else if (!use_eager_fpu()) {
 		this_cpu_write(fpu_owner_task, NULL);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 9895a9a4138..211bce44552 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -365,10 +365,14 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 	return insn.length;
 }
 
-static void __kprobes arch_copy_kprobe(struct kprobe *p)
+static int __kprobes arch_copy_kprobe(struct kprobe *p)
 {
+	int ret;
+
 	/* Copy an instruction with recovering if other optprobe modifies it.*/
-	__copy_instruction(p->ainsn.insn, p->addr);
+	ret = __copy_instruction(p->ainsn.insn, p->addr);
+	if (!ret)
+		return -EINVAL;
 
 	/*
 	 * __copy_instruction can modify the displacement of the instruction,
@@ -384,6 +388,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = p->ainsn.insn[0];
+
+	return 0;
 }
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
@@ -397,8 +403,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	p->ainsn.insn = get_insn_slot();
 	if (!p->ainsn.insn)
 		return -ENOMEM;
-	arch_copy_kprobe(p);
-	return 0;
+
+	return arch_copy_kprobe(p);
 }
 
 void __kprobes arch_arm_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d2c381280e3..3dd37ebd591 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -242,6 +242,7 @@ void __init kvmclock_init(void)
 	if (!mem)
 		return;
 	hv_clock = __va(mem);
+	memset(hv_clock, 0, size);
 
 	if (kvm_register_clock("boot clock")) {
 		hv_clock = NULL;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 4e7a37ff03a..81a5f5e8f14 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -277,18 +277,6 @@ void exit_idle(void)
 }
 #endif
 
-void arch_cpu_idle_prepare(void)
-{
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-}
-
 void arch_cpu_idle_enter(void)
 {
 	local_touch_nmi();
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 7a6f3b3be3c..f2bb9c96720 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -160,7 +160,7 @@ identity_mapped:
 	xorq    %rbp, %rbp
 	xorq	%r8,  %r8
 	xorq	%r9,  %r9
-	xorq	%r10, %r9
+	xorq	%r10, %r10
 	xorq	%r11, %r11
 	xorq	%r12, %r12
 	xorq	%r13, %r13
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8db0010ed15..5953dcea752 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1240,9 +1240,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
 	if (ctxt->modrm_mod == 3) {
+		int highbyte_regs = ctxt->rex_prefix == 0;
+
 		op->type = OP_REG;
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
-		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp);
+		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+					       highbyte_regs && (ctxt->d & ByteOp));
 		if (ctxt->d & Sse) {
 			op->type = OP_XMM;
 			op->bytes = 16;
@@ -3997,7 +4000,8 @@ static const struct opcode twobyte_table[256] = {
 	DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
 	N, D(ImplicitOps | ModRM), N, N,
 	/* 0x10 - 0x1F */
-	N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N,
+	N, N, N, N, N, N, N, N,
+	D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
 	/* 0x20 - 0x2F */
 	DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
 	DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read),
@@ -4836,6 +4840,7 @@ twobyte_insn:
 	case 0x08:		/* invd */
 	case 0x0d:		/* GrpP (prefetch) */
 	case 0x18:		/* Grp16 (prefetch/nop) */
+	case 0x1f:		/* nop */
 		break;
 	case 0x20: /* mov cr, reg */
 		ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e1adbb4aca7..0eee2c8b64d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1861,11 +1861,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	unsigned int sipi_vector;
+	unsigned long pe;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
 		return;
 
-	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
+	pe = xchg(&apic->pending_events, 0);
+
+	if (test_bit(KVM_APIC_INIT, &pe)) {
 		kvm_lapic_reset(vcpu);
 		kvm_vcpu_reset(vcpu);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
@@ -1873,7 +1876,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 		else
 			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 	}
-	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) &&
+	if (test_bit(KVM_APIC_SIPI, &pe) &&
 	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
 		/* evaluate pending_events before reading the vector */
 		smp_rmb();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 094b5d96ab1..e8ba99c3418 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -582,8 +582,6 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	if (index != XCR_XFEATURE_ENABLED_MASK)
 		return 1;
 	xcr0 = xcr;
-	if (kvm_x86_ops->get_cpl(vcpu) != 0)
-		return 1;
 	if (!(xcr0 & XSTATE_FP))
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
@@ -597,7 +595,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
-	if (__kvm_set_xcr(vcpu, index, xcr)) {
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 ||
+	    __kvm_set_xcr(vcpu, index, xcr)) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index eaac1743def..1f34e921977 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -277,6 +277,9 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 	end_pfn = limit_pfn;
 	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 
+	if (!after_bootmem)
+		adjust_range_page_size_mask(mr, nr_range);
+
 	/* try to merge same page size and continuous */
 	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
 		unsigned long old_start;
@@ -291,9 +294,6 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 		nr_range--;
 	}
 
-	if (!after_bootmem)
-		adjust_range_page_size_mask(mr, nr_range);
-
 	for (i = 0; i < nr_range; i++)
 		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
 				mr[i].start, mr[i].end - 1,
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 305c68b8d53..981c2dbd72c 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -628,7 +628,9 @@ int pcibios_add_device(struct pci_dev *dev)
 
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
-		data = phys_to_virt(pa_data);
+		data = ioremap(pa_data, sizeof(*rom));
+		if (!data)
+			return -ENOMEM;
 
 		if (data->type == SETUP_PCI) {
 			rom = (struct pci_setup_rom *)data;
@@ -645,6 +647,7 @@ int pcibios_add_device(struct pci_dev *dev)
 			}
 		}
 		pa_data = data->next;
+		iounmap(data);
 	}
 	return 0;
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 55856b2310d..d2fbcedcf6e 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -42,7 +42,6 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 #include <linux/bcd.h>
-#include <linux/ucs2_string.h>
 
 #include <asm/setup.h>
 #include <asm/efi.h>
@@ -54,12 +53,12 @@
 
 #define EFI_DEBUG	1
 
-/*
- * There's some additional metadata associated with each
- * variable. Intel's reference implementation is 60 bytes - bump that
- * to account for potential alignment constraints
- */
-#define VAR_METADATA_SIZE 64
+#define EFI_MIN_RESERVE 5120
+
+#define EFI_DUMMY_GUID \
+	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
 
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
@@ -79,13 +78,6 @@ struct efi_memory_map memmap;
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
-static u64 efi_var_store_size;
-static u64 efi_var_remaining_size;
-static u64 efi_var_max_var_size;
-static u64 boot_used_size;
-static u64 boot_var_size;
-static u64 active_size;
-
 unsigned long x86_efi_facility;
 
 /*
@@ -188,53 +180,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 					       efi_char16_t *name,
 					       efi_guid_t *vendor)
 {
-	efi_status_t status;
-	static bool finished = false;
-	static u64 var_size;
-
-	status = efi_call_virt3(get_next_variable,
-				name_size, name, vendor);
-
-	if (status == EFI_NOT_FOUND) {
-		finished = true;
-		if (var_size < boot_used_size) {
-			boot_var_size = boot_used_size - var_size;
-			active_size += boot_var_size;
-		} else {
-			printk(KERN_WARNING FW_BUG  "efi: Inconsistent initial sizes\n");
-		}
-	}
-
-	if (boot_used_size && !finished) {
-		unsigned long size;
-		u32 attr;
-		efi_status_t s;
-		void *tmp;
-
-		s = virt_efi_get_variable(name, vendor, &attr, &size, NULL);
-
-		if (s != EFI_BUFFER_TOO_SMALL || !size)
-			return status;
-
-		tmp = kmalloc(size, GFP_ATOMIC);
-
-		if (!tmp)
-			return status;
-
-		s = virt_efi_get_variable(name, vendor, &attr, &size, tmp);
-
-		if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) {
-			var_size += size;
-			var_size += ucs2_strsize(name, 1024);
-			active_size += size;
-			active_size += VAR_METADATA_SIZE;
-			active_size += ucs2_strsize(name, 1024);
-		}
-
-		kfree(tmp);
-	}
-
-	return status;
+	return efi_call_virt3(get_next_variable,
+			      name_size, name, vendor);
 }
 
 static efi_status_t virt_efi_set_variable(efi_char16_t *name,
@@ -243,34 +190,9 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 					  unsigned long data_size,
 					  void *data)
 {
-	efi_status_t status;
-	u32 orig_attr = 0;
-	unsigned long orig_size = 0;
-
-	status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size,
-				       NULL);
-
-	if (status != EFI_BUFFER_TOO_SMALL)
-		orig_size = 0;
-
-	status = efi_call_virt5(set_variable,
-				name, vendor, attr,
-				data_size, data);
-
-	if (status == EFI_SUCCESS) {
-		if (orig_size) {
-			active_size -= orig_size;
-			active_size -= ucs2_strsize(name, 1024);
-			active_size -= VAR_METADATA_SIZE;
-		}
-		if (data_size) {
-			active_size += data_size;
-			active_size += ucs2_strsize(name, 1024);
-			active_size += VAR_METADATA_SIZE;
-		}
-	}
-
-	return status;
+	return efi_call_virt5(set_variable,
+			      name, vendor, attr,
+			      data_size, data);
 }
 
 static efi_status_t virt_efi_query_variable_info(u32 attr,
@@ -786,9 +708,6 @@ void __init efi_init(void)
 	char vendor[100] = "unknown";
 	int i = 0;
 	void *tmp;
-	struct setup_data *data;
-	struct efi_var_bootdata *efi_var_data;
-	u64 pa_data;
 
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
@@ -806,22 +725,6 @@ void __init efi_init(void)
 	if (efi_systab_init(efi_phys.systab))
 		return;
 
-	pa_data = boot_params.hdr.setup_data;
-	while (pa_data) {
-		data = early_ioremap(pa_data, sizeof(*efi_var_data));
-		if (data->type == SETUP_EFI_VARS) {
-			efi_var_data = (struct efi_var_bootdata *)data;
-
-			efi_var_store_size = efi_var_data->store_size;
-			efi_var_remaining_size = efi_var_data->remaining_size;
-			efi_var_max_var_size = efi_var_data->max_var_size;
-		}
-		pa_data = data->next;
-		early_iounmap(data, sizeof(*efi_var_data));
-	}
-
-	boot_used_size = efi_var_store_size - efi_var_remaining_size;
-
 	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
@@ -1085,6 +988,13 @@ void __init efi_enter_virtual_mode(void)
 		runtime_code_page_mkexec();
 
 	kfree(new_memmap);
+
+	/* clean DUMMY object */
+	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+			 EFI_VARIABLE_NON_VOLATILE |
+			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			 EFI_VARIABLE_RUNTIME_ACCESS,
+			 0, NULL);
 }
 
 /*
@@ -1136,33 +1046,70 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 	efi_status_t status;
 	u64 storage_size, remaining_size, max_size;
 
+	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+		return 0;
+
 	status = efi.query_variable_info(attributes, &storage_size,
 					 &remaining_size, &max_size);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	if (!max_size && remaining_size > size)
-		printk_once(KERN_ERR FW_BUG "Broken EFI implementation"
-			    " is returning MaxVariableSize=0\n");
 	/*
 	 * Some firmware implementations refuse to boot if there's insufficient
 	 * space in the variable store. We account for that by refusing the
 	 * write if permitting it would reduce the available space to under
-	 * 50%. However, some firmware won't reclaim variable space until
-	 * after the used (not merely the actively used) space drops below
-	 * a threshold. We can approximate that case with the value calculated
-	 * above. If both the firmware and our calculations indicate that the
-	 * available space would drop below 50%, refuse the write.
+	 * 5KB. This figure was provided by Samsung, so should be safe.
 	 */
+	if ((remaining_size - size < EFI_MIN_RESERVE) &&
+		!efi_no_storage_paranoia) {
+
+		/*
+		 * Triggering garbage collection may require that the firmware
+		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
+		 * that by attempting to use more space than is available.
+		 */
+		unsigned long dummy_size = remaining_size + 1024;
+		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
+
+		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+					  EFI_VARIABLE_NON_VOLATILE |
+					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					  EFI_VARIABLE_RUNTIME_ACCESS,
+					  dummy_size, dummy);
+
+		if (status == EFI_SUCCESS) {
+			/*
+			 * This should have failed, so if it didn't make sure
+			 * that we delete it...
+			 */
+			efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+					 EFI_VARIABLE_NON_VOLATILE |
+					 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					 EFI_VARIABLE_RUNTIME_ACCESS,
+					 0, dummy);
+		}
+
+		kfree(dummy);
 
-	if (!storage_size || size > remaining_size ||
-	    (max_size && size > max_size))
-		return EFI_OUT_OF_RESOURCES;
+		/*
+		 * The runtime code may now have triggered a garbage collection
+		 * run, so check the variable info again
+		 */
+		status = efi.query_variable_info(attributes, &storage_size,
+						 &remaining_size, &max_size);
 
-	if (!efi_no_storage_paranoia &&
-	    ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) &&
-	     (remaining_size - size < storage_size / 2)))
-		return EFI_OUT_OF_RESOURCES;
+		if (status != EFI_SUCCESS)
+			return status;
+
+		/*
+		 * There still isn't enough room, so return an error
+		 */
+		if (remaining_size - size < EFI_MIN_RESERVE)
+			return EFI_OUT_OF_RESOURCES;
+	}
 
 	return EFI_SUCCESS;
 }
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 590be109089..f7bab68a4b8 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -42,9 +42,6 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"^(xen_irq_disable_direct_reloc$|"
 	"xen_save_fl_direct_reloc$|"
 	"VDSO|"
-#if ELF_BITS == 64
-	"__vvar_page|"
-#endif
 	"__crc_)",
 
 /*
@@ -72,6 +69,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"__per_cpu_load|"
 	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
+	"__vvar_page|"
 #endif
 	"_end)$"
 };
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8ff37995d54..d99cae8147d 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/irq_work.h>
+#include <linux/tick.h>
 
 #include <asm/paravirt.h>
 #include <asm/desc.h>
@@ -447,6 +448,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
+	/*
+	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
+	 * clears certain data that the cpu_idle loop (which called us
+	 * and that we return from) expects. The only way to get that
+	 * data back is to call:
+	 */
+	tick_nohz_idle_enter();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
@@ -576,24 +584,22 @@ void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 {
 	unsigned cpu;
 	unsigned int this_cpu = smp_processor_id();
+	int xen_vector = xen_map_vector(vector);
 
-	if (!(num_online_cpus() > 1))
+	if (!(num_online_cpus() > 1) || (xen_vector < 0))
 		return;
 
 	for_each_cpu_and(cpu, mask, cpu_online_mask) {
 		if (this_cpu == cpu)
 			continue;
 
-		xen_smp_send_call_function_single_ipi(cpu);
+		xen_send_IPI_one(cpu, xen_vector);
 	}
 }
 
 void xen_send_IPI_allbutself(int vector)
 {
-	int xen_vector = xen_map_vector(vector);
-
-	if (xen_vector >= 0)
-		xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector);
+	xen_send_IPI_mask_allbutself(cpu_online_mask, vector);
 }
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index 8981a76d081..c7c2d89efd7 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -5,7 +5,6 @@ extern void xen_send_IPI_mask(const struct cpumask *mask,
 extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 				int vector);
 extern void xen_send_IPI_allbutself(int vector);
-extern void physflat_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);
author	Ingo Molnar <mingo@kernel.org>	2013-07-01 11:16:54 +0200
committer	Ingo Molnar <mingo@kernel.org>	2013-07-01 11:18:53 +0200
commit	2fd1b487884310d0aa0c0640179dc7490ad86313 (patch)
tree	1083dce15bd7dc0858c3883b8a361242046c5e09 /arch
parent	333bb864f192015a53b5060b829089decd0220ef (diff)
parent	8bb495e3f02401ee6f76d1b1d77f3ac9f079e376 (diff)