Merge branch 'linus' into queue

Merge reason: development work has dependency on kvm patches merged
upstream.

Conflicts:
	Documentation/feature-removal-schedule.txt

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

90 files changed, 763 insertions, 919 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index f62251e82ffa..3bb7ffeae3bc 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <asm/barrier.h>
+#include <asm/cmpxchg.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -168,73 +169,6 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 	return result;
 }
 
-/*
- * Atomic exchange routines.
- */
-
-#define __ASM__MB
-#define ____xchg(type, args...)		__xchg ## type ## _local(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
-#include <asm/xchg.h>
-
-#define xchg_local(ptr,x)						\
-  ({									\
-     __typeof__(*(ptr)) _x_ = (x);					\
-     (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
-				       sizeof(*(ptr)));			\
-  })
-
-#define cmpxchg_local(ptr, o, n)					\
-  ({									\
-     __typeof__(*(ptr)) _o_ = (o);					\
-     __typeof__(*(ptr)) _n_ = (n);					\
-     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
-					  (unsigned long)_n_,		\
-					  sizeof(*(ptr)));		\
-  })
-
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-
-#ifdef CONFIG_SMP
-#undef __ASM__MB
-#define __ASM__MB	"\tmb\n"
-#endif
-#undef ____xchg
-#undef ____cmpxchg
-#define ____xchg(type, args...)		__xchg ##type(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
-#include <asm/xchg.h>
-
-#define xchg(ptr,x)							\
-  ({									\
-     __typeof__(*(ptr)) _x_ = (x);					\
-     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
-				 sizeof(*(ptr)));			\
-  })
-
-#define cmpxchg(ptr, o, n)						\
-  ({									\
-     __typeof__(*(ptr)) _o_ = (o);					\
-     __typeof__(*(ptr)) _n_ = (n);					\
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		\
-				    (unsigned long)_n_,	sizeof(*(ptr)));\
-  })
-
-#define cmpxchg64(ptr, o, n)						\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
-  })
-
-#undef __ASM__MB
-#undef ____cmpxchg
-
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..429e8cd0d78e
--- /dev/null
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -0,0 +1,71 @@
+#ifndef _ALPHA_CMPXCHG_H
+#define _ALPHA_CMPXCHG_H
+
+/*
+ * Atomic exchange routines.
+ */
+
+#define __ASM__MB
+#define ____xchg(type, args...)		__xchg ## type ## _local(args)
+#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
+#include <asm/xchg.h>
+
+#define xchg_local(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
+				       sizeof(*(ptr)));			\
+})
+
+#define cmpxchg_local(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
+					  (unsigned long)_n_,		\
+					  sizeof(*(ptr)));		\
+})
+
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+})
+
+#ifdef CONFIG_SMP
+#undef __ASM__MB
+#define __ASM__MB	"\tmb\n"
+#endif
+#undef ____xchg
+#undef ____cmpxchg
+#define ____xchg(type, args...)		__xchg ##type(args)
+#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
+#include <asm/xchg.h>
+
+#define xchg(ptr, x)							\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
+				 sizeof(*(ptr)));			\
+})
+
+#define cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	\
+				    (unsigned long)_n_,	sizeof(*(ptr)));\
+})
+
+#define cmpxchg64(ptr, o, n)						\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+})
+
+#undef __ASM__MB
+#undef ____cmpxchg
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+#endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h
index 1d1b436fbff2..0ca9724597c1 100644
--- a/arch/alpha/include/asm/xchg.h
+++ b/arch/alpha/include/asm/xchg.h
@@ -1,10 +1,10 @@
-#ifndef _ALPHA_ATOMIC_H
+#ifndef _ALPHA_CMPXCHG_H
 #error Do not include xchg.h directly!
 #else
 /*
  * xchg/xchg_local and cmpxchg/cmpxchg_local share the same code
  * except that local version do not have the expensive memory barrier.
- * So this file is included twice from asm/system.h.
+ * So this file is included twice from asm/cmpxchg.h.
  */
 
 /*
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index 6ce11c481178..797f04bedb47 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -77,6 +77,8 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 		} else if (atag->hdr.tag == ATAG_MEM) {
 			if (memcount >= sizeof(mem_reg_property)/4)
 				continue;
+			if (!atag->u.mem.size)
+				continue;
 			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
 			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
 		} else if (atag->hdr.tag == ATAG_INITRD2) {
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 5f6045f1766c..dc7e8ce8e6be 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -273,7 +273,7 @@ restart:	adr	r0, LC0
 		add	r0, r0, #0x100
 		mov	r1, r6
 		sub	r2, sp, r6
-		blne	atags_to_fdt
+		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
 		sub	sp, sp, #0x10000
diff --git a/arch/arm/boot/dts/at91sam9g20.dtsi b/arch/arm/boot/dts/at91sam9g20.dtsi
index 799ad1889b51..773ef484037a 100644
--- a/arch/arm/boot/dts/at91sam9g20.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20.dtsi
@@ -55,7 +55,6 @@
 				#interrupt-cells = <2>;
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
-				interrupt-parent;
 				reg = <0xfffff000 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 9e6eb6ecea0e..c8042147eaa2 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -56,7 +56,6 @@
 				#interrupt-cells = <2>;
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
-				interrupt-parent;
 				reg = <0xfffff000 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 70ab3a4e026f..dd4ed748469a 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -54,7 +54,6 @@
 				#interrupt-cells = <2>;
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
-				interrupt-parent;
 				reg = <0xfffff000 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/db8500.dtsi b/arch/arm/boot/dts/db8500.dtsi
index d73dce645667..14bc30705099 100644
--- a/arch/arm/boot/dts/db8500.dtsi
+++ b/arch/arm/boot/dts/db8500.dtsi
@@ -24,7 +24,6 @@
 			#interrupt-cells = <3>;
 			#address-cells = <1>;
 			interrupt-controller;
-			interrupt-parent;
 			reg = <0xa0411000 0x1000>,
 			      <0xa0410100 0x100>;
 		};
diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts
index 37c0ff9c8b90..83e72294aefb 100644
--- a/arch/arm/boot/dts/highbank.dts
+++ b/arch/arm/boot/dts/highbank.dts
@@ -89,7 +89,6 @@
 			#size-cells = <0>;
 			#address-cells = <1>;
 			interrupt-controller;
-			interrupt-parent;
 			reg = <0xfff11000 0x1000>,
 			      <0xfff10100 0x100>;
 		};
diff --git a/arch/arm/common/vic.c b/arch/arm/common/vic.c
index 7a66311f3066..7e288f96cedf 100644
--- a/arch/arm/common/vic.c
+++ b/arch/arm/common/vic.c
@@ -427,19 +427,18 @@ int __init vic_of_init(struct device_node *node, struct device_node *parent)
 
 /*
  * Handle each interrupt in a single VIC.  Returns non-zero if we've
- * handled at least one interrupt.  This does a single read of the
- * status register and handles all interrupts in order from LSB first.
+ * handled at least one interrupt.  This reads the status register
+ * before handling each interrupt, which is necessary given that
+ * handle_IRQ may briefly re-enable interrupts for soft IRQ handling.
  */
 static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs)
 {
 	u32 stat, irq;
 	int handled = 0;
 
-	stat = readl_relaxed(vic->base + VIC_IRQ_STATUS);
-	while (stat) {
+	while ((stat = readl_relaxed(vic->base + VIC_IRQ_STATUS))) {
 		irq = ffs(stat) - 1;
 		handle_IRQ(irq_find_mapping(vic->domain, irq), regs);
-		stat &= ~(1 << irq);
 		handled = 1;
 	}
 
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index 5c5ca2ea62b0..bfc198c75913 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -14,7 +14,7 @@
 #define JUMP_LABEL_NOP	"nop"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\n\t"
 		 JUMP_LABEL_NOP "\n\t"
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b91411371ae1..ebfac782593f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -523,7 +523,21 @@ int __init arm_add_memory(phys_addr_t start, unsigned long size)
 	 */
 	size -= start & ~PAGE_MASK;
 	bank->start = PAGE_ALIGN(start);
-	bank->size  = size & PAGE_MASK;
+
+#ifndef CONFIG_LPAE
+	if (bank->start + size < bank->start) {
+		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
+			"32-bit physical address space\n", (long long)start);
+		/*
+		 * To ensure bank->start + bank->size is representable in
+		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
+		 * This means we lose a page after masking.
+		 */
+		size = ULONG_MAX - bank->start;
+	}
+#endif
+
+	bank->size = size & PAGE_MASK;
 
 	/*
 	 * Check whether this memory region has non-zero size or
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index fef42b21cecb..5b150afb995b 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -118,10 +118,14 @@ static int twd_cpufreq_transition(struct notifier_block *nb,
 	 * The twd clock events must be reprogrammed to account for the new
 	 * frequency.  The timer is local to a cpu, so cross-call to the
 	 * changing cpu.
+	 *
+	 * Only wait for it to finish, if the cpu is active to avoid
+	 * deadlock when cpu1 is spinning on while(!cpu_active(cpu1)) during
+	 * booting of that cpu.
 	 */
 	if (state == CPUFREQ_POSTCHANGE || state == CPUFREQ_RESUMECHANGE)
 		smp_call_function_single(freqs->cpu, twd_update_frequency,
-			NULL, 1);
+					 NULL, cpu_active(freqs->cpu));
 
 	return NOTIFY_OK;
 }
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 0491ceef1cda..e81c35f936b5 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -368,6 +368,7 @@ comment "Flattened Device Tree based board for EXYNOS SoCs"
 
 config MACH_EXYNOS4_DT
 	bool "Samsung Exynos4 Machine using device tree"
+	depends on ARCH_EXYNOS4
 	select CPU_EXYNOS4210
 	select USE_OF
 	select ARM_AMBA
@@ -380,6 +381,7 @@ config MACH_EXYNOS4_DT
 
 config MACH_EXYNOS5_DT
 	bool "SAMSUNG EXYNOS5 Machine using device tree"
+	depends on ARCH_EXYNOS5
 	select SOC_EXYNOS5250
 	select USE_OF
 	select ARM_AMBA
diff --git a/arch/arm/mach-exynos/include/mach/irqs.h b/arch/arm/mach-exynos/include/mach/irqs.h
index 9bee8535d9e0..591e78521a9f 100644
--- a/arch/arm/mach-exynos/include/mach/irqs.h
+++ b/arch/arm/mach-exynos/include/mach/irqs.h
@@ -212,6 +212,8 @@
 #define IRQ_MFC				EXYNOS4_IRQ_MFC
 #define IRQ_SDO				EXYNOS4_IRQ_SDO
 
+#define IRQ_I2S0			EXYNOS4_IRQ_I2S0
+
 #define IRQ_ADC				EXYNOS4_IRQ_ADC0
 #define IRQ_TC				EXYNOS4_IRQ_PEN0
 
diff --git a/arch/arm/mach-exynos/include/mach/map.h b/arch/arm/mach-exynos/include/mach/map.h
index 024d38ff1718..6e6d11ff352a 100644
--- a/arch/arm/mach-exynos/include/mach/map.h
+++ b/arch/arm/mach-exynos/include/mach/map.h
@@ -89,6 +89,10 @@
 #define EXYNOS4_PA_MDMA1		0x12840000
 #define EXYNOS4_PA_PDMA0		0x12680000
 #define EXYNOS4_PA_PDMA1		0x12690000
+#define EXYNOS5_PA_MDMA0		0x10800000
+#define EXYNOS5_PA_MDMA1		0x11C10000
+#define EXYNOS5_PA_PDMA0		0x121A0000
+#define EXYNOS5_PA_PDMA1		0x121B0000
 
 #define EXYNOS4_PA_SYSMMU_MDMA		0x10A40000
 #define EXYNOS4_PA_SYSMMU_SSS		0x10A50000
diff --git a/arch/arm/mach-exynos/include/mach/regs-clock.h b/arch/arm/mach-exynos/include/mach/regs-clock.h
index e141c1fd68d8..d9578a58ae7f 100644
--- a/arch/arm/mach-exynos/include/mach/regs-clock.h
+++ b/arch/arm/mach-exynos/include/mach/regs-clock.h
@@ -255,9 +255,15 @@
 
 /* For EXYNOS5250 */
 
+#define EXYNOS5_APLL_LOCK			EXYNOS_CLKREG(0x00000)
 #define EXYNOS5_APLL_CON0			EXYNOS_CLKREG(0x00100)
 #define EXYNOS5_CLKSRC_CPU			EXYNOS_CLKREG(0x00200)
+#define EXYNOS5_CLKMUX_STATCPU			EXYNOS_CLKREG(0x00400)
 #define EXYNOS5_CLKDIV_CPU0			EXYNOS_CLKREG(0x00500)
+#define EXYNOS5_CLKDIV_CPU1			EXYNOS_CLKREG(0x00504)
+#define EXYNOS5_CLKDIV_STATCPU0			EXYNOS_CLKREG(0x00600)
+#define EXYNOS5_CLKDIV_STATCPU1			EXYNOS_CLKREG(0x00604)
+
 #define EXYNOS5_MPLL_CON0			EXYNOS_CLKREG(0x04100)
 #define EXYNOS5_CLKSRC_CORE1			EXYNOS_CLKREG(0x04204)
 
diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c
index 0d26f50081ad..4711c8920e37 100644
--- a/arch/arm/mach-exynos/mach-exynos5-dt.c
+++ b/arch/arm/mach-exynos/mach-exynos5-dt.c
@@ -45,7 +45,7 @@ static const struct of_dev_auxdata exynos5250_auxdata_lookup[] __initconst = {
 				"exynos4210-uart.3", NULL),
 	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA0, "dma-pl330.0", NULL),
 	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA1, "dma-pl330.1", NULL),
-	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA1, "dma-pl330.2", NULL),
+	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_MDMA1, "dma-pl330.2", NULL),
 	{},
 };
 
diff --git a/arch/arm/mach-exynos/mach-nuri.c b/arch/arm/mach-exynos/mach-nuri.c
index b3982c867c9c..b4f1f902ce6d 100644
--- a/arch/arm/mach-exynos/mach-nuri.c
+++ b/arch/arm/mach-exynos/mach-nuri.c
@@ -307,49 +307,7 @@ static struct i2c_board_info i2c1_devs[] __initdata = {
 };
 
 /* TSP */
-static u8 mxt_init_vals[] = {
-	/* MXT_GEN_COMMAND(6) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_GEN_POWER(7) */
-	0x20, 0xff, 0x32,
-	/* MXT_GEN_ACQUIRE(8) */
-	0x0a, 0x00, 0x05, 0x00, 0x00, 0x00, 0x09, 0x23,
-	/* MXT_TOUCH_MULTI(9) */
-	0x00, 0x00, 0x00, 0x13, 0x0b, 0x00, 0x00, 0x00, 0x02, 0x00,
-	0x00, 0x01, 0x01, 0x0e, 0x0a, 0x0a, 0x0a, 0x0a, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00,
-	/* MXT_TOUCH_KEYARRAY(15) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00,
-	0x00,
-	/* MXT_SPT_GPIOPWM(19) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_PROCI_GRIPFACE(20) */
-	0x07, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x28, 0x04,
-	0x0f, 0x0a,
-	/* MXT_PROCG_NOISE(22) */
-	0x05, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x23, 0x00,
-	0x00, 0x05, 0x0f, 0x19, 0x23, 0x2d, 0x03,
-	/* MXT_TOUCH_PROXIMITY(23) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_PROCI_ONETOUCH(24) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_SPT_SELFTEST(25) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00,
-	/* MXT_PROCI_TWOTOUCH(27) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_SPT_CTECONFIG(28) */
-	0x00, 0x00, 0x02, 0x08, 0x10, 0x00,
-};
-
 static struct mxt_platform_data mxt_platform_data = {
-	.config			= mxt_init_vals,
-	.config_length		= ARRAY_SIZE(mxt_init_vals),
-
 	.x_line			= 18,
 	.y_line			= 11,
 	.x_size			= 1024,
@@ -571,7 +529,7 @@ static struct regulator_init_data __initdata max8997_ldo7_data = {
 
 static struct regulator_init_data __initdata max8997_ldo8_data = {
 	.constraints	= {
-		.name		= "VUSB/VDAC_3.3V_C210",
+		.name		= "VUSB+VDAC_3.3V_C210",
 		.min_uV		= 3300000,
 		.max_uV		= 3300000,
 		.valid_ops_mask	= REGULATOR_CHANGE_STATUS,
@@ -1347,6 +1305,7 @@ static struct platform_device *nuri_devices[] __initdata = {
 
 static void __init nuri_map_io(void)
 {
+	clk_xusbxti.rate = 24000000;
 	exynos_init_io(NULL, 0);
 	s3c24xx_init_clocks(24000000);
 	s3c24xx_init_uarts(nuri_uartcfgs, ARRAY_SIZE(nuri_uartcfgs));
@@ -1379,7 +1338,6 @@ static void __init nuri_machine_init(void)
 	nuri_camera_init();
 
 	nuri_ehci_init();
-	clk_xusbxti.rate = 24000000;
 
 	/* Last */
 	platform_add_devices(nuri_devices, ARRAY_SIZE(nuri_devices));
diff --git a/arch/arm/mach-exynos/mach-universal_c210.c b/arch/arm/mach-exynos/mach-universal_c210.c
index 6bb9dbdd73fd..7ebf79c2ab34 100644
--- a/arch/arm/mach-exynos/mach-universal_c210.c
+++ b/arch/arm/mach-exynos/mach-universal_c210.c
@@ -29,6 +29,7 @@
 #include <asm/mach-types.h>
 
 #include <plat/regs-serial.h>
+#include <plat/clock.h>
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/iic.h>
@@ -1057,6 +1058,7 @@ static struct platform_device *universal_devices[] __initdata = {
 
 static void __init universal_map_io(void)
 {
+	clk_xusbxti.rate = 24000000;
 	exynos_init_io(NULL, 0);
 	s3c24xx_init_clocks(24000000);
 	s3c24xx_init_uarts(universal_uartcfgs, ARRAY_SIZE(universal_uartcfgs));
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index 3698a370d636..26aac363a064 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -86,9 +86,6 @@ static void __init halibut_init(void)
 static void __init halibut_fixup(struct tag *tags, char **cmdline,
 				 struct meminfo *mi)
 {
-	mi->nr_banks=1;
-	mi->bank[0].start = PHYS_OFFSET;
-	mi->bank[0].size = (101*1024*1024);
 }
 
 static void __init halibut_map_io(void)
diff --git a/arch/arm/mach-msm/board-trout-panel.c b/arch/arm/mach-msm/board-trout-panel.c
index 25105c1027fe..89bf6b426699 100644
--- a/arch/arm/mach-msm/board-trout-panel.c
+++ b/arch/arm/mach-msm/board-trout-panel.c
@@ -12,6 +12,7 @@
 
 #include <asm/io.h>
 #include <asm/mach-types.h>
+#include <asm/system_info.h>
 
 #include <mach/msm_fb.h>
 #include <mach/vreg.h>
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 5414f76ec0a9..d4060a37e23d 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/clkdev.h>
 
+#include <asm/system_info.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-msm/proc_comm.c b/arch/arm/mach-msm/proc_comm.c
index 67e701c7f183..9980dc736e7b 100644
--- a/arch/arm/mach-msm/proc_comm.c
+++ b/arch/arm/mach-msm/proc_comm.c
@@ -121,7 +121,7 @@ int msm_proc_comm(unsigned cmd, unsigned *data1, unsigned *data2)
  * and unknown state. This function should be called early to
  * wait on the ARM9.
  */
-void __init proc_comm_boot_wait(void)
+void __devinit proc_comm_boot_wait(void)
 {
 	void __iomem *base = MSM_SHARED_RAM_BASE;
  
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index 7072e0d651b1..3d9d746b221a 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -165,83 +165,3 @@ int omap2_select_table_rate(struct clk *clk, unsigned long rate)
 
 	return 0;
 }
-
-#ifdef CONFIG_CPU_FREQ
-/*
- * Walk PRCM rate table and fillout cpufreq freq_table
- * XXX This should be replaced by an OPP layer in the near future
- */
-static struct cpufreq_frequency_table *freq_table;
-
-void omap2_clk_init_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	const struct prcm_config *prcm;
-	int i = 0;
-	int tbl_sz = 0;
-
-	if (!cpu_is_omap24xx())
-		return;
-
-	for (prcm = rate_table; prcm->mpu_speed; prcm++) {
-		if (!(prcm->flags & cpu_mask))
-			continue;
-		if (prcm->xtal_speed != sclk->rate)
-			continue;
-
-		/* don't put bypass rates in table */
-		if (prcm->dpll_speed == prcm->xtal_speed)
-			continue;
-
-		tbl_sz++;
-	}
-
-	/*
-	 * XXX Ensure that we're doing what CPUFreq expects for this error
-	 * case and the following one
-	 */
-	if (tbl_sz == 0) {
-		pr_warning("%s: no matching entries in rate_table\n",
-			   __func__);
-		return;
-	}
-
-	/* Include the CPUFREQ_TABLE_END terminator entry */
-	tbl_sz++;
-
-	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) * tbl_sz,
-			     GFP_ATOMIC);
-	if (!freq_table) {
-		pr_err("%s: could not kzalloc frequency table\n", __func__);
-		return;
-	}
-
-	for (prcm = rate_table; prcm->mpu_speed; prcm++) {
-		if (!(prcm->flags & cpu_mask))
-			continue;
-		if (prcm->xtal_speed != sclk->rate)
-			continue;
-
-		/* don't put bypass rates in table */
-		if (prcm->dpll_speed == prcm->xtal_speed)
-			continue;
-
-		freq_table[i].index = i;
-		freq_table[i].frequency = prcm->mpu_speed / 1000;
-		i++;
-	}
-
-	freq_table[i].index = i;
-	freq_table[i].frequency = CPUFREQ_TABLE_END;
-
-	*table = &freq_table[0];
-}
-
-void omap2_clk_exit_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	if (!cpu_is_omap24xx())
-		return;
-
-	kfree(freq_table);
-}
-
-#endif
diff --git a/arch/arm/mach-omap2/clock.c b/arch/arm/mach-omap2/clock.c
index f57ed5baeccf..d9f4931513f9 100644
--- a/arch/arm/mach-omap2/clock.c
+++ b/arch/arm/mach-omap2/clock.c
@@ -536,10 +536,5 @@ struct clk_functions omap2_clk_functions = {
 	.clk_set_rate		= omap2_clk_set_rate,
 	.clk_set_parent		= omap2_clk_set_parent,
 	.clk_disable_unused	= omap2_clk_disable_unused,
-#ifdef CONFIG_CPU_FREQ
-	/* These will be removed when the OPP code is integrated */
-	.clk_init_cpufreq_table	= omap2_clk_init_cpufreq_table,
-	.clk_exit_cpufreq_table	= omap2_clk_exit_cpufreq_table,
-#endif
 };
 
diff --git a/arch/arm/mach-omap2/clock.h b/arch/arm/mach-omap2/clock.h
index b8c2a686481c..a1bb23a23351 100644
--- a/arch/arm/mach-omap2/clock.h
+++ b/arch/arm/mach-omap2/clock.h
@@ -146,14 +146,6 @@ extern const struct clksel_rate gpt_sys_rates[];
 extern const struct clksel_rate gfx_l3_rates[];
 extern const struct clksel_rate dsp_ick_rates[];
 
-#if defined(CONFIG_ARCH_OMAP2) && defined(CONFIG_CPU_FREQ)
-extern void omap2_clk_init_cpufreq_table(struct cpufreq_frequency_table **table);
-extern void omap2_clk_exit_cpufreq_table(struct cpufreq_frequency_table **table);
-#else
-#define omap2_clk_init_cpufreq_table	0
-#define omap2_clk_exit_cpufreq_table	0
-#endif
-
 extern const struct clkops clkops_omap2_iclk_dflt_wait;
 extern const struct clkops clkops_omap2_iclk_dflt;
 extern const struct clkops clkops_omap2_iclk_idle_only;
diff --git a/arch/arm/mach-s5pv210/dma.c b/arch/arm/mach-s5pv210/dma.c
index 86ce62f66190..b8337e248b09 100644
--- a/arch/arm/mach-s5pv210/dma.c
+++ b/arch/arm/mach-s5pv210/dma.c
@@ -33,8 +33,6 @@
 #include <mach/irqs.h>
 #include <mach/dma.h>
 
-static u64 dma_dmamask = DMA_BIT_MASK(32);
-
 static u8 pdma0_peri[] = {
 	DMACH_UART0_RX,
 	DMACH_UART0_TX,
diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c
index a9ea64e0da0d..48d018f2332b 100644
--- a/arch/arm/mach-s5pv210/mach-aquila.c
+++ b/arch/arm/mach-s5pv210/mach-aquila.c
@@ -484,8 +484,8 @@ static struct wm8994_pdata wm8994_platform_data = {
 	.gpio_defaults[8] = 0x0100,
 	.gpio_defaults[9] = 0x0100,
 	.gpio_defaults[10] = 0x0100,
-	.ldo[0]	= { S5PV210_MP03(6), NULL, &wm8994_ldo1_data },	/* XM0FRNB_2 */
-	.ldo[1]	= { 0, NULL, &wm8994_ldo2_data },
+	.ldo[0]	= { S5PV210_MP03(6), &wm8994_ldo1_data },	/* XM0FRNB_2 */
+	.ldo[1]	= { 0, &wm8994_ldo2_data },
 };
 
 /* GPIO I2C PMIC */
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index 2cf5ed75f390..a8933de3d627 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -674,8 +674,8 @@ static struct wm8994_pdata wm8994_platform_data = {
 	.gpio_defaults[8] = 0x0100,
 	.gpio_defaults[9] = 0x0100,
 	.gpio_defaults[10] = 0x0100,
-	.ldo[0]	= { S5PV210_MP03(6), NULL, &wm8994_ldo1_data },	/* XM0FRNB_2 */
-	.ldo[1]	= { 0, NULL, &wm8994_ldo2_data },
+	.ldo[0]	= { S5PV210_MP03(6), &wm8994_ldo1_data },	/* XM0FRNB_2 */
+	.ldo[1]	= { 0, &wm8994_ldo2_data },
 };
 
 /* GPIO I2C PMIC */
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7edef9121632..7c8a7d8467bf 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -723,7 +723,7 @@ config CPU_HIGH_VECTOR
 	bool "Select the High exception vector"
 	help
 	  Say Y here to select high exception vector(0xFFFF0000~).
-	  The exception vector can be vary depending on the platform
+	  The exception vector can vary depending on the platform
 	  design in nommu mode. If your platform needs to select
 	  high exception vector, say Y.
 	  Otherwise or if you are unsure, say N, and the low exception
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 9055b5a84ec5..f07467533365 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -320,7 +320,7 @@ retry:
 	 */
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+	if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) {
 		if (fault & VM_FAULT_MAJOR) {
 			tsk->maj_flt++;
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 6486d2f253cd..d51225f90ae2 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -13,6 +13,7 @@
 #include <asm/sections.h>
 #include <asm/page.h>
 #include <asm/setup.h>
+#include <asm/traps.h>
 #include <asm/mach/arch.h>
 
 #include "mm.h"
@@ -39,6 +40,7 @@ void __init sanity_check_meminfo(void)
  */
 void __init paging_init(struct machine_desc *mdesc)
 {
+	early_trap_init((void *)CONFIG_VECTORS_BASE);
 	bootmem_init();
 }
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index f1c8486f7501..c2e2b66f72b5 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -255,6 +255,18 @@ __v7_setup:
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
+#ifndef CONFIG_ARM_THUMBEE
+	mrc	p15, 0, r0, c0, c1, 0		@ read ID_PFR0 for ThumbEE
+	and	r0, r0, #(0xf << 12)		@ ThumbEE enabled field
+	teq	r0, #(1 << 12)			@ check if ThumbEE is present
+	bne	1f
+	mov	r5, #0
+	mcr	p14, 6, r5, c1, c0, 0		@ Initialize TEEHBR to 0
+	mrc	p14, 6, r0, c0, c0, 0		@ load TEECR
+	orr	r0, r0, #1			@ set the 1st bit in order to
+	mcr	p14, 6, r0, c0, c0, 0		@ stop userspace TEEHBR access
+1:
+#endif
 	adr	r5, v7_crval
 	ldmia	r5, {r5, r6}
 #ifdef CONFIG_CPU_ENDIAN_BE8
diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c
index 8506cbb7fea4..62ec5c452792 100644
--- a/arch/arm/plat-omap/clock.c
+++ b/arch/arm/plat-omap/clock.c
@@ -398,32 +398,6 @@ struct clk dummy_ck = {
 	.ops	= &clkops_null,
 };
 
-#ifdef CONFIG_CPU_FREQ
-void clk_init_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	unsigned long flags;
-
-	if (!arch_clock || !arch_clock->clk_init_cpufreq_table)
-		return;
-
-	spin_lock_irqsave(&clockfw_lock, flags);
-	arch_clock->clk_init_cpufreq_table(table);
-	spin_unlock_irqrestore(&clockfw_lock, flags);
-}
-
-void clk_exit_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	unsigned long flags;
-
-	if (!arch_clock || !arch_clock->clk_exit_cpufreq_table)
-		return;
-
-	spin_lock_irqsave(&clockfw_lock, flags);
-	arch_clock->clk_exit_cpufreq_table(table);
-	spin_unlock_irqrestore(&clockfw_lock, flags);
-}
-#endif
-
 /*
  *
  */
diff --git a/arch/arm/plat-omap/include/plat/clock.h b/arch/arm/plat-omap/include/plat/clock.h
index 240a7b9fd946..d0ef57c1d71b 100644
--- a/arch/arm/plat-omap/include/plat/clock.h
+++ b/arch/arm/plat-omap/include/plat/clock.h
@@ -272,8 +272,6 @@ struct clk {
 #endif
 };
 
-struct cpufreq_frequency_table;
-
 struct clk_functions {
 	int		(*clk_enable)(struct clk *clk);
 	void		(*clk_disable)(struct clk *clk);
@@ -283,10 +281,6 @@ struct clk_functions {
 	void		(*clk_allow_idle)(struct clk *clk);
 	void		(*clk_deny_idle)(struct clk *clk);
 	void		(*clk_disable_unused)(struct clk *clk);
-#ifdef CONFIG_CPU_FREQ
-	void		(*clk_init_cpufreq_table)(struct cpufreq_frequency_table **);
-	void		(*clk_exit_cpufreq_table)(struct cpufreq_frequency_table **);
-#endif
 };
 
 extern int mpurate;
@@ -301,10 +295,6 @@ extern void recalculate_root_clocks(void);
 extern unsigned long followparent_recalc(struct clk *clk);
 extern void clk_enable_init_clocks(void);
 unsigned long omap_fixed_divisor_recalc(struct clk *clk);
-#ifdef CONFIG_CPU_FREQ
-extern void clk_init_cpufreq_table(struct cpufreq_frequency_table **table);
-extern void clk_exit_cpufreq_table(struct cpufreq_frequency_table **table);
-#endif
 extern struct clk *omap_clk_get_by_name(const char *name);
 extern int omap_clk_enable_autoidle_all(void);
 extern int omap_clk_disable_autoidle_all(void);
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 71553f410016..a0ffc77da809 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -302,6 +302,7 @@ comment "Power management"
 config SAMSUNG_PM_DEBUG
 	bool "S3C2410 PM Suspend debug"
 	depends on PM
+	select DEBUG_LL
 	help
 	  Say Y here if you want verbose debugging from the PM Suspend and
 	  Resume code. See <file:Documentation/arm/Samsung-S3C24XX/Suspend.txt>
diff --git a/arch/c6x/include/asm/irq.h b/arch/c6x/include/asm/irq.h
index f13b78d5e1ca..ab4577f93d96 100644
--- a/arch/c6x/include/asm/irq.h
+++ b/arch/c6x/include/asm/irq.h
@@ -42,10 +42,6 @@
 /* This number is used when no interrupt has been assigned */
 #define NO_IRQ		0
 
-struct irq_data;
-extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
-extern irq_hw_number_t virq_to_hw(unsigned int virq);
-
 extern void __init init_pic_c64xplus(void);
 
 extern void init_IRQ(void);
diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c
index 65b8ddf54b44..c90fb5e82ad7 100644
--- a/arch/c6x/kernel/irq.c
+++ b/arch/c6x/kernel/irq.c
@@ -130,16 +130,3 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	return 0;
 }
-
-irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-EXPORT_SYMBOL_GPL(irqd_to_hwirq);
-
-irq_hw_number_t virq_to_hw(unsigned int virq)
-{
-	struct irq_data *irq_data = irq_get_irq_data(virq);
-	return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
-}
-EXPORT_SYMBOL_GPL(virq_to_hw);
diff --git a/arch/ia64/include/asm/cmpxchg.h b/arch/ia64/include/asm/cmpxchg.h
index 4c96187e2049..4f37dbbb8640 100644
--- a/arch/ia64/include/asm/cmpxchg.h
+++ b/arch/ia64/include/asm/cmpxchg.h
@@ -1 +1,147 @@
-#include <asm/intrinsics.h>
+#ifndef _ASM_IA64_CMPXCHG_H
+#define _ASM_IA64_CMPXCHG_H
+
+/*
+ * Compare/Exchange, forked from asm/intrinsics.h
+ * which was:
+ *
+ *	Copyright (C) 2002-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+/* include compiler specific intrinsics */
+#include <asm/ia64regs.h>
+#ifdef __INTEL_COMPILER
+# include <asm/intel_intrin.h>
+#else
+# include <asm/gcc_intrin.h>
+#endif
+
+/*
+ * This function doesn't exist, so you'll get a linker error if
+ * something tries to do an invalid xchg().
+ */
+extern void ia64_xchg_called_with_bad_pointer(void);
+
+#define __xchg(x, ptr, size)						\
+({									\
+	unsigned long __xchg_result;					\
+									\
+	switch (size) {							\
+	case 1:								\
+		__xchg_result = ia64_xchg1((__u8 *)ptr, x);		\
+		break;							\
+									\
+	case 2:								\
+		__xchg_result = ia64_xchg2((__u16 *)ptr, x);		\
+		break;							\
+									\
+	case 4:								\
+		__xchg_result = ia64_xchg4((__u32 *)ptr, x);		\
+		break;							\
+									\
+	case 8:								\
+		__xchg_result = ia64_xchg8((__u64 *)ptr, x);		\
+		break;							\
+	default:							\
+		ia64_xchg_called_with_bad_pointer();			\
+	}								\
+	__xchg_result;							\
+})
+
+#define xchg(ptr, x)							\
+((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr))))
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern long ia64_cmpxchg_called_with_bad_pointer(void);
+
+#define ia64_cmpxchg(sem, ptr, old, new, size)				\
+({									\
+	__u64 _o_, _r_;							\
+									\
+	switch (size) {							\
+	case 1:								\
+		_o_ = (__u8) (long) (old);				\
+		break;							\
+	case 2:								\
+		_o_ = (__u16) (long) (old);				\
+		break;							\
+	case 4:								\
+		_o_ = (__u32) (long) (old);				\
+		break;							\
+	case 8:								\
+		_o_ = (__u64) (long) (old);				\
+		break;							\
+	default:							\
+		break;							\
+	}								\
+	switch (size) {							\
+	case 1:								\
+		_r_ = ia64_cmpxchg1_##sem((__u8 *) ptr, new, _o_);	\
+		break;							\
+									\
+	case 2:								\
+		_r_ = ia64_cmpxchg2_##sem((__u16 *) ptr, new, _o_);	\
+		break;							\
+									\
+	case 4:								\
+		_r_ = ia64_cmpxchg4_##sem((__u32 *) ptr, new, _o_);	\
+		break;							\
+									\
+	case 8:								\
+		_r_ = ia64_cmpxchg8_##sem((__u64 *) ptr, new, _o_);	\
+		break;							\
+									\
+	default:							\
+		_r_ = ia64_cmpxchg_called_with_bad_pointer();		\
+		break;							\
+	}								\
+	(__typeof__(old)) _r_;						\
+})
+
+#define cmpxchg_acq(ptr, o, n)	\
+	ia64_cmpxchg(acq, (ptr), (o), (n), sizeof(*(ptr)))
+#define cmpxchg_rel(ptr, o, n)	\
+	ia64_cmpxchg(rel, (ptr), (o), (n), sizeof(*(ptr)))
+
+/* for compatibility with other platforms: */
+#define cmpxchg(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
+
+#define cmpxchg_local		cmpxchg
+#define cmpxchg64_local		cmpxchg64
+
+#ifdef CONFIG_IA64_DEBUG_CMPXCHG
+# define CMPXCHG_BUGCHECK_DECL	int _cmpxchg_bugcheck_count = 128;
+# define CMPXCHG_BUGCHECK(v)						\
+do {									\
+	if (_cmpxchg_bugcheck_count-- <= 0) {				\
+		void *ip;						\
+		extern int printk(const char *fmt, ...);		\
+		ip = (void *) ia64_getreg(_IA64_REG_IP);		\
+		printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));\
+		break;							\
+	}								\
+} while (0)
+#else /* !CONFIG_IA64_DEBUG_CMPXCHG */
+# define CMPXCHG_BUGCHECK_DECL
+# define CMPXCHG_BUGCHECK(v)
+#endif /* !CONFIG_IA64_DEBUG_CMPXCHG */
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_IA64_CMPXCHG_H */
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index 0ab82cc2dc8f..d2bf1fd5e44f 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -106,15 +106,16 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	{
-		register unsigned long r8 __asm ("r8") = 0;
+		register unsigned long r8 __asm ("r8");
 		unsigned long prev;
 		__asm__ __volatile__(
 			"	mf;;					\n"
-			"	mov ar.ccv=%3;;				\n"
-			"[1:]	cmpxchg4.acq %0=[%1],%2,ar.ccv		\n"
+			"	mov %0=r0				\n"
+			"	mov ar.ccv=%4;;				\n"
+			"[1:]	cmpxchg4.acq %1=[%2],%3,ar.ccv		\n"
 			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
 			"[2:]"
-			: "=r" (prev)
+			: "=r" (r8), "=r" (prev)
 			: "r" (uaddr), "r" (newval),
 			  "rO" ((long) (unsigned) oldval)
 			: "memory");
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index e4076b511829..d129e367e764 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -18,6 +18,7 @@
 #else
 # include <asm/gcc_intrin.h>
 #endif
+#include <asm/cmpxchg.h>
 
 #define ia64_native_get_psr_i()	(ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I)
 
@@ -81,119 +82,6 @@ extern unsigned long __bad_increment_for_ia64_fetch_and_add (void);
 
 #define ia64_fetch_and_add(i,v)	(ia64_fetchadd(i, v, rel) + (i)) /* return new value */
 
-/*
- * This function doesn't exist, so you'll get a linker error if
- * something tries to do an invalid xchg().
- */
-extern void ia64_xchg_called_with_bad_pointer (void);
-
-#define __xchg(x,ptr,size)						\
-({									\
-	unsigned long __xchg_result;					\
-									\
-	switch (size) {							\
-	      case 1:							\
-		__xchg_result = ia64_xchg1((__u8 *)ptr, x);		\
-		break;							\
-									\
-	      case 2:							\
-		__xchg_result = ia64_xchg2((__u16 *)ptr, x);		\
-		break;							\
-									\
-	      case 4:							\
-		__xchg_result = ia64_xchg4((__u32 *)ptr, x);		\
-		break;							\
-									\
-	      case 8:							\
-		__xchg_result = ia64_xchg8((__u64 *)ptr, x);		\
-		break;							\
-	      default:							\
-		ia64_xchg_called_with_bad_pointer();			\
-	}								\
-	__xchg_result;							\
-})
-
-#define xchg(ptr,x)							     \
-  ((__typeof__(*(ptr))) __xchg ((unsigned long) (x), (ptr), sizeof(*(ptr))))
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-
-#define __HAVE_ARCH_CMPXCHG 1
-
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid cmpxchg().
- */
-extern long ia64_cmpxchg_called_with_bad_pointer (void);
-
-#define ia64_cmpxchg(sem,ptr,old,new,size)						\
-({											\
-	__u64 _o_, _r_;									\
-											\
-	switch (size) {									\
-	      case 1: _o_ = (__u8 ) (long) (old); break;				\
-	      case 2: _o_ = (__u16) (long) (old); break;				\
-	      case 4: _o_ = (__u32) (long) (old); break;				\
-	      case 8: _o_ = (__u64) (long) (old); break;				\
-	      default: break;								\
-	}										\
-	switch (size) {									\
-	      case 1:									\
-	      	_r_ = ia64_cmpxchg1_##sem((__u8 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      case 2:									\
-	       _r_ = ia64_cmpxchg2_##sem((__u16 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      case 4:									\
-	      	_r_ = ia64_cmpxchg4_##sem((__u32 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      case 8:									\
-		_r_ = ia64_cmpxchg8_##sem((__u64 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      default:									\
-		_r_ = ia64_cmpxchg_called_with_bad_pointer();				\
-		break;									\
-	}										\
-	(__typeof__(old)) _r_;								\
-})
-
-#define cmpxchg_acq(ptr, o, n)	\
-	ia64_cmpxchg(acq, (ptr), (o), (n), sizeof(*(ptr)))
-#define cmpxchg_rel(ptr, o, n)	\
-	ia64_cmpxchg(rel, (ptr), (o), (n), sizeof(*(ptr)))
-
-/* for compatibility with other platforms: */
-#define cmpxchg(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
-#define cmpxchg64(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
-
-#define cmpxchg_local		cmpxchg
-#define cmpxchg64_local		cmpxchg64
-
-#ifdef CONFIG_IA64_DEBUG_CMPXCHG
-# define CMPXCHG_BUGCHECK_DECL	int _cmpxchg_bugcheck_count = 128;
-# define CMPXCHG_BUGCHECK(v)							\
-  do {										\
-	if (_cmpxchg_bugcheck_count-- <= 0) {					\
-		void *ip;							\
-		extern int printk(const char *fmt, ...);			\
-		ip = (void *) ia64_getreg(_IA64_REG_IP);			\
-		printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));	\
-		break;								\
-	}									\
-  } while (0)
-#else /* !CONFIG_IA64_DEBUG_CMPXCHG */
-# define CMPXCHG_BUGCHECK_DECL
-# define CMPXCHG_BUGCHECK(v)
-#endif /* !CONFIG_IA64_DEBUG_CMPXCHG */
-
 #endif
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index cf417e510736..e648af92ced1 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -33,8 +33,6 @@ extern atomic_t ppc_n_lost_interrupts;
 /* Same thing, used by the generic IRQ code */
 #define NR_IRQS_LEGACY		NUM_ISA_INTERRUPTS
 
-struct irq_data;
-extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
 
 /**
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3e57a00b8cba..ba3aeb4bc06a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -206,40 +206,43 @@ reenable_mmu:				/* re-enable mmu so we can */
 	andi.	r10,r10,MSR_EE		/* Did EE change? */
 	beq	1f
 
-	/* Save handler and return address into the 2 unused words
-	 * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
-	 * else can be recovered from the pt_regs except r3 which for
-	 * normal interrupts has been set to pt_regs and for syscalls
-	 * is an argument, so we temporarily use ORIG_GPR3 to save it
-	 */
-	stw	r9,8(r1)
-	stw	r11,12(r1)
-	stw	r3,ORIG_GPR3(r1)
 	/*
 	 * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
 	 * If from user mode there is only one stack frame on the stack, and
 	 * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
 	 * stack frame to make trace_hardirqs_off happy.
+	 *
+	 * This is handy because we also need to save a bunch of GPRs,
+	 * r3 can be different from GPR3(r1) at this point, r9 and r11
+	 * contains the old MSR and handler address respectively,
+	 * r4 & r5 can contain page fault arguments that need to be passed
+	 * along as well. r12, CCR, CTR, XER etc... are left clobbered as
+	 * they aren't useful past this point (aren't syscall arguments),
+	 * the rest is restored from the exception frame.
 	 */
+	stwu	r1,-32(r1)
+	stw	r9,8(r1)
+	stw	r11,12(r1)
+	stw	r3,16(r1)
+	stw	r4,20(r1)
+	stw	r5,24(r1)
 	andi.	r12,r12,MSR_PR
-	beq	11f
-	stwu	r1,-16(r1)
+	b	11f
 	bl	trace_hardirqs_off
-	addi	r1,r1,16
 	b	12f
-
 11:
 	bl	trace_hardirqs_off
 12:
+	lwz	r5,24(r1)
+	lwz	r4,20(r1)
+	lwz	r3,16(r1)
+	lwz	r11,12(r1)
+	lwz	r9,8(r1)
+	addi	r1,r1,32
 	lwz	r0,GPR0(r1)
-	lwz	r3,ORIG_GPR3(r1)
-	lwz	r4,GPR4(r1)
-	lwz	r5,GPR5(r1)
 	lwz	r6,GPR6(r1)
 	lwz	r7,GPR7(r1)
 	lwz	r8,GPR8(r1)
-	lwz	r9,8(r1)
-	lwz	r11,12(r1)
 1:	mtctr	r11
 	mtlr	r9
 	bctr				/* jump to handler */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 243dbabfe74d..5ec1b2354ca6 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -560,12 +560,6 @@ void do_softirq(void)
 	local_irq_restore(flags);
 }
 
-irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-EXPORT_SYMBOL_GPL(irqd_to_hwirq);
-
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(virq);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f88698c0f332..4937c9690090 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1235,7 +1235,7 @@ void __ppc64_runlatch_on(void)
 	ctrl |= CTRL_RUNLATCH;
 	mtspr(SPRN_CTRLT, ctrl);
 
-	ti->local_flags |= TLF_RUNLATCH;
+	ti->local_flags |= _TLF_RUNLATCH;
 }
 
 /* Called with hard IRQs off */
@@ -1244,7 +1244,7 @@ void __ppc64_runlatch_off(void)
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
 
-	ti->local_flags &= ~TLF_RUNLATCH;
+	ti->local_flags &= ~_TLF_RUNLATCH;
 
 	ctrl = mfspr(SPRN_CTRLF);
 	ctrl &= ~CTRL_RUNLATCH;
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index db360fc4cf0e..d09f3e8e6867 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -392,7 +392,7 @@ static int axon_msi_probe(struct platform_device *device)
 	}
 	memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
 
-	msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic);
+	msic->irq_domain = irq_domain_add_nomap(dn, 0, &msic_host_ops, msic);
 	if (!msic->irq_domain) {
 		printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n",
 		       dn->full_name);
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index e5c3a2c6090d..f9a48af335cb 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -239,7 +239,7 @@ void __init beatic_init_IRQ(void)
 	ppc_md.get_irq = beatic_get_irq;
 
 	/* Allocate an irq host */
-	beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL);
+	beatic_host = irq_domain_add_nomap(NULL, 0, &beatic_pic_host_ops, NULL);
 	BUG_ON(beatic_host == NULL);
 	irq_set_default_host(beatic_host);
 }
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index a81e5a88fbdf..b4ddaa3fbb29 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -192,7 +192,7 @@ static int psurge_secondary_ipi_init(void)
 {
 	int rc = -ENOMEM;
 
-	psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL);
+	psurge_host = irq_domain_add_nomap(NULL, 0, &psurge_host_ops, NULL);
 
 	if (psurge_host)
 		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 2a4ff86cc21f..5f3b23220b8e 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -753,9 +753,8 @@ void __init ps3_init_IRQ(void)
 	unsigned cpu;
 	struct irq_domain *host;
 
-	host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL);
+	host = irq_domain_add_nomap(NULL, PS3_PLUG_MAX + 1, &ps3_host_ops, NULL);
 	irq_set_default_host(host);
-	irq_set_virq_count(PS3_PLUG_MAX + 1);
 
 	for_each_possible_cpu(cpu) {
 		struct ps3_private *pd = &per_cpu(ps3_private, cpu);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 2b7c0fbe578e..9015060919a0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -90,7 +90,6 @@ config S390
 	select HAVE_KERNEL_XZ
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
-	select HAVE_RCU_TABLE_FREE if SMP
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 6cf8e26b3137..1957a9dd256d 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,8 +1,12 @@
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_FHANDLE=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_AUDIT=y
-CONFIG_RCU_TRACE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
@@ -14,16 +18,22 @@ CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
+CONFIG_NAMESPACES=y
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_RD_XZ=y
+CONFIG_RD_LZO=y
+CONFIG_EXPERT=y
 # CONFIG_COMPAT_BRK is not set
-CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -34,18 +44,15 @@ CONFIG_KSM=y
 CONFIG_BINFMT_MISC=m
 CONFIG_CMM=m
 CONFIG_HZ_100=y
-CONFIG_KEXEC=y
-CONFIG_PM=y
+CONFIG_CRASH_DUMP=y
 CONFIG_HIBERNATION=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_NET_KEY=y
-CONFIG_AFIUCV=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 # CONFIG_INET_LRO is not set
 CONFIG_IPV6=y
-CONFIG_NET_SCTPPROBE=m
 CONFIG_L2TP=m
 CONFIG_L2TP_DEBUGFS=m
 CONFIG_VLAN_8021Q=y
@@ -84,15 +91,14 @@ CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
 CONFIG_ZFCP=y
-CONFIG_ZFCP_DIF=y
 CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
 CONFIG_BONDING=m
+CONFIG_DUMMY=m
 CONFIG_EQUALIZER=m
 CONFIG_TUN=m
-CONFIG_NET_ETHERNET=y
 CONFIG_VIRTIO_NET=y
 CONFIG_RAW_DRIVER=m
+CONFIG_VIRTIO_BALLOON=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
@@ -103,27 +109,21 @@ CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_TIMER_STATS=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_PROVE_RCU=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
-CONFIG_DEBUG_SPINLOCK_SLEEP=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_NOTIFIERS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_RCU_TRACE=y
 CONFIG_KPROBES_SANITY_TEST=y
 CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
 CONFIG_LATENCYTOP=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_DEBUG_PAGEALLOC=y
-# CONFIG_FTRACE is not set
+CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -173,4 +173,3 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRC7=m
-CONFIG_VIRTIO_BALLOON=y
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 1e5b27edc0c9..2ee66a65f2d4 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -38,12 +38,11 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	unsigned long nr;
 
 	preempt_disable();
-	S390_lowcore.stfl_fac_list = 0;
 	asm volatile(
 		"	.insn s,0xb2b10000,0(0)\n" /* stfl */
 		"0:\n"
 		EX_TABLE(0b, 0b)
-		: "=m" (S390_lowcore.stfl_fac_list));
+		: "+m" (S390_lowcore.stfl_fac_list));
 	nr = 4; /* bytes stored by stfl */
 	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
 	if (S390_lowcore.stfl_fac_list & 0x01000000) {
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 8eef9b5b3cf4..78e3041919de 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -22,10 +22,7 @@ void crst_table_free(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
-void __tlb_remove_table(void *_table);
-#endif
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
diff --git a/arch/s390/include/asm/swab.h b/arch/s390/include/asm/swab.h
index 6bdee21c077e..a3e4ebb32090 100644
--- a/arch/s390/include/asm/swab.h
+++ b/arch/s390/include/asm/swab.h
@@ -77,7 +77,7 @@ static inline __u16 __arch_swab16p(const __u16 *x)
 	
 	asm volatile(
 #ifndef __s390x__
-		"	icm	%0,2,%O+1(%R1)\n"
+		"	icm	%0,2,%O1+1(%R1)\n"
 		"	ic	%0,%1\n"
 		: "=&d" (result) : "Q" (*x) : "cc");
 #else /* __s390x__ */
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index c687a2c83462..775a5eea8f9e 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -30,14 +30,10 @@
 
 struct mmu_gather {
 	struct mm_struct *mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch *batch;
-#endif
 	unsigned int fullmm;
-	unsigned int need_flush;
 };
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 struct mmu_table_batch {
 	struct rcu_head		rcu;
 	unsigned int		nr;
@@ -49,7 +45,6 @@ struct mmu_table_batch {
 
 extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-#endif
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 				  struct mm_struct *mm,
@@ -57,29 +52,20 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 {
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
-	tlb->need_flush = 0;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
-#endif
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
 }
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->need_flush)
-		return;
-	tlb->need_flush = 0;
-	__tlb_flush_mm(tlb->mm);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
-#endif
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
-	tlb_flush_mmu(tlb);
+	tlb_table_flush(tlb);
 }
 
 /*
@@ -105,10 +91,8 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				unsigned long address)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	if (!tlb->fullmm)
 		return page_table_free_rcu(tlb, (unsigned long *) pte);
-#endif
 	page_table_free(tlb->mm, (unsigned long *) pte);
 }
 
@@ -125,10 +109,8 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 31))
 		return;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	if (!tlb->fullmm)
 		return tlb_remove_table(tlb, pmd);
-#endif
 	crst_table_free(tlb->mm, (unsigned long *) pmd);
 #endif
 }
@@ -146,10 +128,8 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 42))
 		return;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	if (!tlb->fullmm)
 		return tlb_remove_table(tlb, pud);
-#endif
 	crst_table_free(tlb->mm, (unsigned long *) pud);
 #endif
 }
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index c27a0727f930..adccd908ebc7 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -474,9 +474,9 @@ ENTRY(startup_kdump)
 	stck	__LC_LAST_UPDATE_CLOCK
 	spt	5f-.LPG0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13)
+	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 #ifndef CONFIG_MARCH_G5
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
-	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 	.insn	s,0xb2b10000,__LC_STFL_FAC_LIST	# store facility list
 	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
 	jz	0f
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 1c2cdd59ccd0..8a22c27219dd 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -118,9 +118,10 @@ asmlinkage void do_softirq(void)
 				         "a" (__do_softirq)
 				     : "0", "1", "2", "3", "4", "5", "14",
 				       "cc", "memory" );
-		} else
+		} else {
 			/* We are already on the async stack. */
 			__do_softirq();
+		}
 	}
 
 	local_irq_restore(flags);
@@ -192,11 +193,12 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 	int index = ext_hash(code);
 
 	spin_lock_irqsave(&ext_int_hash_lock, flags);
-	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
+	list_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
 		if (p->code == code && p->handler == handler) {
 			list_del_rcu(&p->entry);
 			kfree_rcu(p, rcu);
 		}
+	}
 	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
@@ -211,9 +213,10 @@ void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code,
 
 	old_regs = set_irq_regs(regs);
 	irq_enter();
-	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
+	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) {
 		/* Serve timer interrupts first. */
 		clock_comparator_work();
+	}
 	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
 	if (ext_code.code != 0x1004)
 		__get_cpu_var(s390_idle).nohz_delay = 1;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 46405086479c..cb019f429e88 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -178,7 +178,7 @@ static void cpumf_pmu_enable(struct pmu *pmu)
 	err = lcctl(cpuhw->state);
 	if (err) {
 		pr_err("Enabling the performance measuring unit "
-		       "failed with rc=%lx\n", err);
+		       "failed with rc=%x\n", err);
 		return;
 	}
 
@@ -203,7 +203,7 @@ static void cpumf_pmu_disable(struct pmu *pmu)
 	err = lcctl(inactive);
 	if (err) {
 		pr_err("Disabling the performance measuring unit "
-		       "failed with rc=%lx\n", err);
+		       "failed with rc=%x\n", err);
 		return;
 	}
 
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 7bb15fcca75e..e1335dc2b1b7 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -61,21 +61,14 @@ long probe_kernel_write(void *dst, const void *src, size_t size)
 	return copied < 0 ? -EFAULT : 0;
 }
 
-/*
- * Copy memory in real mode (kernel to kernel)
- */
-int memcpy_real(void *dest, void *src, size_t count)
+static int __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
 	register unsigned long _src  asm("4") = (unsigned long) src;
 	register unsigned long _len2 asm("5") = (unsigned long) count;
-	unsigned long flags;
 	int rc = -EFAULT;
 
-	if (!count)
-		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
 	asm volatile (
 		"0:	mvcle	%1,%2,0x0\n"
 		"1:	jo	0b\n"
@@ -86,7 +79,23 @@ int memcpy_real(void *dest, void *src, size_t count)
 		  "+d" (_len2), "=m" (*((long *) dest))
 		: "m" (*((long *) src))
 		: "cc", "memory");
-	arch_local_irq_restore(flags);
+	return rc;
+}
+
+/*
+ * Copy memory in real mode (kernel to kernel)
+ */
+int memcpy_real(void *dest, void *src, size_t count)
+{
+	unsigned long flags;
+	int rc;
+
+	if (!count)
+		return 0;
+	local_irq_save(flags);
+	__arch_local_irq_stnsm(0xfbUL);
+	rc = __memcpy_real(dest, src, count);
+	local_irq_restore(flags);
 	return rc;
 }
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 373adf69b01c..6e765bf00670 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -678,8 +678,6 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	}
 }
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-
 static void __page_table_free_rcu(void *table, unsigned bit)
 {
 	struct page *page;
@@ -733,7 +731,66 @@ void __tlb_remove_table(void *_table)
 		free_pages((unsigned long) table, ALLOC_ORDER);
 }
 
-#endif
+static void tlb_remove_table_smp_sync(void *arg)
+{
+	/* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+	/*
+	 * This isn't an RCU grace period and hence the page-tables cannot be
+	 * assumed to be actually RCU-freed.
+	 *
+	 * It is however sufficient for software page-table walkers that rely
+	 * on IRQ disabling. See the comment near struct mmu_table_batch.
+	 */
+	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	__tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+	struct mmu_table_batch *batch;
+	int i;
+
+	batch = container_of(head, struct mmu_table_batch, rcu);
+
+	for (i = 0; i < batch->nr; i++)
+		__tlb_remove_table(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	if (*batch) {
+		__tlb_flush_mm(tlb->mm);
+		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+		*batch = NULL;
+	}
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	if (*batch == NULL) {
+		*batch = (struct mmu_table_batch *)
+			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		if (*batch == NULL) {
+			__tlb_flush_mm(tlb->mm);
+			tlb_remove_table_one(table);
+			return;
+		}
+		(*batch)->nr = 0;
+	}
+	(*batch)->tables[(*batch)->nr++] = table;
+	if ((*batch)->nr == MAX_TABLE_BATCH)
+		tlb_table_flush(tlb);
+}
 
 /*
  * switch on pgstes for its userspace process (for kvm)
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index fea13c7b1aee..b93c2c9ccb1d 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1264,4 +1264,4 @@ static int __init ds_init(void)
 	return vio_register_driver(&ds_driver);
 }
 
-subsys_initcall(ds_init);
+fs_initcall(ds_init);
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index aba6b958b2a5..19f56058742b 100644
--- a/arch/sparc/kernel/leon_pci.c
+++ b/arch/sparc/kernel/leon_pci.c
@@ -45,7 +45,6 @@ void leon_pci_init(struct platform_device *ofdev, struct leon_pci_info *info)
 
 void __devinit pcibios_fixup_bus(struct pci_bus *pbus)
 {
-	struct leon_pci_info *info = pbus->sysdata;
 	struct pci_dev *dev;
 	int i, has_io, has_mem;
 	u16 cmd;
@@ -111,18 +110,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return pci_enable_resources(dev, mask);
 }
 
-struct device_node *pci_device_to_OF_node(struct pci_dev *pdev)
-{
-	/*
-	 * Currently the OpenBoot nodes are not connected with the PCI device,
-	 * this is because the LEON PROM does not create PCI nodes. Eventually
-	 * this will change and the same approach as pcic.c can be used to
-	 * match PROM nodes with pci devices.
-	 */
-	return NULL;
-}
-EXPORT_SYMBOL(pci_device_to_OF_node);
-
 void __devinit pcibios_update_irq(struct pci_dev *dev, int irq)
 {
 #ifdef CONFIG_PCI_DEBUG
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 77f1b95e0806..9171fc238def 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -20,11 +20,6 @@
 
 		.text
 		.align			32
-__handle_softirq:
-		call			do_softirq
-		 nop
-		ba,a,pt			%xcc, __handle_softirq_continue
-		 nop
 __handle_preemption:
 		call			schedule
 		 wrpr			%g0, RTRAP_PSTATE, %pstate
@@ -89,9 +84,7 @@ rtrap:
 		cmp			%l1, 0
 
 		/* mm/ultra.S:xcall_report_regs KNOWS about this load. */
-		bne,pn			%icc, __handle_softirq
 		 ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
-__handle_softirq_continue:
 rtrap_xcall:
 		sethi			%hi(0xf << 20), %l4
 		and			%l1, %l4, %l4
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 7705c6731e28..df3155a17991 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -225,6 +225,8 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	unsigned long g2;
 	int from_user = !(regs->psr & PSR_PS);
 	int fault, code;
+	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+			      (write ? FAULT_FLAG_WRITE : 0));
 
 	if(text_fault)
 		address = regs->pc;
@@ -251,6 +253,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+retry:
 	down_read(&mm->mmap_sem);
 
 	/*
@@ -289,7 +292,11 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -297,13 +304,29 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			current->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+				      1, regs, address);
+		} else {
+			current->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+				      1, regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
 	}
+
 	up_read(&mm->mmap_sem);
 	return;
 
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 504c0622f729..1fe0429b6314 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -279,6 +279,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	unsigned int insn = 0;
 	int si_code, fault_code, fault;
 	unsigned long address, mm_rss;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	fault_code = get_thread_fault_code();
 
@@ -333,6 +334,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			insn = get_fault_insn(regs, insn);
 			goto handle_kernel_fault;
 		}
+
+retry:
 		down_read(&mm->mmap_sem);
 	}
 
@@ -423,7 +426,12 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
+	flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -431,12 +439,27 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			current->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+				      1, regs, address);
+		} else {
+			current->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+				      1, regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
 	}
 	up_read(&mm->mmap_sem);
 
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index 7a9327046404..446a7f52cc11 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -146,7 +146,6 @@ static ctl_table unaligned_table[] = {
 	},
 	{}
 };
-#endif
 
 static struct ctl_path tile_path[] = {
 	{ .procname = "tile" },
@@ -155,10 +154,9 @@ static struct ctl_path tile_path[] = {
 
 static int __init proc_sys_tile_init(void)
 {
-#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
 	register_sysctl_paths(tile_path, unaligned_table);
-#endif
 	return 0;
 }
 
 arch_initcall(proc_sys_tile_init);
+#endif
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index b949edcec200..172aef7d3159 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -196,6 +196,8 @@ void __cpuinit online_secondary(void)
 	/* This must be done before setting cpu_online_mask */
 	wmb();
 
+	notify_cpu_starting(smp_processor_id());
+
 	/*
 	 * We need to hold call_lock, so there is no inconsistency
 	 * between the time smp_call_function() determines number of
diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h
index dc36b222100b..6673508f3426 100644
--- a/arch/um/drivers/cow.h
+++ b/arch/um/drivers/cow.h
@@ -3,41 +3,6 @@
 
 #include <asm/types.h>
 
-#if defined(__KERNEL__)
-
-# include <asm/byteorder.h>
-
-# if defined(__BIG_ENDIAN)
-#	define ntohll(x) (x)
-#	define htonll(x) (x)
-# elif defined(__LITTLE_ENDIAN)
-#	define ntohll(x)  be64_to_cpu(x)
-#	define htonll(x)  cpu_to_be64(x)
-# else
-#	error "Could not determine byte order"
-# endif
-
-#else
-/* For the definition of ntohl, htonl and __BYTE_ORDER */
-#include <endian.h>
-#include <netinet/in.h>
-#if defined(__BYTE_ORDER)
-
-#  if __BYTE_ORDER == __BIG_ENDIAN
-#	define ntohll(x) (x)
-#	define htonll(x) (x)
-#  elif __BYTE_ORDER == __LITTLE_ENDIAN
-#	define ntohll(x)  bswap_64(x)
-#	define htonll(x)  bswap_64(x)
-#  else
-#	error "Could not determine byte order: __BYTE_ORDER uncorrectly defined"
-#  endif
-
-#else  /* ! defined(__BYTE_ORDER) */
-#	error "Could not determine byte order: __BYTE_ORDER not defined"
-#endif
-#endif /* ! defined(__KERNEL__) */
-
 extern int init_cow_file(int fd, char *cow_file, char *backing_file,
 			 int sectorsize, int alignment, int *bitmap_offset_out,
 			 unsigned long *bitmap_len_out, int *data_offset_out);
diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c
index 9cbb426c0b91..0ee9cc6cc4c7 100644
--- a/arch/um/drivers/cow_user.c
+++ b/arch/um/drivers/cow_user.c
@@ -8,11 +8,10 @@
  * that.
  */
 #include <unistd.h>
-#include <byteswap.h>
 #include <errno.h>
 #include <string.h>
 #include <arpa/inet.h>
-#include <asm/types.h>
+#include <endian.h>
 #include "cow.h"
 #include "cow_sys.h"
 
@@ -214,8 +213,8 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 			   "header\n");
 		goto out;
 	}
-	header->magic = htonl(COW_MAGIC);
-	header->version = htonl(COW_VERSION);
+	header->magic = htobe32(COW_MAGIC);
+	header->version = htobe32(COW_VERSION);
 
 	err = -EINVAL;
 	if (strlen(backing_file) > sizeof(header->backing_file) - 1) {
@@ -246,10 +245,10 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 		goto out_free;
 	}
 
-	header->mtime = htonl(modtime);
-	header->size = htonll(*size);
-	header->sectorsize = htonl(sectorsize);
-	header->alignment = htonl(alignment);
+	header->mtime = htobe32(modtime);
+	header->size = htobe64(*size);
+	header->sectorsize = htobe32(sectorsize);
+	header->alignment = htobe32(alignment);
 	header->cow_format = COW_BITMAP;
 
 	err = cow_write_file(fd, header, sizeof(*header));
@@ -301,8 +300,8 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 	magic = header->v1.magic;
 	if (magic == COW_MAGIC)
 		version = header->v1.version;
-	else if (magic == ntohl(COW_MAGIC))
-		version = ntohl(header->v1.version);
+	else if (magic == be32toh(COW_MAGIC))
+		version = be32toh(header->v1.version);
 	/* No error printed because the non-COW case comes through here */
 	else goto out;
 
@@ -327,9 +326,9 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 				   "header\n");
 			goto out;
 		}
-		*mtime_out = ntohl(header->v2.mtime);
-		*size_out = ntohll(header->v2.size);
-		*sectorsize_out = ntohl(header->v2.sectorsize);
+		*mtime_out = be32toh(header->v2.mtime);
+		*size_out = be64toh(header->v2.size);
+		*sectorsize_out = be32toh(header->v2.sectorsize);
 		*bitmap_offset_out = sizeof(header->v2);
 		*align_out = *sectorsize_out;
 		file = header->v2.backing_file;
@@ -341,10 +340,10 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 				   "header\n");
 			goto out;
 		}
-		*mtime_out = ntohl(header->v3.mtime);
-		*size_out = ntohll(header->v3.size);
-		*sectorsize_out = ntohl(header->v3.sectorsize);
-		*align_out = ntohl(header->v3.alignment);
+		*mtime_out = be32toh(header->v3.mtime);
+		*size_out = be64toh(header->v3.size);
+		*sectorsize_out = be32toh(header->v3.sectorsize);
+		*align_out = be32toh(header->v3.alignment);
 		if (*align_out == 0) {
 			cow_printf("read_cow_header - invalid COW header, "
 				   "align == 0\n");
@@ -366,16 +365,16 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 		 * this was used until Dec2005 - 64bits are needed to represent
 		 * 2038+. I.e. we can safely do this truncating cast.
 		 *
-		 * Additionally, we must use ntohl() instead of ntohll(), since
+		 * Additionally, we must use be32toh() instead of be64toh(), since
 		 * the program used to use the former (tested - I got mtime
 		 * mismatch "0 vs whatever").
 		 *
 		 * Ever heard about bug-to-bug-compatibility ? ;-) */
-		*mtime_out = (time32_t) ntohl(header->v3_b.mtime);
+		*mtime_out = (time32_t) be32toh(header->v3_b.mtime);
 
-		*size_out = ntohll(header->v3_b.size);
-		*sectorsize_out = ntohl(header->v3_b.sectorsize);
-		*align_out = ntohl(header->v3_b.alignment);
+		*size_out = be64toh(header->v3_b.size);
+		*sectorsize_out = be32toh(header->v3_b.sectorsize);
+		*align_out = be32toh(header->v3_b.alignment);
 		if (*align_out == 0) {
 			cow_printf("read_cow_header - invalid COW header, "
 				   "align == 0\n");
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index e672bd6d43e3..43b39d61b538 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -22,6 +22,7 @@
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
+#include <asm/switch_to.h>
 
 #include "init.h"
 #include "irq_kern.h"
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 8419f5cf2ac7..fff24352255d 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,3 +1,4 @@
 generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
 generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
-generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h
+generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
+generic-y += switch_to.h
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 492bc4c1b62b..65a1c3d690ea 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -3,9 +3,10 @@
 # Licensed under the GPL
 #
 
-CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START) \
-                        -DELF_ARCH=$(LDS_ELF_ARCH)        \
-                        -DELF_FORMAT=$(LDS_ELF_FORMAT)
+CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START)		\
+                        -DELF_ARCH=$(LDS_ELF_ARCH)	\
+                        -DELF_FORMAT=$(LDS_ELF_FORMAT)	\
+			$(LDS_EXTRA)
 extra-y := vmlinux.lds
 clean-files :=
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index f386d04a84a5..2b73dedb44ca 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -88,11 +88,8 @@ static inline void set_current(struct task_struct *task)
 
 extern void arch_switch_to(struct task_struct *to);
 
-void *_switch_to(void *prev, void *next, void *last)
+void *__switch_to(struct task_struct *from, struct task_struct *to)
 {
-	struct task_struct *from = prev;
-	struct task_struct *to = next;
-
 	to->thread.prev_sched = from;
 	set_current(to);
 
@@ -111,7 +108,6 @@ void *_switch_to(void *prev, void *next, void *last)
 	} while (current->thread.saved_task);
 
 	return current->thread.prev_sched;
-
 }
 
 void interrupt_end(void)
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 4947b319f53a..0a49ef0c2bf4 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -103,7 +103,6 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 
 void uml_setup_stubs(struct mm_struct *mm)
 {
-	struct page **pages;
 	int err, ret;
 
 	if (!skas_needs_stub)
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 4be406abeefd..36b62bc52638 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -14,6 +14,9 @@ LINK-y			+= $(call cc-option,-m32)
 
 export LDFLAGS
 
+LDS_EXTRA		:= -Ui386
+export LDS_EXTRA
+
 # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y.
 include $(srctree)/arch/x86/Makefile_32.cpu
 
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index b3b733262909..99480e55973d 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -43,7 +43,7 @@ extern void __add_wrong_size(void)
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
 			asm volatile (lock #op "b %b0, %1\n"		\
-				      : "+r" (__ret), "+m" (*(ptr))	\
+				      : "+q" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
@@ -173,7 +173,7 @@ extern void __add_wrong_size(void)
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
 			asm volatile (lock "addb %b1, %0\n"		\
-				      : "+m" (*(ptr)) : "ri" (inc)	\
+				      : "+m" (*(ptr)) : "qi" (inc)	\
 				      : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8be5f54d9360..e0544597cfe7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; };
 
 extern unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
+extern __must_check long
+strncpy_from_user(char *dst, const char __user *src, long count);
 
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 566e803cc602..8084bc73b18c 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
 	return n;
 }
 
-long __must_check strncpy_from_user(char *dst, const char __user *src,
-				    long count);
-long __must_check __strncpy_from_user(char *dst,
-				      const char __user *src, long count);
-
 /**
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 1c66d30971ad..fcd4b6f3ef02 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 }
 
-__must_check long
-strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long
-__strncpy_from_user(char *dst, const char __user *src, long count);
 __must_check long strnlen_user(const char __user *str, long n);
 __must_check long __strnlen_user(const char __user *str, long n);
 __must_check long strlen_user(const char __user *str);
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index f386dc49f988..7515cf0e1805 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -216,9 +216,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	current_thread_info()->sig_on_uaccess_error = 1;
 
 	/*
-	 * 0 is a valid user pointer (in the access_ok sense) on 32-bit and
+	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
 	 * 64-bit, so we don't need to special-case it here.  For all the
-	 * vsyscalls, 0 means "don't write anything" not "write it at
+	 * vsyscalls, NULL means "don't write anything" not "write it at
 	 * address 0".
 	 */
 	ret = -EFAULT;
@@ -247,7 +247,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 		ret = sys_getcpu((unsigned __user *)regs->di,
 				 (unsigned __user *)regs->si,
-				 0);
+				 NULL);
 		break;
 	}
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 173df38dbda5..2e88438ffd83 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -459,17 +459,17 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1);
 
 	if (pmu->version == 1) {
-		pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1;
-		return;
+		pmu->nr_arch_fixed_counters = 0;
+	} else {
+		pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
+				X86_PMC_MAX_FIXED);
+		pmu->counter_bitmask[KVM_PMC_FIXED] =
+			((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
 	}
 
-	pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
-			X86_PMC_MAX_FIXED);
-	pmu->counter_bitmask[KVM_PMC_FIXED] =
-		((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
-	pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1)
-			| (((1ull << pmu->nr_arch_fixed_counters) - 1)
-				<< X86_PMC_IDX_FIXED));
+	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+		(((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED);
+	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 52f685635766..61ebdb6390ee 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2217,9 +2217,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs)
+			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+				preempt_disable();
 				kvm_set_shared_msr(msr->index, msr->data,
 						   msr->mask);
+				preempt_enable();
+			}
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 25feb1ae71c5..b1e6c4b2e8eb 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -379,8 +379,8 @@ err_out:
 	return;
 }
 
-/* Decode moffset16/32/64 */
-static void __get_moffset(struct insn *insn)
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
 {
 	switch (insn->addr_bytes) {
 	case 2:
@@ -397,15 +397,19 @@ static void __get_moffset(struct insn *insn)
 		insn->moffset2.value = get_next(int, insn);
 		insn->moffset2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->moffset1.got = insn->moffset2.got = 1;
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v32(Iz) */
-static void __get_immv32(struct insn *insn)
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -417,14 +421,18 @@ static void __get_immv32(struct insn *insn)
 		insn->immediate.value = get_next(int, insn);
 		insn->immediate.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v64(Iv/Ov) */
-static void __get_immv(struct insn *insn)
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -441,15 +449,18 @@ static void __get_immv(struct insn *insn)
 		insn->immediate2.value = get_next(int, insn);
 		insn->immediate2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /* Decode ptr16:16/32(Ap) */
-static void __get_immptr(struct insn *insn)
+static int __get_immptr(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -462,14 +473,17 @@ static void __get_immptr(struct insn *insn)
 		break;
 	case 8:
 		/* ptr16:64 is not exist (no segment) */
-		return;
+		return 0;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate2.value = get_next(unsigned short, insn);
 	insn->immediate2.nbytes = 2;
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /**
@@ -489,7 +503,8 @@ void insn_get_immediate(struct insn *insn)
 		insn_get_displacement(insn);
 
 	if (inat_has_moffset(insn->attr)) {
-		__get_moffset(insn);
+		if (!__get_moffset(insn))
+			goto err_out;
 		goto done;
 	}
 
@@ -517,16 +532,20 @@ void insn_get_immediate(struct insn *insn)
 		insn->immediate2.nbytes = 4;
 		break;
 	case INAT_IMM_PTR:
-		__get_immptr(insn);
+		if (!__get_immptr(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD32:
-		__get_immv32(insn);
+		if (!__get_immv32(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD:
-		__get_immv(insn);
+		if (!__get_immv(insn))
+			goto err_out;
 		break;
 	default:
-		break;
+		/* Here, insn must have an immediate, but failed */
+		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
 		insn->immediate2.value = get_next(char, insn);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 97be9cb54483..d6ae30bbd7bb 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -7,6 +7,8 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 
+#include <asm/word-at-a-time.h>
+
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
  */
@@ -41,3 +43,104 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
+
+static inline unsigned long count_bytes(unsigned long mask)
+{
+	mask = (mask - 1) & ~mask;
+	mask >>= 7;
+	return count_masked_bytes(mask);
+}
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+{
+	long res = 0;
+
+	/*
+	 * Truncate 'max' to the user-specified limit, so that
+	 * we only have one limit we need to check in the loop
+	 */
+	if (max > count)
+		max = count;
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c;
+
+		/* Fall back to byte-at-a-time if we get a page fault */
+		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+			break;
+		/* This can write a few bytes past the NUL character, but that's ok */
+		*(unsigned long *)(dst+res) = c;
+		c = has_zero(c);
+		if (c)
+			return res + count_bytes(c);
+		res += sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+	while (max) {
+		char c;
+
+		if (unlikely(__get_user(c,src+res)))
+			return -EFAULT;
+		dst[res] = c;
+		if (!c)
+			return res;
+		res++;
+		max--;
+	}
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, that's ok - we got as much as the user asked for.
+	 */
+	if (res >= count)
+		return res;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's an EFAULT.
+	 */
+	return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	max_addr = current_thread_info()->addr_limit.seg;
+	src_addr = (unsigned long)src;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strncpy_from_user(dst, src, count, max);
+	}
+	return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index d9b094ca7aaa..ef2a6a5d78e3 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -33,93 +33,6 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 	__movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n))
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst, src, count, res)			   \
-do {									   \
-	int __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testl %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decl %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subl %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movl %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-/**
- * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- * Caller must check the specified block with access_ok() before calling
- * this function.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b7c2849ffb66..0d0326f388c0 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -9,55 +9,6 @@
 #include <asm/uaccess.h>
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst,src,count,res)			   \
-do {									   \
-	long __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testq %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decq %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subq %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movq %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		return __strncpy_from_user(dst, src, count);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
new file mode 100644
index 000000000000..7d01b8c56c00
--- /dev/null
+++ b/arch/x86/um/asm/barrier.h
@@ -0,0 +1,75 @@
+#ifndef _ASM_UM_BARRIER_H_
+#define _ASM_UM_BARRIER_H_
+
+#include <asm/asm.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm/cmpxchg.h>
+#include <asm/nops.h>
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#ifdef CONFIG_X86_32
+
+#define mb()	alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb()	alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb()	alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+
+#else /* CONFIG_X86_32 */
+
+#define mb()	asm volatile("mfence" : : : "memory")
+#define rmb()	asm volatile("lfence" : : : "memory")
+#define wmb()	asm volatile("sfence" : : : "memory")
+
+#endif /* CONFIG_X86_32 */
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+#define smp_rmb()	rmb()
+#else /* CONFIG_X86_PPRO_FENCE */
+#define smp_rmb()	barrier()
+#endif /* CONFIG_X86_PPRO_FENCE */
+
+#ifdef CONFIG_X86_OOSTORE
+#define smp_wmb()	wmb()
+#else /* CONFIG_X86_OOSTORE */
+#define smp_wmb()	barrier()
+#endif /* CONFIG_X86_OOSTORE */
+
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#else /* CONFIG_SMP */
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif
diff --git a/arch/x86/um/asm/system.h b/arch/x86/um/asm/system.h
deleted file mode 100644
index a459fd9b7598..000000000000
--- a/arch/x86/um/asm/system.h
+++ /dev/null
@@ -1,135 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif