Merge remote-tracking branch 'agust/next' into next

Brings some 52xx updates. Also manually merged tools/perf/perf.h.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

205 files changed, 1971 insertions, 1135 deletions

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 1e6956a..14db93e 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -445,7 +445,7 @@ struct procfs_args {
  * unhappy with OSF UFS. [CHECKME]
  */
 static int
-osf_ufs_mount(char *dirname, struct ufs_args __user *args, int flags)
+osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -465,7 +465,7 @@ osf_ufs_mount(char *dirname, struct ufs_args __user *args, int flags)
 }
 
 static int
-osf_cdfs_mount(char *dirname, struct cdfs_args __user *args, int flags)
+osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -485,7 +485,7 @@ osf_cdfs_mount(char *dirname, struct cdfs_args __user *args, int flags)
 }
 
 static int
-osf_procfs_mount(char *dirname, struct procfs_args __user *args, int flags)
+osf_procfs_mount(const char *dirname, struct procfs_args __user *args, int flags)
 {
 	struct procfs_args tmp;
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ade7e92..9759fec 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -547,6 +547,7 @@ config ARCH_KIRKWOOD
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
 	select PCI
+	select PCI_QUIRKS
 	select PLAT_ORION_LEGACY
 	help
 	  Support for the following Marvell Kirkwood series SoCs:
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index f2aa09e..9137df5 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -33,7 +33,7 @@ ifeq ($(CONFIG_XIP_KERNEL),y)
 
 $(obj)/xipImage: vmlinux FORCE
 	$(call if_changed,objcopy)
-	$(kecho) '  Kernel: $@ is ready (physical address: $(CONFIG_XIP_PHYS_ADDR))'
+	@$(kecho) '  Kernel: $@ is ready (physical address: $(CONFIG_XIP_PHYS_ADDR))'
 
 $(obj)/Image $(obj)/zImage: FORCE
 	@echo 'Kernel configured for XIP (CONFIG_XIP_KERNEL=y)'
@@ -48,14 +48,14 @@ $(obj)/xipImage: FORCE
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
-	$(kecho) '  Kernel: $@ is ready'
+	@$(kecho) '  Kernel: $@ is ready'
 
 $(obj)/compressed/vmlinux: $(obj)/Image FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
 $(obj)/zImage:	$(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
-	$(kecho) '  Kernel: $@ is ready'
+	@$(kecho) '  Kernel: $@ is ready'
 
 endif
 
@@ -90,7 +90,7 @@ fi
 $(obj)/uImage:	$(obj)/zImage FORCE
 	@$(check_for_multiple_loadaddr)
 	$(call if_changed,uimage)
-	$(kecho) '  Image $@ is ready'
+	@$(kecho) '  Image $@ is ready'
 
 $(obj)/bootp/bootp: $(obj)/zImage initrd FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/bootp $@
@@ -98,7 +98,7 @@ $(obj)/bootp/bootp: $(obj)/zImage initrd FORCE
 
 $(obj)/bootpImage: $(obj)/bootp/bootp FORCE
 	$(call if_changed,objcopy)
-	$(kecho) '  Kernel: $@ is ready'
+	@$(kecho) '  Kernel: $@ is ready'
 
 PHONY += initrd FORCE
 initrd:
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 90275f0..49ca86e 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -652,6 +652,15 @@ __setup_mmu:	sub	r3, r4, #16384		@ Page directory size
 		mov	pc, lr
 ENDPROC(__setup_mmu)
 
+@ Enable unaligned access on v6, to allow better code generation
+@ for the decompressor C code:
+__armv6_mmu_cache_on:
+		mrc	p15, 0, r0, c1, c0, 0	@ read SCTLR
+		bic	r0, r0, #2		@ A (no unaligned access fault)
+		orr	r0, r0, #1 << 22	@ U (v6 unaligned access model)
+		mcr	p15, 0, r0, c1, c0, 0	@ write SCTLR
+		b	__armv4_mmu_cache_on
+
 __arm926ejs_mmu_cache_on:
 #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
 		mov	r0, #4			@ put dcache in WT mode
@@ -694,6 +703,9 @@ __armv7_mmu_cache_on:
 		bic	r0, r0, #1 << 28	@ clear SCTLR.TRE
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x003c		@ write buffer
+		bic	r0, r0, #2		@ A (no unaligned access fault)
+		orr	r0, r0, #1 << 22	@ U (v6 unaligned access model)
+						@ (needed for ARM1176)
 #ifdef CONFIG_MMU
 #ifdef CONFIG_CPU_ENDIAN_BE8
 		orr	r0, r0, #1 << 25	@ big-endian page tables
@@ -914,7 +926,7 @@ proc_types:
 
 		.word	0x0007b000		@ ARMv6
 		.word	0x000ff000
-		W(b)	__armv4_mmu_cache_on
+		W(b)	__armv6_mmu_cache_on
 		W(b)	__armv4_mmu_cache_off
 		W(b)	__armv6_mmu_cache_flush
 
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index b1497c7..df7f227 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -73,8 +73,8 @@
 
 	pinmux: pinmux {
 		compatible = "nvidia,tegra30-pinmux";
-		reg = <0x70000868 0xd0    /* Pad control registers */
-		       0x70003000 0x3e0>; /* Mux registers */
+		reg = <0x70000868 0xd4    /* Pad control registers */
+		       0x70003000 0x3e4>; /* Mux registers */
 	};
 
 	serial@70006000 {
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index df13a3f..9d2d3ba 100644
--- a/arch/arm/common/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -162,7 +162,6 @@ static struct clock_event_device sp804_clockevent = {
 	.set_mode	= sp804_set_mode,
 	.set_next_event	= sp804_set_next_event,
 	.rating		= 300,
-	.cpumask	= cpu_all_mask,
 };
 
 static struct irqaction sp804_timer_irq = {
@@ -185,6 +184,7 @@ void __init sp804_clockevents_init(void __iomem *base, unsigned int irq,
 	clkevt_reload = DIV_ROUND_CLOSEST(rate, HZ);
 	evt->name = name;
 	evt->irq = irq;
+	evt->cpumask = cpu_possible_mask;
 
 	setup_irq(irq, &sp804_timer_irq);
 	clockevents_config_and_register(evt, rate, 0xf, 0xffffffff);
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 35c1ed8..42f042e 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -64,7 +64,7 @@ extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %1, %0"
-		     : "+Qo" (*(volatile u16 __force *)addr)
+		     : "+Q" (*(volatile u16 __force *)addr)
 		     : "r" (val));
 }
 
@@ -72,7 +72,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
 	asm volatile("ldrh %1, %0"
-		     : "+Qo" (*(volatile u16 __force *)addr),
+		     : "+Q" (*(volatile u16 __force *)addr),
 		       "=r" (val));
 	return val;
 }
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index 05b8e82..e3f7572 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -10,7 +10,5 @@
 
 extern void sched_clock_postinit(void);
 extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
-extern void setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
-		unsigned long rate);
 
 #endif
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index 6a6f1e4..301c1db 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -27,9 +27,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
@@ -51,9 +51,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
diff --git a/arch/arm/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h
index f254f65..3688fd1 100644
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@@ -18,11 +18,12 @@
 #define HWCAP_THUMBEE	(1 << 11)
 #define HWCAP_NEON	(1 << 12)
 #define HWCAP_VFPv3	(1 << 13)
-#define HWCAP_VFPv3D16	(1 << 14)
+#define HWCAP_VFPv3D16	(1 << 14)	/* also set for VFPv4-D16 */
 #define HWCAP_TLS	(1 << 15)
 #define HWCAP_VFPv4	(1 << 16)
 #define HWCAP_IDIVA	(1 << 17)
 #define HWCAP_IDIVT	(1 << 18)
+#define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
 
 
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index e21bac2..fc6692e 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -107,13 +107,6 @@ static void sched_clock_poll(unsigned long wrap_ticks)
 	update_sched_clock();
 }
 
-void __init setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
-		unsigned long rate)
-{
-	setup_sched_clock(read, bits, rate);
-	cd.needs_suspend = true;
-}
-
 void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 {
 	unsigned long r, w;
@@ -189,18 +182,15 @@ void __init sched_clock_postinit(void)
 static int sched_clock_suspend(void)
 {
 	sched_clock_poll(sched_clock_timer.data);
-	if (cd.needs_suspend)
-		cd.suspended = true;
+	cd.suspended = true;
 	return 0;
 }
 
 static void sched_clock_resume(void)
 {
-	if (cd.needs_suspend) {
-		cd.epoch_cyc = read_sched_clock();
-		cd.epoch_cyc_copy = cd.epoch_cyc;
-		cd.suspended = false;
-	}
+	cd.epoch_cyc = read_sched_clock();
+	cd.epoch_cyc_copy = cd.epoch_cyc;
+	cd.suspended = false;
 }
 
 static struct syscore_ops sched_clock_ops = {
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index 1e122bc..3cee0e6 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -68,7 +68,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 
 	/* Enable overcurrent notification */
 	for (i = 0; i < data->ports; i++) {
-		if (data->overcurrent_pin[i])
+		if (gpio_is_valid(data->overcurrent_pin[i]))
 			at91_set_gpio_input(data->overcurrent_pin[i], 1);
 	}
 
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index aa1e587..414bd85 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -72,7 +72,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 
 	/* Enable overcurrent notification */
 	for (i = 0; i < data->ports; i++) {
-		if (data->overcurrent_pin[i])
+		if (gpio_is_valid(data->overcurrent_pin[i]))
 			at91_set_gpio_input(data->overcurrent_pin[i], 1);
 	}
 
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index b948769..cd604aa 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -72,7 +72,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 
 	/* Enable overcurrent notification */
 	for (i = 0; i < data->ports; i++) {
-		if (data->overcurrent_pin[i])
+		if (gpio_is_valid(data->overcurrent_pin[i]))
 			at91_set_gpio_input(data->overcurrent_pin[i], 1);
 	}
 
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index cb85da2..9c61e59 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -78,7 +78,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 
 	/* Enable overcurrent notification */
 	for (i = 0; i < data->ports; i++) {
-		if (data->overcurrent_pin[i])
+		if (gpio_is_valid(data->overcurrent_pin[i]))
 			at91_set_gpio_input(data->overcurrent_pin[i], 1);
 	}
 
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index b159607..fcd233c 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -1841,8 +1841,8 @@ static struct resource sha_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= AT91SAM9G45_ID_AESTDESSHA,
-		.end	= AT91SAM9G45_ID_AESTDESSHA,
+		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AESTDESSHA,
+		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AESTDESSHA,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
@@ -1874,8 +1874,8 @@ static struct resource tdes_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= AT91SAM9G45_ID_AESTDESSHA,
-		.end	= AT91SAM9G45_ID_AESTDESSHA,
+		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AESTDESSHA,
+		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AESTDESSHA,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
@@ -1910,8 +1910,8 @@ static struct resource aes_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= AT91SAM9G45_ID_AESTDESSHA,
-		.end	= AT91SAM9G45_ID_AESTDESSHA,
+		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AESTDESSHA,
+		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AESTDESSHA,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index cd0c8b1..14e9947 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -713,8 +713,7 @@ static int dm644x_venc_setup_clock(enum vpbe_enc_timings_type type,
 		break;
 	case VPBE_ENC_CUSTOM_TIMINGS:
 		if (pclock <= 27000000) {
-			v |= DM644X_VPSS_MUXSEL_PLL2_MODE |
-			     DM644X_VPSS_DACCLKEN;
+			v |= DM644X_VPSS_DACCLKEN;
 			writel(v, DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL));
 		} else {
 			/*
diff --git a/arch/arm/mach-dove/include/mach/pm.h b/arch/arm/mach-dove/include/mach/pm.h
index 7bcd0df..b47f750 100644
--- a/arch/arm/mach-dove/include/mach/pm.h
+++ b/arch/arm/mach-dove/include/mach/pm.h
@@ -63,7 +63,7 @@ static inline int pmu_to_irq(int pin)
 
 static inline int irq_to_pmu(int irq)
 {
-	if (IRQ_DOVE_PMU_START < irq && irq < NR_IRQS)
+	if (IRQ_DOVE_PMU_START <= irq && irq < NR_IRQS)
 		return irq - IRQ_DOVE_PMU_START;
 
 	return -EINVAL;
diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c
index 0877115..bc4344a 100644
--- a/arch/arm/mach-dove/irq.c
+++ b/arch/arm/mach-dove/irq.c
@@ -46,8 +46,20 @@ static void pmu_irq_ack(struct irq_data *d)
 	int pin = irq_to_pmu(d->irq);
 	u32 u;
 
+	/*
+	 * The PMU mask register is not RW0C: it is RW.  This means that
+	 * the bits take whatever value is written to them; if you write
+	 * a '1', you will set the interrupt.
+	 *
+	 * Unfortunately this means there is NO race free way to clear
+	 * these interrupts.
+	 *
+	 * So, let's structure the code so that the window is as small as
+	 * possible.
+	 */
 	u = ~(1 << (pin & 31));
-	writel(u, PMU_INTERRUPT_CAUSE);
+	u &= readl_relaxed(PMU_INTERRUPT_CAUSE);
+	writel_relaxed(u, PMU_INTERRUPT_CAUSE);
 }
 
 static struct irq_chip pmu_irq_chip = {
diff --git a/arch/arm/mach-exynos/dma.c b/arch/arm/mach-exynos/dma.c
index 21d568b..87e07d6 100644
--- a/arch/arm/mach-exynos/dma.c
+++ b/arch/arm/mach-exynos/dma.c
@@ -275,6 +275,9 @@ static int __init exynos_dma_init(void)
 		exynos_pdma1_pdata.nr_valid_peri =
 			ARRAY_SIZE(exynos4210_pdma1_peri);
 		exynos_pdma1_pdata.peri_id = exynos4210_pdma1_peri;
+
+		if (samsung_rev() == EXYNOS4210_REV_0)
+			exynos_mdma1_device.res.start = EXYNOS4_PA_S_MDMA1;
 	} else if (soc_is_exynos4212() || soc_is_exynos4412()) {
 		exynos_pdma0_pdata.nr_valid_peri =
 			ARRAY_SIZE(exynos4212_pdma0_peri);
diff --git a/arch/arm/mach-exynos/include/mach/map.h b/arch/arm/mach-exynos/include/mach/map.h
index 8480849..ed4da45 100644
--- a/arch/arm/mach-exynos/include/mach/map.h
+++ b/arch/arm/mach-exynos/include/mach/map.h
@@ -90,6 +90,7 @@
 
 #define EXYNOS4_PA_MDMA0		0x10810000
 #define EXYNOS4_PA_MDMA1		0x12850000
+#define EXYNOS4_PA_S_MDMA1		0x12840000
 #define EXYNOS4_PA_PDMA0		0x12680000
 #define EXYNOS4_PA_PDMA1		0x12690000
 #define EXYNOS5_PA_MDMA0		0x10800000
diff --git a/arch/arm/mach-highbank/system.c b/arch/arm/mach-highbank/system.c
index 82c2723..86e37cd 100644
--- a/arch/arm/mach-highbank/system.c
+++ b/arch/arm/mach-highbank/system.c
@@ -28,6 +28,7 @@ void highbank_restart(char mode, const char *cmd)
 		hignbank_set_pwr_soft_reset();
 
 	scu_power_mode(scu_base_addr, SCU_PM_POWEROFF);
-	cpu_do_idle();
+	while (1)
+		cpu_do_idle();
 }
 
diff --git a/arch/arm/mach-imx/clk-gate2.c b/arch/arm/mach-imx/clk-gate2.c
index 3c1b8ff..cc49c7a 100644
--- a/arch/arm/mach-imx/clk-gate2.c
+++ b/arch/arm/mach-imx/clk-gate2.c
@@ -112,7 +112,7 @@ struct clk *clk_register_gate2(struct device *dev, const char *name,
 
 	clk = clk_register(dev, &gate->hw);
 	if (IS_ERR(clk))
-		kfree(clk);
+		kfree(gate);
 
 	return clk;
 }
diff --git a/arch/arm/mach-imx/ehci-imx25.c b/arch/arm/mach-imx/ehci-imx25.c
index 412c583..576af74 100644
--- a/arch/arm/mach-imx/ehci-imx25.c
+++ b/arch/arm/mach-imx/ehci-imx25.c
@@ -30,7 +30,7 @@
 #define MX25_H1_SIC_SHIFT	21
 #define MX25_H1_SIC_MASK	(0x3 << MX25_H1_SIC_SHIFT)
 #define MX25_H1_PP_BIT		(1 << 18)
-#define MX25_H1_PM_BIT		(1 << 8)
+#define MX25_H1_PM_BIT		(1 << 16)
 #define MX25_H1_IPPUE_UP_BIT	(1 << 7)
 #define MX25_H1_IPPUE_DOWN_BIT	(1 << 6)
 #define MX25_H1_TLL_BIT		(1 << 5)
diff --git a/arch/arm/mach-imx/ehci-imx35.c b/arch/arm/mach-imx/ehci-imx35.c
index 779e16e..2933978 100644
--- a/arch/arm/mach-imx/ehci-imx35.c
+++ b/arch/arm/mach-imx/ehci-imx35.c
@@ -30,7 +30,7 @@
 #define MX35_H1_SIC_SHIFT	21
 #define MX35_H1_SIC_MASK	(0x3 << MX35_H1_SIC_SHIFT)
 #define MX35_H1_PP_BIT		(1 << 18)
-#define MX35_H1_PM_BIT		(1 << 8)
+#define MX35_H1_PM_BIT		(1 << 16)
 #define MX35_H1_IPPUE_UP_BIT	(1 << 7)
 #define MX35_H1_IPPUE_DOWN_BIT	(1 << 6)
 #define MX35_H1_TLL_BIT		(1 << 5)
diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c
index 1694f01..6d6bde3 100644
--- a/arch/arm/mach-ixp4xx/common-pci.c
+++ b/arch/arm/mach-ixp4xx/common-pci.c
@@ -410,6 +410,7 @@ void __init ixp4xx_pci_preinit(void)
 		 * Enable the IO window to be way up high, at 0xfffffc00
 		 */
 		local_write_config(PCI_BASE_ADDRESS_5, 4, 0xfffffc01);
+		local_write_config(0x40, 4, 0x000080FF); /* No TRDY time limit */
 	} else {
 		printk("PCI: IXP4xx is target - No bus scan performed\n");
 	}
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index fdf91a1..8c0c0e2 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -67,15 +67,12 @@ static struct map_desc ixp4xx_io_desc[] __initdata = {
 		.pfn		= __phys_to_pfn(IXP4XX_PCI_CFG_BASE_PHYS),
 		.length		= IXP4XX_PCI_CFG_REGION_SIZE,
 		.type		= MT_DEVICE
-	},
-#ifdef CONFIG_DEBUG_LL
-	{	/* Debug UART mapping */
-		.virtual	= (unsigned long)IXP4XX_DEBUG_UART_BASE_VIRT,
-		.pfn		= __phys_to_pfn(IXP4XX_DEBUG_UART_BASE_PHYS),
-		.length		= IXP4XX_DEBUG_UART_REGION_SIZE,
+	}, {	/* Queue Manager */
+		.virtual	= (unsigned long)IXP4XX_QMGR_BASE_VIRT,
+		.pfn		= __phys_to_pfn(IXP4XX_QMGR_BASE_PHYS),
+		.length		= IXP4XX_QMGR_REGION_SIZE,
 		.type		= MT_DEVICE
-	}
-#endif
+	},
 };
 
 void __init ixp4xx_map_io(void)
diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c
index b800a03..53b8348 100644
--- a/arch/arm/mach-ixp4xx/goramo_mlr.c
+++ b/arch/arm/mach-ixp4xx/goramo_mlr.c
@@ -15,6 +15,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/pci.h>
+#include <asm/system_info.h>
 
 #define SLOT_ETHA		0x0B	/* IDSEL = AD21 */
 #define SLOT_ETHB		0x0C	/* IDSEL = AD20 */
@@ -329,7 +330,7 @@ static struct platform_device device_hss_tab[] = {
 };
 
 
-static struct platform_device *device_tab[6] __initdata = {
+static struct platform_device *device_tab[7] __initdata = {
 	&device_flash,		/* index 0 */
 };
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/debug-macro.S b/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
index 8c9f8d5..ff686cb 100644
--- a/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
@@ -17,8 +17,8 @@
 #else
 		mov	\rp, #0
 #endif
-                orr     \rv, \rp, #0xff000000	@ virtual
-		orr	\rv, \rv, #0x00b00000
+		orr	\rv, \rp, #0xfe000000	@ virtual
+		orr	\rv, \rv, #0x00f00000
                 orr     \rp, \rp, #0xc8000000	@ physical
                 .endm
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h b/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h
index eb68b61..c5bae9c 100644
--- a/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h
+++ b/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h
@@ -30,51 +30,43 @@
  *
  * 0x50000000	0x10000000	ioremap'd	EXP BUS
  *
- * 0x6000000	0x00004000	ioremap'd	QMgr
+ * 0xC8000000	0x00013000	0xFEF00000	On-Chip Peripherals
  *
- * 0xC0000000	0x00001000	0xffbff000	PCI CFG
+ * 0xC0000000	0x00001000	0xFEF13000	PCI CFG
  *
- * 0xC4000000	0x00001000	0xffbfe000	EXP CFG
+ * 0xC4000000	0x00001000	0xFEF14000	EXP CFG
  *
- * 0xC8000000	0x00013000	0xffbeb000	On-Chip Peripherals
+ * 0x60000000	0x00004000	0xFEF15000	QMgr
  */
 
 /*
  * Queue Manager
  */
-#define IXP4XX_QMGR_BASE_PHYS		(0x60000000)
-#define IXP4XX_QMGR_REGION_SIZE		(0x00004000)
+#define IXP4XX_QMGR_BASE_PHYS		0x60000000
+#define IXP4XX_QMGR_BASE_VIRT		IOMEM(0xFEF15000)
+#define IXP4XX_QMGR_REGION_SIZE		0x00004000
 
 /*
- * Expansion BUS Configuration registers
+ * Peripheral space, including debug UART. Must be section-aligned so that
+ * it can be used with the low-level debug code.
  */
-#define IXP4XX_EXP_CFG_BASE_PHYS	(0xC4000000)
-#define IXP4XX_EXP_CFG_BASE_VIRT	IOMEM(0xFFBFE000)
-#define IXP4XX_EXP_CFG_REGION_SIZE	(0x00001000)
+#define IXP4XX_PERIPHERAL_BASE_PHYS	0xC8000000
+#define IXP4XX_PERIPHERAL_BASE_VIRT	IOMEM(0xFEF00000)
+#define IXP4XX_PERIPHERAL_REGION_SIZE	0x00013000
 
 /*
  * PCI Config registers
  */
-#define IXP4XX_PCI_CFG_BASE_PHYS	(0xC0000000)
-#define	IXP4XX_PCI_CFG_BASE_VIRT	IOMEM(0xFFBFF000)
-#define IXP4XX_PCI_CFG_REGION_SIZE	(0x00001000)
-
-/*
- * Peripheral space
- */
-#define IXP4XX_PERIPHERAL_BASE_PHYS	(0xC8000000)
-#define IXP4XX_PERIPHERAL_BASE_VIRT	IOMEM(0xFFBEB000)
-#define IXP4XX_PERIPHERAL_REGION_SIZE	(0x00013000)
+#define IXP4XX_PCI_CFG_BASE_PHYS	0xC0000000
+#define IXP4XX_PCI_CFG_BASE_VIRT	IOMEM(0xFEF13000)
+#define IXP4XX_PCI_CFG_REGION_SIZE	0x00001000
 
 /*
- * Debug UART
- *
- * This is basically a remap of UART1 into a region that is section
- * aligned so that it * can be used with the low-level debug code.
+ * Expansion BUS Configuration registers
  */
-#define	IXP4XX_DEBUG_UART_BASE_PHYS	(0xC8000000)
-#define	IXP4XX_DEBUG_UART_BASE_VIRT	IOMEM(0xffb00000)
-#define	IXP4XX_DEBUG_UART_REGION_SIZE	(0x00001000)
+#define IXP4XX_EXP_CFG_BASE_PHYS	0xC4000000
+#define IXP4XX_EXP_CFG_BASE_VIRT	0xFEF14000
+#define IXP4XX_EXP_CFG_REGION_SIZE	0x00001000
 
 #define IXP4XX_EXP_CS0_OFFSET	0x00
 #define IXP4XX_EXP_CS1_OFFSET   0x04
diff --git a/arch/arm/mach-ixp4xx/include/mach/qmgr.h b/arch/arm/mach-ixp4xx/include/mach/qmgr.h
index 9e7cad2..4de8da5 100644
--- a/arch/arm/mach-ixp4xx/include/mach/qmgr.h
+++ b/arch/arm/mach-ixp4xx/include/mach/qmgr.h
@@ -86,7 +86,7 @@ void qmgr_release_queue(unsigned int queue);
 
 static inline void qmgr_put_entry(unsigned int queue, u32 val)
 {
-	extern struct qmgr_regs __iomem *qmgr_regs;
+	struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 #if DEBUG_QMGR
 	BUG_ON(!qmgr_queue_descs[queue]); /* not yet requested */
 
@@ -99,7 +99,7 @@ static inline void qmgr_put_entry(unsigned int queue, u32 val)
 static inline u32 qmgr_get_entry(unsigned int queue)
 {
 	u32 val;
-	extern struct qmgr_regs __iomem *qmgr_regs;
+	const struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 	val = __raw_readl(&qmgr_regs->acc[queue][0]);
 #if DEBUG_QMGR
 	BUG_ON(!qmgr_queue_descs[queue]); /* not yet requested */
@@ -112,14 +112,14 @@ static inline u32 qmgr_get_entry(unsigned int queue)
 
 static inline int __qmgr_get_stat1(unsigned int queue)
 {
-	extern struct qmgr_regs __iomem *qmgr_regs;
+	const struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 	return (__raw_readl(&qmgr_regs->stat1[queue >> 3])
 		>> ((queue & 7) << 2)) & 0xF;
 }
 
 static inline int __qmgr_get_stat2(unsigned int queue)
 {
-	extern struct qmgr_regs __iomem *qmgr_regs;
+	const struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 	BUG_ON(queue >= HALF_QUEUES);
 	return (__raw_readl(&qmgr_regs->stat2[queue >> 4])
 		>> ((queue & 0xF) << 1)) & 0x3;
@@ -145,7 +145,7 @@ static inline int qmgr_stat_empty(unsigned int queue)
  */
 static inline int qmgr_stat_below_low_watermark(unsigned int queue)
 {
-	extern struct qmgr_regs __iomem *qmgr_regs;
+	const struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 	if (queue >= HALF_QUEUES)
 		return (__raw_readl(&qmgr_regs->statne_h) >>
 			(queue - HALF_QUEUES)) & 0x01;
@@ -172,7 +172,7 @@ static inline int qmgr_stat_above_high_watermark(unsigned int queue)
  */
 static inline int qmgr_stat_full(unsigned int queue)
 {
-	extern struct qmgr_regs __iomem *qmgr_regs;
+	const struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 	if (queue >= HALF_QUEUES)
 		return (__raw_readl(&qmgr_regs->statf_h) >>
 			(queue - HALF_QUEUES)) & 0x01;
diff --git a/arch/arm/mach-ixp4xx/ixp4xx_npe.c b/arch/arm/mach-ixp4xx/ixp4xx_npe.c
index a17ed79..d4eb09a 100644
--- a/arch/arm/mach-ixp4xx/ixp4xx_npe.c
+++ b/arch/arm/mach-ixp4xx/ixp4xx_npe.c
@@ -116,7 +116,11 @@
 /* NPE mailbox_status value for reset */
 #define RESET_MBOX_STAT			0x0000F0F0
 
-const char *npe_names[] = { "NPE-A", "NPE-B", "NPE-C" };
+#define NPE_A_FIRMWARE "NPE-A"
+#define NPE_B_FIRMWARE "NPE-B"
+#define NPE_C_FIRMWARE "NPE-C"
+
+const char *npe_names[] = { NPE_A_FIRMWARE, NPE_B_FIRMWARE, NPE_C_FIRMWARE };
 
 #define print_npe(pri, npe, fmt, ...)					\
 	printk(pri "%s: " fmt, npe_name(npe), ## __VA_ARGS__)
@@ -724,6 +728,9 @@ module_exit(npe_cleanup_module);
 
 MODULE_AUTHOR("Krzysztof Halasa");
 MODULE_LICENSE("GPL v2");
+MODULE_FIRMWARE(NPE_A_FIRMWARE);
+MODULE_FIRMWARE(NPE_B_FIRMWARE);
+MODULE_FIRMWARE(NPE_C_FIRMWARE);
 
 EXPORT_SYMBOL(npe_names);
 EXPORT_SYMBOL(npe_running);
diff --git a/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c
index 852f7c9..9d1b6b7 100644
--- a/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c
+++ b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c
@@ -14,7 +14,7 @@
 #include <linux/module.h>
 #include <mach/qmgr.h>
 
-struct qmgr_regs __iomem *qmgr_regs;
+static struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
 static struct resource *mem_res;
 static spinlock_t qmgr_lock;
 static u32 used_sram_bitmap[4]; /* 128 16-dword pages */
@@ -293,12 +293,6 @@ static int qmgr_init(void)
 	if (mem_res == NULL)
 		return -EBUSY;
 
-	qmgr_regs = ioremap(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
-	if (qmgr_regs == NULL) {
-		err = -ENOMEM;
-		goto error_map;
-	}
-
 	/* reset qmgr registers */
 	for (i = 0; i < 4; i++) {
 		__raw_writel(0x33333333, &qmgr_regs->stat1[i]);
@@ -347,8 +341,6 @@ static int qmgr_init(void)
 error_irq2:
 	free_irq(IRQ_IXP4XX_QM1, NULL);
 error_irq:
-	iounmap(qmgr_regs);
-error_map:
 	release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
 	return err;
 }
@@ -359,7 +351,6 @@ static void qmgr_remove(void)
 	free_irq(IRQ_IXP4XX_QM2, NULL);
 	synchronize_irq(IRQ_IXP4XX_QM1);
 	synchronize_irq(IRQ_IXP4XX_QM2);
-	iounmap(qmgr_regs);
 	release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
 }
 
@@ -369,7 +360,6 @@ module_exit(qmgr_remove);
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Krzysztof Halasa");
 
-EXPORT_SYMBOL(qmgr_regs);
 EXPORT_SYMBOL(qmgr_set_irq);
 EXPORT_SYMBOL(qmgr_enable_irq);
 EXPORT_SYMBOL(qmgr_disable_irq);
diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c
index ec54491..74fc5a0 100644
--- a/arch/arm/mach-kirkwood/pcie.c
+++ b/arch/arm/mach-kirkwood/pcie.c
@@ -207,14 +207,19 @@ static int __init kirkwood_pcie_setup(int nr, struct pci_sys_data *sys)
 	return 1;
 }
 
+/*
+ * The root complex has a hardwired class of PCI_CLASS_MEMORY_OTHER, when it
+ * is operating as a root complex this needs to be switched to
+ * PCI_CLASS_BRIDGE_HOST or Linux will errantly try to process the BAR's on
+ * the device. Decoding setup is handled by the orion code.
+ */
 static void __devinit rc_pci_fixup(struct pci_dev *dev)
 {
-	/*
-	 * Prevent enumeration of root complex.
-	 */
 	if (dev->bus->parent == NULL && dev->devfn == 0) {
 		int i;
 
+		dev->class &= 0xff;
+		dev->class |= PCI_CLASS_BRIDGE_HOST << 8;
 		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 			dev->resource[i].start = 0;
 			dev->resource[i].end   = 0;
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 48d5e41..3785906 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -580,6 +580,11 @@ static void __init igep_wlan_bt_init(void)
 	} else
 		return;
 
+	/* Make sure that the GPIO pins are muxed correctly */
+	omap_mux_init_gpio(igep_wlan_bt_gpios[0].gpio, OMAP_PIN_OUTPUT);
+	omap_mux_init_gpio(igep_wlan_bt_gpios[1].gpio, OMAP_PIN_OUTPUT);
+	omap_mux_init_gpio(igep_wlan_bt_gpios[2].gpio, OMAP_PIN_OUTPUT);
+
 	err = gpio_request_array(igep_wlan_bt_gpios,
 				 ARRAY_SIZE(igep_wlan_bt_gpios));
 	if (err) {
diff --git a/arch/arm/mach-omap2/clockdomains44xx_data.c b/arch/arm/mach-omap2/clockdomains44xx_data.c
index b56d06b..95192a0 100644
--- a/arch/arm/mach-omap2/clockdomains44xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains44xx_data.c
@@ -359,7 +359,7 @@ static struct clockdomain iss_44xx_clkdm = {
 	.clkdm_offs	  = OMAP4430_CM2_CAM_CAM_CDOFFS,
 	.wkdep_srcs	  = iss_wkup_sleep_deps,
 	.sleepdep_srcs	  = iss_wkup_sleep_deps,
-	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+	.flags		  = CLKDM_CAN_SWSUP,
 };
 
 static struct clockdomain l3_dss_44xx_clkdm = {
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index 48daac2..84551f2 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -64,30 +64,36 @@ void __init omap_ads7846_init(int bus_num, int gpio_pendown, int gpio_debounce,
 	struct spi_board_info *spi_bi = &ads7846_spi_board_info;
 	int err;
 
-	err = gpio_request_one(gpio_pendown, GPIOF_IN, "TSPenDown");
-	if (err) {
-		pr_err("Couldn't obtain gpio for TSPenDown: %d\n", err);
-		return;
-	}
+	/*
+	 * If a board defines get_pendown_state() function, request the pendown
+	 * GPIO and set the GPIO debounce time.
+	 * If a board does not define the get_pendown_state() function, then
+	 * the ads7846 driver will setup the pendown GPIO itself.
+	 */
+	if (board_pdata && board_pdata->get_pendown_state) {
+		err = gpio_request_one(gpio_pendown, GPIOF_IN, "TSPenDown");
+		if (err) {
+			pr_err("Couldn't obtain gpio for TSPenDown: %d\n", err);
+			return;
+		}
 
-	if (gpio_debounce)
-		gpio_set_debounce(gpio_pendown, gpio_debounce);
+		if (gpio_debounce)
+			gpio_set_debounce(gpio_pendown, gpio_debounce);
+
+		gpio_export(gpio_pendown, 0);
+	}
 
 	spi_bi->bus_num	= bus_num;
 	spi_bi->irq	= gpio_to_irq(gpio_pendown);
 
+	ads7846_config.gpio_pendown = gpio_pendown;
+
 	if (board_pdata) {
 		board_pdata->gpio_pendown = gpio_pendown;
+		board_pdata->gpio_pendown_debounce = gpio_debounce;
 		spi_bi->platform_data = board_pdata;
-		if (board_pdata->get_pendown_state)
-			gpio_export(gpio_pendown, 0);
-	} else {
-		ads7846_config.gpio_pendown = gpio_pendown;
 	}
 
-	if (!board_pdata || (board_pdata && !board_pdata->get_pendown_state))
-		gpio_free(gpio_pendown);
-
 	spi_register_board_info(&ads7846_spi_board_info, 1);
 }
 #else
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index cba60e0..c72b5a7 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -19,6 +19,7 @@
 #include <linux/of.h>
 #include <linux/pinctrl/machine.h>
 #include <linux/platform_data/omap4-keypad.h>
+#include <linux/platform_data/omap_ocp2scp.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
@@ -613,6 +614,83 @@ static void omap_init_vout(void)
 static inline void omap_init_vout(void) {}
 #endif
 
+#if defined(CONFIG_OMAP_OCP2SCP) || defined(CONFIG_OMAP_OCP2SCP_MODULE)
+static int count_ocp2scp_devices(struct omap_ocp2scp_dev *ocp2scp_dev)
+{
+	int cnt	= 0;
+
+	while (ocp2scp_dev->drv_name != NULL) {
+		cnt++;
+		ocp2scp_dev++;
+	}
+
+	return cnt;
+}
+
+static void omap_init_ocp2scp(void)
+{
+	struct omap_hwmod	*oh;
+	struct platform_device	*pdev;
+	int			bus_id = -1, dev_cnt = 0, i;
+	struct omap_ocp2scp_dev	*ocp2scp_dev;
+	const char		*oh_name, *name;
+	struct omap_ocp2scp_platform_data *pdata;
+
+	if (!cpu_is_omap44xx())
+		return;
+
+	oh_name = "ocp2scp_usb_phy";
+	name	= "omap-ocp2scp";
+
+	oh = omap_hwmod_lookup(oh_name);
+	if (!oh) {
+		pr_err("%s: could not find omap_hwmod for %s\n", __func__,
+								oh_name);
+		return;
+	}
+
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		pr_err("%s: No memory for ocp2scp pdata\n", __func__);
+		return;
+	}
+
+	ocp2scp_dev = oh->dev_attr;
+	dev_cnt = count_ocp2scp_devices(ocp2scp_dev);
+
+	if (!dev_cnt) {
+		pr_err("%s: No devices connected to ocp2scp\n", __func__);
+		kfree(pdata);
+		return;
+	}
+
+	pdata->devices = kzalloc(sizeof(struct omap_ocp2scp_dev *)
+					* dev_cnt, GFP_KERNEL);
+	if (!pdata->devices) {
+		pr_err("%s: No memory for ocp2scp pdata devices\n", __func__);
+		kfree(pdata);
+		return;
+	}
+
+	for (i = 0; i < dev_cnt; i++, ocp2scp_dev++)
+		pdata->devices[i] = ocp2scp_dev;
+
+	pdata->dev_cnt	= dev_cnt;
+
+	pdev = omap_device_build(name, bus_id, oh, pdata, sizeof(*pdata), NULL,
+								0, false);
+	if (IS_ERR(pdev)) {
+		pr_err("Could not build omap_device for %s %s\n",
+						name, oh_name);
+		kfree(pdata->devices);
+		kfree(pdata);
+		return;
+	}
+}
+#else
+static inline void omap_init_ocp2scp(void) { }
+#endif
+
 /*-------------------------------------------------------------------------*/
 
 static int __init omap2_init_devices(void)
@@ -640,6 +718,7 @@ static int __init omap2_init_devices(void)
 	omap_init_sham();
 	omap_init_aes();
 	omap_init_vout();
+	omap_init_ocp2scp();
 
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index b969ab1..87cc6d0 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -422,6 +422,38 @@ static int _set_softreset(struct omap_hwmod *oh, u32 *v)
 }
 
 /**
+ * _wait_softreset_complete - wait for an OCP softreset to complete
+ * @oh: struct omap_hwmod * to wait on
+ *
+ * Wait until the IP block represented by @oh reports that its OCP
+ * softreset is complete.  This can be triggered by software (see
+ * _ocp_softreset()) or by hardware upon returning from off-mode (one
+ * example is HSMMC).  Waits for up to MAX_MODULE_SOFTRESET_WAIT
+ * microseconds.  Returns the number of microseconds waited.
+ */
+static int _wait_softreset_complete(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_class_sysconfig *sysc;
+	u32 softrst_mask;
+	int c = 0;
+
+	sysc = oh->class->sysc;
+
+	if (sysc->sysc_flags & SYSS_HAS_RESET_STATUS)
+		omap_test_timeout((omap_hwmod_read(oh, sysc->syss_offs)
+				   & SYSS_RESETDONE_MASK),
+				  MAX_MODULE_SOFTRESET_WAIT, c);
+	else if (sysc->sysc_flags & SYSC_HAS_RESET_STATUS) {
+		softrst_mask = (0x1 << sysc->sysc_fields->srst_shift);
+		omap_test_timeout(!(omap_hwmod_read(oh, sysc->sysc_offs)
+				    & softrst_mask),
+				  MAX_MODULE_SOFTRESET_WAIT, c);
+	}
+
+	return c;
+}
+
+/**
  * _set_dmadisable: set OCP_SYSCONFIG.DMADISABLE bit in @v
  * @oh: struct omap_hwmod *
  *
@@ -1282,6 +1314,18 @@ static void _enable_sysc(struct omap_hwmod *oh)
 	if (!oh->class->sysc)
 		return;
 
+	/*
+	 * Wait until reset has completed, this is needed as the IP
+	 * block is reset automatically by hardware in some cases
+	 * (off-mode for example), and the drivers require the
+	 * IP to be ready when they access it
+	 */
+	if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
+		_enable_optional_clocks(oh);
+	_wait_softreset_complete(oh);
+	if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
+		_disable_optional_clocks(oh);
+
 	v = oh->_sysc_cache;
 	sf = oh->class->sysc->sysc_flags;
 
@@ -1804,7 +1848,7 @@ static int _am33xx_disable_module(struct omap_hwmod *oh)
  */
 static int _ocp_softreset(struct omap_hwmod *oh)
 {
-	u32 v, softrst_mask;
+	u32 v;
 	int c = 0;
 	int ret = 0;
 
@@ -1834,19 +1878,7 @@ static int _ocp_softreset(struct omap_hwmod *oh)
 	if (oh->class->sysc->srst_udelay)
 		udelay(oh->class->sysc->srst_udelay);
 
-	if (oh->class->sysc->sysc_flags & SYSS_HAS_RESET_STATUS)
-		omap_test_timeout((omap_hwmod_read(oh,
-						    oh->class->sysc->syss_offs)
-				   & SYSS_RESETDONE_MASK),
-				  MAX_MODULE_SOFTRESET_WAIT, c);
-	else if (oh->class->sysc->sysc_flags & SYSC_HAS_RESET_STATUS) {
-		softrst_mask = (0x1 << oh->class->sysc->sysc_fields->srst_shift);
-		omap_test_timeout(!(omap_hwmod_read(oh,
-						     oh->class->sysc->sysc_offs)
-				   & softrst_mask),
-				  MAX_MODULE_SOFTRESET_WAIT, c);
-	}
-
+	c = _wait_softreset_complete(oh);
 	if (c == MAX_MODULE_SOFTRESET_WAIT)
 		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
 			   oh->name, MAX_MODULE_SOFTRESET_WAIT);
@@ -2352,6 +2384,9 @@ static int __init _setup_reset(struct omap_hwmod *oh)
 	if (oh->_state != _HWMOD_STATE_INITIALIZED)
 		return -EINVAL;
 
+	if (oh->flags & HWMOD_EXT_OPT_MAIN_CLK)
+		return -EPERM;
+
 	if (oh->rst_lines_cnt == 0) {
 		r = _enable(oh);
 		if (r) {
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 652d028..0b1249e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -21,6 +21,7 @@
 #include <linux/io.h>
 #include <linux/platform_data/gpio-omap.h>
 #include <linux/power/smartreflex.h>
+#include <linux/platform_data/omap_ocp2scp.h>
 
 #include <plat/omap_hwmod.h>
 #include <plat/i2c.h>
@@ -2125,6 +2126,14 @@ static struct omap_hwmod omap44xx_mcpdm_hwmod = {
 	.name		= "mcpdm",
 	.class		= &omap44xx_mcpdm_hwmod_class,
 	.clkdm_name	= "abe_clkdm",
+	/*
+	 * It's suspected that the McPDM requires an off-chip main
+	 * functional clock, controlled via I2C.  This IP block is
+	 * currently reset very early during boot, before I2C is
+	 * available, so it doesn't seem that we have any choice in
+	 * the kernel other than to avoid resetting it.
+	 */
+	.flags		= HWMOD_EXT_OPT_MAIN_CLK,
 	.mpu_irqs	= omap44xx_mcpdm_irqs,
 	.sdma_reqs	= omap44xx_mcpdm_sdma_reqs,
 	.main_clk	= "mcpdm_fck",
@@ -2681,6 +2690,32 @@ static struct omap_hwmod_class omap44xx_ocp2scp_hwmod_class = {
 	.sysc	= &omap44xx_ocp2scp_sysc,
 };
 
+/* ocp2scp dev_attr */
+static struct resource omap44xx_usb_phy_and_pll_addrs[] = {
+	{
+		.name		= "usb_phy",
+		.start		= 0x4a0ad080,
+		.end		= 0x4a0ae000,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		/* XXX: Remove this once control module driver is in place */
+		.name		= "ctrl_dev",
+		.start		= 0x4a002300,
+		.end		= 0x4a002303,
+		.flags		= IORESOURCE_MEM,
+	},
+	{ }
+};
+
+static struct omap_ocp2scp_dev ocp2scp_dev_attr[] = {
+	{
+		.drv_name       = "omap-usb2",
+		.res		= omap44xx_usb_phy_and_pll_addrs,
+	},
+	{ }
+};
+
 /* ocp2scp_usb_phy */
 static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = {
 	.name		= "ocp2scp_usb_phy",
@@ -2694,6 +2729,7 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = {
 			.modulemode   = MODULEMODE_HWCTRL,
 		},
 	},
+	.dev_attr	= ocp2scp_dev_attr,
 };
 
 /*
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index 635e109..a256135 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -73,6 +73,7 @@ void __init omap4_pmic_init(const char *pmic_type,
 {
 	/* PMIC part*/
 	omap_mux_init_signal("sys_nirq1", OMAP_PIN_INPUT_PULLUP | OMAP_PIN_OFF_WAKEUPENABLE);
+	omap_mux_init_signal("fref_clk0_out.sys_drm_msecure", OMAP_PIN_OUTPUT);
 	omap_pmic_init(1, 400, pmic_type, 7 + OMAP44XX_IRQ_GIC_START, pmic_data);
 
 	/* Register additional devices on i2c1 bus if needed */
@@ -366,7 +367,7 @@ static struct regulator_init_data omap4_clk32kg_idata = {
 };
 
 static struct regulator_consumer_supply omap4_vdd1_supply[] = {
-	REGULATOR_SUPPLY("vcc", "mpu.0"),
+	REGULATOR_SUPPLY("vcc", "cpu0"),
 };
 
 static struct regulator_consumer_supply omap4_vdd2_supply[] = {
diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c
index 880249b..75878c3 100644
--- a/arch/arm/mach-omap2/vc.c
+++ b/arch/arm/mach-omap2/vc.c
@@ -264,7 +264,7 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm)
 
 	if (initialized) {
 		if (voltdm->pmic->i2c_high_speed != i2c_high_speed)
-			pr_warn("%s: I2C config for vdd_%s does not match other channels (%u).",
+			pr_warn("%s: I2C config for vdd_%s does not match other channels (%u).\n",
 				__func__, voltdm->name, i2c_high_speed);
 		return;
 	}
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 5ecbd17..e2c6391 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -28,6 +28,7 @@
 #include <linux/mfd/asic3.h>
 #include <linux/mtd/physmap.h>
 #include <linux/pda_power.h>
+#include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/gpio-regulator.h>
@@ -556,7 +557,7 @@ static struct platform_device hx4700_lcd = {
  */
 
 static struct platform_pwm_backlight_data backlight_data = {
-	.pwm_id         = 1,
+	.pwm_id         = -1,	/* Superseded by pwm_lookup */
 	.max_brightness = 200,
 	.dft_brightness = 100,
 	.pwm_period_ns  = 30923,
@@ -571,6 +572,10 @@ static struct platform_device backlight = {
 	},
 };
 
+static struct pwm_lookup hx4700_pwm_lookup[] = {
+	PWM_LOOKUP("pxa27x-pwm.1", 0, "pwm-backlight", NULL),
+};
+
 /*
  * USB "Transceiver"
  */
@@ -872,6 +877,7 @@ static void __init hx4700_init(void)
 	pxa_set_stuart_info(NULL);
 
 	platform_add_devices(devices, ARRAY_SIZE(devices));
+	pwm_add_table(hx4700_pwm_lookup, ARRAY_SIZE(hx4700_pwm_lookup));
 
 	pxa_set_ficp_info(&ficp_info);
 	pxa27x_set_i2c_power_info(NULL);
diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c
index 438f02f..842596d 100644
--- a/arch/arm/mach-pxa/spitz_pm.c
+++ b/arch/arm/mach-pxa/spitz_pm.c
@@ -86,10 +86,7 @@ static void spitz_discharge1(int on)
 	gpio_set_value(SPITZ_GPIO_LED_GREEN, on);
 }
 
-static unsigned long gpio18_config[] = {
-	GPIO18_RDY,
-	GPIO18_GPIO,
-};
+static unsigned long gpio18_config = GPIO18_GPIO;
 
 static void spitz_presuspend(void)
 {
@@ -112,7 +109,7 @@ static void spitz_presuspend(void)
 	PGSR3 &= ~SPITZ_GPIO_G3_STROBE_BIT;
 	PGSR2 |= GPIO_bit(SPITZ_GPIO_KEY_STROBE0);
 
-	pxa2xx_mfp_config(&gpio18_config[0], 1);
+	pxa2xx_mfp_config(&gpio18_config, 1);
 	gpio_request_one(18, GPIOF_OUT_INIT_HIGH, "Unknown");
 	gpio_free(18);
 
@@ -131,7 +128,6 @@ static void spitz_presuspend(void)
 
 static void spitz_postsuspend(void)
 {
-	pxa2xx_mfp_config(&gpio18_config[1], 1);
 }
 
 static int spitz_should_wakeup(unsigned int resume_on_alarm)
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 023f4437..b820eda 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -745,7 +745,7 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
-	union offset_union offset;
+	union offset_union uninitialized_var(offset);
 	unsigned long instr = 0, instrptr;
 	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
 	unsigned int type;
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 86b8b48..09c5233 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -89,7 +89,7 @@ ENTRY(cpu_v6_dcache_clean_area)
 	mov	pc, lr
 
 /*
- *	cpu_arm926_switch_mm(pgd_phys, tsk)
+ *	cpu_v6_switch_mm(pgd_phys, tsk)
  *
  *	Set the translation table base pointer to be pgd_phys
  *
diff --git a/arch/arm/plat-omap/i2c.c b/arch/arm/plat-omap/i2c.c
index a5683a8..6013831 100644
--- a/arch/arm/plat-omap/i2c.c
+++ b/arch/arm/plat-omap/i2c.c
@@ -26,12 +26,14 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
+#include <linux/i2c-omap.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/clk.h>
 
 #include <mach/irqs.h>
 #include <plat/i2c.h>
+#include <plat/omap-pm.h>
 #include <plat/omap_device.h>
 
 #define OMAP_I2C_SIZE		0x3f
@@ -127,6 +129,16 @@ static inline int omap1_i2c_add_bus(int bus_id)
 
 
 #ifdef CONFIG_ARCH_OMAP2PLUS
+/*
+ * XXX This function is a temporary compatibility wrapper - only
+ * needed until the I2C driver can be converted to call
+ * omap_pm_set_max_dev_wakeup_lat() and handle a return code.
+ */
+static void omap_pm_set_max_mpu_wakeup_lat_compat(struct device *dev, long t)
+{
+	omap_pm_set_max_mpu_wakeup_lat(dev, t);
+}
+
 static inline int omap2_i2c_add_bus(int bus_id)
 {
 	int l;
@@ -158,6 +170,15 @@ static inline int omap2_i2c_add_bus(int bus_id)
 	dev_attr = (struct omap_i2c_dev_attr *)oh->dev_attr;
 	pdata->flags = dev_attr->flags;
 
+	/*
+	 * When waiting for completion of a i2c transfer, we need to
+	 * set a wake up latency constraint for the MPU. This is to
+	 * ensure quick enough wakeup from idle, when transfer
+	 * completes.
+	 * Only omap3 has support for constraints
+	 */
+	if (cpu_is_omap34xx())
+		pdata->set_mpu_wkup_lat = omap_pm_set_max_mpu_wakeup_lat_compat;
 	pdev = omap_device_build(name, bus_id, oh, pdata,
 			sizeof(struct omap_i2c_bus_platform_data),
 			NULL, 0, 0);
diff --git a/arch/arm/plat-omap/include/plat/omap_hwmod.h b/arch/arm/plat-omap/include/plat/omap_hwmod.h
index b3349f7..1db0294 100644
--- a/arch/arm/plat-omap/include/plat/omap_hwmod.h
+++ b/arch/arm/plat-omap/include/plat/omap_hwmod.h
@@ -443,6 +443,11 @@ struct omap_hwmod_omap4_prcm {
  *     in order to complete the reset. Optional clocks will be disabled
  *     again after the reset.
  * HWMOD_16BIT_REG: Module has 16bit registers
+ * HWMOD_EXT_OPT_MAIN_CLK: The only main functional clock source for
+ *     this IP block comes from an off-chip source and is not always
+ *     enabled.  This prevents the hwmod code from being able to
+ *     enable and reset the IP block early.  XXX Eventually it should
+ *     be possible to query the clock framework for this information.
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -453,6 +458,7 @@ struct omap_hwmod_omap4_prcm {
 #define HWMOD_NO_IDLEST				(1 << 6)
 #define HWMOD_CONTROL_OPT_CLKS_IN_RESET		(1 << 7)
 #define HWMOD_16BIT_REG				(1 << 8)
+#define HWMOD_EXT_OPT_MAIN_CLK			(1 << 9)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index db98e70..0abd1c4 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -473,12 +473,13 @@ int s3c2410_dma_enqueue(enum dma_ch channel, void *id,
 		pr_debug("dma%d: %s: buffer %p queued onto non-empty channel\n",
 			 chan->number, __func__, buf);
 
-		if (chan->end == NULL)
+		if (chan->end == NULL) {
 			pr_debug("dma%d: %s: %p not empty, and chan->end==NULL?\n",
 				 chan->number, __func__, chan);
-
-		chan->end->next = buf;
-		chan->end = buf;
+		} else {
+			chan->end->next = buf;
+			chan->end = buf;
+		}
 	}
 
 	/* if necessary, update the next buffer field */
diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile
index cd60a81..32d05c8 100644
--- a/arch/arm/tools/Makefile
+++ b/arch/arm/tools/Makefile
@@ -5,6 +5,6 @@
 #
 
 include/generated/mach-types.h: $(src)/gen-mach-types $(src)/mach-types
-	$(kecho) '  Generating $@'
+	@$(kecho) '  Generating $@'
 	@mkdir -p $(dir $@)
 	$(Q)$(AWK) -f $^ > $@ || { rm -f $@; /bin/false; }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index c834b32..3b44e0d 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -701,11 +701,14 @@ static int __init vfp_init(void)
 			elf_hwcap |= HWCAP_VFPv3;
 
 			/*
-			 * Check for VFPv3 D16. CPUs in this configuration
-			 * only have 16 x 64bit registers.
+			 * Check for VFPv3 D16 and VFPv4 D16.  CPUs in
+			 * this configuration only have 16 x 64bit
+			 * registers.
 			 */
 			if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK)) == 1)
-				elf_hwcap |= HWCAP_VFPv3D16;
+				elf_hwcap |= HWCAP_VFPv3D16; /* also v4-D16 */
+			else
+				elf_hwcap |= HWCAP_VFPD32;
 		}
 #endif
 		/*
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 59bcb96..f576092 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -166,3 +166,14 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 	*pages = NULL;
 }
 EXPORT_SYMBOL_GPL(free_xenballooned_pages);
+
+/* In the hypervisor.S file. */
+EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version);
+EXPORT_SYMBOL_GPL(HYPERVISOR_console_io);
+EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
+EXPORT_SYMBOL_GPL(privcmd_call);
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index 074f5ed..71f7239 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -48,20 +48,16 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/opcodes-virt.h>
 #include <xen/interface/xen.h>
 
 
-/* HVC 0xEA1 */
-#ifdef CONFIG_THUMB2_KERNEL
-#define xen_hvc .word 0xf7e08ea1
-#else
-#define xen_hvc .word 0xe140ea71
-#endif
+#define XEN_IMM 0xEA1
 
 #define HYPERCALL_SIMPLE(hypercall)		\
 ENTRY(HYPERVISOR_##hypercall)			\
 	mov r12, #__HYPERVISOR_##hypercall;	\
-	xen_hvc;							\
+	__HVC(XEN_IMM);						\
 	mov pc, lr;							\
 ENDPROC(HYPERVISOR_##hypercall)
 
@@ -76,7 +72,7 @@ ENTRY(HYPERVISOR_##hypercall)			\
 	stmdb sp!, {r4}						\
 	ldr r4, [sp, #4]					\
 	mov r12, #__HYPERVISOR_##hypercall;	\
-	xen_hvc								\
+	__HVC(XEN_IMM);						\
 	ldm sp!, {r4}						\
 	mov pc, lr							\
 ENDPROC(HYPERVISOR_##hypercall)
@@ -100,7 +96,7 @@ ENTRY(privcmd_call)
 	mov r2, r3
 	ldr r3, [sp, #8]
 	ldr r4, [sp, #4]
-	xen_hvc
+	__HVC(XEN_IMM)
 	ldm sp!, {r4}
 	mov pc, lr
 ENDPROC(privcmd_call);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ef54a59..15ac18a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,6 +1,7 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_HARDIRQS_NO_DEPRECATED
 	select GENERIC_IOMAP
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index cf28464..07fea29 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -25,12 +25,10 @@
 #include <asm/user.h>
 
 typedef unsigned long elf_greg_t;
-typedef unsigned long elf_freg_t[3];
 
 #define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t))
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_fp elf_fpregset_t;
+typedef struct user_fpsimd_state elf_fpregset_t;
 
 #define EM_AARCH64		183
 
@@ -87,7 +85,6 @@ typedef struct user_fp elf_fpregset_t;
 #define R_AARCH64_MOVW_PREL_G2_NC	292
 #define R_AARCH64_MOVW_PREL_G3		293
 
-
 /*
  * These are used to set parameters in the core dumps.
  */
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index b42fab9..c43b4ac 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -25,9 +25,8 @@
  *  - FPSR and FPCR
  *  - 32 128-bit data registers
  *
- * Note that user_fp forms a prefix of this structure, which is relied
- * upon in the ptrace FP/SIMD accessors. struct user_fpsimd_state must
- * form a prefix of struct fpsimd_state.
+ * Note that user_fpsimd forms a prefix of this structure, which is
+ * relied upon in the ptrace FP/SIMD accessors.
  */
 struct fpsimd_state {
 	union {
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 74a2a7d..d2f05a6 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -114,7 +114,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  *  I/O port access primitives.
  */
 #define IO_SPACE_LIMIT		0xffff
-#define PCI_IOBASE		((void __iomem *)0xffffffbbfffe0000UL)
+#define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_2M))
 
 static inline u8 inb(unsigned long addr)
 {
@@ -222,12 +222,12 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_XN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
 
-#define ioremap(addr, size)		__ioremap((addr), (size), PROT_DEVICE_nGnRE)
-#define ioremap_nocache(addr, size)	__ioremap((addr), (size), PROT_DEVICE_nGnRE)
-#define ioremap_wc(addr, size)		__ioremap((addr), (size), PROT_NORMAL_NC)
+#define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
+#define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
+#define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define iounmap				__iounmap
 
 #define ARCH_HAS_IOREMAP_WC
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 0f3b458..75fd13d 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -38,7 +38,8 @@
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_NG		(_AT(pmdval_t, 1) << 11)
-#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 54)
+#define PMD_SECT_PXN		(_AT(pmdval_t, 1) << 53)
+#define PMD_SECT_UXN		(_AT(pmdval_t, 1) << 54)
 
 /*
  * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
@@ -57,7 +58,8 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
-#define PTE_XN			(_AT(pteval_t, 1) << 54)	/* XN */
+#define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
+#define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
 
 /*
  * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 8960239..14aba2d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -62,23 +62,23 @@ extern pgprot_t pgprot_default;
 
 #define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
 
-#define PAGE_NONE		_MOD_PROT(pgprot_default, PTE_NG | PTE_XN | PTE_RDONLY)
-#define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_XN)
-#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG)
-#define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_RDONLY)
-#define PAGE_READONLY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_RDONLY)
-#define PAGE_KERNEL		_MOD_PROT(pgprot_default, PTE_XN | PTE_DIRTY)
-#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_default, PTE_DIRTY)
-
-#define __PAGE_NONE		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_XN | PTE_RDONLY)
-#define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_XN)
-#define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG)
-#define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define __PAGE_COPY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_RDONLY)
-#define __PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define __PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_RDONLY)
+#define PAGE_NONE		_MOD_PROT(pgprot_default, PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define PAGE_READONLY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define PAGE_KERNEL		_MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY)
+#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY)
+
+#define __PAGE_NONE		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define __PAGE_COPY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define __PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define __PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
 
 #endif /* __ASSEMBLY__ */
 
@@ -130,10 +130,10 @@ extern struct page *empty_zero_page;
 #define pte_young(pte)		(pte_val(pte) & PTE_AF)
 #define pte_special(pte)	(pte_val(pte) & PTE_SPECIAL)
 #define pte_write(pte)		(!(pte_val(pte) & PTE_RDONLY))
-#define pte_exec(pte)		(!(pte_val(pte) & PTE_XN))
+#define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #define pte_present_exec_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_XN)) == \
+	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == \
 	 (PTE_VALID | PTE_USER))
 
 #define PTE_BIT_FUNC(fn,op) \
@@ -262,7 +262,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const pteval_t mask = PTE_USER | PTE_XN | PTE_RDONLY;
+	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5d81004..77f696c 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -43,6 +43,8 @@
 #else
 #define STACK_TOP		STACK_TOP_MAX
 #endif /* CONFIG_COMPAT */
+
+#define ARCH_LOW_ADDRESS_LIMIT	PHYS_MASK
 #endif /* __KERNEL__ */
 
 struct debug_info {
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 63f853f..68aff28 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -14,7 +14,6 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #ifdef CONFIG_COMPAT
-#define __ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 #define __ARCH_WANT_COMPAT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 6d909fa..656a6f2 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -392,7 +392,7 @@ __SYSCALL(367, sys_fanotify_init)
 __SYSCALL(368, compat_sys_fanotify_mark_wrapper)
 __SYSCALL(369, sys_prlimit64)
 __SYSCALL(370, sys_name_to_handle_at)
-__SYSCALL(371, sys_open_by_handle_at)
+__SYSCALL(371, compat_sys_open_by_handle_at)
 __SYSCALL(372, sys_clock_adjtime)
 __SYSCALL(373, sys_syncfs)
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index ecbf2d8..c76c724 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -613,17 +613,11 @@ enum armv8_pmuv3_perf_types {
 	ARMV8_PMUV3_PERFCTR_BUS_ACCESS				= 0x19,
 	ARMV8_PMUV3_PERFCTR_MEM_ERROR				= 0x1A,
 	ARMV8_PMUV3_PERFCTR_BUS_CYCLES				= 0x1D,
-
-	/*
-	 * This isn't an architected event.
-	 * We detect this event number and use the cycle counter instead.
-	 */
-	ARMV8_PMUV3_PERFCTR_CPU_CYCLES				= 0xFF,
 };
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
-	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
@@ -1106,7 +1100,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	unsigned long evtype = event->config_base & ARMV8_EVTYPE_EVENT;
 
 	/* Always place a cycle counter into the cycle counter. */
-	if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) {
+	if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) {
 		if (test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
 			return -EAGAIN;
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f22965e..e04cebd 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -310,24 +310,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
 }
 
 /*
- * Fill in the task's elfregs structure for a core dump.
- */
-int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs)
-{
-	elf_core_copy_regs(elfregs, task_pt_regs(t));
-	return 1;
-}
-
-/*
- * fill in the fpe structure for a core dump...
- */
-int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
-{
-	return 0;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-/*
  * Shuffle the argument into the correct register before calling the
  * thread function.  x1 is the thread argument, x2 is the pointer to
  * the thread function, and x3 points to the exit function.
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 226b6bf..538300f 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -211,8 +211,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	 * before we continue.
 	 */
 	set_cpu_online(cpu, true);
-	while (!cpu_active(cpu))
-		cpu_relax();
+	complete(&cpu_running);
 
 	/*
 	 * OK, it's off to the idle thread for us
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index efbf7df..4cd2893 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -80,7 +80,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 #ifdef CONFIG_ZONE_DMA32
 	/* 4GB maximum for 32-bit only capable devices */
 	max_dma32 = min(max, MAX_DMA32_PFN);
-	zone_size[ZONE_DMA32] = max_dma32 - min;
+	zone_size[ZONE_DMA32] = max(min, max_dma32) - min;
 #endif
 	zone_size[ZONE_NORMAL] = max - max_dma32;
 
diff --git a/arch/c6x/include/asm/setup.h b/arch/c6x/include/asm/setup.h
new file mode 100644
index 0000000..ecead15
--- /dev/null
+++ b/arch/c6x/include/asm/setup.h
@@ -0,0 +1,33 @@
+/*
+ *  Port on Texas Instruments TMS320C6x architecture
+ *
+ *  Copyright (C) 2004, 2009, 2010 2011 Texas Instruments Incorporated
+ *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#ifndef _ASM_C6X_SETUP_H
+#define _ASM_C6X_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+#ifndef __ASSEMBLY__
+extern char c6x_command_line[COMMAND_LINE_SIZE];
+
+extern int c6x_add_memory(phys_addr_t start, unsigned long size);
+
+extern unsigned long ram_start;
+extern unsigned long ram_end;
+
+extern int c6x_num_cores;
+extern unsigned int c6x_silicon_rev;
+extern unsigned int c6x_devstat;
+extern unsigned char c6x_fuse_mac[6];
+
+extern void machine_init(unsigned long dt_ptr);
+extern void time_init(void);
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_C6X_SETUP_H */
diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild
index c312b42..e9bc2b2 100644
--- a/arch/c6x/include/uapi/asm/Kbuild
+++ b/arch/c6x/include/uapi/asm/Kbuild
@@ -1,6 +1,8 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += kvm_para.h
+
 header-y += byteorder.h
 header-y += kvm_para.h
 header-y += ptrace.h
diff --git a/arch/c6x/include/uapi/asm/kvm_para.h b/arch/c6x/include/uapi/asm/kvm_para.h
deleted file mode 100644
index 14fab8f..0000000
--- a/arch/c6x/include/uapi/asm/kvm_para.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kvm_para.h>
diff --git a/arch/c6x/include/uapi/asm/setup.h b/arch/c6x/include/uapi/asm/setup.h
index a01e318..ad9ac97 100644
--- a/arch/c6x/include/uapi/asm/setup.h
+++ b/arch/c6x/include/uapi/asm/setup.h
@@ -1,33 +1,6 @@
-/*
- *  Port on Texas Instruments TMS320C6x architecture
- *
- *  Copyright (C) 2004, 2009, 2010 2011 Texas Instruments Incorporated
- *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-#ifndef _ASM_C6X_SETUP_H
-#define _ASM_C6X_SETUP_H
+#ifndef _UAPI_ASM_C6X_SETUP_H
+#define _UAPI_ASM_C6X_SETUP_H
 
 #define COMMAND_LINE_SIZE   1024
 
-#ifndef __ASSEMBLY__
-extern char c6x_command_line[COMMAND_LINE_SIZE];
-
-extern int c6x_add_memory(phys_addr_t start, unsigned long size);
-
-extern unsigned long ram_start;
-extern unsigned long ram_end;
-
-extern int c6x_num_cores;
-extern unsigned int c6x_silicon_rev;
-extern unsigned int c6x_devstat;
-extern unsigned char c6x_fuse_mac[6];
-
-extern void machine_init(unsigned long dt_ptr);
-extern void time_init(void);
-
-#endif /* !__ASSEMBLY__ */
-#endif /* _ASM_C6X_SETUP_H */
+#endif /* _UAPI_ASM_C6X_SETUP_H */
diff --git a/arch/c6x/kernel/entry.S b/arch/c6x/kernel/entry.S
index 5449c36..0ed6157 100644
--- a/arch/c6x/kernel/entry.S
+++ b/arch/c6x/kernel/entry.S
@@ -277,6 +277,8 @@ work_rescheduled:
  [A1]	BNOP	.S1	work_resched,5
 
 work_notifysig:
+	;; enable interrupts for do_notify_resume()
+	UNMASK_INT B2
 	B	.S2	do_notify_resume
 	LDW	.D2T1	*+SP(REGS__END+8),A6 ; syscall flag
 	ADDKPC	.S2	resume_userspace,B3,1
@@ -427,8 +429,7 @@ ENTRY(ret_from_kernel_execve)
 ENDPROC(ret_from_kernel_execve)
 
 	;;
-	;; These are the interrupt handlers, responsible for calling __do_IRQ()
-	;; int6 is used for syscalls (see _system_call entry)
+	;; These are the interrupt handlers, responsible for calling c6x_do_IRQ()
 	;;
 	.macro SAVE_ALL_INT
 	SAVE_ALL IRP,ITSR
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index b741250..df2eb4b 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -13,6 +13,7 @@ config FRV
 	select GENERIC_CPU_DEVICES
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 
 config ZONE_DMA
 	bool
diff --git a/arch/frv/boot/Makefile b/arch/frv/boot/Makefile
index 6ae3254..636d5bb 100644
--- a/arch/frv/boot/Makefile
+++ b/arch/frv/boot/Makefile
@@ -17,6 +17,8 @@ PARAMS_PHYS	 = 0x0207c000
 INITRD_PHYS	 = 0x02180000
 INITRD_VIRT	 = 0x02180000
 
+OBJCOPYFLAGS	:=-O binary -R .note -R .note.gnu.build-id -R .comment
+
 #
 # If you don't define ZRELADDR above,
 # then it defaults to ZTEXTADDR
@@ -32,18 +34,18 @@ Image: $(obj)/Image
 targets: $(obj)/Image
 
 $(obj)/Image: vmlinux FORCE
-	$(OBJCOPY) -O binary -R .note -R .comment -S vmlinux $@
+	$(OBJCOPY) $(OBJCOPYFLAGS) -S vmlinux $@
 
 #$(obj)/Image:	$(CONFIGURE) $(SYSTEM)
-#	$(OBJCOPY) -O binary -R .note -R .comment -g -S $(SYSTEM) $@
+#	$(OBJCOPY) $(OBJCOPYFLAGS) -g -S $(SYSTEM) $@
 
 bzImage: zImage
 
 zImage:	$(CONFIGURE) compressed/$(LINUX)
-	$(OBJCOPY) -O binary -R .note -R .comment -S compressed/$(LINUX) $@
+	$(OBJCOPY) $(OBJCOPYFLAGS) -S compressed/$(LINUX) $@
 
 bootpImage: bootp/bootp
-	$(OBJCOPY) -O binary -R .note -R .comment -S bootp/bootp $@
+	$(OBJCOPY) $(OBJCOPYFLAGS) -S bootp/bootp $@
 
 compressed/$(LINUX): $(LINUX) dep
 	@$(MAKE) -C compressed $(LINUX)
diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h
index 266a5b2..2358634 100644
--- a/arch/frv/include/asm/unistd.h
+++ b/arch/frv/include/asm/unistd.h
@@ -30,7 +30,6 @@
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_SYS_EXECVE
-#define __ARCH_WANT_KERNEL_EXECVE
 
 /*
  * "Conditional" syscalls
diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S
index ee0beb3..dfcd263 100644
--- a/arch/frv/kernel/entry.S
+++ b/arch/frv/kernel/entry.S
@@ -869,11 +869,6 @@ ret_from_kernel_thread:
 	call		schedule_tail
 	calll.p		@(gr21,gr0)
 	or		gr20,gr20,gr8
-	bra		sys_exit
-
-	.globl		ret_from_kernel_execve
-ret_from_kernel_execve:
-	ori		gr28,0,sp
 	bra		__syscall_exit
 
 ###################################################################################################
@@ -1080,27 +1075,10 @@ __entry_return_from_kernel_interrupt:
 	subicc		gr5,#0,gr0,icc0
 	beq		icc0,#0,__entry_return_direct
 
-__entry_preempt_need_resched:
-	ldi		@(gr15,#TI_FLAGS),gr4
-	andicc		gr4,#_TIF_NEED_RESCHED,gr0,icc0
-	beq		icc0,#1,__entry_return_direct
-
-	setlos		#PREEMPT_ACTIVE,gr5
-	sti		gr5,@(gr15,#TI_FLAGS)
-
-	andi		gr23,#~PSR_PIL,gr23
-	movgs		gr23,psr
-
-	call		schedule
-	sti		gr0,@(gr15,#TI_PRE_COUNT)
-
-	movsg		psr,gr23
-	ori		gr23,#PSR_PIL_14,gr23
-	movgs		gr23,psr
-	bra		__entry_preempt_need_resched
-#else
-	bra		__entry_return_direct
+	subcc		gr0,gr0,gr0,icc2		/* set Z and clear C */
+	call		preempt_schedule_irq
 #endif
+	bra		__entry_return_direct
 
 
 ###############################################################################
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index e1e3aa1..7e33215 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -181,6 +181,9 @@ int copy_thread(unsigned long clone_flags,
 	childregs = (struct pt_regs *)
 		(task_stack_page(p) + THREAD_SIZE - FRV_FRAME0_SIZE);
 
+	/* set up the userspace frame (the only place that the USP is stored) */
+	*childregs = *__kernel_frame0_ptr;
+
 	p->set_child_tid = p->clear_child_tid = NULL;
 
 	p->thread.frame	 = childregs;
@@ -191,10 +194,8 @@ int copy_thread(unsigned long clone_flags,
 	p->thread.frame0 = childregs;
 
 	if (unlikely(!regs)) {
-		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gr9 = usp; /* function */
 		childregs->gr8 = arg;
-		childregs->psr = PSR_S;
 		p->thread.pc = (unsigned long) ret_from_kernel_thread;
 		save_user_regs(p->thread.user);
 		return 0;
diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c
index e47857f..b99c2a7 100644
--- a/arch/frv/mb93090-mb00/pci-dma-nommu.c
+++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c
@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/pci.h>
diff --git a/arch/h8300/include/asm/cache.h b/arch/h8300/include/asm/cache.h
index c635028..05887a1 100644
--- a/arch/h8300/include/asm/cache.h
+++ b/arch/h8300/include/asm/cache.h
@@ -2,7 +2,8 @@
 #define __ARCH_H8300_CACHE_H
 
 /* bytes per L1 cache line */
-#define        L1_CACHE_BYTES  4
+#define        L1_CACHE_SHIFT  2
+#define        L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
 
 /* m68k-elf-gcc  2.95.2 doesn't like these */
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index acd5b68..082e383 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -637,7 +637,6 @@ mem_init (void)
 
 	high_memory = __va(max_low_pfn * PAGE_SIZE);
 
-	reset_zone_present_pages();
 	for_each_online_pgdat(pgdat)
 		if (pgdat->bdata->node_bootmem_map)
 			totalram_pages += free_all_bootmem_node(pgdat);
diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h
index 67e489d..2df26b5 100644
--- a/arch/m68k/include/asm/signal.h
+++ b/arch/m68k/include/asm/signal.h
@@ -41,7 +41,7 @@ struct k_sigaction {
 static inline void sigaddset(sigset_t *set, int _sig)
 {
 	asm ("bfset %0{%1,#1}"
-		: "+od" (*set)
+		: "+o" (*set)
 		: "id" ((_sig - 1) ^ 31)
 		: "cc");
 }
@@ -49,7 +49,7 @@ static inline void sigaddset(sigset_t *set, int _sig)
 static inline void sigdelset(sigset_t *set, int _sig)
 {
 	asm ("bfclr %0{%1,#1}"
-		: "+od" (*set)
+		: "+o" (*set)
 		: "id" ((_sig - 1) ^ 31)
 		: "cc");
 }
@@ -65,7 +65,7 @@ static inline int __gen_sigismember(sigset_t *set, int _sig)
 	int ret;
 	asm ("bfextu %1{%2,#1},%0"
 		: "=d" (ret)
-		: "od" (*set), "id" ((_sig-1) ^ 31)
+		: "o" (*set), "id" ((_sig-1) ^ 31)
 		: "cc");
 	return ret;
 }
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 3847e5b..3903e3d 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -111,7 +111,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 
 	/* It is more difficult to avoid calling this function than to
 	 call it and ignore errors. */
-	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->r1))
+	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->r1) == -EFAULT)
 		goto badframe;
 
 	return rval;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-l2c.c b/arch/mips/cavium-octeon/executive/cvmx-l2c.c
index d38246e..9f883bf 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-l2c.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-l2c.c
@@ -30,6 +30,7 @@
  * measurement, and debugging facilities.
  */
 
+#include <linux/irqflags.h>
 #include <asm/octeon/cvmx.h>
 #include <asm/octeon/cvmx-l2c.h>
 #include <asm/octeon/cvmx-spinlock.h>
diff --git a/arch/mips/fw/arc/misc.c b/arch/mips/fw/arc/misc.c
index 7cf80ca..f9f5307 100644
--- a/arch/mips/fw/arc/misc.c
+++ b/arch/mips/fw/arc/misc.c
@@ -11,6 +11,7 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/irqflags.h>
 
 #include <asm/bcache.h>
 
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 82ad35c..46ac73a 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -14,7 +14,6 @@
 #endif
 
 #include <linux/compiler.h>
-#include <linux/irqflags.h>
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include <asm/byteorder.h>		/* sigh ... */
@@ -44,6 +43,24 @@
 #define smp_mb__before_clear_bit()	smp_mb__before_llsc()
 #define smp_mb__after_clear_bit()	smp_llsc_mb()
 
+
+/*
+ * These are the "slower" versions of the functions and are in bitops.c.
+ * These functions call raw_local_irq_{save,restore}().
+ */
+void __mips_set_bit(unsigned long nr, volatile unsigned long *addr);
+void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr);
+void __mips_change_bit(unsigned long nr, volatile unsigned long *addr);
+int __mips_test_and_set_bit(unsigned long nr,
+			    volatile unsigned long *addr);
+int __mips_test_and_set_bit_lock(unsigned long nr,
+				 volatile unsigned long *addr);
+int __mips_test_and_clear_bit(unsigned long nr,
+			      volatile unsigned long *addr);
+int __mips_test_and_change_bit(unsigned long nr,
+			       volatile unsigned long *addr);
+
+
 /*
  * set_bit - Atomically set a bit in memory
  * @nr: the bit to set
@@ -57,7 +74,7 @@
 static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 	unsigned long temp;
 
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {
@@ -92,17 +109,8 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 			: "=&r" (temp), "+m" (*m)
 			: "ir" (1UL << bit));
 		} while (unlikely(!temp));
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		*a |= mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		__mips_set_bit(nr, addr);
 }
 
 /*
@@ -118,7 +126,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 	unsigned long temp;
 
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {
@@ -153,17 +161,8 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 			: "=&r" (temp), "+m" (*m)
 			: "ir" (~(1UL << bit)));
 		} while (unlikely(!temp));
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		*a &= ~mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		__mips_clear_bit(nr, addr);
 }
 
 /*
@@ -191,7 +190,7 @@ static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *ad
  */
 static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
@@ -220,17 +219,8 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 			: "=&r" (temp), "+m" (*m)
 			: "ir" (1UL << bit));
 		} while (unlikely(!temp));
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		*a ^= mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		__mips_change_bit(nr, addr);
 }
 
 /*
@@ -244,7 +234,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 static inline int test_and_set_bit(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 	unsigned long res;
 
 	smp_mb__before_llsc();
@@ -281,18 +271,8 @@ static inline int test_and_set_bit(unsigned long nr,
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		res = (mask & *a);
-		*a |= mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		res = __mips_test_and_set_bit(nr, addr);
 
 	smp_llsc_mb();
 
@@ -310,7 +290,7 @@ static inline int test_and_set_bit(unsigned long nr,
 static inline int test_and_set_bit_lock(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 	unsigned long res;
 
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {
@@ -345,18 +325,8 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		res = (mask & *a);
-		*a |= mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		res = __mips_test_and_set_bit_lock(nr, addr);
 
 	smp_llsc_mb();
 
@@ -373,7 +343,7 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 static inline int test_and_clear_bit(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 	unsigned long res;
 
 	smp_mb__before_llsc();
@@ -428,18 +398,8 @@ static inline int test_and_clear_bit(unsigned long nr,
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		res = (mask & *a);
-		*a &= ~mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		res = __mips_test_and_clear_bit(nr, addr);
 
 	smp_llsc_mb();
 
@@ -457,7 +417,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 static inline int test_and_change_bit(unsigned long nr,
 	volatile unsigned long *addr)
 {
-	unsigned short bit = nr & SZLONG_MASK;
+	int bit = nr & SZLONG_MASK;
 	unsigned long res;
 
 	smp_mb__before_llsc();
@@ -494,18 +454,8 @@ static inline int test_and_change_bit(unsigned long nr,
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
-	} else {
-		volatile unsigned long *a = addr;
-		unsigned long mask;
-		unsigned long flags;
-
-		a += nr >> SZLONG_LOG;
-		mask = 1UL << bit;
-		raw_local_irq_save(flags);
-		res = (mask & *a);
-		*a ^= mask;
-		raw_local_irq_restore(flags);
-	}
+	} else
+		res = __mips_test_and_change_bit(nr, addr);
 
 	smp_llsc_mb();
 
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 58277e0..3c5d146 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -290,7 +290,7 @@ struct compat_shmid64_ds {
 
 static inline int is_compat_task(void)
 {
-	return test_thread_flag(TIF_32BIT);
+	return test_thread_flag(TIF_32BIT_ADDR);
 }
 
 #endif /* _ASM_COMPAT_H */
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 29d9c23..ff2e034 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -15,6 +15,7 @@
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/irqflags.h>
 
 #include <asm/addrspace.h>
 #include <asm/bug.h>
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 309cbcd..9f3384c 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -16,83 +16,13 @@
 #include <linux/compiler.h>
 #include <asm/hazards.h>
 
-__asm__(
-	"	.macro	arch_local_irq_enable				\n"
-	"	.set	push						\n"
-	"	.set	reorder						\n"
-	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	$1, $2, 1	# SMTC - clear TCStatus.IXMT	\n"
-	"	ori	$1, 0x400					\n"
-	"	xori	$1, 0x400					\n"
-	"	mtc0	$1, $2, 1					\n"
-#elif defined(CONFIG_CPU_MIPSR2)
-	"	ei							\n"
-#else
-	"	mfc0	$1,$12						\n"
-	"	ori	$1,0x1f						\n"
-	"	xori	$1,0x1e						\n"
-	"	mtc0	$1,$12						\n"
-#endif
-	"	irq_enable_hazard					\n"
-	"	.set	pop						\n"
-	"	.endm");
+#if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_MIPS_MT_SMTC)
 
-extern void smtc_ipi_replay(void);
-
-static inline void arch_local_irq_enable(void)
-{
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC kernel needs to do a software replay of queued
-	 * IPIs, at the cost of call overhead on each local_irq_enable()
-	 */
-	smtc_ipi_replay();
-#endif
-	__asm__ __volatile__(
-		"arch_local_irq_enable"
-		: /* no outputs */
-		: /* no inputs */
-		: "memory");
-}
-
-
-/*
- * For cli() we have to insert nops to make sure that the new value
- * has actually arrived in the status register before the end of this
- * macro.
- * R4000/R4400 need three nops, the R4600 two nops and the R10000 needs
- * no nops at all.
- */
-/*
- * For TX49, operating only IE bit is not enough.
- *
- * If mfc0 $12 follows store and the mfc0 is last instruction of a
- * page and fetching the next instruction causes TLB miss, the result
- * of the mfc0 might wrongly contain EXL bit.
- *
- * ERT-TX49H2-027, ERT-TX49H3-012, ERT-TX49HL3-006, ERT-TX49H4-008
- *
- * Workaround: mask EXL bit of the result or place a nop before mfc0.
- */
 __asm__(
 	"	.macro	arch_local_irq_disable\n"
 	"	.set	push						\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	$1, $2, 1					\n"
-	"	ori	$1, 0x400					\n"
-	"	.set	noreorder					\n"
-	"	mtc0	$1, $2, 1					\n"
-#elif defined(CONFIG_CPU_MIPSR2)
 	"	di							\n"
-#else
-	"	mfc0	$1,$12						\n"
-	"	ori	$1,0x1f						\n"
-	"	xori	$1,0x1f						\n"
-	"	.set	noreorder					\n"
-	"	mtc0	$1,$12						\n"
-#endif
 	"	irq_disable_hazard					\n"
 	"	.set	pop						\n"
 	"	.endm							\n");
@@ -106,46 +36,14 @@ static inline void arch_local_irq_disable(void)
 		: "memory");
 }
 
-__asm__(
-	"	.macro	arch_local_save_flags flags			\n"
-	"	.set	push						\n"
-	"	.set	reorder						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	\\flags, $2, 1					\n"
-#else
-	"	mfc0	\\flags, $12					\n"
-#endif
-	"	.set	pop						\n"
-	"	.endm							\n");
-
-static inline unsigned long arch_local_save_flags(void)
-{
-	unsigned long flags;
-	asm volatile("arch_local_save_flags %0" : "=r" (flags));
-	return flags;
-}
 
 __asm__(
 	"	.macro	arch_local_irq_save result			\n"
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	\\result, $2, 1					\n"
-	"	ori	$1, \\result, 0x400				\n"
-	"	.set	noreorder					\n"
-	"	mtc0	$1, $2, 1					\n"
-	"	andi	\\result, \\result, 0x400			\n"
-#elif defined(CONFIG_CPU_MIPSR2)
 	"	di	\\result					\n"
 	"	andi	\\result, 1					\n"
-#else
-	"	mfc0	\\result, $12					\n"
-	"	ori	$1, \\result, 0x1f				\n"
-	"	xori	$1, 0x1f					\n"
-	"	.set	noreorder					\n"
-	"	mtc0	$1, $12						\n"
-#endif
 	"	irq_disable_hazard					\n"
 	"	.set	pop						\n"
 	"	.endm							\n");
@@ -160,61 +58,37 @@ static inline unsigned long arch_local_irq_save(void)
 	return flags;
 }
 
+
 __asm__(
 	"	.macro	arch_local_irq_restore flags			\n"
 	"	.set	push						\n"
 	"	.set	noreorder					\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"mfc0	$1, $2, 1						\n"
-	"andi	\\flags, 0x400						\n"
-	"ori	$1, 0x400						\n"
-	"xori	$1, 0x400						\n"
-	"or	\\flags, $1						\n"
-	"mtc0	\\flags, $2, 1						\n"
-#elif defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU)
+#if defined(CONFIG_IRQ_CPU)
 	/*
 	 * Slow, but doesn't suffer from a relatively unlikely race
 	 * condition we're having since days 1.
 	 */
 	"	beqz	\\flags, 1f					\n"
-	"	 di							\n"
+	"	di							\n"
 	"	ei							\n"
 	"1:								\n"
-#elif defined(CONFIG_CPU_MIPSR2)
+#else
 	/*
 	 * Fast, dangerous.  Life is fun, life is good.
 	 */
 	"	mfc0	$1, $12						\n"
 	"	ins	$1, \\flags, 0, 1				\n"
 	"	mtc0	$1, $12						\n"
-#else
-	"	mfc0	$1, $12						\n"
-	"	andi	\\flags, 1					\n"
-	"	ori	$1, 0x1f					\n"
-	"	xori	$1, 0x1f					\n"
-	"	or	\\flags, $1					\n"
-	"	mtc0	\\flags, $12					\n"
 #endif
 	"	irq_disable_hazard					\n"
 	"	.set	pop						\n"
 	"	.endm							\n");
 
-
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	unsigned long __tmp1;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC kernel needs to do a software replay of queued
-	 * IPIs, at the cost of branch and call overhead on each
-	 * local_irq_restore()
-	 */
-	if (unlikely(!(flags & 0x0400)))
-		smtc_ipi_replay();
-#endif
-
 	__asm__ __volatile__(
 		"arch_local_irq_restore\t%0"
 		: "=r" (__tmp1)
@@ -232,6 +106,75 @@ static inline void __arch_local_irq_restore(unsigned long flags)
 		: "0" (flags)
 		: "memory");
 }
+#else
+/* Functions that require preempt_{dis,en}able() are in mips-atomic.c */
+void arch_local_irq_disable(void);
+unsigned long arch_local_irq_save(void);
+void arch_local_irq_restore(unsigned long flags);
+void __arch_local_irq_restore(unsigned long flags);
+#endif /* if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_MIPS_MT_SMTC) */
+
+
+__asm__(
+	"	.macro	arch_local_irq_enable				\n"
+	"	.set	push						\n"
+	"	.set	reorder						\n"
+	"	.set	noat						\n"
+#ifdef CONFIG_MIPS_MT_SMTC
+	"	mfc0	$1, $2, 1	# SMTC - clear TCStatus.IXMT	\n"
+	"	ori	$1, 0x400					\n"
+	"	xori	$1, 0x400					\n"
+	"	mtc0	$1, $2, 1					\n"
+#elif defined(CONFIG_CPU_MIPSR2)
+	"	ei							\n"
+#else
+	"	mfc0	$1,$12						\n"
+	"	ori	$1,0x1f						\n"
+	"	xori	$1,0x1e						\n"
+	"	mtc0	$1,$12						\n"
+#endif
+	"	irq_enable_hazard					\n"
+	"	.set	pop						\n"
+	"	.endm");
+
+extern void smtc_ipi_replay(void);
+
+static inline void arch_local_irq_enable(void)
+{
+#ifdef CONFIG_MIPS_MT_SMTC
+	/*
+	 * SMTC kernel needs to do a software replay of queued
+	 * IPIs, at the cost of call overhead on each local_irq_enable()
+	 */
+	smtc_ipi_replay();
+#endif
+	__asm__ __volatile__(
+		"arch_local_irq_enable"
+		: /* no outputs */
+		: /* no inputs */
+		: "memory");
+}
+
+
+__asm__(
+	"	.macro	arch_local_save_flags flags			\n"
+	"	.set	push						\n"
+	"	.set	reorder						\n"
+#ifdef CONFIG_MIPS_MT_SMTC
+	"	mfc0	\\flags, $2, 1					\n"
+#else
+	"	mfc0	\\flags, $12					\n"
+#endif
+	"	.set	pop						\n"
+	"	.endm							\n");
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("arch_local_save_flags %0" : "=r" (flags));
+	return flags;
+}
+
 
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
@@ -245,7 +188,7 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 #endif
 }
 
-#endif
+#endif /* #ifndef __ASSEMBLY__ */
 
 /*
  * Do the CPU's IRQ-state tracing from assembly code.
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 8debe9e..18806a5 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -112,12 +112,6 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define TIF_LOAD_WATCH		25	/* If set, load watch registers */
 #define TIF_SYSCALL_TRACE	31	/* syscall trace active */
 
-#ifdef CONFIG_MIPS32_O32
-#define TIF_32BIT TIF_32BIT_REGS
-#elif defined(CONFIG_MIPS32_N32)
-#define TIF_32BIT _TIF_32BIT_ADDR
-#endif /* CONFIG_MIPS32_O32 */
-
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index a53f8ec..290dc6a 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -79,7 +79,7 @@ static struct resource data_resource = { .name = "Kernel data", };
 void __init add_memory_region(phys_t start, phys_t size, long type)
 {
 	int x = boot_mem_map.nr_map;
-	struct boot_mem_map_entry *prev = boot_mem_map.map + x - 1;
+	int i;
 
 	/* Sanity check */
 	if (start + size < start) {
@@ -88,15 +88,29 @@ void __init add_memory_region(phys_t start, phys_t size, long type)
 	}
 
 	/*
-	 * Try to merge with previous entry if any.  This is far less than
-	 * perfect but is sufficient for most real world cases.
+	 * Try to merge with existing entry, if any.
 	 */
-	if (x && prev->addr + prev->size == start && prev->type == type) {
-		prev->size += size;
+	for (i = 0; i < boot_mem_map.nr_map; i++) {
+		struct boot_mem_map_entry *entry = boot_mem_map.map + i;
+		unsigned long top;
+
+		if (entry->type != type)
+			continue;
+
+		if (start + size < entry->addr)
+			continue;			/* no overlap */
+
+		if (entry->addr + entry->size < start)
+			continue;			/* no overlap */
+
+		top = max(entry->addr + entry->size, start + size);
+		entry->addr = min(entry->addr, start);
+		entry->size = top - entry->addr;
+
 		return;
 	}
 
-	if (x == BOOT_MEM_MAP_MAX) {
+	if (boot_mem_map.nr_map == BOOT_MEM_MAP_MAX) {
 		pr_err("Ooops! Too many entries in the memory map!\n");
 		return;
 	}
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index c4a82e8..eeddc58 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -2,8 +2,9 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o delay.o memcpy.o memset.o \
-	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
+lib-y	+= bitops.o csum_partial.o delay.o memcpy.o memset.o \
+	   mips-atomic.o strlen_user.o strncpy_user.o \
+	   strnlen_user.o uncached.o
 
 obj-y			+= iomap.o
 obj-$(CONFIG_PCI)	+= iomap-pci.o
diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c
new file mode 100644
index 0000000..239a9c9
--- /dev/null
+++ b/arch/mips/lib/bitops.c
@@ -0,0 +1,179 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1994-1997, 99, 2000, 06, 07 Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (c) 1999, 2000  Silicon Graphics, Inc.
+ */
+#include <linux/bitops.h>
+#include <linux/irqflags.h>
+#include <linux/export.h>
+
+
+/**
+ * __mips_set_bit - Atomically set a bit in memory.  This is called by
+ * set_bit() if it cannot find a faster solution.
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ */
+void __mips_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	*a |= mask;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__mips_set_bit);
+
+
+/**
+ * __mips_clear_bit - Clears a bit in memory.  This is called by clear_bit() if
+ * it cannot find a faster solution.
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ */
+void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	*a &= ~mask;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__mips_clear_bit);
+
+
+/**
+ * __mips_change_bit - Toggle a bit in memory.  This is called by change_bit()
+ * if it cannot find a faster solution.
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ */
+void __mips_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	*a ^= mask;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__mips_change_bit);
+
+
+/**
+ * __mips_test_and_set_bit - Set a bit and return its old value.  This is
+ * called by test_and_set_bit() if it cannot find a faster solution.
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+int __mips_test_and_set_bit(unsigned long nr,
+			    volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+	unsigned long res;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a);
+	*a |= mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_set_bit);
+
+
+/**
+ * __mips_test_and_set_bit_lock - Set a bit and return its old value.  This is
+ * called by test_and_set_bit_lock() if it cannot find a faster solution.
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+int __mips_test_and_set_bit_lock(unsigned long nr,
+				 volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+	unsigned long res;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a);
+	*a |= mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_set_bit_lock);
+
+
+/**
+ * __mips_test_and_clear_bit - Clear a bit and return its old value.  This is
+ * called by test_and_clear_bit() if it cannot find a faster solution.
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ */
+int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+	unsigned long res;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a);
+	*a &= ~mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_clear_bit);
+
+
+/**
+ * __mips_test_and_change_bit - Change a bit and return its old value.  This is
+ * called by test_and_change_bit() if it cannot find a faster solution.
+ * @nr: Bit to change
+ * @addr: Address to count from
+ */
+int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = addr;
+	unsigned bit = nr & SZLONG_MASK;
+	unsigned long mask;
+	unsigned long flags;
+	unsigned long res;
+
+	a += nr >> SZLONG_LOG;
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a);
+	*a ^= mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_change_bit);
diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c
new file mode 100644
index 0000000..cd160be
--- /dev/null
+++ b/arch/mips/lib/mips-atomic.c
@@ -0,0 +1,176 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994, 95, 96, 97, 98, 99, 2003 by Ralf Baechle
+ * Copyright (C) 1996 by Paul M. Antoine
+ * Copyright (C) 1999 Silicon Graphics
+ * Copyright (C) 2000 MIPS Technologies, Inc.
+ */
+#include <asm/irqflags.h>
+#include <asm/hazards.h>
+#include <linux/compiler.h>
+#include <linux/preempt.h>
+#include <linux/export.h>
+
+#if !defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT_SMTC)
+
+/*
+ * For cli() we have to insert nops to make sure that the new value
+ * has actually arrived in the status register before the end of this
+ * macro.
+ * R4000/R4400 need three nops, the R4600 two nops and the R10000 needs
+ * no nops at all.
+ */
+/*
+ * For TX49, operating only IE bit is not enough.
+ *
+ * If mfc0 $12 follows store and the mfc0 is last instruction of a
+ * page and fetching the next instruction causes TLB miss, the result
+ * of the mfc0 might wrongly contain EXL bit.
+ *
+ * ERT-TX49H2-027, ERT-TX49H3-012, ERT-TX49HL3-006, ERT-TX49H4-008
+ *
+ * Workaround: mask EXL bit of the result or place a nop before mfc0.
+ */
+__asm__(
+	"	.macro	arch_local_irq_disable\n"
+	"	.set	push						\n"
+	"	.set	noat						\n"
+#ifdef CONFIG_MIPS_MT_SMTC
+	"	mfc0	$1, $2, 1					\n"
+	"	ori	$1, 0x400					\n"
+	"	.set	noreorder					\n"
+	"	mtc0	$1, $2, 1					\n"
+#elif defined(CONFIG_CPU_MIPSR2)
+	/* see irqflags.h for inline function */
+#else
+	"	mfc0	$1,$12						\n"
+	"	ori	$1,0x1f						\n"
+	"	xori	$1,0x1f						\n"
+	"	.set	noreorder					\n"
+	"	mtc0	$1,$12						\n"
+#endif
+	"	irq_disable_hazard					\n"
+	"	.set	pop						\n"
+	"	.endm							\n");
+
+notrace void arch_local_irq_disable(void)
+{
+	preempt_disable();
+	__asm__ __volatile__(
+		"arch_local_irq_disable"
+		: /* no outputs */
+		: /* no inputs */
+		: "memory");
+	preempt_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_disable);
+
+
+__asm__(
+	"	.macro	arch_local_irq_save result			\n"
+	"	.set	push						\n"
+	"	.set	reorder						\n"
+	"	.set	noat						\n"
+#ifdef CONFIG_MIPS_MT_SMTC
+	"	mfc0	\\result, $2, 1					\n"
+	"	ori	$1, \\result, 0x400				\n"
+	"	.set	noreorder					\n"
+	"	mtc0	$1, $2, 1					\n"
+	"	andi	\\result, \\result, 0x400			\n"
+#elif defined(CONFIG_CPU_MIPSR2)
+	/* see irqflags.h for inline function */
+#else
+	"	mfc0	\\result, $12					\n"
+	"	ori	$1, \\result, 0x1f				\n"
+	"	xori	$1, 0x1f					\n"
+	"	.set	noreorder					\n"
+	"	mtc0	$1, $12						\n"
+#endif
+	"	irq_disable_hazard					\n"
+	"	.set	pop						\n"
+	"	.endm							\n");
+
+notrace unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+	preempt_disable();
+	asm volatile("arch_local_irq_save\t%0"
+		     : "=r" (flags)
+		     : /* no inputs */
+		     : "memory");
+	preempt_enable();
+	return flags;
+}
+EXPORT_SYMBOL(arch_local_irq_save);
+
+
+__asm__(
+	"	.macro	arch_local_irq_restore flags			\n"
+	"	.set	push						\n"
+	"	.set	noreorder					\n"
+	"	.set	noat						\n"
+#ifdef CONFIG_MIPS_MT_SMTC
+	"mfc0	$1, $2, 1						\n"
+	"andi	\\flags, 0x400						\n"
+	"ori	$1, 0x400						\n"
+	"xori	$1, 0x400						\n"
+	"or	\\flags, $1						\n"
+	"mtc0	\\flags, $2, 1						\n"
+#elif defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU)
+	/* see irqflags.h for inline function */
+#elif defined(CONFIG_CPU_MIPSR2)
+	/* see irqflags.h for inline function */
+#else
+	"	mfc0	$1, $12						\n"
+	"	andi	\\flags, 1					\n"
+	"	ori	$1, 0x1f					\n"
+	"	xori	$1, 0x1f					\n"
+	"	or	\\flags, $1					\n"
+	"	mtc0	\\flags, $12					\n"
+#endif
+	"	irq_disable_hazard					\n"
+	"	.set	pop						\n"
+	"	.endm							\n");
+
+notrace void arch_local_irq_restore(unsigned long flags)
+{
+	unsigned long __tmp1;
+
+#ifdef CONFIG_MIPS_MT_SMTC
+	/*
+	 * SMTC kernel needs to do a software replay of queued
+	 * IPIs, at the cost of branch and call overhead on each
+	 * local_irq_restore()
+	 */
+	if (unlikely(!(flags & 0x0400)))
+		smtc_ipi_replay();
+#endif
+	preempt_disable();
+	__asm__ __volatile__(
+		"arch_local_irq_restore\t%0"
+		: "=r" (__tmp1)
+		: "0" (flags)
+		: "memory");
+	preempt_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_restore);
+
+
+notrace void __arch_local_irq_restore(unsigned long flags)
+{
+	unsigned long __tmp1;
+
+	preempt_disable();
+	__asm__ __volatile__(
+		"arch_local_irq_restore\t%0"
+		: "=r" (__tmp1)
+		: "0" (flags)
+		: "memory");
+	preempt_enable();
+}
+EXPORT_SYMBOL(__arch_local_irq_restore);
+
+#endif /* !defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT_SMTC) */
diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c
index 80562b8..7473217 100644
--- a/arch/mips/mti-malta/malta-platform.c
+++ b/arch/mips/mti-malta/malta-platform.c
@@ -29,6 +29,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <asm/mips-boards/maltaint.h>
 #include <mtd/mtd-abi.h>
 
 #define SMC_PORT(base, int)						\
@@ -48,7 +49,7 @@ static struct plat_serial8250_port uart8250_data[] = {
 	SMC_PORT(0x2F8, 3),
 	{
 		.mapbase	= 0x1f000900,	/* The CBUS UART */
-		.irq		= MIPS_CPU_IRQ_BASE + 2,
+		.irq		= MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB2,
 		.uartclk	= 3686400,	/* Twice the usual clk! */
 		.iotype		= UPIO_MEM32,
 		.flags		= CBUS_UART_FLAGS,
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index 3011029..ddedc8a 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -84,7 +84,6 @@ asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_sigframe *frame = (struct rt_sigframe __user *)regs->sp;
 	sigset_t set;
-	stack_t st;
 
 	/*
 	 * Since we stacked the signal on a dword boundary,
@@ -104,11 +103,10 @@ asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 
-	if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
-		goto badframe;
 	/* It is more difficult to avoid calling this function than to
 	   call it and ignore errors.  */
-	do_sigaltstack(&st, NULL, regs->sp);
+	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
+		goto badframe;
 
 	return regs->gpr[11];
 
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index fd49aed..5dede04 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -65,7 +65,8 @@ put_sigset32(compat_sigset_t __user *up, sigset_t *set, size_t sz)
 {
 	compat_sigset_t s;
 
-	if (sz != sizeof *set) panic("put_sigset32()");
+	if (sz != sizeof *set)
+		return -EINVAL;
 	sigset_64to32(&s, set);
 
 	return copy_to_user(up, &s, sizeof s);
@@ -77,7 +78,8 @@ get_sigset32(compat_sigset_t __user *up, sigset_t *set, size_t sz)
 	compat_sigset_t s;
 	int r;
 
-	if (sz != sizeof *set) panic("put_sigset32()");
+	if (sz != sizeof *set)
+		return -EINVAL;
 
 	if ((r = copy_from_user(&s, up, sz)) == 0) {
 		sigset_32to64(set, &s);
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 7426e40..f76c108 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -73,6 +73,8 @@ static unsigned long get_shared_area(struct address_space *mapping,
 	struct vm_area_struct *vma;
 	int offset = mapping ? get_offset(mapping) : 0;
 
+	offset = (offset + (pgoff << PAGE_SHIFT)) & 0x3FF000;
+
 	addr = DCACHE_ALIGN(addr - offset) + offset;
 
 	for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 3735abd..cbf5d59 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -60,7 +60,7 @@
 	ENTRY_SAME(fork_wrapper)
 	ENTRY_SAME(read)
 	ENTRY_SAME(write)
-	ENTRY_SAME(open)		/* 5 */
+	ENTRY_COMP(open)		/* 5 */
 	ENTRY_SAME(close)
 	ENTRY_SAME(waitpid)
 	ENTRY_SAME(creat)
diff --git a/arch/powerpc/boot/dts/a3m071.dts b/arch/powerpc/boot/dts/a3m071.dts
new file mode 100644
index 0000000..877a28c
--- /dev/null
+++ b/arch/powerpc/boot/dts/a3m071.dts
@@ -0,0 +1,144 @@
+/*
+ * a3m071 board Device Tree Source
+ *
+ * Copyright 2012 Stefan Roese <sr@denx.de>
+ *
+ * Copyright (C) 2011 DENX Software Engineering GmbH
+ * Heiko Schocher <hs@denx.de>
+ *
+ * Copyright (C) 2007 Semihalf
+ * Marian Balakowicz <m8@semihalf.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "mpc5200b.dtsi"
+
+/ {
+	model = "anonymous,a3m071";
+	compatible = "anonymous,a3m071";
+
+	soc5200@f0000000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,mpc5200b-immr";
+		ranges = <0 0xf0000000 0x0000c000>;
+		reg = <0xf0000000 0x00000100>;
+		bus-frequency = <0>; /* From boot loader */
+		system-frequency = <0>; /* From boot loader */
+
+		timer@600 {
+			fsl,has-wdt;
+		};
+
+		spi@f00 {
+			status = "disabled";
+		};
+
+		usb: usb@1000 {
+			status = "disabled";
+		};
+
+		psc@2000 {
+			compatible = "fsl,mpc5200b-psc-uart","fsl,mpc5200-psc-uart";
+			reg = <0x2000 0x100>;
+			interrupts = <2 1 0>;
+		};
+
+		psc@2200 {
+			status = "disabled";
+		};
+
+		psc@2400 {
+			status = "disabled";
+		};
+
+		psc@2600 {
+			status = "disabled";
+		};
+
+		psc@2800 {
+			status = "disabled";
+		};
+
+		psc@2c00 {		// PSC6
+			compatible = "fsl,mpc5200b-psc-uart","fsl,mpc5200-psc-uart";
+			reg = <0x2c00 0x100>;
+			interrupts = <2 4 0>;
+		};
+
+		ethernet@3000 {
+			phy-handle = <&phy0>;
+		};
+
+		mdio@3000 {
+			phy0: ethernet-phy@3 {
+				reg = <0x03>;
+			};
+		};
+
+		ata@3a00 {
+			status = "disabled";
+		};
+
+		i2c@3d00 {
+			status = "disabled";
+		};
+
+		i2c@3d40 {
+			status = "disabled";
+		};
+	};
+
+	localbus {
+		compatible = "fsl,mpc5200b-lpb","simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0xfc000000 0x02000000
+			  3 0 0xe9000000 0x00080000
+			  5 0 0xe8000000 0x00010000>;
+
+		flash@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0 0x0 0x02000000>;
+			compatible = "cfi-flash";
+			bank-width = <2>;
+			partition@0x0 {
+				label = "u-boot";
+				reg = <0x00000000 0x00040000>;
+				read-only;
+			};
+			partition@0x00040000 {
+				label = "env";
+				reg = <0x00040000 0x00020000>;
+			};
+			partition@0x00060000 {
+				label = "dtb";
+				reg = <0x00060000 0x00020000>;
+			};
+			partition@0x00080000 {
+				label = "kernel";
+				reg = <0x00080000 0x00500000>;
+			};
+			partition@0x00580000 {
+				label = "root";
+				reg = <0x00580000 0x00A80000>;
+			};
+		};
+
+		fpga@3,0 {
+			compatible = "anonymous,a3m071-fpga";
+			reg = <3 0x0 0x00080000
+			       5 0x0 0x00010000>;
+			interrupts = <0 0 3>;  /* level low */
+		};
+	};
+
+	pci@f0000d00 {
+		status = "disabled";
+	};
+};
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index b62508b..c169998 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -2,7 +2,6 @@ config PPC_MPC512x
 	bool "512x-based boards"
 	depends on 6xx
 	select FSL_SOC
-	select FB_FSL_DIU
 	select IPIC
 	select PPC_CLOCK
 	select PPC_PCI_CHOICE
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c
index dcef6ad..0a134e0 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads.c
@@ -42,7 +42,10 @@ static void __init mpc5121_ads_setup_arch(void)
 	for_each_compatible_node(np, "pci", "fsl,mpc5121-pci")
 		mpc83xx_add_bridge(np);
 #endif
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
 	mpc512x_setup_diu();
+#endif
 }
 
 static void __init mpc5121_ads_init_IRQ(void)
diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h
index 1ab6d11..c32b399 100644
--- a/arch/powerpc/platforms/512x/mpc512x.h
+++ b/arch/powerpc/platforms/512x/mpc512x.h
@@ -16,6 +16,13 @@ extern void __init mpc512x_init(void);
 extern int __init mpc5121_clk_init(void);
 void __init mpc512x_declare_of_platform_devices(void);
 extern void mpc512x_restart(char *cmd);
-extern void mpc512x_init_diu(void);
-extern void mpc512x_setup_diu(void);
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+void mpc512x_init_diu(void);
+void mpc512x_setup_diu(void);
+#else
+#define mpc512x_init_diu NULL
+#define mpc512x_setup_diu NULL
+#endif
+
 #endif				/* __MPC512X_H__ */
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index 1650e09..35f14fd 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -58,6 +58,8 @@ void mpc512x_restart(char *cmd)
 		;
 }
 
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+
 struct fsl_diu_shared_fb {
 	u8		gamma[0x300];	/* 32-bit aligned! */
 	struct diu_ad	ad0;		/* 32-bit aligned! */
@@ -66,25 +68,6 @@ struct fsl_diu_shared_fb {
 	bool		in_use;
 };
 
-u32 mpc512x_get_pixel_format(enum fsl_diu_monitor_port port,
-			     unsigned int bits_per_pixel)
-{
-	switch (bits_per_pixel) {
-	case 32:
-		return 0x88883316;
-	case 24:
-		return 0x88082219;
-	case 16:
-		return 0x65053118;
-	}
-	return 0x00000400;
-}
-
-void mpc512x_set_gamma_table(enum fsl_diu_monitor_port port,
-			     char *gamma_table_base)
-{
-}
-
 void mpc512x_set_monitor_port(enum fsl_diu_monitor_port port)
 {
 }
@@ -320,14 +303,14 @@ void __init mpc512x_setup_diu(void)
 		}
 	}
 
-	diu_ops.get_pixel_format	= mpc512x_get_pixel_format;
-	diu_ops.set_gamma_table		= mpc512x_set_gamma_table;
 	diu_ops.set_monitor_port	= mpc512x_set_monitor_port;
 	diu_ops.set_pixel_clock		= mpc512x_set_pixel_clock;
 	diu_ops.valid_monitor_port	= mpc512x_valid_monitor_port;
 	diu_ops.release_bootmem		= mpc512x_release_bootmem;
 }
 
+#endif
+
 void __init mpc512x_init_IRQ(void)
 {
 	struct device_node *np;
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index 9cf3602..792a301 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -50,6 +50,7 @@ static void __init mpc5200_simple_setup_arch(void)
 
 /* list of the supported boards */
 static const char *board[] __initdata = {
+	"anonymous,a3m071",
 	"anonymous,a4m072",
 	"anon,charon",
 	"ifm,o2d",
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
index 2351f9e..16150fa 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -578,18 +578,4 @@ static struct platform_driver mpc52xx_lpbfifo_driver = {
 	.probe = mpc52xx_lpbfifo_probe,
 	.remove = __devexit_p(mpc52xx_lpbfifo_remove),
 };
-
-/***********************************************************************
- * Module init/exit
- */
-static int __init mpc52xx_lpbfifo_init(void)
-{
-	return platform_driver_register(&mpc52xx_lpbfifo_driver);
-}
-module_init(mpc52xx_lpbfifo_init);
-
-static void __exit mpc52xx_lpbfifo_exit(void)
-{
-	platform_driver_unregister(&mpc52xx_lpbfifo_driver);
-}
-module_exit(mpc52xx_lpbfifo_exit);
+module_platform_driver(mpc52xx_lpbfifo_driver);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 5dba755..d385f39 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -96,6 +96,7 @@ config S390
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CMPXCHG_DOUBLE
+	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select VIRT_CPU_ACCOUNTING
 	select ARCH_DISCARD_MEMBLOCK
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index 55bde60..ad2b924 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -9,6 +9,8 @@
 
 #define LPM_ANYPATH 0xff
 #define __MAX_CSSID 0
+#define __MAX_SUBCHANNEL 65535
+#define __MAX_SSID 3
 
 #include <asm/scsw.h>
 
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index a34a9d6..18cd6b5 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -20,7 +20,7 @@
 #define PSW32_MASK_CC		0x00003000UL
 #define PSW32_MASK_PM		0x00000f00UL
 
-#define PSW32_MASK_USER		0x00003F00UL
+#define PSW32_MASK_USER		0x0000FF00UL
 
 #define PSW32_ADDR_AMODE	0x80000000UL
 #define PSW32_ADDR_INSN		0x7FFFFFFFUL
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index dd647c9..2d3b7cb 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -506,12 +506,15 @@ static inline int pud_bad(pud_t pud)
 
 static inline int pmd_present(pmd_t pmd)
 {
-	return (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) != 0UL;
+	unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO;
+	return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE ||
+	       !(pmd_val(pmd) & _SEGMENT_ENTRY_INV);
 }
 
 static inline int pmd_none(pmd_t pmd)
 {
-	return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) != 0UL;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) &&
+	       !(pmd_val(pmd) & _SEGMENT_ENTRY_RO);
 }
 
 static inline int pmd_large(pmd_t pmd)
@@ -1223,6 +1226,11 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define SEGMENT_NONE	__pgprot(_HPAGE_TYPE_NONE)
+#define SEGMENT_RO	__pgprot(_HPAGE_TYPE_RO)
+#define SEGMENT_RW	__pgprot(_HPAGE_TYPE_RW)
+
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
 
@@ -1242,16 +1250,15 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 
 static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 {
-	unsigned long pgprot_pmd = 0;
-
-	if (pgprot_val(pgprot) & _PAGE_INVALID) {
-		if (pgprot_val(pgprot) & _PAGE_SWT)
-			pgprot_pmd |= _HPAGE_TYPE_NONE;
-		pgprot_pmd |= _SEGMENT_ENTRY_INV;
-	}
-	if (pgprot_val(pgprot) & _PAGE_RO)
-		pgprot_pmd |= _SEGMENT_ENTRY_RO;
-	return pgprot_pmd;
+	/*
+	 * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx)
+	 * Convert to segment table entry format.
+	 */
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
+		return pgprot_val(SEGMENT_NONE);
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_RO))
+		return pgprot_val(SEGMENT_RO);
+	return pgprot_val(SEGMENT_RW);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
@@ -1269,7 +1276,9 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
-	pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO;
+	/* Do not clobber _HPAGE_TYPE_NONE pages! */
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV))
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO;
 	return pmd;
 }
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 9ca3053..9935cbd 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -8,6 +8,9 @@ struct cpu;
 
 #ifdef CONFIG_SCHED_BOOK
 
+extern unsigned char cpu_socket_id[NR_CPUS];
+#define topology_physical_package_id(cpu) (cpu_socket_id[cpu])
+
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 705588a..a5ca214 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -239,7 +239,7 @@ typedef struct
 #define PSW_MASK_EA		0x00000000UL
 #define PSW_MASK_BA		0x00000000UL
 
-#define PSW_MASK_USER		0x00003F00UL
+#define PSW_MASK_USER		0x0000FF00UL
 
 #define PSW_ADDR_AMODE		0x80000000UL
 #define PSW_ADDR_INSN		0x7FFFFFFFUL
@@ -269,7 +269,7 @@ typedef struct
 #define PSW_MASK_EA		0x0000000100000000UL
 #define PSW_MASK_BA		0x0000000080000000UL
 
-#define PSW_MASK_USER		0x00003F8180000000UL
+#define PSW_MASK_USER		0x0000FF8180000000UL
 
 #define PSW_ADDR_AMODE		0x0000000000000000UL
 #define PSW_ADDR_INSN		0xFFFFFFFFFFFFFFFFUL
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index a1e8a86..593fcc9 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -309,6 +309,10 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 		(__u64)(regs32.psw.mask & PSW32_MASK_USER) << 32 |
 		(__u64)(regs32.psw.addr & PSW32_ADDR_AMODE);
+	/* Check for invalid user address space control. */
+	if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC))
+		regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) |
+			(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN);
 	for (i = 0; i < NUM_GPRS; i++)
 		regs->gprs[i] = (__u64) regs32.gprs[i];
@@ -481,7 +485,10 @@ static int setup_frame32(int sig, struct k_sigaction *ka,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (__force __u64) frame;
-	regs->psw.mask |= PSW_MASK_BA;		/* force amode 31 */
+	/* Force 31 bit amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (__force __u64) ka->sa.sa_handler;
 
 	regs->gprs[2] = map_signal(sig);
@@ -549,7 +556,10 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (__force __u64) frame;
-	regs->psw.mask |= PSW_MASK_BA;		/* force amode 31 */
+	/* Force 31 bit amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (__u64) ka->sa.sa_handler;
 
 	regs->gprs[2] = map_signal(sig);
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index ad79b84..827e094 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -28,7 +28,7 @@ ENTRY(sys32_open_wrapper)
 	llgtr	%r2,%r2			# const char *
 	lgfr	%r3,%r3			# int
 	lgfr	%r4,%r4			# int
-	jg	sys_open		# branch to system call
+	jg	compat_sys_open		# branch to system call
 
 ENTRY(sys32_close_wrapper)
 	llgfr	%r2,%r2			# unsigned int
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index bf05389..b6506ee 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -44,6 +44,12 @@ _sclp_wait_int:
 #endif
 	mvc	.LoldpswS1-.LbaseS1(16,%r13),0(%r8)
 	mvc	0(16,%r8),0(%r9)
+#ifdef CONFIG_64BIT
+	epsw	%r6,%r7				# set current addressing mode
+	nill	%r6,0x1				# in new psw (31 or 64 bit mode)
+	nilh	%r7,0x8000
+	stm	%r6,%r7,0(%r8)
+#endif
 	lhi	%r6,0x0200			# cr mask for ext int (cr0.54)
 	ltr	%r2,%r2
 	jz	.LsetctS1
@@ -87,7 +93,7 @@ _sclp_wait_int:
 	.long	0x00080000, 0x80000000+.LwaitS1	# PSW to handle ext int
 #ifdef CONFIG_64BIT
 .LextpswS1_64:
-	.quad	0x0000000180000000, .LwaitS1	# PSW to handle ext int, 64 bit
+	.quad	0, .LwaitS1			# PSW to handle ext int, 64 bit
 #endif
 .LwaitpswS1:
 	.long	0x010a0000, 0x00000000+.LloopS1	# PSW to wait for ext int
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index c13a2a3..d1259d8 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -136,6 +136,10 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	/* Use regs->psw.mask instead of psw_user_bits to preserve PER bit. */
 	regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 		(user_sregs.regs.psw.mask & PSW_MASK_USER);
+	/* Check for invalid user address space control. */
+	if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC))
+		regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) |
+			(regs->psw.mask & ~PSW_MASK_ASC);
 	/* Check for invalid amode */
 	if (regs->psw.mask & PSW_MASK_EA)
 		regs->psw.mask |= PSW_MASK_BA;
@@ -273,7 +277,10 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (unsigned long) frame;
-	regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA;	/* 64 bit amode */
+	/* Force default amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
 
 	regs->gprs[2] = map_signal(sig);
@@ -346,7 +353,10 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (unsigned long) frame;
-	regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA;	/* 64 bit amode */
+	/* Force default amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
 
 	regs->gprs[2] = map_signal(sig);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 54d93f4..dd55f7c 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -40,6 +40,7 @@ static DEFINE_SPINLOCK(topology_lock);
 static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
+unsigned char cpu_socket_id[NR_CPUS];
 
 static struct mask_info book_info;
 cpumask_t cpu_book_map[NR_CPUS];
@@ -83,11 +84,12 @@ static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
 			cpumask_set_cpu(lcpu, &book->mask);
 			cpu_book_id[lcpu] = book->id;
 			cpumask_set_cpu(lcpu, &core->mask);
+			cpu_core_id[lcpu] = rcpu;
 			if (one_core_per_cpu) {
-				cpu_core_id[lcpu] = rcpu;
+				cpu_socket_id[lcpu] = rcpu;
 				core = core->next;
 			} else {
-				cpu_core_id[lcpu] = core->id;
+				cpu_socket_id[lcpu] = core->id;
 			}
 			smp_cpu_set_polarization(lcpu, tl_cpu->pp);
 		}
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 2d37bb8..9017a63 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -39,7 +39,7 @@ static __always_inline unsigned long follow_table(struct mm_struct *mm,
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return -0x10UL;
-	if (pmd_huge(*pmd)) {
+	if (pmd_large(*pmd)) {
 		if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO))
 			return -0x04UL;
 		return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 60acb93..1f5315d1 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -126,7 +126,7 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
 		 */
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (unlikely(pmd_huge(pmd))) {
+		if (unlikely(pmd_large(pmd))) {
 			if (!gup_huge_pmd(pmdp, pmd, addr, next,
 					  write, pages, nr))
 				return 0;
@@ -180,8 +180,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	addr = start;
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 	end = start + len;
-	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
-					(void __user *)start, len)))
+	if ((end < start) || (end > TASK_SIZE))
 		return 0;
 
 	local_irq_save(flags);
@@ -229,7 +228,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	addr = start;
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 	end = start + len;
-	if (end < start)
+	if ((end < start) || (end > TASK_SIZE))
 		goto slow_irqon;
 
 	/*
diff --git a/arch/score/kernel/signal.c b/arch/score/kernel/signal.c
index c268bbf..02353bd 100644
--- a/arch/score/kernel/signal.c
+++ b/arch/score/kernel/signal.c
@@ -148,7 +148,6 @@ score_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_sigframe __user *frame;
 	sigset_t set;
-	stack_t st;
 	int sig;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -168,12 +167,10 @@ score_rt_sigreturn(struct pt_regs *regs)
 	else if (sig)
 		force_sig(sig, current);
 
-	if (__copy_from_user(&st, &frame->rs_uc.uc_stack, sizeof(st)))
-		goto badframe;
-
 	/* It is more difficult to avoid calling this function than to
 	   call it and ignore errors.  */
-	do_sigaltstack((stack_t __user *)&st, NULL, regs->regs[0]);
+	if (do_sigaltstack(&frame->rs_uc.uc_stack, NULL, regs->regs[0]) == -EFAULT)
+		goto badframe;
 	regs->is_syscall = 0;
 
 	__asm__ __volatile__(
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index 2385381..d867cd9 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -347,7 +347,6 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3,
 {
 	struct rt_sigframe __user *frame = (struct rt_sigframe __user *) (long) REF_REG_SP;
 	sigset_t set;
-	stack_t __user st;
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -365,11 +364,10 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3,
 		goto badframe;
 	regs->pc -= 4;
 
-	if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
-		goto badframe;
 	/* It is more difficult to avoid calling this function than to
 	   call it and ignore errors.  */
-	do_sigaltstack(&st, NULL, REF_REG_SP);
+	if (do_sigaltstack(&frame->uc.uc_stack, NULL, REF_REG_SP) == -EFAULT)
+		goto badframe;
 
 	return (int) ret;
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index b6b442b..9f2edb5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -20,6 +20,7 @@ config SPARC
 	select HAVE_ARCH_TRACEHOOK
 	select SYSCTL_EXCEPTION_TRACE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select RTC_CLASS
 	select RTC_DRV_M48T59
 	select HAVE_IRQ_WORK
diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile
index 6ae1ad5..5d469d8 100644
--- a/arch/sparc/crypto/Makefile
+++ b/arch/sparc/crypto/Makefile
@@ -13,13 +13,13 @@ obj-$(CONFIG_CRYPTO_DES_SPARC64) += camellia-sparc64.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_SPARC64) += crc32c-sparc64.o
 
-sha1-sparc64-y := sha1_asm.o sha1_glue.o crop_devid.o
-sha256-sparc64-y := sha256_asm.o sha256_glue.o crop_devid.o
-sha512-sparc64-y := sha512_asm.o sha512_glue.o crop_devid.o
-md5-sparc64-y := md5_asm.o md5_glue.o crop_devid.o
+sha1-sparc64-y := sha1_asm.o sha1_glue.o
+sha256-sparc64-y := sha256_asm.o sha256_glue.o
+sha512-sparc64-y := sha512_asm.o sha512_glue.o
+md5-sparc64-y := md5_asm.o md5_glue.o
 
-aes-sparc64-y := aes_asm.o aes_glue.o crop_devid.o
-des-sparc64-y := des_asm.o des_glue.o crop_devid.o
-camellia-sparc64-y := camellia_asm.o camellia_glue.o crop_devid.o
+aes-sparc64-y := aes_asm.o aes_glue.o
+des-sparc64-y := des_asm.o des_glue.o
+camellia-sparc64-y := camellia_asm.o camellia_glue.o
 
-crc32c-sparc64-y := crc32c_asm.o crc32c_glue.o crop_devid.o
+crc32c-sparc64-y := crc32c_asm.o crc32c_glue.o
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 8f1c998..3965d1d 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -475,3 +475,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated");
 
 MODULE_ALIAS("aes");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 42905c0..62c89af 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -320,3 +320,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated");
 
 MODULE_ALIAS("aes");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c
index 0bd89ce..5162fad 100644
--- a/arch/sparc/crypto/crc32c_glue.c
+++ b/arch/sparc/crypto/crc32c_glue.c
@@ -177,3 +177,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated");
 
 MODULE_ALIAS("crc32c");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index c4940c2..41524ce 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -527,3 +527,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated");
 
 MODULE_ALIAS("des");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 603d723..09a9ea1 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -186,3 +186,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated");
 
 MODULE_ALIAS("md5");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 2bbb20b..6cd5f29 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -181,3 +181,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated");
 
 MODULE_ALIAS("sha1");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 591e656..04f555a 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -239,3 +239,5 @@ MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 op
 
 MODULE_ALIAS("sha224");
 MODULE_ALIAS("sha256");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index 486f0a2..f04d199 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -224,3 +224,5 @@ MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 op
 
 MODULE_ALIAS("sha384");
 MODULE_ALIAS("sha512");
+
+#include "crop_devid.c"
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index ce35a1c..be56a24 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -1,7 +1,7 @@
 /* atomic.h: Thankfully the V9 is at least reasonable for this
  *           stuff.
  *
- * Copyright (C) 1996, 1997, 2000 David S. Miller (davem@redhat.com)
+ * Copyright (C) 1996, 1997, 2000, 2012 David S. Miller (davem@redhat.com)
  */
 
 #ifndef __ARCH_SPARC64_ATOMIC__
@@ -106,6 +106,8 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
+extern long atomic64_dec_if_positive(atomic64_t *v);
+
 /* Atomic operations are already serializing */
 #define smp_mb__before_atomic_dec()	barrier()
 #define smp_mb__after_atomic_dec()	barrier()
diff --git a/arch/sparc/include/asm/backoff.h b/arch/sparc/include/asm/backoff.h
index db3af0d..4e02086 100644
--- a/arch/sparc/include/asm/backoff.h
+++ b/arch/sparc/include/asm/backoff.h
@@ -1,6 +1,46 @@
 #ifndef _SPARC64_BACKOFF_H
 #define _SPARC64_BACKOFF_H
 
+/* The macros in this file implement an exponential backoff facility
+ * for atomic operations.
+ *
+ * When multiple threads compete on an atomic operation, it is
+ * possible for one thread to be continually denied a successful
+ * completion of the compare-and-swap instruction.  Heavily
+ * threaded cpu implementations like Niagara can compound this
+ * problem even further.
+ *
+ * When an atomic operation fails and needs to be retried, we spin a
+ * certain number of times.  At each subsequent failure of the same
+ * operation we double the spin count, realizing an exponential
+ * backoff.
+ *
+ * When we spin, we try to use an operation that will cause the
+ * current cpu strand to block, and therefore make the core fully
+ * available to any other other runnable strands.  There are two
+ * options, based upon cpu capabilities.
+ *
+ * On all cpus prior to SPARC-T4 we do three dummy reads of the
+ * condition code register.  Each read blocks the strand for something
+ * between 40 and 50 cpu cycles.
+ *
+ * For SPARC-T4 and later we have a special "pause" instruction
+ * available.  This is implemented using writes to register %asr27.
+ * The cpu will block the number of cycles written into the register,
+ * unless a disrupting trap happens first.  SPARC-T4 specifically
+ * implements pause with a granularity of 8 cycles.  Each strand has
+ * an internal pause counter which decrements every 8 cycles.  So the
+ * chip shifts the %asr27 value down by 3 bits, and writes the result
+ * into the pause counter.  If a value smaller than 8 is written, the
+ * chip blocks for 1 cycle.
+ *
+ * To achieve the same amount of backoff as the three %ccr reads give
+ * on earlier chips, we shift the backoff value up by 7 bits.  (Three
+ * %ccr reads block for about 128 cycles, 1 << 7 == 128) We write the
+ * whole amount we want to block into the pause register, rather than
+ * loop writing 128 each time.
+ */
+
 #define BACKOFF_LIMIT	(4 * 1024)
 
 #ifdef CONFIG_SMP
@@ -11,16 +51,25 @@
 #define BACKOFF_LABEL(spin_label, continue_label) \
 	spin_label
 
-#define BACKOFF_SPIN(reg, tmp, label)	\
-	mov	reg, tmp; \
-88:	brnz,pt	tmp, 88b; \
-	 sub	tmp, 1, tmp; \
-	set	BACKOFF_LIMIT, tmp; \
-	cmp	reg, tmp; \
-	bg,pn	%xcc, label; \
-	 nop; \
-	ba,pt	%xcc, label; \
-	 sllx	reg, 1, reg;
+#define BACKOFF_SPIN(reg, tmp, label)		\
+	mov		reg, tmp;		\
+88:	rd		%ccr, %g0;		\
+	rd		%ccr, %g0;		\
+	rd		%ccr, %g0;		\
+	.section	.pause_3insn_patch,"ax";\
+	.word		88b;			\
+	sllx		tmp, 7, tmp;		\
+	wr		tmp, 0, %asr27;		\
+	clr		tmp;			\
+	.previous;				\
+	brnz,pt		tmp, 88b;		\
+	 sub		tmp, 1, tmp;		\
+	set		BACKOFF_LIMIT, tmp;	\
+	cmp		reg, tmp;		\
+	bg,pn		%xcc, label;		\
+	 nop;					\
+	ba,pt		%xcc, label;		\
+	 sllx		reg, 1, reg;
 
 #else
 
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index cef99fb..830502fe 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -232,9 +232,10 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 	struct pt_regs *regs = current_thread_info()->kregs;
 	unsigned long usp = regs->u_regs[UREG_I6];
 
-	if (!(test_thread_flag(TIF_32BIT)))
+	if (test_thread_64bit_stack(usp))
 		usp += STACK_BIAS;
-	else
+
+	if (test_thread_flag(TIF_32BIT))
 		usp &= 0xffffffffUL;
 
 	usp -= len;
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 4e5a483..721e25f 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -196,7 +196,22 @@ extern unsigned long get_wchan(struct task_struct *task);
 #define KSTK_EIP(tsk)  (task_pt_regs(tsk)->tpc)
 #define KSTK_ESP(tsk)  (task_pt_regs(tsk)->u_regs[UREG_FP])
 
-#define cpu_relax()	barrier()
+/* Please see the commentary in asm/backoff.h for a description of
+ * what these instructions are doing and how they have been choosen.
+ * To make a long story short, we are trying to yield the current cpu
+ * strand during busy loops.
+ */
+#define cpu_relax()	asm volatile("\n99:\n\t"			\
+				     "rd	%%ccr, %%g0\n\t"	\
+				     "rd	%%ccr, %%g0\n\t"	\
+				     "rd	%%ccr, %%g0\n\t"	\
+				     ".section	.pause_3insn_patch,\"ax\"\n\t"\
+				     ".word	99b\n\t"		\
+				     "wr	%%g0, 128, %%asr27\n\t"	\
+				     "nop\n\t"				\
+				     "nop\n\t"				\
+				     ".previous"			\
+				     ::: "memory")
 
 /* Prefetch support.  This is tuned for UltraSPARC-III and later.
  * UltraSPARC-I will treat these as nops, and UltraSPARC-II has
diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index c287651..67c6257 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -63,5 +63,13 @@ extern char *of_console_options;
 extern void irq_trans_init(struct device_node *dp);
 extern char *build_path_component(struct device_node *dp);
 
+/* SPARC has local implementations */
+extern int of_address_to_resource(struct device_node *dev, int index,
+				  struct resource *r);
+#define of_address_to_resource of_address_to_resource
+
+void __iomem *of_iomap(struct device_node *node, int index);
+#define of_iomap of_iomap
+
 #endif /* __KERNEL__ */
 #endif /* _SPARC_PROM_H */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 4e227663..a3fe4dc 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -259,6 +259,11 @@ static inline bool test_and_clear_restore_sigmask(void)
 
 #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
 
+#define thread32_stack_is_64bit(__SP) (((__SP) & 0x1) != 0)
+#define test_thread_64bit_stack(__SP) \
+	((test_thread_flag(TIF_32BIT) && !thread32_stack_is_64bit(__SP)) ? \
+	 false : true)
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 48f2807..71b5a67 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -372,7 +372,9 @@ etrap_spill_fixup_64bit:				\
 
 /* Normal 32bit spill */
 #define SPILL_2_GENERIC(ASI)				\
-	srl	%sp, 0, %sp;				\
+	and	%sp, 1, %g3;				\
+	brnz,pn	%g3, (. - (128 + 4));			\
+	 srl	%sp, 0, %sp;				\
 	stwa	%l0, [%sp + %g0] ASI;			\
 	mov	0x04, %g3;				\
 	stwa	%l1, [%sp + %g3] ASI;			\
@@ -398,14 +400,16 @@ etrap_spill_fixup_64bit:				\
 	stwa	%i6, [%g1 + %g0] ASI;			\
 	stwa	%i7, [%g1 + %g3] ASI;			\
 	saved;						\
-        retry; nop; nop;				\
+        retry;						\
 	b,a,pt	%xcc, spill_fixup_dax;			\
 	b,a,pt	%xcc, spill_fixup_mna;			\
 	b,a,pt	%xcc, spill_fixup;
 
 #define SPILL_2_GENERIC_ETRAP		\
 etrap_user_spill_32bit:			\
-	srl	%sp, 0, %sp;		\
+	and	%sp, 1, %g3;		\
+	brnz,pn	%g3, etrap_user_spill_64bit;	\
+	 srl	%sp, 0, %sp;		\
 	stwa	%l0, [%sp + 0x00] %asi;	\
 	stwa	%l1, [%sp + 0x04] %asi;	\
 	stwa	%l2, [%sp + 0x08] %asi;	\
@@ -427,7 +431,7 @@ etrap_user_spill_32bit:			\
 	ba,pt	%xcc, etrap_save;	\
 	 wrpr	%g1, %cwp;		\
 	nop; nop; nop; nop;		\
-	nop; nop; nop; nop;		\
+	nop; nop;			\
 	ba,a,pt	%xcc, etrap_spill_fixup_32bit; \
 	ba,a,pt	%xcc, etrap_spill_fixup_32bit; \
 	ba,a,pt	%xcc, etrap_spill_fixup_32bit;
@@ -592,7 +596,9 @@ user_rtt_fill_64bit:					\
 
 /* Normal 32bit fill */
 #define FILL_2_GENERIC(ASI)				\
-	srl	%sp, 0, %sp;				\
+	and	%sp, 1, %g3;				\
+	brnz,pn	%g3, (. - (128 + 4));			\
+	 srl	%sp, 0, %sp;				\
 	lduwa	[%sp + %g0] ASI, %l0;			\
 	mov	0x04, %g2;				\
 	mov	0x08, %g3;				\
@@ -616,14 +622,16 @@ user_rtt_fill_64bit:					\
 	lduwa	[%g1 + %g3] ASI, %i6;			\
 	lduwa	[%g1 + %g5] ASI, %i7;			\
 	restored;					\
-	retry; nop; nop; nop; nop;			\
+	retry; nop; nop;				\
 	b,a,pt	%xcc, fill_fixup_dax;			\
 	b,a,pt	%xcc, fill_fixup_mna;			\
 	b,a,pt	%xcc, fill_fixup;
 
 #define FILL_2_GENERIC_RTRAP				\
 user_rtt_fill_32bit:					\
-	srl	%sp, 0, %sp;				\
+	and	%sp, 1, %g3;				\
+	brnz,pn	%g3, user_rtt_fill_64bit;		\
+	 srl	%sp, 0, %sp;				\
 	lduwa	[%sp + 0x00] %asi, %l0;			\
 	lduwa	[%sp + 0x04] %asi, %l1;			\
 	lduwa	[%sp + 0x08] %asi, %l2;			\
@@ -643,7 +651,7 @@ user_rtt_fill_32bit:					\
 	ba,pt	%xcc, user_rtt_pre_restore;		\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
-	nop; nop; nop; nop; nop;			\
+	nop; nop; nop;					\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index 8974ef7..cac719d 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -405,8 +405,13 @@
 #define __NR_setns		337
 #define __NR_process_vm_readv	338
 #define __NR_process_vm_writev	339
+#define __NR_kern_features	340
+#define __NR_kcmp		341
 
-#define NR_syscalls		340
+#define NR_syscalls		342
+
+/* Bitmask values returned from kern_features system call.  */
+#define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
 
 #ifdef __32bit_syscall_numbers__
 /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 0c218e4..cc3c5cb 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -59,6 +59,13 @@ struct popc_6insn_patch_entry {
 extern struct popc_6insn_patch_entry __popc_6insn_patch,
 	__popc_6insn_patch_end;
 
+struct pause_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[3];
+};
+extern struct pause_patch_entry __pause_3insn_patch,
+	__pause_3insn_patch_end;
+
 extern void __init per_cpu_patch(void);
 extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
 				    struct sun4v_1insn_patch_entry *);
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index f8b6eee..87f60ee 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -56,11 +56,13 @@ static inline unsigned int leon_eirq_get(int cpu)
 static void leon_handle_ext_irq(unsigned int irq, struct irq_desc *desc)
 {
 	unsigned int eirq;
+	struct irq_bucket *p;
 	int cpu = sparc_leon3_cpuid();
 
 	eirq = leon_eirq_get(cpu);
-	if ((eirq & 0x10) && irq_map[eirq]->irq) /* bit4 tells if IRQ happened */
-		generic_handle_irq(irq_map[eirq]->irq);
+	p = irq_map[eirq];
+	if ((eirq & 0x10) && p && p->irq) /* bit4 tells if IRQ happened */
+		generic_handle_irq(p->irq);
 }
 
 /* The extended IRQ controller has been found, this function registers it */
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 885a8af..b5c38fa 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1762,15 +1762,25 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 
 	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
-		struct sparc_stackf32 *usf, sf;
 		unsigned long pc;
 
-		usf = (struct sparc_stackf32 *) ufp;
-		if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
-			break;
+		if (thread32_stack_is_64bit(ufp)) {
+			struct sparc_stackf *usf, sf;
 
-		pc = sf.callers_pc;
-		ufp = (unsigned long)sf.fp;
+			ufp += STACK_BIAS;
+			usf = (struct sparc_stackf *) ufp;
+			if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
+				break;
+			pc = sf.callers_pc & 0xffffffff;
+			ufp = ((unsigned long) sf.fp) & 0xffffffff;
+		} else {
+			struct sparc_stackf32 *usf, sf;
+			usf = (struct sparc_stackf32 *) ufp;
+			if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
+				break;
+			pc = sf.callers_pc;
+			ufp = (unsigned long)sf.fp;
+		}
 		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d778248..c6e0c29 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -452,13 +452,16 @@ void flush_thread(void)
 /* It's a bit more tricky when 64-bit tasks are involved... */
 static unsigned long clone_stackframe(unsigned long csp, unsigned long psp)
 {
+	bool stack_64bit = test_thread_64bit_stack(psp);
 	unsigned long fp, distance, rval;
 
-	if (!(test_thread_flag(TIF_32BIT))) {
+	if (stack_64bit) {
 		csp += STACK_BIAS;
 		psp += STACK_BIAS;
 		__get_user(fp, &(((struct reg_window __user *)psp)->ins[6]));
 		fp += STACK_BIAS;
+		if (test_thread_flag(TIF_32BIT))
+			fp &= 0xffffffff;
 	} else
 		__get_user(fp, &(((struct reg_window32 __user *)psp)->ins[6]));
 
@@ -472,7 +475,7 @@ static unsigned long clone_stackframe(unsigned long csp, unsigned long psp)
 	rval = (csp - distance);
 	if (copy_in_user((void __user *) rval, (void __user *) psp, distance))
 		rval = 0;
-	else if (test_thread_flag(TIF_32BIT)) {
+	else if (!stack_64bit) {
 		if (put_user(((u32)csp),
 			     &(((struct reg_window32 __user *)rval)->ins[6])))
 			rval = 0;
@@ -507,18 +510,18 @@ void synchronize_user_stack(void)
 
 	flush_user_windows();
 	if ((window = get_thread_wsaved()) != 0) {
-		int winsize = sizeof(struct reg_window);
-		int bias = 0;
-
-		if (test_thread_flag(TIF_32BIT))
-			winsize = sizeof(struct reg_window32);
-		else
-			bias = STACK_BIAS;
-
 		window -= 1;
 		do {
-			unsigned long sp = (t->rwbuf_stkptrs[window] + bias);
 			struct reg_window *rwin = &t->reg_window[window];
+			int winsize = sizeof(struct reg_window);
+			unsigned long sp;
+
+			sp = t->rwbuf_stkptrs[window];
+
+			if (test_thread_64bit_stack(sp))
+				sp += STACK_BIAS;
+			else
+				winsize = sizeof(struct reg_window32);
 
 			if (!copy_to_user((char __user *)sp, rwin, winsize)) {
 				shift_window_buffer(window, get_thread_wsaved() - 1, t);
@@ -544,13 +547,6 @@ void fault_in_user_windows(void)
 {
 	struct thread_info *t = current_thread_info();
 	unsigned long window;
-	int winsize = sizeof(struct reg_window);
-	int bias = 0;
-
-	if (test_thread_flag(TIF_32BIT))
-		winsize = sizeof(struct reg_window32);
-	else
-		bias = STACK_BIAS;
 
 	flush_user_windows();
 	window = get_thread_wsaved();
@@ -558,8 +554,16 @@ void fault_in_user_windows(void)
 	if (likely(window != 0)) {
 		window -= 1;
 		do {
-			unsigned long sp = (t->rwbuf_stkptrs[window] + bias);
 			struct reg_window *rwin = &t->reg_window[window];
+			int winsize = sizeof(struct reg_window);
+			unsigned long sp;
+
+			sp = t->rwbuf_stkptrs[window];
+
+			if (test_thread_64bit_stack(sp))
+				sp += STACK_BIAS;
+			else
+				winsize = sizeof(struct reg_window32);
 
 			if (unlikely(sp & 0x7UL))
 				stack_unaligned(sp);
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 484daba..7ff45e4 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -151,7 +151,7 @@ static int regwindow64_get(struct task_struct *target,
 {
 	unsigned long rw_addr = regs->u_regs[UREG_I6];
 
-	if (test_tsk_thread_flag(current, TIF_32BIT)) {
+	if (!test_thread_64bit_stack(rw_addr)) {
 		struct reg_window32 win32;
 		int i;
 
@@ -176,7 +176,7 @@ static int regwindow64_set(struct task_struct *target,
 {
 	unsigned long rw_addr = regs->u_regs[UREG_I6];
 
-	if (test_tsk_thread_flag(current, TIF_32BIT)) {
+	if (!test_thread_64bit_stack(rw_addr)) {
 		struct reg_window32 win32;
 		int i;
 
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 0800e71..0eaf005 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -316,6 +316,25 @@ static void __init popc_patch(void)
 	}
 }
 
+static void __init pause_patch(void)
+{
+	struct pause_patch_entry *p;
+
+	p = &__pause_3insn_patch;
+	while (p < &__pause_3insn_patch_end) {
+		unsigned long i, addr = p->addr;
+
+		for (i = 0; i < 3; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p++;
+	}
+}
+
 #ifdef CONFIG_SMP
 void __init boot_cpu_id_too_large(int cpu)
 {
@@ -528,6 +547,8 @@ static void __init init_sparc64_elf_hwcap(void)
 
 	if (sparc64_elf_hwcap & AV_SPARC_POPC)
 		popc_patch();
+	if (sparc64_elf_hwcap & AV_SPARC_PAUSE)
+		pause_patch();
 }
 
 void __init setup_arch(char **cmdline_p)
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 867de2f..689e1ba 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -295,9 +295,7 @@ void do_rt_sigreturn(struct pt_regs *regs)
 		err |= restore_fpu_state(regs, fpu_save);
 
 	err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t));
-	err |= do_sigaltstack(&sf->stack, NULL, (unsigned long)sf);
-
-	if (err)
+	if (err || do_sigaltstack(&sf->stack, NULL, (unsigned long)sf) == -EFAULT)
 		goto segv;
 
 	err |= __get_user(rwin_save, &sf->rwin_save);
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 11c6c96..878ef3d 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -751,3 +751,8 @@ int kernel_execve(const char *filename,
 		      : "cc");
 	return __res;
 }
+
+asmlinkage long sys_kern_features(void)
+{
+	return KERN_FEATURE_MIXED_MODE_STACK;
+}
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 63402f9..5147f57 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -85,3 +85,4 @@ sys_call_table:
 /*325*/	.long sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init
 /*330*/	.long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 /*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
+/*340*/	.long sys_ni_syscall, sys_kcmp
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 3a58e0d..1c9af9f 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -86,6 +86,7 @@ sys_call_table32:
 	.word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo, sys_perf_event_open, compat_sys_recvmmsg, sys_fanotify_init
 /*330*/	.word sys32_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime
 	.word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
+/*340*/	.word sys_kern_features, sys_kcmp
 
 #endif /* CONFIG_COMPAT */
 
@@ -163,3 +164,4 @@ sys_call_table:
 	.word sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init
 /*330*/	.word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 	.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
+/*340*/	.word sys_kern_features, sys_kcmp
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index f81d038..8201c25e 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -113,21 +113,24 @@ static inline long sign_extend_imm13(long imm)
 
 static unsigned long fetch_reg(unsigned int reg, struct pt_regs *regs)
 {
-	unsigned long value;
+	unsigned long value, fp;
 	
 	if (reg < 16)
 		return (!reg ? 0 : regs->u_regs[reg]);
+
+	fp = regs->u_regs[UREG_FP];
+
 	if (regs->tstate & TSTATE_PRIV) {
 		struct reg_window *win;
-		win = (struct reg_window *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window *)(fp + STACK_BIAS);
 		value = win->locals[reg - 16];
-	} else if (test_thread_flag(TIF_32BIT)) {
+	} else if (!test_thread_64bit_stack(fp)) {
 		struct reg_window32 __user *win32;
-		win32 = (struct reg_window32 __user *)((unsigned long)((u32)regs->u_regs[UREG_FP]));
+		win32 = (struct reg_window32 __user *)((unsigned long)((u32)fp));
 		get_user(value, &win32->locals[reg - 16]);
 	} else {
 		struct reg_window __user *win;
-		win = (struct reg_window __user *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window __user *)(fp + STACK_BIAS);
 		get_user(value, &win->locals[reg - 16]);
 	}
 	return value;
@@ -135,19 +138,24 @@ static unsigned long fetch_reg(unsigned int reg, struct pt_regs *regs)
 
 static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs)
 {
+	unsigned long fp;
+
 	if (reg < 16)
 		return &regs->u_regs[reg];
+
+	fp = regs->u_regs[UREG_FP];
+
 	if (regs->tstate & TSTATE_PRIV) {
 		struct reg_window *win;
-		win = (struct reg_window *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window *)(fp + STACK_BIAS);
 		return &win->locals[reg - 16];
-	} else if (test_thread_flag(TIF_32BIT)) {
+	} else if (!test_thread_64bit_stack(fp)) {
 		struct reg_window32 *win32;
-		win32 = (struct reg_window32 *)((unsigned long)((u32)regs->u_regs[UREG_FP]));
+		win32 = (struct reg_window32 *)((unsigned long)((u32)fp));
 		return (unsigned long *)&win32->locals[reg - 16];
 	} else {
 		struct reg_window *win;
-		win = (struct reg_window *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window *)(fp + STACK_BIAS);
 		return &win->locals[reg - 16];
 	}
 }
@@ -392,13 +400,15 @@ int handle_popc(u32 insn, struct pt_regs *regs)
 		if (rd)
 			regs->u_regs[rd] = ret;
 	} else {
-		if (test_thread_flag(TIF_32BIT)) {
+		unsigned long fp = regs->u_regs[UREG_FP];
+
+		if (!test_thread_64bit_stack(fp)) {
 			struct reg_window32 __user *win32;
-			win32 = (struct reg_window32 __user *)((unsigned long)((u32)regs->u_regs[UREG_FP]));
+			win32 = (struct reg_window32 __user *)((unsigned long)((u32)fp));
 			put_user(ret, &win32->locals[rd - 16]);
 		} else {
 			struct reg_window __user *win;
-			win = (struct reg_window __user *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+			win = (struct reg_window __user *)(fp + STACK_BIAS);
 			put_user(ret, &win->locals[rd - 16]);
 		}
 	}
@@ -554,7 +564,7 @@ void handle_ld_nf(u32 insn, struct pt_regs *regs)
 		reg[0] = 0;
 		if ((insn & 0x780000) == 0x180000)
 			reg[1] = 0;
-	} else if (test_thread_flag(TIF_32BIT)) {
+	} else if (!test_thread_64bit_stack(regs->u_regs[UREG_FP])) {
 		put_user(0, (int __user *) reg);
 		if ((insn & 0x780000) == 0x180000)
 			put_user(0, ((int __user *) reg) + 1);
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index 08e074b7..c096c62 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -149,21 +149,24 @@ static inline void maybe_flush_windows(unsigned int rs1, unsigned int rs2,
 
 static unsigned long fetch_reg(unsigned int reg, struct pt_regs *regs)
 {
-	unsigned long value;
+	unsigned long value, fp;
 	
 	if (reg < 16)
 		return (!reg ? 0 : regs->u_regs[reg]);
+
+	fp = regs->u_regs[UREG_FP];
+
 	if (regs->tstate & TSTATE_PRIV) {
 		struct reg_window *win;
-		win = (struct reg_window *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window *)(fp + STACK_BIAS);
 		value = win->locals[reg - 16];
-	} else if (test_thread_flag(TIF_32BIT)) {
+	} else if (!test_thread_64bit_stack(fp)) {
 		struct reg_window32 __user *win32;
-		win32 = (struct reg_window32 __user *)((unsigned long)((u32)regs->u_regs[UREG_FP]));
+		win32 = (struct reg_window32 __user *)((unsigned long)((u32)fp));
 		get_user(value, &win32->locals[reg - 16]);
 	} else {
 		struct reg_window __user *win;
-		win = (struct reg_window __user *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window __user *)(fp + STACK_BIAS);
 		get_user(value, &win->locals[reg - 16]);
 	}
 	return value;
@@ -172,16 +175,18 @@ static unsigned long fetch_reg(unsigned int reg, struct pt_regs *regs)
 static inline unsigned long __user *__fetch_reg_addr_user(unsigned int reg,
 							  struct pt_regs *regs)
 {
+	unsigned long fp = regs->u_regs[UREG_FP];
+
 	BUG_ON(reg < 16);
 	BUG_ON(regs->tstate & TSTATE_PRIV);
 
-	if (test_thread_flag(TIF_32BIT)) {
+	if (!test_thread_64bit_stack(fp)) {
 		struct reg_window32 __user *win32;
-		win32 = (struct reg_window32 __user *)((unsigned long)((u32)regs->u_regs[UREG_FP]));
+		win32 = (struct reg_window32 __user *)((unsigned long)((u32)fp));
 		return (unsigned long __user *)&win32->locals[reg - 16];
 	} else {
 		struct reg_window __user *win;
-		win = (struct reg_window __user *)(regs->u_regs[UREG_FP] + STACK_BIAS);
+		win = (struct reg_window __user *)(fp + STACK_BIAS);
 		return &win->locals[reg - 16];
 	}
 }
@@ -204,7 +209,7 @@ static void store_reg(struct pt_regs *regs, unsigned long val, unsigned long rd)
 	} else {
 		unsigned long __user *rd_user = __fetch_reg_addr_user(rd, regs);
 
-		if (test_thread_flag(TIF_32BIT))
+		if (!test_thread_64bit_stack(regs->u_regs[UREG_FP]))
 			__put_user((u32)val, (u32 __user *)rd_user);
 		else
 			__put_user(val, rd_user);
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 89c2c29..0bacceb 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -132,6 +132,11 @@ SECTIONS
 		*(.popc_6insn_patch)
 		__popc_6insn_patch_end = .;
 	}
+	.pause_3insn_patch : {
+		__pause_3insn_patch = .;
+		*(.pause_3insn_patch)
+		__pause_3insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index a6b0863..1e67ce9 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -43,6 +43,8 @@ spill_fixup_mna:
 spill_fixup_dax:
 	TRAP_LOAD_THREAD_REG(%g6, %g1)
 	ldx	[%g6 + TI_FLAGS], %g1
+	andcc	%sp, 0x1, %g0
+	movne	%icc, 0, %g1
 	andcc	%g1, _TIF_32BIT, %g0
 	ldub	[%g6 + TI_WSAVED], %g1
 	sll	%g1, 3, %g3
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index 4d502da..85c233d 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -1,6 +1,6 @@
 /* atomic.S: These things are too big to do inline.
  *
- * Copyright (C) 1999, 2007 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 1999, 2007 2012 David S. Miller (davem@davemloft.net)
  */
 
 #include <linux/linkage.h>
@@ -117,3 +117,17 @@ ENTRY(atomic64_sub_ret) /* %o0 = decrement, %o1 = atomic_ptr */
 	 sub	%g1, %o0, %o0
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
 ENDPROC(atomic64_sub_ret)
+
+ENTRY(atomic64_dec_if_positive) /* %o0 = atomic_ptr */
+	BACKOFF_SETUP(%o2)
+1:	ldx	[%o0], %g1
+	brlez,pn %g1, 3f
+	 sub	%g1, 1, %g7
+	casx	[%o0], %g1, %g7
+	cmp	%g1, %g7
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
+	 nop
+3:	retl
+	 sub	%g1, 1, %o0
+2:	BACKOFF_SPIN(%o2, %o3, 1b)
+ENDPROC(atomic64_dec_if_positive)
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index ee31b88..0c4e35e 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -116,6 +116,7 @@ EXPORT_SYMBOL(atomic64_add);
 EXPORT_SYMBOL(atomic64_add_ret);
 EXPORT_SYMBOL(atomic64_sub);
 EXPORT_SYMBOL(atomic64_sub_ret);
+EXPORT_SYMBOL(atomic64_dec_if_positive);
 
 /* Atomic bit operations. */
 EXPORT_SYMBOL(test_and_set_bit);
diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c
index 1704068..034aadb 100644
--- a/arch/sparc/math-emu/math_64.c
+++ b/arch/sparc/math-emu/math_64.c
@@ -320,7 +320,7 @@ int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap)
 					XR = 0;
 				else if (freg < 16)
 					XR = regs->u_regs[freg];
-				else if (test_thread_flag(TIF_32BIT)) {
+				else if (!test_thread_64bit_stack(regs->u_regs[UREG_FP])) {
 					struct reg_window32 __user *win32;
 					flushw_user ();
 					win32 = (struct reg_window32 __user *)((unsigned long)((u32)regs->u_regs[UREG_FP]));
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 3a8ece7..0d7103c 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -32,13 +32,14 @@ void flush_thread(void)
 		       "err = %d\n", ret);
 		force_sig(SIGKILL, current);
 	}
+	get_safe_registers(current_pt_regs()->regs.gp,
+			   current_pt_regs()->regs.fp);
 
 	__switch_mm(&current->mm->context.id);
 }
 
 void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
 {
-	get_safe_registers(regs->regs.gp, regs->regs.fp);
 	PT_REGS_IP(regs) = eip;
 	PT_REGS_SP(regs) = esp;
 	current->ptrace &= ~PT_DTRACE;
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index e5c5473..c4fbb21 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -16,6 +16,8 @@ config UNICORE32
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IOMAP
 	select MODULES_USE_ELF_REL
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
@@ -64,6 +66,9 @@ config GENERIC_CALIBRATE_DELAY
 config ARCH_MAY_HAVE_PC_FDC
 	bool
 
+config ZONE_DMA
+	def_bool y
+
 config NEED_DMA_MAP_STATE
        def_bool y
 
@@ -216,7 +221,7 @@ config PUV3_GPIO
 	bool
 	depends on !ARCH_FPGA
 	select GENERIC_GPIO
-	select GPIO_SYSFS if EXPERIMENTAL
+	select GPIO_SYSFS
 	default y
 
 if PUV3_NB0916
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index c910c98..601e92f 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -1,4 +1,3 @@
-include include/asm-generic/Kbuild.asm
 
 generic-y += atomic.h
 generic-y += auxvec.h
diff --git a/arch/unicore32/include/asm/bug.h b/arch/unicore32/include/asm/bug.h
index b1ff8ca..93a56f3 100644
--- a/arch/unicore32/include/asm/bug.h
+++ b/arch/unicore32/include/asm/bug.h
@@ -19,9 +19,4 @@ extern void die(const char *msg, struct pt_regs *regs, int err);
 extern void uc32_notify_die(const char *str, struct pt_regs *regs,
 		struct siginfo *info, unsigned long err, unsigned long trap);
 
-extern asmlinkage void __backtrace(void);
-extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
-
-extern void __show_regs(struct pt_regs *);
-
 #endif /* __UNICORE_BUG_H__ */
diff --git a/arch/unicore32/include/asm/cmpxchg.h b/arch/unicore32/include/asm/cmpxchg.h
index df4d5ac..8e797ad 100644
--- a/arch/unicore32/include/asm/cmpxchg.h
+++ b/arch/unicore32/include/asm/cmpxchg.h
@@ -35,7 +35,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
 			: "memory", "cc");
 		break;
 	default:
-		ret = __xchg_bad_pointer();
+		__xchg_bad_pointer();
 	}
 
 	return ret;
diff --git a/arch/unicore32/include/asm/kvm_para.h b/arch/unicore32/include/asm/kvm_para.h
deleted file mode 100644
index 14fab8f..0000000
--- a/arch/unicore32/include/asm/kvm_para.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kvm_para.h>
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index 14382cb..4eaa421 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/arch/unicore32/include/asm/processor.h
@@ -72,11 +72,6 @@ unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
 
-/*
- * Create a new kernel thread
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 
diff --git a/arch/unicore32/include/asm/ptrace.h b/arch/unicore32/include/asm/ptrace.h
index b9caf9b..726749d 100644
--- a/arch/unicore32/include/asm/ptrace.h
+++ b/arch/unicore32/include/asm/ptrace.h
@@ -12,80 +12,10 @@
 #ifndef __UNICORE_PTRACE_H__
 #define __UNICORE_PTRACE_H__
 
-#define PTRACE_GET_THREAD_AREA	22
-
-/*
- * PSR bits
- */
-#define USER_MODE	0x00000010
-#define REAL_MODE	0x00000011
-#define INTR_MODE	0x00000012
-#define PRIV_MODE	0x00000013
-#define ABRT_MODE	0x00000017
-#define EXTN_MODE	0x0000001b
-#define SUSR_MODE	0x0000001f
-#define MODE_MASK	0x0000001f
-#define PSR_R_BIT	0x00000040
-#define PSR_I_BIT	0x00000080
-#define PSR_V_BIT	0x10000000
-#define PSR_C_BIT	0x20000000
-#define PSR_Z_BIT	0x40000000
-#define PSR_S_BIT	0x80000000
-
-/*
- * Groups of PSR bits
- */
-#define PSR_f		0xff000000	/* Flags		*/
-#define PSR_c		0x000000ff	/* Control		*/
+#include <uapi/asm/ptrace.h>
 
 #ifndef __ASSEMBLY__
 
-/*
- * This struct defines the way the registers are stored on the
- * stack during a system call.  Note that sizeof(struct pt_regs)
- * has to be a multiple of 8.
- */
-struct pt_regs {
-	unsigned long uregs[34];
-};
-
-#define UCreg_asr		uregs[32]
-#define UCreg_pc		uregs[31]
-#define UCreg_lr		uregs[30]
-#define UCreg_sp		uregs[29]
-#define UCreg_ip		uregs[28]
-#define UCreg_fp		uregs[27]
-#define UCreg_26		uregs[26]
-#define UCreg_25		uregs[25]
-#define UCreg_24		uregs[24]
-#define UCreg_23		uregs[23]
-#define UCreg_22		uregs[22]
-#define UCreg_21		uregs[21]
-#define UCreg_20		uregs[20]
-#define UCreg_19		uregs[19]
-#define UCreg_18		uregs[18]
-#define UCreg_17		uregs[17]
-#define UCreg_16		uregs[16]
-#define UCreg_15		uregs[15]
-#define UCreg_14		uregs[14]
-#define UCreg_13		uregs[13]
-#define UCreg_12		uregs[12]
-#define UCreg_11		uregs[11]
-#define UCreg_10		uregs[10]
-#define UCreg_09		uregs[9]
-#define UCreg_08		uregs[8]
-#define UCreg_07		uregs[7]
-#define UCreg_06		uregs[6]
-#define UCreg_05		uregs[5]
-#define UCreg_04		uregs[4]
-#define UCreg_03		uregs[3]
-#define UCreg_02		uregs[2]
-#define UCreg_01		uregs[1]
-#define UCreg_00		uregs[0]
-#define UCreg_ORIG_00		uregs[33]
-
-#ifdef __KERNEL__
-
 #define user_mode(regs)	\
 	(processor_mode(regs) == USER_MODE)
 
@@ -125,9 +55,5 @@ static inline int valid_user_regs(struct pt_regs *regs)
 
 #define instruction_pointer(regs)	((regs)->UCreg_pc)
 
-#endif /* __KERNEL__ */
-
 #endif /* __ASSEMBLY__ */
-
 #endif
-
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
index baebb3d..0514d7a 100644
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ b/arch/unicore32/include/uapi/asm/Kbuild
@@ -1,3 +1,10 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+header-y += byteorder.h
+header-y += kvm_para.h
+header-y += ptrace.h
+header-y += sigcontext.h
+header-y += unistd.h
+
+generic-y += kvm_para.h
diff --git a/arch/unicore32/include/asm/byteorder.h b/arch/unicore32/include/uapi/asm/byteorder.h
index ebe1b3f..ebe1b3f 100644
--- a/arch/unicore32/include/asm/byteorder.h
+++ b/arch/unicore32/include/uapi/asm/byteorder.h
diff --git a/arch/unicore32/include/uapi/asm/ptrace.h b/arch/unicore32/include/uapi/asm/ptrace.h
new file mode 100644
index 0000000..187aa2e
--- /dev/null
+++ b/arch/unicore32/include/uapi/asm/ptrace.h
@@ -0,0 +1,90 @@
+/*
+ * linux/arch/unicore32/include/asm/ptrace.h
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _UAPI__UNICORE_PTRACE_H__
+#define _UAPI__UNICORE_PTRACE_H__
+
+#define PTRACE_GET_THREAD_AREA	22
+
+/*
+ * PSR bits
+ */
+#define USER_MODE	0x00000010
+#define REAL_MODE	0x00000011
+#define INTR_MODE	0x00000012
+#define PRIV_MODE	0x00000013
+#define ABRT_MODE	0x00000017
+#define EXTN_MODE	0x0000001b
+#define SUSR_MODE	0x0000001f
+#define MODE_MASK	0x0000001f
+#define PSR_R_BIT	0x00000040
+#define PSR_I_BIT	0x00000080
+#define PSR_V_BIT	0x10000000
+#define PSR_C_BIT	0x20000000
+#define PSR_Z_BIT	0x40000000
+#define PSR_S_BIT	0x80000000
+
+/*
+ * Groups of PSR bits
+ */
+#define PSR_f		0xff000000	/* Flags		*/
+#define PSR_c		0x000000ff	/* Control		*/
+
+#ifndef __ASSEMBLY__
+
+/*
+ * This struct defines the way the registers are stored on the
+ * stack during a system call.  Note that sizeof(struct pt_regs)
+ * has to be a multiple of 8.
+ */
+struct pt_regs {
+	unsigned long uregs[34];
+};
+
+#define UCreg_asr		uregs[32]
+#define UCreg_pc		uregs[31]
+#define UCreg_lr		uregs[30]
+#define UCreg_sp		uregs[29]
+#define UCreg_ip		uregs[28]
+#define UCreg_fp		uregs[27]
+#define UCreg_26		uregs[26]
+#define UCreg_25		uregs[25]
+#define UCreg_24		uregs[24]
+#define UCreg_23		uregs[23]
+#define UCreg_22		uregs[22]
+#define UCreg_21		uregs[21]
+#define UCreg_20		uregs[20]
+#define UCreg_19		uregs[19]
+#define UCreg_18		uregs[18]
+#define UCreg_17		uregs[17]
+#define UCreg_16		uregs[16]
+#define UCreg_15		uregs[15]
+#define UCreg_14		uregs[14]
+#define UCreg_13		uregs[13]
+#define UCreg_12		uregs[12]
+#define UCreg_11		uregs[11]
+#define UCreg_10		uregs[10]
+#define UCreg_09		uregs[9]
+#define UCreg_08		uregs[8]
+#define UCreg_07		uregs[7]
+#define UCreg_06		uregs[6]
+#define UCreg_05		uregs[5]
+#define UCreg_04		uregs[4]
+#define UCreg_03		uregs[3]
+#define UCreg_02		uregs[2]
+#define UCreg_01		uregs[1]
+#define UCreg_00		uregs[0]
+#define UCreg_ORIG_00		uregs[33]
+
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI__UNICORE_PTRACE_H__ */
diff --git a/arch/unicore32/include/asm/sigcontext.h b/arch/unicore32/include/uapi/asm/sigcontext.h
index 6a2d767..6a2d767 100644
--- a/arch/unicore32/include/asm/sigcontext.h
+++ b/arch/unicore32/include/uapi/asm/sigcontext.h
diff --git a/arch/unicore32/include/asm/unistd.h b/arch/unicore32/include/uapi/asm/unistd.h
index 2abcf61..d18a3be8 100644
--- a/arch/unicore32/include/asm/unistd.h
+++ b/arch/unicore32/include/uapi/asm/unistd.h
@@ -12,3 +12,4 @@
 
 /* Use the standard ABI for syscalls. */
 #include <asm-generic/unistd.h>
+#define __ARCH_WANT_SYS_EXECVE
diff --git a/arch/unicore32/kernel/entry.S b/arch/unicore32/kernel/entry.S
index dcb87ab..7049350 100644
--- a/arch/unicore32/kernel/entry.S
+++ b/arch/unicore32/kernel/entry.S
@@ -573,17 +573,16 @@ ENDPROC(ret_to_user)
  */
 ENTRY(ret_from_fork)
 	b.l	schedule_tail
-	get_thread_info tsk
-	ldw	r1, [tsk+], #TI_FLAGS		@ check for syscall tracing
-	mov	why, #1
-	cand.a	r1, #_TIF_SYSCALL_TRACE		@ are we tracing syscalls?
-	beq	ret_slow_syscall
-	mov	r1, sp
-	mov	r0, #1				@ trace exit [IP = 1]
-	b.l	syscall_trace
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
 
+ENTRY(ret_from_kernel_thread)
+	b.l	schedule_tail
+	mov	r0, r5
+	adr	lr, ret_slow_syscall
+	mov	pc, r4
+ENDPROC(ret_from_kernel_thread)
+
 /*=============================================================================
  * SWI handler
  *-----------------------------------------------------------------------------
@@ -669,11 +668,6 @@ __cr_alignment:
 #endif
 	.ltorg
 
-ENTRY(sys_execve)
-		add	r3, sp, #S_OFF
-		b	__sys_execve
-ENDPROC(sys_execve)
-
 ENTRY(sys_clone)
 		add	ip, sp, #S_OFF
 		stw	ip, [sp+], #4
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index b008586..a8fe265 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -258,6 +258,7 @@ void release_thread(struct task_struct *dead_task)
 }
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
 int
 copy_thread(unsigned long clone_flags, unsigned long stack_start,
@@ -266,17 +267,22 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
 
-	*childregs = *regs;
-	childregs->UCreg_00 = 0;
-	childregs->UCreg_sp = stack_start;
-
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 	thread->cpu_context.sp = (unsigned long)childregs;
-	thread->cpu_context.pc = (unsigned long)ret_from_fork;
-
-	if (clone_flags & CLONE_SETTLS)
-		childregs->UCreg_16 = regs->UCreg_03;
+	if (unlikely(!regs)) {
+		thread->cpu_context.pc = (unsigned long)ret_from_kernel_thread;
+		thread->cpu_context.r4 = stack_start;
+		thread->cpu_context.r5 = stk_sz;
+		memset(childregs, 0, sizeof(struct pt_regs));
+	} else {
+		thread->cpu_context.pc = (unsigned long)ret_from_fork;
+		*childregs = *regs;
+		childregs->UCreg_00 = 0;
+		childregs->UCreg_sp = stack_start;
 
+		if (clone_flags & CLONE_SETTLS)
+			childregs->UCreg_16 = regs->UCreg_03;
+	}
 	return 0;
 }
 
@@ -305,42 +311,6 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fp)
 }
 EXPORT_SYMBOL(dump_fpu);
 
-/*
- * Shuffle the argument into the correct register before calling the
- * thread function.  r1 is the thread argument, r2 is the pointer to
- * the thread function, and r3 points to the exit function.
- */
-asm(".pushsection .text\n"
-"	.align\n"
-"	.type	kernel_thread_helper, #function\n"
-"kernel_thread_helper:\n"
-"	mov.a	asr, r7\n"
-"	mov	r0, r4\n"
-"	mov	lr, r6\n"
-"	mov	pc, r5\n"
-"	.size	kernel_thread_helper, . - kernel_thread_helper\n"
-"	.popsection");
-
-/*
- * Create a kernel thread.
- */
-pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-
-	regs.UCreg_04 = (unsigned long)arg;
-	regs.UCreg_05 = (unsigned long)fn;
-	regs.UCreg_06 = (unsigned long)do_exit;
-	regs.UCreg_07 = PRIV_MODE;
-	regs.UCreg_pc = (unsigned long)kernel_thread_helper;
-	regs.UCreg_asr = regs.UCreg_07 | PSR_I_BIT;
-
-	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
diff --git a/arch/unicore32/kernel/setup.h b/arch/unicore32/kernel/setup.h
index f239550..30f749d 100644
--- a/arch/unicore32/kernel/setup.h
+++ b/arch/unicore32/kernel/setup.h
@@ -30,4 +30,10 @@ extern char __vectors_start[], __vectors_end[];
 extern void kernel_thread_helper(void);
 
 extern void __init early_signal_init(void);
+
+extern asmlinkage void __backtrace(void);
+extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
+
+extern void __show_regs(struct pt_regs *);
+
 #endif
diff --git a/arch/unicore32/kernel/sys.c b/arch/unicore32/kernel/sys.c
index fabdee9..9680134 100644
--- a/arch/unicore32/kernel/sys.c
+++ b/arch/unicore32/kernel/sys.c
@@ -42,69 +42,6 @@ asmlinkage long __sys_clone(unsigned long clone_flags, unsigned long newsp,
 			parent_tid, child_tid);
 }
 
-/* sys_execve() executes a new program.
- * This is called indirectly via a small wrapper
- */
-asmlinkage long __sys_execve(const char __user *filename,
-			  const char __user *const __user *argv,
-			  const char __user *const __user *envp,
-			  struct pt_regs *regs)
-{
-	int error;
-	struct filename *fn;
-
-	fn = getname(filename);
-	error = PTR_ERR(fn);
-	if (IS_ERR(fn))
-		goto out;
-	error = do_execve(fn->name, argv, envp, regs);
-	putname(fn);
-out:
-	return error;
-}
-
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	struct pt_regs regs;
-	int ret;
-
-	memset(&regs, 0, sizeof(struct pt_regs));
-	ret = do_execve(filename,
-			(const char __user *const __user *)argv,
-			(const char __user *const __user *)envp, &regs);
-	if (ret < 0)
-		goto out;
-
-	/*
-	 * Save argc to the register structure for userspace.
-	 */
-	regs.UCreg_00 = ret;
-
-	/*
-	 * We were successful.  We won't be returning to our caller, but
-	 * instead to user space by manipulating the kernel stack.
-	 */
-	asm("add	r0, %0, %1\n\t"
-		"mov	r1, %2\n\t"
-		"mov	r2, %3\n\t"
-		"mov	r22, #0\n\t"	/* not a syscall */
-		"mov	r23, %0\n\t"	/* thread structure */
-		"b.l	memmove\n\t"	/* copy regs to top of stack */
-		"mov	sp, r0\n\t"	/* reposition stack pointer */
-		"b	ret_to_user"
-		:
-		: "r" (current_thread_info()),
-		  "Ir" (THREAD_START_SP - sizeof(regs)),
-		  "r" (&regs),
-		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "ip", "lr", "memory");
-
- out:
-	return ret;
-}
-
 /* Note: used by the compat code even in 64-bit Linux. */
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 2eeb9c0..f9b5c10 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -168,7 +168,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 }
 
 static int __do_pf(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		struct task_struct *tsk)
+		unsigned int flags, struct task_struct *tsk)
 {
 	struct vm_area_struct *vma;
 	int fault;
@@ -194,14 +194,7 @@ good_area:
 	 * If for any reason at all we couldn't handle the fault, make
 	 * sure we exit gracefully rather than endlessly redo the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK,
-			    (!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
-	if (unlikely(fault & VM_FAULT_ERROR))
-		return fault;
-	if (fault & VM_FAULT_MAJOR)
-		tsk->maj_flt++;
-	else
-		tsk->min_flt++;
+	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
 	return fault;
 
 check_stack:
@@ -216,6 +209,8 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+				 ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
 
 	tsk = current;
 	mm = tsk->mm;
@@ -236,6 +231,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		if (!user_mode(regs)
 		    && !search_exception_tables(regs->UCreg_pc))
 			goto no_context;
+retry:
 		down_read(&mm->mmap_sem);
 	} else {
 		/*
@@ -251,7 +247,28 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 #endif
 	}
 
-	fault = __do_pf(mm, addr, fsr, tsk);
+	fault = __do_pf(mm, addr, fsr, flags, tsk);
+
+	/* If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_sem because
+	 * it would already be released in __lock_page_or_retry in
+	 * mm/filemap.c. */
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return 0;
+
+	if (!(fault & VM_FAULT_ERROR) && (flags & FAULT_FLAG_ALLOW_RETRY)) {
+		if (fault & VM_FAULT_MAJOR)
+			tsk->maj_flt++;
+		else
+			tsk->min_flt++;
+		if (fault & VM_FAULT_RETRY) {
+			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+			* of starvation. */
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			goto retry;
+		}
+	}
+
 	up_read(&mm->mmap_sem);
 
 	/*
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c760e07..e87b0ca 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -12,6 +12,8 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 
+#undef memcpy			/* Use memcpy from misc.c */
+
 #include "eboot.h"
 
 static efi_system_table_t *sys_table;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 2a01744..8c132a6 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -476,6 +476,3 @@ die:
 setup_corrupt:
 	.byte	7
 	.string	"No setup signature found...\n"
-
-	.data
-dummy:	.long	0
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 66e5f0e..79fd8a3 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += mce.h
 header-y += msr-index.h
 header-y += msr.h
 header-y += mtrr.h
+header-y += perf_regs.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
 header-y += posix_types_x32.h
@@ -19,8 +20,10 @@ header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
 header-y += sigcontext32.h
+header-y += svm.h
 header-y += ucontext.h
 header-y += vm86.h
+header-y += vmx.h
 header-y += vsyscall.h
 
 genhdr-y += unistd_32.h
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 831dbb9..41ab26e 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -399,14 +399,17 @@ static inline void drop_init_fpu(struct task_struct *tsk)
 typedef struct { int preload; } fpu_switch_t;
 
 /*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
  *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
  */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
 	return new == this_cpu_read_stable(fpu_owner_task) &&
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index dcfde52..19f16eb 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -205,21 +205,14 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 }
 #endif
 
-/*
- * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps.  The previous stack will be directly underneath the saved
- * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
- *
- * This is valid only for kernel mode traps.
- */
-static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
-{
 #ifdef CONFIG_X86_32
-	return (unsigned long)(&regs->sp);
+extern unsigned long kernel_stack_pointer(struct pt_regs *regs);
 #else
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
 	return regs->sp;
-#endif
 }
+#endif
 
 #define GET_IP(regs) ((regs)->ip)
 #define GET_FP(regs) ((regs)->bp)
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 59c226d..c20d1ce 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -359,18 +359,14 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
 		return _hypercall4(int, update_va_mapping, va,
 				   new_val.pte, new_val.pte >> 32, flags);
 }
+extern int __must_check xen_event_channel_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_event_channel_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, event_channel_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct evtchn_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, event_channel_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
+	if (unlikely(rc == -ENOSYS))
+		rc = xen_event_channel_op_compat(cmd, arg);
 	return rc;
 }
 
@@ -386,17 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 
+extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, physdev_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct physdev_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, physdev_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
+	if (unlikely(rc == -ENOSYS))
+		rc = HYPERVISOR_physdev_op_compat(cmd, arg);
 	return rc;
 }
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 66d0fff..125f344 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,7 +33,6 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-/* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f7e98a2..1b7d165 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			wrmsrl_safe(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 698b6ec..1ac581f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -6,7 +6,7 @@
  *
  *  Written by Jacob Shin - AMD, Inc.
  *
- *  Support: borislav.petkov@amd.com
+ *  Maintained by: Borislav Petkov <bp@alien8.de>
  *
  *  April 2006
  *     - added support for AMD Family 0x10 processors
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 5f88abf..4f9a3cb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,34 +285,39 @@ void cmci_clear(void)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
+static long cmci_rediscover_work_func(void *arg)
+{
+	int banks;
+
+	/* Recheck banks in case CPUs don't all have the same */
+	if (cmci_supported(&banks))
+		cmci_discover(banks);
+
+	return 0;
+}
+
 /*
  * After a CPU went down cycle through all the others and rediscover
  * Must run in process context.
  */
 void cmci_rediscover(int dying)
 {
-	int banks;
-	int cpu;
-	cpumask_var_t old;
+	int cpu, banks;
 
 	if (!cmci_supported(&banks))
 		return;
-	if (!alloc_cpumask_var(&old, GFP_KERNEL))
-		return;
-	cpumask_copy(old, &current->cpus_allowed);
 
 	for_each_online_cpu(cpu) {
 		if (cpu == dying)
 			continue;
-		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
+
+		if (cpu == smp_processor_id()) {
+			cmci_rediscover_work_func(NULL);
 			continue;
-		/* Recheck banks in case CPUs don't all have the same */
-		if (cmci_supported(&banks))
-			cmci_discover(banks);
-	}
+		}
 
-	set_cpus_allowed_ptr(current, old);
-	free_cpumask_var(old);
+		work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b51b2c7..1328fe4 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -995,8 +995,8 @@ END(interrupt)
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
 	interrupt do_IRQ
 	/* 0(%rsp): old_rsp-ARGOFFSET */
@@ -1135,8 +1135,8 @@ END(common_interrupt)
  */
 .macro apicinterrupt num sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	pushq_cfi $~(\num)
 .Lcommon_\sym:
 	interrupt \do_sym
@@ -1190,8 +1190,8 @@ apicinterrupt IRQ_WORK_VECTOR \
  */
 .macro zeroentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1208,8 +1208,8 @@ END(\sym)
 
 .macro paranoidzeroentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1227,8 +1227,8 @@ END(\sym)
 #define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
 .macro paranoidzeroentry_ist sym do_sym ist
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1247,8 +1247,8 @@ END(\sym)
 
 .macro errorentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1266,8 +1266,8 @@ END(\sym)
 	/* error code is on the stack already */
 .macro paranoiderrorentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 957a47a..4dac2f6 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -292,8 +292,8 @@ default_entry:
  *	be using the global pages. 
  *
  *	NOTE! If we are on a 486 we may have no cr4 at all!
- *	Specifically, cr4 exists if and only if CPUID exists,
- *	which in turn exists if and only if EFLAGS.ID exists.
+ *	Specifically, cr4 exists if and only if CPUID exists
+ *	and has flags other than the FPU flag set.
  */
 	movl $X86_EFLAGS_ID,%ecx
 	pushl %ecx
@@ -308,6 +308,11 @@ default_entry:
 	testl %ecx,%eax
 	jz 6f			# No ID flag = no CPUID = no CR4
 
+	movl $1,%eax
+	cpuid
+	andl $~1,%edx		# Ignore CPUID.FPU
+	jz 6f			# No flags or only CPUID.FPU = no CR4
+
 	movl pa(mmu_cr4_features),%eax
 	movl %eax,%cr4
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7720ff5..efdec7c 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -8,8 +8,8 @@
  *  Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
  *
  *  Maintainers:
- *  Andreas Herrmann <andreas.herrmann3@amd.com>
- *  Borislav Petkov <borislav.petkov@amd.com>
+ *  Andreas Herrmann <herrmann.der.user@googlemail.com>
+ *  Borislav Petkov <bp@alien8.de>
  *
  *  This driver allows to upgrade microcode on F10h AMD
  *  CPUs and later.
@@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 #define F1XH_MPB_MAX_SIZE 2048
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
 
 	switch (c->x86) {
 	case 0x14:
@@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 	case 0x15:
 		max_size = F15H_MPB_MAX_SIZE;
 		break;
+	case 0x16:
+		max_size = F16H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index b00b33a..974b67e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/rcupdate.h>
+#include <linux/module.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -166,6 +167,35 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK		FLAG_MASK_32
 
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps.  The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+	unsigned long sp = (unsigned long)&regs->sp;
+	struct thread_info *tinfo;
+
+	if (context == (sp & ~(THREAD_SIZE - 1)))
+		return sp;
+
+	tinfo = (struct thread_info *)context;
+	if (tinfo->previous_esp)
+		return tinfo->previous_esp;
+
+	return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
 static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
 	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
@@ -1511,6 +1541,13 @@ void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
+	/*
+	 * We may come here right after calling schedule_user()
+	 * or do_notify_resume(), in which case we can be in RCU
+	 * user mode.
+	 */
+	rcu_user_exit();
+
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33b..f3e2ec8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,6 +68,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -818,6 +820,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+	/* the FPU context is blank, nobody can own it */
+	__cpu_disable_lazy_restore(cpu);
+
 	err = do_boot_cpu(apicid, cpu, tidle);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a10e460..58fc514 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -24,6 +24,9 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	if (!static_cpu_has(X86_FEATURE_XSAVE))
+		return 0;
+
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 39171cb..bba39bf 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -426,8 +426,7 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 			_ASM_EXTABLE(1b, 3b)				\
 			: "=m" ((ctxt)->eflags), "=&r" (_tmp),		\
 			  "+a" (*rax), "+d" (*rdx), "+qm"(_ex)		\
-			: "i" (EFLAGS_MASK), "m" ((ctxt)->src.val),	\
-			  "a" (*rax), "d" (*rdx));			\
+			: "i" (EFLAGS_MASK), "m" ((ctxt)->src.val));	\
 	} while (0)
 
 /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ad6b1dd..f858159 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6549,19 +6549,22 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
 	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
+		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 	} else {
-		exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-			     exec_control);
+		if (cpu_has_secondary_exec_ctrls()) {
+			exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+			vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+				     exec_control);
+		}
 		if (best)
 			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 224a7e7..4f76417 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5781,6 +5781,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0777f04..60f926c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -197,7 +197,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	}
 
 	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
-					|| vmflag == VM_HUGETLB) {
+					|| vmflag & VM_HUGETLB) {
 		local_flush_tlb();
 		goto flush_all;
 	}
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 41bd2a2..b914e20 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -115,6 +115,16 @@ static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
 	reg_read(reg, value);
 }
 
+static void reg_noirq_read(struct sim_dev_reg *reg, u32 *value)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_config_lock, flags);
+	/* force interrupt pin value to 0 */
+	*value = reg->sim_reg.value & 0xfff00ff;
+	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
 static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
 	DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
@@ -144,6 +154,7 @@ static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
 	DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 7, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 	DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
 	DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
@@ -161,8 +172,10 @@ static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
 	DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(16, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 	DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(18, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 };
 
 static void __init init_sim_regs(void)
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 4c61b52..92525cb 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -21,12 +21,25 @@
 #include <asm/i8259.h>
 #include <asm/io.h>
 #include <asm/io_apic.h>
+#include <asm/emergency-restart.h>
 
 static int ce4100_i8042_detect(void)
 {
 	return 0;
 }
 
+/*
+ * The CE4100 platform has an internal 8051 Microcontroller which is
+ * responsible for signaling to the external Power Management Unit the
+ * intention to reset, reboot or power off the system. This 8051 device has
+ * its command register mapped at I/O port 0xcf9 and the value 0x4 is used
+ * to power off the system.
+ */
+static void ce4100_power_off(void)
+{
+	outb(0x4, 0xcf9);
+}
+
 #ifdef CONFIG_SERIAL_8250
 
 static unsigned int mem_serial_in(struct uart_port *p, int offset)
@@ -139,8 +152,19 @@ void __init x86_ce4100_early_setup(void)
 	x86_init.mpparse.find_smp_config = x86_init_noop;
 	x86_init.pci.init = ce4100_pci_init;
 
+	/*
+	 * By default, the reboot method is ACPI which is supported by the
+	 * CE4100 bootloader CEFDK using FADT.ResetReg Address and ResetValue
+	 * the bootloader will however issue a system power off instead of
+	 * reboot. By using BOOT_KBD we ensure proper system reboot as
+	 * expected.
+	 */
+	reboot_type = BOOT_KBD;
+
 #ifdef CONFIG_X86_IO_APIC
 	x86_init.pci.init_irq = sdv_pci_init;
 	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
 #endif
+
+	pm_power_off = ce4100_power_off;
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6226c99..dcf5f2d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1288,6 +1288,25 @@ unsigned long xen_read_cr2_direct(void)
 	return this_cpu_read(xen_vcpu_info.arch.cr2);
 }
 
+void xen_flush_tlb_all(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_all(0);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_ALL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
 static void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
@@ -2518,7 +2537,7 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	err = 0;
 out:
 
-	flush_tlb_all();
+	xen_flush_tlb_all();
 
 	return err;
 }
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index cdcb48a..0d1f36a 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -13,6 +13,8 @@ config XTENSA
 	select GENERIC_CPU_DEVICES
 	select MODULES_USE_ELF_RELA
 	select GENERIC_PCI_IOMAP
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index e6be5b9..700c2e6 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -62,6 +62,10 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 static inline void iounmap(volatile void __iomem *addr)
 {
 }
+
+#define virt_to_bus     virt_to_phys
+#define bus_to_virt     phys_to_virt
+
 #endif /* CONFIG_MMU */
 
 /*
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 5c371d8..2d630e7 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -152,6 +152,7 @@ struct thread_struct {
 
 /* Clearing a0 terminates the backtrace. */
 #define start_thread(regs, new_pc, new_sp) \
+	memset(regs, 0, sizeof(*regs)); \
 	regs->pc = new_pc; \
 	regs->ps = USER_PS_VALUE; \
 	regs->areg[1] = new_sp; \
@@ -168,9 +169,6 @@ struct mm_struct;
 /* Free all resources held by a thread. */
 #define release_thread(thread) do { } while(0)
 
-/* Create a kernel thread without removing it from tasklists */
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
 /* Copy and release all segment info associated with a VM */
 #define copy_segments(p, mm)	do { } while(0)
 #define release_segments(mm)	do { } while(0)
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index c1dacca..124aeee 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -10,7 +10,7 @@
 
 struct pt_regs;
 struct sigaction;
-asmlinkage long xtensa_execve(char*, char**, char**, struct pt_regs*);
+asmlinkage long sys_execve(char*, char**, char**, struct pt_regs*);
 asmlinkage long xtensa_clone(unsigned long, unsigned long, struct pt_regs*);
 asmlinkage long xtensa_ptrace(long, long, long, long);
 asmlinkage long xtensa_sigreturn(struct pt_regs*);
diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h
index 9ef1c31..f4e6eaa 100644
--- a/arch/xtensa/include/asm/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
@@ -1,16 +1,9 @@
-/*
- * include/asm-xtensa/unistd.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- */
+#ifndef _XTENSA_UNISTD_H
+#define _XTENSA_UNISTD_H
 
+#define __ARCH_WANT_SYS_EXECVE
 #include <uapi/asm/unistd.h>
 
-
 /*
  * "Conditional" syscalls
  *
@@ -37,3 +30,5 @@
 #define __IGNORE_mmap				/* use mmap2 */
 #define __IGNORE_vfork				/* use clone */
 #define __IGNORE_fadvise64			/* use fadvise64_64 */
+
+#endif /* _XTENSA_UNISTD_H */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 479abae..9f36d0e 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -1,14 +1,4 @@
-/*
- * include/asm-xtensa/unistd.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2012 Tensilica Inc.
- */
-
-#ifndef _UAPI_XTENSA_UNISTD_H
+#if !defined(_UAPI_XTENSA_UNISTD_H) || defined(__SYSCALL)
 #define _UAPI_XTENSA_UNISTD_H
 
 #ifndef __SYSCALL
@@ -272,7 +262,7 @@ __SYSCALL(115, sys_sendmmsg, 4)
 #define __NR_clone 				116
 __SYSCALL(116, xtensa_clone, 5)
 #define __NR_execve 				117
-__SYSCALL(117, xtensa_execve, 3)
+__SYSCALL(117, sys_execve, 3)
 #define __NR_exit 				118
 __SYSCALL(118, sys_exit, 1)
 #define __NR_exit_group 			119
@@ -759,4 +749,6 @@ __SYSCALL(331, sys_kcmp, 5)
 
 #define SYS_XTENSA_COUNT                  5     /* count */
 
+#undef __SYSCALL
+
 #endif /* _UAPI_XTENSA_UNISTD_H */
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 18453067..90bfc1d 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1833,50 +1833,6 @@ ENTRY(system_call)
 
 
 /*
- * Create a kernel thread
- *
- * int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
- * a2                    a2                 a3             a4
- */
-
-ENTRY(kernel_thread)
-	entry	a1, 16
-
-	mov	a5, a2			# preserve fn over syscall
-	mov	a7, a3			# preserve args over syscall
-
-	movi	a3, _CLONE_VM | _CLONE_UNTRACED
-	movi	a2, __NR_clone
-	or	a6, a4, a3		# arg0: flags
-	mov	a3, a1			# arg1: sp
-	syscall
-
-	beq	a3, a1, 1f		# branch if parent
-	mov	a6, a7			# args
-	callx4	a5			# fn(args)
-
-	movi	a2, __NR_exit
-	syscall				# return value of fn(args) still in a6
-
-1:	retw
-
-/*
- * Do a system call from kernel instead of calling sys_execve, so we end up
- * with proper pt_regs.
- *
- * int kernel_execve(const char *fname, char *const argv[], charg *const envp[])
- * a2                        a2               a3                  a4
- */
-
-ENTRY(kernel_execve)
-	entry	a1, 16
-	mov	a6, a2			# arg0 is in a6
-	movi	a2, __NR_execve
-	syscall
-
-	retw
-
-/*
  * Task switch.
  *
  * struct task*  _switch_to (struct task* prev, struct task* next)
@@ -1958,3 +1914,16 @@ ENTRY(ret_from_fork)
 
 	j	common_exception_return
 
+/*
+ * Kernel thread creation helper
+ * On entry, set up by copy_thread: a2 = thread_fn, a3 = thread_fn arg
+ *           left from _switch_to: a6 = prev
+ */
+ENTRY(ret_from_kernel_thread)
+
+	call4	schedule_tail
+	mov	a6, a3
+	callx4	a2
+	j	common_exception_return
+
+ENDPROC(ret_from_kernel_thread)
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 1908f66..09ae7bf 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -45,6 +45,7 @@
 #include <asm/regs.h>
 
 extern void ret_from_fork(void);
+extern void ret_from_kernel_thread(void);
 
 struct task_struct *current_set[NR_CPUS] = {&init_task, };
 
@@ -158,18 +159,30 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 /*
  * Copy thread.
  *
+ * There are two modes in which this function is called:
+ * 1) Userspace thread creation,
+ *    regs != NULL, usp_thread_fn is userspace stack pointer.
+ *    It is expected to copy parent regs (in case CLONE_VM is not set
+ *    in the clone_flags) and set up passed usp in the childregs.
+ * 2) Kernel thread creation,
+ *    regs == NULL, usp_thread_fn is the function to run in the new thread
+ *    and thread_fn_arg is its parameter.
+ *    childregs are not used for the kernel threads.
+ *
  * The stack layout for the new thread looks like this:
  *
- *	+------------------------+ <- sp in childregs (= tos)
+ *	+------------------------+
  *	|       childregs        |
  *	+------------------------+ <- thread.sp = sp in dummy-frame
  *	|      dummy-frame       |    (saved in dummy-frame spill-area)
  *	+------------------------+
  *
- * We create a dummy frame to return to ret_from_fork:
- *   a0 points to ret_from_fork (simulating a call4)
+ * We create a dummy frame to return to either ret_from_fork or
+ *   ret_from_kernel_thread:
+ *   a0 points to ret_from_fork/ret_from_kernel_thread (simulating a call4)
  *   sp points to itself (thread.sp)
- *   a2, a3 are unused.
+ *   a2, a3 are unused for userspace threads,
+ *   a2 points to thread_fn, a3 holds thread_fn arg for kernel threads.
  *
  * Note: This is a pristine frame, so we don't need any spill region on top of
  *       childregs.
@@ -185,43 +198,63 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  * involved.  Much simpler to just not copy those live frames across.
  */
 
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long unused,
-                struct task_struct * p, struct pt_regs * regs)
+int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
+		unsigned long thread_fn_arg,
+		struct task_struct *p, struct pt_regs *unused)
 {
-	struct pt_regs *childregs;
-	unsigned long tos;
-	int user_mode = user_mode(regs);
+	struct pt_regs *childregs = task_pt_regs(p);
 
 #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS)
 	struct thread_info *ti;
 #endif
 
-	/* Set up new TSS. */
-	tos = (unsigned long)task_stack_page(p) + THREAD_SIZE;
-	if (user_mode)
-		childregs = (struct pt_regs*)(tos - PT_USER_SIZE);
-	else
-		childregs = (struct pt_regs*)tos - 1;
-
-	/* This does not copy all the regs.  In a bout of brilliance or madness,
-	   ARs beyond a0-a15 exist past the end of the struct. */
-	*childregs = *regs;
-
 	/* Create a call4 dummy-frame: a0 = 0, a1 = childregs. */
 	*((int*)childregs - 3) = (unsigned long)childregs;
 	*((int*)childregs - 4) = 0;
 
-	childregs->areg[2] = 0;
-	p->set_child_tid = p->clear_child_tid = NULL;
-	p->thread.ra = MAKE_RA_FOR_CALL((unsigned long)ret_from_fork, 0x1);
 	p->thread.sp = (unsigned long)childregs;
 
-	if (user_mode(regs)) {
+	if (!(p->flags & PF_KTHREAD)) {
+		struct pt_regs *regs = current_pt_regs();
+		unsigned long usp = usp_thread_fn ?
+			usp_thread_fn : regs->areg[1];
 
+		p->thread.ra = MAKE_RA_FOR_CALL(
+				(unsigned long)ret_from_fork, 0x1);
+
+		/* This does not copy all the regs.
+		 * In a bout of brilliance or madness,
+		 * ARs beyond a0-a15 exist past the end of the struct.
+		 */
+		*childregs = *regs;
 		childregs->areg[1] = usp;
+		childregs->areg[2] = 0;
+
+		/* When sharing memory with the parent thread, the child
+		   usually starts on a pristine stack, so we have to reset
+		   windowbase, windowstart and wmask.
+		   (Note that such a new thread is required to always create
+		   an initial call4 frame)
+		   The exception is vfork, where the new thread continues to
+		   run on the parent's stack until it calls execve. This could
+		   be a call8 or call12, which requires a legal stack frame
+		   of the previous caller for the overflow handlers to work.
+		   (Note that it's always legal to overflow live registers).
+		   In this case, ensure to spill at least the stack pointer
+		   of that frame. */
+
 		if (clone_flags & CLONE_VM) {
-			childregs->wmask = 1;	/* can't share live windows */
+			/* check that caller window is live and same stack */
+			int len = childregs->wmask & ~0xf;
+			if (regs->areg[1] == usp && len != 0) {
+				int callinc = (regs->areg[0] >> 30) & 3;
+				int caller_ars = XCHAL_NUM_AREGS - callinc * 4;
+				put_user(regs->areg[caller_ars+1],
+					 (unsigned __user*)(usp - 12));
+			}
+			childregs->wmask = 1;
+			childregs->windowstart = 1;
+			childregs->windowbase = 0;
 		} else {
 			int len = childregs->wmask & ~0xf;
 			memcpy(&childregs->areg[XCHAL_NUM_AREGS - len/4],
@@ -230,11 +263,19 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 // FIXME: we need to set THREADPTR in thread_info...
 		if (clone_flags & CLONE_SETTLS)
 			childregs->areg[2] = childregs->areg[6];
-
 	} else {
-		/* In kernel space, we start a new thread with a new stack. */
-		childregs->wmask = 1;
-		childregs->areg[1] = tos;
+		p->thread.ra = MAKE_RA_FOR_CALL(
+				(unsigned long)ret_from_kernel_thread, 1);
+
+		/* pass parameters to ret_from_kernel_thread:
+		 * a2 = thread_fn, a3 = thread_fn arg
+		 */
+		*((int *)childregs - 1) = thread_fn_arg;
+		*((int *)childregs - 2) = usp_thread_fn;
+
+		/* Childregs are only used when we're going to userspace
+		 * in which case start_thread will set them up.
+		 */
 	}
 
 #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS)
@@ -330,32 +371,5 @@ long xtensa_clone(unsigned long clone_flags, unsigned long newsp,
                   void __user *child_tid, long a5,
                   struct pt_regs *regs)
 {
-        if (!newsp)
-                newsp = regs->areg[1];
         return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
 }
-
-/*
- * xtensa_execve() executes a new program.
- */
-
-asmlinkage
-long xtensa_execve(const char __user *name,
-		   const char __user *const __user *argv,
-                   const char __user *const __user *envp,
-                   long a3, long a4, long a5,
-                   struct pt_regs *regs)
-{
-	long error;
-	struct filename *filename;
-
-	filename = getname(name);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename->name, argv, envp, regs);
-	putname(filename);
-out:
-	return error;
-}
-
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index a5c01e7..5702065 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -32,10 +32,8 @@ typedef void (*syscall_t)(void);
 syscall_t sys_call_table[__NR_syscall_count] /* FIXME __cacheline_aligned */= {
 	[0 ... __NR_syscall_count - 1] = (syscall_t)&sys_ni_syscall,
 
-#undef __SYSCALL
 #define __SYSCALL(nr,symbol,nargs) [ nr ] = (syscall_t)symbol,
-#undef  __KERNEL_SYSCALLS__
-#include <asm/unistd.h>
+#include <uapi/asm/unistd.h>
 };
 
 asmlinkage long xtensa_shmat(int shmid, char __user *shmaddr, int shmflg)
@@ -49,7 +47,8 @@ asmlinkage long xtensa_shmat(int shmid, char __user *shmaddr, int shmflg)
 	return (long)ret;
 }
 
-asmlinkage long xtensa_fadvise64_64(int fd, int advice, unsigned long long offset, unsigned long long len)
+asmlinkage long xtensa_fadvise64_64(int fd, int advice,
+		unsigned long long offset, unsigned long long len)
 {
 	return sys_fadvise64_64(fd, offset, len, advice);
 }
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index a8b9f1f..afe058b 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -43,7 +43,6 @@ EXPORT_SYMBOL(__strncpy_user);
 EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(kernel_thread);
 EXPORT_SYMBOL(empty_zero_page);
 
 /*